| 876 59 40 19 5 11 45 3 42 2 16 16 1 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | // SPDX-License-Identifier: GPL-2.0 #include <net/ip.h> #include <net/udp.h> #include <net/udplite.h> #include <asm/checksum.h> #ifndef _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, __wsum csum) { int carry; __u32 ulen; __u32 uproto; __u32 sum = (__force u32)csum; sum += (__force u32)saddr->s6_addr32[0]; carry = (sum < (__force u32)saddr->s6_addr32[0]); sum += carry; sum += (__force u32)saddr->s6_addr32[1]; carry = (sum < (__force u32)saddr->s6_addr32[1]); sum += carry; sum += (__force u32)saddr->s6_addr32[2]; carry = (sum < (__force u32)saddr->s6_addr32[2]); sum += carry; sum += (__force u32)saddr->s6_addr32[3]; carry = (sum < (__force u32)saddr->s6_addr32[3]); sum += carry; sum += (__force u32)daddr->s6_addr32[0]; carry = (sum < (__force u32)daddr->s6_addr32[0]); sum += carry; sum += (__force u32)daddr->s6_addr32[1]; carry = (sum < (__force u32)daddr->s6_addr32[1]); sum += carry; sum += (__force u32)daddr->s6_addr32[2]; carry = (sum < (__force u32)daddr->s6_addr32[2]); sum += carry; sum += (__force u32)daddr->s6_addr32[3]; carry = (sum < (__force u32)daddr->s6_addr32[3]); sum += carry; ulen = (__force u32)htonl((__u32) len); sum += ulen; carry = (sum < ulen); sum += carry; uproto = (__force u32)htonl(proto); sum += uproto; carry = (sum < uproto); sum += carry; return csum_fold((__force __wsum)sum); } EXPORT_SYMBOL(csum_ipv6_magic); #endif int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) { int err; UDP_SKB_CB(skb)->partial_cov = 0; UDP_SKB_CB(skb)->cscov = skb->len; if (proto == IPPROTO_UDPLITE) { err = udplite_checksum_init(skb, uh); if (err) return err; if (UDP_SKB_CB(skb)->partial_cov) { skb->csum = ip6_compute_pseudo(skb, proto); return 0; } } /* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels) * we accept a checksum of zero here. When we find the socket * for the UDP packet we'll check if that socket allows zero checksum * for IPv6 (set by socket option). * * Note, we are only interested in != 0 or == 0, thus the * force to int. */ err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check, ip6_compute_pseudo); if (err) return err; if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) { /* If SW calculated the value, we know it's bad */ if (skb->csum_complete_sw) return 1; /* HW says the value is bad. Let's validate that. * skb->csum is no longer the full packet checksum, * so don't treat is as such. */ skb_checksum_complete_unset(skb); } return 0; } EXPORT_SYMBOL(udp6_csum_init); /* Function to set UDP checksum for an IPv6 UDP packet. This is intended * for the simple case like when setting the checksum for a UDP tunnel. */ void udp6_set_csum(bool nocheck, struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, int len) { struct udphdr *uh = udp_hdr(skb); if (nocheck) uh->check = 0; else if (skb_is_gso(skb)) uh->check = ~udp_v6_check(len, saddr, daddr, 0); else if (skb->ip_summed == CHECKSUM_PARTIAL) { uh->check = 0; uh->check = udp_v6_check(len, saddr, daddr, lco_csum(skb)); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); uh->check = ~udp_v6_check(len, saddr, daddr, 0); } } EXPORT_SYMBOL(udp6_set_csum); |
| 54 71 78 71 75 5 193 7 217 7 2 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM tcp #if !defined(_TRACE_TCP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TCP_H #include <linux/ipv6.h> #include <linux/tcp.h> #include <linux/tracepoint.h> #include <net/ipv6.h> #include <net/tcp.h> #include <linux/sock_diag.h> #include <net/rstreason.h> /* * tcp event with arguments sk and skb * * Note: this class requires a valid sk pointer; while skb pointer could * be NULL. */ DECLARE_EVENT_CLASS(tcp_event_sk_skb, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( __field(const void *, skbaddr) __field(const void *, skaddr) __field(int, state) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skbaddr = skb; __entry->skaddr = sk; __entry->state = sk->sk_state; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("skbaddr=%p skaddr=%p family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s", __entry->skbaddr, __entry->skaddr, show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->state)) ); DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_skb, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); #undef FN #define FN(reason) TRACE_DEFINE_ENUM(SK_RST_REASON_##reason); DEFINE_RST_REASON(FN, FN) #undef FN #undef FNe #define FN(reason) { SK_RST_REASON_##reason, #reason }, #define FNe(reason) { SK_RST_REASON_##reason, #reason } /* * skb of trace_tcp_send_reset is the skb that caused RST. In case of * active reset, skb should be NULL */ TRACE_EVENT(tcp_send_reset, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const enum sk_rst_reason reason), TP_ARGS(sk, skb, reason), TP_STRUCT__entry( __field(const void *, skbaddr) __field(const void *, skaddr) __field(int, state) __field(enum sk_rst_reason, reason) __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->skbaddr = skb; __entry->skaddr = sk; /* Zero means unknown state. */ __entry->state = sk ? sk->sk_state : 0; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); if (sk && sk_fullsock(sk)) { const struct inet_sock *inet = inet_sk(sk); TP_STORE_ADDR_PORTS(__entry, inet, sk); } else if (skb) { const struct tcphdr *th = (const struct tcphdr *)skb->data; /* * We should reverse the 4-tuple of skb, so later * it can print the right flow direction of rst. */ TP_STORE_ADDR_PORTS_SKB(skb, th, entry->daddr, entry->saddr); } __entry->reason = reason; ), TP_printk("skbaddr=%p skaddr=%p src=%pISpc dest=%pISpc state=%s reason=%s", __entry->skbaddr, __entry->skaddr, __entry->saddr, __entry->daddr, __entry->state ? show_tcp_state_name(__entry->state) : "UNKNOWN", __print_symbolic(__entry->reason, DEFINE_RST_REASON(FN, FNe))) ); #undef FN #undef FNe /* * tcp event with arguments sk * * Note: this class requires a valid sk pointer. */ DECLARE_EVENT_CLASS(tcp_event_sk, TP_PROTO(struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(const void *, skaddr) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) __field(__u64, sock_cookie) ), TP_fast_assign( struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skaddr = sk; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); __entry->sock_cookie = sock_gen_cookie(sk); ), TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c sock_cookie=%llx", show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->sock_cookie) ); DEFINE_EVENT(tcp_event_sk, tcp_receive_reset, TP_PROTO(struct sock *sk), TP_ARGS(sk) ); DEFINE_EVENT(tcp_event_sk, tcp_destroy_sock, TP_PROTO(struct sock *sk), TP_ARGS(sk) ); DEFINE_EVENT(tcp_event_sk, tcp_rcv_space_adjust, TP_PROTO(struct sock *sk), TP_ARGS(sk) ); TRACE_EVENT(tcp_retransmit_synack, TP_PROTO(const struct sock *sk, const struct request_sock *req), TP_ARGS(sk, req), TP_STRUCT__entry( __field(const void *, skaddr) __field(const void *, req) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( struct inet_request_sock *ireq = inet_rsk(req); __be32 *p32; __entry->skaddr = sk; __entry->req = req; __entry->sport = ireq->ir_num; __entry->dport = ntohs(ireq->ir_rmt_port); __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = ireq->ir_loc_addr; p32 = (__be32 *) __entry->daddr; *p32 = ireq->ir_rmt_addr; TP_STORE_ADDRS(__entry, ireq->ir_loc_addr, ireq->ir_rmt_addr, ireq->ir_v6_loc_addr, ireq->ir_v6_rmt_addr); ), TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6) ); #include <trace/events/net_probe_common.h> TRACE_EVENT(tcp_probe, TP_PROTO(struct sock *sk, struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u32, mark) __field(__u16, data_len) __field(__u32, snd_nxt) __field(__u32, snd_una) __field(__u32, snd_cwnd) __field(__u32, ssthresh) __field(__u32, snd_wnd) __field(__u32, srtt) __field(__u32, rcv_wnd) __field(__u64, sock_cookie) __field(const void *, skbaddr) __field(const void *, skaddr) ), TP_fast_assign( const struct tcphdr *th = (const struct tcphdr *)skb->data; const struct inet_sock *inet = inet_sk(sk); const struct tcp_sock *tp = tcp_sk(sk); memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS(__entry, inet, sk); /* For filtering use */ __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->mark = skb->mark; __entry->family = sk->sk_family; __entry->data_len = skb->len - __tcp_hdrlen(th); __entry->snd_nxt = tp->snd_nxt; __entry->snd_una = tp->snd_una; __entry->snd_cwnd = tcp_snd_cwnd(tp); __entry->snd_wnd = tp->snd_wnd; __entry->rcv_wnd = tp->rcv_wnd; __entry->ssthresh = tcp_current_ssthresh(sk); __entry->srtt = tp->srtt_us >> 3; __entry->sock_cookie = sock_gen_cookie(sk); __entry->skbaddr = skb; __entry->skaddr = sk; ), TP_printk("family=%s src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx skbaddr=%p skaddr=%p", show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->mark, __entry->data_len, __entry->snd_nxt, __entry->snd_una, __entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd, __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie, __entry->skbaddr, __entry->skaddr) ); /* * tcp event with only skb */ DECLARE_EVENT_CLASS(tcp_event_skb, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __field(const void *, skbaddr) __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( const struct tcphdr *th = (const struct tcphdr *)skb->data; __entry->skbaddr = skb; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS_SKB(skb, th, __entry->saddr, __entry->daddr); ), TP_printk("skbaddr=%p src=%pISpc dest=%pISpc", __entry->skbaddr, __entry->saddr, __entry->daddr) ); DEFINE_EVENT(tcp_event_skb, tcp_bad_csum, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); TRACE_EVENT(tcp_cong_state_set, TP_PROTO(struct sock *sk, const u8 ca_state), TP_ARGS(sk, ca_state), TP_STRUCT__entry( __field(const void *, skaddr) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) __field(__u8, cong_state) ), TP_fast_assign( struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skaddr = sk; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); __entry->cong_state = ca_state; ), TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->cong_state) ); DECLARE_EVENT_CLASS(tcp_hash_event, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( __field(__u64, net_cookie) __field(const void *, skbaddr) __field(const void *, skaddr) __field(int, state) /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(int, l3index) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(bool, fin) __field(bool, syn) __field(bool, rst) __field(bool, psh) __field(bool, ack) ), TP_fast_assign( const struct tcphdr *th = (const struct tcphdr *)skb->data; __entry->net_cookie = sock_net(sk)->net_cookie; __entry->skbaddr = skb; __entry->skaddr = sk; __entry->state = sk->sk_state; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS_SKB(skb, th, __entry->saddr, __entry->daddr); __entry->l3index = inet_sdif(skb) ? inet_iif(skb) : 0; /* For filtering use */ __entry->sport = ntohs(th->source); __entry->dport = ntohs(th->dest); __entry->family = sk->sk_family; __entry->fin = th->fin; __entry->syn = th->syn; __entry->rst = th->rst; __entry->psh = th->psh; __entry->ack = th->ack; ), TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc L3index=%d [%c%c%c%c%c]", __entry->net_cookie, show_tcp_state_name(__entry->state), show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->l3index, __entry->fin ? 'F' : ' ', __entry->syn ? 'S' : ' ', __entry->rst ? 'R' : ' ', __entry->psh ? 'P' : ' ', __entry->ack ? '.' : ' ') ); DEFINE_EVENT(tcp_hash_event, tcp_hash_bad_header, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); DEFINE_EVENT(tcp_hash_event, tcp_hash_md5_required, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); DEFINE_EVENT(tcp_hash_event, tcp_hash_md5_unexpected, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); DEFINE_EVENT(tcp_hash_event, tcp_hash_md5_mismatch, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); DEFINE_EVENT(tcp_hash_event, tcp_hash_ao_required, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); DECLARE_EVENT_CLASS(tcp_ao_event, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen), TP_STRUCT__entry( __field(__u64, net_cookie) __field(const void *, skbaddr) __field(const void *, skaddr) __field(int, state) /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(int, l3index) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(bool, fin) __field(bool, syn) __field(bool, rst) __field(bool, psh) __field(bool, ack) __field(__u8, keyid) __field(__u8, rnext) __field(__u8, maclen) ), TP_fast_assign( const struct tcphdr *th = (const struct tcphdr *)skb->data; __entry->net_cookie = sock_net(sk)->net_cookie; __entry->skbaddr = skb; __entry->skaddr = sk; __entry->state = sk->sk_state; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS_SKB(skb, th, __entry->saddr, __entry->daddr); __entry->l3index = inet_sdif(skb) ? inet_iif(skb) : 0; /* For filtering use */ __entry->sport = ntohs(th->source); __entry->dport = ntohs(th->dest); __entry->family = sk->sk_family; __entry->fin = th->fin; __entry->syn = th->syn; __entry->rst = th->rst; __entry->psh = th->psh; __entry->ack = th->ack; __entry->keyid = keyid; __entry->rnext = rnext; __entry->maclen = maclen; ), TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc L3index=%d [%c%c%c%c%c] keyid=%u rnext=%u maclen=%u", __entry->net_cookie, show_tcp_state_name(__entry->state), show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->l3index, __entry->fin ? 'F' : ' ', __entry->syn ? 'S' : ' ', __entry->rst ? 'R' : ' ', __entry->psh ? 'P' : ' ', __entry->ack ? '.' : ' ', __entry->keyid, __entry->rnext, __entry->maclen) ); DEFINE_EVENT(tcp_ao_event, tcp_ao_handshake_failure, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen) ); DEFINE_EVENT(tcp_ao_event, tcp_ao_wrong_maclen, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen) ); DEFINE_EVENT(tcp_ao_event, tcp_ao_mismatch, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen) ); DEFINE_EVENT(tcp_ao_event, tcp_ao_key_not_found, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen) ); DEFINE_EVENT(tcp_ao_event, tcp_ao_rnext_request, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen) ); DECLARE_EVENT_CLASS(tcp_ao_event_sk, TP_PROTO(const struct sock *sk, const __u8 keyid, const __u8 rnext), TP_ARGS(sk, keyid, rnext), TP_STRUCT__entry( __field(__u64, net_cookie) __field(const void *, skaddr) __field(int, state) /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u8, keyid) __field(__u8, rnext) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __entry->net_cookie = sock_net(sk)->net_cookie; __entry->skaddr = sk; __entry->state = sk->sk_state; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS(__entry, inet, sk); /* For filtering use */ __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; __entry->keyid = keyid; __entry->rnext = rnext; ), TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc keyid=%u rnext=%u", __entry->net_cookie, show_tcp_state_name(__entry->state), show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->keyid, __entry->rnext) ); DEFINE_EVENT(tcp_ao_event_sk, tcp_ao_synack_no_key, TP_PROTO(const struct sock *sk, const __u8 keyid, const __u8 rnext), TP_ARGS(sk, keyid, rnext) ); DECLARE_EVENT_CLASS(tcp_ao_event_sne, TP_PROTO(const struct sock *sk, __u32 new_sne), TP_ARGS(sk, new_sne), TP_STRUCT__entry( __field(__u64, net_cookie) __field(const void *, skaddr) __field(int, state) /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u32, new_sne) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __entry->net_cookie = sock_net(sk)->net_cookie; __entry->skaddr = sk; __entry->state = sk->sk_state; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS(__entry, inet, sk); /* For filtering use */ __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; __entry->new_sne = new_sne; ), TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc sne=%u", __entry->net_cookie, show_tcp_state_name(__entry->state), show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->new_sne) ); DEFINE_EVENT(tcp_ao_event_sne, tcp_ao_snd_sne_update, TP_PROTO(const struct sock *sk, __u32 new_sne), TP_ARGS(sk, new_sne) ); DEFINE_EVENT(tcp_ao_event_sne, tcp_ao_rcv_sne_update, TP_PROTO(const struct sock *sk, __u32 new_sne), TP_ARGS(sk, new_sne) ); #endif /* _TRACE_TCP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 6320 6324 428 6340 311 313 35 5 35 34 313 309 314 314 314 141 141 3 3 70 70 30 70 70 30 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 | // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /* * local_irq_save() is needed to make the function irq safe: * - The slow path would be ok as protected by an irq-safe spinlock. * - this_cpu_add would be ok as it is irq-safe by definition. * But: * The decision slow path/fast path and the actual update must be atomic, too. * Otherwise a call in process context could check the current values and * decide that the fast path can be used. If now an interrupt occurs before * the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters), * then the this_cpu_add() that is executed after the interrupt has completed * can produce values larger than "batch" or even overflows. */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; unsigned long flags; local_irq_save(flags); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { raw_spin_lock(&fbc->lock); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock(&fbc->lock); } else { this_cpu_add(*fbc->counters, amount); } local_irq_restore(flags); } EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive(). * * We use the cpu mask of (cpu_online_mask | cpu_dying_mask) to capture sums * from CPUs that are in the process of being taken offline. Dying cpus have * been removed from the online mask, but may not have had the hotplug dead * notifier called to fold the percpu count back into the global counter sum. * By including dying CPUs in the iteration mask, we avoid this race condition * so __percpu_counter_sum() just does the right thing when CPUs are being taken * offline. */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters, struct lock_class_key *key) { unsigned long flags __maybe_unused; size_t counter_size; s32 __percpu *counters; u32 i; counter_size = ALIGN(sizeof(*counters), __alignof__(*counters)); counters = __alloc_percpu_gfp(nr_counters * counter_size, __alignof__(*counters), gfp); if (!counters) { fbc[0].counters = NULL; return -ENOMEM; } for (i = 0; i < nr_counters; i++) { raw_spin_lock_init(&fbc[i].lock); lockdep_set_class(&fbc[i].lock, key); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc[i].list); #endif fbc[i].count = amount; fbc[i].counters = (void *)counters + (i * counter_size); debug_percpu_counter_activate(&fbc[i]); } #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); for (i = 0; i < nr_counters; i++) list_add(&fbc[i].list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init_many); void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters) { unsigned long flags __maybe_unused; u32 i; if (WARN_ON_ONCE(!fbc)) return; if (!fbc[0].counters) return; for (i = 0; i < nr_counters; i++) debug_percpu_counter_deactivate(&fbc[i]); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); for (i = 0; i < nr_counters; i++) list_del(&fbc[i].list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc[0].counters); for (i = 0; i < nr_counters; i++) fbc[i].counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy_many); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); /* * Compare counter, and add amount if total is: less than or equal to limit if * amount is positive, or greater than or equal to limit if amount is negative. * Return true if amount is added, or false if total would be beyond the limit. * * Negative limit is allowed, but unusual. * When negative amounts (subs) are given to percpu_counter_limited_add(), * the limit would most naturally be 0 - but other limits are also allowed. * * Overflow beyond S64_MAX is not allowed for: counter, limit and amount * are all assumed to be sane (far from S64_MIN and S64_MAX). */ bool __percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount, s32 batch) { s64 count; s64 unknown; unsigned long flags; bool good = false; if (amount == 0) return true; local_irq_save(flags); unknown = batch * num_online_cpus(); count = __this_cpu_read(*fbc->counters); /* Skip taking the lock when safe */ if (abs(count + amount) <= batch && ((amount > 0 && fbc->count + unknown <= limit) || (amount < 0 && fbc->count - unknown >= limit))) { this_cpu_add(*fbc->counters, amount); local_irq_restore(flags); return true; } raw_spin_lock(&fbc->lock); count = fbc->count + amount; /* Skip percpu_counter_sum() when safe */ if (amount > 0) { if (count - unknown > limit) goto out; if (count + unknown <= limit) good = true; } else { if (count + unknown < limit) goto out; if (count - unknown >= limit) good = true; } if (!good) { s32 *pcount; int cpu; for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { pcount = per_cpu_ptr(fbc->counters, cpu); count += *pcount; } if (amount > 0) { if (count > limit) goto out; } else { if (count < limit) goto out; } good = true; } count = __this_cpu_read(*fbc->counters); fbc->count += count + amount; __this_cpu_sub(*fbc->counters, count); out: raw_spin_unlock(&fbc->lock); local_irq_restore(flags); return good; } static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup); |
| 15 15 24 24 14 13 13 13 13 14 18 16 13 3 3 13 9 4 2 3 42 2 40 9 1 45 4 33 9 9 20 16 3 1 17 2 55 4 50 6 3 3 3 3 13 13 13 13 11 2 16 7 13 13 12 1 2 2 21 14 7 16 16 3 3 15 21 21 23 2 21 21 20 1 3 3 13 13 3 3 4 4 3 3 1 1 25 3 13 3 3 3 3 3 5 5 9 9 11 11 11 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2007-2014 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/init.h> #include <linux/module.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/jhash.h> #include <linux/delay.h> #include <linux/time.h> #include <linux/etherdevice.h> #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/ethtool.h> #include <linux/wait.h> #include <asm/div64.h> #include <linux/highmem.h> #include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv4.h> #include <linux/inetdevice.h> #include <linux/list.h> #include <linux/openvswitch.h> #include <linux/rculist.h> #include <linux/dmi.h> #include <net/genetlink.h> #include <net/gso.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/pkt_cls.h> #include "datapath.h" #include "drop.h" #include "flow.h" #include "flow_table.h" #include "flow_netlink.h" #include "meter.h" #include "openvswitch_trace.h" #include "vport-internal_dev.h" #include "vport-netdev.h" unsigned int ovs_net_id __read_mostly; static struct genl_family dp_packet_genl_family; static struct genl_family dp_flow_genl_family; static struct genl_family dp_datapath_genl_family; static const struct nla_policy flow_policy[]; static const struct genl_multicast_group ovs_dp_flow_multicast_group = { .name = OVS_FLOW_MCGROUP, }; static const struct genl_multicast_group ovs_dp_datapath_multicast_group = { .name = OVS_DATAPATH_MCGROUP, }; static const struct genl_multicast_group ovs_dp_vport_multicast_group = { .name = OVS_VPORT_MCGROUP, }; /* Check if need to build a reply message. * OVS userspace sets the NLM_F_ECHO flag if it needs the reply. */ static bool ovs_must_notify(struct genl_family *family, struct genl_info *info, unsigned int group) { return info->nlhdr->nlmsg_flags & NLM_F_ECHO || genl_has_listeners(family, genl_info_net(info), group); } static void ovs_notify(struct genl_family *family, struct sk_buff *skb, struct genl_info *info) { genl_notify(family, skb, info, 0, GFP_KERNEL); } /** * DOC: Locking: * * All writes e.g. Writes to device state (add/remove datapath, port, set * operations on vports, etc.), Writes to other state (flow table * modifications, set miscellaneous datapath parameters, etc.) are protected * by ovs_lock. * * Reads are protected by RCU. * * There are a few special cases (mostly stats) that have their own * synchronization but they nest under all of above and don't interact with * each other. * * The RTNL lock nests inside ovs_mutex. */ static DEFINE_MUTEX(ovs_mutex); void ovs_lock(void) { mutex_lock(&ovs_mutex); } void ovs_unlock(void) { mutex_unlock(&ovs_mutex); } #ifdef CONFIG_LOCKDEP int lockdep_ovsl_is_held(void) { if (debug_locks) return lockdep_is_held(&ovs_mutex); else return 1; } #endif static struct vport *new_vport(const struct vport_parms *); static int queue_gso_packets(struct datapath *dp, struct sk_buff *, const struct sw_flow_key *, const struct dp_upcall_info *, uint32_t cutlen); static int queue_userspace_packet(struct datapath *dp, struct sk_buff *, const struct sw_flow_key *, const struct dp_upcall_info *, uint32_t cutlen); static void ovs_dp_masks_rebalance(struct work_struct *work); static int ovs_dp_set_upcall_portids(struct datapath *, const struct nlattr *); /* Must be called with rcu_read_lock or ovs_mutex. */ const char *ovs_dp_name(const struct datapath *dp) { struct vport *vport = ovs_vport_ovsl_rcu(dp, OVSP_LOCAL); return ovs_vport_name(vport); } static int get_dpifindex(const struct datapath *dp) { struct vport *local; int ifindex; rcu_read_lock(); local = ovs_vport_rcu(dp, OVSP_LOCAL); if (local) ifindex = local->dev->ifindex; else ifindex = 0; rcu_read_unlock(); return ifindex; } static void destroy_dp_rcu(struct rcu_head *rcu) { struct datapath *dp = container_of(rcu, struct datapath, rcu); ovs_flow_tbl_destroy(&dp->table); free_percpu(dp->stats_percpu); kfree(dp->ports); ovs_meters_exit(dp); kfree(rcu_dereference_raw(dp->upcall_portids)); kfree(dp); } static struct hlist_head *vport_hash_bucket(const struct datapath *dp, u16 port_no) { return &dp->ports[port_no & (DP_VPORT_HASH_BUCKETS - 1)]; } /* Called with ovs_mutex or RCU read lock. */ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) { struct vport *vport; struct hlist_head *head; head = vport_hash_bucket(dp, port_no); hlist_for_each_entry_rcu(vport, head, dp_hash_node, lockdep_ovsl_is_held()) { if (vport->port_no == port_no) return vport; } return NULL; } /* Called with ovs_mutex. */ static struct vport *new_vport(const struct vport_parms *parms) { struct vport *vport; vport = ovs_vport_add(parms); if (!IS_ERR(vport)) { struct datapath *dp = parms->dp; struct hlist_head *head = vport_hash_bucket(dp, vport->port_no); hlist_add_head_rcu(&vport->dp_hash_node, head); } return vport; } static void ovs_vport_update_upcall_stats(struct sk_buff *skb, const struct dp_upcall_info *upcall_info, bool upcall_result) { struct vport *p = OVS_CB(skb)->input_vport; struct vport_upcall_stats_percpu *stats; if (upcall_info->cmd != OVS_PACKET_CMD_MISS && upcall_info->cmd != OVS_PACKET_CMD_ACTION) return; stats = this_cpu_ptr(p->upcall_stats); u64_stats_update_begin(&stats->syncp); if (upcall_result) u64_stats_inc(&stats->n_success); else u64_stats_inc(&stats->n_fail); u64_stats_update_end(&stats->syncp); } void ovs_dp_detach_port(struct vport *p) { ASSERT_OVSL(); /* First drop references to device. */ hlist_del_rcu(&p->dp_hash_node); /* Then destroy it. */ ovs_vport_del(p); } /* Must be called with rcu_read_lock. */ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) { const struct vport *p = OVS_CB(skb)->input_vport; struct datapath *dp = p->dp; struct sw_flow *flow; struct sw_flow_actions *sf_acts; struct dp_stats_percpu *stats; u64 *stats_counter; u32 n_mask_hit; u32 n_cache_hit; int error; stats = this_cpu_ptr(dp->stats_percpu); /* Look up flow. */ flow = ovs_flow_tbl_lookup_stats(&dp->table, key, skb_get_hash(skb), &n_mask_hit, &n_cache_hit); if (unlikely(!flow)) { struct dp_upcall_info upcall; memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_MISS; if (dp->user_features & OVS_DP_F_DISPATCH_UPCALL_PER_CPU) upcall.portid = ovs_dp_get_upcall_portid(dp, smp_processor_id()); else upcall.portid = ovs_vport_find_upcall_portid(p, skb); upcall.mru = OVS_CB(skb)->mru; error = ovs_dp_upcall(dp, skb, key, &upcall, 0); switch (error) { case 0: case -EAGAIN: case -ERESTARTSYS: case -EINTR: consume_skb(skb); break; default: kfree_skb(skb); break; } stats_counter = &stats->n_missed; goto out; } ovs_flow_stats_update(flow, key->tp.flags, skb); sf_acts = rcu_dereference(flow->sf_acts); error = ovs_execute_actions(dp, skb, sf_acts, key); if (unlikely(error)) net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n", ovs_dp_name(dp), error); stats_counter = &stats->n_hit; out: /* Update datapath statistics. */ u64_stats_update_begin(&stats->syncp); (*stats_counter)++; stats->n_mask_hit += n_mask_hit; stats->n_cache_hit += n_cache_hit; u64_stats_update_end(&stats->syncp); } int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_key *key, const struct dp_upcall_info *upcall_info, uint32_t cutlen) { struct dp_stats_percpu *stats; int err; if (trace_ovs_dp_upcall_enabled()) trace_ovs_dp_upcall(dp, skb, key, upcall_info); if (upcall_info->portid == 0) { err = -ENOTCONN; goto err; } if (!skb_is_gso(skb)) err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen); else err = queue_gso_packets(dp, skb, key, upcall_info, cutlen); ovs_vport_update_upcall_stats(skb, upcall_info, !err); if (err) goto err; return 0; err: stats = this_cpu_ptr(dp->stats_percpu); u64_stats_update_begin(&stats->syncp); stats->n_lost++; u64_stats_update_end(&stats->syncp); return err; } static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_key *key, const struct dp_upcall_info *upcall_info, uint32_t cutlen) { unsigned int gso_type = skb_shinfo(skb)->gso_type; struct sw_flow_key later_key; struct sk_buff *segs, *nskb; int err; BUILD_BUG_ON(sizeof(*OVS_CB(skb)) > SKB_GSO_CB_OFFSET); segs = __skb_gso_segment(skb, NETIF_F_SG, false); if (IS_ERR(segs)) return PTR_ERR(segs); if (segs == NULL) return -EINVAL; if (gso_type & SKB_GSO_UDP) { /* The initial flow key extracted by ovs_flow_key_extract() * in this case is for a first fragment, so we need to * properly mark later fragments. */ later_key = *key; later_key.ip.frag = OVS_FRAG_TYPE_LATER; } /* Queue all of the segments. */ skb_list_walk_safe(segs, skb, nskb) { if (gso_type & SKB_GSO_UDP && skb != segs) key = &later_key; err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen); if (err) break; } /* Free all of the segments. */ skb_list_walk_safe(segs, skb, nskb) { if (err) kfree_skb(skb); else consume_skb(skb); } return err; } static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info, unsigned int hdrlen, int actions_attrlen) { size_t size = NLMSG_ALIGN(sizeof(struct ovs_header)) + nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */ + nla_total_size(ovs_key_attr_size()) /* OVS_PACKET_ATTR_KEY */ + nla_total_size(sizeof(unsigned int)) /* OVS_PACKET_ATTR_LEN */ + nla_total_size(sizeof(u64)); /* OVS_PACKET_ATTR_HASH */ /* OVS_PACKET_ATTR_USERDATA */ if (upcall_info->userdata) size += NLA_ALIGN(upcall_info->userdata->nla_len); /* OVS_PACKET_ATTR_EGRESS_TUN_KEY */ if (upcall_info->egress_tun_info) size += nla_total_size(ovs_tun_key_attr_size()); /* OVS_PACKET_ATTR_ACTIONS */ if (upcall_info->actions_len) size += nla_total_size(actions_attrlen); /* OVS_PACKET_ATTR_MRU */ if (upcall_info->mru) size += nla_total_size(sizeof(upcall_info->mru)); return size; } static void pad_packet(struct datapath *dp, struct sk_buff *skb) { if (!(dp->user_features & OVS_DP_F_UNALIGNED)) { size_t plen = NLA_ALIGN(skb->len) - skb->len; if (plen > 0) skb_put_zero(skb, plen); } } static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_key *key, const struct dp_upcall_info *upcall_info, uint32_t cutlen) { struct ovs_header *upcall; struct sk_buff *nskb = NULL; struct sk_buff *user_skb = NULL; /* to be queued to userspace */ struct nlattr *nla; size_t len; unsigned int hlen; int err, dp_ifindex; u64 hash; dp_ifindex = get_dpifindex(dp); if (!dp_ifindex) return -ENODEV; if (skb_vlan_tag_present(skb)) { nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; nskb = __vlan_hwaccel_push_inside(nskb); if (!nskb) return -ENOMEM; skb = nskb; } if (nla_attr_size(skb->len) > USHRT_MAX) { err = -EFBIG; goto out; } /* Complete checksum if needed */ if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_csum_hwoffload_help(skb, 0))) goto out; /* Older versions of OVS user space enforce alignment of the last * Netlink attribute to NLA_ALIGNTO which would require extensive * padding logic. Only perform zerocopy if padding is not required. */ if (dp->user_features & OVS_DP_F_UNALIGNED) hlen = skb_zerocopy_headlen(skb); else hlen = skb->len; len = upcall_msg_size(upcall_info, hlen - cutlen, OVS_CB(skb)->acts_origlen); user_skb = genlmsg_new(len, GFP_ATOMIC); if (!user_skb) { err = -ENOMEM; goto out; } upcall = genlmsg_put(user_skb, 0, 0, &dp_packet_genl_family, 0, upcall_info->cmd); if (!upcall) { err = -EINVAL; goto out; } upcall->dp_ifindex = dp_ifindex; err = ovs_nla_put_key(key, key, OVS_PACKET_ATTR_KEY, false, user_skb); if (err) goto out; if (upcall_info->userdata) __nla_put(user_skb, OVS_PACKET_ATTR_USERDATA, nla_len(upcall_info->userdata), nla_data(upcall_info->userdata)); if (upcall_info->egress_tun_info) { nla = nla_nest_start_noflag(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY); if (!nla) { err = -EMSGSIZE; goto out; } err = ovs_nla_put_tunnel_info(user_skb, upcall_info->egress_tun_info); if (err) goto out; nla_nest_end(user_skb, nla); } if (upcall_info->actions_len) { nla = nla_nest_start_noflag(user_skb, OVS_PACKET_ATTR_ACTIONS); if (!nla) { err = -EMSGSIZE; goto out; } err = ovs_nla_put_actions(upcall_info->actions, upcall_info->actions_len, user_skb); if (!err) nla_nest_end(user_skb, nla); else nla_nest_cancel(user_skb, nla); } /* Add OVS_PACKET_ATTR_MRU */ if (upcall_info->mru && nla_put_u16(user_skb, OVS_PACKET_ATTR_MRU, upcall_info->mru)) { err = -ENOBUFS; goto out; } /* Add OVS_PACKET_ATTR_LEN when packet is truncated */ if (cutlen > 0 && nla_put_u32(user_skb, OVS_PACKET_ATTR_LEN, skb->len)) { err = -ENOBUFS; goto out; } /* Add OVS_PACKET_ATTR_HASH */ hash = skb_get_hash_raw(skb); if (skb->sw_hash) hash |= OVS_PACKET_HASH_SW_BIT; if (skb->l4_hash) hash |= OVS_PACKET_HASH_L4_BIT; if (nla_put(user_skb, OVS_PACKET_ATTR_HASH, sizeof (u64), &hash)) { err = -ENOBUFS; goto out; } /* Only reserve room for attribute header, packet data is added * in skb_zerocopy() */ if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) { err = -ENOBUFS; goto out; } nla->nla_len = nla_attr_size(skb->len - cutlen); err = skb_zerocopy(user_skb, skb, skb->len - cutlen, hlen); if (err) goto out; /* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */ pad_packet(dp, user_skb); ((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len; err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid); user_skb = NULL; out: if (err) skb_tx_error(skb); consume_skb(user_skb); consume_skb(nskb); return err; } static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) { struct ovs_header *ovs_header = genl_info_userhdr(info); struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; struct sw_flow_actions *acts; struct sk_buff *packet; struct sw_flow *flow; struct sw_flow_actions *sf_acts; struct datapath *dp; struct vport *input_vport; u16 mru = 0; u64 hash; int len; int err; bool log = !a[OVS_PACKET_ATTR_PROBE]; err = -EINVAL; if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] || !a[OVS_PACKET_ATTR_ACTIONS]) goto err; len = nla_len(a[OVS_PACKET_ATTR_PACKET]); packet = __dev_alloc_skb(NET_IP_ALIGN + len, GFP_KERNEL); err = -ENOMEM; if (!packet) goto err; skb_reserve(packet, NET_IP_ALIGN); nla_memcpy(__skb_put(packet, len), a[OVS_PACKET_ATTR_PACKET], len); /* Set packet's mru */ if (a[OVS_PACKET_ATTR_MRU]) { mru = nla_get_u16(a[OVS_PACKET_ATTR_MRU]); packet->ignore_df = 1; } OVS_CB(packet)->mru = mru; if (a[OVS_PACKET_ATTR_HASH]) { hash = nla_get_u64(a[OVS_PACKET_ATTR_HASH]); __skb_set_hash(packet, hash & 0xFFFFFFFFULL, !!(hash & OVS_PACKET_HASH_SW_BIT), !!(hash & OVS_PACKET_HASH_L4_BIT)); } /* Build an sw_flow for sending this packet. */ flow = ovs_flow_alloc(); err = PTR_ERR(flow); if (IS_ERR(flow)) goto err_kfree_skb; err = ovs_flow_key_extract_userspace(net, a[OVS_PACKET_ATTR_KEY], packet, &flow->key, log); if (err) goto err_flow_free; err = ovs_nla_copy_actions(net, a[OVS_PACKET_ATTR_ACTIONS], &flow->key, &acts, log); if (err) goto err_flow_free; rcu_assign_pointer(flow->sf_acts, acts); packet->priority = flow->key.phy.priority; packet->mark = flow->key.phy.skb_mark; rcu_read_lock(); dp = get_dp_rcu(net, ovs_header->dp_ifindex); err = -ENODEV; if (!dp) goto err_unlock; input_vport = ovs_vport_rcu(dp, flow->key.phy.in_port); if (!input_vport) input_vport = ovs_vport_rcu(dp, OVSP_LOCAL); if (!input_vport) goto err_unlock; packet->dev = input_vport->dev; OVS_CB(packet)->input_vport = input_vport; sf_acts = rcu_dereference(flow->sf_acts); local_bh_disable(); err = ovs_execute_actions(dp, packet, sf_acts, &flow->key); local_bh_enable(); rcu_read_unlock(); ovs_flow_free(flow, false); return err; err_unlock: rcu_read_unlock(); err_flow_free: ovs_flow_free(flow, false); err_kfree_skb: kfree_skb(packet); err: return err; } static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = { [OVS_PACKET_ATTR_PACKET] = { .len = ETH_HLEN }, [OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED }, [OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED }, [OVS_PACKET_ATTR_PROBE] = { .type = NLA_FLAG }, [OVS_PACKET_ATTR_MRU] = { .type = NLA_U16 }, [OVS_PACKET_ATTR_HASH] = { .type = NLA_U64 }, }; static const struct genl_small_ops dp_packet_genl_ops[] = { { .cmd = OVS_PACKET_CMD_EXECUTE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .doit = ovs_packet_cmd_execute } }; static struct genl_family dp_packet_genl_family __ro_after_init = { .hdrsize = sizeof(struct ovs_header), .name = OVS_PACKET_FAMILY, .version = OVS_PACKET_VERSION, .maxattr = OVS_PACKET_ATTR_MAX, .policy = packet_policy, .netnsok = true, .parallel_ops = true, .small_ops = dp_packet_genl_ops, .n_small_ops = ARRAY_SIZE(dp_packet_genl_ops), .resv_start_op = OVS_PACKET_CMD_EXECUTE + 1, .module = THIS_MODULE, }; static void get_dp_stats(const struct datapath *dp, struct ovs_dp_stats *stats, struct ovs_dp_megaflow_stats *mega_stats) { int i; memset(mega_stats, 0, sizeof(*mega_stats)); stats->n_flows = ovs_flow_tbl_count(&dp->table); mega_stats->n_masks = ovs_flow_tbl_num_masks(&dp->table); stats->n_hit = stats->n_missed = stats->n_lost = 0; for_each_possible_cpu(i) { const struct dp_stats_percpu *percpu_stats; struct dp_stats_percpu local_stats; unsigned int start; percpu_stats = per_cpu_ptr(dp->stats_percpu, i); do { start = u64_stats_fetch_begin(&percpu_stats->syncp); local_stats = *percpu_stats; } while (u64_stats_fetch_retry(&percpu_stats->syncp, start)); stats->n_hit += local_stats.n_hit; stats->n_missed += local_stats.n_missed; stats->n_lost += local_stats.n_lost; mega_stats->n_mask_hit += local_stats.n_mask_hit; mega_stats->n_cache_hit += local_stats.n_cache_hit; } } static bool should_fill_key(const struct sw_flow_id *sfid, uint32_t ufid_flags) { return ovs_identifier_is_ufid(sfid) && !(ufid_flags & OVS_UFID_F_OMIT_KEY); } static bool should_fill_mask(uint32_t ufid_flags) { return !(ufid_flags & OVS_UFID_F_OMIT_MASK); } static bool should_fill_actions(uint32_t ufid_flags) { return !(ufid_flags & OVS_UFID_F_OMIT_ACTIONS); } static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts, const struct sw_flow_id *sfid, uint32_t ufid_flags) { size_t len = NLMSG_ALIGN(sizeof(struct ovs_header)); /* OVS_FLOW_ATTR_UFID, or unmasked flow key as fallback * see ovs_nla_put_identifier() */ if (sfid && ovs_identifier_is_ufid(sfid)) len += nla_total_size(sfid->ufid_len); else len += nla_total_size(ovs_key_attr_size()); /* OVS_FLOW_ATTR_KEY */ if (!sfid || should_fill_key(sfid, ufid_flags)) len += nla_total_size(ovs_key_attr_size()); /* OVS_FLOW_ATTR_MASK */ if (should_fill_mask(ufid_flags)) len += nla_total_size(ovs_key_attr_size()); /* OVS_FLOW_ATTR_ACTIONS */ if (should_fill_actions(ufid_flags)) len += nla_total_size(acts->orig_len); return len + nla_total_size_64bit(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */ + nla_total_size(1) /* OVS_FLOW_ATTR_TCP_FLAGS */ + nla_total_size_64bit(8); /* OVS_FLOW_ATTR_USED */ } /* Called with ovs_mutex or RCU read lock. */ static int ovs_flow_cmd_fill_stats(const struct sw_flow *flow, struct sk_buff *skb) { struct ovs_flow_stats stats; __be16 tcp_flags; unsigned long used; ovs_flow_stats_get(flow, &stats, &used, &tcp_flags); if (used && nla_put_u64_64bit(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used), OVS_FLOW_ATTR_PAD)) return -EMSGSIZE; if (stats.n_packets && nla_put_64bit(skb, OVS_FLOW_ATTR_STATS, sizeof(struct ovs_flow_stats), &stats, OVS_FLOW_ATTR_PAD)) return -EMSGSIZE; if ((u8)ntohs(tcp_flags) && nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, (u8)ntohs(tcp_flags))) return -EMSGSIZE; return 0; } /* Called with ovs_mutex or RCU read lock. */ static int ovs_flow_cmd_fill_actions(const struct sw_flow *flow, struct sk_buff *skb, int skb_orig_len) { struct nlattr *start; int err; /* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if * this is the first flow to be dumped into 'skb'. This is unusual for * Netlink but individual action lists can be longer than * NLMSG_GOODSIZE and thus entirely undumpable if we didn't do this. * The userspace caller can always fetch the actions separately if it * really wants them. (Most userspace callers in fact don't care.) * * This can only fail for dump operations because the skb is always * properly sized for single flows. */ start = nla_nest_start_noflag(skb, OVS_FLOW_ATTR_ACTIONS); if (start) { const struct sw_flow_actions *sf_acts; sf_acts = rcu_dereference_ovsl(flow->sf_acts); err = ovs_nla_put_actions(sf_acts->actions, sf_acts->actions_len, skb); if (!err) nla_nest_end(skb, start); else { if (skb_orig_len) return err; nla_nest_cancel(skb, start); } } else if (skb_orig_len) { return -EMSGSIZE; } return 0; } /* Called with ovs_mutex or RCU read lock. */ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex, struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd, u32 ufid_flags) { const int skb_orig_len = skb->len; struct ovs_header *ovs_header; int err; ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd); if (!ovs_header) return -EMSGSIZE; ovs_header->dp_ifindex = dp_ifindex; err = ovs_nla_put_identifier(flow, skb); if (err) goto error; if (should_fill_key(&flow->id, ufid_flags)) { err = ovs_nla_put_masked_key(flow, skb); if (err) goto error; } if (should_fill_mask(ufid_flags)) { err = ovs_nla_put_mask(flow, skb); if (err) goto error; } err = ovs_flow_cmd_fill_stats(flow, skb); if (err) goto error; if (should_fill_actions(ufid_flags)) { err = ovs_flow_cmd_fill_actions(flow, skb, skb_orig_len); if (err) goto error; } genlmsg_end(skb, ovs_header); return 0; error: genlmsg_cancel(skb, ovs_header); return err; } /* May not be called with RCU read lock. */ static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *acts, const struct sw_flow_id *sfid, struct genl_info *info, bool always, uint32_t ufid_flags) { struct sk_buff *skb; size_t len; if (!always && !ovs_must_notify(&dp_flow_genl_family, info, 0)) return NULL; len = ovs_flow_cmd_msg_size(acts, sfid, ufid_flags); skb = genlmsg_new(len, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); return skb; } /* Called with ovs_mutex. */ static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow, int dp_ifindex, struct genl_info *info, u8 cmd, bool always, u32 ufid_flags) { struct sk_buff *skb; int retval; skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), &flow->id, info, always, ufid_flags); if (IS_ERR_OR_NULL(skb)) return skb; retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb, info->snd_portid, info->snd_seq, 0, cmd, ufid_flags); if (WARN_ON_ONCE(retval < 0)) { kfree_skb(skb); skb = ERR_PTR(retval); } return skb; } static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; struct ovs_header *ovs_header = genl_info_userhdr(info); struct sw_flow *flow = NULL, *new_flow; struct sw_flow_mask mask; struct sk_buff *reply; struct datapath *dp; struct sw_flow_key *key; struct sw_flow_actions *acts; struct sw_flow_match match; u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); int error; bool log = !a[OVS_FLOW_ATTR_PROBE]; /* Must have key and actions. */ error = -EINVAL; if (!a[OVS_FLOW_ATTR_KEY]) { OVS_NLERR(log, "Flow key attr not present in new flow."); goto error; } if (!a[OVS_FLOW_ATTR_ACTIONS]) { OVS_NLERR(log, "Flow actions attr not present in new flow."); goto error; } /* Most of the time we need to allocate a new flow, do it before * locking. */ new_flow = ovs_flow_alloc(); if (IS_ERR(new_flow)) { error = PTR_ERR(new_flow); goto error; } /* Extract key. */ key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) { error = -ENOMEM; goto err_kfree_flow; } ovs_match_init(&match, key, false, &mask); error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) goto err_kfree_key; ovs_flow_mask_key(&new_flow->key, key, true, &mask); /* Extract flow identifier. */ error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], key, log); if (error) goto err_kfree_key; /* Validate actions. */ error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, &acts, log); if (error) { OVS_NLERR(log, "Flow actions may not be safe on all matching packets."); goto err_kfree_key; } reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false, ufid_flags); if (IS_ERR(reply)) { error = PTR_ERR(reply); goto err_kfree_acts; } ovs_lock(); dp = get_dp(net, ovs_header->dp_ifindex); if (unlikely(!dp)) { error = -ENODEV; goto err_unlock_ovs; } /* Check if this is a duplicate flow */ if (ovs_identifier_is_ufid(&new_flow->id)) flow = ovs_flow_tbl_lookup_ufid(&dp->table, &new_flow->id); if (!flow) flow = ovs_flow_tbl_lookup(&dp->table, key); if (likely(!flow)) { rcu_assign_pointer(new_flow->sf_acts, acts); /* Put flow in bucket. */ error = ovs_flow_tbl_insert(&dp->table, new_flow, &mask); if (unlikely(error)) { acts = NULL; goto err_unlock_ovs; } if (unlikely(reply)) { error = ovs_flow_cmd_fill_info(new_flow, ovs_header->dp_ifindex, reply, info->snd_portid, info->snd_seq, 0, OVS_FLOW_CMD_NEW, ufid_flags); BUG_ON(error < 0); } ovs_unlock(); } else { struct sw_flow_actions *old_acts; /* Bail out if we're not allowed to modify an existing flow. * We accept NLM_F_CREATE in place of the intended NLM_F_EXCL * because Generic Netlink treats the latter as a dump * request. We also accept NLM_F_EXCL in case that bug ever * gets fixed. */ if (unlikely(info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL))) { error = -EEXIST; goto err_unlock_ovs; } /* The flow identifier has to be the same for flow updates. * Look for any overlapping flow. */ if (unlikely(!ovs_flow_cmp(flow, &match))) { if (ovs_identifier_is_key(&flow->id)) flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); else /* UFID matches but key is different */ flow = NULL; if (!flow) { error = -ENOENT; goto err_unlock_ovs; } } /* Update actions. */ old_acts = ovsl_dereference(flow->sf_acts); rcu_assign_pointer(flow->sf_acts, acts); if (unlikely(reply)) { error = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, reply, info->snd_portid, info->snd_seq, 0, OVS_FLOW_CMD_NEW, ufid_flags); BUG_ON(error < 0); } ovs_unlock(); ovs_nla_free_flow_actions_rcu(old_acts); ovs_flow_free(new_flow, false); } if (reply) ovs_notify(&dp_flow_genl_family, reply, info); kfree(key); return 0; err_unlock_ovs: ovs_unlock(); kfree_skb(reply); err_kfree_acts: ovs_nla_free_flow_actions(acts); err_kfree_key: kfree(key); err_kfree_flow: ovs_flow_free(new_flow, false); error: return error; } /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */ static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net, const struct nlattr *a, const struct sw_flow_key *key, const struct sw_flow_mask *mask, bool log) { struct sw_flow_actions *acts; struct sw_flow_key masked_key; int error; ovs_flow_mask_key(&masked_key, key, true, mask); error = ovs_nla_copy_actions(net, a, &masked_key, &acts, log); if (error) { OVS_NLERR(log, "Actions may not be safe on all matching packets"); return ERR_PTR(error); } return acts; } /* Factor out match-init and action-copy to avoid * "Wframe-larger-than=1024" warning. Because mask is only * used to get actions, we new a function to save some * stack space. * * If there are not key and action attrs, we return 0 * directly. In the case, the caller will also not use the * match as before. If there is action attr, we try to get * actions and save them to *acts. Before returning from * the function, we reset the match->mask pointer. Because * we should not to return match object with dangling reference * to mask. * */ static noinline_for_stack int ovs_nla_init_match_and_action(struct net *net, struct sw_flow_match *match, struct sw_flow_key *key, struct nlattr **a, struct sw_flow_actions **acts, bool log) { struct sw_flow_mask mask; int error = 0; if (a[OVS_FLOW_ATTR_KEY]) { ovs_match_init(match, key, true, &mask); error = ovs_nla_get_match(net, match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) goto error; } if (a[OVS_FLOW_ATTR_ACTIONS]) { if (!a[OVS_FLOW_ATTR_KEY]) { OVS_NLERR(log, "Flow key attribute not present in set flow."); error = -EINVAL; goto error; } *acts = get_flow_actions(net, a[OVS_FLOW_ATTR_ACTIONS], key, &mask, log); if (IS_ERR(*acts)) { error = PTR_ERR(*acts); goto error; } } /* On success, error is 0. */ error: match->mask = NULL; return error; } static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; struct ovs_header *ovs_header = genl_info_userhdr(info); struct sw_flow_key key; struct sw_flow *flow; struct sk_buff *reply = NULL; struct datapath *dp; struct sw_flow_actions *old_acts = NULL, *acts = NULL; struct sw_flow_match match; struct sw_flow_id sfid; u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); int error = 0; bool log = !a[OVS_FLOW_ATTR_PROBE]; bool ufid_present; ufid_present = ovs_nla_get_ufid(&sfid, a[OVS_FLOW_ATTR_UFID], log); if (!a[OVS_FLOW_ATTR_KEY] && !ufid_present) { OVS_NLERR(log, "Flow set message rejected, Key attribute missing."); return -EINVAL; } error = ovs_nla_init_match_and_action(net, &match, &key, a, &acts, log); if (error) goto error; if (acts) { /* Can allocate before locking if have acts. */ reply = ovs_flow_cmd_alloc_info(acts, &sfid, info, false, ufid_flags); if (IS_ERR(reply)) { error = PTR_ERR(reply); goto err_kfree_acts; } } ovs_lock(); dp = get_dp(net, ovs_header->dp_ifindex); if (unlikely(!dp)) { error = -ENODEV; goto err_unlock_ovs; } /* Check that the flow exists. */ if (ufid_present) flow = ovs_flow_tbl_lookup_ufid(&dp->table, &sfid); else flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); if (unlikely(!flow)) { error = -ENOENT; goto err_unlock_ovs; } /* Update actions, if present. */ if (likely(acts)) { old_acts = ovsl_dereference(flow->sf_acts); rcu_assign_pointer(flow->sf_acts, acts); if (unlikely(reply)) { error = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, reply, info->snd_portid, info->snd_seq, 0, OVS_FLOW_CMD_SET, ufid_flags); BUG_ON(error < 0); } } else { /* Could not alloc without acts before locking. */ reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info, OVS_FLOW_CMD_SET, false, ufid_flags); if (IS_ERR(reply)) { error = PTR_ERR(reply); goto err_unlock_ovs; } } /* Clear stats. */ if (a[OVS_FLOW_ATTR_CLEAR]) ovs_flow_stats_clear(flow); ovs_unlock(); if (reply) ovs_notify(&dp_flow_genl_family, reply, info); if (old_acts) ovs_nla_free_flow_actions_rcu(old_acts); return 0; err_unlock_ovs: ovs_unlock(); kfree_skb(reply); err_kfree_acts: ovs_nla_free_flow_actions(acts); error: return error; } static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct ovs_header *ovs_header = genl_info_userhdr(info); struct net *net = sock_net(skb->sk); struct sw_flow_key key; struct sk_buff *reply; struct sw_flow *flow; struct datapath *dp; struct sw_flow_match match; struct sw_flow_id ufid; u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); int err = 0; bool log = !a[OVS_FLOW_ATTR_PROBE]; bool ufid_present; ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log); if (a[OVS_FLOW_ATTR_KEY]) { ovs_match_init(&match, &key, true, NULL); err = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], NULL, log); } else if (!ufid_present) { OVS_NLERR(log, "Flow get message rejected, Key attribute missing."); err = -EINVAL; } if (err) return err; ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { err = -ENODEV; goto unlock; } if (ufid_present) flow = ovs_flow_tbl_lookup_ufid(&dp->table, &ufid); else flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); if (!flow) { err = -ENOENT; goto unlock; } reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info, OVS_FLOW_CMD_GET, true, ufid_flags); if (IS_ERR(reply)) { err = PTR_ERR(reply); goto unlock; } ovs_unlock(); return genlmsg_reply(reply, info); unlock: ovs_unlock(); return err; } static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct ovs_header *ovs_header = genl_info_userhdr(info); struct net *net = sock_net(skb->sk); struct sw_flow_key key; struct sk_buff *reply; struct sw_flow *flow = NULL; struct datapath *dp; struct sw_flow_match match; struct sw_flow_id ufid; u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); int err; bool log = !a[OVS_FLOW_ATTR_PROBE]; bool ufid_present; ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log); if (a[OVS_FLOW_ATTR_KEY]) { ovs_match_init(&match, &key, true, NULL); err = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], NULL, log); if (unlikely(err)) return err; } ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (unlikely(!dp)) { err = -ENODEV; goto unlock; } if (unlikely(!a[OVS_FLOW_ATTR_KEY] && !ufid_present)) { err = ovs_flow_tbl_flush(&dp->table); goto unlock; } if (ufid_present) flow = ovs_flow_tbl_lookup_ufid(&dp->table, &ufid); else flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); if (unlikely(!flow)) { err = -ENOENT; goto unlock; } ovs_flow_tbl_remove(&dp->table, flow); ovs_unlock(); reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts, &flow->id, info, false, ufid_flags); if (likely(reply)) { if (!IS_ERR(reply)) { rcu_read_lock(); /*To keep RCU checker happy. */ err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, reply, info->snd_portid, info->snd_seq, 0, OVS_FLOW_CMD_DEL, ufid_flags); rcu_read_unlock(); if (WARN_ON_ONCE(err < 0)) { kfree_skb(reply); goto out_free; } ovs_notify(&dp_flow_genl_family, reply, info); } else { netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, PTR_ERR(reply)); } } out_free: ovs_flow_free(flow, true); return 0; unlock: ovs_unlock(); return err; } static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *a[__OVS_FLOW_ATTR_MAX]; struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh)); struct table_instance *ti; struct datapath *dp; u32 ufid_flags; int err; err = genlmsg_parse_deprecated(cb->nlh, &dp_flow_genl_family, a, OVS_FLOW_ATTR_MAX, flow_policy, NULL); if (err) return err; ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); rcu_read_lock(); dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { rcu_read_unlock(); return -ENODEV; } ti = rcu_dereference(dp->table.ti); for (;;) { struct sw_flow *flow; u32 bucket, obj; bucket = cb->args[0]; obj = cb->args[1]; flow = ovs_flow_tbl_dump_next(ti, &bucket, &obj); if (!flow) break; if (ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_FLOW_CMD_GET, ufid_flags) < 0) break; cb->args[0] = bucket; cb->args[1] = obj; } rcu_read_unlock(); return skb->len; } static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = { [OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED }, [OVS_FLOW_ATTR_MASK] = { .type = NLA_NESTED }, [OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED }, [OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG }, [OVS_FLOW_ATTR_PROBE] = { .type = NLA_FLAG }, [OVS_FLOW_ATTR_UFID] = { .type = NLA_UNSPEC, .len = 1 }, [OVS_FLOW_ATTR_UFID_FLAGS] = { .type = NLA_U32 }, }; static const struct genl_small_ops dp_flow_genl_ops[] = { { .cmd = OVS_FLOW_CMD_NEW, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .doit = ovs_flow_cmd_new }, { .cmd = OVS_FLOW_CMD_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .doit = ovs_flow_cmd_del }, { .cmd = OVS_FLOW_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, /* OK for unprivileged users. */ .doit = ovs_flow_cmd_get, .dumpit = ovs_flow_cmd_dump }, { .cmd = OVS_FLOW_CMD_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .doit = ovs_flow_cmd_set, }, }; static struct genl_family dp_flow_genl_family __ro_after_init = { .hdrsize = sizeof(struct ovs_header), .name = OVS_FLOW_FAMILY, .version = OVS_FLOW_VERSION, .maxattr = OVS_FLOW_ATTR_MAX, .policy = flow_policy, .netnsok = true, .parallel_ops = true, .small_ops = dp_flow_genl_ops, .n_small_ops = ARRAY_SIZE(dp_flow_genl_ops), .resv_start_op = OVS_FLOW_CMD_SET + 1, .mcgrps = &ovs_dp_flow_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, }; static size_t ovs_dp_cmd_msg_size(void) { size_t msgsize = NLMSG_ALIGN(sizeof(struct ovs_header)); msgsize += nla_total_size(IFNAMSIZ); msgsize += nla_total_size_64bit(sizeof(struct ovs_dp_stats)); msgsize += nla_total_size_64bit(sizeof(struct ovs_dp_megaflow_stats)); msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */ msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_MASKS_CACHE_SIZE */ msgsize += nla_total_size(sizeof(u32) * nr_cpu_ids); /* OVS_DP_ATTR_PER_CPU_PIDS */ return msgsize; } /* Called with ovs_mutex. */ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) { struct ovs_header *ovs_header; struct ovs_dp_stats dp_stats; struct ovs_dp_megaflow_stats dp_megaflow_stats; struct dp_nlsk_pids *pids = ovsl_dereference(dp->upcall_portids); int err, pids_len; ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family, flags, cmd); if (!ovs_header) goto error; ovs_header->dp_ifindex = get_dpifindex(dp); err = nla_put_string(skb, OVS_DP_ATTR_NAME, ovs_dp_name(dp)); if (err) goto nla_put_failure; get_dp_stats(dp, &dp_stats, &dp_megaflow_stats); if (nla_put_64bit(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), &dp_stats, OVS_DP_ATTR_PAD)) goto nla_put_failure; if (nla_put_64bit(skb, OVS_DP_ATTR_MEGAFLOW_STATS, sizeof(struct ovs_dp_megaflow_stats), &dp_megaflow_stats, OVS_DP_ATTR_PAD)) goto nla_put_failure; if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features)) goto nla_put_failure; if (nla_put_u32(skb, OVS_DP_ATTR_MASKS_CACHE_SIZE, ovs_flow_tbl_masks_cache_size(&dp->table))) goto nla_put_failure; if (dp->user_features & OVS_DP_F_DISPATCH_UPCALL_PER_CPU && pids) { pids_len = min(pids->n_pids, nr_cpu_ids) * sizeof(u32); if (nla_put(skb, OVS_DP_ATTR_PER_CPU_PIDS, pids_len, &pids->pids)) goto nla_put_failure; } genlmsg_end(skb, ovs_header); return 0; nla_put_failure: genlmsg_cancel(skb, ovs_header); error: return -EMSGSIZE; } static struct sk_buff *ovs_dp_cmd_alloc_info(void) { return genlmsg_new(ovs_dp_cmd_msg_size(), GFP_KERNEL); } /* Called with rcu_read_lock or ovs_mutex. */ static struct datapath *lookup_datapath(struct net *net, const struct ovs_header *ovs_header, struct nlattr *a[OVS_DP_ATTR_MAX + 1]) { struct datapath *dp; if (!a[OVS_DP_ATTR_NAME]) dp = get_dp(net, ovs_header->dp_ifindex); else { struct vport *vport; vport = ovs_vport_locate(net, nla_data(a[OVS_DP_ATTR_NAME])); dp = vport && vport->port_no == OVSP_LOCAL ? vport->dp : NULL; } return dp ? dp : ERR_PTR(-ENODEV); } static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *info) { struct datapath *dp; dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), info->attrs); if (IS_ERR(dp)) return; pr_warn("%s: Dropping previously announced user features\n", ovs_dp_name(dp)); dp->user_features = 0; } static int ovs_dp_set_upcall_portids(struct datapath *dp, const struct nlattr *ids) { struct dp_nlsk_pids *old, *dp_nlsk_pids; if (!nla_len(ids) || nla_len(ids) % sizeof(u32)) return -EINVAL; old = ovsl_dereference(dp->upcall_portids); dp_nlsk_pids = kmalloc(sizeof(*dp_nlsk_pids) + nla_len(ids), GFP_KERNEL); if (!dp_nlsk_pids) return -ENOMEM; dp_nlsk_pids->n_pids = nla_len(ids) / sizeof(u32); nla_memcpy(dp_nlsk_pids->pids, ids, nla_len(ids)); rcu_assign_pointer(dp->upcall_portids, dp_nlsk_pids); kfree_rcu(old, rcu); return 0; } u32 ovs_dp_get_upcall_portid(const struct datapath *dp, uint32_t cpu_id) { struct dp_nlsk_pids *dp_nlsk_pids; dp_nlsk_pids = rcu_dereference(dp->upcall_portids); if (dp_nlsk_pids) { if (cpu_id < dp_nlsk_pids->n_pids) { return dp_nlsk_pids->pids[cpu_id]; } else if (dp_nlsk_pids->n_pids > 0 && cpu_id >= dp_nlsk_pids->n_pids) { /* If the number of netlink PIDs is mismatched with * the number of CPUs as seen by the kernel, log this * and send the upcall to an arbitrary socket (0) in * order to not drop packets */ pr_info_ratelimited("cpu_id mismatch with handler threads"); return dp_nlsk_pids->pids[cpu_id % dp_nlsk_pids->n_pids]; } else { return 0; } } else { return 0; } } static int ovs_dp_change(struct datapath *dp, struct nlattr *a[]) { u32 user_features = 0, old_features = dp->user_features; int err; if (a[OVS_DP_ATTR_USER_FEATURES]) { user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]); if (user_features & ~(OVS_DP_F_VPORT_PIDS | OVS_DP_F_UNALIGNED | OVS_DP_F_TC_RECIRC_SHARING | OVS_DP_F_DISPATCH_UPCALL_PER_CPU)) return -EOPNOTSUPP; #if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT) if (user_features & OVS_DP_F_TC_RECIRC_SHARING) return -EOPNOTSUPP; #endif } if (a[OVS_DP_ATTR_MASKS_CACHE_SIZE]) { int err; u32 cache_size; cache_size = nla_get_u32(a[OVS_DP_ATTR_MASKS_CACHE_SIZE]); err = ovs_flow_tbl_masks_cache_resize(&dp->table, cache_size); if (err) return err; } dp->user_features = user_features; if (dp->user_features & OVS_DP_F_DISPATCH_UPCALL_PER_CPU && a[OVS_DP_ATTR_PER_CPU_PIDS]) { /* Upcall Netlink Port IDs have been updated */ err = ovs_dp_set_upcall_portids(dp, a[OVS_DP_ATTR_PER_CPU_PIDS]); if (err) return err; } if ((dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) && !(old_features & OVS_DP_F_TC_RECIRC_SHARING)) tc_skb_ext_tc_enable(); else if (!(dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) && (old_features & OVS_DP_F_TC_RECIRC_SHARING)) tc_skb_ext_tc_disable(); return 0; } static int ovs_dp_stats_init(struct datapath *dp) { dp->stats_percpu = netdev_alloc_pcpu_stats(struct dp_stats_percpu); if (!dp->stats_percpu) return -ENOMEM; return 0; } static int ovs_dp_vport_init(struct datapath *dp) { int i; dp->ports = kmalloc_array(DP_VPORT_HASH_BUCKETS, sizeof(struct hlist_head), GFP_KERNEL); if (!dp->ports) return -ENOMEM; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) INIT_HLIST_HEAD(&dp->ports[i]); return 0; } static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct vport_parms parms; struct sk_buff *reply; struct datapath *dp; struct vport *vport; struct ovs_net *ovs_net; int err; err = -EINVAL; if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID]) goto err; reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; err = -ENOMEM; dp = kzalloc(sizeof(*dp), GFP_KERNEL); if (dp == NULL) goto err_destroy_reply; ovs_dp_set_net(dp, sock_net(skb->sk)); /* Allocate table. */ err = ovs_flow_tbl_init(&dp->table); if (err) goto err_destroy_dp; err = ovs_dp_stats_init(dp); if (err) goto err_destroy_table; err = ovs_dp_vport_init(dp); if (err) goto err_destroy_stats; err = ovs_meters_init(dp); if (err) goto err_destroy_ports; /* Set up our datapath device. */ parms.name = nla_data(a[OVS_DP_ATTR_NAME]); parms.type = OVS_VPORT_TYPE_INTERNAL; parms.options = NULL; parms.dp = dp; parms.port_no = OVSP_LOCAL; parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID]; parms.desired_ifindex = a[OVS_DP_ATTR_IFINDEX] ? nla_get_s32(a[OVS_DP_ATTR_IFINDEX]) : 0; /* So far only local changes have been made, now need the lock. */ ovs_lock(); err = ovs_dp_change(dp, a); if (err) goto err_unlock_and_destroy_meters; vport = new_vport(&parms); if (IS_ERR(vport)) { err = PTR_ERR(vport); if (err == -EBUSY) err = -EEXIST; if (err == -EEXIST) { /* An outdated user space instance that does not understand * the concept of user_features has attempted to create a new * datapath and is likely to reuse it. Drop all user features. */ if (info->genlhdr->version < OVS_DP_VER_FEATURES) ovs_dp_reset_user_features(skb, info); } goto err_destroy_portids; } err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, info->snd_seq, 0, OVS_DP_CMD_NEW); BUG_ON(err < 0); ovs_net = net_generic(ovs_dp_get_net(dp), ovs_net_id); list_add_tail_rcu(&dp->list_node, &ovs_net->dps); ovs_unlock(); ovs_notify(&dp_datapath_genl_family, reply, info); return 0; err_destroy_portids: kfree(rcu_dereference_raw(dp->upcall_portids)); err_unlock_and_destroy_meters: ovs_unlock(); ovs_meters_exit(dp); err_destroy_ports: kfree(dp->ports); err_destroy_stats: free_percpu(dp->stats_percpu); err_destroy_table: ovs_flow_tbl_destroy(&dp->table); err_destroy_dp: kfree(dp); err_destroy_reply: kfree_skb(reply); err: return err; } /* Called with ovs_mutex. */ static void __dp_destroy(struct datapath *dp) { struct flow_table *table = &dp->table; int i; if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) tc_skb_ext_tc_disable(); for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; struct hlist_node *n; hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) if (vport->port_no != OVSP_LOCAL) ovs_dp_detach_port(vport); } list_del_rcu(&dp->list_node); /* OVSP_LOCAL is datapath internal port. We need to make sure that * all ports in datapath are destroyed first before freeing datapath. */ ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL)); /* Flush sw_flow in the tables. RCU cb only releases resource * such as dp, ports and tables. That may avoid some issues * such as RCU usage warning. */ table_instance_flow_flush(table, ovsl_dereference(table->ti), ovsl_dereference(table->ufid_ti)); /* RCU destroy the ports, meters and flow tables. */ call_rcu(&dp->rcu, destroy_dp_rcu); } static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *reply; struct datapath *dp; int err; reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) goto err_unlock_free; err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, info->snd_seq, 0, OVS_DP_CMD_DEL); BUG_ON(err < 0); __dp_destroy(dp); ovs_unlock(); ovs_notify(&dp_datapath_genl_family, reply, info); return 0; err_unlock_free: ovs_unlock(); kfree_skb(reply); return err; } static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *reply; struct datapath *dp; int err; reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) goto err_unlock_free; err = ovs_dp_change(dp, info->attrs); if (err) goto err_unlock_free; err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, info->snd_seq, 0, OVS_DP_CMD_SET); BUG_ON(err < 0); ovs_unlock(); ovs_notify(&dp_datapath_genl_family, reply, info); return 0; err_unlock_free: ovs_unlock(); kfree_skb(reply); return err; } static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *reply; struct datapath *dp; int err; reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), info->attrs); if (IS_ERR(dp)) { err = PTR_ERR(dp); goto err_unlock_free; } err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, info->snd_seq, 0, OVS_DP_CMD_GET); BUG_ON(err < 0); ovs_unlock(); return genlmsg_reply(reply, info); err_unlock_free: ovs_unlock(); kfree_skb(reply); return err; } static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); struct datapath *dp; int skip = cb->args[0]; int i = 0; ovs_lock(); list_for_each_entry(dp, &ovs_net->dps, list_node) { if (i >= skip && ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_DP_CMD_GET) < 0) break; i++; } ovs_unlock(); cb->args[0] = i; return skb->len; } static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { [OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 }, [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, [OVS_DP_ATTR_MASKS_CACHE_SIZE] = NLA_POLICY_RANGE(NLA_U32, 0, PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)), [OVS_DP_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0), }; static const struct genl_small_ops dp_datapath_genl_ops[] = { { .cmd = OVS_DP_CMD_NEW, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .doit = ovs_dp_cmd_new }, { .cmd = OVS_DP_CMD_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .doit = ovs_dp_cmd_del }, { .cmd = OVS_DP_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, /* OK for unprivileged users. */ .doit = ovs_dp_cmd_get, .dumpit = ovs_dp_cmd_dump }, { .cmd = OVS_DP_CMD_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .doit = ovs_dp_cmd_set, }, }; static struct genl_family dp_datapath_genl_family __ro_after_init = { .hdrsize = sizeof(struct ovs_header), .name = OVS_DATAPATH_FAMILY, .version = OVS_DATAPATH_VERSION, .maxattr = OVS_DP_ATTR_MAX, .policy = datapath_policy, .netnsok = true, .parallel_ops = true, .small_ops = dp_datapath_genl_ops, .n_small_ops = ARRAY_SIZE(dp_datapath_genl_ops), .resv_start_op = OVS_DP_CMD_SET + 1, .mcgrps = &ovs_dp_datapath_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, }; /* Called with ovs_mutex or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, struct net *net, u32 portid, u32 seq, u32 flags, u8 cmd, gfp_t gfp) { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; int err; ovs_header = genlmsg_put(skb, portid, seq, &dp_vport_genl_family, flags, cmd); if (!ovs_header) return -EMSGSIZE; ovs_header->dp_ifindex = get_dpifindex(vport->dp); if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) || nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) || nla_put_string(skb, OVS_VPORT_ATTR_NAME, ovs_vport_name(vport)) || nla_put_u32(skb, OVS_VPORT_ATTR_IFINDEX, vport->dev->ifindex)) goto nla_put_failure; if (!net_eq(net, dev_net(vport->dev))) { int id = peernet2id_alloc(net, dev_net(vport->dev), gfp); if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id)) goto nla_put_failure; } ovs_vport_get_stats(vport, &vport_stats); if (nla_put_64bit(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats), &vport_stats, OVS_VPORT_ATTR_PAD)) goto nla_put_failure; if (ovs_vport_get_upcall_stats(vport, skb)) goto nla_put_failure; if (ovs_vport_get_upcall_portids(vport, skb)) goto nla_put_failure; err = ovs_vport_get_options(vport, skb); if (err == -EMSGSIZE) goto error; genlmsg_end(skb, ovs_header); return 0; nla_put_failure: err = -EMSGSIZE; error: genlmsg_cancel(skb, ovs_header); return err; } static struct sk_buff *ovs_vport_cmd_alloc_info(void) { return nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); } /* Called with ovs_mutex, only via ovs_dp_notify_wq(). */ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, u32 portid, u32 seq, u8 cmd) { struct sk_buff *skb; int retval; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd, GFP_KERNEL); BUG_ON(retval < 0); return skb; } /* Called with ovs_mutex or RCU read lock. */ static struct vport *lookup_vport(struct net *net, const struct ovs_header *ovs_header, struct nlattr *a[OVS_VPORT_ATTR_MAX + 1]) { struct datapath *dp; struct vport *vport; if (a[OVS_VPORT_ATTR_IFINDEX]) return ERR_PTR(-EOPNOTSUPP); if (a[OVS_VPORT_ATTR_NAME]) { vport = ovs_vport_locate(net, nla_data(a[OVS_VPORT_ATTR_NAME])); if (!vport) return ERR_PTR(-ENODEV); if (ovs_header->dp_ifindex && ovs_header->dp_ifindex != get_dpifindex(vport->dp)) return ERR_PTR(-ENODEV); return vport; } else if (a[OVS_VPORT_ATTR_PORT_NO]) { u32 port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]); if (port_no >= DP_MAX_PORTS) return ERR_PTR(-EFBIG); dp = get_dp(net, ovs_header->dp_ifindex); if (!dp) return ERR_PTR(-ENODEV); vport = ovs_vport_ovsl_rcu(dp, port_no); if (!vport) return ERR_PTR(-ENODEV); return vport; } else return ERR_PTR(-EINVAL); } static unsigned int ovs_get_max_headroom(struct datapath *dp) { unsigned int dev_headroom, max_headroom = 0; struct net_device *dev; struct vport *vport; int i; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, lockdep_ovsl_is_held()) { dev = vport->dev; dev_headroom = netdev_get_fwd_headroom(dev); if (dev_headroom > max_headroom) max_headroom = dev_headroom; } } return max_headroom; } /* Called with ovs_mutex */ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom) { struct vport *vport; int i; dp->max_headroom = new_headroom; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, lockdep_ovsl_is_held()) netdev_set_rx_headroom(vport->dev, new_headroom); } } static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct ovs_header *ovs_header = genl_info_userhdr(info); struct vport_parms parms; struct sk_buff *reply; struct vport *vport; struct datapath *dp; unsigned int new_headroom; u32 port_no; int err; if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] || !a[OVS_VPORT_ATTR_UPCALL_PID]) return -EINVAL; parms.type = nla_get_u32(a[OVS_VPORT_ATTR_TYPE]); if (a[OVS_VPORT_ATTR_IFINDEX] && parms.type != OVS_VPORT_TYPE_INTERNAL) return -EOPNOTSUPP; port_no = a[OVS_VPORT_ATTR_PORT_NO] ? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0; if (port_no >= DP_MAX_PORTS) return -EFBIG; reply = ovs_vport_cmd_alloc_info(); if (!reply) return -ENOMEM; ovs_lock(); restart: dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); err = -ENODEV; if (!dp) goto exit_unlock_free; if (port_no) { vport = ovs_vport_ovsl(dp, port_no); err = -EBUSY; if (vport) goto exit_unlock_free; } else { for (port_no = 1; ; port_no++) { if (port_no >= DP_MAX_PORTS) { err = -EFBIG; goto exit_unlock_free; } vport = ovs_vport_ovsl(dp, port_no); if (!vport) break; } } parms.name = nla_data(a[OVS_VPORT_ATTR_NAME]); parms.options = a[OVS_VPORT_ATTR_OPTIONS]; parms.dp = dp; parms.port_no = port_no; parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID]; parms.desired_ifindex = a[OVS_VPORT_ATTR_IFINDEX] ? nla_get_s32(a[OVS_VPORT_ATTR_IFINDEX]) : 0; vport = new_vport(&parms); err = PTR_ERR(vport); if (IS_ERR(vport)) { if (err == -EAGAIN) goto restart; goto exit_unlock_free; } err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, OVS_VPORT_CMD_NEW, GFP_KERNEL); new_headroom = netdev_get_fwd_headroom(vport->dev); if (new_headroom > dp->max_headroom) ovs_update_headroom(dp, new_headroom); else netdev_set_rx_headroom(vport->dev, dp->max_headroom); BUG_ON(err < 0); ovs_unlock(); ovs_notify(&dp_vport_genl_family, reply, info); return 0; exit_unlock_free: ovs_unlock(); kfree_skb(reply); return err; } static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct sk_buff *reply; struct vport *vport; int err; reply = ovs_vport_cmd_alloc_info(); if (!reply) return -ENOMEM; ovs_lock(); vport = lookup_vport(sock_net(skb->sk), genl_info_userhdr(info), a); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock_free; if (a[OVS_VPORT_ATTR_TYPE] && nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type) { err = -EINVAL; goto exit_unlock_free; } if (a[OVS_VPORT_ATTR_OPTIONS]) { err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]); if (err) goto exit_unlock_free; } if (a[OVS_VPORT_ATTR_UPCALL_PID]) { struct nlattr *ids = a[OVS_VPORT_ATTR_UPCALL_PID]; err = ovs_vport_set_upcall_portids(vport, ids); if (err) goto exit_unlock_free; } err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, OVS_VPORT_CMD_SET, GFP_KERNEL); BUG_ON(err < 0); ovs_unlock(); ovs_notify(&dp_vport_genl_family, reply, info); return 0; exit_unlock_free: ovs_unlock(); kfree_skb(reply); return err; } static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) { bool update_headroom = false; struct nlattr **a = info->attrs; struct sk_buff *reply; struct datapath *dp; struct vport *vport; unsigned int new_headroom; int err; reply = ovs_vport_cmd_alloc_info(); if (!reply) return -ENOMEM; ovs_lock(); vport = lookup_vport(sock_net(skb->sk), genl_info_userhdr(info), a); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock_free; if (vport->port_no == OVSP_LOCAL) { err = -EINVAL; goto exit_unlock_free; } err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, OVS_VPORT_CMD_DEL, GFP_KERNEL); BUG_ON(err < 0); /* the vport deletion may trigger dp headroom update */ dp = vport->dp; if (netdev_get_fwd_headroom(vport->dev) == dp->max_headroom) update_headroom = true; netdev_reset_rx_headroom(vport->dev); ovs_dp_detach_port(vport); if (update_headroom) { new_headroom = ovs_get_max_headroom(dp); if (new_headroom < dp->max_headroom) ovs_update_headroom(dp, new_headroom); } ovs_unlock(); ovs_notify(&dp_vport_genl_family, reply, info); return 0; exit_unlock_free: ovs_unlock(); kfree_skb(reply); return err; } static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct ovs_header *ovs_header = genl_info_userhdr(info); struct sk_buff *reply; struct vport *vport; int err; reply = ovs_vport_cmd_alloc_info(); if (!reply) return -ENOMEM; rcu_read_lock(); vport = lookup_vport(sock_net(skb->sk), ovs_header, a); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock_free; err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, OVS_VPORT_CMD_GET, GFP_ATOMIC); BUG_ON(err < 0); rcu_read_unlock(); return genlmsg_reply(reply, info); exit_unlock_free: rcu_read_unlock(); kfree_skb(reply); return err; } static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh)); struct datapath *dp; int bucket = cb->args[0], skip = cb->args[1]; int i, j = 0; rcu_read_lock(); dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { rcu_read_unlock(); return -ENODEV; } for (i = bucket; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; j = 0; hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { if (j >= skip && ovs_vport_cmd_fill_info(vport, skb, sock_net(skb->sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_VPORT_CMD_GET, GFP_ATOMIC) < 0) goto out; j++; } skip = 0; } out: rcu_read_unlock(); cb->args[0] = i; cb->args[1] = j; return skb->len; } static void ovs_dp_masks_rebalance(struct work_struct *work) { struct ovs_net *ovs_net = container_of(work, struct ovs_net, masks_rebalance.work); struct datapath *dp; ovs_lock(); list_for_each_entry(dp, &ovs_net->dps, list_node) ovs_flow_masks_rebalance(&dp->table); ovs_unlock(); schedule_delayed_work(&ovs_net->masks_rebalance, msecs_to_jiffies(DP_MASKS_REBALANCE_INTERVAL)); } static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) }, [OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC }, [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, [OVS_VPORT_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0), [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, [OVS_VPORT_ATTR_UPCALL_STATS] = { .type = NLA_NESTED }, }; static const struct genl_small_ops dp_vport_genl_ops[] = { { .cmd = OVS_VPORT_CMD_NEW, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .doit = ovs_vport_cmd_new }, { .cmd = OVS_VPORT_CMD_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .doit = ovs_vport_cmd_del }, { .cmd = OVS_VPORT_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, /* OK for unprivileged users. */ .doit = ovs_vport_cmd_get, .dumpit = ovs_vport_cmd_dump }, { .cmd = OVS_VPORT_CMD_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .doit = ovs_vport_cmd_set, }, }; struct genl_family dp_vport_genl_family __ro_after_init = { .hdrsize = sizeof(struct ovs_header), .name = OVS_VPORT_FAMILY, .version = OVS_VPORT_VERSION, .maxattr = OVS_VPORT_ATTR_MAX, .policy = vport_policy, .netnsok = true, .parallel_ops = true, .small_ops = dp_vport_genl_ops, .n_small_ops = ARRAY_SIZE(dp_vport_genl_ops), .resv_start_op = OVS_VPORT_CMD_SET + 1, .mcgrps = &ovs_dp_vport_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, }; static struct genl_family * const dp_genl_families[] = { &dp_datapath_genl_family, &dp_vport_genl_family, &dp_flow_genl_family, &dp_packet_genl_family, &dp_meter_genl_family, #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) &dp_ct_limit_genl_family, #endif }; static void dp_unregister_genl(int n_families) { int i; for (i = 0; i < n_families; i++) genl_unregister_family(dp_genl_families[i]); } static int __init dp_register_genl(void) { int err; int i; for (i = 0; i < ARRAY_SIZE(dp_genl_families); i++) { err = genl_register_family(dp_genl_families[i]); if (err) goto error; } return 0; error: dp_unregister_genl(i); return err; } static int __net_init ovs_init_net(struct net *net) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); int err; INIT_LIST_HEAD(&ovs_net->dps); INIT_WORK(&ovs_net->dp_notify_work, ovs_dp_notify_wq); INIT_DELAYED_WORK(&ovs_net->masks_rebalance, ovs_dp_masks_rebalance); err = ovs_ct_init(net); if (err) return err; schedule_delayed_work(&ovs_net->masks_rebalance, msecs_to_jiffies(DP_MASKS_REBALANCE_INTERVAL)); return 0; } static void __net_exit list_vports_from_net(struct net *net, struct net *dnet, struct list_head *head) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); struct datapath *dp; list_for_each_entry(dp, &ovs_net->dps, list_node) { int i; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; hlist_for_each_entry(vport, &dp->ports[i], dp_hash_node) { if (vport->ops->type != OVS_VPORT_TYPE_INTERNAL) continue; if (dev_net(vport->dev) == dnet) list_add(&vport->detach_list, head); } } } } static void __net_exit ovs_exit_net(struct net *dnet) { struct datapath *dp, *dp_next; struct ovs_net *ovs_net = net_generic(dnet, ovs_net_id); struct vport *vport, *vport_next; struct net *net; LIST_HEAD(head); ovs_lock(); ovs_ct_exit(dnet); list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node) __dp_destroy(dp); down_read(&net_rwsem); for_each_net(net) list_vports_from_net(net, dnet, &head); up_read(&net_rwsem); /* Detach all vports from given namespace. */ list_for_each_entry_safe(vport, vport_next, &head, detach_list) { list_del(&vport->detach_list); ovs_dp_detach_port(vport); } ovs_unlock(); cancel_delayed_work_sync(&ovs_net->masks_rebalance); cancel_work_sync(&ovs_net->dp_notify_work); } static struct pernet_operations ovs_net_ops = { .init = ovs_init_net, .exit = ovs_exit_net, .id = &ovs_net_id, .size = sizeof(struct ovs_net), }; static const char * const ovs_drop_reasons[] = { #define S(x) (#x), OVS_DROP_REASONS(S) #undef S }; static struct drop_reason_list drop_reason_list_ovs = { .reasons = ovs_drop_reasons, .n_reasons = ARRAY_SIZE(ovs_drop_reasons), }; static int __init dp_init(void) { int err; BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_field(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath\n"); err = action_fifos_init(); if (err) goto error; err = ovs_internal_dev_rtnl_link_register(); if (err) goto error_action_fifos_exit; err = ovs_flow_init(); if (err) goto error_unreg_rtnl_link; err = ovs_vport_init(); if (err) goto error_flow_exit; err = register_pernet_device(&ovs_net_ops); if (err) goto error_vport_exit; err = register_netdevice_notifier(&ovs_dp_device_notifier); if (err) goto error_netns_exit; err = ovs_netdev_init(); if (err) goto error_unreg_notifier; err = dp_register_genl(); if (err < 0) goto error_unreg_netdev; drop_reasons_register_subsys(SKB_DROP_REASON_SUBSYS_OPENVSWITCH, &drop_reason_list_ovs); return 0; error_unreg_netdev: ovs_netdev_exit(); error_unreg_notifier: unregister_netdevice_notifier(&ovs_dp_device_notifier); error_netns_exit: unregister_pernet_device(&ovs_net_ops); error_vport_exit: ovs_vport_exit(); error_flow_exit: ovs_flow_exit(); error_unreg_rtnl_link: ovs_internal_dev_rtnl_link_unregister(); error_action_fifos_exit: action_fifos_exit(); error: return err; } static void dp_cleanup(void) { dp_unregister_genl(ARRAY_SIZE(dp_genl_families)); ovs_netdev_exit(); unregister_netdevice_notifier(&ovs_dp_device_notifier); unregister_pernet_device(&ovs_net_ops); drop_reasons_unregister_subsys(SKB_DROP_REASON_SUBSYS_OPENVSWITCH); rcu_barrier(); ovs_vport_exit(); ovs_flow_exit(); ovs_internal_dev_rtnl_link_unregister(); action_fifos_exit(); } module_init(dp_init); module_exit(dp_cleanup); MODULE_DESCRIPTION("Open vSwitch switching datapath"); MODULE_LICENSE("GPL"); MODULE_ALIAS_GENL_FAMILY(OVS_DATAPATH_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_VPORT_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_FLOW_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_PACKET_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_METER_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_CT_LIMIT_FAMILY); |
| 24 24 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 12472 12473 12474 12475 12476 12477 12478 12479 12480 12481 12482 12483 12484 12485 12486 12487 12488 12489 12490 12491 12492 12493 12494 12495 12496 12497 12498 12499 12500 12501 12502 12503 12504 12505 12506 12507 12508 12509 12510 12511 12512 12513 12514 12515 12516 12517 12518 12519 12520 12521 12522 12523 12524 12525 12526 12527 12528 12529 12530 12531 12532 12533 12534 12535 12536 12537 12538 12539 12540 12541 12542 12543 12544 12545 12546 12547 12548 12549 12550 12551 12552 12553 12554 12555 12556 12557 12558 12559 12560 12561 12562 12563 12564 12565 12566 12567 12568 12569 12570 12571 12572 12573 12574 12575 12576 12577 12578 12579 12580 12581 12582 12583 12584 12585 12586 12587 12588 12589 12590 12591 12592 12593 12594 12595 12596 12597 12598 12599 12600 12601 12602 12603 12604 12605 12606 12607 12608 12609 12610 12611 12612 12613 12614 12615 12616 12617 12618 12619 12620 12621 12622 12623 12624 12625 12626 12627 12628 12629 12630 12631 12632 12633 12634 12635 12636 12637 12638 12639 12640 12641 12642 12643 12644 12645 12646 12647 12648 12649 12650 12651 12652 12653 12654 12655 12656 12657 12658 12659 12660 12661 12662 12663 12664 12665 12666 12667 12668 12669 12670 12671 12672 12673 12674 12675 12676 12677 12678 12679 12680 12681 12682 12683 12684 12685 12686 12687 12688 12689 12690 12691 12692 12693 12694 12695 12696 12697 12698 12699 12700 12701 12702 12703 12704 12705 12706 12707 12708 12709 12710 12711 12712 12713 12714 12715 12716 12717 12718 12719 12720 12721 12722 12723 12724 12725 12726 12727 12728 12729 12730 12731 12732 12733 12734 12735 12736 12737 12738 12739 12740 12741 12742 12743 12744 12745 12746 12747 12748 12749 12750 12751 12752 12753 12754 12755 12756 12757 12758 12759 12760 12761 12762 12763 12764 12765 12766 12767 12768 12769 12770 12771 12772 12773 12774 12775 12776 12777 12778 12779 12780 12781 12782 12783 12784 12785 12786 12787 12788 12789 12790 12791 12792 12793 12794 12795 12796 12797 12798 12799 12800 12801 12802 12803 12804 12805 12806 12807 12808 12809 12810 12811 12812 12813 12814 12815 12816 12817 12818 12819 12820 12821 12822 12823 12824 12825 12826 12827 12828 12829 12830 12831 12832 12833 12834 12835 12836 12837 12838 12839 12840 12841 12842 12843 12844 12845 12846 12847 12848 12849 12850 12851 12852 12853 12854 12855 12856 12857 12858 12859 12860 12861 12862 12863 12864 12865 12866 12867 12868 12869 12870 12871 12872 12873 12874 12875 12876 12877 12878 12879 12880 12881 12882 12883 12884 12885 12886 12887 12888 12889 12890 12891 12892 12893 12894 12895 12896 12897 12898 12899 12900 12901 12902 12903 12904 12905 12906 12907 12908 12909 12910 12911 12912 12913 12914 12915 12916 12917 12918 12919 12920 12921 12922 12923 12924 12925 12926 12927 12928 12929 12930 12931 12932 12933 12934 12935 12936 12937 12938 12939 12940 12941 12942 12943 12944 12945 12946 12947 12948 12949 12950 12951 12952 12953 12954 12955 12956 12957 12958 12959 12960 12961 12962 12963 12964 12965 12966 12967 12968 12969 12970 12971 12972 12973 12974 12975 12976 12977 12978 12979 12980 12981 12982 12983 12984 12985 12986 12987 12988 12989 12990 12991 12992 12993 12994 12995 12996 12997 12998 12999 13000 13001 13002 13003 13004 13005 13006 13007 13008 13009 13010 13011 13012 13013 13014 13015 13016 13017 13018 13019 13020 13021 13022 13023 13024 13025 13026 13027 13028 13029 13030 13031 13032 13033 13034 13035 13036 13037 13038 13039 13040 13041 13042 13043 13044 13045 13046 13047 13048 13049 13050 13051 13052 13053 13054 13055 13056 13057 13058 13059 13060 13061 13062 13063 13064 13065 13066 13067 13068 13069 13070 13071 13072 13073 13074 13075 13076 13077 13078 13079 13080 13081 13082 13083 13084 13085 13086 13087 13088 13089 13090 13091 13092 13093 13094 13095 13096 13097 13098 13099 13100 13101 13102 13103 13104 13105 13106 13107 13108 13109 13110 13111 13112 13113 13114 13115 13116 13117 13118 13119 13120 13121 13122 13123 13124 13125 13126 13127 13128 13129 13130 13131 13132 13133 13134 13135 13136 13137 13138 13139 13140 13141 13142 13143 13144 13145 13146 13147 13148 13149 13150 13151 13152 13153 13154 13155 13156 13157 13158 13159 13160 13161 13162 13163 13164 13165 13166 13167 13168 13169 13170 13171 13172 13173 13174 13175 13176 13177 13178 13179 13180 13181 13182 13183 13184 13185 13186 13187 13188 13189 13190 13191 13192 13193 13194 13195 13196 13197 13198 13199 13200 13201 13202 13203 13204 13205 13206 13207 13208 13209 13210 13211 13212 13213 13214 13215 13216 13217 13218 13219 13220 13221 13222 13223 13224 13225 13226 13227 13228 13229 13230 13231 13232 13233 13234 13235 13236 13237 13238 13239 13240 13241 13242 13243 13244 13245 13246 13247 13248 13249 13250 13251 13252 13253 13254 13255 13256 13257 13258 13259 13260 13261 13262 13263 13264 13265 13266 13267 13268 13269 13270 13271 13272 13273 13274 13275 13276 13277 13278 13279 13280 13281 13282 13283 13284 13285 13286 13287 13288 13289 13290 13291 13292 13293 13294 13295 13296 13297 13298 13299 13300 13301 13302 13303 13304 13305 13306 13307 13308 13309 13310 13311 13312 13313 13314 13315 13316 13317 13318 13319 13320 13321 13322 13323 13324 13325 13326 13327 13328 13329 13330 13331 13332 13333 13334 13335 13336 13337 13338 13339 13340 13341 13342 13343 13344 13345 13346 13347 13348 13349 13350 13351 13352 13353 13354 13355 13356 13357 13358 13359 13360 13361 13362 13363 13364 13365 13366 13367 13368 13369 13370 13371 13372 13373 13374 13375 13376 13377 13378 13379 13380 13381 13382 13383 13384 13385 13386 13387 13388 13389 13390 13391 13392 13393 13394 13395 13396 13397 13398 13399 13400 13401 13402 13403 13404 13405 13406 13407 13408 13409 13410 13411 13412 13413 13414 13415 13416 13417 13418 13419 13420 13421 13422 13423 13424 13425 13426 13427 13428 13429 13430 13431 13432 13433 13434 13435 13436 13437 13438 13439 13440 13441 13442 13443 13444 13445 13446 13447 13448 13449 13450 13451 13452 13453 13454 13455 13456 13457 13458 13459 13460 13461 13462 13463 13464 13465 13466 13467 13468 13469 13470 13471 13472 13473 13474 13475 13476 13477 13478 13479 13480 13481 13482 13483 13484 13485 13486 13487 13488 13489 13490 13491 13492 13493 13494 13495 13496 13497 13498 13499 13500 13501 13502 13503 13504 13505 13506 13507 13508 13509 13510 13511 13512 13513 13514 13515 13516 13517 13518 13519 13520 13521 13522 13523 13524 13525 13526 13527 13528 13529 13530 13531 13532 13533 13534 13535 13536 13537 13538 13539 13540 13541 13542 13543 13544 13545 13546 13547 13548 13549 13550 13551 13552 13553 13554 13555 13556 13557 13558 13559 13560 13561 13562 13563 13564 13565 13566 13567 13568 13569 13570 13571 13572 13573 13574 13575 13576 13577 13578 13579 13580 13581 13582 13583 13584 13585 13586 13587 13588 13589 13590 13591 13592 13593 13594 13595 13596 13597 13598 13599 13600 13601 13602 13603 13604 13605 13606 13607 13608 13609 13610 13611 13612 13613 13614 13615 13616 13617 13618 13619 13620 13621 13622 13623 13624 13625 13626 13627 13628 13629 13630 13631 13632 13633 13634 13635 13636 13637 13638 13639 13640 13641 13642 13643 13644 13645 13646 13647 13648 13649 13650 13651 13652 13653 13654 13655 13656 13657 13658 13659 13660 13661 13662 13663 13664 13665 13666 13667 13668 13669 13670 13671 13672 13673 13674 13675 13676 13677 13678 13679 13680 13681 13682 13683 13684 13685 13686 13687 13688 13689 13690 13691 13692 13693 13694 13695 13696 13697 13698 13699 13700 13701 13702 13703 13704 13705 13706 13707 13708 13709 13710 13711 13712 13713 13714 13715 13716 13717 13718 13719 13720 13721 13722 13723 13724 13725 13726 13727 13728 13729 13730 13731 13732 13733 13734 13735 13736 13737 13738 13739 13740 13741 13742 13743 13744 13745 13746 13747 13748 13749 13750 13751 13752 13753 13754 13755 13756 13757 13758 13759 13760 13761 13762 13763 13764 13765 13766 13767 13768 13769 13770 13771 13772 13773 13774 13775 13776 13777 13778 13779 13780 13781 13782 13783 13784 13785 13786 13787 13788 13789 13790 13791 13792 13793 13794 13795 13796 13797 13798 13799 13800 13801 13802 13803 13804 13805 13806 13807 13808 13809 13810 13811 13812 13813 13814 13815 13816 13817 13818 13819 13820 13821 13822 13823 13824 13825 13826 13827 13828 13829 13830 13831 13832 13833 13834 13835 13836 13837 13838 13839 13840 13841 13842 13843 13844 13845 13846 13847 13848 13849 13850 13851 13852 13853 13854 13855 13856 13857 13858 13859 13860 13861 13862 13863 13864 13865 13866 13867 13868 13869 13870 13871 13872 13873 13874 13875 13876 13877 13878 13879 13880 13881 13882 13883 13884 13885 13886 13887 13888 13889 13890 13891 13892 13893 13894 13895 13896 13897 13898 13899 13900 13901 13902 13903 13904 13905 13906 13907 13908 13909 13910 13911 13912 13913 13914 13915 13916 13917 13918 13919 13920 13921 13922 13923 13924 13925 13926 13927 13928 13929 13930 13931 13932 13933 13934 13935 13936 13937 13938 13939 13940 13941 13942 13943 13944 13945 13946 13947 13948 13949 13950 13951 13952 13953 13954 13955 13956 13957 13958 13959 13960 13961 13962 13963 13964 13965 13966 13967 13968 13969 13970 13971 13972 13973 13974 13975 13976 13977 13978 13979 13980 13981 13982 13983 13984 13985 13986 13987 13988 13989 13990 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine driver for Linux * * derived from drivers/kvm/kvm_main.c * * Copyright (C) 2006 Qumranet, Inc. * Copyright (C) 2008 Qumranet, Inc. * Copyright IBM Corporation, 2008 * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> * Amit Shah <amit.shah@qumranet.com> * Ben-Ami Yassour <benami@il.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "irq.h" #include "ioapic.h" #include "mmu.h" #include "i8254.h" #include "tss.h" #include "kvm_cache_regs.h" #include "kvm_emulate.h" #include "mmu/page_track.h" #include "x86.h" #include "cpuid.h" #include "pmu.h" #include "hyperv.h" #include "lapic.h" #include "xen.h" #include "smm.h" #include <linux/clocksource.h> #include <linux/interrupt.h> #include <linux/kvm.h> #include <linux/fs.h> #include <linux/vmalloc.h> #include <linux/export.h> #include <linux/moduleparam.h> #include <linux/mman.h> #include <linux/highmem.h> #include <linux/iommu.h> #include <linux/cpufreq.h> #include <linux/user-return-notifier.h> #include <linux/srcu.h> #include <linux/slab.h> #include <linux/perf_event.h> #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/pci.h> #include <linux/timekeeper_internal.h> #include <linux/pvclock_gtod.h> #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> #include <linux/sched/stat.h> #include <linux/sched/isolation.h> #include <linux/mem_encrypt.h> #include <linux/entry-kvm.h> #include <linux/suspend.h> #include <linux/smp.h> #include <trace/events/ipi.h> #include <trace/events/kvm.h> #include <asm/debugreg.h> #include <asm/msr.h> #include <asm/desc.h> #include <asm/mce.h> #include <asm/pkru.h> #include <linux/kernel_stat.h> #include <asm/fpu/api.h> #include <asm/fpu/xcr.h> #include <asm/fpu/xstate.h> #include <asm/pvclock.h> #include <asm/div64.h> #include <asm/irq_remapping.h> #include <asm/mshyperv.h> #include <asm/hypervisor.h> #include <asm/tlbflush.h> #include <asm/intel_pt.h> #include <asm/emulate_prefix.h> #include <asm/sgx.h> #include <clocksource/hyperv_timer.h> #define CREATE_TRACE_POINTS #include "trace.h" #define MAX_IO_MSRS 256 #define KVM_MAX_MCE_BANKS 32 /* * Note, kvm_caps fields should *never* have default values, all fields must be * recomputed from scratch during vendor module load, e.g. to account for a * vendor module being reloaded with different module parameters. */ struct kvm_caps kvm_caps __read_mostly; EXPORT_SYMBOL_GPL(kvm_caps); #define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) #define emul_to_vcpu(ctxt) \ ((struct kvm_vcpu *)(ctxt)->vcpu) /* EFER defaults: * - enable syscall per default because its emulated by KVM * - enable LME and LMA per default on 64 bit KVM */ #ifdef CONFIG_X86_64 static u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); #else static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; #define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) #define KVM_CAP_PMU_VALID_MASK KVM_PMU_CAP_DISABLE #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu); static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static DEFINE_MUTEX(vendor_module_lock); struct kvm_x86_ops kvm_x86_ops __read_mostly; #define KVM_X86_OP(func) \ DEFINE_STATIC_CALL_NULL(kvm_x86_##func, \ *(((struct kvm_x86_ops *)0)->func)); #define KVM_X86_OP_OPTIONAL KVM_X86_OP #define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP #include <asm/kvm-x86-ops.h> EXPORT_STATIC_CALL_GPL(kvm_x86_get_cs_db_l_bits); EXPORT_STATIC_CALL_GPL(kvm_x86_cache_reg); static bool __read_mostly ignore_msrs = 0; module_param(ignore_msrs, bool, 0644); bool __read_mostly report_ignored_msrs = true; module_param(report_ignored_msrs, bool, 0644); EXPORT_SYMBOL_GPL(report_ignored_msrs); unsigned int min_timer_period_us = 200; module_param(min_timer_period_us, uint, 0644); static bool __read_mostly kvmclock_periodic_sync = true; module_param(kvmclock_periodic_sync, bool, 0444); /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, 0644); static bool __read_mostly vector_hashing = true; module_param(vector_hashing, bool, 0444); bool __read_mostly enable_vmware_backdoor = false; module_param(enable_vmware_backdoor, bool, 0444); EXPORT_SYMBOL_GPL(enable_vmware_backdoor); /* * Flags to manipulate forced emulation behavior (any non-zero value will * enable forced emulation). */ #define KVM_FEP_CLEAR_RFLAGS_RF BIT(1) static int __read_mostly force_emulation_prefix; module_param(force_emulation_prefix, int, 0644); int __read_mostly pi_inject_timer = -1; module_param(pi_inject_timer, bint, 0644); /* Enable/disable PMU virtualization */ bool __read_mostly enable_pmu = true; EXPORT_SYMBOL_GPL(enable_pmu); module_param(enable_pmu, bool, 0444); bool __read_mostly eager_page_split = true; module_param(eager_page_split, bool, 0644); /* Enable/disable SMT_RSB bug mitigation */ static bool __read_mostly mitigate_smt_rsb; module_param(mitigate_smt_rsb, bool, 0444); /* * Restoring the host value for MSRs that are only consumed when running in * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU * returns to userspace, i.e. the kernel can run with the guest's value. */ #define KVM_MAX_NR_USER_RETURN_MSRS 16 struct kvm_user_return_msrs { struct user_return_notifier urn; bool registered; struct kvm_user_return_msr_values { u64 host; u64 curr; } values[KVM_MAX_NR_USER_RETURN_MSRS]; }; u32 __read_mostly kvm_nr_uret_msrs; EXPORT_SYMBOL_GPL(kvm_nr_uret_msrs); static u32 __read_mostly kvm_uret_msrs_list[KVM_MAX_NR_USER_RETURN_MSRS]; static struct kvm_user_return_msrs __percpu *user_return_msrs; #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \ | XFEATURE_MASK_PKRU | XFEATURE_MASK_XTILE) u64 __read_mostly host_efer; EXPORT_SYMBOL_GPL(host_efer); bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); bool __read_mostly enable_apicv = true; EXPORT_SYMBOL_GPL(enable_apicv); u64 __read_mostly host_xss; EXPORT_SYMBOL_GPL(host_xss); u64 __read_mostly host_arch_capabilities; EXPORT_SYMBOL_GPL(host_arch_capabilities); const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_COUNTER(VM, mmu_shadow_zapped), STATS_DESC_COUNTER(VM, mmu_pte_write), STATS_DESC_COUNTER(VM, mmu_pde_zapped), STATS_DESC_COUNTER(VM, mmu_flooded), STATS_DESC_COUNTER(VM, mmu_recycled), STATS_DESC_COUNTER(VM, mmu_cache_miss), STATS_DESC_ICOUNTER(VM, mmu_unsync), STATS_DESC_ICOUNTER(VM, pages_4k), STATS_DESC_ICOUNTER(VM, pages_2m), STATS_DESC_ICOUNTER(VM, pages_1g), STATS_DESC_ICOUNTER(VM, nx_lpage_splits), STATS_DESC_PCOUNTER(VM, max_mmu_rmap_size), STATS_DESC_PCOUNTER(VM, max_mmu_page_hash_collisions) }; const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), .id_offset = sizeof(struct kvm_stats_header), .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + sizeof(kvm_vm_stats_desc), }; const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, pf_taken), STATS_DESC_COUNTER(VCPU, pf_fixed), STATS_DESC_COUNTER(VCPU, pf_emulate), STATS_DESC_COUNTER(VCPU, pf_spurious), STATS_DESC_COUNTER(VCPU, pf_fast), STATS_DESC_COUNTER(VCPU, pf_mmio_spte_created), STATS_DESC_COUNTER(VCPU, pf_guest), STATS_DESC_COUNTER(VCPU, tlb_flush), STATS_DESC_COUNTER(VCPU, invlpg), STATS_DESC_COUNTER(VCPU, exits), STATS_DESC_COUNTER(VCPU, io_exits), STATS_DESC_COUNTER(VCPU, mmio_exits), STATS_DESC_COUNTER(VCPU, signal_exits), STATS_DESC_COUNTER(VCPU, irq_window_exits), STATS_DESC_COUNTER(VCPU, nmi_window_exits), STATS_DESC_COUNTER(VCPU, l1d_flush), STATS_DESC_COUNTER(VCPU, halt_exits), STATS_DESC_COUNTER(VCPU, request_irq_exits), STATS_DESC_COUNTER(VCPU, irq_exits), STATS_DESC_COUNTER(VCPU, host_state_reload), STATS_DESC_COUNTER(VCPU, fpu_reload), STATS_DESC_COUNTER(VCPU, insn_emulation), STATS_DESC_COUNTER(VCPU, insn_emulation_fail), STATS_DESC_COUNTER(VCPU, hypercalls), STATS_DESC_COUNTER(VCPU, irq_injections), STATS_DESC_COUNTER(VCPU, nmi_injections), STATS_DESC_COUNTER(VCPU, req_event), STATS_DESC_COUNTER(VCPU, nested_run), STATS_DESC_COUNTER(VCPU, directed_yield_attempted), STATS_DESC_COUNTER(VCPU, directed_yield_successful), STATS_DESC_COUNTER(VCPU, preemption_reported), STATS_DESC_COUNTER(VCPU, preemption_other), STATS_DESC_IBOOLEAN(VCPU, guest_mode), STATS_DESC_COUNTER(VCPU, notify_window_exits), }; const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), .id_offset = sizeof(struct kvm_stats_header), .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + sizeof(kvm_vcpu_stats_desc), }; u64 __read_mostly host_xcr0; static struct kmem_cache *x86_emulator_cache; /* * When called, it means the previous get/set msr reached an invalid msr. * Return true if we want to ignore/silent this failed msr access. */ static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write) { const char *op = write ? "wrmsr" : "rdmsr"; if (ignore_msrs) { if (report_ignored_msrs) kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", op, msr, data); /* Mask the error */ return true; } else { kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", op, msr, data); return false; } } static struct kmem_cache *kvm_alloc_emulator_cache(void) { unsigned int useroffset = offsetof(struct x86_emulate_ctxt, src); unsigned int size = sizeof(struct x86_emulate_ctxt); return kmem_cache_create_usercopy("x86_emulator", size, __alignof__(struct x86_emulate_ctxt), SLAB_ACCOUNT, useroffset, size - useroffset, NULL); } static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) { int i; for (i = 0; i < ASYNC_PF_PER_VCPU; i++) vcpu->arch.apf.gfns[i] = ~0; } static void kvm_on_user_return(struct user_return_notifier *urn) { unsigned slot; struct kvm_user_return_msrs *msrs = container_of(urn, struct kvm_user_return_msrs, urn); struct kvm_user_return_msr_values *values; unsigned long flags; /* * Disabling irqs at this point since the following code could be * interrupted and executed through kvm_arch_hardware_disable() */ local_irq_save(flags); if (msrs->registered) { msrs->registered = false; user_return_notifier_unregister(urn); } local_irq_restore(flags); for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) { values = &msrs->values[slot]; if (values->host != values->curr) { wrmsrl(kvm_uret_msrs_list[slot], values->host); values->curr = values->host; } } } static int kvm_probe_user_return_msr(u32 msr) { u64 val; int ret; preempt_disable(); ret = rdmsrl_safe(msr, &val); if (ret) goto out; ret = wrmsrl_safe(msr, val); out: preempt_enable(); return ret; } int kvm_add_user_return_msr(u32 msr) { BUG_ON(kvm_nr_uret_msrs >= KVM_MAX_NR_USER_RETURN_MSRS); if (kvm_probe_user_return_msr(msr)) return -1; kvm_uret_msrs_list[kvm_nr_uret_msrs] = msr; return kvm_nr_uret_msrs++; } EXPORT_SYMBOL_GPL(kvm_add_user_return_msr); int kvm_find_user_return_msr(u32 msr) { int i; for (i = 0; i < kvm_nr_uret_msrs; ++i) { if (kvm_uret_msrs_list[i] == msr) return i; } return -1; } EXPORT_SYMBOL_GPL(kvm_find_user_return_msr); static void kvm_user_return_msr_cpu_online(void) { unsigned int cpu = smp_processor_id(); struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); u64 value; int i; for (i = 0; i < kvm_nr_uret_msrs; ++i) { rdmsrl_safe(kvm_uret_msrs_list[i], &value); msrs->values[i].host = value; msrs->values[i].curr = value; } } int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) { unsigned int cpu = smp_processor_id(); struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); int err; value = (value & mask) | (msrs->values[slot].host & ~mask); if (value == msrs->values[slot].curr) return 0; err = wrmsrl_safe(kvm_uret_msrs_list[slot], value); if (err) return 1; msrs->values[slot].curr = value; if (!msrs->registered) { msrs->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&msrs->urn); msrs->registered = true; } return 0; } EXPORT_SYMBOL_GPL(kvm_set_user_return_msr); static void drop_user_return_notifiers(void) { unsigned int cpu = smp_processor_id(); struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); if (msrs->registered) kvm_on_user_return(&msrs->urn); } u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) { return vcpu->arch.apic_base; } enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu) { return kvm_apic_mode(kvm_get_apic_base(vcpu)); } EXPORT_SYMBOL_GPL(kvm_get_apic_mode); int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { enum lapic_mode old_mode = kvm_get_apic_mode(vcpu); enum lapic_mode new_mode = kvm_apic_mode(msr_info->data); u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff | (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID) return 1; if (!msr_info->host_initiated) { if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC) return 1; if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC) return 1; } kvm_lapic_set_base(vcpu, msr_info->data); kvm_recalculate_apic_map(vcpu->kvm); return 0; } /* * Handle a fault on a hardware virtualization (VMX or SVM) instruction. * * Hardware virtualization extension instructions may fault if a reboot turns * off virtualization while processes are running. Usually after catching the * fault we just panic; during reboot instead the instruction is ignored. */ noinstr void kvm_spurious_fault(void) { /* Fault while not rebooting. We want the trace. */ BUG_ON(!kvm_rebooting); } EXPORT_SYMBOL_GPL(kvm_spurious_fault); #define EXCPT_BENIGN 0 #define EXCPT_CONTRIBUTORY 1 #define EXCPT_PF 2 static int exception_class(int vector) { switch (vector) { case PF_VECTOR: return EXCPT_PF; case DE_VECTOR: case TS_VECTOR: case NP_VECTOR: case SS_VECTOR: case GP_VECTOR: return EXCPT_CONTRIBUTORY; default: break; } return EXCPT_BENIGN; } #define EXCPT_FAULT 0 #define EXCPT_TRAP 1 #define EXCPT_ABORT 2 #define EXCPT_INTERRUPT 3 #define EXCPT_DB 4 static int exception_type(int vector) { unsigned int mask; if (WARN_ON(vector > 31 || vector == NMI_VECTOR)) return EXCPT_INTERRUPT; mask = 1 << vector; /* * #DBs can be trap-like or fault-like, the caller must check other CPU * state, e.g. DR6, to determine whether a #DB is a trap or fault. */ if (mask & (1 << DB_VECTOR)) return EXCPT_DB; if (mask & ((1 << BP_VECTOR) | (1 << OF_VECTOR))) return EXCPT_TRAP; if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR))) return EXCPT_ABORT; /* Reserved exceptions will result in fault */ return EXCPT_FAULT; } void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu, struct kvm_queued_exception *ex) { if (!ex->has_payload) return; switch (ex->vector) { case DB_VECTOR: /* * "Certain debug exceptions may clear bit 0-3. The * remaining contents of the DR6 register are never * cleared by the processor". */ vcpu->arch.dr6 &= ~DR_TRAP_BITS; /* * In order to reflect the #DB exception payload in guest * dr6, three components need to be considered: active low * bit, FIXED_1 bits and active high bits (e.g. DR6_BD, * DR6_BS and DR6_BT) * DR6_ACTIVE_LOW contains the FIXED_1 and active low bits. * In the target guest dr6: * FIXED_1 bits should always be set. * Active low bits should be cleared if 1-setting in payload. * Active high bits should be set if 1-setting in payload. * * Note, the payload is compatible with the pending debug * exceptions/exit qualification under VMX, that active_low bits * are active high in payload. * So they need to be flipped for DR6. */ vcpu->arch.dr6 |= DR6_ACTIVE_LOW; vcpu->arch.dr6 |= ex->payload; vcpu->arch.dr6 ^= ex->payload & DR6_ACTIVE_LOW; /* * The #DB payload is defined as compatible with the 'pending * debug exceptions' field under VMX, not DR6. While bit 12 is * defined in the 'pending debug exceptions' field (enabled * breakpoint), it is reserved and must be zero in DR6. */ vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: vcpu->arch.cr2 = ex->payload; break; } ex->has_payload = false; ex->payload = 0; } EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload); static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vector, bool has_error_code, u32 error_code, bool has_payload, unsigned long payload) { struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; ex->vector = vector; ex->injected = false; ex->pending = true; ex->has_error_code = has_error_code; ex->error_code = error_code; ex->has_payload = has_payload; ex->payload = payload; } /* Forcibly leave the nested mode in cases like a vCPU reset */ static void kvm_leave_nested(struct kvm_vcpu *vcpu) { kvm_x86_ops.nested_ops->leave_nested(vcpu); } static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload, bool reinject) { u32 prev_nr; int class1, class2; kvm_make_request(KVM_REQ_EVENT, vcpu); /* * If the exception is destined for L2 and isn't being reinjected, * morph it to a VM-Exit if L1 wants to intercept the exception. A * previously injected exception is not checked because it was checked * when it was original queued, and re-checking is incorrect if _L1_ * injected the exception, in which case it's exempt from interception. */ if (!reinject && is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, nr, error_code)) { kvm_queue_exception_vmexit(vcpu, nr, has_error, error_code, has_payload, payload); return; } if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) { queue: if (reinject) { /* * On VM-Entry, an exception can be pending if and only * if event injection was blocked by nested_run_pending. * In that case, however, vcpu_enter_guest() requests an * immediate exit, and the guest shouldn't proceed far * enough to need reinjection. */ WARN_ON_ONCE(kvm_is_exception_pending(vcpu)); vcpu->arch.exception.injected = true; if (WARN_ON_ONCE(has_payload)) { /* * A reinjected event has already * delivered its payload. */ has_payload = false; payload = 0; } } else { vcpu->arch.exception.pending = true; vcpu->arch.exception.injected = false; } vcpu->arch.exception.has_error_code = has_error; vcpu->arch.exception.vector = nr; vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; if (!is_guest_mode(vcpu)) kvm_deliver_exception_payload(vcpu, &vcpu->arch.exception); return; } /* to check exception */ prev_nr = vcpu->arch.exception.vector; if (prev_nr == DF_VECTOR) { /* triple fault -> shutdown */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return; } class1 = exception_class(prev_nr); class2 = exception_class(nr); if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { /* * Synthesize #DF. Clear the previously injected or pending * exception so as not to incorrectly trigger shutdown. */ vcpu->arch.exception.injected = false; vcpu->arch.exception.pending = false; kvm_queue_exception_e(vcpu, DF_VECTOR, 0); } else { /* replace previous exception with a new one in a hope that instruction re-execution will regenerate lost exception */ goto queue; } } void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) { kvm_multiple_exception(vcpu, nr, false, 0, false, 0, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception); void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr) { kvm_multiple_exception(vcpu, nr, false, 0, false, 0, true); } EXPORT_SYMBOL_GPL(kvm_requeue_exception); void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload) { kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception_p); static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code, unsigned long payload) { kvm_multiple_exception(vcpu, nr, true, error_code, true, payload, false); } int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) { if (err) kvm_inject_gp(vcpu, 0); else return kvm_skip_emulated_instruction(vcpu); return 1; } EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err) { if (err) { kvm_inject_gp(vcpu, 0); return 1; } return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE | EMULTYPE_SKIP | EMULTYPE_COMPLETE_USER_EXIT); } void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; /* * Async #PF in L2 is always forwarded to L1 as a VM-Exit regardless of * whether or not L1 wants to intercept "regular" #PF. */ if (is_guest_mode(vcpu) && fault->async_page_fault) kvm_queue_exception_vmexit(vcpu, PF_VECTOR, true, fault->error_code, true, fault->address); else kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code, fault->address); } void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { struct kvm_mmu *fault_mmu; WARN_ON_ONCE(fault->vector != PF_VECTOR); fault_mmu = fault->nested_page_fault ? vcpu->arch.mmu : vcpu->arch.walk_mmu; /* * Invalidate the TLB entry for the faulting address, if it exists, * else the access will fault indefinitely (and to emulate hardware). */ if ((fault->error_code & PFERR_PRESENT_MASK) && !(fault->error_code & PFERR_RSVD_MASK)) kvm_mmu_invalidate_addr(vcpu, fault_mmu, fault->address, KVM_MMU_ROOT_CURRENT); fault_mmu->inject_page_fault(vcpu, fault); } EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault); void kvm_inject_nmi(struct kvm_vcpu *vcpu) { atomic_inc(&vcpu->arch.nmi_queued); kvm_make_request(KVM_REQ_NMI, vcpu); } void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) { kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception_e); void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) { kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, true); } EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); /* * Checks if cpl <= required_cpl; if true, return true. Otherwise queue * a #GP and return false. */ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) { if (static_call(kvm_x86_get_cpl)(vcpu) <= required_cpl) return true; kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return false; } bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr) { if ((dr != 4 && dr != 5) || !kvm_is_cr4_bit_set(vcpu, X86_CR4_DE)) return true; kvm_queue_exception(vcpu, UD_VECTOR); return false; } EXPORT_SYMBOL_GPL(kvm_require_dr); static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); } /* * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; gpa_t real_gpa; int i; int ret; u64 pdpte[ARRAY_SIZE(mmu->pdptrs)]; /* * If the MMU is nested, CR3 holds an L2 GPA and needs to be translated * to an L1 GPA. */ real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(pdpt_gfn), PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); if (real_gpa == INVALID_GPA) return 0; /* Note the offset, PDPTRs are 32 byte aligned when using PAE paging. */ ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(real_gpa), pdpte, cr3 & GENMASK(11, 5), sizeof(pdpte)); if (ret < 0) return 0; for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if ((pdpte[i] & PT_PRESENT_MASK) && (pdpte[i] & pdptr_rsvd_bits(vcpu))) { return 0; } } /* * Marking VCPU_EXREG_PDPTR dirty doesn't work for !tdp_enabled. * Shadow page roots need to be reconstructed instead. */ if (!tdp_enabled && memcmp(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs))) kvm_mmu_free_roots(vcpu->kvm, mmu, KVM_MMU_ROOT_CURRENT); memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); vcpu->arch.pdptrs_from_userspace = false; return 1; } EXPORT_SYMBOL_GPL(load_pdptrs); static bool kvm_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { #ifdef CONFIG_X86_64 if (cr0 & 0xffffffff00000000UL) return false; #endif if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) return false; if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) return false; return static_call(kvm_x86_is_valid_cr0)(vcpu, cr0); } void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0) { /* * CR0.WP is incorporated into the MMU role, but only for non-nested, * indirect shadow MMUs. If paging is disabled, no updates are needed * as there are no permission bits to emulate. If TDP is enabled, the * MMU's metadata needs to be updated, e.g. so that emulating guest * translations does the right thing, but there's no need to unload the * root as CR0.WP doesn't affect SPTEs. */ if ((cr0 ^ old_cr0) == X86_CR0_WP) { if (!(cr0 & X86_CR0_PG)) return; if (tdp_enabled) { kvm_init_mmu(vcpu); return; } } if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); /* * Clearing CR0.PG is defined to flush the TLB from the guest's * perspective. */ if (!(cr0 & X86_CR0_PG)) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS) kvm_mmu_reset_context(vcpu); if (((cr0 ^ old_cr0) & X86_CR0_CD) && kvm_mmu_honors_guest_mtrrs(vcpu->kvm) && !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); } EXPORT_SYMBOL_GPL(kvm_post_set_cr0); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); if (!kvm_is_valid_cr0(vcpu, cr0)) return 1; cr0 |= X86_CR0_ET; /* Write to CR0 reserved bits are ignored, even on Intel. */ cr0 &= ~CR0_RESERVED_BITS; #ifdef CONFIG_X86_64 if ((vcpu->arch.efer & EFER_LME) && !is_paging(vcpu) && (cr0 & X86_CR0_PG)) { int cs_db, cs_l; if (!is_pae(vcpu)) return 1; static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); if (cs_l) return 1; } #endif if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) && is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS) && !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if (!(cr0 & X86_CR0_PG) && (is_64_bit_mode(vcpu) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE))) return 1; static_call(kvm_x86_set_cr0)(vcpu, cr0); kvm_post_set_cr0(vcpu, old_cr0, cr0); return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr0); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) { (void)kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f)); } EXPORT_SYMBOL_GPL(kvm_lmsw); void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) { if (vcpu->arch.guest_state_protected) return; if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && vcpu->arch.ia32_xss != host_xss) wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } if (cpu_feature_enabled(X86_FEATURE_PKU) && vcpu->arch.pkru != vcpu->arch.host_pkru && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) write_pkru(vcpu->arch.pkru); } EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) { if (vcpu->arch.guest_state_protected) return; if (cpu_feature_enabled(X86_FEATURE_PKU) && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) { vcpu->arch.pkru = rdpkru(); if (vcpu->arch.pkru != vcpu->arch.host_pkru) write_pkru(vcpu->arch.host_pkru); } if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && vcpu->arch.ia32_xss != host_xss) wrmsrl(MSR_IA32_XSS, host_xss); } } EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); #ifdef CONFIG_X86_64 static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) { return vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC; } #endif static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0 = xcr; u64 old_xcr0 = vcpu->arch.xcr0; u64 valid_bits; /* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */ if (index != XCR_XFEATURE_ENABLED_MASK) return 1; if (!(xcr0 & XFEATURE_MASK_FP)) return 1; if ((xcr0 & XFEATURE_MASK_YMM) && !(xcr0 & XFEATURE_MASK_SSE)) return 1; /* * Do not allow the guest to set bits that we do not support * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; if ((!(xcr0 & XFEATURE_MASK_BNDREGS)) != (!(xcr0 & XFEATURE_MASK_BNDCSR))) return 1; if (xcr0 & XFEATURE_MASK_AVX512) { if (!(xcr0 & XFEATURE_MASK_YMM)) return 1; if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512) return 1; } if ((xcr0 & XFEATURE_MASK_XTILE) && ((xcr0 & XFEATURE_MASK_XTILE) != XFEATURE_MASK_XTILE)) return 1; vcpu->arch.xcr0 = xcr0; if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) kvm_update_cpuid_runtime(vcpu); return 0; } int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) { /* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */ if (static_call(kvm_x86_get_cpl)(vcpu) != 0 || __kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) { kvm_inject_gp(vcpu, 0); return 1; } return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_xsetbv); bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (cr4 & cr4_reserved_bits) return false; if (cr4 & vcpu->arch.cr4_guest_rsvd_bits) return false; return true; } EXPORT_SYMBOL_GPL(__kvm_is_valid_cr4); static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { return __kvm_is_valid_cr4(vcpu, cr4) && static_call(kvm_x86_is_valid_cr4)(vcpu, cr4); } void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4) { if ((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) kvm_mmu_reset_context(vcpu); /* * If CR4.PCIDE is changed 0 -> 1, there is no need to flush the TLB * according to the SDM; however, stale prev_roots could be reused * incorrectly in the future after a MOV to CR3 with NOFLUSH=1, so we * free them all. This is *not* a superset of KVM_REQ_TLB_FLUSH_GUEST * or KVM_REQ_TLB_FLUSH_CURRENT, because the hardware TLB is not flushed, * so fall through. */ if (!tdp_enabled && (cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) kvm_mmu_unload(vcpu); /* * The TLB has to be flushed for all PCIDs if any of the following * (architecturally required) changes happen: * - CR4.PCIDE is changed from 1 to 0 * - CR4.PGE is toggled * * This is a superset of KVM_REQ_TLB_FLUSH_CURRENT. */ if (((cr4 ^ old_cr4) & X86_CR4_PGE) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); /* * The TLB has to be flushed for the current PCID if any of the * following (architecturally required) changes happen: * - CR4.SMEP is changed from 0 to 1 * - CR4.PAE is toggled */ else if (((cr4 ^ old_cr4) & X86_CR4_PAE) || ((cr4 & X86_CR4_SMEP) && !(old_cr4 & X86_CR4_SMEP))) kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } EXPORT_SYMBOL_GPL(kvm_post_set_cr4); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); if (!kvm_is_valid_cr4(vcpu, cr4)) return 1; if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; if ((cr4 ^ old_cr4) & X86_CR4_LA57) return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) && ((cr4 ^ old_cr4) & X86_CR4_PDPTR_BITS) && !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) return 1; } static_call(kvm_x86_set_cr4)(vcpu, cr4); kvm_post_set_cr4(vcpu, old_cr4, cr4); return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr4); static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) { struct kvm_mmu *mmu = vcpu->arch.mmu; unsigned long roots_to_free = 0; int i; /* * MOV CR3 and INVPCID are usually not intercepted when using TDP, but * this is reachable when running EPT=1 and unrestricted_guest=0, and * also via the emulator. KVM's TDP page tables are not in the scope of * the invalidation, but the guest's TLB entries need to be flushed as * the CPU may have cached entries in its TLB for the target PCID. */ if (unlikely(tdp_enabled)) { kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return; } /* * If neither the current CR3 nor any of the prev_roots use the given * PCID, then nothing needs to be done here because a resync will * happen anyway before switching to any other CR3. */ if (kvm_get_active_pcid(vcpu) == pcid) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } /* * If PCID is disabled, there is no need to free prev_roots even if the * PCIDs for them are also 0, because MOV to CR3 always flushes the TLB * with PCIDE=0. */ if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) return; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd) == pcid) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); kvm_mmu_free_roots(vcpu->kvm, mmu, roots_to_free); } int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { bool skip_tlb_flush = false; unsigned long pcid = 0; #ifdef CONFIG_X86_64 if (kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) { skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH; cr3 &= ~X86_CR3_PCID_NOFLUSH; pcid = cr3 & X86_CR3_PCID_MASK; } #endif /* PDPTRs are always reloaded for PAE paging. */ if (cr3 == kvm_read_cr3(vcpu) && !is_pae_paging(vcpu)) goto handle_tlb_flush; /* * Do not condition the GPA check on long mode, this helper is used to * stuff CR3, e.g. for RSM emulation, and there is no guarantee that * the current vCPU mode is accurate. */ if (!kvm_vcpu_is_legal_cr3(vcpu, cr3)) return 1; if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) return 1; if (cr3 != kvm_read_cr3(vcpu)) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); /* Do not call post_set_cr3, we do not get here for confidential guests. */ handle_tlb_flush: /* * A load of CR3 that flushes the TLB flushes only the current PCID, * even if PCID is disabled, in which case PCID=0 is flushed. It's a * moot point in the end because _disabling_ PCID will flush all PCIDs, * and it's impossible to use a non-zero PCID when PCID is disabled, * i.e. only PCID=0 can be relevant. */ if (!skip_tlb_flush) kvm_invalidate_pcid(vcpu, pcid); return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr3); int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) { if (cr8 & CR8_RESERVED_BITS) return 1; if (lapic_in_kernel(vcpu)) kvm_lapic_set_tpr(vcpu, cr8); else vcpu->arch.cr8 = cr8; return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr8); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) { if (lapic_in_kernel(vcpu)) return kvm_lapic_get_cr8(vcpu); else return vcpu->arch.cr8; } EXPORT_SYMBOL_GPL(kvm_get_cr8); static void kvm_update_dr0123(struct kvm_vcpu *vcpu) { int i; if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { for (i = 0; i < KVM_NR_DB_REGS; i++) vcpu->arch.eff_db[i] = vcpu->arch.db[i]; } } void kvm_update_dr7(struct kvm_vcpu *vcpu) { unsigned long dr7; if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) dr7 = vcpu->arch.guest_debug_dr7; else dr7 = vcpu->arch.dr7; static_call(kvm_x86_set_dr7)(vcpu, dr7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED; if (dr7 & DR7_BP_EN_MASK) vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED; } EXPORT_SYMBOL_GPL(kvm_update_dr7); static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) { u64 fixed = DR6_FIXED_1; if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM)) fixed |= DR6_RTM; if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) fixed |= DR6_BUS_LOCK; return fixed; } int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { size_t size = ARRAY_SIZE(vcpu->arch.db); switch (dr) { case 0 ... 3: vcpu->arch.db[array_index_nospec(dr, size)] = val; if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) vcpu->arch.eff_db[dr] = val; break; case 4: case 6: if (!kvm_dr6_valid(val)) return 1; /* #GP */ vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); break; case 5: default: /* 7 */ if (!kvm_dr7_valid(val)) return 1; /* #GP */ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; kvm_update_dr7(vcpu); break; } return 0; } EXPORT_SYMBOL_GPL(kvm_set_dr); unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr) { size_t size = ARRAY_SIZE(vcpu->arch.db); switch (dr) { case 0 ... 3: return vcpu->arch.db[array_index_nospec(dr, size)]; case 4: case 6: return vcpu->arch.dr6; case 5: default: /* 7 */ return vcpu->arch.dr7; } } EXPORT_SYMBOL_GPL(kvm_get_dr); int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu) { u32 ecx = kvm_rcx_read(vcpu); u64 data; if (kvm_pmu_rdpmc(vcpu, ecx, &data)) { kvm_inject_gp(vcpu, 0); return 1; } kvm_rax_write(vcpu, (u32)data); kvm_rdx_write(vcpu, data >> 32); return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); /* * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that * require host support, i.e. should be probed via RDMSR. emulated_msrs holds * MSRs that KVM emulates without strictly requiring host support. * msr_based_features holds MSRs that enumerate features, i.e. are effectively * CPUID leafs. Note, msr_based_features isn't mutually exclusive with * msrs_to_save and emulated_msrs. */ static const u32 msrs_to_save_base[] = { MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, MSR_IA32_UMWAIT_CONTROL, MSR_IA32_XFD, MSR_IA32_XFD_ERR, }; static const u32 msrs_to_save_pmu[] = { MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL, MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, /* This part of MSRs should match KVM_INTEL_PMC_MAX_GENERIC. */ MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, /* This part of MSRs should match KVM_AMD_PMC_MAX_GENERIC. */ MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, MSR_AMD64_PERF_CNTR_GLOBAL_CTL, MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, }; static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + ARRAY_SIZE(msrs_to_save_pmu)]; static unsigned num_msrs_to_save; static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, #ifdef CONFIG_KVM_HYPERV HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, HV_X64_MSR_RESET, HV_X64_MSR_VP_INDEX, HV_X64_MSR_VP_RUNTIME, HV_X64_MSR_SCONTROL, HV_X64_MSR_STIMER0_CONFIG, HV_X64_MSR_VP_ASSIST_PAGE, HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_X64_MSR_SYNDBG_OPTIONS, HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, HV_X64_MSR_SYNDBG_PENDING_BUFFER, #endif MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, MSR_IA32_TSC_ADJUST, MSR_IA32_TSC_DEADLINE, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, MSR_IA32_MCG_EXT_CTL, MSR_IA32_SMBASE, MSR_SMI_COUNT, MSR_PLATFORM_INFO, MSR_MISC_FEATURES_ENABLES, MSR_AMD64_VIRT_SPEC_CTRL, MSR_AMD64_TSC_RATIO, MSR_IA32_POWER_CTL, MSR_IA32_UCODE_REV, /* * KVM always supports the "true" VMX control MSRs, even if the host * does not. The VMX MSRs as a whole are considered "emulated" as KVM * doesn't strictly require them to exist in the host (ignoring that * KVM would refuse to load in the first place if the core set of MSRs * aren't supported). */ MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, MSR_IA32_VMX_TRUE_PROCBASED_CTLS, MSR_IA32_VMX_TRUE_EXIT_CTLS, MSR_IA32_VMX_TRUE_ENTRY_CTLS, MSR_IA32_VMX_MISC, MSR_IA32_VMX_CR0_FIXED0, MSR_IA32_VMX_CR4_FIXED0, MSR_IA32_VMX_VMCS_ENUM, MSR_IA32_VMX_PROCBASED_CTLS2, MSR_IA32_VMX_EPT_VPID_CAP, MSR_IA32_VMX_VMFUNC, MSR_K7_HWCR, MSR_KVM_POLL_CONTROL, }; static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; static unsigned num_emulated_msrs; /* * List of MSRs that control the existence of MSR-based features, i.e. MSRs * that are effectively CPUID leafs. VMX MSRs are also included in the set of * feature MSRs, but are handled separately to allow expedited lookups. */ static const u32 msr_based_features_all_except_vmx[] = { MSR_AMD64_DE_CFG, MSR_IA32_UCODE_REV, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, }; static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; static unsigned int num_msr_based_features; /* * All feature MSRs except uCode revID, which tracks the currently loaded uCode * patch, are immutable once the vCPU model is defined. */ static bool kvm_is_immutable_feature_msr(u32 msr) { int i; if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) return true; for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { if (msr == msr_based_features_all_except_vmx[i]) return msr != MSR_IA32_UCODE_REV; } return false; } /* * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM * does not yet virtualize. These include: * 10 - MISC_PACKAGE_CTRLS * 11 - ENERGY_FILTERING_CTL * 12 - DOITM * 18 - FB_CLEAR_CTRL * 21 - XAPIC_DISABLE_STATUS * 23 - OVERCLOCKING_STATUS */ #define KVM_SUPPORTED_ARCH_CAP \ (ARCH_CAP_RDCL_NO | ARCH_CAP_IBRS_ALL | ARCH_CAP_RSBA | \ ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) static u64 kvm_get_arch_capabilities(void) { u64 data = host_arch_capabilities & KVM_SUPPORTED_ARCH_CAP; /* * If nx_huge_pages is enabled, KVM's shadow paging will ensure that * the nested hypervisor runs with NX huge pages. If it is not, * L1 is anyway vulnerable to ITLB_MULTIHIT exploits from other * L1 guests, so it need not worry about its own (L2) guests. */ data |= ARCH_CAP_PSCHANGE_MC_NO; /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us * (ARCH_CAP_SKIP_VMENTRY_L1DFLUSH), we can safely pass that * capability to the guest too, and if EPT is disabled we're not * vulnerable. Overall, only VMENTER_L1D_FLUSH_NEVER will * require a nested hypervisor to do a flush of its own. */ if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) data |= ARCH_CAP_RDCL_NO; if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; if (!boot_cpu_has_bug(X86_BUG_RFDS)) data |= ARCH_CAP_RFDS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* * If RTM=0 because the kernel has disabled TSX, the host might * have TAA_NO or TSX_CTRL. Clear TAA_NO (the guest sees RTM=0 * and therefore knows that there cannot be TAA) but keep * TSX_CTRL: some buggy userspaces leave it set on tsx=on hosts, * and we want to allow migrating those guests to tsx=off hosts. */ data &= ~ARCH_CAP_TAA_NO; } else if (!boot_cpu_has_bug(X86_BUG_TAA)) { data |= ARCH_CAP_TAA_NO; } else { /* * Nothing to do here; we emulate TSX_CTRL if present on the * host so the guest can choose between disabling TSX or * using VERW to clear CPU buffers. */ } if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated()) data |= ARCH_CAP_GDS_NO; return data; } static int kvm_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { case MSR_IA32_ARCH_CAPABILITIES: msr->data = kvm_get_arch_capabilities(); break; case MSR_IA32_PERF_CAPABILITIES: msr->data = kvm_caps.supported_perf_cap; break; case MSR_IA32_UCODE_REV: rdmsrl_safe(msr->index, &msr->data); break; default: return static_call(kvm_x86_get_msr_feature)(msr); } return 0; } static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { struct kvm_msr_entry msr; int r; /* Unconditionally clear the output for simplicity */ msr.data = 0; msr.index = index; r = kvm_get_msr_feature(&msr); if (r == KVM_MSR_RET_INVALID && kvm_msr_ignored_check(index, 0, false)) r = 0; *data = msr.data; return r; } static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & EFER_AUTOIBRS && !guest_cpuid_has(vcpu, X86_FEATURE_AUTOIBRS)) return false; if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT)) return false; if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM)) return false; if (efer & (EFER_LME | EFER_LMA) && !guest_cpuid_has(vcpu, X86_FEATURE_LM)) return false; if (efer & EFER_NX && !guest_cpuid_has(vcpu, X86_FEATURE_NX)) return false; return true; } bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & efer_reserved_bits) return false; return __kvm_valid_efer(vcpu, efer); } EXPORT_SYMBOL_GPL(kvm_valid_efer); static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u64 old_efer = vcpu->arch.efer; u64 efer = msr_info->data; int r; if (efer & efer_reserved_bits) return 1; if (!msr_info->host_initiated) { if (!__kvm_valid_efer(vcpu, efer)) return 1; if (is_paging(vcpu) && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) return 1; } efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; r = static_call(kvm_x86_set_efer)(vcpu, efer); if (r) { WARN_ON(r > 0); return r; } if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS) kvm_mmu_reset_context(vcpu); if (!static_cpu_has(X86_FEATURE_XSAVES) && (efer & EFER_SVME)) kvm_hv_xsaves_xsavec_maybe_warn(vcpu); return 0; } void kvm_enable_efer_bits(u64 mask) { efer_reserved_bits &= ~mask; } EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type) { struct kvm_x86_msr_filter *msr_filter; struct msr_bitmap_range *ranges; struct kvm *kvm = vcpu->kvm; bool allowed; int idx; u32 i; /* x2APIC MSRs do not support filtering. */ if (index >= 0x800 && index <= 0x8ff) return true; idx = srcu_read_lock(&kvm->srcu); msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu); if (!msr_filter) { allowed = true; goto out; } allowed = msr_filter->default_allow; ranges = msr_filter->ranges; for (i = 0; i < msr_filter->count; i++) { u32 start = ranges[i].base; u32 end = start + ranges[i].nmsrs; u32 flags = ranges[i].flags; unsigned long *bitmap = ranges[i].bitmap; if ((index >= start) && (index < end) && (flags & type)) { allowed = test_bit(index - start, bitmap); break; } } out: srcu_read_unlock(&kvm->srcu, idx); return allowed; } EXPORT_SYMBOL_GPL(kvm_msr_allowed); /* * Write @data into the MSR specified by @index. Select MSR specific fault * checks are bypassed if @host_initiated is %true. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, bool host_initiated) { struct msr_data msr; switch (index) { case MSR_FS_BASE: case MSR_GS_BASE: case MSR_KERNEL_GS_BASE: case MSR_CSTAR: case MSR_LSTAR: if (is_noncanonical_address(data, vcpu)) return 1; break; case MSR_IA32_SYSENTER_EIP: case MSR_IA32_SYSENTER_ESP: /* * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if * non-canonical address is written on Intel but not on * AMD (which ignores the top 32-bits, because it does * not implement 64-bit SYSENTER). * * 64-bit code should hence be able to write a non-canonical * value on AMD. Making the address canonical ensures that * vmentry does not fail on Intel after writing a non-canonical * value, and that something deterministic happens if the guest * invokes 64-bit SYSENTER. */ data = __canonical_address(data, vcpu_virt_addr_bits(vcpu)); break; case MSR_TSC_AUX: if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) return 1; if (!host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) return 1; /* * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has * incomplete and conflicting architectural behavior. Current * AMD CPUs completely ignore bits 63:32, i.e. they aren't * reserved and always read as zeros. Enforce Intel's reserved * bits check if and only if the guest CPU is Intel, and clear * the bits in all other cases. This ensures cross-vendor * migration will provide consistent behavior for the guest. */ if (guest_cpuid_is_intel(vcpu) && (data >> 32) != 0) return 1; data = (u32)data; break; } msr.data = data; msr.index = index; msr.host_initiated = host_initiated; return static_call(kvm_x86_set_msr)(vcpu, &msr); } static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 data, bool host_initiated) { int ret = __kvm_set_msr(vcpu, index, data, host_initiated); if (ret == KVM_MSR_RET_INVALID) if (kvm_msr_ignored_check(index, data, true)) ret = 0; return ret; } /* * Read the MSR specified by @index into @data. Select MSR specific fault * checks are bypassed if @host_initiated is %true. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated) { struct msr_data msr; int ret; switch (index) { case MSR_TSC_AUX: if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) return 1; if (!host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) return 1; break; } msr.index = index; msr.host_initiated = host_initiated; ret = static_call(kvm_x86_get_msr)(vcpu, &msr); if (!ret) *data = msr.data; return ret; } static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated) { int ret = __kvm_get_msr(vcpu, index, data, host_initiated); if (ret == KVM_MSR_RET_INVALID) { /* Unconditionally clear *data for simplicity */ *data = 0; if (kvm_msr_ignored_check(index, 0, false)) ret = 0; } return ret; } static int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data) { if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) return KVM_MSR_RET_FILTERED; return kvm_get_msr_ignored_check(vcpu, index, data, false); } static int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data) { if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) return KVM_MSR_RET_FILTERED; return kvm_set_msr_ignored_check(vcpu, index, data, false); } int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) { return kvm_get_msr_ignored_check(vcpu, index, data, false); } EXPORT_SYMBOL_GPL(kvm_get_msr); int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) { return kvm_set_msr_ignored_check(vcpu, index, data, false); } EXPORT_SYMBOL_GPL(kvm_set_msr); static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu) { if (!vcpu->run->msr.error) { kvm_rax_write(vcpu, (u32)vcpu->run->msr.data); kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32); } } static int complete_emulated_msr_access(struct kvm_vcpu *vcpu) { return complete_emulated_insn_gp(vcpu, vcpu->run->msr.error); } static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) { complete_userspace_rdmsr(vcpu); return complete_emulated_msr_access(vcpu); } static int complete_fast_msr_access(struct kvm_vcpu *vcpu) { return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error); } static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) { complete_userspace_rdmsr(vcpu); return complete_fast_msr_access(vcpu); } static u64 kvm_msr_reason(int r) { switch (r) { case KVM_MSR_RET_INVALID: return KVM_MSR_EXIT_REASON_UNKNOWN; case KVM_MSR_RET_FILTERED: return KVM_MSR_EXIT_REASON_FILTER; default: return KVM_MSR_EXIT_REASON_INVAL; } } static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u32 exit_reason, u64 data, int (*completion)(struct kvm_vcpu *vcpu), int r) { u64 msr_reason = kvm_msr_reason(r); /* Check if the user wanted to know about this MSR fault */ if (!(vcpu->kvm->arch.user_space_msr_mask & msr_reason)) return 0; vcpu->run->exit_reason = exit_reason; vcpu->run->msr.error = 0; memset(vcpu->run->msr.pad, 0, sizeof(vcpu->run->msr.pad)); vcpu->run->msr.reason = msr_reason; vcpu->run->msr.index = index; vcpu->run->msr.data = data; vcpu->arch.complete_userspace_io = completion; return 1; } int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = kvm_rcx_read(vcpu); u64 data; int r; r = kvm_get_msr_with_filter(vcpu, ecx, &data); if (!r) { trace_kvm_msr_read(ecx, data); kvm_rax_write(vcpu, data & -1u); kvm_rdx_write(vcpu, (data >> 32) & -1u); } else { /* MSR read failed? See if we should ask user space */ if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_RDMSR, 0, complete_fast_rdmsr, r)) return 0; trace_kvm_msr_read_ex(ecx); } return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr); int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) { u32 ecx = kvm_rcx_read(vcpu); u64 data = kvm_read_edx_eax(vcpu); int r; r = kvm_set_msr_with_filter(vcpu, ecx, data); if (!r) { trace_kvm_msr_write(ecx, data); } else { /* MSR write failed? See if we should ask user space */ if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_WRMSR, data, complete_fast_msr_access, r)) return 0; /* Signal all other negative errors to userspace */ if (r < 0) return r; trace_kvm_msr_write_ex(ecx, data); } return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); int kvm_emulate_as_nop(struct kvm_vcpu *vcpu) { return kvm_skip_emulated_instruction(vcpu); } int kvm_emulate_invd(struct kvm_vcpu *vcpu) { /* Treat an INVD instruction as a NOP and just skip it. */ return kvm_emulate_as_nop(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_invd); int kvm_handle_invalid_op(struct kvm_vcpu *vcpu) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } EXPORT_SYMBOL_GPL(kvm_handle_invalid_op); static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn) { if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) && !guest_cpuid_has(vcpu, X86_FEATURE_MWAIT)) return kvm_handle_invalid_op(vcpu); pr_warn_once("%s instruction emulated as NOP!\n", insn); return kvm_emulate_as_nop(vcpu); } int kvm_emulate_mwait(struct kvm_vcpu *vcpu) { return kvm_emulate_monitor_mwait(vcpu, "MWAIT"); } EXPORT_SYMBOL_GPL(kvm_emulate_mwait); int kvm_emulate_monitor(struct kvm_vcpu *vcpu) { return kvm_emulate_monitor_mwait(vcpu, "MONITOR"); } EXPORT_SYMBOL_GPL(kvm_emulate_monitor); static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) { xfer_to_guest_mode_prepare(); return vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending(); } /* * The fast path for frequent and performance sensitive wrmsr emulation, * i.e. the sending of IPI, sending IPI early in the VM-Exit flow reduces * the latency of virtual IPI by avoiding the expensive bits of transitioning * from guest to host, e.g. reacquiring KVM's SRCU lock. In contrast to the * other cases which must be called after interrupts are enabled on the host. */ static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data) { if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(vcpu->arch.apic)) return 1; if (((data & APIC_SHORT_MASK) == APIC_DEST_NOSHORT) && ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) && ((data & APIC_MODE_MASK) == APIC_DM_FIXED) && ((u32)(data >> 32) != X2APIC_BROADCAST)) return kvm_x2apic_icr_write(vcpu->arch.apic, data); return 1; } static int handle_fastpath_set_tscdeadline(struct kvm_vcpu *vcpu, u64 data) { if (!kvm_can_use_hv_timer(vcpu)) return 1; kvm_set_lapic_tscdeadline_msr(vcpu, data); return 0; } fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) { u32 msr = kvm_rcx_read(vcpu); u64 data; fastpath_t ret = EXIT_FASTPATH_NONE; kvm_vcpu_srcu_read_lock(vcpu); switch (msr) { case APIC_BASE_MSR + (APIC_ICR >> 4): data = kvm_read_edx_eax(vcpu); if (!handle_fastpath_set_x2apic_icr_irqoff(vcpu, data)) { kvm_skip_emulated_instruction(vcpu); ret = EXIT_FASTPATH_EXIT_HANDLED; } break; case MSR_IA32_TSC_DEADLINE: data = kvm_read_edx_eax(vcpu); if (!handle_fastpath_set_tscdeadline(vcpu, data)) { kvm_skip_emulated_instruction(vcpu); ret = EXIT_FASTPATH_REENTER_GUEST; } break; default: break; } if (ret != EXIT_FASTPATH_NONE) trace_kvm_msr_write(msr, data); kvm_vcpu_srcu_read_unlock(vcpu); return ret; } EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff); /* * Adapt set_msr() to msr_io()'s calling convention */ static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { return kvm_get_msr_ignored_check(vcpu, index, data, true); } static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { u64 val; /* * Disallow writes to immutable feature MSRs after KVM_RUN. KVM does * not support modifying the guest vCPU model on the fly, e.g. changing * the nVMX capabilities while L2 is running is nonsensical. Allow * writes of the same value, e.g. to allow userspace to blindly stuff * all MSRs when emulating RESET. */ if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index) && (do_get_msr(vcpu, index, &val) || *data != val)) return -EINVAL; return kvm_set_msr_ignored_check(vcpu, index, *data, true); } #ifdef CONFIG_X86_64 struct pvclock_clock { int vclock_mode; u64 cycle_last; u64 mask; u32 mult; u32 shift; u64 base_cycles; u64 offset; }; struct pvclock_gtod_data { seqcount_t seq; struct pvclock_clock clock; /* extract of a clocksource struct */ struct pvclock_clock raw_clock; /* extract of a clocksource struct */ ktime_t offs_boot; u64 wall_time_sec; }; static struct pvclock_gtod_data pvclock_gtod_data; static void update_pvclock_gtod(struct timekeeper *tk) { struct pvclock_gtod_data *vdata = &pvclock_gtod_data; write_seqcount_begin(&vdata->seq); /* copy pvclock gtod data */ vdata->clock.vclock_mode = tk->tkr_mono.clock->vdso_clock_mode; vdata->clock.cycle_last = tk->tkr_mono.cycle_last; vdata->clock.mask = tk->tkr_mono.mask; vdata->clock.mult = tk->tkr_mono.mult; vdata->clock.shift = tk->tkr_mono.shift; vdata->clock.base_cycles = tk->tkr_mono.xtime_nsec; vdata->clock.offset = tk->tkr_mono.base; vdata->raw_clock.vclock_mode = tk->tkr_raw.clock->vdso_clock_mode; vdata->raw_clock.cycle_last = tk->tkr_raw.cycle_last; vdata->raw_clock.mask = tk->tkr_raw.mask; vdata->raw_clock.mult = tk->tkr_raw.mult; vdata->raw_clock.shift = tk->tkr_raw.shift; vdata->raw_clock.base_cycles = tk->tkr_raw.xtime_nsec; vdata->raw_clock.offset = tk->tkr_raw.base; vdata->wall_time_sec = tk->xtime_sec; vdata->offs_boot = tk->offs_boot; write_seqcount_end(&vdata->seq); } static s64 get_kvmclock_base_ns(void) { /* Count up from boot time, but with the frequency of the raw clock. */ return ktime_to_ns(ktime_add(ktime_get_raw(), pvclock_gtod_data.offs_boot)); } #else static s64 get_kvmclock_base_ns(void) { /* Master clock not used, so we can just use CLOCK_BOOTTIME. */ return ktime_get_boottime_ns(); } #endif static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs) { int version; int r; struct pvclock_wall_clock wc; u32 wc_sec_hi; u64 wall_nsec; if (!wall_clock) return; r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version)); if (r) return; if (version & 1) ++version; /* first time write, random junk */ ++version; if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version))) return; wall_nsec = kvm_get_wall_clock_epoch(kvm); wc.nsec = do_div(wall_nsec, NSEC_PER_SEC); wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */ wc.version = version; kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); if (sec_hi_ofs) { wc_sec_hi = wall_nsec >> 32; kvm_write_guest(kvm, wall_clock + sec_hi_ofs, &wc_sec_hi, sizeof(wc_sec_hi)); } version++; kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); } static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, bool old_msr, bool host_initiated) { struct kvm_arch *ka = &vcpu->kvm->arch; if (vcpu->vcpu_id == 0 && !host_initiated) { if (ka->boot_vcpu_runs_old_kvmclock != old_msr) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); ka->boot_vcpu_runs_old_kvmclock = old_msr; } vcpu->arch.time = system_time; kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); /* we verify if the enable bit is set... */ if (system_time & 1) kvm_gpc_activate(&vcpu->arch.pv_time, system_time & ~1ULL, sizeof(struct pvclock_vcpu_time_info)); else kvm_gpc_deactivate(&vcpu->arch.pv_time); return; } static uint32_t div_frac(uint32_t dividend, uint32_t divisor) { do_shl32_div32(dividend, divisor); return dividend; } static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz, s8 *pshift, u32 *pmultiplier) { uint64_t scaled64; int32_t shift = 0; uint64_t tps64; uint32_t tps32; tps64 = base_hz; scaled64 = scaled_hz; while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) { tps64 >>= 1; shift--; } tps32 = (uint32_t)tps64; while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000ULL) { if (scaled64 & 0xffffffff00000000ULL || tps32 & 0x80000000) scaled64 >>= 1; else tps32 <<= 1; shift++; } *pshift = shift; *pmultiplier = div_frac(scaled64, tps32); } #ifdef CONFIG_X86_64 static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); #endif static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); static unsigned long max_tsc_khz; static u32 adjust_tsc_khz(u32 khz, s32 ppm) { u64 v = (u64)khz * (1000000 + ppm); do_div(v, 1000000); return v; } static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier); static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) { u64 ratio; /* Guest TSC same frequency as host TSC? */ if (!scale) { kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio); return 0; } /* TSC scaling supported? */ if (!kvm_caps.has_tsc_control) { if (user_tsc_khz > tsc_khz) { vcpu->arch.tsc_catchup = 1; vcpu->arch.tsc_always_catchup = 1; return 0; } else { pr_warn_ratelimited("user requested TSC rate below hardware speed\n"); return -1; } } /* TSC scaling required - calculate ratio */ ratio = mul_u64_u32_div(1ULL << kvm_caps.tsc_scaling_ratio_frac_bits, user_tsc_khz, tsc_khz); if (ratio == 0 || ratio >= kvm_caps.max_tsc_scaling_ratio) { pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", user_tsc_khz); return -1; } kvm_vcpu_write_tsc_multiplier(vcpu, ratio); return 0; } static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) { u32 thresh_lo, thresh_hi; int use_scaling = 0; /* tsc_khz can be zero if TSC calibration fails */ if (user_tsc_khz == 0) { /* set tsc_scaling_ratio to a safe value */ kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio); return -1; } /* Compute a scale to convert nanoseconds in TSC cycles */ kvm_get_time_scale(user_tsc_khz * 1000LL, NSEC_PER_SEC, &vcpu->arch.virtual_tsc_shift, &vcpu->arch.virtual_tsc_mult); vcpu->arch.virtual_tsc_khz = user_tsc_khz; /* * Compute the variation in TSC rate which is acceptable * within the range of tolerance and decide if the * rate being applied is within that bounds of the hardware * rate. If so, no scaling or compensation need be done. */ thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) { pr_debug("requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi); use_scaling = 1; } return set_tsc_khz(vcpu, user_tsc_khz, use_scaling); } static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) { u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec, vcpu->arch.virtual_tsc_mult, vcpu->arch.virtual_tsc_shift); tsc += vcpu->arch.this_tsc_write; return tsc; } #ifdef CONFIG_X86_64 static inline bool gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } #endif static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation) { #ifdef CONFIG_X86_64 struct kvm_arch *ka = &vcpu->kvm->arch; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; /* * To use the masterclock, the host clocksource must be based on TSC * and all vCPUs must have matching TSCs. Note, the count for matching * vCPUs doesn't include the reference vCPU, hence "+1". */ bool use_master_clock = (ka->nr_vcpus_matched_tsc + 1 == atomic_read(&vcpu->kvm->online_vcpus)) && gtod_is_based_on_tsc(gtod->clock.vclock_mode); /* * Request a masterclock update if the masterclock needs to be toggled * on/off, or when starting a new generation and the masterclock is * enabled (compute_guest_tsc() requires the masterclock snapshot to be * taken _after_ the new generation is created). */ if ((ka->use_master_clock && new_generation) || (ka->use_master_clock != use_master_clock)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, atomic_read(&vcpu->kvm->online_vcpus), ka->use_master_clock, gtod->clock.vclock_mode); #endif } /* * Multiply tsc by a fixed point number represented by ratio. * * The most significant 64-N bits (mult) of ratio represent the * integral part of the fixed point number; the remaining N bits * (frac) represent the fractional part, ie. ratio represents a fixed * point number (mult + frac * 2^(-N)). * * N equals to kvm_caps.tsc_scaling_ratio_frac_bits. */ static inline u64 __scale_tsc(u64 ratio, u64 tsc) { return mul_u64_u64_shr(tsc, ratio, kvm_caps.tsc_scaling_ratio_frac_bits); } u64 kvm_scale_tsc(u64 tsc, u64 ratio) { u64 _tsc = tsc; if (ratio != kvm_caps.default_tsc_scaling_ratio) _tsc = __scale_tsc(ratio, tsc); return _tsc; } static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) { u64 tsc; tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio); return target_tsc - tsc; } u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { return vcpu->arch.l1_tsc_offset + kvm_scale_tsc(host_tsc, vcpu->arch.l1_tsc_scaling_ratio); } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier) { u64 nested_offset; if (l2_multiplier == kvm_caps.default_tsc_scaling_ratio) nested_offset = l1_offset; else nested_offset = mul_s64_u64_shr((s64) l1_offset, l2_multiplier, kvm_caps.tsc_scaling_ratio_frac_bits); nested_offset += l2_offset; return nested_offset; } EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_offset); u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier) { if (l2_multiplier != kvm_caps.default_tsc_scaling_ratio) return mul_u64_u64_shr(l1_multiplier, l2_multiplier, kvm_caps.tsc_scaling_ratio_frac_bits); return l1_multiplier; } EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_multiplier); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset) { trace_kvm_write_tsc_offset(vcpu->vcpu_id, vcpu->arch.l1_tsc_offset, l1_offset); vcpu->arch.l1_tsc_offset = l1_offset; /* * If we are here because L1 chose not to trap WRMSR to TSC then * according to the spec this should set L1's TSC (as opposed to * setting L1's offset for L2). */ if (is_guest_mode(vcpu)) vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( l1_offset, static_call(kvm_x86_get_l2_tsc_offset)(vcpu), static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu)); else vcpu->arch.tsc_offset = l1_offset; static_call(kvm_x86_write_tsc_offset)(vcpu); } static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier) { vcpu->arch.l1_tsc_scaling_ratio = l1_multiplier; /* Userspace is changing the multiplier while L2 is active */ if (is_guest_mode(vcpu)) vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier( l1_multiplier, static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu)); else vcpu->arch.tsc_scaling_ratio = l1_multiplier; if (kvm_caps.has_tsc_control) static_call(kvm_x86_write_tsc_multiplier)(vcpu); } static inline bool kvm_check_tsc_unstable(void) { #ifdef CONFIG_X86_64 /* * TSC is marked unstable when we're running on Hyper-V, * 'TSC page' clocksource is good. */ if (pvclock_gtod_data.clock.vclock_mode == VDSO_CLOCKMODE_HVCLOCK) return false; #endif return check_tsc_unstable(); } /* * Infers attempts to synchronize the guest's tsc from host writes. Sets the * offset for the vcpu and tracks the TSC matching generation that the vcpu * participates in. */ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, u64 ns, bool matched) { struct kvm *kvm = vcpu->kvm; lockdep_assert_held(&kvm->arch.tsc_write_lock); /* * We also track th most recent recorded KHZ, write and time to * allow the matching interval to be extended at each write. */ kvm->arch.last_tsc_nsec = ns; kvm->arch.last_tsc_write = tsc; kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz; kvm->arch.last_tsc_offset = offset; vcpu->arch.last_guest_tsc = tsc; kvm_vcpu_write_tsc_offset(vcpu, offset); if (!matched) { /* * We split periods of matched TSC writes into generations. * For each generation, we track the original measured * nanosecond time, offset, and write, so if TSCs are in * sync, we can match exact offset, and if not, we can match * exact software computation in compute_guest_tsc() * * These values are tracked in kvm->arch.cur_xxx variables. */ kvm->arch.cur_tsc_generation++; kvm->arch.cur_tsc_nsec = ns; kvm->arch.cur_tsc_write = tsc; kvm->arch.cur_tsc_offset = offset; kvm->arch.nr_vcpus_matched_tsc = 0; } else if (vcpu->arch.this_tsc_generation != kvm->arch.cur_tsc_generation) { kvm->arch.nr_vcpus_matched_tsc++; } /* Keep track of which generation this VCPU has synchronized to */ vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation; vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; kvm_track_tsc_matching(vcpu, !matched); } static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) { u64 data = user_value ? *user_value : 0; struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; bool matched = false; bool synchronizing = false; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = kvm_compute_l1_tsc_offset(vcpu, data); ns = get_kvmclock_base_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; if (vcpu->arch.virtual_tsc_khz) { if (data == 0) { /* * Force synchronization when creating a vCPU, or when * userspace explicitly writes a zero value. */ synchronizing = true; } else if (kvm->arch.user_set_tsc) { u64 tsc_exp = kvm->arch.last_tsc_write + nsec_to_cycles(vcpu, elapsed); u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL; /* * Here lies UAPI baggage: when a user-initiated TSC write has * a small delta (1 second) of virtual cycle time against the * previously set vCPU, we assume that they were intended to be * in sync and the delta was only due to the racy nature of the * legacy API. * * This trick falls down when restoring a guest which genuinely * has been running for less time than the 1 second of imprecision * which we allow for in the legacy API. In this case, the first * value written by userspace (on any vCPU) should not be subject * to this 'correction' to make it sync up with values that only * come from the kernel's default vCPU creation. Make the 1-second * slop hack only trigger if the user_set_tsc flag is already set. */ synchronizing = data < tsc_exp + tsc_hz && data + tsc_hz > tsc_exp; } } if (user_value) kvm->arch.user_set_tsc = true; /* * For a reliable TSC, we can match TSC offsets, and for an unstable * TSC, we add elapsed time in this computation. We could let the * compensation code attempt to catch up if we fall behind, but * it's better to try to match offsets from the beginning. */ if (synchronizing && vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) { if (!kvm_check_tsc_unstable()) { offset = kvm->arch.cur_tsc_offset; } else { u64 delta = nsec_to_cycles(vcpu, elapsed); data += delta; offset = kvm_compute_l1_tsc_offset(vcpu, data); } matched = true; } __kvm_synchronize_tsc(vcpu, offset, data, ns, matched); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); } static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { u64 tsc_offset = vcpu->arch.l1_tsc_offset; kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment); } static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) { if (vcpu->arch.l1_tsc_scaling_ratio != kvm_caps.default_tsc_scaling_ratio) WARN_ON(adjustment < 0); adjustment = kvm_scale_tsc((u64) adjustment, vcpu->arch.l1_tsc_scaling_ratio); adjust_tsc_offset_guest(vcpu, adjustment); } #ifdef CONFIG_X86_64 static u64 read_tsc(void) { u64 ret = (u64)rdtsc_ordered(); u64 last = pvclock_gtod_data.clock.cycle_last; if (likely(ret >= last)) return ret; /* * GCC likes to generate cmov here, but this branch is extremely * predictable (it's just a function of time and the likely is * very likely) and there's a data dependence, so force GCC * to generate a branch instead. I don't barrier() because * we don't actually need a barrier, and if this function * ever gets inlined it will generate worse code. */ asm volatile (""); return last; } static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp, int *mode) { u64 tsc_pg_val; long v; switch (clock->vclock_mode) { case VDSO_CLOCKMODE_HVCLOCK: if (hv_read_tsc_page_tsc(hv_get_tsc_page(), tsc_timestamp, &tsc_pg_val)) { /* TSC page valid */ *mode = VDSO_CLOCKMODE_HVCLOCK; v = (tsc_pg_val - clock->cycle_last) & clock->mask; } else { /* TSC page invalid */ *mode = VDSO_CLOCKMODE_NONE; } break; case VDSO_CLOCKMODE_TSC: *mode = VDSO_CLOCKMODE_TSC; *tsc_timestamp = read_tsc(); v = (*tsc_timestamp - clock->cycle_last) & clock->mask; break; default: *mode = VDSO_CLOCKMODE_NONE; } if (*mode == VDSO_CLOCKMODE_NONE) *tsc_timestamp = v = 0; return v * clock->mult; } /* * As with get_kvmclock_base_ns(), this counts from boot time, at the * frequency of CLOCK_MONOTONIC_RAW (hence adding gtos->offs_boot). */ static int do_kvmclock_base(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; int mode; u64 ns; do { seq = read_seqcount_begin(>od->seq); ns = gtod->raw_clock.base_cycles; ns += vgettsc(>od->raw_clock, tsc_timestamp, &mode); ns >>= gtod->raw_clock.shift; ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot)); } while (unlikely(read_seqcount_retry(>od->seq, seq))); *t = ns; return mode; } /* * This calculates CLOCK_MONOTONIC at the time of the TSC snapshot, with * no boot time offset. */ static int do_monotonic(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; int mode; u64 ns; do { seq = read_seqcount_begin(>od->seq); ns = gtod->clock.base_cycles; ns += vgettsc(>od->clock, tsc_timestamp, &mode); ns >>= gtod->clock.shift; ns += ktime_to_ns(gtod->clock.offset); } while (unlikely(read_seqcount_retry(>od->seq, seq))); *t = ns; return mode; } static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; int mode; u64 ns; do { seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_sec; ns = gtod->clock.base_cycles; ns += vgettsc(>od->clock, tsc_timestamp, &mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns); ts->tv_nsec = ns; return mode; } /* * Calculates the kvmclock_base_ns (CLOCK_MONOTONIC_RAW + boot time) and * reports the TSC value from which it do so. Returns true if host is * using TSC based clocksource. */ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) { /* checked again under seqlock below */ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; return gtod_is_based_on_tsc(do_kvmclock_base(kernel_ns, tsc_timestamp)); } /* * Calculates CLOCK_MONOTONIC and reports the TSC value from which it did * so. Returns true if host is using TSC based clocksource. */ bool kvm_get_monotonic_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) { /* checked again under seqlock below */ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; return gtod_is_based_on_tsc(do_monotonic(kernel_ns, tsc_timestamp)); } /* * Calculates CLOCK_REALTIME and reports the TSC value from which it did * so. Returns true if host is using TSC based clocksource. * * DO NOT USE this for anything related to migration. You want CLOCK_TAI * for that. */ static bool kvm_get_walltime_and_clockread(struct timespec64 *ts, u64 *tsc_timestamp) { /* checked again under seqlock below */ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; return gtod_is_based_on_tsc(do_realtime(ts, tsc_timestamp)); } #endif /* * * Assuming a stable TSC across physical CPUS, and a stable TSC * across virtual CPUs, the following condition is possible. * Each numbered line represents an event visible to both * CPUs at the next numbered event. * * "timespecX" represents host monotonic time. "tscX" represents * RDTSC value. * * VCPU0 on CPU0 | VCPU1 on CPU1 * * 1. read timespec0,tsc0 * 2. | timespec1 = timespec0 + N * | tsc1 = tsc0 + M * 3. transition to guest | transition to guest * 4. ret0 = timespec0 + (rdtsc - tsc0) | * 5. | ret1 = timespec1 + (rdtsc - tsc1) * | ret1 = timespec0 + N + (rdtsc - (tsc0 + M)) * * Since ret0 update is visible to VCPU1 at time 5, to obey monotonicity: * * - ret0 < ret1 * - timespec0 + (rdtsc - tsc0) < timespec0 + N + (rdtsc - (tsc0 + M)) * ... * - 0 < N - M => M < N * * That is, when timespec0 != timespec1, M < N. Unfortunately that is not * always the case (the difference between two distinct xtime instances * might be smaller then the difference between corresponding TSC reads, * when updating guest vcpus pvclock areas). * * To avoid that problem, do not allow visibility of distinct * system_timestamp/tsc_timestamp values simultaneously: use a master * copy of host monotonic time values. Update that master copy * in lockstep. * * Rely on synchronization of host TSCs and guest TSCs for monotonicity. * */ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) { #ifdef CONFIG_X86_64 struct kvm_arch *ka = &kvm->arch; int vclock_mode; bool host_tsc_clocksource, vcpus_matched; lockdep_assert_held(&kvm->arch.tsc_write_lock); vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == atomic_read(&kvm->online_vcpus)); /* * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ host_tsc_clocksource = kvm_get_time_and_clockread( &ka->master_kernel_ns, &ka->master_cycle_now); ka->use_master_clock = host_tsc_clocksource && vcpus_matched && !ka->backwards_tsc_observed && !ka->boot_vcpu_runs_old_kvmclock; if (ka->use_master_clock) atomic_set(&kvm_guest_has_master_clock, 1); vclock_mode = pvclock_gtod_data.clock.vclock_mode; trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode, vcpus_matched); #endif } static void kvm_make_mclock_inprogress_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); } static void __kvm_start_pvclock_update(struct kvm *kvm) { raw_spin_lock_irq(&kvm->arch.tsc_write_lock); write_seqcount_begin(&kvm->arch.pvclock_sc); } static void kvm_start_pvclock_update(struct kvm *kvm) { kvm_make_mclock_inprogress_request(kvm); /* no guest entries from this point */ __kvm_start_pvclock_update(kvm); } static void kvm_end_pvclock_update(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct kvm_vcpu *vcpu; unsigned long i; write_seqcount_end(&ka->pvclock_sc); raw_spin_unlock_irq(&ka->tsc_write_lock); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); /* guest entries allowed */ kvm_for_each_vcpu(i, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); } static void kvm_update_masterclock(struct kvm *kvm) { kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); kvm_end_pvclock_update(kvm); } /* * Use the kernel's tsc_khz directly if the TSC is constant, otherwise use KVM's * per-CPU value (which may be zero if a CPU is going offline). Note, tsc_khz * can change during boot even if the TSC is constant, as it's possible for KVM * to be loaded before TSC calibration completes. Ideally, KVM would get a * notification when calibration completes, but practically speaking calibration * will complete before userspace is alive enough to create VMs. */ static unsigned long get_cpu_tsc_khz(void) { if (static_cpu_has(X86_FEATURE_CONSTANT_TSC)) return tsc_khz; else return __this_cpu_read(cpu_tsc_khz); } /* Called within read_seqcount_begin/retry for kvm->pvclock_sc. */ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); data->flags = 0; if (ka->use_master_clock && (static_cpu_has(X86_FEATURE_CONSTANT_TSC) || __this_cpu_read(cpu_tsc_khz))) { #ifdef CONFIG_X86_64 struct timespec64 ts; if (kvm_get_walltime_and_clockread(&ts, &data->host_tsc)) { data->realtime = ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec; data->flags |= KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC; } else #endif data->host_tsc = rdtsc(); data->flags |= KVM_CLOCK_TSC_STABLE; hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; kvm_get_time_scale(NSEC_PER_SEC, get_cpu_tsc_khz() * 1000LL, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc); } else { data->clock = get_kvmclock_base_ns() + ka->kvmclock_offset; } put_cpu(); } static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) { struct kvm_arch *ka = &kvm->arch; unsigned seq; do { seq = read_seqcount_begin(&ka->pvclock_sc); __get_kvmclock(kvm, data); } while (read_seqcount_retry(&ka->pvclock_sc, seq)); } u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_clock_data data; get_kvmclock(kvm, &data); return data.clock; } static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, struct gfn_to_pfn_cache *gpc, unsigned int offset, bool force_tsc_unstable) { struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info *guest_hv_clock; unsigned long flags; read_lock_irqsave(&gpc->lock, flags); while (!kvm_gpc_check(gpc, offset + sizeof(*guest_hv_clock))) { read_unlock_irqrestore(&gpc->lock, flags); if (kvm_gpc_refresh(gpc, offset + sizeof(*guest_hv_clock))) return; read_lock_irqsave(&gpc->lock, flags); } guest_hv_clock = (void *)(gpc->khva + offset); /* * This VCPU is paused, but it's legal for a guest to read another * VCPU's kvmclock, so we really have to follow the specification where * it says that version is odd if data is being modified, and even after * it is consistent. */ guest_hv_clock->version = vcpu->hv_clock.version = (guest_hv_clock->version + 1) | 1; smp_wmb(); /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ vcpu->hv_clock.flags |= (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED); if (vcpu->pvclock_set_guest_stopped_request) { vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED; vcpu->pvclock_set_guest_stopped_request = false; } memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock)); if (force_tsc_unstable) guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT; smp_wmb(); guest_hv_clock->version = ++vcpu->hv_clock.version; kvm_gpc_mark_dirty_in_slot(gpc); read_unlock_irqrestore(&gpc->lock, flags); trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); } static int kvm_guest_time_update(struct kvm_vcpu *v) { unsigned long flags, tgt_tsc_khz; unsigned seq; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; s64 kernel_ns; u64 tsc_timestamp, host_tsc; u8 pvclock_flags; bool use_master_clock; #ifdef CONFIG_KVM_XEN /* * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless * explicitly told to use TSC as its clocksource Xen will not set this bit. * This default behaviour led to bugs in some guest kernels which cause * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags. */ bool xen_pvclock_tsc_unstable = ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; #endif kernel_ns = 0; host_tsc = 0; /* * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ do { seq = read_seqcount_begin(&ka->pvclock_sc); use_master_clock = ka->use_master_clock; if (use_master_clock) { host_tsc = ka->master_cycle_now; kernel_ns = ka->master_kernel_ns; } } while (read_seqcount_retry(&ka->pvclock_sc, seq)); /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); tgt_tsc_khz = get_cpu_tsc_khz(); if (unlikely(tgt_tsc_khz == 0)) { local_irq_restore(flags); kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); return 1; } if (!use_master_clock) { host_tsc = rdtsc(); kernel_ns = get_kvmclock_base_ns(); } tsc_timestamp = kvm_read_l1_tsc(v, host_tsc); /* * We may have to catch up the TSC to match elapsed wall clock * time for two reasons, even if kvmclock is used. * 1) CPU could have been running below the maximum TSC rate * 2) Broken TSC compensation resets the base at each VCPU * entry to avoid unknown leaps of TSC even when running * again on the same CPU. This may cause apparent elapsed * time to disappear, and the guest to stand still or run * very slowly. */ if (vcpu->tsc_catchup) { u64 tsc = compute_guest_tsc(v, kernel_ns); if (tsc > tsc_timestamp) { adjust_tsc_offset_guest(v, tsc - tsc_timestamp); tsc_timestamp = tsc; } } local_irq_restore(flags); /* With all the info we got, fill in the values */ if (kvm_caps.has_tsc_control) tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz, v->arch.l1_tsc_scaling_ratio); if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) { kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL, &vcpu->hv_clock.tsc_shift, &vcpu->hv_clock.tsc_to_system_mul); vcpu->hw_tsc_khz = tgt_tsc_khz; kvm_xen_update_tsc_info(v); } vcpu->hv_clock.tsc_timestamp = tsc_timestamp; vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_guest_tsc = tsc_timestamp; /* If the host uses TSC clocksource, then it is stable */ pvclock_flags = 0; if (use_master_clock) pvclock_flags |= PVCLOCK_TSC_STABLE_BIT; vcpu->hv_clock.flags = pvclock_flags; if (vcpu->pv_time.active) kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false); #ifdef CONFIG_KVM_XEN if (vcpu->xen.vcpu_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache, offsetof(struct compat_vcpu_info, time), xen_pvclock_tsc_unstable); if (vcpu->xen.vcpu_time_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0, xen_pvclock_tsc_unstable); #endif kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } /* * The pvclock_wall_clock ABI tells the guest the wall clock time at * which it started (i.e. its epoch, when its kvmclock was zero). * * In fact those clocks are subtly different; wall clock frequency is * adjusted by NTP and has leap seconds, while the kvmclock is a * simple function of the TSC without any such adjustment. * * Perhaps the ABI should have exposed CLOCK_TAI and a ratio between * that and kvmclock, but even that would be subject to change over * time. * * Attempt to calculate the epoch at a given moment using the *same* * TSC reading via kvm_get_walltime_and_clockread() to obtain both * wallclock and kvmclock times, and subtracting one from the other. * * Fall back to using their values at slightly different moments by * calling ktime_get_real_ns() and get_kvmclock_ns() separately. */ uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm) { #ifdef CONFIG_X86_64 struct pvclock_vcpu_time_info hv_clock; struct kvm_arch *ka = &kvm->arch; unsigned long seq, local_tsc_khz; struct timespec64 ts; uint64_t host_tsc; do { seq = read_seqcount_begin(&ka->pvclock_sc); local_tsc_khz = 0; if (!ka->use_master_clock) break; /* * The TSC read and the call to get_cpu_tsc_khz() must happen * on the same CPU. */ get_cpu(); local_tsc_khz = get_cpu_tsc_khz(); if (local_tsc_khz && !kvm_get_walltime_and_clockread(&ts, &host_tsc)) local_tsc_khz = 0; /* Fall back to old method */ put_cpu(); /* * These values must be snapshotted within the seqcount loop. * After that, it's just mathematics which can happen on any * CPU at any time. */ hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; } while (read_seqcount_retry(&ka->pvclock_sc, seq)); /* * If the conditions were right, and obtaining the wallclock+TSC was * successful, calculate the KVM clock at the corresponding time and * subtract one from the other to get the guest's epoch in nanoseconds * since 1970-01-01. */ if (local_tsc_khz) { kvm_get_time_scale(NSEC_PER_SEC, local_tsc_khz * NSEC_PER_USEC, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); return ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec - __pvclock_read_cycles(&hv_clock, host_tsc); } #endif return ktime_get_real_ns() - get_kvmclock_ns(kvm); } /* * kvmclock updates which are isolated to a given vcpu, such as * vcpu->cpu migration, should not allow system_timestamp from * the rest of the vcpus to remain static. Otherwise ntp frequency * correction applies to one vcpu's system_timestamp but not * the others. * * So in those cases, request a kvmclock update for all vcpus. * We need to rate-limit these requests though, as they can * considerably slow guests that have a large number of vcpus. * The time for a remote vcpu to update its kvmclock is bound * by the delay we use to rate-limit the updates. */ #define KVMCLOCK_UPDATE_DELAY msecs_to_jiffies(100) static void kvmclock_update_fn(struct work_struct *work) { unsigned long i; struct delayed_work *dwork = to_delayed_work(work); struct kvm_arch *ka = container_of(dwork, struct kvm_arch, kvmclock_update_work); struct kvm *kvm = container_of(ka, struct kvm, arch); struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); kvm_vcpu_kick(vcpu); } } static void kvm_gen_kvmclock_update(struct kvm_vcpu *v) { struct kvm *kvm = v->kvm; kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); schedule_delayed_work(&kvm->arch.kvmclock_update_work, KVMCLOCK_UPDATE_DELAY); } #define KVMCLOCK_SYNC_PERIOD (300 * HZ) static void kvmclock_sync_fn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct kvm_arch *ka = container_of(dwork, struct kvm_arch, kvmclock_sync_work); struct kvm *kvm = container_of(ka, struct kvm, arch); schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); } /* These helpers are safe iff @msr is known to be an MCx bank MSR. */ static bool is_mci_control_msr(u32 msr) { return (msr & 3) == 0; } static bool is_mci_status_msr(u32 msr) { return (msr & 3) == 1; } /* * On AMD, HWCR[McStatusWrEn] controls whether setting MCi_STATUS results in #GP. */ static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ if (guest_cpuid_is_amd_compatible(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; } static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u64 mcg_cap = vcpu->arch.mcg_cap; unsigned bank_num = mcg_cap & 0xff; u32 msr = msr_info->index; u64 data = msr_info->data; u32 offset, last_msr; switch (msr) { case MSR_IA32_MCG_STATUS: vcpu->arch.mcg_status = data; break; case MSR_IA32_MCG_CTL: if (!(mcg_cap & MCG_CTL_P) && (data || !msr_info->host_initiated)) return 1; if (data != 0 && data != ~(u64)0) return 1; vcpu->arch.mcg_ctl = data; break; case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: last_msr = MSR_IA32_MCx_CTL2(bank_num) - 1; if (msr > last_msr) return 1; if (!(mcg_cap & MCG_CMCI_P) && (data || !msr_info->host_initiated)) return 1; /* An attempt to write a 1 to a reserved bit raises #GP */ if (data & ~(MCI_CTL2_CMCI_EN | MCI_CTL2_CMCI_THRESHOLD_MASK)) return 1; offset = array_index_nospec(msr - MSR_IA32_MC0_CTL2, last_msr + 1 - MSR_IA32_MC0_CTL2); vcpu->arch.mci_ctl2_banks[offset] = data; break; case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: last_msr = MSR_IA32_MCx_CTL(bank_num) - 1; if (msr > last_msr) return 1; /* * Only 0 or all 1s can be written to IA32_MCi_CTL, all other * values are architecturally undefined. But, some Linux * kernels clear bit 10 in bank 4 to workaround a BIOS/GART TLB * issue on AMD K8s, allow bit 10 to be clear when setting all * other bits in order to avoid an uncaught #GP in the guest. * * UNIXWARE clears bit 0 of MC1_CTL to ignore correctable, * single-bit ECC data errors. */ if (is_mci_control_msr(msr) && data != 0 && (data | (1 << 10) | 1) != ~(u64)0) return 1; /* * All CPUs allow writing 0 to MCi_STATUS MSRs to clear the MSR. * AMD-based CPUs allow non-zero values, but if and only if * HWCR[McStatusWrEn] is set. */ if (!msr_info->host_initiated && is_mci_status_msr(msr) && data != 0 && !can_set_mci_status(vcpu)) return 1; offset = array_index_nospec(msr - MSR_IA32_MC0_CTL, last_msr + 1 - MSR_IA32_MC0_CTL); vcpu->arch.mce_banks[offset] = data; break; default: return 1; } return 0; } static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) { u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; return (vcpu->arch.apf.msr_en_val & mask) == mask; } static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; /* Bits 4:5 are reserved, Should be zero */ if (data & 0x30) return 1; if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_VMEXIT) && (data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT)) return 1; if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT) && (data & KVM_ASYNC_PF_DELIVERY_AS_INT)) return 1; if (!lapic_in_kernel(vcpu)) return data ? 1 : 0; vcpu->arch.apf.msr_en_val = data; if (!kvm_pv_async_pf_enabled(vcpu)) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); return 0; } if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, sizeof(u64))) return 1; vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; kvm_async_pf_wakeup_all(vcpu); return 0; } static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data) { /* Bits 8-63 are reserved */ if (data >> 8) return 1; if (!lapic_in_kernel(vcpu)) return 1; vcpu->arch.apf.msr_int_val = data; vcpu->arch.apf.vec = data & KVM_ASYNC_PF_VEC_MASK; return 0; } static void kvmclock_reset(struct kvm_vcpu *vcpu) { kvm_gpc_deactivate(&vcpu->arch.pv_time); vcpu->arch.time = 0; } static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; static_call(kvm_x86_flush_tlb_all)(vcpu); /* Flushing all ASIDs flushes the current ASID... */ kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; if (!tdp_enabled) { /* * A TLB flush on behalf of the guest is equivalent to * INVPCID(all), toggling CR4.PGE, etc., which requires * a forced sync of the shadow page tables. Ensure all the * roots are synced and the guest TLB in hardware is clean. */ kvm_mmu_sync_roots(vcpu); kvm_mmu_sync_prev_roots(vcpu); } static_call(kvm_x86_flush_tlb_guest)(vcpu); /* * Flushing all "guest" TLB is always a superset of Hyper-V's fine * grained flushing. */ kvm_hv_vcpu_purge_flush_tlb(vcpu); } static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; static_call(kvm_x86_flush_tlb_current)(vcpu); } /* * Service "local" TLB flush requests, which are specific to the current MMU * context. In addition to the generic event handling in vcpu_enter_guest(), * TLB flushes that are targeted at an MMU context also need to be serviced * prior before nested VM-Enter/VM-Exit. */ void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu) { if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); } EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests); static void record_steal_time(struct kvm_vcpu *vcpu) { struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; struct kvm_steal_time __user *st; struct kvm_memslots *slots; gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; u64 steal; u32 version; if (kvm_xen_msr_enabled(vcpu->kvm)) { kvm_xen_runstate_set_running(vcpu); return; } if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; if (WARN_ON_ONCE(current->mm != vcpu->kvm->mm)) return; slots = kvm_memslots(vcpu->kvm); if (unlikely(slots->generation != ghc->generation || gpa != ghc->gpa || kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { /* We rely on the fact that it fits in a single page. */ BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS); if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st)) || kvm_is_error_hva(ghc->hva) || !ghc->memslot) return; } st = (struct kvm_steal_time __user *)ghc->hva; /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { u8 st_preempted = 0; int err = -EFAULT; if (!user_access_begin(st, sizeof(*st))) return; asm volatile("1: xchgb %0, %2\n" "xor %1, %1\n" "2:\n" _ASM_EXTABLE_UA(1b, 2b) : "+q" (st_preempted), "+&r" (err), "+m" (st->preempted)); if (err) goto out; user_access_end(); vcpu->arch.st.preempted = 0; trace_kvm_pv_tlb_flush(vcpu->vcpu_id, st_preempted & KVM_VCPU_FLUSH_TLB); if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); if (!user_access_begin(st, sizeof(*st))) goto dirty; } else { if (!user_access_begin(st, sizeof(*st))) return; unsafe_put_user(0, &st->preempted, out); vcpu->arch.st.preempted = 0; } unsafe_get_user(version, &st->version, out); if (version & 1) version += 1; /* first time write, random junk */ version += 1; unsafe_put_user(version, &st->version, out); smp_wmb(); unsafe_get_user(steal, &st->steal, out); steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; unsafe_put_user(steal, &st->steal, out); version += 1; unsafe_put_user(version, &st->version, out); out: user_access_end(); dirty: mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } static bool kvm_is_msr_to_save(u32 msr_index) { unsigned int i; for (i = 0; i < num_msrs_to_save; i++) { if (msrs_to_save[i] == msr_index) return true; } return false; } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u32 msr = msr_info->index; u64 data = msr_info->data; if (msr && msr == vcpu->kvm->arch.xen_hvm_config.msr) return kvm_xen_write_hypercall_page(vcpu, data); switch (msr) { case MSR_AMD64_NB_CFG: case MSR_IA32_UCODE_WRITE: case MSR_VM_HSAVE_PA: case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: break; case MSR_IA32_UCODE_REV: if (msr_info->host_initiated) vcpu->arch.microcode_version = data; break; case MSR_IA32_ARCH_CAPABILITIES: if (!msr_info->host_initiated) return 1; vcpu->arch.arch_capabilities = data; break; case MSR_IA32_PERF_CAPABILITIES: if (!msr_info->host_initiated) return 1; if (data & ~kvm_caps.supported_perf_cap) return 1; /* * Note, this is not just a performance optimization! KVM * disallows changing feature MSRs after the vCPU has run; PMU * refresh will bug the VM if called after the vCPU has run. */ if (vcpu->arch.perf_capabilities == data) break; vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); break; case MSR_IA32_PRED_CMD: { u64 reserved_bits = ~(PRED_CMD_IBPB | PRED_CMD_SBPB); if (!msr_info->host_initiated) { if ((!guest_has_pred_cmd_msr(vcpu))) return 1; if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) reserved_bits |= PRED_CMD_IBPB; if (!guest_cpuid_has(vcpu, X86_FEATURE_SBPB)) reserved_bits |= PRED_CMD_SBPB; } if (!boot_cpu_has(X86_FEATURE_IBPB)) reserved_bits |= PRED_CMD_IBPB; if (!boot_cpu_has(X86_FEATURE_SBPB)) reserved_bits |= PRED_CMD_SBPB; if (data & reserved_bits) return 1; if (!data) break; wrmsrl(MSR_IA32_PRED_CMD, data); break; } case MSR_IA32_FLUSH_CMD: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)) return 1; if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D) || (data & ~L1D_FLUSH)) return 1; if (!data) break; wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); break; case MSR_EFER: return set_efer(vcpu, msr_info); case MSR_K7_HWCR: data &= ~(u64)0x40; /* ignore flush filter disable */ data &= ~(u64)0x100; /* ignore ignne emulation enable */ data &= ~(u64)0x8; /* ignore TLB cache disable */ /* * Allow McStatusWrEn and TscFreqSel. (Linux guests from v3.2 * through at least v6.6 whine if TscFreqSel is clear, * depending on F/M/S. */ if (data & ~(BIT_ULL(18) | BIT_ULL(24))) { kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } vcpu->arch.msr_hwcr = data; break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; case MSR_IA32_CR_PAT: if (!kvm_pat_valid(data)) return 1; vcpu->arch.pat = data; break; case MTRRphysBase_MSR(0) ... MSR_MTRRfix4K_F8000: case MSR_MTRRdefType: return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSC_DEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); break; case MSR_IA32_TSC_ADJUST: if (guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST)) { if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; adjust_tsc_offset_guest(vcpu, adj); /* Before back to guest, tsc_timestamp must be adjusted * as well, otherwise guest's percpu pvclock time could jump. */ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); } vcpu->arch.ia32_tsc_adjust_msr = data; } break; case MSR_IA32_MISC_ENABLE: { u64 old_val = vcpu->arch.ia32_misc_enable_msr; if (!msr_info->host_initiated) { /* RO bits */ if ((old_val ^ data) & MSR_IA32_MISC_ENABLE_PMU_RO_MASK) return 1; /* R bits, i.e. writes are ignored, but don't fault. */ data = data & ~MSR_IA32_MISC_ENABLE_EMON; data |= old_val & MSR_IA32_MISC_ENABLE_EMON; } if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT) && ((old_val ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) { if (!guest_cpuid_has(vcpu, X86_FEATURE_XMM3)) return 1; vcpu->arch.ia32_misc_enable_msr = data; kvm_update_cpuid_runtime(vcpu); } else { vcpu->arch.ia32_misc_enable_msr = data; } break; } case MSR_IA32_SMBASE: if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated) return 1; vcpu->arch.smbase = data; break; case MSR_IA32_POWER_CTL: vcpu->arch.msr_ia32_power_ctl = data; break; case MSR_IA32_TSC: if (msr_info->host_initiated) { kvm_synchronize_tsc(vcpu, &data); } else { u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); vcpu->arch.ia32_tsc_adjust_msr += adj; } break; case MSR_IA32_XSS: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) return 1; /* * KVM supports exposing PT to the guest, but does not support * IA32_XSS[bit 8]. Guests have to use RDMSR/WRMSR rather than * XSAVES/XRSTORS to save/restore PT MSRs. */ if (data & ~kvm_caps.supported_xss) return 1; vcpu->arch.ia32_xss = data; kvm_update_cpuid_runtime(vcpu); break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) return 1; vcpu->arch.smi_count = data; break; case MSR_KVM_WALL_CLOCK_NEW: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) return 1; vcpu->kvm->arch.wall_clock = data; kvm_write_wall_clock(vcpu->kvm, data, 0); break; case MSR_KVM_WALL_CLOCK: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) return 1; vcpu->kvm->arch.wall_clock = data; kvm_write_wall_clock(vcpu->kvm, data, 0); break; case MSR_KVM_SYSTEM_TIME_NEW: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) return 1; kvm_write_system_time(vcpu, data, false, msr_info->host_initiated); break; case MSR_KVM_SYSTEM_TIME: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) return 1; kvm_write_system_time(vcpu, data, true, msr_info->host_initiated); break; case MSR_KVM_ASYNC_PF_EN: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) return 1; if (kvm_pv_enable_async_pf(vcpu, data)) return 1; break; case MSR_KVM_ASYNC_PF_INT: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; if (kvm_pv_enable_async_pf_int(vcpu, data)) return 1; break; case MSR_KVM_ASYNC_PF_ACK: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; if (data & 0x1) { vcpu->arch.apf.pageready_pending = false; kvm_check_async_pf_completion(vcpu); } break; case MSR_KVM_STEAL_TIME: if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME)) return 1; if (unlikely(!sched_info_on())) return 1; if (data & KVM_STEAL_RESERVED_MASK) return 1; vcpu->arch.st.msr_val = data; if (!(data & KVM_MSR_ENABLED)) break; kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); break; case MSR_KVM_PV_EOI_EN: if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) return 1; if (kvm_lapic_set_pv_eoi(vcpu, data, sizeof(u8))) return 1; break; case MSR_KVM_POLL_CONTROL: if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL)) return 1; /* only enable bit supported */ if (data & (-1ULL << 1)) return 1; vcpu->arch.msr_kvm_poll_control = data; break; case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: return set_msr_mce(vcpu, msr_info); case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); if (data) kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_K7_CLK_CTL: /* * Ignore all writes to this no longer documented MSR. * Writes are only relevant for old K7 processors, * all pre-dating SVM, but a recommended workaround from * AMD for these chips. It is possible to specify the * affected processor models on the command line, hence * the need to ignore the workaround. */ break; #ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); #endif case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. */ kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) return 1; vcpu->arch.osvw.length = data; break; case MSR_AMD64_OSVW_STATUS: if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) return 1; vcpu->arch.osvw.status = data; break; case MSR_PLATFORM_INFO: if (!msr_info->host_initiated || (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) && cpuid_fault_enabled(vcpu))) return 1; vcpu->arch.msr_platform_info = data; break; case MSR_MISC_FEATURES_ENABLES: if (data & ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT || (data & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT && !supports_cpuid_fault(vcpu))) return 1; vcpu->arch.msr_misc_features_enables = data; break; #ifdef CONFIG_X86_64 case MSR_IA32_XFD: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data); break; case MSR_IA32_XFD_ERR: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; vcpu->arch.guest_fpu.xfd_err = data; break; #endif default: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); /* * Userspace is allowed to write '0' to MSRs that KVM reports * as to-be-saved, even if an MSRs isn't fully supported. */ if (msr_info->host_initiated && !data && kvm_is_msr_to_save(msr)) break; return KVM_MSR_RET_INVALID; } return 0; } EXPORT_SYMBOL_GPL(kvm_set_msr_common); static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { u64 data; u64 mcg_cap = vcpu->arch.mcg_cap; unsigned bank_num = mcg_cap & 0xff; u32 offset, last_msr; switch (msr) { case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: data = 0; break; case MSR_IA32_MCG_CAP: data = vcpu->arch.mcg_cap; break; case MSR_IA32_MCG_CTL: if (!(mcg_cap & MCG_CTL_P) && !host) return 1; data = vcpu->arch.mcg_ctl; break; case MSR_IA32_MCG_STATUS: data = vcpu->arch.mcg_status; break; case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: last_msr = MSR_IA32_MCx_CTL2(bank_num) - 1; if (msr > last_msr) return 1; if (!(mcg_cap & MCG_CMCI_P) && !host) return 1; offset = array_index_nospec(msr - MSR_IA32_MC0_CTL2, last_msr + 1 - MSR_IA32_MC0_CTL2); data = vcpu->arch.mci_ctl2_banks[offset]; break; case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: last_msr = MSR_IA32_MCx_CTL(bank_num) - 1; if (msr > last_msr) return 1; offset = array_index_nospec(msr - MSR_IA32_MC0_CTL, last_msr + 1 - MSR_IA32_MC0_CTL); data = vcpu->arch.mce_banks[offset]; break; default: return 1; } *pdata = data; return 0; } int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { switch (msr_info->index) { case MSR_IA32_PLATFORM_ID: case MSR_IA32_EBL_CR_POWERON: case MSR_IA32_LASTBRANCHFROMIP: case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: case MSR_AMD64_SYSCFG: case MSR_K8_TSEG_ADDR: case MSR_K8_TSEG_MASK: case MSR_VM_HSAVE_PA: case MSR_K8_INT_PENDING_MSG: case MSR_AMD64_NB_CFG: case MSR_FAM10H_MMIO_CONF_BASE: case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: /* * Intel Sandy Bridge CPUs must support the RAPL (running average power * limit) MSRs. Just return 0, as we do not want to expose the host * data here. Do not conditionalize this on CPUID, as KVM does not do * so for existing CPU-specific MSRs. */ case MSR_RAPL_POWER_UNIT: case MSR_PP0_ENERGY_STATUS: /* Power plane 0 (core) */ case MSR_PP1_ENERGY_STATUS: /* Power plane 1 (graphics uncore) */ case MSR_PKG_ENERGY_STATUS: /* Total package */ case MSR_DRAM_ENERGY_STATUS: /* DRAM controller */ msr_info->data = 0; break; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); msr_info->data = 0; break; case MSR_IA32_UCODE_REV: msr_info->data = vcpu->arch.microcode_version; break; case MSR_IA32_ARCH_CAPABILITIES: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) return 1; msr_info->data = vcpu->arch.arch_capabilities; break; case MSR_IA32_PERF_CAPABILITIES: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) return 1; msr_info->data = vcpu->arch.perf_capabilities; break; case MSR_IA32_POWER_CTL: msr_info->data = vcpu->arch.msr_ia32_power_ctl; break; case MSR_IA32_TSC: { /* * Intel SDM states that MSR_IA32_TSC read adds the TSC offset * even when not intercepted. AMD manual doesn't explicitly * state this but appears to behave the same. * * On userspace reads and writes, however, we unconditionally * return L1's TSC value to ensure backwards-compatible * behavior for migration. */ u64 offset, ratio; if (msr_info->host_initiated) { offset = vcpu->arch.l1_tsc_offset; ratio = vcpu->arch.l1_tsc_scaling_ratio; } else { offset = vcpu->arch.tsc_offset; ratio = vcpu->arch.tsc_scaling_ratio; } msr_info->data = kvm_scale_tsc(rdtsc(), ratio) + offset; break; } case MSR_IA32_CR_PAT: msr_info->data = vcpu->arch.pat; break; case MSR_MTRRcap: case MTRRphysBase_MSR(0) ... MSR_MTRRfix4K_F8000: case MSR_MTRRdefType: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); case 0xcd: /* fsb frequency */ msr_info->data = 3; break; /* * MSR_EBC_FREQUENCY_ID * Conservative value valid for even the basic CPU models. * Models 0,1: 000 in bits 23:21 indicating a bus speed of * 100MHz, model 2 000 in bits 18:16 indicating 100MHz, * and 266MHz for model 3, or 4. Set Core Clock * Frequency to System Bus Frequency Ratio to 1 (bits * 31:24) even though these are only valid for CPU * models > 2, however guests may end up dividing or * multiplying by zero otherwise. */ case MSR_EBC_FREQUENCY_ID: msr_info->data = 1 << 24; break; case MSR_IA32_APICBASE: msr_info->data = kvm_get_apic_base(vcpu); break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); case MSR_IA32_TSC_DEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; case MSR_IA32_TSC_ADJUST: msr_info->data = (u64)vcpu->arch.ia32_tsc_adjust_msr; break; case MSR_IA32_MISC_ENABLE: msr_info->data = vcpu->arch.ia32_misc_enable_msr; break; case MSR_IA32_SMBASE: if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated) return 1; msr_info->data = vcpu->arch.smbase; break; case MSR_SMI_COUNT: msr_info->data = vcpu->arch.smi_count; break; case MSR_IA32_PERF_STATUS: /* TSC increment by tick */ msr_info->data = 1000ULL; /* CPU multiplier */ msr_info->data |= (((uint64_t)4ULL) << 40); break; case MSR_EFER: msr_info->data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) return 1; msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_WALL_CLOCK_NEW: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) return 1; msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) return 1; msr_info->data = vcpu->arch.time; break; case MSR_KVM_SYSTEM_TIME_NEW: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) return 1; msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) return 1; msr_info->data = vcpu->arch.apf.msr_en_val; break; case MSR_KVM_ASYNC_PF_INT: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; msr_info->data = vcpu->arch.apf.msr_int_val; break; case MSR_KVM_ASYNC_PF_ACK: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; msr_info->data = 0; break; case MSR_KVM_STEAL_TIME: if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME)) return 1; msr_info->data = vcpu->arch.st.msr_val; break; case MSR_KVM_PV_EOI_EN: if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) return 1; msr_info->data = vcpu->arch.pv_eoi.msr_val; break; case MSR_KVM_POLL_CONTROL: if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL)) return 1; msr_info->data = vcpu->arch.msr_kvm_poll_control; break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: case MSR_IA32_MCG_CAP: case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: return get_msr_mce(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); case MSR_IA32_XSS: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) return 1; msr_info->data = vcpu->arch.ia32_xss; break; case MSR_K7_CLK_CTL: /* * Provide expected ramp-up count for K7. All other * are set to zero, indicating minimum divisors for * every field. * * This prevents guest kernels on AMD host with CPU * type 6, model 8 and higher from exploding due to * the rdmsr failing. */ msr_info->data = 0x20000000; break; #ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); #endif case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current * silicon. It is however accessed by winxp in very narrow * scenarios where it sets bit #19, itself documented as * a "reserved" bit. Best effort attempt to source coherent * read data here should the balance of the register be * interpreted by the guest: * * L2 cache control register 3: 64GB range, 256KB size, * enabled, latency 0x1, configured */ msr_info->data = 0xbe702111; break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) return 1; msr_info->data = vcpu->arch.osvw.length; break; case MSR_AMD64_OSVW_STATUS: if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) return 1; msr_info->data = vcpu->arch.osvw.status; break; case MSR_PLATFORM_INFO: if (!msr_info->host_initiated && !vcpu->kvm->arch.guest_can_read_msr_platform_info) return 1; msr_info->data = vcpu->arch.msr_platform_info; break; case MSR_MISC_FEATURES_ENABLES: msr_info->data = vcpu->arch.msr_misc_features_enables; break; case MSR_K7_HWCR: msr_info->data = vcpu->arch.msr_hwcr; break; #ifdef CONFIG_X86_64 case MSR_IA32_XFD: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; msr_info->data = vcpu->arch.guest_fpu.fpstate->xfd; break; case MSR_IA32_XFD_ERR: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; msr_info->data = vcpu->arch.guest_fpu.xfd_err; break; #endif default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); /* * Userspace is allowed to read MSRs that KVM reports as * to-be-saved, even if an MSR isn't fully supported. */ if (msr_info->host_initiated && kvm_is_msr_to_save(msr_info->index)) { msr_info->data = 0; break; } return KVM_MSR_RET_INVALID; } return 0; } EXPORT_SYMBOL_GPL(kvm_get_msr_common); /* * Read or write a bunch of msrs. All parameters are kernel addresses. * * @return number of msrs set successfully. */ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, struct kvm_msr_entry *entries, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data)) { int i; for (i = 0; i < msrs->nmsrs; ++i) if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; return i; } /* * Read or write a bunch of msrs. Parameters are user addresses. * * @return number of msrs set successfully. */ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data), int writeback) { struct kvm_msrs msrs; struct kvm_msr_entry *entries; unsigned size; int r; r = -EFAULT; if (copy_from_user(&msrs, user_msrs, sizeof(msrs))) goto out; r = -E2BIG; if (msrs.nmsrs >= MAX_IO_MSRS) goto out; size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; entries = memdup_user(user_msrs->entries, size); if (IS_ERR(entries)) { r = PTR_ERR(entries); goto out; } r = __msr_io(vcpu, &msrs, entries, do_msr); if (writeback && copy_to_user(user_msrs->entries, entries, size)) r = -EFAULT; kfree(entries); out: return r; } static inline bool kvm_can_mwait_in_guest(void) { return boot_cpu_has(X86_FEATURE_MWAIT) && !boot_cpu_has_bug(X86_BUG_MONITOR) && boot_cpu_has(X86_FEATURE_ARAT); } #ifdef CONFIG_KVM_HYPERV static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 __user *cpuid_arg) { struct kvm_cpuid2 cpuid; int r; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) return r; r = kvm_get_hv_cpuid(vcpu, &cpuid, cpuid_arg->entries); if (r) return r; r = -EFAULT; if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) return r; return 0; } #endif static bool kvm_is_vm_type_supported(unsigned long type) { return type < 32 && (kvm_caps.supported_vm_types & BIT(type)); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r = 0; switch (ext) { case KVM_CAP_IRQCHIP: case KVM_CAP_HLT: case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: case KVM_CAP_EXT_EMUL_CPUID: case KVM_CAP_CLOCKSOURCE: case KVM_CAP_PIT: case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: case KVM_CAP_SYNC_MMU: case KVM_CAP_USER_NMI: case KVM_CAP_REINJECT_CONTROL: case KVM_CAP_IRQ_INJECT_STATUS: case KVM_CAP_IOEVENTFD: case KVM_CAP_IOEVENTFD_NO_LENGTH: case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_VCPU_EVENTS: #ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: case KVM_CAP_HYPERV_TIME: case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_HYPERV_SYNIC2: case KVM_CAP_HYPERV_VP_INDEX: case KVM_CAP_HYPERV_EVENTFD: case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: case KVM_CAP_HYPERV_CPUID: case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: #endif case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: case KVM_CAP_XSAVE: case KVM_CAP_ASYNC_PF: case KVM_CAP_ASYNC_PF_INT: case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_KVMCLOCK_CTRL: case KVM_CAP_READONLY_MEM: case KVM_CAP_IOAPIC_POLARITY_IGNORED: case KVM_CAP_TSC_DEADLINE_TIMER: case KVM_CAP_DISABLE_QUIRKS: case KVM_CAP_SET_BOOT_CPU_ID: case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_PMU_EVENT_FILTER: case KVM_CAP_PMU_EVENT_MASKED_EVENTS: case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: case KVM_CAP_X86_TRIPLE_FAULT_EVENT: case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_LAST_CPU: case KVM_CAP_X86_USER_SPACE_MSR: case KVM_CAP_X86_MSR_FILTER: case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: #ifdef CONFIG_X86_SGX_KVM case KVM_CAP_SGX_ATTRIBUTE: #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_SYS_ATTRIBUTES: case KVM_CAP_VAPIC: case KVM_CAP_ENABLE_CAP: case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: case KVM_CAP_IRQFD_RESAMPLE: case KVM_CAP_MEMORY_FAULT_INFO: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: r = KVM_EXIT_HYPERCALL_VALID_MASK; break; case KVM_CAP_SET_GUEST_DEBUG2: return KVM_GUESTDBG_VALID_MASK; #ifdef CONFIG_KVM_XEN case KVM_CAP_XEN_HVM: r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | KVM_XEN_HVM_CONFIG_SHARED_INFO | KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | KVM_XEN_HVM_CONFIG_EVTCHN_SEND | KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE | KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE | KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; break; #endif case KVM_CAP_SYNC_REGS: r = KVM_SYNC_X86_VALID_FIELDS; break; case KVM_CAP_ADJUST_CLOCK: r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: r = KVM_X86_DISABLE_EXITS_PAUSE; if (!mitigate_smt_rsb) { r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_CSTATE; if (kvm_can_mwait_in_guest()) r |= KVM_X86_DISABLE_EXITS_MWAIT; } break; case KVM_CAP_X86_SMM: if (!IS_ENABLED(CONFIG_KVM_SMM)) break; /* SMBASE is usually relocated above 1M on modern chipsets, * and SMM handlers might indeed rely on 4G segment limits, * so do not report SMM to be available if real mode is * emulated via vm86 mode. Still, do not go to great lengths * to avoid userspace's usage of the feature, because it is a * fringe case that is not enabled except via specific settings * of the module parameters. */ r = static_call(kvm_x86_has_emulated_msr)(kvm, MSR_IA32_SMBASE); break; case KVM_CAP_NR_VCPUS: r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; break; case KVM_CAP_MAX_VCPU_ID: r = KVM_MAX_VCPU_IDS; break; case KVM_CAP_PV_MMU: /* obsolete */ r = 0; break; case KVM_CAP_MCE: r = KVM_MAX_MCE_BANKS; break; case KVM_CAP_XCRS: r = boot_cpu_has(X86_FEATURE_XSAVE); break; case KVM_CAP_TSC_CONTROL: case KVM_CAP_VM_TSC_CONTROL: r = kvm_caps.has_tsc_control; break; case KVM_CAP_X2APIC_API: r = KVM_X2APIC_API_VALID_FLAGS; break; case KVM_CAP_NESTED_STATE: r = kvm_x86_ops.nested_ops->get_state ? kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0; break; #ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: r = kvm_x86_ops.enable_l2_tlb_flush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: r = kvm_x86_ops.nested_ops->enable_evmcs != NULL; break; #endif case KVM_CAP_SMALLER_MAXPHYADDR: r = (int) allow_smaller_maxphyaddr; break; case KVM_CAP_STEAL_TIME: r = sched_info_on(); break; case KVM_CAP_X86_BUS_LOCK_EXIT: if (kvm_caps.has_bus_lock_exit) r = KVM_BUS_LOCK_DETECTION_OFF | KVM_BUS_LOCK_DETECTION_EXIT; else r = 0; break; case KVM_CAP_XSAVE2: { r = xstate_required_size(kvm_get_filtered_xcr0(), false); if (r < sizeof(struct kvm_xsave)) r = sizeof(struct kvm_xsave); break; } case KVM_CAP_PMU_CAPABILITY: r = enable_pmu ? KVM_CAP_PMU_VALID_MASK : 0; break; case KVM_CAP_DISABLE_QUIRKS2: r = KVM_X86_VALID_QUIRKS; break; case KVM_CAP_X86_NOTIFY_VMEXIT: r = kvm_caps.has_notify_vmexit; break; case KVM_CAP_VM_TYPES: r = kvm_caps.supported_vm_types; break; default: break; } return r; } static int __kvm_x86_dev_get_attr(struct kvm_device_attr *attr, u64 *val) { if (attr->group) { if (kvm_x86_ops.dev_get_attr) return static_call(kvm_x86_dev_get_attr)(attr->group, attr->attr, val); return -ENXIO; } switch (attr->attr) { case KVM_X86_XCOMP_GUEST_SUPP: *val = kvm_caps.supported_xcr0; return 0; default: return -ENXIO; } } static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) { u64 __user *uaddr = u64_to_user_ptr(attr->addr); int r; u64 val; r = __kvm_x86_dev_get_attr(attr, &val); if (r < 0) return r; if (put_user(val, uaddr)) return -EFAULT; return 0; } static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr) { u64 val; return __kvm_x86_dev_get_attr(attr, &val); } long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; long r; switch (ioctl) { case KVM_GET_MSR_INDEX_LIST: { struct kvm_msr_list __user *user_msr_list = argp; struct kvm_msr_list msr_list; unsigned n; r = -EFAULT; if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list))) goto out; n = msr_list.nmsrs; msr_list.nmsrs = num_msrs_to_save + num_emulated_msrs; if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list))) goto out; r = -E2BIG; if (n < msr_list.nmsrs) goto out; r = -EFAULT; if (copy_to_user(user_msr_list->indices, &msrs_to_save, num_msrs_to_save * sizeof(u32))) goto out; if (copy_to_user(user_msr_list->indices + num_msrs_to_save, &emulated_msrs, num_emulated_msrs * sizeof(u32))) goto out; r = 0; break; } case KVM_GET_SUPPORTED_CPUID: case KVM_GET_EMULATED_CPUID: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries, ioctl); if (r) goto out; r = -EFAULT; if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) goto out; r = 0; break; } case KVM_X86_GET_MCE_CAP_SUPPORTED: r = -EFAULT; if (copy_to_user(argp, &kvm_caps.supported_mce_cap, sizeof(kvm_caps.supported_mce_cap))) goto out; r = 0; break; case KVM_GET_MSR_FEATURE_INDEX_LIST: { struct kvm_msr_list __user *user_msr_list = argp; struct kvm_msr_list msr_list; unsigned int n; r = -EFAULT; if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list))) goto out; n = msr_list.nmsrs; msr_list.nmsrs = num_msr_based_features; if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list))) goto out; r = -E2BIG; if (n < msr_list.nmsrs) goto out; r = -EFAULT; if (copy_to_user(user_msr_list->indices, &msr_based_features, num_msr_based_features * sizeof(u32))) goto out; r = 0; break; } case KVM_GET_MSRS: r = msr_io(NULL, argp, do_get_msr_feature, 1); break; #ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; #endif case KVM_GET_DEVICE_ATTR: { struct kvm_device_attr attr; r = -EFAULT; if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) break; r = kvm_x86_dev_get_attr(&attr); break; } case KVM_HAS_DEVICE_ATTR: { struct kvm_device_attr attr; r = -EFAULT; if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) break; r = kvm_x86_dev_has_attr(&attr); break; } default: r = -EINVAL; break; } out: return r; } static void wbinvd_ipi(void *garbage) { wbinvd(); } static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) { return kvm_arch_has_noncoherent_dma(vcpu->kvm); } void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Address WBINVD may be executed by guest */ if (need_emulate_wbinvd(vcpu)) { if (static_call(kvm_x86_has_wbinvd_exit)()) cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); else if (vcpu->cpu != -1 && vcpu->cpu != cpu) smp_call_function_single(vcpu->cpu, wbinvd_ipi, NULL, 1); } static_call(kvm_x86_vcpu_load)(vcpu, cpu); /* Save host pkru register if supported */ vcpu->arch.host_pkru = read_pkru(); /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); vcpu->arch.tsc_offset_adjustment = 0; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); } if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) { s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : rdtsc() - vcpu->arch.last_host_tsc; if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); if (kvm_check_tsc_unstable()) { u64 offset = kvm_compute_l1_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_vcpu_write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; } if (kvm_lapic_hv_timer_in_use(vcpu)) kvm_lapic_restart_hv_timer(vcpu); /* * On a host with synchronized TSC, there is no need to update * kvmclock on vcpu->cpu migration */ if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1) kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); if (vcpu->cpu != cpu) kvm_make_request(KVM_REQ_MIGRATE_TIMER, vcpu); vcpu->cpu = cpu; } kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); } static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; struct kvm_steal_time __user *st; struct kvm_memslots *slots; static const u8 preempted = KVM_VCPU_PREEMPTED; gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; /* * The vCPU can be marked preempted if and only if the VM-Exit was on * an instruction boundary and will not trigger guest emulation of any * kind (see vcpu_run). Vendor specific code controls (conservatively) * when this is true, for example allowing the vCPU to be marked * preempted if and only if the VM-Exit was due to a host interrupt. */ if (!vcpu->arch.at_instruction_boundary) { vcpu->stat.preemption_other++; return; } vcpu->stat.preemption_reported++; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; if (vcpu->arch.st.preempted) return; /* This happens on process exit */ if (unlikely(current->mm != vcpu->kvm->mm)) return; slots = kvm_memslots(vcpu->kvm); if (unlikely(slots->generation != ghc->generation || gpa != ghc->gpa || kvm_is_error_hva(ghc->hva) || !ghc->memslot)) return; st = (struct kvm_steal_time __user *)ghc->hva; BUILD_BUG_ON(sizeof(st->preempted) != sizeof(preempted)); if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted))) vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { int idx; if (vcpu->preempted) { vcpu->arch.preempted_in_kernel = kvm_arch_vcpu_in_kernel(vcpu); /* * Take the srcu lock as memslots will be accessed to check the gfn * cache generation against the memslots generation. */ idx = srcu_read_lock(&vcpu->kvm->srcu); if (kvm_xen_msr_enabled(vcpu->kvm)) kvm_xen_runstate_set_preempted(vcpu); else kvm_steal_time_set_preempted(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, idx); } static_call(kvm_x86_vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); return kvm_apic_get_state(vcpu, s); } static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { int r; r = kvm_apic_set_state(vcpu, s); if (r) return r; update_cr8_intercept(vcpu); return 0; } static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) { /* * We can accept userspace's request for interrupt injection * as long as we have a place to store the interrupt number. * The actual injection will happen when the CPU is able to * deliver the interrupt. */ if (kvm_cpu_has_extint(vcpu)) return false; /* Acknowledging ExtINT does not happen if LINT0 is masked. */ return (!lapic_in_kernel(vcpu) || kvm_apic_accept_pic_intr(vcpu)); } static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { /* * Do not cause an interrupt window exit if an exception * is pending or an event needs reinjection; userspace * might want to inject the interrupt manually using KVM_SET_REGS * or KVM_SET_SREGS. For that to work, we must be at an * instruction boundary and with no events half-injected. */ return (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_accept_dm_intr(vcpu) && !kvm_event_needs_reinjection(vcpu) && !kvm_is_exception_pending(vcpu)); } static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { if (irq->irq >= KVM_NR_INTERRUPTS) return -EINVAL; if (!irqchip_in_kernel(vcpu->kvm)) { kvm_queue_interrupt(vcpu, irq->irq, false); kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } /* * With in-kernel LAPIC, we only use this to inject EXTINT, so * fail for in-kernel 8259. */ if (pic_in_kernel(vcpu->kvm)) return -ENXIO; if (vcpu->arch.pending_external_vector != -1) return -EEXIST; vcpu->arch.pending_external_vector = irq->irq; kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) { kvm_inject_nmi(vcpu); return 0; } static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, struct kvm_tpr_access_ctl *tac) { if (tac->flags) return -EINVAL; vcpu->arch.tpr_access_reporting = !!tac->enabled; return 0; } static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, u64 mcg_cap) { int r; unsigned bank_num = mcg_cap & 0xff, bank; r = -EINVAL; if (!bank_num || bank_num > KVM_MAX_MCE_BANKS) goto out; if (mcg_cap & ~(kvm_caps.supported_mce_cap | 0xff | 0xff0000)) goto out; r = 0; vcpu->arch.mcg_cap = mcg_cap; /* Init IA32_MCG_CTL to all 1s */ if (mcg_cap & MCG_CTL_P) vcpu->arch.mcg_ctl = ~(u64)0; /* Init IA32_MCi_CTL to all 1s, IA32_MCi_CTL2 to all 0s */ for (bank = 0; bank < bank_num; bank++) { vcpu->arch.mce_banks[bank*4] = ~(u64)0; if (mcg_cap & MCG_CMCI_P) vcpu->arch.mci_ctl2_banks[bank] = 0; } kvm_apic_after_set_mcg_cap(vcpu); static_call(kvm_x86_setup_mce)(vcpu); out: return r; } /* * Validate this is an UCNA (uncorrectable no action) error by checking the * MCG_STATUS and MCi_STATUS registers: * - none of the bits for Machine Check Exceptions are set * - both the VAL (valid) and UC (uncorrectable) bits are set * MCI_STATUS_PCC - Processor Context Corrupted * MCI_STATUS_S - Signaled as a Machine Check Exception * MCI_STATUS_AR - Software recoverable Action Required */ static bool is_ucna(struct kvm_x86_mce *mce) { return !mce->mcg_status && !(mce->status & (MCI_STATUS_PCC | MCI_STATUS_S | MCI_STATUS_AR)) && (mce->status & MCI_STATUS_VAL) && (mce->status & MCI_STATUS_UC); } static int kvm_vcpu_x86_set_ucna(struct kvm_vcpu *vcpu, struct kvm_x86_mce *mce, u64* banks) { u64 mcg_cap = vcpu->arch.mcg_cap; banks[1] = mce->status; banks[2] = mce->addr; banks[3] = mce->misc; vcpu->arch.mcg_status = mce->mcg_status; if (!(mcg_cap & MCG_CMCI_P) || !(vcpu->arch.mci_ctl2_banks[mce->bank] & MCI_CTL2_CMCI_EN)) return 0; if (lapic_in_kernel(vcpu)) kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTCMCI); return 0; } static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, struct kvm_x86_mce *mce) { u64 mcg_cap = vcpu->arch.mcg_cap; unsigned bank_num = mcg_cap & 0xff; u64 *banks = vcpu->arch.mce_banks; if (mce->bank >= bank_num || !(mce->status & MCI_STATUS_VAL)) return -EINVAL; banks += array_index_nospec(4 * mce->bank, 4 * bank_num); if (is_ucna(mce)) return kvm_vcpu_x86_set_ucna(vcpu, mce, banks); /* * if IA32_MCG_CTL is not all 1s, the uncorrected error * reporting is disabled */ if ((mce->status & MCI_STATUS_UC) && (mcg_cap & MCG_CTL_P) && vcpu->arch.mcg_ctl != ~(u64)0) return 0; /* * if IA32_MCi_CTL is not all 1s, the uncorrected error * reporting is disabled for the bank */ if ((mce->status & MCI_STATUS_UC) && banks[0] != ~(u64)0) return 0; if (mce->status & MCI_STATUS_UC) { if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) || !kvm_is_cr4_bit_set(vcpu, X86_CR4_MCE)) { kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return 0; } if (banks[1] & MCI_STATUS_VAL) mce->status |= MCI_STATUS_OVER; banks[2] = mce->addr; banks[3] = mce->misc; vcpu->arch.mcg_status = mce->mcg_status; banks[1] = mce->status; kvm_queue_exception(vcpu, MC_VECTOR); } else if (!(banks[1] & MCI_STATUS_VAL) || !(banks[1] & MCI_STATUS_UC)) { if (banks[1] & MCI_STATUS_VAL) mce->status |= MCI_STATUS_OVER; banks[2] = mce->addr; banks[3] = mce->misc; banks[1] = mce->status; } else banks[1] |= MCI_STATUS_OVER; return 0; } static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { struct kvm_queued_exception *ex; process_nmi(vcpu); #ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); #endif /* * KVM's ABI only allows for one exception to be migrated. Luckily, * the only time there can be two queued exceptions is if there's a * non-exiting _injected_ exception, and a pending exiting exception. * In that case, ignore the VM-Exiting exception as it's an extension * of the injected exception. */ if (vcpu->arch.exception_vmexit.pending && !vcpu->arch.exception.pending && !vcpu->arch.exception.injected) ex = &vcpu->arch.exception_vmexit; else ex = &vcpu->arch.exception; /* * In guest mode, payload delivery should be deferred if the exception * will be intercepted by L1, e.g. KVM should not modifying CR2 if L1 * intercepts #PF, ditto for DR6 and #DBs. If the per-VM capability, * KVM_CAP_EXCEPTION_PAYLOAD, is not set, userspace may or may not * propagate the payload and so it cannot be safely deferred. Deliver * the payload if the capability hasn't been requested. */ if (!vcpu->kvm->arch.exception_payload_enabled && ex->pending && ex->has_payload) kvm_deliver_exception_payload(vcpu, ex); memset(events, 0, sizeof(*events)); /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP * isn't advanced, we should expect to encounter the exception * again. */ if (!kvm_exception_is_soft(ex->vector)) { events->exception.injected = ex->injected; events->exception.pending = ex->pending; /* * For ABI compatibility, deliberately conflate * pending and injected exceptions when * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled. */ if (!vcpu->kvm->arch.exception_payload_enabled) events->exception.injected |= ex->pending; } events->exception.nr = ex->vector; events->exception.has_error_code = ex->has_error_code; events->exception.error_code = ex->error_code; events->exception_has_payload = ex->has_payload; events->exception_payload = ex->payload; events->interrupt.injected = vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = kvm_get_nr_pending_nmis(vcpu); events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu); /* events->sipi_vector is never valid when reporting to user space */ #ifdef CONFIG_KVM_SMM events->smi.smm = is_smm(vcpu); events->smi.pending = vcpu->arch.smi_pending; events->smi.smm_inside_nmi = !!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK); #endif events->smi.latched_init = kvm_lapic_latched_init(vcpu); events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING | KVM_VCPUEVENT_VALID_SHADOW | KVM_VCPUEVENT_VALID_SMM); if (vcpu->kvm->arch.exception_payload_enabled) events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD; if (vcpu->kvm->arch.triple_fault_event) { events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu); events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT; } } static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING | KVM_VCPUEVENT_VALID_SIPI_VECTOR | KVM_VCPUEVENT_VALID_SHADOW | KVM_VCPUEVENT_VALID_SMM | KVM_VCPUEVENT_VALID_PAYLOAD | KVM_VCPUEVENT_VALID_TRIPLE_FAULT)) return -EINVAL; if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) { if (!vcpu->kvm->arch.exception_payload_enabled) return -EINVAL; if (events->exception.pending) events->exception.injected = 0; else events->exception_has_payload = 0; } else { events->exception.pending = 0; events->exception_has_payload = 0; } if ((events->exception.injected || events->exception.pending) && (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR)) return -EINVAL; /* INITs are latched while in SMM */ if (events->flags & KVM_VCPUEVENT_VALID_SMM && (events->smi.smm || events->smi.pending) && vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) return -EINVAL; process_nmi(vcpu); /* * Flag that userspace is stuffing an exception, the next KVM_RUN will * morph the exception to a VM-Exit if appropriate. Do this only for * pending exceptions, already-injected exceptions are not subject to * intercpetion. Note, userspace that conflates pending and injected * is hosed, and will incorrectly convert an injected exception into a * pending exception, which in turn may cause a spurious VM-Exit. */ vcpu->arch.exception_from_userspace = events->exception.pending; vcpu->arch.exception_vmexit.pending = false; vcpu->arch.exception.injected = events->exception.injected; vcpu->arch.exception.pending = events->exception.pending; vcpu->arch.exception.vector = events->exception.nr; vcpu->arch.exception.has_error_code = events->exception.has_error_code; vcpu->arch.exception.error_code = events->exception.error_code; vcpu->arch.exception.has_payload = events->exception_has_payload; vcpu->arch.exception.payload = events->exception_payload; vcpu->arch.interrupt.injected = events->interrupt.injected; vcpu->arch.interrupt.nr = events->interrupt.nr; vcpu->arch.interrupt.soft = events->interrupt.soft; if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) static_call(kvm_x86_set_interrupt_shadow)(vcpu, events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) { vcpu->arch.nmi_pending = 0; atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending); if (events->nmi.pending) kvm_make_request(KVM_REQ_NMI, vcpu); } static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && lapic_in_kernel(vcpu)) vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { #ifdef CONFIG_KVM_SMM if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { kvm_leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); } vcpu->arch.smi_pending = events->smi.pending; if (events->smi.smm) { if (events->smi.smm_inside_nmi) vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; } #else if (events->smi.smm || events->smi.pending || events->smi.smm_inside_nmi) return -EINVAL; #endif if (lapic_in_kernel(vcpu)) { if (events->smi.latched_init) set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); else clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } } if (events->flags & KVM_VCPUEVENT_VALID_TRIPLE_FAULT) { if (!vcpu->kvm->arch.triple_fault_event) return -EINVAL; if (events->triple_fault.pending) kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); else kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); } kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } static int kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, struct kvm_debugregs *dbgregs) { unsigned int i; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; memset(dbgregs, 0, sizeof(*dbgregs)); BUILD_BUG_ON(ARRAY_SIZE(vcpu->arch.db) != ARRAY_SIZE(dbgregs->db)); for (i = 0; i < ARRAY_SIZE(vcpu->arch.db); i++) dbgregs->db[i] = vcpu->arch.db[i]; dbgregs->dr6 = vcpu->arch.dr6; dbgregs->dr7 = vcpu->arch.dr7; return 0; } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, struct kvm_debugregs *dbgregs) { unsigned int i; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; if (dbgregs->flags) return -EINVAL; if (!kvm_dr6_valid(dbgregs->dr6)) return -EINVAL; if (!kvm_dr7_valid(dbgregs->dr7)) return -EINVAL; for (i = 0; i < ARRAY_SIZE(vcpu->arch.db); i++) vcpu->arch.db[i] = dbgregs->db[i]; kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; vcpu->arch.dr7 = dbgregs->dr7; kvm_update_dr7(vcpu); return 0; } static int kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, u8 *state, unsigned int size) { /* * Only copy state for features that are enabled for the guest. The * state itself isn't problematic, but setting bits in the header for * features that are supported in *this* host but not exposed to the * guest can result in KVM_SET_XSAVE failing when live migrating to a * compatible host without the features that are NOT exposed to the * guest. * * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't * supported by the host. */ u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size, supported_xcr0, vcpu->arch.pkru); return 0; } static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, sizeof(guest_xsave->region)); } static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, guest_xsave->region, kvm_caps.supported_xcr0, &vcpu->arch.pkru); } static int kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, struct kvm_xcrs *guest_xcrs) { if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; if (!boot_cpu_has(X86_FEATURE_XSAVE)) { guest_xcrs->nr_xcrs = 0; return 0; } guest_xcrs->nr_xcrs = 1; guest_xcrs->flags = 0; guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK; guest_xcrs->xcrs[0].value = vcpu->arch.xcr0; return 0; } static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, struct kvm_xcrs *guest_xcrs) { int i, r = 0; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -EINVAL; if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags) return -EINVAL; for (i = 0; i < guest_xcrs->nr_xcrs; i++) /* Only support XCR0 currently */ if (guest_xcrs->xcrs[i].xcr == XCR_XFEATURE_ENABLED_MASK) { r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK, guest_xcrs->xcrs[i].value); break; } if (r) r = -EINVAL; return r; } /* * kvm_set_guest_paused() indicates to the guest kernel that it has been * stopped by the hypervisor. This function will be called from the host only. * EINVAL is returned when the host attempts to set the flag for a guest that * does not support pv clocks. */ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) { if (!vcpu->arch.pv_time.active) return -EINVAL; vcpu->arch.pvclock_set_guest_stopped_request = true; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); return 0; } static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int r; switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: r = 0; break; default: r = -ENXIO; } return r; } static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { u64 __user *uaddr = u64_to_user_ptr(attr->addr); int r; switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: r = -EFAULT; if (put_user(vcpu->arch.l1_tsc_offset, uaddr)) break; r = 0; break; default: r = -ENXIO; } return r; } static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { u64 __user *uaddr = u64_to_user_ptr(attr->addr); struct kvm *kvm = vcpu->kvm; int r; switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: { u64 offset, tsc, ns; unsigned long flags; bool matched; r = -EFAULT; if (get_user(offset, uaddr)) break; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); matched = (vcpu->arch.virtual_tsc_khz && kvm->arch.last_tsc_khz == vcpu->arch.virtual_tsc_khz && kvm->arch.last_tsc_offset == offset); tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset; ns = get_kvmclock_base_ns(); kvm->arch.user_set_tsc = true; __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); r = 0; break; } default: r = -ENXIO; } return r; } static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu, unsigned int ioctl, void __user *argp) { struct kvm_device_attr attr; int r; if (copy_from_user(&attr, argp, sizeof(attr))) return -EFAULT; if (attr.group != KVM_VCPU_TSC_CTRL) return -ENXIO; switch (ioctl) { case KVM_HAS_DEVICE_ATTR: r = kvm_arch_tsc_has_attr(vcpu, &attr); break; case KVM_GET_DEVICE_ATTR: r = kvm_arch_tsc_get_attr(vcpu, &attr); break; case KVM_SET_DEVICE_ATTR: r = kvm_arch_tsc_set_attr(vcpu, &attr); break; } return r; } static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, struct kvm_enable_cap *cap) { if (cap->flags) return -EINVAL; switch (cap->cap) { #ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; fallthrough; case KVM_CAP_HYPERV_SYNIC: if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: { int r; uint16_t vmcs_version; void __user *user_ptr; if (!kvm_x86_ops.nested_ops->enable_evmcs) return -ENOTTY; r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); if (!r) { user_ptr = (void __user *)(uintptr_t)cap->args[0]; if (copy_to_user(user_ptr, &vmcs_version, sizeof(vmcs_version))) r = -EFAULT; } return r; } case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: if (!kvm_x86_ops.enable_l2_tlb_flush) return -ENOTTY; return static_call(kvm_x86_enable_l2_tlb_flush)(vcpu); case KVM_CAP_HYPERV_ENFORCE_CPUID: return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); #endif case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; if (vcpu->arch.pv_cpuid.enforce) kvm_update_pv_runtime(vcpu); return 0; default: return -EINVAL; } } long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; int r; union { struct kvm_sregs2 *sregs2; struct kvm_lapic_state *lapic; struct kvm_xsave *xsave; struct kvm_xcrs *xcrs; void *buffer; } u; vcpu_load(vcpu); u.buffer = NULL; switch (ioctl) { case KVM_GET_LAPIC: { r = -EINVAL; if (!lapic_in_kernel(vcpu)) goto out; u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.lapic) goto out; r = kvm_vcpu_ioctl_get_lapic(vcpu, u.lapic); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, u.lapic, sizeof(struct kvm_lapic_state))) goto out; r = 0; break; } case KVM_SET_LAPIC: { r = -EINVAL; if (!lapic_in_kernel(vcpu)) goto out; u.lapic = memdup_user(argp, sizeof(*u.lapic)); if (IS_ERR(u.lapic)) { r = PTR_ERR(u.lapic); goto out_nofree; } r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic); break; } case KVM_INTERRUPT: { struct kvm_interrupt irq; r = -EFAULT; if (copy_from_user(&irq, argp, sizeof(irq))) goto out; r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); break; } case KVM_NMI: { r = kvm_vcpu_ioctl_nmi(vcpu); break; } case KVM_SMI: { r = kvm_inject_smi(vcpu); break; } case KVM_SET_CPUID: { struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries); break; } case KVM_SET_CPUID2: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid, cpuid_arg->entries); break; } case KVM_GET_CPUID2: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid, cpuid_arg->entries); if (r) goto out; r = -EFAULT; if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) goto out; r = 0; break; } case KVM_GET_MSRS: { int idx = srcu_read_lock(&vcpu->kvm->srcu); r = msr_io(vcpu, argp, do_get_msr, 1); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_SET_MSRS: { int idx = srcu_read_lock(&vcpu->kvm->srcu); r = msr_io(vcpu, argp, do_set_msr, 0); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_TPR_ACCESS_REPORTING: { struct kvm_tpr_access_ctl tac; r = -EFAULT; if (copy_from_user(&tac, argp, sizeof(tac))) goto out; r = vcpu_ioctl_tpr_access_reporting(vcpu, &tac); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &tac, sizeof(tac))) goto out; r = 0; break; }; case KVM_SET_VAPIC_ADDR: { struct kvm_vapic_addr va; int idx; r = -EINVAL; if (!lapic_in_kernel(vcpu)) goto out; r = -EFAULT; if (copy_from_user(&va, argp, sizeof(va))) goto out; idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_X86_SETUP_MCE: { u64 mcg_cap; r = -EFAULT; if (copy_from_user(&mcg_cap, argp, sizeof(mcg_cap))) goto out; r = kvm_vcpu_ioctl_x86_setup_mce(vcpu, mcg_cap); break; } case KVM_X86_SET_MCE: { struct kvm_x86_mce mce; r = -EFAULT; if (copy_from_user(&mce, argp, sizeof(mce))) goto out; r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); break; } case KVM_GET_VCPU_EVENTS: { struct kvm_vcpu_events events; kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events); r = -EFAULT; if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events))) break; r = 0; break; } case KVM_SET_VCPU_EVENTS: { struct kvm_vcpu_events events; r = -EFAULT; if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) break; r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); break; } case KVM_GET_DEBUGREGS: { struct kvm_debugregs dbgregs; r = kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); if (r < 0) break; r = -EFAULT; if (copy_to_user(argp, &dbgregs, sizeof(struct kvm_debugregs))) break; r = 0; break; } case KVM_SET_DEBUGREGS: { struct kvm_debugregs dbgregs; r = -EFAULT; if (copy_from_user(&dbgregs, argp, sizeof(struct kvm_debugregs))) break; r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs); break; } case KVM_GET_XSAVE: { r = -EINVAL; if (vcpu->arch.guest_fpu.uabi_size > sizeof(struct kvm_xsave)) break; u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.xsave) break; r = kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); if (r < 0) break; r = -EFAULT; if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave))) break; r = 0; break; } case KVM_SET_XSAVE: { int size = vcpu->arch.guest_fpu.uabi_size; u.xsave = memdup_user(argp, size); if (IS_ERR(u.xsave)) { r = PTR_ERR(u.xsave); goto out_nofree; } r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); break; } case KVM_GET_XSAVE2: { int size = vcpu->arch.guest_fpu.uabi_size; u.xsave = kzalloc(size, GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.xsave) break; r = kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); if (r < 0) break; r = -EFAULT; if (copy_to_user(argp, u.xsave, size)) break; r = 0; break; } case KVM_GET_XCRS: { u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.xcrs) break; r = kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); if (r < 0) break; r = -EFAULT; if (copy_to_user(argp, u.xcrs, sizeof(struct kvm_xcrs))) break; r = 0; break; } case KVM_SET_XCRS: { u.xcrs = memdup_user(argp, sizeof(*u.xcrs)); if (IS_ERR(u.xcrs)) { r = PTR_ERR(u.xcrs); goto out_nofree; } r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); break; } case KVM_SET_TSC_KHZ: { u32 user_tsc_khz; r = -EINVAL; user_tsc_khz = (u32)arg; if (kvm_caps.has_tsc_control && user_tsc_khz >= kvm_caps.max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) user_tsc_khz = tsc_khz; if (!kvm_set_tsc_khz(vcpu, user_tsc_khz)) r = 0; goto out; } case KVM_GET_TSC_KHZ: { r = vcpu->arch.virtual_tsc_khz; goto out; } case KVM_KVMCLOCK_CTRL: { r = kvm_set_guest_paused(vcpu); goto out; } case KVM_ENABLE_CAP: { struct kvm_enable_cap cap; r = -EFAULT; if (copy_from_user(&cap, argp, sizeof(cap))) goto out; r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); break; } case KVM_GET_NESTED_STATE: { struct kvm_nested_state __user *user_kvm_nested_state = argp; u32 user_data_size; r = -EINVAL; if (!kvm_x86_ops.nested_ops->get_state) break; BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); r = -EFAULT; if (get_user(user_data_size, &user_kvm_nested_state->size)) break; r = kvm_x86_ops.nested_ops->get_state(vcpu, user_kvm_nested_state, user_data_size); if (r < 0) break; if (r > user_data_size) { if (put_user(r, &user_kvm_nested_state->size)) r = -EFAULT; else r = -E2BIG; break; } r = 0; break; } case KVM_SET_NESTED_STATE: { struct kvm_nested_state __user *user_kvm_nested_state = argp; struct kvm_nested_state kvm_state; int idx; r = -EINVAL; if (!kvm_x86_ops.nested_ops->set_state) break; r = -EFAULT; if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state))) break; r = -EINVAL; if (kvm_state.size < sizeof(kvm_state)) break; if (kvm_state.flags & ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE | KVM_STATE_NESTED_EVMCS | KVM_STATE_NESTED_MTF_PENDING | KVM_STATE_NESTED_GIF_SET)) break; /* nested_run_pending implies guest_mode. */ if ((kvm_state.flags & KVM_STATE_NESTED_RUN_PENDING) && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE)) break; idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_x86_ops.nested_ops->set_state(vcpu, user_kvm_nested_state, &kvm_state); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } #ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; #endif #ifdef CONFIG_KVM_XEN case KVM_XEN_VCPU_GET_ATTR: { struct kvm_xen_vcpu_attr xva; r = -EFAULT; if (copy_from_user(&xva, argp, sizeof(xva))) goto out; r = kvm_xen_vcpu_get_attr(vcpu, &xva); if (!r && copy_to_user(argp, &xva, sizeof(xva))) r = -EFAULT; break; } case KVM_XEN_VCPU_SET_ATTR: { struct kvm_xen_vcpu_attr xva; r = -EFAULT; if (copy_from_user(&xva, argp, sizeof(xva))) goto out; r = kvm_xen_vcpu_set_attr(vcpu, &xva); break; } #endif case KVM_GET_SREGS2: { r = -EINVAL; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) goto out; u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL); r = -ENOMEM; if (!u.sregs2) goto out; __get_sregs2(vcpu, u.sregs2); r = -EFAULT; if (copy_to_user(argp, u.sregs2, sizeof(struct kvm_sregs2))) goto out; r = 0; break; } case KVM_SET_SREGS2: { r = -EINVAL; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) goto out; u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2)); if (IS_ERR(u.sregs2)) { r = PTR_ERR(u.sregs2); u.sregs2 = NULL; goto out; } r = __set_sregs2(vcpu, u.sregs2); break; } case KVM_HAS_DEVICE_ATTR: case KVM_GET_DEVICE_ATTR: case KVM_SET_DEVICE_ATTR: r = kvm_vcpu_ioctl_device_attr(vcpu, ioctl, argp); break; default: r = -EINVAL; } out: kfree(u.buffer); out_nofree: vcpu_put(vcpu); return r; } vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) { int ret; if (addr > (unsigned int)(-3 * PAGE_SIZE)) return -EINVAL; ret = static_call(kvm_x86_set_tss_addr)(kvm, addr); return ret; } static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { return static_call(kvm_x86_set_identity_map_addr)(kvm, ident_addr); } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages) { if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; mutex_lock(&kvm->slots_lock); kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages; mutex_unlock(&kvm->slots_lock); return 0; } static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) { struct kvm_pic *pic = kvm->arch.vpic; int r; r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_PIC_MASTER: memcpy(&chip->chip.pic, &pic->pics[0], sizeof(struct kvm_pic_state)); break; case KVM_IRQCHIP_PIC_SLAVE: memcpy(&chip->chip.pic, &pic->pics[1], sizeof(struct kvm_pic_state)); break; case KVM_IRQCHIP_IOAPIC: kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; break; } return r; } static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) { struct kvm_pic *pic = kvm->arch.vpic; int r; r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_PIC_MASTER: spin_lock(&pic->lock); memcpy(&pic->pics[0], &chip->chip.pic, sizeof(struct kvm_pic_state)); spin_unlock(&pic->lock); break; case KVM_IRQCHIP_PIC_SLAVE: spin_lock(&pic->lock); memcpy(&pic->pics[1], &chip->chip.pic, sizeof(struct kvm_pic_state)); spin_unlock(&pic->lock); break; case KVM_IRQCHIP_IOAPIC: kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; break; } kvm_pic_update_irq(pic); return r; } static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) { struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state; BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels)); mutex_lock(&kps->lock); memcpy(ps, &kps->channels, sizeof(*ps)); mutex_unlock(&kps->lock); return 0; } static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) { int i; struct kvm_pit *pit = kvm->arch.vpit; mutex_lock(&pit->pit_state.lock); memcpy(&pit->pit_state.channels, ps, sizeof(*ps)); for (i = 0; i < 3; i++) kvm_pit_load_count(pit, i, ps->channels[i].count, 0); mutex_unlock(&pit->pit_state.lock); return 0; } static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels, sizeof(ps->channels)); ps->flags = kvm->arch.vpit->pit_state.flags; mutex_unlock(&kvm->arch.vpit->pit_state.lock); memset(&ps->reserved, 0, sizeof(ps->reserved)); return 0; } static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { int start = 0; int i; u32 prev_legacy, cur_legacy; struct kvm_pit *pit = kvm->arch.vpit; mutex_lock(&pit->pit_state.lock); prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY; if (!prev_legacy && cur_legacy) start = 1; memcpy(&pit->pit_state.channels, &ps->channels, sizeof(pit->pit_state.channels)); pit->pit_state.flags = ps->flags; for (i = 0; i < 3; i++) kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count, start && i == 0); mutex_unlock(&pit->pit_state.lock); return 0; } static int kvm_vm_ioctl_reinject(struct kvm *kvm, struct kvm_reinject_control *control) { struct kvm_pit *pit = kvm->arch.vpit; /* pit->pit_state.lock was overloaded to prevent userspace from getting * an inconsistent state after running multiple KVM_REINJECT_CONTROL * ioctls in parallel. Use a separate lock if that ioctl isn't rare. */ mutex_lock(&pit->pit_state.lock); kvm_pit_set_reinject(pit, control->pit_reinject); mutex_unlock(&pit->pit_state.lock); return 0; } void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { /* * Flush all CPUs' dirty log buffers to the dirty_bitmap. Called * before reporting dirty_bitmap to userspace. KVM flushes the buffers * on all VM-Exits, thus we only need to kick running vCPUs to force a * VM-Exit. */ struct kvm_vcpu *vcpu; unsigned long i; if (!kvm_x86_ops.cpu_dirty_log_size) return; kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); } int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, bool line_status) { if (!irqchip_in_kernel(kvm)) return -ENXIO; irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event->irq, irq_event->level, line_status); return 0; } int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { int r; if (cap->flags) return -EINVAL; switch (cap->cap) { case KVM_CAP_DISABLE_QUIRKS2: r = -EINVAL; if (cap->args[0] & ~KVM_X86_VALID_QUIRKS) break; fallthrough; case KVM_CAP_DISABLE_QUIRKS: kvm->arch.disabled_quirks = cap->args[0]; r = 0; break; case KVM_CAP_SPLIT_IRQCHIP: { mutex_lock(&kvm->lock); r = -EINVAL; if (cap->args[0] > MAX_NR_RESERVED_IOAPIC_PINS) goto split_irqchip_unlock; r = -EEXIST; if (irqchip_in_kernel(kvm)) goto split_irqchip_unlock; if (kvm->created_vcpus) goto split_irqchip_unlock; r = kvm_setup_empty_irq_routing(kvm); if (r) goto split_irqchip_unlock; /* Pairs with irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT); r = 0; split_irqchip_unlock: mutex_unlock(&kvm->lock); break; } case KVM_CAP_X2APIC_API: r = -EINVAL; if (cap->args[0] & ~KVM_X2APIC_API_VALID_FLAGS) break; if (cap->args[0] & KVM_X2APIC_API_USE_32BIT_IDS) kvm->arch.x2apic_format = true; if (cap->args[0] & KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) kvm->arch.x2apic_broadcast_quirk_disabled = true; r = 0; break; case KVM_CAP_X86_DISABLE_EXITS: r = -EINVAL; if (cap->args[0] & ~KVM_X86_DISABLE_VALID_EXITS) break; if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE) kvm->arch.pause_in_guest = true; #define SMT_RSB_MSG "This processor is affected by the Cross-Thread Return Predictions vulnerability. " \ "KVM_CAP_X86_DISABLE_EXITS should only be used with SMT disabled or trusted guests." if (!mitigate_smt_rsb) { if (boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible() && (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE)) pr_warn_once(SMT_RSB_MSG); if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) && kvm_can_mwait_in_guest()) kvm->arch.mwait_in_guest = true; if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) kvm->arch.hlt_in_guest = true; if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) kvm->arch.cstate_in_guest = true; } r = 0; break; case KVM_CAP_MSR_PLATFORM_INFO: kvm->arch.guest_can_read_msr_platform_info = cap->args[0]; r = 0; break; case KVM_CAP_EXCEPTION_PAYLOAD: kvm->arch.exception_payload_enabled = cap->args[0]; r = 0; break; case KVM_CAP_X86_TRIPLE_FAULT_EVENT: kvm->arch.triple_fault_event = cap->args[0]; r = 0; break; case KVM_CAP_X86_USER_SPACE_MSR: r = -EINVAL; if (cap->args[0] & ~KVM_MSR_EXIT_REASON_VALID_MASK) break; kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; break; case KVM_CAP_X86_BUS_LOCK_EXIT: r = -EINVAL; if (cap->args[0] & ~KVM_BUS_LOCK_DETECTION_VALID_MODE) break; if ((cap->args[0] & KVM_BUS_LOCK_DETECTION_OFF) && (cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)) break; if (kvm_caps.has_bus_lock_exit && cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT) kvm->arch.bus_lock_detection_enabled = true; r = 0; break; #ifdef CONFIG_X86_SGX_KVM case KVM_CAP_SGX_ATTRIBUTE: { unsigned long allowed_attributes = 0; r = sgx_set_attribute(&allowed_attributes, cap->args[0]); if (r) break; /* KVM only supports the PROVISIONKEY privileged attribute. */ if ((allowed_attributes & SGX_ATTR_PROVISIONKEY) && !(allowed_attributes & ~SGX_ATTR_PROVISIONKEY)) kvm->arch.sgx_provisioning_allowed = true; else r = -EINVAL; break; } #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: r = -EINVAL; if (!kvm_x86_ops.vm_copy_enc_context_from) break; r = static_call(kvm_x86_vm_copy_enc_context_from)(kvm, cap->args[0]); break; case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: r = -EINVAL; if (!kvm_x86_ops.vm_move_enc_context_from) break; r = static_call(kvm_x86_vm_move_enc_context_from)(kvm, cap->args[0]); break; case KVM_CAP_EXIT_HYPERCALL: if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { r = -EINVAL; break; } kvm->arch.hypercall_exit_enabled = cap->args[0]; r = 0; break; case KVM_CAP_EXIT_ON_EMULATION_FAILURE: r = -EINVAL; if (cap->args[0] & ~1) break; kvm->arch.exit_on_emulation_error = cap->args[0]; r = 0; break; case KVM_CAP_PMU_CAPABILITY: r = -EINVAL; if (!enable_pmu || (cap->args[0] & ~KVM_CAP_PMU_VALID_MASK)) break; mutex_lock(&kvm->lock); if (!kvm->created_vcpus) { kvm->arch.enable_pmu = !(cap->args[0] & KVM_PMU_CAP_DISABLE); r = 0; } mutex_unlock(&kvm->lock); break; case KVM_CAP_MAX_VCPU_ID: r = -EINVAL; if (cap->args[0] > KVM_MAX_VCPU_IDS) break; mutex_lock(&kvm->lock); if (kvm->arch.max_vcpu_ids == cap->args[0]) { r = 0; } else if (!kvm->arch.max_vcpu_ids) { kvm->arch.max_vcpu_ids = cap->args[0]; r = 0; } mutex_unlock(&kvm->lock); break; case KVM_CAP_X86_NOTIFY_VMEXIT: r = -EINVAL; if ((u32)cap->args[0] & ~KVM_X86_NOTIFY_VMEXIT_VALID_BITS) break; if (!kvm_caps.has_notify_vmexit) break; if (!((u32)cap->args[0] & KVM_X86_NOTIFY_VMEXIT_ENABLED)) break; mutex_lock(&kvm->lock); if (!kvm->created_vcpus) { kvm->arch.notify_window = cap->args[0] >> 32; kvm->arch.notify_vmexit_flags = (u32)cap->args[0]; r = 0; } mutex_unlock(&kvm->lock); break; case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: r = -EINVAL; /* * Since the risk of disabling NX hugepages is a guest crashing * the system, ensure the userspace process has permission to * reboot the system. * * Note that unlike the reboot() syscall, the process must have * this capability in the root namespace because exposing * /dev/kvm into a container does not limit the scope of the * iTLB multihit bug to that container. In other words, * this must use capable(), not ns_capable(). */ if (!capable(CAP_SYS_BOOT)) { r = -EPERM; break; } if (cap->args[0]) break; mutex_lock(&kvm->lock); if (!kvm->created_vcpus) { kvm->arch.disable_nx_huge_pages = true; r = 0; } mutex_unlock(&kvm->lock); break; default: r = -EINVAL; break; } return r; } static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow) { struct kvm_x86_msr_filter *msr_filter; msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT); if (!msr_filter) return NULL; msr_filter->default_allow = default_allow; return msr_filter; } static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) { u32 i; if (!msr_filter) return; for (i = 0; i < msr_filter->count; i++) kfree(msr_filter->ranges[i].bitmap); kfree(msr_filter); } static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, struct kvm_msr_filter_range *user_range) { unsigned long *bitmap; size_t bitmap_size; if (!user_range->nmsrs) return 0; if (user_range->flags & ~KVM_MSR_FILTER_RANGE_VALID_MASK) return -EINVAL; if (!user_range->flags) return -EINVAL; bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long); if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE) return -EINVAL; bitmap = memdup_user((__user u8*)user_range->bitmap, bitmap_size); if (IS_ERR(bitmap)) return PTR_ERR(bitmap); msr_filter->ranges[msr_filter->count] = (struct msr_bitmap_range) { .flags = user_range->flags, .base = user_range->base, .nmsrs = user_range->nmsrs, .bitmap = bitmap, }; msr_filter->count++; return 0; } static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, struct kvm_msr_filter *filter) { struct kvm_x86_msr_filter *new_filter, *old_filter; bool default_allow; bool empty = true; int r; u32 i; if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK) return -EINVAL; for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) empty &= !filter->ranges[i].nmsrs; default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY); if (empty && !default_allow) return -EINVAL; new_filter = kvm_alloc_msr_filter(default_allow); if (!new_filter) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) { r = kvm_add_msr_filter(new_filter, &filter->ranges[i]); if (r) { kvm_free_msr_filter(new_filter); return r; } } mutex_lock(&kvm->lock); old_filter = rcu_replace_pointer(kvm->arch.msr_filter, new_filter, mutex_is_locked(&kvm->lock)); mutex_unlock(&kvm->lock); synchronize_srcu(&kvm->srcu); kvm_free_msr_filter(old_filter); kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED); return 0; } #ifdef CONFIG_KVM_COMPAT /* for KVM_X86_SET_MSR_FILTER */ struct kvm_msr_filter_range_compat { __u32 flags; __u32 nmsrs; __u32 base; __u32 bitmap; }; struct kvm_msr_filter_compat { __u32 flags; struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES]; }; #define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat) long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; struct kvm *kvm = filp->private_data; long r = -ENOTTY; switch (ioctl) { case KVM_X86_SET_MSR_FILTER_COMPAT: { struct kvm_msr_filter __user *user_msr_filter = argp; struct kvm_msr_filter_compat filter_compat; struct kvm_msr_filter filter; int i; if (copy_from_user(&filter_compat, user_msr_filter, sizeof(filter_compat))) return -EFAULT; filter.flags = filter_compat.flags; for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { struct kvm_msr_filter_range_compat *cr; cr = &filter_compat.ranges[i]; filter.ranges[i] = (struct kvm_msr_filter_range) { .flags = cr->flags, .nmsrs = cr->nmsrs, .base = cr->base, .bitmap = (__u8 *)(ulong)cr->bitmap, }; } r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); break; } } return r; } #endif #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_arch_suspend_notifier(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; int ret = 0; mutex_lock(&kvm->lock); kvm_for_each_vcpu(i, vcpu, kvm) { if (!vcpu->arch.pv_time.active) continue; ret = kvm_set_guest_paused(vcpu); if (ret) { kvm_err("Failed to pause guest VCPU%d: %d\n", vcpu->vcpu_id, ret); break; } } mutex_unlock(&kvm->lock); return ret ? NOTIFY_BAD : NOTIFY_DONE; } int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state) { switch (state) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: return kvm_arch_suspend_notifier(kvm); } return NOTIFY_DONE; } #endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ static int kvm_vm_ioctl_get_clock(struct kvm *kvm, void __user *argp) { struct kvm_clock_data data = { 0 }; get_kvmclock(kvm, &data); if (copy_to_user(argp, &data, sizeof(data))) return -EFAULT; return 0; } static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) { struct kvm_arch *ka = &kvm->arch; struct kvm_clock_data data; u64 now_raw_ns; if (copy_from_user(&data, argp, sizeof(data))) return -EFAULT; /* * Only KVM_CLOCK_REALTIME is used, but allow passing the * result of KVM_GET_CLOCK back to KVM_SET_CLOCK. */ if (data.flags & ~KVM_CLOCK_VALID_FLAGS) return -EINVAL; kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); /* * This pairs with kvm_guest_time_update(): when masterclock is * in use, we use master_kernel_ns + kvmclock_offset to set * unsigned 'system_time' so if we use get_kvmclock_ns() (which * is slightly ahead) here we risk going negative on unsigned * 'system_time' when 'data.clock' is very small. */ if (data.flags & KVM_CLOCK_REALTIME) { u64 now_real_ns = ktime_get_real_ns(); /* * Avoid stepping the kvmclock backwards. */ if (now_real_ns > data.realtime) data.clock += now_real_ns - data.realtime; } if (ka->use_master_clock) now_raw_ns = ka->master_kernel_ns; else now_raw_ns = get_kvmclock_base_ns(); ka->kvmclock_offset = data.clock - now_raw_ns; kvm_end_pvclock_update(kvm); return 0; } int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; int r = -ENOTTY; /* * This union makes it completely explicit to gcc-3.x * that these two variables' stack usage should be * combined, not added together. */ union { struct kvm_pit_state ps; struct kvm_pit_state2 ps2; struct kvm_pit_config pit_config; } u; switch (ioctl) { case KVM_SET_TSS_ADDR: r = kvm_vm_ioctl_set_tss_addr(kvm, arg); break; case KVM_SET_IDENTITY_MAP_ADDR: { u64 ident_addr; mutex_lock(&kvm->lock); r = -EINVAL; if (kvm->created_vcpus) goto set_identity_unlock; r = -EFAULT; if (copy_from_user(&ident_addr, argp, sizeof(ident_addr))) goto set_identity_unlock; r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr); set_identity_unlock: mutex_unlock(&kvm->lock); break; } case KVM_SET_NR_MMU_PAGES: r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); break; case KVM_CREATE_IRQCHIP: { mutex_lock(&kvm->lock); r = -EEXIST; if (irqchip_in_kernel(kvm)) goto create_irqchip_unlock; r = -EINVAL; if (kvm->created_vcpus) goto create_irqchip_unlock; r = kvm_pic_init(kvm); if (r) goto create_irqchip_unlock; r = kvm_ioapic_init(kvm); if (r) { kvm_pic_destroy(kvm); goto create_irqchip_unlock; } r = kvm_setup_default_irq_routing(kvm); if (r) { kvm_ioapic_destroy(kvm); kvm_pic_destroy(kvm); goto create_irqchip_unlock; } /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT); create_irqchip_unlock: mutex_unlock(&kvm->lock); break; } case KVM_CREATE_PIT: u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY; goto create_pit; case KVM_CREATE_PIT2: r = -EFAULT; if (copy_from_user(&u.pit_config, argp, sizeof(struct kvm_pit_config))) goto out; create_pit: mutex_lock(&kvm->lock); r = -EEXIST; if (kvm->arch.vpit) goto create_pit_unlock; r = -ENOENT; if (!pic_in_kernel(kvm)) goto create_pit_unlock; r = -ENOMEM; kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags); if (kvm->arch.vpit) r = 0; create_pit_unlock: mutex_unlock(&kvm->lock); break; case KVM_GET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ struct kvm_irqchip *chip; chip = memdup_user(argp, sizeof(*chip)); if (IS_ERR(chip)) { r = PTR_ERR(chip); goto out; } r = -ENXIO; if (!irqchip_kernel(kvm)) goto get_irqchip_out; r = kvm_vm_ioctl_get_irqchip(kvm, chip); if (r) goto get_irqchip_out; r = -EFAULT; if (copy_to_user(argp, chip, sizeof(*chip))) goto get_irqchip_out; r = 0; get_irqchip_out: kfree(chip); break; } case KVM_SET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ struct kvm_irqchip *chip; chip = memdup_user(argp, sizeof(*chip)); if (IS_ERR(chip)) { r = PTR_ERR(chip); goto out; } r = -ENXIO; if (!irqchip_kernel(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); set_irqchip_out: kfree(chip); break; } case KVM_GET_PIT: { r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof(struct kvm_pit_state))) goto out; r = -ENXIO; if (!kvm->arch.vpit) goto out; r = kvm_vm_ioctl_get_pit(kvm, &u.ps); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &u.ps, sizeof(struct kvm_pit_state))) goto out; r = 0; break; } case KVM_SET_PIT: { r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof(u.ps))) goto out; mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) goto set_pit_out; r = kvm_vm_ioctl_set_pit(kvm, &u.ps); set_pit_out: mutex_unlock(&kvm->lock); break; } case KVM_GET_PIT2: { r = -ENXIO; if (!kvm->arch.vpit) goto out; r = kvm_vm_ioctl_get_pit2(kvm, &u.ps2); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &u.ps2, sizeof(u.ps2))) goto out; r = 0; break; } case KVM_SET_PIT2: { r = -EFAULT; if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) goto out; mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) goto set_pit2_out; r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); set_pit2_out: mutex_unlock(&kvm->lock); break; } case KVM_REINJECT_CONTROL: { struct kvm_reinject_control control; r = -EFAULT; if (copy_from_user(&control, argp, sizeof(control))) goto out; r = -ENXIO; if (!kvm->arch.vpit) goto out; r = kvm_vm_ioctl_reinject(kvm, &control); break; } case KVM_SET_BOOT_CPU_ID: r = 0; mutex_lock(&kvm->lock); if (kvm->created_vcpus) r = -EBUSY; else kvm->arch.bsp_vcpu_id = arg; mutex_unlock(&kvm->lock); break; #ifdef CONFIG_KVM_XEN case KVM_XEN_HVM_CONFIG: { struct kvm_xen_hvm_config xhc; r = -EFAULT; if (copy_from_user(&xhc, argp, sizeof(xhc))) goto out; r = kvm_xen_hvm_config(kvm, &xhc); break; } case KVM_XEN_HVM_GET_ATTR: { struct kvm_xen_hvm_attr xha; r = -EFAULT; if (copy_from_user(&xha, argp, sizeof(xha))) goto out; r = kvm_xen_hvm_get_attr(kvm, &xha); if (!r && copy_to_user(argp, &xha, sizeof(xha))) r = -EFAULT; break; } case KVM_XEN_HVM_SET_ATTR: { struct kvm_xen_hvm_attr xha; r = -EFAULT; if (copy_from_user(&xha, argp, sizeof(xha))) goto out; r = kvm_xen_hvm_set_attr(kvm, &xha); break; } case KVM_XEN_HVM_EVTCHN_SEND: { struct kvm_irq_routing_xen_evtchn uxe; r = -EFAULT; if (copy_from_user(&uxe, argp, sizeof(uxe))) goto out; r = kvm_xen_hvm_evtchn_send(kvm, &uxe); break; } #endif case KVM_SET_CLOCK: r = kvm_vm_ioctl_set_clock(kvm, argp); break; case KVM_GET_CLOCK: r = kvm_vm_ioctl_get_clock(kvm, argp); break; case KVM_SET_TSC_KHZ: { u32 user_tsc_khz; r = -EINVAL; user_tsc_khz = (u32)arg; if (kvm_caps.has_tsc_control && user_tsc_khz >= kvm_caps.max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) user_tsc_khz = tsc_khz; WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz); r = 0; goto out; } case KVM_GET_TSC_KHZ: { r = READ_ONCE(kvm->arch.default_tsc_khz); goto out; } case KVM_MEMORY_ENCRYPT_OP: { r = -ENOTTY; if (!kvm_x86_ops.mem_enc_ioctl) goto out; r = static_call(kvm_x86_mem_enc_ioctl)(kvm, argp); break; } case KVM_MEMORY_ENCRYPT_REG_REGION: { struct kvm_enc_region region; r = -EFAULT; if (copy_from_user(®ion, argp, sizeof(region))) goto out; r = -ENOTTY; if (!kvm_x86_ops.mem_enc_register_region) goto out; r = static_call(kvm_x86_mem_enc_register_region)(kvm, ®ion); break; } case KVM_MEMORY_ENCRYPT_UNREG_REGION: { struct kvm_enc_region region; r = -EFAULT; if (copy_from_user(®ion, argp, sizeof(region))) goto out; r = -ENOTTY; if (!kvm_x86_ops.mem_enc_unregister_region) goto out; r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, ®ion); break; } #ifdef CONFIG_KVM_HYPERV case KVM_HYPERV_EVENTFD: { struct kvm_hyperv_eventfd hvevfd; r = -EFAULT; if (copy_from_user(&hvevfd, argp, sizeof(hvevfd))) goto out; r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd); break; } #endif case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; case KVM_X86_SET_MSR_FILTER: { struct kvm_msr_filter __user *user_msr_filter = argp; struct kvm_msr_filter filter; if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) return -EFAULT; r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); break; } default: r = -ENOTTY; } out: return r; } static void kvm_probe_feature_msr(u32 msr_index) { struct kvm_msr_entry msr = { .index = msr_index, }; if (kvm_get_msr_feature(&msr)) return; msr_based_features[num_msr_based_features++] = msr_index; } static void kvm_probe_msr_to_save(u32 msr_index) { u32 dummy[2]; if (rdmsr_safe(msr_index, &dummy[0], &dummy[1])) return; /* * Even MSRs that are valid in the host may not be exposed to guests in * some cases. */ switch (msr_index) { case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported()) return; break; case MSR_TSC_AUX: if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && !kvm_cpu_cap_has(X86_FEATURE_RDPID)) return; break; case MSR_IA32_UMWAIT_CONTROL: if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG)) return; break; case MSR_IA32_RTIT_CTL: case MSR_IA32_RTIT_STATUS: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) return; break; case MSR_IA32_RTIT_CR3_MATCH: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) return; break; case MSR_IA32_RTIT_OUTPUT_BASE: case MSR_IA32_RTIT_OUTPUT_MASK: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) return; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || (msr_index - MSR_IA32_RTIT_ADDR0_A >= intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)) return; break; case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >= kvm_pmu_cap.num_counters_gp) return; break; case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: if (msr_index - MSR_ARCH_PERFMON_EVENTSEL0 >= kvm_pmu_cap.num_counters_gp) return; break; case MSR_ARCH_PERFMON_FIXED_CTR0 ... MSR_ARCH_PERFMON_FIXED_CTR_MAX: if (msr_index - MSR_ARCH_PERFMON_FIXED_CTR0 >= kvm_pmu_cap.num_counters_fixed) return; break; case MSR_AMD64_PERF_CNTR_GLOBAL_CTL: case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS: case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR: if (!kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) return; break; case MSR_IA32_XFD: case MSR_IA32_XFD_ERR: if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) return; break; case MSR_IA32_TSX_CTRL: if (!(kvm_get_arch_capabilities() & ARCH_CAP_TSX_CTRL_MSR)) return; break; default: break; } msrs_to_save[num_msrs_to_save++] = msr_index; } static void kvm_init_msr_lists(void) { unsigned i; BUILD_BUG_ON_MSG(KVM_PMC_MAX_FIXED != 3, "Please update the fixed PMCs in msrs_to_save_pmu[]"); num_msrs_to_save = 0; num_emulated_msrs = 0; num_msr_based_features = 0; for (i = 0; i < ARRAY_SIZE(msrs_to_save_base); i++) kvm_probe_msr_to_save(msrs_to_save_base[i]); if (enable_pmu) { for (i = 0; i < ARRAY_SIZE(msrs_to_save_pmu); i++) kvm_probe_msr_to_save(msrs_to_save_pmu[i]); } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { if (!static_call(kvm_x86_has_emulated_msr)(NULL, emulated_msrs_all[i])) continue; emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; } for (i = KVM_FIRST_EMULATED_VMX_MSR; i <= KVM_LAST_EMULATED_VMX_MSR; i++) kvm_probe_feature_msr(i); for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) kvm_probe_feature_msr(msr_based_features_all_except_vmx[i]); } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, const void *v) { int handled = 0; int n; do { n = min(len, 8); if (!(lapic_in_kernel(vcpu) && !kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v)) && kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v)) break; handled += n; addr += n; len -= n; v += n; } while (len); return handled; } static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) { int handled = 0; int n; do { n = min(len, 8); if (!(lapic_in_kernel(vcpu) && !kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev, addr, n, v)) && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v)) break; trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, v); handled += n; addr += n; len -= n; v += n; } while (len); return handled; } void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { static_call(kvm_x86_set_segment)(vcpu, var, seg); } void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { static_call(kvm_x86_get_segment)(vcpu, var, seg); } gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.mmu; gpa_t t_gpa; BUG_ON(!mmu_is_nested(vcpu)); /* NPT walks are always user-walks */ access |= PFERR_USER_MASK; t_gpa = mmu->gva_to_gpa(vcpu, mmu, gpa, access, exception); return t_gpa; } gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); /* uses this to access any guest's mapped memory without checking CPL */ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; return mmu->gva_to_gpa(vcpu, mmu, gva, 0, exception); } static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu, u64 access, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; if (gpa == INVALID_GPA) return X86EMUL_PROPAGATE_FAULT; ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, data, offset, toread); if (ret < 0) { r = X86EMUL_IO_NEEDED; goto out; } bytes -= toread; data += toread; addr += toread; } out: return r; } /* used for instruction fetching */ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; /* Inline kvm_read_guest_virt_helper for speed. */ gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access|PFERR_FETCH_MASK, exception); if (unlikely(gpa == INVALID_GPA)) return X86EMUL_PROPAGATE_FAULT; offset = addr & (PAGE_SIZE-1); if (WARN_ON(offset + bytes > PAGE_SIZE)) bytes = (unsigned)PAGE_SIZE - offset; ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, val, offset, bytes); if (unlikely(ret < 0)) return X86EMUL_IO_NEEDED; return X86EMUL_CONTINUE; } int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; /* * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED * is returned, but our callers are not ready for that and they blindly * call kvm_inject_page_fault. Ensure that they at least do not leak * uninitialized kernel stack memory into cr2 and error code. */ memset(exception, 0, sizeof(*exception)); return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } EXPORT_SYMBOL_GPL(kvm_read_guest_virt); static int emulator_read_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception, bool system) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u64 access = 0; if (system) access |= PFERR_IMPLICIT_ACCESS; else if (static_call(kvm_x86_get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu, u64 access, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; if (gpa == INVALID_GPA) return X86EMUL_PROPAGATE_FAULT; ret = kvm_vcpu_write_guest(vcpu, gpa, data, towrite); if (ret < 0) { r = X86EMUL_IO_NEEDED; goto out; } bytes -= towrite; data += towrite; addr += towrite; } out: return r; } static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception, bool system) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u64 access = PFERR_WRITE_MASK; if (system) access |= PFERR_IMPLICIT_ACCESS; else if (static_call(kvm_x86_get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { /* kvm_write_guest_virt_system can pull in tons of pages. */ vcpu->arch.l1tf_flush_l1d = true; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, PFERR_WRITE_MASK, exception); } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); static int kvm_check_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) { return static_call(kvm_x86_check_emulate_instruction)(vcpu, emul_type, insn, insn_len); } int handle_ud(struct kvm_vcpu *vcpu) { static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; int fep_flags = READ_ONCE(force_emulation_prefix); int emul_type = EMULTYPE_TRAP_UD; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; int r; r = kvm_check_emulate_insn(vcpu, emul_type, NULL, 0); if (r != X86EMUL_CONTINUE) return 1; if (fep_flags && kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu), sig, sizeof(sig), &e) == 0 && memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) { if (fep_flags & KVM_FEP_CLEAR_RFLAGS_RF) kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) & ~X86_EFLAGS_RF); kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig)); emul_type = EMULTYPE_TRAP_UD_FORCED; } return kvm_emulate_instruction(vcpu, emul_type); } EXPORT_SYMBOL_GPL(handle_ud); static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t gpa, bool write) { /* For APIC access vmexit */ if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) return 1; if (vcpu_match_mmio_gpa(vcpu, gpa)) { trace_vcpu_match_mmio(gva, gpa, write, true); return 1; } return 0; } static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u64 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); /* * currently PKRU is only applied to ept enabled guest so * there is no pkey in EPT page table for L1 guest or EPT * shadow page table for L2 guest. */ if (vcpu_match_mmio_gva(vcpu, gva) && (!is_paging(vcpu) || !permission_fault(vcpu, vcpu->arch.walk_mmu, vcpu->arch.mmio_access, 0, access))) { *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | (gva & (PAGE_SIZE - 1)); trace_vcpu_match_mmio(gva, *gpa, write, false); return 1; } *gpa = mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); if (*gpa == INVALID_GPA) return -1; return vcpu_is_mmio_gpa(vcpu, gva, *gpa, write); } int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes) { int ret; ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes); if (ret < 0) return 0; kvm_page_track_write(vcpu, gpa, val, bytes); return 1; } struct read_write_emulator_ops { int (*read_write_prepare)(struct kvm_vcpu *vcpu, void *val, int bytes); int (*read_write_emulate)(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes); int (*read_write_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val); int (*read_write_exit_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes); bool write; }; static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) { if (vcpu->mmio_read_completed) { trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, vcpu->mmio_fragments[0].gpa, val); vcpu->mmio_read_completed = 0; return 1; } return 0; } static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { return !kvm_vcpu_read_guest(vcpu, gpa, val, bytes); } static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { return emulator_write_phys(vcpu, gpa, val, bytes); } static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val) { trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, val); return vcpu_mmio_write(vcpu, gpa, bytes, val); } static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, NULL); return X86EMUL_IO_NEEDED; } static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0]; memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len)); return X86EMUL_CONTINUE; } static const struct read_write_emulator_ops read_emultor = { .read_write_prepare = read_prepare, .read_write_emulate = read_emulate, .read_write_mmio = vcpu_mmio_read, .read_write_exit_mmio = read_exit_mmio, }; static const struct read_write_emulator_ops write_emultor = { .read_write_emulate = write_emulate, .read_write_mmio = write_mmio, .read_write_exit_mmio = write_exit_mmio, .write = true, }; static int emulator_read_write_onepage(unsigned long addr, void *val, unsigned int bytes, struct x86_exception *exception, struct kvm_vcpu *vcpu, const struct read_write_emulator_ops *ops) { gpa_t gpa; int handled, ret; bool write = ops->write; struct kvm_mmio_fragment *frag; struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; /* * If the exit was due to a NPF we may already have a GPA. * If the GPA is present, use it to avoid the GVA to GPA table walk. * Note, this cannot be used on string operations since string * operation using rep will only have the initial GPA from the NPF * occurred. */ if (ctxt->gpa_available && emulator_can_use_gpa(ctxt) && (addr & ~PAGE_MASK) == (ctxt->gpa_val & ~PAGE_MASK)) { gpa = ctxt->gpa_val; ret = vcpu_is_mmio_gpa(vcpu, addr, gpa, write); } else { ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); if (ret < 0) return X86EMUL_PROPAGATE_FAULT; } if (!ret && ops->read_write_emulate(vcpu, gpa, val, bytes)) return X86EMUL_CONTINUE; /* * Is this MMIO handled locally? */ handled = ops->read_write_mmio(vcpu, gpa, bytes, val); if (handled == bytes) return X86EMUL_CONTINUE; gpa += handled; bytes -= handled; val += handled; WARN_ON(vcpu->mmio_nr_fragments >= KVM_MAX_MMIO_FRAGMENTS); frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++]; frag->gpa = gpa; frag->data = val; frag->len = bytes; return X86EMUL_CONTINUE; } static int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, void *val, unsigned int bytes, struct x86_exception *exception, const struct read_write_emulator_ops *ops) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); gpa_t gpa; int rc; if (ops->read_write_prepare && ops->read_write_prepare(vcpu, val, bytes)) return X86EMUL_CONTINUE; vcpu->mmio_nr_fragments = 0; /* Crossing a page boundary? */ if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { int now; now = -addr & ~PAGE_MASK; rc = emulator_read_write_onepage(addr, val, now, exception, vcpu, ops); if (rc != X86EMUL_CONTINUE) return rc; addr += now; if (ctxt->mode != X86EMUL_MODE_PROT64) addr = (u32)addr; val += now; bytes -= now; } rc = emulator_read_write_onepage(addr, val, bytes, exception, vcpu, ops); if (rc != X86EMUL_CONTINUE) return rc; if (!vcpu->mmio_nr_fragments) return rc; gpa = vcpu->mmio_fragments[0].gpa; vcpu->mmio_needed = 1; vcpu->mmio_cur_fragment = 0; vcpu->run->mmio.len = min(8u, vcpu->mmio_fragments[0].len); vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write; vcpu->run->exit_reason = KVM_EXIT_MMIO; vcpu->run->mmio.phys_addr = gpa; return ops->read_write_exit_mmio(vcpu, gpa, val, bytes); } static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, void *val, unsigned int bytes, struct x86_exception *exception) { return emulator_read_write(ctxt, addr, val, bytes, exception, &read_emultor); } static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, const void *val, unsigned int bytes, struct x86_exception *exception) { return emulator_read_write(ctxt, addr, (void *)val, bytes, exception, &write_emultor); } #define emulator_try_cmpxchg_user(t, ptr, old, new) \ (__try_cmpxchg_user((t __user *)(ptr), (t *)(old), *(t *)(new), efault ## t)) static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, const void *old, const void *new, unsigned int bytes, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u64 page_line_mask; unsigned long hva; gpa_t gpa; int r; /* guests cmpxchg8b have to be emulated atomically */ if (bytes > 8 || (bytes & (bytes - 1))) goto emul_write; gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); if (gpa == INVALID_GPA || (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) goto emul_write; /* * Emulate the atomic as a straight write to avoid #AC if SLD is * enabled in the host and the access splits a cache line. */ if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) page_line_mask = ~(cache_line_size() - 1); else page_line_mask = PAGE_MASK; if (((gpa + bytes - 1) & page_line_mask) != (gpa & page_line_mask)) goto emul_write; hva = kvm_vcpu_gfn_to_hva(vcpu, gpa_to_gfn(gpa)); if (kvm_is_error_hva(hva)) goto emul_write; hva += offset_in_page(gpa); switch (bytes) { case 1: r = emulator_try_cmpxchg_user(u8, hva, old, new); break; case 2: r = emulator_try_cmpxchg_user(u16, hva, old, new); break; case 4: r = emulator_try_cmpxchg_user(u32, hva, old, new); break; case 8: r = emulator_try_cmpxchg_user(u64, hva, old, new); break; default: BUG(); } if (r < 0) return X86EMUL_UNHANDLEABLE; /* * Mark the page dirty _before_ checking whether or not the CMPXCHG was * successful, as the old value is written back on failure. Note, for * live migration, this is unnecessarily conservative as CMPXCHG writes * back the original value and the access is atomic, but KVM's ABI is * that all writes are dirty logged, regardless of the value written. */ kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa)); if (r) return X86EMUL_CMPXCHG_FAILED; kvm_page_track_write(vcpu, gpa, new, bytes); return X86EMUL_CONTINUE; emul_write: pr_warn_once("emulating exchange as write\n"); return emulator_write_emulated(ctxt, addr, new, bytes, exception); } static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, unsigned short port, void *data, unsigned int count, bool in) { unsigned i; int r; WARN_ON_ONCE(vcpu->arch.pio.count); for (i = 0; i < count; i++) { if (in) r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, port, size, data); else r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, port, size, data); if (r) { if (i == 0) goto userspace_io; /* * Userspace must have unregistered the device while PIO * was running. Drop writes / read as 0. */ if (in) memset(data, 0, size * (count - i)); break; } data += size; } return 1; userspace_io: vcpu->arch.pio.port = port; vcpu->arch.pio.in = in; vcpu->arch.pio.count = count; vcpu->arch.pio.size = size; if (in) memset(vcpu->arch.pio_data, 0, size * count); else memcpy(vcpu->arch.pio_data, data, size * count); vcpu->run->exit_reason = KVM_EXIT_IO; vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; vcpu->run->io.size = size; vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; vcpu->run->io.count = count; vcpu->run->io.port = port; return 0; } static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port, void *val, unsigned int count) { int r = emulator_pio_in_out(vcpu, size, port, val, count, true); if (r) trace_kvm_pio(KVM_PIO_IN, port, size, count, val); return r; } static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val) { int size = vcpu->arch.pio.size; unsigned int count = vcpu->arch.pio.count; memcpy(val, vcpu->arch.pio_data, size * count); trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data); vcpu->arch.pio.count = 0; } static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, int size, unsigned short port, void *val, unsigned int count) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); if (vcpu->arch.pio.count) { /* * Complete a previous iteration that required userspace I/O. * Note, @count isn't guaranteed to match pio.count as userspace * can modify ECX before rerunning the vCPU. Ignore any such * shenanigans as KVM doesn't support modifying the rep count, * and the emulator ensures @count doesn't overflow the buffer. */ complete_emulator_pio_in(vcpu, val); return 1; } return emulator_pio_in(vcpu, size, port, val, count); } static int emulator_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port, const void *val, unsigned int count) { trace_kvm_pio(KVM_PIO_OUT, port, size, count, val); return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); } static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, int size, unsigned short port, const void *val, unsigned int count) { return emulator_pio_out(emul_to_vcpu(ctxt), size, port, val, count); } static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { return static_call(kvm_x86_get_segment_base)(vcpu, seg); } static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) { kvm_mmu_invlpg(emul_to_vcpu(ctxt), address); } static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) { if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; if (static_call(kvm_x86_has_wbinvd_exit)()) { int cpu = get_cpu(); cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask, wbinvd_ipi, NULL, 1); put_cpu(); cpumask_clear(vcpu->arch.wbinvd_dirty_mask); } else wbinvd(); return X86EMUL_CONTINUE; } int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) { kvm_emulate_wbinvd_noskip(vcpu); return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) { kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } static unsigned long emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr) { return kvm_get_dr(emul_to_vcpu(ctxt), dr); } static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) { return kvm_set_dr(emul_to_vcpu(ctxt), dr, value); } static u64 mk_cr_64(u64 curr_cr, u32 new_val) { return (curr_cr & ~((1ULL << 32) - 1)) | new_val; } static unsigned long emulator_get_cr(struct x86_emulate_ctxt *ctxt, int cr) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); unsigned long value; switch (cr) { case 0: value = kvm_read_cr0(vcpu); break; case 2: value = vcpu->arch.cr2; break; case 3: value = kvm_read_cr3(vcpu); break; case 4: value = kvm_read_cr4(vcpu); break; case 8: value = kvm_get_cr8(vcpu); break; default: kvm_err("%s: unexpected cr %u\n", __func__, cr); return 0; } return value; } static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int res = 0; switch (cr) { case 0: res = kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); break; case 2: vcpu->arch.cr2 = val; break; case 3: res = kvm_set_cr3(vcpu, val); break; case 4: res = kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); break; case 8: res = kvm_set_cr8(vcpu, val); break; default: kvm_err("%s: unexpected cr %u\n", __func__, cr); res = -1; } return res; } static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { return static_call(kvm_x86_get_cpl)(emul_to_vcpu(ctxt)); } static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { static_call(kvm_x86_get_gdt)(emul_to_vcpu(ctxt), dt); } static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { static_call(kvm_x86_get_idt)(emul_to_vcpu(ctxt), dt); } static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { static_call(kvm_x86_set_gdt)(emul_to_vcpu(ctxt), dt); } static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { static_call(kvm_x86_set_idt)(emul_to_vcpu(ctxt), dt); } static unsigned long emulator_get_cached_segment_base( struct x86_emulate_ctxt *ctxt, int seg) { return get_segment_base(emul_to_vcpu(ctxt), seg); } static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector, struct desc_struct *desc, u32 *base3, int seg) { struct kvm_segment var; kvm_get_segment(emul_to_vcpu(ctxt), &var, seg); *selector = var.selector; if (var.unusable) { memset(desc, 0, sizeof(*desc)); if (base3) *base3 = 0; return false; } if (var.g) var.limit >>= 12; set_desc_limit(desc, var.limit); set_desc_base(desc, (unsigned long)var.base); #ifdef CONFIG_X86_64 if (base3) *base3 = var.base >> 32; #endif desc->type = var.type; desc->s = var.s; desc->dpl = var.dpl; desc->p = var.present; desc->avl = var.avl; desc->l = var.l; desc->d = var.db; desc->g = var.g; return true; } static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, struct desc_struct *desc, u32 base3, int seg) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); struct kvm_segment var; var.selector = selector; var.base = get_desc_base(desc); #ifdef CONFIG_X86_64 var.base |= ((u64)base3) << 32; #endif var.limit = get_desc_limit(desc); if (desc->g) var.limit = (var.limit << 12) | 0xfff; var.type = desc->type; var.dpl = desc->dpl; var.db = desc->d; var.s = desc->s; var.l = desc->l; var.g = desc->g; var.avl = desc->avl; var.present = desc->p; var.unusable = !var.present; var.padding = 0; kvm_set_segment(vcpu, &var, seg); return; } static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int r; r = kvm_get_msr_with_filter(vcpu, msr_index, pdata); if (r < 0) return X86EMUL_UNHANDLEABLE; if (r) { if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, complete_emulated_rdmsr, r)) return X86EMUL_IO_NEEDED; trace_kvm_msr_read_ex(msr_index); return X86EMUL_PROPAGATE_FAULT; } trace_kvm_msr_read(msr_index, *pdata); return X86EMUL_CONTINUE; } static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int r; r = kvm_set_msr_with_filter(vcpu, msr_index, data); if (r < 0) return X86EMUL_UNHANDLEABLE; if (r) { if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, complete_emulated_msr_access, r)) return X86EMUL_IO_NEEDED; trace_kvm_msr_write_ex(msr_index, data); return X86EMUL_PROPAGATE_FAULT; } trace_kvm_msr_write(msr_index, data); return X86EMUL_CONTINUE; } static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); } static int emulator_check_rdpmc_early(struct x86_emulate_ctxt *ctxt, u32 pmc) { return kvm_pmu_check_rdpmc_early(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata) { return kvm_pmu_rdpmc(emul_to_vcpu(ctxt), pmc, pdata); } static void emulator_halt(struct x86_emulate_ctxt *ctxt) { emul_to_vcpu(ctxt)->arch.halt_request = 1; } static int emulator_intercept(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage) { return static_call(kvm_x86_check_intercept)(emul_to_vcpu(ctxt), info, stage, &ctxt->exception); } static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only) { return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, exact_only); } static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt) { return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); } static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) { return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); } static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt) { return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); } static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) { return kvm_register_read_raw(emul_to_vcpu(ctxt), reg); } static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val) { kvm_register_write_raw(emul_to_vcpu(ctxt), reg, val); } static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) { static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked); } static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt) { return is_smm(emul_to_vcpu(ctxt)); } static bool emulator_is_guest_mode(struct x86_emulate_ctxt *ctxt) { return is_guest_mode(emul_to_vcpu(ctxt)); } #ifndef CONFIG_KVM_SMM static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) { WARN_ON_ONCE(1); return X86EMUL_UNHANDLEABLE; } #endif static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt) { kvm_make_request(KVM_REQ_TRIPLE_FAULT, emul_to_vcpu(ctxt)); } static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr) { return __kvm_set_xcr(emul_to_vcpu(ctxt), index, xcr); } static void emulator_vm_bugged(struct x86_emulate_ctxt *ctxt) { struct kvm *kvm = emul_to_vcpu(ctxt)->kvm; if (!kvm->vm_bugged) kvm_vm_bugged(kvm); } static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt, gva_t addr, unsigned int flags) { if (!kvm_x86_ops.get_untagged_addr) return addr; return static_call(kvm_x86_get_untagged_addr)(emul_to_vcpu(ctxt), addr, flags); } static const struct x86_emulate_ops emulate_ops = { .vm_bugged = emulator_vm_bugged, .read_gpr = emulator_read_gpr, .write_gpr = emulator_write_gpr, .read_std = emulator_read_std, .write_std = emulator_write_std, .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, .invlpg = emulator_invlpg, .pio_in_emulated = emulator_pio_in_emulated, .pio_out_emulated = emulator_pio_out_emulated, .get_segment = emulator_get_segment, .set_segment = emulator_set_segment, .get_cached_segment_base = emulator_get_cached_segment_base, .get_gdt = emulator_get_gdt, .get_idt = emulator_get_idt, .set_gdt = emulator_set_gdt, .set_idt = emulator_set_idt, .get_cr = emulator_get_cr, .set_cr = emulator_set_cr, .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, .set_msr_with_filter = emulator_set_msr_with_filter, .get_msr_with_filter = emulator_get_msr_with_filter, .get_msr = emulator_get_msr, .check_rdpmc_early = emulator_check_rdpmc_early, .read_pmc = emulator_read_pmc, .halt = emulator_halt, .wbinvd = emulator_wbinvd, .fix_hypercall = emulator_fix_hypercall, .intercept = emulator_intercept, .get_cpuid = emulator_get_cpuid, .guest_has_movbe = emulator_guest_has_movbe, .guest_has_fxsr = emulator_guest_has_fxsr, .guest_has_rdpid = emulator_guest_has_rdpid, .set_nmi_mask = emulator_set_nmi_mask, .is_smm = emulator_is_smm, .is_guest_mode = emulator_is_guest_mode, .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, .get_untagged_addr = emulator_get_untagged_addr, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) { u32 int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); /* * an sti; sti; sequence only disable interrupts for the first * instruction. So, if the last instruction, be it emulated or * not, left the system with the INT_STI flag enabled, it * means that the last instruction is an sti. We should not * leave the flag on in this case. The same goes for mov ss */ if (int_shadow & mask) mask = 0; if (unlikely(int_shadow || mask)) { static_call(kvm_x86_set_interrupt_shadow)(vcpu, mask); if (!mask) kvm_make_request(KVM_REQ_EVENT, vcpu); } } static void inject_emulated_exception(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; if (ctxt->exception.vector == PF_VECTOR) kvm_inject_emulated_page_fault(vcpu, &ctxt->exception); else if (ctxt->exception.error_code_valid) kvm_queue_exception_e(vcpu, ctxt->exception.vector, ctxt->exception.error_code); else kvm_queue_exception(vcpu, ctxt->exception.vector); } static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt; ctxt = kmem_cache_zalloc(x86_emulator_cache, GFP_KERNEL_ACCOUNT); if (!ctxt) { pr_err("failed to allocate vcpu's emulator\n"); return NULL; } ctxt->vcpu = vcpu; ctxt->ops = &emulate_ops; vcpu->arch.emulate_ctxt = ctxt; return ctxt; } static void init_emulate_ctxt(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int cs_db, cs_l; static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); ctxt->gpa_available = false; ctxt->eflags = kvm_get_rflags(vcpu); ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; ctxt->eip = kvm_rip_read(vcpu); ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; ctxt->interruptibility = 0; ctxt->have_exception = false; ctxt->exception.vector = -1; ctxt->perm_ok = false; init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); ctxt->op_bytes = 2; ctxt->ad_bytes = 2; ctxt->_eip = ctxt->eip + inc_eip; ret = emulate_int_real(ctxt, irq); if (ret != X86EMUL_CONTINUE) { kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); } else { ctxt->eip = ctxt->_eip; kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); } } EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, u8 ndata, u8 *insn_bytes, u8 insn_size) { struct kvm_run *run = vcpu->run; u64 info[5]; u8 info_start; /* * Zero the whole array used to retrieve the exit info, as casting to * u32 for select entries will leave some chunks uninitialized. */ memset(&info, 0, sizeof(info)); static_call(kvm_x86_get_exit_info)(vcpu, (u32 *)&info[0], &info[1], &info[2], (u32 *)&info[3], (u32 *)&info[4]); run->exit_reason = KVM_EXIT_INTERNAL_ERROR; run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION; /* * There's currently space for 13 entries, but 5 are used for the exit * reason and info. Restrict to 4 to reduce the maintenance burden * when expanding kvm_run.emulation_failure in the future. */ if (WARN_ON_ONCE(ndata > 4)) ndata = 4; /* Always include the flags as a 'data' entry. */ info_start = 1; run->emulation_failure.flags = 0; if (insn_size) { BUILD_BUG_ON((sizeof(run->emulation_failure.insn_size) + sizeof(run->emulation_failure.insn_bytes) != 16)); info_start += 2; run->emulation_failure.flags |= KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES; run->emulation_failure.insn_size = insn_size; memset(run->emulation_failure.insn_bytes, 0x90, sizeof(run->emulation_failure.insn_bytes)); memcpy(run->emulation_failure.insn_bytes, insn_bytes, insn_size); } memcpy(&run->internal.data[info_start], info, sizeof(info)); memcpy(&run->internal.data[info_start + ARRAY_SIZE(info)], data, ndata * sizeof(data[0])); run->emulation_failure.ndata = info_start + ARRAY_SIZE(info) + ndata; } static void prepare_emulation_ctxt_failure_exit(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; prepare_emulation_failure_exit(vcpu, NULL, 0, ctxt->fetch.data, ctxt->fetch.end - ctxt->fetch.data); } void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, u8 ndata) { prepare_emulation_failure_exit(vcpu, data, ndata, NULL, 0); } EXPORT_SYMBOL_GPL(__kvm_prepare_emulation_failure_exit); void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) { __kvm_prepare_emulation_failure_exit(vcpu, NULL, 0); } EXPORT_SYMBOL_GPL(kvm_prepare_emulation_failure_exit); static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { struct kvm *kvm = vcpu->kvm; ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); if (emulation_type & EMULTYPE_VMWARE_GP) { kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return 1; } if (kvm->arch.exit_on_emulation_error || (emulation_type & EMULTYPE_SKIP)) { prepare_emulation_ctxt_failure_exit(vcpu); return 0; } kvm_queue_exception(vcpu, UD_VECTOR); if (!is_guest_mode(vcpu) && static_call(kvm_x86_get_cpl)(vcpu) == 0) { prepare_emulation_ctxt_failure_exit(vcpu); return 0; } return 1; } static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type) { gpa_t gpa = cr2_or_gpa; kvm_pfn_t pfn; if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; if (WARN_ON_ONCE(is_guest_mode(vcpu)) || WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) return false; if (!vcpu->arch.mmu->root_role.direct) { /* * Write permission should be allowed since only * write access need to be emulated. */ gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); /* * If the mapping is invalid in guest, let cpu retry * it to generate fault. */ if (gpa == INVALID_GPA) return true; } /* * Do not retry the unhandleable instruction if it faults on the * readonly host memory, otherwise it will goto a infinite loop: * retry instruction -> write #PF -> emulation fail -> retry * instruction -> ... */ pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa)); /* * If the instruction failed on the error pfn, it can not be fixed, * report the error to userspace. */ if (is_error_noslot_pfn(pfn)) return false; kvm_release_pfn_clean(pfn); /* * If emulation may have been triggered by a write to a shadowed page * table, unprotect the gfn (zap any relevant SPTEs) and re-enter the * guest to let the CPU re-execute the instruction in the hope that the * CPU can cleanly execute the instruction that KVM failed to emulate. */ if (vcpu->kvm->arch.indirect_shadow_pages) kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); /* * If the failed instruction faulted on an access to page tables that * are used to translate any part of the instruction, KVM can't resolve * the issue by unprotecting the gfn, as zapping the shadow page will * result in the instruction taking a !PRESENT page fault and thus put * the vCPU into an infinite loop of page faults. E.g. KVM will create * a SPTE and write-protect the gfn to resolve the !PRESENT fault, and * then zap the SPTE to unprotect the gfn, and then do it all over * again. Report the error to userspace. */ return !(emulation_type & EMULTYPE_WRITE_PF_TO_SP); } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, gpa_t cr2_or_gpa, int emulation_type) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; last_retry_eip = vcpu->arch.last_retry_eip; last_retry_addr = vcpu->arch.last_retry_addr; /* * If the emulation is caused by #PF and it is non-page_table * writing instruction, it means the VM-EXIT is caused by shadow * page protected, we can zap the shadow page and retry this * instruction directly. * * Note: if the guest uses a non-page-table modifying instruction * on the PDE that points to the instruction, then we will unmap * the instruction and go to an infinite loop. So, we cache the * last retried eip and the last fault address, if we meet the eip * and the address again, we can break out of the potential infinite * loop. */ vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; if (WARN_ON_ONCE(is_guest_mode(vcpu)) || WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) return false; if (x86_page_table_writing_insn(ctxt)) return false; if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) return false; vcpu->arch.last_retry_eip = ctxt->eip; vcpu->arch.last_retry_addr = cr2_or_gpa; if (!vcpu->arch.mmu->root_role.direct) gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); return true; } static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, unsigned long *db) { u32 dr6 = 0; int i; u32 enable, rwlen; enable = dr7; rwlen = dr7 >> 16; for (i = 0; i < 4; i++, enable >>= 2, rwlen >>= 4) if ((enable & 3) && (rwlen & 15) == type && db[i] == addr) dr6 |= (1 << i); return dr6; } static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { kvm_run->debug.arch.dr6 = DR6_BS | DR6_ACTIVE_LOW; kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; return 0; } kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS); return 1; } int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); int r; r = static_call(kvm_x86_skip_emulated_instruction)(vcpu); if (unlikely(!r)) return 0; kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED); /* * rflags is the old, "raw" value of the flags. The new value has * not been saved yet. * * This is correct even for TF set by the guest, because "the * processor will not generate this exception after the instruction * that sets the TF flag". */ if (unlikely(rflags & X86_EFLAGS_TF)) r = kvm_vcpu_do_singlestep(vcpu); return r; } EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); static bool kvm_is_code_breakpoint_inhibited(struct kvm_vcpu *vcpu) { u32 shadow; if (kvm_get_rflags(vcpu) & X86_EFLAGS_RF) return true; /* * Intel CPUs inhibit code #DBs when MOV/POP SS blocking is active, * but AMD CPUs do not. MOV/POP SS blocking is rare, check that first * to avoid the relatively expensive CPUID lookup. */ shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); return (shadow & KVM_X86_SHADOW_INT_MOV_SS) && guest_cpuid_is_intel(vcpu); } static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int emulation_type, int *r) { WARN_ON_ONCE(emulation_type & EMULTYPE_NO_DECODE); /* * Do not check for code breakpoints if hardware has already done the * checks, as inferred from the emulation type. On NO_DECODE and SKIP, * the instruction has passed all exception checks, and all intercepted * exceptions that trigger emulation have lower priority than code * breakpoints, i.e. the fact that the intercepted exception occurred * means any code breakpoints have already been serviced. * * Note, KVM needs to check for code #DBs on EMULTYPE_TRAP_UD_FORCED as * hardware has checked the RIP of the magic prefix, but not the RIP of * the instruction being emulated. The intent of forced emulation is * to behave as if KVM intercepted the instruction without an exception * and without a prefix. */ if (emulation_type & (EMULTYPE_NO_DECODE | EMULTYPE_SKIP | EMULTYPE_TRAP_UD | EMULTYPE_VMWARE_GP | EMULTYPE_PF)) return false; if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) && (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) { struct kvm_run *kvm_run = vcpu->run; unsigned long eip = kvm_get_linear_rip(vcpu); u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0, vcpu->arch.guest_debug_dr7, vcpu->arch.eff_db); if (dr6 != 0) { kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW; kvm_run->debug.arch.pc = eip; kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; *r = 0; return true; } } if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) && !kvm_is_code_breakpoint_inhibited(vcpu)) { unsigned long eip = kvm_get_linear_rip(vcpu); u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0, vcpu->arch.dr7, vcpu->arch.db); if (dr6 != 0) { kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); *r = 1; return true; } } return false; } static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) { switch (ctxt->opcode_len) { case 1: switch (ctxt->b) { case 0xe4: /* IN */ case 0xe5: case 0xec: case 0xed: case 0xe6: /* OUT */ case 0xe7: case 0xee: case 0xef: case 0x6c: /* INS */ case 0x6d: case 0x6e: /* OUTS */ case 0x6f: return true; } break; case 2: switch (ctxt->b) { case 0x33: /* RDPMC */ return true; } break; } return false; } /* * Decode an instruction for emulation. The caller is responsible for handling * code breakpoints. Note, manually detecting code breakpoints is unnecessary * (and wrong) when emulating on an intercepted fault-like exception[*], as * code breakpoints have higher priority and thus have already been done by * hardware. * * [*] Except #MC, which is higher priority, but KVM should never emulate in * response to a machine check. */ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, void *insn, int insn_len) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int r; init_emulate_ctxt(vcpu); r = x86_decode_insn(ctxt, insn, insn_len, emulation_type); trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; return r; } EXPORT_SYMBOL_GPL(x86_decode_emulated_instruction); int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len) { int r; struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; r = kvm_check_emulate_insn(vcpu, emulation_type, insn, insn_len); if (r != X86EMUL_CONTINUE) { if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) return 1; WARN_ON_ONCE(r != X86EMUL_UNHANDLEABLE); return handle_emulation_failure(vcpu, emulation_type); } vcpu->arch.l1tf_flush_l1d = true; if (!(emulation_type & EMULTYPE_NO_DECODE)) { kvm_clear_exception_queue(vcpu); /* * Return immediately if RIP hits a code breakpoint, such #DBs * are fault-like and are higher priority than any faults on * the code fetch itself. */ if (kvm_vcpu_check_code_breakpoint(vcpu, emulation_type, &r)) return r; r = x86_decode_emulated_instruction(vcpu, emulation_type, insn, insn_len); if (r != EMULATION_OK) { if ((emulation_type & EMULTYPE_TRAP_UD) || (emulation_type & EMULTYPE_TRAP_UD_FORCED)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } if (reexecute_instruction(vcpu, cr2_or_gpa, emulation_type)) return 1; if (ctxt->have_exception && !(emulation_type & EMULTYPE_SKIP)) { /* * #UD should result in just EMULATION_FAILED, and trap-like * exception should not be encountered during decode. */ WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR || exception_type(ctxt->exception.vector) == EXCPT_TRAP); inject_emulated_exception(vcpu); return 1; } return handle_emulation_failure(vcpu, emulation_type); } } if ((emulation_type & EMULTYPE_VMWARE_GP) && !is_vmware_backdoor_opcode(ctxt)) { kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return 1; } /* * EMULTYPE_SKIP without EMULTYPE_COMPLETE_USER_EXIT is intended for * use *only* by vendor callbacks for kvm_skip_emulated_instruction(). * The caller is responsible for updating interruptibility state and * injecting single-step #DBs. */ if (emulation_type & EMULTYPE_SKIP) { if (ctxt->mode != X86EMUL_MODE_PROT64) ctxt->eip = (u32)ctxt->_eip; else ctxt->eip = ctxt->_eip; if (emulation_type & EMULTYPE_COMPLETE_USER_EXIT) { r = 1; goto writeback; } kvm_rip_write(vcpu, ctxt->eip); if (ctxt->eflags & X86_EFLAGS_RF) kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); return 1; } if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) return 1; /* this is needed for vmware backdoor interface to work since it changes registers values during IO operation */ if (vcpu->arch.emulate_regs_need_sync_from_vcpu) { vcpu->arch.emulate_regs_need_sync_from_vcpu = false; emulator_invalidate_register_cache(ctxt); } restart: if (emulation_type & EMULTYPE_PF) { /* Save the faulting GPA (cr2) in the address field */ ctxt->exception.address = cr2_or_gpa; /* With shadow page tables, cr2 contains a GVA or nGPA. */ if (vcpu->arch.mmu->root_role.direct) { ctxt->gpa_available = true; ctxt->gpa_val = cr2_or_gpa; } } else { /* Sanitize the address out of an abundance of paranoia. */ ctxt->exception.address = 0; } r = x86_emulate_insn(ctxt); if (r == EMULATION_INTERCEPTED) return 1; if (r == EMULATION_FAILED) { if (reexecute_instruction(vcpu, cr2_or_gpa, emulation_type)) return 1; return handle_emulation_failure(vcpu, emulation_type); } if (ctxt->have_exception) { WARN_ON_ONCE(vcpu->mmio_needed && !vcpu->mmio_is_write); vcpu->mmio_needed = false; r = 1; inject_emulated_exception(vcpu); } else if (vcpu->arch.pio.count) { if (!vcpu->arch.pio.in) { /* FIXME: return into emulator if single-stepping. */ vcpu->arch.pio.count = 0; } else { writeback = false; vcpu->arch.complete_userspace_io = complete_emulated_pio; } r = 0; } else if (vcpu->mmio_needed) { ++vcpu->stat.mmio_exits; if (!vcpu->mmio_is_write) writeback = false; r = 0; vcpu->arch.complete_userspace_io = complete_emulated_mmio; } else if (vcpu->arch.complete_userspace_io) { writeback = false; r = 0; } else if (r == EMULATION_RESTART) goto restart; else r = 1; writeback: if (writeback) { unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; /* * Note, EXCPT_DB is assumed to be fault-like as the emulator * only supports code breakpoints and general detect #DB, both * of which are fault-like. */ if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED); if (ctxt->is_branch) kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED); kvm_rip_write(vcpu, ctxt->eip); if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) r = kvm_vcpu_do_singlestep(vcpu); static_call_cond(kvm_x86_update_emulated_instruction)(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } /* * For STI, interrupts are shadowed; so KVM_REQ_EVENT will * do nothing, and it will be requested again as soon as * the shadow expires. But we still need to check here, * because POPF has no interrupt shadow. */ if (unlikely((ctxt->eflags & ~rflags) & X86_EFLAGS_IF)) kvm_make_request(KVM_REQ_EVENT, vcpu); } else vcpu->arch.emulate_regs_need_sync_to_vcpu = true; return r; } int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type) { return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0); } EXPORT_SYMBOL_GPL(kvm_emulate_instruction); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len) { return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len); } EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu) { vcpu->arch.pio.count = 0; return 1; } static int complete_fast_pio_out(struct kvm_vcpu *vcpu) { vcpu->arch.pio.count = 0; if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) return 1; return kvm_skip_emulated_instruction(vcpu); } static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { unsigned long val = kvm_rax_read(vcpu); int ret = emulator_pio_out(vcpu, size, port, &val, 1); if (ret) return ret; /* * Workaround userspace that relies on old KVM behavior of %rip being * incremented prior to exiting to userspace to handle "OUT 0x7e". */ if (port == 0x7e && kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) { vcpu->arch.complete_userspace_io = complete_fast_pio_out_port_0x7e; kvm_skip_emulated_instruction(vcpu); } else { vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_out; } return 0; } static int complete_fast_pio_in(struct kvm_vcpu *vcpu) { unsigned long val; /* We should only ever be called with arch.pio.count equal to 1 */ BUG_ON(vcpu->arch.pio.count != 1); if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) { vcpu->arch.pio.count = 0; return 1; } /* For size less than 4 we merge, else we zero extend */ val = (vcpu->arch.pio.size < 4) ? kvm_rax_read(vcpu) : 0; complete_emulator_pio_in(vcpu, &val); kvm_rax_write(vcpu, val); return kvm_skip_emulated_instruction(vcpu); } static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port) { unsigned long val; int ret; /* For size less than 4 we merge, else we zero extend */ val = (size < 4) ? kvm_rax_read(vcpu) : 0; ret = emulator_pio_in(vcpu, size, port, &val, 1); if (ret) { kvm_rax_write(vcpu, val); return ret; } vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_in; return 0; } int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in) { int ret; if (in) ret = kvm_fast_pio_in(vcpu, size, port); else ret = kvm_fast_pio_out(vcpu, size, port); return ret && kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_fast_pio); static int kvmclock_cpu_down_prep(unsigned int cpu) { __this_cpu_write(cpu_tsc_khz, 0); return 0; } static void tsc_khz_changed(void *data) { struct cpufreq_freqs *freq = data; unsigned long khz; WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_CONSTANT_TSC)); if (data) khz = freq->new; else khz = cpufreq_quick_get(raw_smp_processor_id()); if (!khz) khz = tsc_khz; __this_cpu_write(cpu_tsc_khz, khz); } #ifdef CONFIG_X86_64 static void kvm_hyperv_tsc_notifier(void) { struct kvm *kvm; int cpu; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_make_mclock_inprogress_request(kvm); /* no guest entries from this point */ hyperv_stop_tsc_emulation(); /* TSC frequency always matches when on Hyper-V */ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { for_each_present_cpu(cpu) per_cpu(cpu_tsc_khz, cpu) = tsc_khz; } kvm_caps.max_guest_tsc_khz = tsc_khz; list_for_each_entry(kvm, &vm_list, vm_list) { __kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); kvm_end_pvclock_update(kvm); } mutex_unlock(&kvm_lock); } #endif static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu) { struct kvm *kvm; struct kvm_vcpu *vcpu; int send_ipi = 0; unsigned long i; /* * We allow guests to temporarily run on slowing clocks, * provided we notify them after, or to run on accelerating * clocks, provided we notify them before. Thus time never * goes backwards. * * However, we have a problem. We can't atomically update * the frequency of a given CPU from this function; it is * merely a notifier, which can be called from any CPU. * Changing the TSC frequency at arbitrary points in time * requires a recomputation of local variables related to * the TSC for each VCPU. We must flag these local variables * to be updated and be sure the update takes place with the * new frequency before any guests proceed. * * Unfortunately, the combination of hotplug CPU and frequency * change creates an intractable locking scenario; the order * of when these callouts happen is undefined with respect to * CPU hotplug, and they can race with each other. As such, * merely setting per_cpu(cpu_tsc_khz) = X during a hotadd is * undefined; you can actually have a CPU frequency change take * place in between the computation of X and the setting of the * variable. To protect against this problem, all updates of * the per_cpu tsc_khz variable are done in an interrupt * protected IPI, and all callers wishing to update the value * must wait for a synchronous IPI to complete (which is trivial * if the caller is on the CPU already). This establishes the * necessary total order on variable updates. * * Note that because a guest time update may take place * anytime after the setting of the VCPU's request bit, the * correct TSC value must be set before the request. However, * to ensure the update actually makes it to any guest which * starts running in hardware virtualization between the set * and the acquisition of the spinlock, we must also ping the * CPU after setting the request bit. * */ smp_call_function_single(cpu, tsc_khz_changed, freq, 1); mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != cpu) continue; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); if (vcpu->cpu != raw_smp_processor_id()) send_ipi = 1; } } mutex_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* * We upscale the frequency. Must make the guest * doesn't see old kvmclock values while running with * the new frequency, otherwise we risk the guest sees * time go backwards. * * In case we update the frequency for another cpu * (which might be in guest context) send an interrupt * to kick the cpu out of guest context. Next time * guest context is entered kvmclock will be updated, * so the guest will not see stale values. */ smp_call_function_single(cpu, tsc_khz_changed, freq, 1); } } static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { struct cpufreq_freqs *freq = data; int cpu; if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) return 0; if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) return 0; for_each_cpu(cpu, freq->policy->cpus) __kvmclock_cpufreq_notifier(freq, cpu); return 0; } static struct notifier_block kvmclock_cpufreq_notifier_block = { .notifier_call = kvmclock_cpufreq_notifier }; static int kvmclock_cpu_online(unsigned int cpu) { tsc_khz_changed(NULL); return 0; } static void kvm_timer_init(void) { if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { max_tsc_khz = tsc_khz; if (IS_ENABLED(CONFIG_CPU_FREQ)) { struct cpufreq_policy *policy; int cpu; cpu = get_cpu(); policy = cpufreq_cpu_get(cpu); if (policy) { if (policy->cpuinfo.max_freq) max_tsc_khz = policy->cpuinfo.max_freq; cpufreq_cpu_put(policy); } put_cpu(); } cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online", kvmclock_cpu_online, kvmclock_cpu_down_prep); } } #ifdef CONFIG_X86_64 static void pvclock_gtod_update_fn(struct work_struct *work) { struct kvm *kvm; struct kvm_vcpu *vcpu; unsigned long i; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); atomic_set(&kvm_guest_has_master_clock, 0); mutex_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); /* * Indirection to move queue_work() out of the tk_core.seq write held * region to prevent possible deadlocks against time accessors which * are invoked with work related locks held. */ static void pvclock_irq_work_fn(struct irq_work *w) { queue_work(system_long_wq, &pvclock_gtod_work); } static DEFINE_IRQ_WORK(pvclock_irq_work, pvclock_irq_work_fn); /* * Notification about pvclock gtod data update. */ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, void *priv) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; struct timekeeper *tk = priv; update_pvclock_gtod(tk); /* * Disable master clock if host does not trust, or does not use, * TSC based clocksource. Delegate queue_work() to irq_work as * this is invoked with tk_core.seq write held. */ if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) && atomic_read(&kvm_guest_has_master_clock) != 0) irq_work_queue(&pvclock_irq_work); return 0; } static struct notifier_block pvclock_gtod_notifier = { .notifier_call = pvclock_gtod_notify, }; #endif static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) { memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); #define __KVM_X86_OP(func) \ static_call_update(kvm_x86_##func, kvm_x86_ops.func); #define KVM_X86_OP(func) \ WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func) #define KVM_X86_OP_OPTIONAL __KVM_X86_OP #define KVM_X86_OP_OPTIONAL_RET0(func) \ static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \ (void *)__static_call_return0); #include <asm/kvm-x86-ops.h> #undef __KVM_X86_OP kvm_pmu_ops_update(ops->pmu_ops); } static int kvm_x86_check_processor_compatibility(void) { int cpu = smp_processor_id(); struct cpuinfo_x86 *c = &cpu_data(cpu); /* * Compatibility checks are done when loading KVM and when enabling * hardware, e.g. during CPU hotplug, to ensure all online CPUs are * compatible, i.e. KVM should never perform a compatibility check on * an offline CPU. */ WARN_ON(!cpu_online(cpu)); if (__cr4_reserved_bits(cpu_has, c) != __cr4_reserved_bits(cpu_has, &boot_cpu_data)) return -EIO; return static_call(kvm_x86_check_processor_compatibility)(); } static void kvm_x86_check_cpu_compat(void *ret) { *(int *)ret = kvm_x86_check_processor_compatibility(); } int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) { u64 host_pat; int r, cpu; guard(mutex)(&vendor_module_lock); if (kvm_x86_ops.hardware_enable) { pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; } /* * KVM explicitly assumes that the guest has an FPU and * FXSAVE/FXRSTOR. For example, the KVM_GET_FPU explicitly casts the * vCPU's FPU state as a fxregs_state struct. */ if (!boot_cpu_has(X86_FEATURE_FPU) || !boot_cpu_has(X86_FEATURE_FXSR)) { pr_err("inadequate fpu\n"); return -EOPNOTSUPP; } if (IS_ENABLED(CONFIG_PREEMPT_RT) && !boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { pr_err("RT requires X86_FEATURE_CONSTANT_TSC\n"); return -EOPNOTSUPP; } /* * KVM assumes that PAT entry '0' encodes WB memtype and simply zeroes * the PAT bits in SPTEs. Bail if PAT[0] is programmed to something * other than WB. Note, EPT doesn't utilize the PAT, but don't bother * with an exception. PAT[0] is set to WB on RESET and also by the * kernel, i.e. failure indicates a kernel bug or broken firmware. */ if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) || (host_pat & GENMASK(2, 0)) != 6) { pr_err("host PAT[0] is not WB\n"); return -EIO; } memset(&kvm_caps, 0, sizeof(kvm_caps)); x86_emulator_cache = kvm_alloc_emulator_cache(); if (!x86_emulator_cache) { pr_err("failed to allocate cache for x86 emulator\n"); return -ENOMEM; } user_return_msrs = alloc_percpu(struct kvm_user_return_msrs); if (!user_return_msrs) { pr_err("failed to allocate percpu kvm_user_return_msrs\n"); r = -ENOMEM; goto out_free_x86_emulator_cache; } kvm_nr_uret_msrs = 0; r = kvm_mmu_vendor_module_init(); if (r) goto out_free_percpu; kvm_caps.supported_vm_types = BIT(KVM_X86_DEFAULT_VM); kvm_caps.supported_mce_cap = MCG_CTL_P | MCG_SER_P; if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; } rdmsrl_safe(MSR_EFER, &host_efer); if (boot_cpu_has(X86_FEATURE_XSAVES)) rdmsrl(MSR_IA32_XSS, host_xss); kvm_init_pmu_capability(ops->pmu_ops); if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, host_arch_capabilities); r = ops->hardware_setup(); if (r != 0) goto out_mmu_exit; kvm_ops_update(ops); for_each_online_cpu(cpu) { smp_call_function_single(cpu, kvm_x86_check_cpu_compat, &r, 1); if (r < 0) goto out_unwind_ops; } /* * Point of no return! DO NOT add error paths below this point unless * absolutely necessary, as most operations from this point forward * require unwinding. */ kvm_timer_init(); if (pi_inject_timer == -1) pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER); #ifdef CONFIG_X86_64 pvclock_gtod_register_notifier(&pvclock_gtod_notifier); if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) set_hv_tscchange_cb(kvm_hyperv_tsc_notifier); #endif kvm_register_perf_callbacks(ops->handle_intel_pt_intr); if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled) kvm_caps.supported_vm_types |= BIT(KVM_X86_SW_PROTECTED_VM); if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) kvm_caps.supported_xss = 0; #define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); #undef __kvm_cpu_cap_has if (kvm_caps.has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that * fit into a signed integer. * A min value is not calculated because it will always * be 1 on all machines. */ u64 max = min(0x7fffffffULL, __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz)); kvm_caps.max_guest_tsc_khz = max; } kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; kvm_init_msr_lists(); return 0; out_unwind_ops: kvm_x86_ops.hardware_enable = NULL; static_call(kvm_x86_hardware_unsetup)(); out_mmu_exit: kvm_mmu_vendor_module_exit(); out_free_percpu: free_percpu(user_return_msrs); out_free_x86_emulator_cache: kmem_cache_destroy(x86_emulator_cache); return r; } EXPORT_SYMBOL_GPL(kvm_x86_vendor_init); void kvm_x86_vendor_exit(void) { kvm_unregister_perf_callbacks(); #ifdef CONFIG_X86_64 if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) clear_hv_tscchange_cb(); #endif kvm_lapic_exit(); if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); } #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); irq_work_sync(&pvclock_irq_work); cancel_work_sync(&pvclock_gtod_work); #endif static_call(kvm_x86_hardware_unsetup)(); kvm_mmu_vendor_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled); WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); #endif mutex_lock(&vendor_module_lock); kvm_x86_ops.hardware_enable = NULL; mutex_unlock(&vendor_module_lock); } EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit); static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { /* * The vCPU has halted, e.g. executed HLT. Update the run state if the * local APIC is in-kernel, the run loop will detect the non-runnable * state and halt the vCPU. Exit to userspace if the local APIC is * managed by userspace, in which case userspace is responsible for * handling wake events. */ ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { vcpu->arch.mp_state = state; return 1; } else { vcpu->run->exit_reason = reason; return 0; } } int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) { return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); } EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); int kvm_emulate_halt(struct kvm_vcpu *vcpu) { int ret = kvm_skip_emulated_instruction(vcpu); /* * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered * KVM_EXIT_DEBUG here. */ return kvm_emulate_halt_noskip(vcpu) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_halt); int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) { int ret = kvm_skip_emulated_instruction(vcpu); return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) { struct kvm_clock_pairing clock_pairing; struct timespec64 ts; u64 cycle; int ret; if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; /* * When tsc is in permanent catchup mode guests won't be able to use * pvclock_read_retry loop to get consistent view of pvclock */ if (vcpu->arch.tsc_always_catchup) return -KVM_EOPNOTSUPP; if (!kvm_get_walltime_and_clockread(&ts, &cycle)) return -KVM_EOPNOTSUPP; clock_pairing.sec = ts.tv_sec; clock_pairing.nsec = ts.tv_nsec; clock_pairing.tsc = kvm_read_l1_tsc(vcpu, cycle); clock_pairing.flags = 0; memset(&clock_pairing.pad, 0, sizeof(clock_pairing.pad)); ret = 0; if (kvm_write_guest(vcpu->kvm, paddr, &clock_pairing, sizeof(struct kvm_clock_pairing))) ret = -KVM_EFAULT; return ret; } #endif /* * kvm_pv_kick_cpu_op: Kick a vcpu. * * @apicid - apicid of vcpu to be kicked. */ static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid) { /* * All other fields are unused for APIC_DM_REMRD, but may be consumed by * common code, e.g. for tracing. Defer initialization to the compiler. */ struct kvm_lapic_irq lapic_irq = { .delivery_mode = APIC_DM_REMRD, .dest_mode = APIC_DEST_PHYSICAL, .shorthand = APIC_DEST_NOSHORT, .dest_id = apicid, }; kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } bool kvm_apicv_activated(struct kvm *kvm) { return (READ_ONCE(kvm->arch.apicv_inhibit_reasons) == 0); } EXPORT_SYMBOL_GPL(kvm_apicv_activated); bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu) { ulong vm_reasons = READ_ONCE(vcpu->kvm->arch.apicv_inhibit_reasons); ulong vcpu_reasons = static_call(kvm_x86_vcpu_get_apicv_inhibit_reasons)(vcpu); return (vm_reasons | vcpu_reasons) == 0; } EXPORT_SYMBOL_GPL(kvm_vcpu_apicv_activated); static void set_or_clear_apicv_inhibit(unsigned long *inhibits, enum kvm_apicv_inhibit reason, bool set) { if (set) __set_bit(reason, inhibits); else __clear_bit(reason, inhibits); trace_kvm_apicv_inhibit_changed(reason, set, *inhibits); } static void kvm_apicv_init(struct kvm *kvm) { enum kvm_apicv_inhibit reason = enable_apicv ? APICV_INHIBIT_REASON_ABSENT : APICV_INHIBIT_REASON_DISABLE; set_or_clear_apicv_inhibit(&kvm->arch.apicv_inhibit_reasons, reason, true); init_rwsem(&kvm->arch.apicv_update_lock); } static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) { struct kvm_vcpu *target = NULL; struct kvm_apic_map *map; vcpu->stat.directed_yield_attempted++; if (single_task_running()) goto no_yield; rcu_read_lock(); map = rcu_dereference(vcpu->kvm->arch.apic_map); if (likely(map) && dest_id <= map->max_apic_id && map->phys_map[dest_id]) target = map->phys_map[dest_id]->vcpu; rcu_read_unlock(); if (!target || !READ_ONCE(target->ready)) goto no_yield; /* Ignore requests to yield to self */ if (vcpu == target) goto no_yield; if (kvm_vcpu_yield_to(target) <= 0) goto no_yield; vcpu->stat.directed_yield_successful++; no_yield: return; } static int complete_hypercall_exit(struct kvm_vcpu *vcpu) { u64 ret = vcpu->run->hypercall.ret; if (!is_64_bit_mode(vcpu)) ret = (u32)ret; kvm_rax_write(vcpu, ret); ++vcpu->stat.hypercalls; return kvm_skip_emulated_instruction(vcpu); } unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3, int op_64_bit, int cpl) { unsigned long ret; trace_kvm_hypercall(nr, a0, a1, a2, a3); if (!op_64_bit) { nr &= 0xFFFFFFFF; a0 &= 0xFFFFFFFF; a1 &= 0xFFFFFFFF; a2 &= 0xFFFFFFFF; a3 &= 0xFFFFFFFF; } if (cpl) { ret = -KVM_EPERM; goto out; } ret = -KVM_ENOSYS; switch (nr) { case KVM_HC_VAPIC_POLL_IRQ: ret = 0; break; case KVM_HC_KICK_CPU: if (!guest_pv_has(vcpu, KVM_FEATURE_PV_UNHALT)) break; kvm_pv_kick_cpu_op(vcpu->kvm, a1); kvm_sched_yield(vcpu, a1); ret = 0; break; #ifdef CONFIG_X86_64 case KVM_HC_CLOCK_PAIRING: ret = kvm_pv_clock_pairing(vcpu, a0, a1); break; #endif case KVM_HC_SEND_IPI: if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SEND_IPI)) break; ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit); break; case KVM_HC_SCHED_YIELD: if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SCHED_YIELD)) break; kvm_sched_yield(vcpu, a0); ret = 0; break; case KVM_HC_MAP_GPA_RANGE: { u64 gpa = a0, npages = a1, attrs = a2; ret = -KVM_ENOSYS; if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) break; if (!PAGE_ALIGNED(gpa) || !npages || gpa_to_gfn(gpa) + npages <= gpa_to_gfn(gpa)) { ret = -KVM_EINVAL; break; } vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; vcpu->run->hypercall.args[0] = gpa; vcpu->run->hypercall.args[1] = npages; vcpu->run->hypercall.args[2] = attrs; vcpu->run->hypercall.flags = 0; if (op_64_bit) vcpu->run->hypercall.flags |= KVM_EXIT_HYPERCALL_LONG_MODE; WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ); vcpu->arch.complete_userspace_io = complete_hypercall_exit; /* stat is incremented on completion. */ return 0; } default: ret = -KVM_ENOSYS; break; } out: ++vcpu->stat.hypercalls; return ret; } EXPORT_SYMBOL_GPL(__kvm_emulate_hypercall); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; int op_64_bit; int cpl; if (kvm_xen_hypercall_enabled(vcpu->kvm)) return kvm_xen_hypercall(vcpu); if (kvm_hv_hypercall_enabled(vcpu)) return kvm_hv_hypercall(vcpu); nr = kvm_rax_read(vcpu); a0 = kvm_rbx_read(vcpu); a1 = kvm_rcx_read(vcpu); a2 = kvm_rdx_read(vcpu); a3 = kvm_rsi_read(vcpu); op_64_bit = is_64_bit_hypercall(vcpu); cpl = static_call(kvm_x86_get_cpl)(vcpu); ret = __kvm_emulate_hypercall(vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl); if (nr == KVM_HC_MAP_GPA_RANGE && !ret) /* MAP_GPA tosses the request to the user space. */ return 0; if (!op_64_bit) ret = (u32)ret; kvm_rax_write(vcpu, ret); return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); char instruction[3]; unsigned long rip = kvm_rip_read(vcpu); /* * If the quirk is disabled, synthesize a #UD and let the guest pick up * the pieces. */ if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_FIX_HYPERCALL_INSN)) { ctxt->exception.error_code_valid = false; ctxt->exception.vector = UD_VECTOR; ctxt->have_exception = true; return X86EMUL_PROPAGATE_FAULT; } static_call(kvm_x86_patch_hypercall)(vcpu, instruction); return emulator_write_emulated(ctxt, rip, instruction, 3, &ctxt->exception); } static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { return vcpu->run->request_interrupt_window && likely(!pic_in_kernel(vcpu->kvm)); } /* Called within kvm->srcu read side. */ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu); kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; } static void update_cr8_intercept(struct kvm_vcpu *vcpu) { int max_irr, tpr; if (!kvm_x86_ops.update_cr8_intercept) return; if (!lapic_in_kernel(vcpu)) return; if (vcpu->arch.apic->apicv_active) return; if (!vcpu->arch.apic->vapic_addr) max_irr = kvm_lapic_find_highest_irr(vcpu); else max_irr = -1; if (max_irr != -1) max_irr >>= 4; tpr = kvm_lapic_get_cr8(vcpu); static_call(kvm_x86_update_cr8_intercept)(vcpu, tpr, max_irr); } int kvm_check_nested_events(struct kvm_vcpu *vcpu) { if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { kvm_x86_ops.nested_ops->triple_fault(vcpu); return 1; } return kvm_x86_ops.nested_ops->check_events(vcpu); } static void kvm_inject_exception(struct kvm_vcpu *vcpu) { /* * Suppress the error code if the vCPU is in Real Mode, as Real Mode * exceptions don't report error codes. The presence of an error code * is carried with the exception and only stripped when the exception * is injected as intercepted #PF VM-Exits for AMD's Paged Real Mode do * report an error code despite the CPU being in Real Mode. */ vcpu->arch.exception.has_error_code &= is_protmode(vcpu); trace_kvm_inj_exception(vcpu->arch.exception.vector, vcpu->arch.exception.has_error_code, vcpu->arch.exception.error_code, vcpu->arch.exception.injected); static_call(kvm_x86_inject_exception)(vcpu); } /* * Check for any event (interrupt or exception) that is ready to be injected, * and if there is at least one event, inject the event with the highest * priority. This handles both "pending" events, i.e. events that have never * been injected into the guest, and "injected" events, i.e. events that were * injected as part of a previous VM-Enter, but weren't successfully delivered * and need to be re-injected. * * Note, this is not guaranteed to be invoked on a guest instruction boundary, * i.e. doesn't guarantee that there's an event window in the guest. KVM must * be able to inject exceptions in the "middle" of an instruction, and so must * also be able to re-inject NMIs and IRQs in the middle of an instruction. * I.e. for exceptions and re-injected events, NOT invoking this on instruction * boundaries is necessary and correct. * * For simplicity, KVM uses a single path to inject all events (except events * that are injected directly from L1 to L2) and doesn't explicitly track * instruction boundaries for asynchronous events. However, because VM-Exits * that can occur during instruction execution typically result in KVM skipping * the instruction or injecting an exception, e.g. instruction and exception * intercepts, and because pending exceptions have higher priority than pending * interrupts, KVM still honors instruction boundaries in most scenarios. * * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip * the instruction or inject an exception, then KVM can incorrecty inject a new * asynchronous event if the event became pending after the CPU fetched the * instruction (in the guest). E.g. if a page fault (#PF, #NPF, EPT violation) * occurs and is resolved by KVM, a coincident NMI, SMI, IRQ, etc... can be * injected on the restarted instruction instead of being deferred until the * instruction completes. * * In practice, this virtualization hole is unlikely to be observed by the * guest, and even less likely to cause functional problems. To detect the * hole, the guest would have to trigger an event on a side effect of an early * phase of instruction execution, e.g. on the instruction fetch from memory. * And for it to be a functional problem, the guest would need to depend on the * ordering between that side effect, the instruction completing, _and_ the * delivery of the asynchronous event. */ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, bool *req_immediate_exit) { bool can_inject; int r; /* * Process nested events first, as nested VM-Exit supersedes event * re-injection. If there's an event queued for re-injection, it will * be saved into the appropriate vmc{b,s}12 fields on nested VM-Exit. */ if (is_guest_mode(vcpu)) r = kvm_check_nested_events(vcpu); else r = 0; /* * Re-inject exceptions and events *especially* if immediate entry+exit * to/from L2 is needed, as any event that has already been injected * into L2 needs to complete its lifecycle before injecting a new event. * * Don't re-inject an NMI or interrupt if there is a pending exception. * This collision arises if an exception occurred while vectoring the * injected event, KVM intercepted said exception, and KVM ultimately * determined the fault belongs to the guest and queues the exception * for injection back into the guest. * * "Injected" interrupts can also collide with pending exceptions if * userspace ignores the "ready for injection" flag and blindly queues * an interrupt. In that case, prioritizing the exception is correct, * as the exception "occurred" before the exit to userspace. Trap-like * exceptions, e.g. most #DBs, have higher priority than interrupts. * And while fault-like exceptions, e.g. #GP and #PF, are the lowest * priority, they're only generated (pended) during instruction * execution, and interrupts are recognized at instruction boundaries. * Thus a pending fault-like exception means the fault occurred on the * *previous* instruction and must be serviced prior to recognizing any * new events in order to fully complete the previous instruction. */ if (vcpu->arch.exception.injected) kvm_inject_exception(vcpu); else if (kvm_is_exception_pending(vcpu)) ; /* see above */ else if (vcpu->arch.nmi_injected) static_call(kvm_x86_inject_nmi)(vcpu); else if (vcpu->arch.interrupt.injected) static_call(kvm_x86_inject_irq)(vcpu, true); /* * Exceptions that morph to VM-Exits are handled above, and pending * exceptions on top of injected exceptions that do not VM-Exit should * either morph to #DF or, sadly, override the injected exception. */ WARN_ON_ONCE(vcpu->arch.exception.injected && vcpu->arch.exception.pending); /* * Bail if immediate entry+exit to/from the guest is needed to complete * nested VM-Enter or event re-injection so that a different pending * event can be serviced (or if KVM needs to exit to userspace). * * Otherwise, continue processing events even if VM-Exit occurred. The * VM-Exit will have cleared exceptions that were meant for L2, but * there may now be events that can be injected into L1. */ if (r < 0) goto out; /* * A pending exception VM-Exit should either result in nested VM-Exit * or force an immediate re-entry and exit to/from L2, and exception * VM-Exits cannot be injected (flag should _never_ be set). */ WARN_ON_ONCE(vcpu->arch.exception_vmexit.injected || vcpu->arch.exception_vmexit.pending); /* * New events, other than exceptions, cannot be injected if KVM needs * to re-inject a previous event. See above comments on re-injecting * for why pending exceptions get priority. */ can_inject = !kvm_event_needs_reinjection(vcpu); if (vcpu->arch.exception.pending) { /* * Fault-class exceptions, except #DBs, set RF=1 in the RFLAGS * value pushed on the stack. Trap-like exception and all #DBs * leave RF as-is (KVM follows Intel's behavior in this regard; * AMD states that code breakpoint #DBs excplitly clear RF=0). * * Note, most versions of Intel's SDM and AMD's APM incorrectly * describe the behavior of General Detect #DBs, which are * fault-like. They do _not_ set RF, a la code breakpoints. */ if (exception_type(vcpu->arch.exception.vector) == EXCPT_FAULT) __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) | X86_EFLAGS_RF); if (vcpu->arch.exception.vector == DB_VECTOR) { kvm_deliver_exception_payload(vcpu, &vcpu->arch.exception); if (vcpu->arch.dr7 & DR7_GD) { vcpu->arch.dr7 &= ~DR7_GD; kvm_update_dr7(vcpu); } } kvm_inject_exception(vcpu); vcpu->arch.exception.pending = false; vcpu->arch.exception.injected = true; can_inject = false; } /* Don't inject interrupts if the user asked to avoid doing so */ if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) return 0; /* * Finally, inject interrupt events. If an event cannot be injected * due to architectural conditions (e.g. IF=0) a window-open exit * will re-request KVM_REQ_EVENT. Sometimes however an event is pending * and can architecturally be injected, but we cannot do it right now: * an interrupt could have arrived just now and we have to inject it * as a vmexit, or there could already an event in the queue, which is * indicated by can_inject. In that case we request an immediate exit * in order to make progress and get back here for another iteration. * The kvm_x86_ops hooks communicate this by returning -EBUSY. */ #ifdef CONFIG_KVM_SMM if (vcpu->arch.smi_pending) { r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto out; if (r) { vcpu->arch.smi_pending = false; ++vcpu->arch.smi_count; enter_smm(vcpu); can_inject = false; } else static_call(kvm_x86_enable_smi_window)(vcpu); } #endif if (vcpu->arch.nmi_pending) { r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto out; if (r) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; static_call(kvm_x86_inject_nmi)(vcpu); can_inject = false; WARN_ON(static_call(kvm_x86_nmi_allowed)(vcpu, true) < 0); } if (vcpu->arch.nmi_pending) static_call(kvm_x86_enable_nmi_window)(vcpu); } if (kvm_cpu_has_injectable_intr(vcpu)) { r = can_inject ? static_call(kvm_x86_interrupt_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto out; if (r) { int irq = kvm_cpu_get_interrupt(vcpu); if (!WARN_ON_ONCE(irq == -1)) { kvm_queue_interrupt(vcpu, irq, false); static_call(kvm_x86_inject_irq)(vcpu, false); WARN_ON(static_call(kvm_x86_interrupt_allowed)(vcpu, true) < 0); } } if (kvm_cpu_has_injectable_intr(vcpu)) static_call(kvm_x86_enable_irq_window)(vcpu); } if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && kvm_x86_ops.nested_ops->has_events(vcpu)) *req_immediate_exit = true; /* * KVM must never queue a new exception while injecting an event; KVM * is done emulating and should only propagate the to-be-injected event * to the VMCS/VMCB. Queueing a new exception can put the vCPU into an * infinite loop as KVM will bail from VM-Enter to inject the pending * exception and start the cycle all over. * * Exempt triple faults as they have special handling and won't put the * vCPU into an infinite loop. Triple fault can be queued when running * VMX without unrestricted guest, as that requires KVM to emulate Real * Mode events (see kvm_inject_realmode_interrupt()). */ WARN_ON_ONCE(vcpu->arch.exception.pending || vcpu->arch.exception_vmexit.pending); return 0; out: if (r == -EBUSY) { *req_immediate_exit = true; r = 0; } return r; } static void process_nmi(struct kvm_vcpu *vcpu) { unsigned int limit; /* * x86 is limited to one NMI pending, but because KVM can't react to * incoming NMIs as quickly as bare metal, e.g. if the vCPU is * scheduled out, KVM needs to play nice with two queued NMIs showing * up at the same time. To handle this scenario, allow two NMIs to be * (temporarily) pending so long as NMIs are not blocked and KVM is not * waiting for a previous NMI injection to complete (which effectively * blocks NMIs). KVM will immediately inject one of the two NMIs, and * will request an NMI window to handle the second NMI. */ if (static_call(kvm_x86_get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected) limit = 1; else limit = 2; /* * Adjust the limit to account for pending virtual NMIs, which aren't * tracked in vcpu->arch.nmi_pending. */ if (static_call(kvm_x86_is_vnmi_pending)(vcpu)) limit--; vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); if (vcpu->arch.nmi_pending && (static_call(kvm_x86_set_vnmi_pending)(vcpu))) vcpu->arch.nmi_pending--; if (vcpu->arch.nmi_pending) kvm_make_request(KVM_REQ_EVENT, vcpu); } /* Return total number of NMIs pending injection to the VM */ int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu) { return vcpu->arch.nmi_pending + static_call(kvm_x86_is_vnmi_pending)(vcpu); } void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, unsigned long *vcpu_bitmap) { kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, vcpu_bitmap); } void kvm_make_scan_ioapic_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); } void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; bool activate; if (!lapic_in_kernel(vcpu)) return; down_read(&vcpu->kvm->arch.apicv_update_lock); preempt_disable(); /* Do not activate APICV when APIC is disabled */ activate = kvm_vcpu_apicv_activated(vcpu) && (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED); if (apic->apicv_active == activate) goto out; apic->apicv_active = activate; kvm_apic_update_apicv(vcpu); static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu); /* * When APICv gets disabled, we may still have injected interrupts * pending. At the same time, KVM_REQ_EVENT may not be set as APICv was * still active when the interrupt got accepted. Make sure * kvm_check_and_inject_events() is called to check for that. */ if (!apic->apicv_active) kvm_make_request(KVM_REQ_EVENT, vcpu); out: preempt_enable(); up_read(&vcpu->kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_GPL(__kvm_vcpu_update_apicv); static void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) return; /* * Due to sharing page tables across vCPUs, the xAPIC memslot must be * deleted if any vCPU has xAPIC virtualization and x2APIC enabled, but * and hardware doesn't support x2APIC virtualization. E.g. some AMD * CPUs support AVIC but not x2APIC. KVM still allows enabling AVIC in * this case so that KVM can the AVIC doorbell to inject interrupts to * running vCPUs, but KVM must not create SPTEs for the APIC base as * the vCPU would incorrectly be able to access the vAPIC page via MMIO * despite being in x2APIC mode. For simplicity, inhibiting the APIC * access page is sticky. */ if (apic_x2apic_mode(vcpu->arch.apic) && kvm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization) kvm_inhibit_apic_access_page(vcpu); __kvm_vcpu_update_apicv(vcpu); } void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set) { unsigned long old, new; lockdep_assert_held_write(&kvm->arch.apicv_update_lock); if (!(kvm_x86_ops.required_apicv_inhibits & BIT(reason))) return; old = new = kvm->arch.apicv_inhibit_reasons; set_or_clear_apicv_inhibit(&new, reason, set); if (!!old != !!new) { /* * Kick all vCPUs before setting apicv_inhibit_reasons to avoid * false positives in the sanity check WARN in svm_vcpu_run(). * This task will wait for all vCPUs to ack the kick IRQ before * updating apicv_inhibit_reasons, and all other vCPUs will * block on acquiring apicv_update_lock so that vCPUs can't * redo svm_vcpu_run() without seeing the new inhibit state. * * Note, holding apicv_update_lock and taking it in the read * side (handling the request) also prevents other vCPUs from * servicing the request with a stale apicv_inhibit_reasons. */ kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); kvm->arch.apicv_inhibit_reasons = new; if (new) { unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE); int idx = srcu_read_lock(&kvm->srcu); kvm_zap_gfn_range(kvm, gfn, gfn+1); srcu_read_unlock(&kvm->srcu, idx); } } else { kvm->arch.apicv_inhibit_reasons = new; } } void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set) { if (!enable_apicv) return; down_write(&kvm->arch.apicv_update_lock); __kvm_set_or_clear_apicv_inhibit(kvm, reason, set); up_write(&kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_GPL(kvm_set_or_clear_apicv_inhibit); static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { if (!kvm_apic_present(vcpu)) return; bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); if (is_guest_mode(vcpu)) vcpu->arch.load_eoi_exitmap_pending = true; else kvm_make_request(KVM_REQ_LOAD_EOI_EXITMAP, vcpu); } static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) { if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; #ifdef CONFIG_KVM_HYPERV if (to_hv_vcpu(vcpu)) { u64 eoi_exit_bitmap[4]; bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); return; } #endif static_call_cond(kvm_x86_load_eoi_exitmap)( vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm); } static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) return; static_call_cond(kvm_x86_set_apic_access_page_addr)(vcpu); } /* * Called within kvm->srcu read side. * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. */ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; bool req_int_win = dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); fastpath_t exit_fastpath; bool req_immediate_exit = false; if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) { r = -EIO; goto out; } if (kvm_dirty_ring_check_request(vcpu)) { r = 0; goto out; } if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { r = 0; goto out; } } if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) kvm_mmu_free_obsolete_roots(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) __kvm_migrate_timers(vcpu); if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu)) kvm_update_masterclock(vcpu->kvm); if (kvm_check_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu)) kvm_gen_kvmclock_update(vcpu); if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) { r = kvm_guest_time_update(vcpu); if (unlikely(r)) goto out; } if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) kvm_mmu_sync_roots(vcpu); if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu)) kvm_mmu_load_pgd(vcpu); /* * Note, the order matters here, as flushing "all" TLB entries * also flushes the "current" TLB entries, i.e. servicing the * flush "all" will clear any request to flush "current". */ if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) kvm_vcpu_flush_tlb_all(vcpu); kvm_service_local_tlb_flush_requests(vcpu); /* * Fall back to a "full" guest flush if Hyper-V's precise * flushing fails. Note, Hyper-V's flushing is per-vCPU, but * the flushes are considered "remote" and not "local" because * the requests can be initiated from other vCPUs. */ #ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) && kvm_hv_vcpu_flush_tlb(vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); #endif if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; goto out; } if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { if (is_guest_mode(vcpu)) kvm_x86_ops.nested_ops->triple_fault(vcpu); if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; r = 0; goto out; } } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ vcpu->arch.apf.halted = true; r = 1; goto out; } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); if (kvm_check_request(KVM_REQ_PMU, vcpu)) kvm_pmu_handle_event(vcpu); if (kvm_check_request(KVM_REQ_PMI, vcpu)) kvm_pmu_deliver_pmi(vcpu); #ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); #endif if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); if (test_bit(vcpu->arch.pending_ioapic_eoi, vcpu->arch.ioapic_handled_vectors)) { vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI; vcpu->run->eoi.vector = vcpu->arch.pending_ioapic_eoi; r = 0; goto out; } } if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) vcpu_scan_ioapic(vcpu); if (kvm_check_request(KVM_REQ_LOAD_EOI_EXITMAP, vcpu)) vcpu_load_eoi_exitmap(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) kvm_vcpu_reload_apic_access_page(vcpu); #ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; vcpu->run->system_event.ndata = 0; r = 0; goto out; } if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET; vcpu->run->system_event.ndata = 0; r = 0; goto out; } if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); vcpu->run->exit_reason = KVM_EXIT_HYPERV; vcpu->run->hyperv = hv_vcpu->exit; r = 0; goto out; } /* * KVM_REQ_HV_STIMER has to be processed after * KVM_REQ_CLOCK_UPDATE, because Hyper-V SynIC timers * depend on the guest clock being up-to-date */ if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) kvm_hv_process_stimers(vcpu); #endif if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) kvm_vcpu_update_apicv(vcpu); if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) kvm_check_async_pf_completion(vcpu); if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu)) static_call(kvm_x86_msr_filter_changed)(vcpu); if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu)) static_call(kvm_x86_update_cpu_dirty_logging)(vcpu); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || kvm_xen_has_interrupt(vcpu)) { ++vcpu->stat.req_event; r = kvm_apic_accept_events(vcpu); if (r < 0) { r = 0; goto out; } if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { r = 1; goto out; } r = kvm_check_and_inject_events(vcpu, &req_immediate_exit); if (r < 0) { r = 0; goto out; } if (req_int_win) static_call(kvm_x86_enable_irq_window)(vcpu); if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); kvm_lapic_sync_to_vapic(vcpu); } } r = kvm_mmu_reload(vcpu); if (unlikely(r)) { goto cancel_injection; } preempt_disable(); static_call(kvm_x86_prepare_switch_to_guest)(vcpu); /* * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt * IPI are then delayed after guest entry, which ensures that they * result in virtual interrupt delivery. */ local_irq_disable(); /* Store vcpu->apicv_active before vcpu->mode. */ smp_store_release(&vcpu->mode, IN_GUEST_MODE); kvm_vcpu_srcu_read_unlock(vcpu); /* * 1) We should set ->mode before checking ->requests. Please see * the comment in kvm_vcpu_exiting_guest_mode(). * * 2) For APICv, we should set ->mode before checking PID.ON. This * pairs with the memory barrier implicit in pi_test_and_set_on * (see vmx_deliver_posted_interrupt). * * 3) This also orders the write to mode from any reads to the page * tables done while the VCPU is running. Please see the comment * in kvm_flush_remote_tlbs. */ smp_mb__after_srcu_read_unlock(); /* * Process pending posted interrupts to handle the case where the * notification IRQ arrived in the host, or was never sent (because the * target vCPU wasn't running). Do this regardless of the vCPU's APICv * status, KVM doesn't update assigned devices when APICv is inhibited, * i.e. they can post interrupts even if APICv is temporarily disabled. */ if (kvm_lapic_enabled(vcpu)) static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); local_irq_enable(); preempt_enable(); kvm_vcpu_srcu_read_lock(vcpu); r = 1; goto cancel_injection; } if (req_immediate_exit) kvm_make_request(KVM_REQ_EVENT, vcpu); fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_return(); if (vcpu->arch.guest_fpu.xfd_err) wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); set_debugreg(vcpu->arch.eff_db[0], 0); set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); } else if (unlikely(hw_breakpoint_active())) { set_debugreg(0, 7); } guest_timing_enter_irqoff(); for (;;) { /* * Assert that vCPU vs. VM APICv state is consistent. An APICv * update must kick and wait for all vCPUs before toggling the * per-VM state, and responding vCPUs must wait for the update * to complete before servicing KVM_REQ_APICV_UPDATE. */ WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED)); exit_fastpath = static_call(kvm_x86_vcpu_run)(vcpu, req_immediate_exit); if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; if (kvm_lapic_enabled(vcpu)) static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (unlikely(kvm_vcpu_exit_request(vcpu))) { exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; break; } /* Note, VM-Exits that go down the "slow" path are accounted below. */ ++vcpu->stat.exits; } /* * Do this here before restoring debug registers on the host. And * since we do this before handling the vmexit, a DR access vmexit * can (a) read the correct value of the debug registers, (b) set * KVM_DEBUGREG_WONT_EXIT again. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); static_call(kvm_x86_sync_dirty_debug_regs)(vcpu); kvm_update_dr0123(vcpu); kvm_update_dr7(vcpu); } /* * If the guest has used debug registers, at least dr7 * will be disabled while returning to the host. * If we don't have active breakpoints in the host, we don't * care about the messed up debug address registers. But if * we have some of them active, restore the old state. */ if (hw_breakpoint_active()) hw_breakpoint_restore(); vcpu->arch.last_vmentry_cpu = vcpu->cpu; vcpu->arch.last_guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); /* * Sync xfd before calling handle_exit_irqoff() which may * rely on the fact that guest_fpu::xfd is up-to-date (e.g. * in #NM irqoff handler). */ if (vcpu->arch.xfd_no_write_intercept) fpu_sync_guest_vmexit_xfd_state(); static_call(kvm_x86_handle_exit_irqoff)(vcpu); if (vcpu->arch.guest_fpu.xfd_err) wrmsrl(MSR_IA32_XFD_ERR, 0); /* * Consume any pending interrupts, including the possible source of * VM-Exit on SVM and any ticks that occur between VM-Exit and now. * An instruction is required after local_irq_enable() to fully unblock * interrupts on processors that implement an interrupt shadow, the * stat.exits increment will do nicely. */ kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); local_irq_enable(); ++vcpu->stat.exits; local_irq_disable(); kvm_after_interrupt(vcpu); /* * Wait until after servicing IRQs to account guest time so that any * ticks that occurred while running the guest are properly accounted * to the guest. Waiting until IRQs are enabled degrades the accuracy * of accounting via context tracking, but the loss of accuracy is * acceptable for all known use cases. */ guest_timing_exit_irqoff(); local_irq_enable(); preempt_enable(); kvm_vcpu_srcu_read_lock(vcpu); /* * Profile KVM exit RIPs: */ if (unlikely(prof_on == KVM_PROFILING)) { unsigned long rip = kvm_rip_read(vcpu); profile_hit(KVM_PROFILING, (void *)rip); } if (unlikely(vcpu->arch.tsc_always_catchup)) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); r = static_call(kvm_x86_handle_exit)(vcpu, exit_fastpath); return r; cancel_injection: if (req_immediate_exit) kvm_make_request(KVM_REQ_EVENT, vcpu); static_call(kvm_x86_cancel_injection)(vcpu); if (unlikely(vcpu->arch.apic_attention)) kvm_lapic_sync_from_vapic(vcpu); out: return r; } /* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm_vcpu *vcpu) { bool hv_timer; if (!kvm_arch_vcpu_runnable(vcpu)) { /* * Switch to the software timer before halt-polling/blocking as * the guest's timer may be a break event for the vCPU, and the * hypervisor timer runs only when the CPU is in guest mode. * Switch before halt-polling so that KVM recognizes an expired * timer before blocking. */ hv_timer = kvm_lapic_hv_timer_in_use(vcpu); if (hv_timer) kvm_lapic_switch_to_sw_timer(vcpu); kvm_vcpu_srcu_read_unlock(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) kvm_vcpu_halt(vcpu); else kvm_vcpu_block(vcpu); kvm_vcpu_srcu_read_lock(vcpu); if (hv_timer) kvm_lapic_switch_to_hv_timer(vcpu); /* * If the vCPU is not runnable, a signal or another host event * of some kind is pending; service it without changing the * vCPU's activity state. */ if (!kvm_arch_vcpu_runnable(vcpu)) return 1; } /* * Evaluate nested events before exiting the halted state. This allows * the halt state to be recorded properly in the VMCS12's activity * state field (AMD does not have a similar field and a VM-Exit always * causes a spurious wakeup from HLT). */ if (is_guest_mode(vcpu)) { if (kvm_check_nested_events(vcpu) < 0) return 0; } if (kvm_apic_accept_events(vcpu) < 0) return 0; switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: case KVM_MP_STATE_AP_RESET_HOLD: vcpu->arch.pv.pv_unhalted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; fallthrough; case KVM_MP_STATE_RUNNABLE: vcpu->arch.apf.halted = false; break; case KVM_MP_STATE_INIT_RECEIVED: break; default: WARN_ON_ONCE(1); break; } return 1; } static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); } /* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->arch.l1tf_flush_l1d = true; for (;;) { /* * If another guest vCPU requests a PV TLB flush in the middle * of instruction emulation, the rest of the emulation could * use a stale page translation. Assume that any code after * this point can start executing an instruction. */ vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { r = vcpu_block(vcpu); } if (r <= 0) break; kvm_clear_request(KVM_REQ_UNBLOCK, vcpu); if (kvm_xen_has_pending_events(vcpu)) kvm_xen_inject_pending_events(vcpu); if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); if (dm_request_for_irq_injection(vcpu) && kvm_vcpu_ready_for_interrupt_injection(vcpu)) { r = 0; vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; ++vcpu->stat.request_irq_exits; break; } if (__xfer_to_guest_mode_work_pending()) { kvm_vcpu_srcu_read_unlock(vcpu); r = xfer_to_guest_mode_handle_work(vcpu); kvm_vcpu_srcu_read_lock(vcpu); if (r) return r; } } return r; } static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); } static int complete_emulated_pio(struct kvm_vcpu *vcpu) { BUG_ON(!vcpu->arch.pio.count); return complete_emulated_io(vcpu); } /* * Implements the following, as a state machine: * * read: * for each fragment * for each mmio piece in the fragment * write gpa, len * exit * copy data * execute insn * * write: * for each fragment * for each mmio piece in the fragment * write gpa, len * copy data * exit */ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; struct kvm_mmio_fragment *frag; unsigned len; BUG_ON(!vcpu->mmio_needed); /* Complete previous fragment */ frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment]; len = min(8u, frag->len); if (!vcpu->mmio_is_write) memcpy(frag->data, run->mmio.data, len); if (frag->len <= 8) { /* Switch to the next fragment. */ frag++; vcpu->mmio_cur_fragment++; } else { /* Go forward to the next mmio piece. */ frag->data += len; frag->gpa += len; frag->len -= len; } if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { vcpu->mmio_needed = 0; /* FIXME: return into emulator if single-stepping. */ if (vcpu->mmio_is_write) return 1; vcpu->mmio_read_completed = 1; return complete_emulated_io(vcpu); } run->exit_reason = KVM_EXIT_MMIO; run->mmio.phys_addr = frag->gpa; if (vcpu->mmio_is_write) memcpy(run->mmio.data, frag->data, min(8u, frag->len)); run->mmio.len = min(8u, frag->len); run->mmio.is_write = vcpu->mmio_is_write; vcpu->arch.complete_userspace_io = complete_emulated_mmio; return 0; } /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { /* Exclude PKRU, it's restored separately immediately after VM-Exit. */ fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true); trace_kvm_fpu(1); } /* When vcpu_run ends, restore user space FPU context. */ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false); ++vcpu->stat.fpu_reload; trace_kvm_fpu(0); } int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; struct kvm_run *kvm_run = vcpu->run; int r; vcpu_load(vcpu); kvm_sigset_activate(vcpu); kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); kvm_vcpu_srcu_read_lock(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; goto out; } /* * Don't bother switching APIC timer emulation from the * hypervisor timer to the software timer, the only way for the * APIC timer to be active is if userspace stuffed vCPU state, * i.e. put the vCPU into a nonsensical state. Only an INIT * will transition the vCPU out of UNINITIALIZED (without more * state stuffing from userspace), which will reset the local * APIC and thus cancel the timer or drop the IRQ (if the timer * already expired). */ kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_block(vcpu); kvm_vcpu_srcu_read_lock(vcpu); if (kvm_apic_accept_events(vcpu) < 0) { r = 0; goto out; } r = -EAGAIN; if (signal_pending(current)) { r = -EINTR; kvm_run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; } goto out; } if ((kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) || (kvm_run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS)) { r = -EINVAL; goto out; } if (kvm_run->kvm_dirty_regs) { r = sync_regs(vcpu); if (r != 0) goto out; } /* re-sync apic's tpr */ if (!lapic_in_kernel(vcpu)) { if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) { r = -EINVAL; goto out; } } /* * If userspace set a pending exception and L2 is active, convert it to * a pending VM-Exit if L1 wants to intercept the exception. */ if (vcpu->arch.exception_from_userspace && is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, ex->vector, ex->error_code)) { kvm_queue_exception_vmexit(vcpu, ex->vector, ex->has_error_code, ex->error_code, ex->has_payload, ex->payload); ex->injected = false; ex->pending = false; } vcpu->arch.exception_from_userspace = false; if (unlikely(vcpu->arch.complete_userspace_io)) { int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io; vcpu->arch.complete_userspace_io = NULL; r = cui(vcpu); if (r <= 0) goto out; } else { WARN_ON_ONCE(vcpu->arch.pio.count); WARN_ON_ONCE(vcpu->mmio_needed); } if (kvm_run->immediate_exit) { r = -EINTR; goto out; } r = static_call(kvm_x86_vcpu_pre_run)(vcpu); if (r <= 0) goto out; r = vcpu_run(vcpu); out: kvm_put_guest_fpu(vcpu); if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); kvm_vcpu_srcu_read_unlock(vcpu); kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); return r; } static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { if (vcpu->arch.emulate_regs_need_sync_to_vcpu) { /* * We are here if userspace calls get_regs() in the middle of * instruction emulation. Registers state needs to be copied * back from emulation context to vcpu. Userspace shouldn't do * that usually, but some bad designed PV devices (vmware * backdoor interface) need this to work */ emulator_writeback_register_cache(vcpu->arch.emulate_ctxt); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; } regs->rax = kvm_rax_read(vcpu); regs->rbx = kvm_rbx_read(vcpu); regs->rcx = kvm_rcx_read(vcpu); regs->rdx = kvm_rdx_read(vcpu); regs->rsi = kvm_rsi_read(vcpu); regs->rdi = kvm_rdi_read(vcpu); regs->rsp = kvm_rsp_read(vcpu); regs->rbp = kvm_rbp_read(vcpu); #ifdef CONFIG_X86_64 regs->r8 = kvm_r8_read(vcpu); regs->r9 = kvm_r9_read(vcpu); regs->r10 = kvm_r10_read(vcpu); regs->r11 = kvm_r11_read(vcpu); regs->r12 = kvm_r12_read(vcpu); regs->r13 = kvm_r13_read(vcpu); regs->r14 = kvm_r14_read(vcpu); regs->r15 = kvm_r15_read(vcpu); #endif regs->rip = kvm_rip_read(vcpu); regs->rflags = kvm_get_rflags(vcpu); } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; vcpu_load(vcpu); __get_regs(vcpu, regs); vcpu_put(vcpu); return 0; } static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { vcpu->arch.emulate_regs_need_sync_from_vcpu = true; vcpu->arch.emulate_regs_need_sync_to_vcpu = false; kvm_rax_write(vcpu, regs->rax); kvm_rbx_write(vcpu, regs->rbx); kvm_rcx_write(vcpu, regs->rcx); kvm_rdx_write(vcpu, regs->rdx); kvm_rsi_write(vcpu, regs->rsi); kvm_rdi_write(vcpu, regs->rdi); kvm_rsp_write(vcpu, regs->rsp); kvm_rbp_write(vcpu, regs->rbp); #ifdef CONFIG_X86_64 kvm_r8_write(vcpu, regs->r8); kvm_r9_write(vcpu, regs->r9); kvm_r10_write(vcpu, regs->r10); kvm_r11_write(vcpu, regs->r11); kvm_r12_write(vcpu, regs->r12); kvm_r13_write(vcpu, regs->r13); kvm_r14_write(vcpu, regs->r14); kvm_r15_write(vcpu, regs->r15); #endif kvm_rip_write(vcpu, regs->rip); kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED); vcpu->arch.exception.pending = false; vcpu->arch.exception_vmexit.pending = false; kvm_make_request(KVM_REQ_EVENT, vcpu); } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; vcpu_load(vcpu); __set_regs(vcpu, regs); vcpu_put(vcpu); return 0; } static void __get_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct desc_ptr dt; if (vcpu->arch.guest_state_protected) goto skip_protected_regs; kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES); kvm_get_segment(vcpu, &sregs->fs, VCPU_SREG_FS); kvm_get_segment(vcpu, &sregs->gs, VCPU_SREG_GS); kvm_get_segment(vcpu, &sregs->ss, VCPU_SREG_SS); kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); static_call(kvm_x86_get_idt)(vcpu, &dt); sregs->idt.limit = dt.size; sregs->idt.base = dt.address; static_call(kvm_x86_get_gdt)(vcpu, &dt); sregs->gdt.limit = dt.size; sregs->gdt.base = dt.address; sregs->cr2 = vcpu->arch.cr2; sregs->cr3 = kvm_read_cr3(vcpu); skip_protected_regs: sregs->cr0 = kvm_read_cr0(vcpu); sregs->cr4 = kvm_read_cr4(vcpu); sregs->cr8 = kvm_get_cr8(vcpu); sregs->efer = vcpu->arch.efer; sregs->apic_base = kvm_get_apic_base(vcpu); } static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { __get_sregs_common(vcpu, sregs); if (vcpu->arch.guest_state_protected) return; if (vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft) set_bit(vcpu->arch.interrupt.nr, (unsigned long *)sregs->interrupt_bitmap); } static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) { int i; __get_sregs_common(vcpu, (struct kvm_sregs *)sregs2); if (vcpu->arch.guest_state_protected) return; if (is_pae_paging(vcpu)) { for (i = 0 ; i < 4 ; i++) sregs2->pdptrs[i] = kvm_pdptr_read(vcpu, i); sregs2->flags |= KVM_SREGS2_FLAGS_PDPTRS_VALID; } } int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; vcpu_load(vcpu); __get_sregs(vcpu, sregs); vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { int r; vcpu_load(vcpu); if (kvm_mpx_supported()) kvm_load_guest_fpu(vcpu); r = kvm_apic_accept_events(vcpu); if (r < 0) goto out; r = 0; if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && vcpu->arch.pv.pv_unhalted) mp_state->mp_state = KVM_MP_STATE_RUNNABLE; else mp_state->mp_state = vcpu->arch.mp_state; out: if (kvm_mpx_supported()) kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); return r; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { int ret = -EINVAL; vcpu_load(vcpu); switch (mp_state->mp_state) { case KVM_MP_STATE_UNINITIALIZED: case KVM_MP_STATE_HALTED: case KVM_MP_STATE_AP_RESET_HOLD: case KVM_MP_STATE_INIT_RECEIVED: case KVM_MP_STATE_SIPI_RECEIVED: if (!lapic_in_kernel(vcpu)) goto out; break; case KVM_MP_STATE_RUNNABLE: break; default: goto out; } /* * Pending INITs are reported using KVM_SET_VCPU_EVENTS, disallow * forcing the guest into INIT/SIPI if those events are supposed to be * blocked. KVM prioritizes SMI over INIT, so reject INIT/SIPI state * if an SMI is pending as well. */ if ((!kvm_apic_init_sipi_allowed(vcpu) || vcpu->arch.smi_pending) && (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) goto out; if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) { vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events); } else vcpu->arch.mp_state = mp_state->mp_state; kvm_make_request(KVM_REQ_EVENT, vcpu); ret = 0; out: vcpu_put(vcpu); return ret; } int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason, has_error_code, error_code); if (ret) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; return 0; } kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); return 1; } EXPORT_SYMBOL_GPL(kvm_task_switch); static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in * 64-bit mode (though maybe in a 32-bit code segment). * CR4.PAE and EFER.LMA must be set. */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; if (!kvm_vcpu_is_legal_cr3(vcpu, sregs->cr3)) return false; } else { /* * Not in 64-bit mode: EFER.LMA is clear and the code * segment cannot be 64-bit. */ if (sregs->efer & EFER_LMA || sregs->cs.l) return false; } return kvm_is_valid_cr4(vcpu, sregs->cr4) && kvm_is_valid_cr0(vcpu, sregs->cr0); } static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, int *mmu_reset_needed, bool update_pdptrs) { struct msr_data apic_base_msr; int idx; struct desc_ptr dt; if (!kvm_is_valid_sregs(vcpu, sregs)) return -EINVAL; apic_base_msr.data = sregs->apic_base; apic_base_msr.host_initiated = true; if (kvm_set_apic_base(vcpu, &apic_base_msr)) return -EINVAL; if (vcpu->arch.guest_state_protected) return 0; dt.size = sregs->idt.limit; dt.address = sregs->idt.base; static_call(kvm_x86_set_idt)(vcpu, &dt); dt.size = sregs->gdt.limit; dt.address = sregs->gdt.base; static_call(kvm_x86_set_gdt)(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); static_call_cond(kvm_x86_post_set_cr3)(vcpu, sregs->cr3); kvm_set_cr8(vcpu, sregs->cr8); *mmu_reset_needed |= vcpu->arch.efer != sregs->efer; static_call(kvm_x86_set_efer)(vcpu, sregs->efer); *mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0); *mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); if (update_pdptrs) { idx = srcu_read_lock(&vcpu->kvm->srcu); if (is_pae_paging(vcpu)) { load_pdptrs(vcpu, kvm_read_cr3(vcpu)); *mmu_reset_needed = 1; } srcu_read_unlock(&vcpu->kvm->srcu, idx); } kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); kvm_set_segment(vcpu, &sregs->es, VCPU_SREG_ES); kvm_set_segment(vcpu, &sregs->fs, VCPU_SREG_FS); kvm_set_segment(vcpu, &sregs->gs, VCPU_SREG_GS); kvm_set_segment(vcpu, &sregs->ss, VCPU_SREG_SS); kvm_set_segment(vcpu, &sregs->tr, VCPU_SREG_TR); kvm_set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); update_cr8_intercept(vcpu); /* Older userspace won't unhalt the vcpu on reset. */ if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 && sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 && !is_protmode(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; return 0; } static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { int pending_vec, max_bits; int mmu_reset_needed = 0; int ret = __set_sregs_common(vcpu, sregs, &mmu_reset_needed, true); if (ret) return ret; if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } max_bits = KVM_NR_INTERRUPTS; pending_vec = find_first_bit( (const unsigned long *)sregs->interrupt_bitmap, max_bits); if (pending_vec < max_bits) { kvm_queue_interrupt(vcpu, pending_vec, false); pr_debug("Set back pending irq %d\n", pending_vec); kvm_make_request(KVM_REQ_EVENT, vcpu); } return 0; } static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) { int mmu_reset_needed = 0; bool valid_pdptrs = sregs2->flags & KVM_SREGS2_FLAGS_PDPTRS_VALID; bool pae = (sregs2->cr0 & X86_CR0_PG) && (sregs2->cr4 & X86_CR4_PAE) && !(sregs2->efer & EFER_LMA); int i, ret; if (sregs2->flags & ~KVM_SREGS2_FLAGS_PDPTRS_VALID) return -EINVAL; if (valid_pdptrs && (!pae || vcpu->arch.guest_state_protected)) return -EINVAL; ret = __set_sregs_common(vcpu, (struct kvm_sregs *)sregs2, &mmu_reset_needed, !valid_pdptrs); if (ret) return ret; if (valid_pdptrs) { for (i = 0; i < 4 ; i++) kvm_pdptr_write(vcpu, i, sregs2->pdptrs[i]); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); mmu_reset_needed = 1; vcpu->arch.pdptrs_from_userspace = true; } if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } return 0; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { int ret; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; vcpu_load(vcpu); ret = __set_sregs(vcpu, sregs); vcpu_put(vcpu); return ret; } static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) { bool set = false; struct kvm_vcpu *vcpu; unsigned long i; if (!enable_apicv) return; down_write(&kvm->arch.apicv_update_lock); kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) { set = true; break; } } __kvm_set_or_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_BLOCKIRQ, set); up_write(&kvm->arch.apicv_update_lock); } int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { unsigned long rflags; int i, r; if (vcpu->arch.guest_state_protected) return -EINVAL; vcpu_load(vcpu); if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { r = -EBUSY; if (kvm_is_exception_pending(vcpu)) goto out; if (dbg->control & KVM_GUESTDBG_INJECT_DB) kvm_queue_exception(vcpu, DB_VECTOR); else kvm_queue_exception(vcpu, BP_VECTOR); } /* * Read rflags as long as potentially injected trace flags are still * filtered out. */ rflags = kvm_get_rflags(vcpu); vcpu->guest_debug = dbg->control; if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) vcpu->guest_debug = 0; if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { for (i = 0; i < KVM_NR_DB_REGS; ++i) vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; vcpu->arch.guest_debug_dr7 = dbg->arch.debugreg[7]; } else { for (i = 0; i < KVM_NR_DB_REGS; i++) vcpu->arch.eff_db[i] = vcpu->arch.db[i]; } kvm_update_dr7(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu); /* * Trigger an rflags update that will inject or remove the trace * flags. */ kvm_set_rflags(vcpu, rflags); static_call(kvm_x86_update_exception_bitmap)(vcpu); kvm_arch_vcpu_guestdbg_update_apicv_inhibit(vcpu->kvm); r = 0; out: vcpu_put(vcpu); return r; } /* * Translate a guest virtual address to a guest physical address. */ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr) { unsigned long vaddr = tr->linear_address; gpa_t gpa; int idx; vcpu_load(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL); srcu_read_unlock(&vcpu->kvm->srcu, idx); tr->physical_address = gpa; tr->valid = gpa != INVALID_GPA; tr->writeable = 1; tr->usermode = 0; vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { struct fxregs_state *fxsave; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; vcpu_load(vcpu); fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; fpu->fsw = fxsave->swd; fpu->ftwx = fxsave->twd; fpu->last_opcode = fxsave->fop; fpu->last_ip = fxsave->rip; fpu->last_dp = fxsave->rdp; memcpy(fpu->xmm, fxsave->xmm_space, sizeof(fxsave->xmm_space)); vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { struct fxregs_state *fxsave; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; vcpu_load(vcpu); fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; fxsave->swd = fpu->fsw; fxsave->twd = fpu->ftwx; fxsave->fop = fpu->last_opcode; fxsave->rip = fpu->last_ip; fxsave->rdp = fpu->last_dp; memcpy(fxsave->xmm_space, fpu->xmm, sizeof(fxsave->xmm_space)); vcpu_put(vcpu); return 0; } static void store_regs(struct kvm_vcpu *vcpu) { BUILD_BUG_ON(sizeof(struct kvm_sync_regs) > SYNC_REGS_SIZE_BYTES); if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_REGS) __get_regs(vcpu, &vcpu->run->s.regs.regs); if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_SREGS) __get_sregs(vcpu, &vcpu->run->s.regs.sregs); if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_EVENTS) kvm_vcpu_ioctl_x86_get_vcpu_events( vcpu, &vcpu->run->s.regs.events); } static int sync_regs(struct kvm_vcpu *vcpu) { if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_REGS) { __set_regs(vcpu, &vcpu->run->s.regs.regs); vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_REGS; } if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_SREGS) { struct kvm_sregs sregs = vcpu->run->s.regs.sregs; if (__set_sregs(vcpu, &sregs)) return -EINVAL; vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_SREGS; } if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_EVENTS) { struct kvm_vcpu_events events = vcpu->run->s.regs.events; if (kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events)) return -EINVAL; vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_EVENTS; } return 0; } int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { if (kvm_check_tsc_unstable() && kvm->created_vcpus) pr_warn_once("SMP vm created on host with unstable TSC; " "guest TSC will not be reliable\n"); if (!kvm->arch.max_vcpu_ids) kvm->arch.max_vcpu_ids = KVM_MAX_VCPU_IDS; if (id >= kvm->arch.max_vcpu_ids) return -EINVAL; return static_call(kvm_x86_vcpu_precreate)(kvm); } int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { struct page *page; int r; vcpu->arch.last_vmentry_cpu = -1; vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm); if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; r = kvm_mmu_create(vcpu); if (r < 0) return r; r = kvm_create_lapic(vcpu); if (r < 0) goto fail_mmu_destroy; r = -ENOMEM; page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) goto fail_free_lapic; vcpu->arch.pio_data = page_address(page); vcpu->arch.mce_banks = kcalloc(KVM_MAX_MCE_BANKS * 4, sizeof(u64), GFP_KERNEL_ACCOUNT); vcpu->arch.mci_ctl2_banks = kcalloc(KVM_MAX_MCE_BANKS, sizeof(u64), GFP_KERNEL_ACCOUNT); if (!vcpu->arch.mce_banks || !vcpu->arch.mci_ctl2_banks) goto fail_free_mce_banks; vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL_ACCOUNT)) goto fail_free_mce_banks; if (!alloc_emulate_ctxt(vcpu)) goto free_wbinvd_dirty_mask; if (!fpu_alloc_guest_fpstate(&vcpu->arch.guest_fpu)) { pr_err("failed to allocate vcpu's fpu\n"); goto free_emulate_ctxt; } vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; kvm_async_pf_hash_reset(vcpu); vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap; kvm_pmu_init(vcpu); vcpu->arch.pending_external_vector = -1; vcpu->arch.preempted_in_kernel = false; #if IS_ENABLED(CONFIG_HYPERV) vcpu->arch.hv_root_tdp = INVALID_PAGE; #endif r = static_call(kvm_x86_vcpu_create)(vcpu); if (r) goto free_guest_fpu; vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_xen_init_vcpu(vcpu); kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz); kvm_vcpu_reset(vcpu, false); kvm_init_mmu(vcpu); vcpu_put(vcpu); return 0; free_guest_fpu: fpu_free_guest_fpstate(&vcpu->arch.guest_fpu); free_emulate_ctxt: kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_wbinvd_dirty_mask: free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); fail_free_mce_banks: kfree(vcpu->arch.mce_banks); kfree(vcpu->arch.mci_ctl2_banks); free_page((unsigned long)vcpu->arch.pio_data); fail_free_lapic: kvm_free_lapic(vcpu); fail_mmu_destroy: kvm_mmu_destroy(vcpu); return r; } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); kvm_synchronize_tsc(vcpu, NULL); vcpu_put(vcpu); /* poll control enabled by default */ vcpu->arch.msr_kvm_poll_control = 1; mutex_unlock(&vcpu->mutex); if (kvmclock_periodic_sync && vcpu->vcpu_idx == 0) schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { int idx; kvmclock_reset(vcpu); static_call(kvm_x86_vcpu_free)(vcpu); kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); fpu_free_guest_fpstate(&vcpu->arch.guest_fpu); kvm_xen_destroy_vcpu(vcpu); kvm_hv_vcpu_uninit(vcpu); kvm_pmu_destroy(vcpu); kfree(vcpu->arch.mce_banks); kfree(vcpu->arch.mci_ctl2_banks); kvm_free_lapic(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_mmu_destroy(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, idx); free_page((unsigned long)vcpu->arch.pio_data); kvfree(vcpu->arch.cpuid_entries); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_cpuid_entry2 *cpuid_0x1; unsigned long old_cr0 = kvm_read_cr0(vcpu); unsigned long new_cr0; /* * Several of the "set" flows, e.g. ->set_cr0(), read other registers * to handle side effects. RESET emulation hits those flows and relies * on emulated/virtualized registers, including those that are loaded * into hardware, to be zeroed at vCPU creation. Use CRs as a sentinel * to detect improper or missing initialization. */ WARN_ON_ONCE(!init_event && (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu))); /* * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's * possible to INIT the vCPU while L2 is active. Force the vCPU back * into L1 as EFER.SVME is cleared on INIT (along with all other EFER * bits), i.e. virtualization is disabled. */ if (is_guest_mode(vcpu)) kvm_leave_nested(vcpu); kvm_lapic_reset(vcpu, init_event); WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu)); vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; vcpu->arch.smi_count = 0; atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; kvm_clear_interrupt_queue(vcpu); kvm_clear_exception_queue(vcpu); memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); vcpu->arch.dr6 = DR6_ACTIVE_LOW; vcpu->arch.dr7 = DR7_FIXED_1; kvm_update_dr7(vcpu); vcpu->arch.cr2 = 0; kvm_make_request(KVM_REQ_EVENT, vcpu); vcpu->arch.apf.msr_en_val = 0; vcpu->arch.apf.msr_int_val = 0; vcpu->arch.st.msr_val = 0; kvmclock_reset(vcpu); kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; if (vcpu->arch.guest_fpu.fpstate && kvm_mpx_supported()) { struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate; /* * All paths that lead to INIT are required to load the guest's * FPU state (because most paths are buried in KVM_RUN). */ if (init_event) kvm_put_guest_fpu(vcpu); fpstate_clear_xstate_component(fpstate, XFEATURE_BNDREGS); fpstate_clear_xstate_component(fpstate, XFEATURE_BNDCSR); if (init_event) kvm_load_guest_fpu(vcpu); } if (!init_event) { vcpu->arch.smbase = 0x30000; vcpu->arch.msr_misc_features_enables = 0; vcpu->arch.ia32_misc_enable_msr = MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL | MSR_IA32_MISC_ENABLE_BTS_UNAVAIL; __kvm_set_xcr(vcpu, 0, XFEATURE_MASK_FP); __kvm_set_msr(vcpu, MSR_IA32_XSS, 0, true); } /* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */ memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); kvm_register_mark_dirty(vcpu, VCPU_REGS_RSP); /* * Fall back to KVM's default Family/Model/Stepping of 0x600 (P6/Athlon) * if no CPUID match is found. Note, it's impossible to get a match at * RESET since KVM emulates RESET before exposing the vCPU to userspace, * i.e. it's impossible for kvm_find_cpuid_entry() to find a valid entry * on RESET. But, go through the motions in case that's ever remedied. */ cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1); kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600); static_call(kvm_x86_vcpu_reset)(vcpu, init_event); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0xfff0); vcpu->arch.cr3 = 0; kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); /* * CR0.CD/NW are set on RESET, preserved on INIT. Note, some versions * of Intel's SDM list CD/NW as being set on INIT, but they contradict * (or qualify) that with a footnote stating that CD/NW are preserved. */ new_cr0 = X86_CR0_ET; if (init_event) new_cr0 |= (old_cr0 & (X86_CR0_NW | X86_CR0_CD)); else new_cr0 |= X86_CR0_NW | X86_CR0_CD; static_call(kvm_x86_set_cr0)(vcpu, new_cr0); static_call(kvm_x86_set_cr4)(vcpu, 0); static_call(kvm_x86_set_efer)(vcpu, 0); static_call(kvm_x86_update_exception_bitmap)(vcpu); /* * On the standard CR0/CR4/EFER modification paths, there are several * complex conditions determining whether the MMU has to be reset and/or * which PCIDs have to be flushed. However, CR0.WP and the paging-related * bits in CR4 and EFER are irrelevant if CR0.PG was '0'; and a reset+flush * is needed anyway if CR0.PG was '1' (which can only happen for INIT, as * CR0 will be '0' prior to RESET). So we only need to check CR0.PG here. */ if (old_cr0 & X86_CR0_PG) { kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); kvm_mmu_reset_context(vcpu); } /* * Intel's SDM states that all TLB entries are flushed on INIT. AMD's * APM states the TLBs are untouched by INIT, but it also states that * the TLBs are flushed on "External initialization of the processor." * Flush the guest TLB regardless of vendor, there is no meaningful * benefit in relying on the guest to flush the TLB immediately after * INIT. A spurious TLB flush is benign and likely negligible from a * performance perspective. */ if (init_event) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } EXPORT_SYMBOL_GPL(kvm_vcpu_reset); void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) { struct kvm_segment cs; kvm_get_segment(vcpu, &cs, VCPU_SREG_CS); cs.selector = vector << 8; cs.base = vector << 12; kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); kvm_rip_write(vcpu, 0); } EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); int kvm_arch_hardware_enable(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; unsigned long i; int ret; u64 local_tsc; u64 max_tsc = 0; bool stable, backwards_tsc = false; kvm_user_return_msr_cpu_online(); ret = kvm_x86_check_processor_compatibility(); if (ret) return ret; ret = static_call(kvm_x86_hardware_enable)(); if (ret != 0) return ret; local_tsc = rdtsc(); stable = !kvm_check_tsc_unstable(); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (!stable && vcpu->cpu == smp_processor_id()) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); if (stable && vcpu->arch.last_host_tsc > local_tsc) { backwards_tsc = true; if (vcpu->arch.last_host_tsc > max_tsc) max_tsc = vcpu->arch.last_host_tsc; } } } /* * Sometimes, even reliable TSCs go backwards. This happens on * platforms that reset TSC during suspend or hibernate actions, but * maintain synchronization. We must compensate. Fortunately, we can * detect that condition here, which happens early in CPU bringup, * before any KVM threads can be running. Unfortunately, we can't * bring the TSCs fully up to date with real time, as we aren't yet far * enough into CPU bringup that we know how much real time has actually * elapsed; our helper function, ktime_get_boottime_ns() will be using boot * variables that haven't been updated yet. * * So we simply find the maximum observed TSC above, then record the * adjustment to TSC in each VCPU. When the VCPU later gets loaded, * the adjustment will be applied. Note that we accumulate * adjustments, in case multiple suspend cycles happen before some VCPU * gets a chance to run again. In the event that no KVM threads get a * chance to run, we will miss the entire elapsed period, as we'll have * reset last_host_tsc, so VCPUs will not have the TSC adjusted and may * loose cycle time. This isn't too big a deal, since the loss will be * uniform across all VCPUs (not to mention the scenario is extremely * unlikely). It is possible that a second hibernate recovery happens * much faster than a first, causing the observed TSC here to be * smaller; this would require additional padding adjustment, which is * why we set last_host_tsc to the local tsc observed here. * * N.B. - this code below runs only on platforms with reliable TSC, * as that is the only way backwards_tsc is set above. Also note * that this runs for ALL vcpus, which is not a bug; all VCPUs should * have the same delta_cyc adjustment applied if backwards_tsc * is detected. Note further, this adjustment is only done once, * as we reset last_host_tsc on all VCPUs to stop this from being * called multiple times (one for each physical CPU bringup). * * Platforms with unreliable TSCs don't have to deal with this, they * will be compensated by the logic in vcpu_load, which sets the TSC to * catchup mode. This will catchup all VCPUs to real time, but cannot * guarantee that they stay in perfect synchronization. */ if (backwards_tsc) { u64 delta_cyc = max_tsc - local_tsc; list_for_each_entry(kvm, &vm_list, vm_list) { kvm->arch.backwards_tsc_observed = true; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.tsc_offset_adjustment += delta_cyc; vcpu->arch.last_host_tsc = local_tsc; kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); } /* * We have to disable TSC offset matching.. if you were * booting a VM while issuing an S4 host suspend.... * you may have some problem. Solving this issue is * left as an exercise to the reader. */ kvm->arch.last_tsc_nsec = 0; kvm->arch.last_tsc_write = 0; } } return 0; } void kvm_arch_hardware_disable(void) { static_call(kvm_x86_hardware_disable)(); drop_user_return_notifiers(); } bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; } bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) { return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; } void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); vcpu->arch.l1tf_flush_l1d = true; if (pmu->version && unlikely(pmu->event_count)) { pmu->need_cleanup = true; kvm_make_request(KVM_REQ_PMU, vcpu); } static_call(kvm_x86_sched_in)(vcpu, cpu); } void kvm_arch_free_vm(struct kvm *kvm) { #if IS_ENABLED(CONFIG_HYPERV) kfree(kvm->arch.hv_pa_pg); #endif __kvm_arch_free_vm(kvm); } int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { int ret; unsigned long flags; if (!kvm_is_vm_type_supported(type)) return -EINVAL; kvm->arch.vm_type = type; kvm->arch.has_private_mem = (type == KVM_X86_SW_PROTECTED_VM); ret = kvm_page_track_init(kvm); if (ret) goto out; kvm_mmu_init_vm(kvm); ret = static_call(kvm_x86_vm_init)(kvm); if (ret) goto out_uninit_mmu; INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); atomic_set(&kvm->arch.noncoherent_dma_count, 0); /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); /* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */ set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); raw_spin_lock_init(&kvm->arch.tsc_write_lock); mutex_init(&kvm->arch.apic_map_lock); seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock); kvm->arch.kvmclock_offset = -get_kvmclock_base_ns(); raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); pvclock_update_vm_gtod_copy(kvm); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); kvm->arch.default_tsc_khz = max_tsc_khz ? : tsc_khz; kvm->arch.guest_can_read_msr_platform_info = true; kvm->arch.enable_pmu = enable_pmu; #if IS_ENABLED(CONFIG_HYPERV) spin_lock_init(&kvm->arch.hv_root_tdp_lock); kvm->arch.hv_root_tdp = INVALID_PAGE; #endif INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); return 0; out_uninit_mmu: kvm_mmu_uninit_vm(kvm); kvm_page_track_cleanup(kvm); out: return ret; } int kvm_arch_post_init_vm(struct kvm *kvm) { return kvm_mmu_post_init_vm(kvm); } static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { vcpu_load(vcpu); kvm_mmu_unload(vcpu); vcpu_put(vcpu); } static void kvm_unload_vcpu_mmus(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { kvm_clear_async_pf_completion_queue(vcpu); kvm_unload_vcpu_mmu(vcpu); } } void kvm_arch_sync_events(struct kvm *kvm) { cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work); cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work); kvm_free_pit(kvm); } /** * __x86_set_memory_region: Setup KVM internal memory slot * * @kvm: the kvm pointer to the VM. * @id: the slot ID to setup. * @gpa: the GPA to install the slot (unused when @size == 0). * @size: the size of the slot. Set to zero to uninstall a slot. * * This function helps to setup a KVM internal memory slot. Specify * @size > 0 to install a new slot, while @size == 0 to uninstall a * slot. The return code can be one of the following: * * HVA: on success (uninstall will return a bogus HVA) * -errno: on error * * The caller should always use IS_ERR() to check the return value * before use. Note, the KVM internal memory slots are guaranteed to * remain valid and unchanged until the VM is destroyed, i.e., the * GPA->HVA translation will not change. However, the HVA is a user * address, i.e. its accessibility is not guaranteed, and must be * accessed via __copy_{to,from}_user(). */ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) { int i, r; unsigned long hva, old_npages; struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *slot; /* Called with kvm->slots_lock held. */ if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) return ERR_PTR_USR(-EINVAL); slot = id_to_memslot(slots, id); if (size) { if (slot && slot->npages) return ERR_PTR_USR(-EEXIST); /* * MAP_SHARED to prevent internal slot pages from being moved * by fork()/COW. */ hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, 0); if (IS_ERR_VALUE(hva)) return (void __user *)hva; } else { if (!slot || !slot->npages) return NULL; old_npages = slot->npages; hva = slot->userspace_addr; } for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { struct kvm_userspace_memory_region2 m; m.slot = id | (i << 16); m.flags = 0; m.guest_phys_addr = gpa; m.userspace_addr = hva; m.memory_size = size; r = __kvm_set_memory_region(kvm, &m); if (r < 0) return ERR_PTR_USR(r); } if (!size) vm_munmap(hva, old_npages * PAGE_SIZE); return (void __user *)hva; } EXPORT_SYMBOL_GPL(__x86_set_memory_region); void kvm_arch_pre_destroy_vm(struct kvm *kvm) { kvm_mmu_pre_destroy_vm(kvm); } void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { /* * Free memory regions allocated on behalf of userspace, * unless the memory map has changed due to process exit * or fd copying. */ mutex_lock(&kvm->slots_lock); __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0); __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); mutex_unlock(&kvm->slots_lock); } kvm_unload_vcpu_mmus(kvm); static_call_cond(kvm_x86_vm_destroy)(kvm); kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); kvm_destroy_vcpus(kvm); kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1)); kvm_mmu_uninit_vm(kvm); kvm_page_track_cleanup(kvm); kvm_xen_destroy_vm(kvm); kvm_hv_destroy_vm(kvm); } static void memslot_rmap_free(struct kvm_memory_slot *slot) { int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { vfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; } } void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { int i; memslot_rmap_free(slot); for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } kvm_page_track_free_memslot(slot); } int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages) { const int sz = sizeof(*slot->arch.rmap[0]); int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { int level = i + 1; int lpages = __kvm_mmu_slot_lpages(slot, npages, level); if (slot->arch.rmap[i]) continue; slot->arch.rmap[i] = __vcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); if (!slot->arch.rmap[i]) { memslot_rmap_free(slot); return -ENOMEM; } } return 0; } static int kvm_alloc_memslot_metadata(struct kvm *kvm, struct kvm_memory_slot *slot) { unsigned long npages = slot->npages; int i, r; /* * Clear out the previous array pointers for the KVM_MR_MOVE case. The * old arrays will be freed by __kvm_set_memory_region() if installing * the new memslot is successful. */ memset(&slot->arch, 0, sizeof(slot->arch)); if (kvm_memslots_have_rmaps(kvm)) { r = memslot_rmap_alloc(slot, npages); if (r) return r; } for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; int lpages; int level = i + 1; lpages = __kvm_mmu_slot_lpages(slot, npages, level); linfo = __vcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) goto out_free; slot->arch.lpage_info[i - 1] = linfo; if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1)) linfo[0].disallow_lpage = 1; if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1)) linfo[lpages - 1].disallow_lpage = 1; ugfn = slot->userspace_addr >> PAGE_SHIFT; /* * If the gfn and userspace address are not aligned wrt each * other, disable large page support for this slot. */ if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1)) { unsigned long j; for (j = 0; j < lpages; ++j) linfo[j].disallow_lpage = 1; } } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES kvm_mmu_init_memslot_memory_attributes(kvm, slot); #endif if (kvm_page_track_create_memslot(kvm, slot, npages)) goto out_free; return 0; out_free: memslot_rmap_free(slot); for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } return -ENOMEM; } void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { struct kvm_vcpu *vcpu; unsigned long i; /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ kvm_mmu_invalidate_mmio_sptes(kvm, gen); /* Force re-initialization of steal_time cache */ kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); } int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { /* * KVM doesn't support moving memslots when there are external page * trackers attached to the VM, i.e. if KVMGT is in use. */ if (change == KVM_MR_MOVE && kvm_page_track_has_external_user(kvm)) return -EINVAL; if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) return -EINVAL; return kvm_alloc_memslot_metadata(kvm, new); } if (change == KVM_MR_FLAGS_ONLY) memcpy(&new->arch, &old->arch, sizeof(old->arch)); else if (WARN_ON_ONCE(change != KVM_MR_DELETE)) return -EIO; return 0; } static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable) { int nr_slots; if (!kvm_x86_ops.cpu_dirty_log_size) return; nr_slots = atomic_read(&kvm->nr_memslots_dirty_logging); if ((enable && nr_slots == 1) || !nr_slots) kvm_make_all_cpus_request(kvm, KVM_REQ_UPDATE_CPU_DIRTY_LOGGING); } static void kvm_mmu_slot_apply_flags(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { u32 old_flags = old ? old->flags : 0; u32 new_flags = new ? new->flags : 0; bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES; /* * Update CPU dirty logging if dirty logging is being toggled. This * applies to all operations. */ if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages); /* * Nothing more to do for RO slots (which can't be dirtied and can't be * made writable) or CREATE/MOVE/DELETE of a slot. * * For a memslot with dirty logging disabled: * CREATE: No dirty mappings will already exist. * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot() * * For a memslot with dirty logging enabled: * CREATE: No shadow pages exist, thus nothing to write-protect * and no dirty bits to clear. * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot(). */ if ((change != KVM_MR_FLAGS_ONLY) || (new_flags & KVM_MEM_READONLY)) return; /* * READONLY and non-flags changes were filtered out above, and the only * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty * logging isn't being toggled on or off. */ if (WARN_ON_ONCE(!((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES))) return; if (!log_dirty_pages) { /* * Dirty logging tracks sptes in 4k granularity, meaning that * large sptes have to be split. If live migration succeeds, * the guest in the source machine will be destroyed and large * sptes will be created in the destination. However, if the * guest continues to run in the source machine (for example if * live migration fails), small sptes will remain around and * cause bad performance. * * Scan sptes if dirty logging has been stopped, dropping those * which can be collapsed into a single large-page spte. Later * page faults will create the large-page sptes. */ kvm_mmu_zap_collapsible_sptes(kvm, new); } else { /* * Initially-all-set does not require write protecting any page, * because they're all assumed to be dirty. */ if (kvm_dirty_log_manual_protect_and_init_set(kvm)) return; if (READ_ONCE(eager_page_split)) kvm_mmu_slot_try_split_huge_pages(kvm, new, PG_LEVEL_4K); if (kvm_x86_ops.cpu_dirty_log_size) { kvm_mmu_slot_leaf_clear_dirty(kvm, new); kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_2M); } else { kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K); } /* * Unconditionally flush the TLBs after enabling dirty logging. * A flush is almost always going to be necessary (see below), * and unconditionally flushing allows the helpers to omit * the subtly complex checks when removing write access. * * Do the flush outside of mmu_lock to reduce the amount of * time mmu_lock is held. Flushing after dropping mmu_lock is * safe as KVM only needs to guarantee the slot is fully * write-protected before returning to userspace, i.e. before * userspace can consume the dirty status. * * Flushing outside of mmu_lock requires KVM to be careful when * making decisions based on writable status of an SPTE, e.g. a * !writable SPTE doesn't guarantee a CPU can't perform writes. * * Specifically, KVM also write-protects guest page tables to * monitor changes when using shadow paging, and must guarantee * no CPUs can write to those page before mmu_lock is dropped. * Because CPUs may have stale TLB entries at this point, a * !writable SPTE doesn't guarantee CPUs can't perform writes. * * KVM also allows making SPTES writable outside of mmu_lock, * e.g. to allow dirty logging without taking mmu_lock. * * To handle these scenarios, KVM uses a separate software-only * bit (MMU-writable) to track if a SPTE is !writable due to * a guest page table being write-protected (KVM clears the * MMU-writable flag when write-protecting for shadow paging). * * The use of MMU-writable is also the primary motivation for * the unconditional flush. Because KVM must guarantee that a * CPU doesn't contain stale, writable TLB entries for a * !MMU-writable SPTE, KVM must flush if it encounters any * MMU-writable SPTE regardless of whether the actual hardware * writable bit was set. I.e. KVM is almost guaranteed to need * to flush, while unconditionally flushing allows the "remove * write access" helpers to ignore MMU-writable entirely. * * See is_writable_pte() for more details (the case involving * access-tracked SPTEs is particularly relevant). */ kvm_flush_remote_tlbs_memslot(kvm, new); } } void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { if (change == KVM_MR_DELETE) kvm_page_track_delete_slot(kvm, old); if (!kvm->arch.n_requested_mmu_pages && (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { unsigned long nr_mmu_pages; nr_mmu_pages = kvm->nr_memslot_pages / KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO; nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); } kvm_mmu_slot_apply_flags(kvm, old, new, change); /* Free the arrays associated with the old memslot. */ if (change == KVM_MR_MOVE) kvm_arch_free_memslot(kvm, old); } static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { return (is_guest_mode(vcpu) && static_call(kvm_x86_guest_apic_has_interrupt)(vcpu)); } static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) { if (!list_empty_careful(&vcpu->async_pf.done)) return true; if (kvm_apic_has_pending_init_or_sipi(vcpu) && kvm_apic_init_sipi_allowed(vcpu)) return true; if (vcpu->arch.pv.pv_unhalted) return true; if (kvm_is_exception_pending(vcpu)) return true; if (kvm_test_request(KVM_REQ_NMI, vcpu) || (vcpu->arch.nmi_pending && static_call(kvm_x86_nmi_allowed)(vcpu, false))) return true; #ifdef CONFIG_KVM_SMM if (kvm_test_request(KVM_REQ_SMI, vcpu) || (vcpu->arch.smi_pending && static_call(kvm_x86_smi_allowed)(vcpu, false))) return true; #endif if (kvm_test_request(KVM_REQ_PMI, vcpu)) return true; if (kvm_arch_interrupt_allowed(vcpu) && (kvm_cpu_has_interrupt(vcpu) || kvm_guest_apic_has_interrupt(vcpu))) return true; if (kvm_hv_has_stimer_pending(vcpu)) return true; if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && kvm_x86_ops.nested_ops->has_events(vcpu)) return true; if (kvm_xen_has_pending_events(vcpu)) return true; return false; } int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) { return kvm_vcpu_apicv_active(vcpu) && static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu); } bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) { return vcpu->arch.preempted_in_kernel; } bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) { if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) return true; if (kvm_test_request(KVM_REQ_NMI, vcpu) || #ifdef CONFIG_KVM_SMM kvm_test_request(KVM_REQ_SMI, vcpu) || #endif kvm_test_request(KVM_REQ_EVENT, vcpu)) return true; return kvm_arch_dy_has_pending_interrupt(vcpu); } bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { if (vcpu->arch.guest_state_protected) return true; return static_call(kvm_x86_get_cpl)(vcpu) == 0; } unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) { return kvm_rip_read(vcpu); } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { return static_call(kvm_x86_interrupt_allowed)(vcpu, false); } unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) { /* Can't read the RIP when guest state is protected, just return 0 */ if (vcpu->arch.guest_state_protected) return 0; if (is_64_bit_mode(vcpu)) return kvm_rip_read(vcpu); return (u32)(get_segment_base(vcpu, VCPU_SREG_CS) + kvm_rip_read(vcpu)); } EXPORT_SYMBOL_GPL(kvm_get_linear_rip); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip) { return kvm_get_linear_rip(vcpu) == linear_rip; } EXPORT_SYMBOL_GPL(kvm_is_linear_rip); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags; rflags = static_call(kvm_x86_get_rflags)(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) rflags &= ~X86_EFLAGS_TF; return rflags; } EXPORT_SYMBOL_GPL(kvm_get_rflags); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) rflags |= X86_EFLAGS_TF; static_call(kvm_x86_set_rflags)(vcpu, rflags); } void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { __kvm_set_rflags(vcpu, rflags); kvm_make_request(KVM_REQ_EVENT, vcpu); } EXPORT_SYMBOL_GPL(kvm_set_rflags); static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) { BUILD_BUG_ON(!is_power_of_2(ASYNC_PF_PER_VCPU)); return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU)); } static inline u32 kvm_async_pf_next_probe(u32 key) { return (key + 1) & (ASYNC_PF_PER_VCPU - 1); } static void kvm_add_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) { u32 key = kvm_async_pf_hash_fn(gfn); while (vcpu->arch.apf.gfns[key] != ~0) key = kvm_async_pf_next_probe(key); vcpu->arch.apf.gfns[key] = gfn; } static u32 kvm_async_pf_gfn_slot(struct kvm_vcpu *vcpu, gfn_t gfn) { int i; u32 key = kvm_async_pf_hash_fn(gfn); for (i = 0; i < ASYNC_PF_PER_VCPU && (vcpu->arch.apf.gfns[key] != gfn && vcpu->arch.apf.gfns[key] != ~0); i++) key = kvm_async_pf_next_probe(key); return key; } bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) { return vcpu->arch.apf.gfns[kvm_async_pf_gfn_slot(vcpu, gfn)] == gfn; } static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) { u32 i, j, k; i = j = kvm_async_pf_gfn_slot(vcpu, gfn); if (WARN_ON_ONCE(vcpu->arch.apf.gfns[i] != gfn)) return; while (true) { vcpu->arch.apf.gfns[i] = ~0; do { j = kvm_async_pf_next_probe(j); if (vcpu->arch.apf.gfns[j] == ~0) return; k = kvm_async_pf_hash_fn(vcpu->arch.apf.gfns[j]); /* * k lies cyclically in ]i,j] * | i.k.j | * |....j i.k.| or |.k..j i...| */ } while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j)); vcpu->arch.apf.gfns[i] = vcpu->arch.apf.gfns[j]; i = j; } } static inline int apf_put_user_notpresent(struct kvm_vcpu *vcpu) { u32 reason = KVM_PV_REASON_PAGE_NOT_PRESENT; return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &reason, sizeof(reason)); } static inline int apf_put_user_ready(struct kvm_vcpu *vcpu, u32 token) { unsigned int offset = offsetof(struct kvm_vcpu_pv_apf_data, token); return kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.apf.data, &token, offset, sizeof(token)); } static inline bool apf_pageready_slot_free(struct kvm_vcpu *vcpu) { unsigned int offset = offsetof(struct kvm_vcpu_pv_apf_data, token); u32 val; if (kvm_read_guest_offset_cached(vcpu->kvm, &vcpu->arch.apf.data, &val, offset, sizeof(val))) return false; return !val; } static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) { if (!kvm_pv_async_pf_enabled(vcpu)) return false; if (vcpu->arch.apf.send_user_only && static_call(kvm_x86_get_cpl)(vcpu) == 0) return false; if (is_guest_mode(vcpu)) { /* * L1 needs to opt into the special #PF vmexits that are * used to deliver async page faults. */ return vcpu->arch.apf.delivery_as_pf_vmexit; } else { /* * Play it safe in case the guest temporarily disables paging. * The real mode IDT in particular is unlikely to have a #PF * exception setup. */ return is_paging(vcpu); } } bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || kvm_event_needs_reinjection(vcpu) || kvm_is_exception_pending(vcpu))) return false; if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu)) return false; /* * If interrupts are off we cannot even use an artificial * halt state. */ return kvm_arch_interrupt_allowed(vcpu); } bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { struct x86_exception fault; trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); if (kvm_can_deliver_async_pf(vcpu) && !apf_put_user_notpresent(vcpu)) { fault.vector = PF_VECTOR; fault.error_code_valid = true; fault.error_code = 0; fault.nested_page_fault = false; fault.address = work->arch.token; fault.async_page_fault = true; kvm_inject_page_fault(vcpu, &fault); return true; } else { /* * It is not possible to deliver a paravirtualized asynchronous * page fault, but putting the guest in an artificial halt state * can be beneficial nevertheless: if an interrupt arrives, we * can deliver it timely and perhaps the guest will schedule * another process. When the instruction that triggered a page * fault is retried, hopefully the page will be ready in the host. */ kvm_make_request(KVM_REQ_APF_HALT, vcpu); return false; } } void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { struct kvm_lapic_irq irq = { .delivery_mode = APIC_DM_FIXED, .vector = vcpu->arch.apf.vec }; if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa); if ((work->wakeup_all || work->notpresent_injected) && kvm_pv_async_pf_enabled(vcpu) && !apf_put_user_ready(vcpu, work->arch.token)) { vcpu->arch.apf.pageready_pending = true; kvm_apic_set_irq(vcpu, &irq, NULL); } vcpu->arch.apf.halted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu) { kvm_make_request(KVM_REQ_APF_READY, vcpu); if (!vcpu->arch.apf.pageready_pending) kvm_vcpu_kick(vcpu); } bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) { if (!kvm_pv_async_pf_enabled(vcpu)) return true; else return kvm_lapic_enabled(vcpu) && apf_pageready_slot_free(vcpu); } void kvm_arch_start_assignment(struct kvm *kvm) { if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1) static_call_cond(kvm_x86_pi_start_assignment)(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); void kvm_arch_end_assignment(struct kvm *kvm) { atomic_dec(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) { return raw_atomic_read(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm) { /* * Non-coherent DMA assignment and de-assignment will affect * whether KVM honors guest MTRRs and cause changes in memtypes * in TDP. * So, pass %true unconditionally to indicate non-coherent DMA was, * or will be involved, and that zapping SPTEs might be necessary. */ if (__kvm_mmu_honors_guest_mtrrs(true)) kvm_zap_gfn_range(kvm, gpa_to_gfn(0), gpa_to_gfn(~0ULL)); } void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { if (atomic_inc_return(&kvm->arch.noncoherent_dma_count) == 1) kvm_noncoherent_dma_assignment_start_or_stop(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { if (!atomic_dec_return(&kvm->arch.noncoherent_dma_count)) kvm_noncoherent_dma_assignment_start_or_stop(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma); bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) { return atomic_read(&kvm->arch.noncoherent_dma_count); } EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); bool kvm_arch_has_irq_bypass(void) { return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP); } int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, struct irq_bypass_producer *prod) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); int ret; irqfd->producer = prod; kvm_arch_start_assignment(irqfd->kvm); ret = static_call(kvm_x86_pi_update_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 1); if (ret) kvm_arch_end_assignment(irqfd->kvm); return ret; } void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, struct irq_bypass_producer *prod) { int ret; struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); WARN_ON(irqfd->producer != prod); irqfd->producer = NULL; /* * When producer of consumer is unregistered, we change back to * remapped mode, so we can re-use the current implementation * when the irq is masked/disabled or the consumer side (KVM * int this case doesn't want to receive the interrupts. */ ret = static_call(kvm_x86_pi_update_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 0); if (ret) printk(KERN_INFO "irq bypass consumer (token %p) unregistration" " fails: %d\n", irqfd->consumer.token, ret); kvm_arch_end_assignment(irqfd->kvm); } int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set) { return static_call(kvm_x86_pi_update_irte)(kvm, host_irq, guest_irq, set); } bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old, struct kvm_kernel_irq_routing_entry *new) { if (new->type != KVM_IRQ_ROUTING_MSI) return true; return !!memcmp(&old->msi, &new->msi, sizeof(new->msi)); } bool kvm_vector_hashing_enabled(void) { return vector_hashing; } bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { return (vcpu->arch.msr_kvm_poll_control & 1) == 0; } EXPORT_SYMBOL_GPL(kvm_arch_no_poll); int kvm_spec_ctrl_test_value(u64 value) { /* * test that setting IA32_SPEC_CTRL to given value * is allowed by the host processor */ u64 saved_value; unsigned long flags; int ret = 0; local_irq_save(flags); if (rdmsrl_safe(MSR_IA32_SPEC_CTRL, &saved_value)) ret = 1; else if (wrmsrl_safe(MSR_IA32_SPEC_CTRL, value)) ret = 1; else wrmsrl(MSR_IA32_SPEC_CTRL, saved_value); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; struct x86_exception fault; u64 access = error_code & (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || mmu->gva_to_gpa(vcpu, mmu, gva, access, &fault) != INVALID_GPA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed * with the error code that the processor gave. */ fault.vector = PF_VECTOR; fault.error_code_valid = true; fault.error_code = error_code; fault.nested_page_fault = false; fault.address = gva; fault.async_page_fault = false; } vcpu->arch.walk_mmu->inject_page_fault(vcpu, &fault); } EXPORT_SYMBOL_GPL(kvm_fixup_and_inject_pf_error); /* * Handles kvm_read/write_guest_virt*() result and either injects #PF or returns * KVM_EXIT_INTERNAL_ERROR for cases not currently handled by KVM. Return value * indicates whether exit to userspace is needed. */ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e) { if (r == X86EMUL_PROPAGATE_FAULT) { if (KVM_BUG_ON(!e, vcpu->kvm)) return -EIO; kvm_inject_emulated_page_fault(vcpu, e); return 1; } /* * In case kvm_read/write_guest_virt*() failed with X86EMUL_IO_NEEDED * while handling a VMX instruction KVM could've handled the request * correctly by exiting to userspace and performing I/O but there * doesn't seem to be a real use-case behind such requests, just return * KVM_EXIT_INTERNAL_ERROR for now. */ kvm_prepare_emulation_failure_exit(vcpu); return 0; } EXPORT_SYMBOL_GPL(kvm_handle_memory_failure); int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) { bool pcid_enabled; struct x86_exception e; struct { u64 pcid; u64 gla; } operand; int r; r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e); if (r != X86EMUL_CONTINUE) return kvm_handle_memory_failure(vcpu, r, &e); if (operand.pcid >> 12 != 0) { kvm_inject_gp(vcpu, 0); return 1; } pcid_enabled = kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE); switch (type) { case INVPCID_TYPE_INDIV_ADDR: /* * LAM doesn't apply to addresses that are inputs to TLB * invalidation. */ if ((!pcid_enabled && (operand.pcid != 0)) || is_noncanonical_address(operand.gla, vcpu)) { kvm_inject_gp(vcpu, 0); return 1; } kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid); return kvm_skip_emulated_instruction(vcpu); case INVPCID_TYPE_SINGLE_CTXT: if (!pcid_enabled && (operand.pcid != 0)) { kvm_inject_gp(vcpu, 0); return 1; } kvm_invalidate_pcid(vcpu, operand.pcid); return kvm_skip_emulated_instruction(vcpu); case INVPCID_TYPE_ALL_NON_GLOBAL: /* * Currently, KVM doesn't mark global entries in the shadow * page tables, so a non-global flush just degenerates to a * global flush. If needed, we could optimize this later by * keeping track of global entries in shadow page tables. */ fallthrough; case INVPCID_TYPE_ALL_INCL_GLOBAL: kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return kvm_skip_emulated_instruction(vcpu); default: kvm_inject_gp(vcpu, 0); return 1; } } EXPORT_SYMBOL_GPL(kvm_handle_invpcid); static int complete_sev_es_emulated_mmio(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; struct kvm_mmio_fragment *frag; unsigned int len; BUG_ON(!vcpu->mmio_needed); /* Complete previous fragment */ frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment]; len = min(8u, frag->len); if (!vcpu->mmio_is_write) memcpy(frag->data, run->mmio.data, len); if (frag->len <= 8) { /* Switch to the next fragment. */ frag++; vcpu->mmio_cur_fragment++; } else { /* Go forward to the next mmio piece. */ frag->data += len; frag->gpa += len; frag->len -= len; } if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { vcpu->mmio_needed = 0; // VMG change, at this point, we're always done // RIP has already been advanced return 1; } // More MMIO is needed run->mmio.phys_addr = frag->gpa; run->mmio.len = min(8u, frag->len); run->mmio.is_write = vcpu->mmio_is_write; if (run->mmio.is_write) memcpy(run->mmio.data, frag->data, min(8u, frag->len)); run->exit_reason = KVM_EXIT_MMIO; vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; return 0; } int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, void *data) { int handled; struct kvm_mmio_fragment *frag; if (!data) return -EINVAL; handled = write_emultor.read_write_mmio(vcpu, gpa, bytes, data); if (handled == bytes) return 1; bytes -= handled; gpa += handled; data += handled; /*TODO: Check if need to increment number of frags */ frag = vcpu->mmio_fragments; vcpu->mmio_nr_fragments = 1; frag->len = bytes; frag->gpa = gpa; frag->data = data; vcpu->mmio_needed = 1; vcpu->mmio_cur_fragment = 0; vcpu->run->mmio.phys_addr = gpa; vcpu->run->mmio.len = min(8u, frag->len); vcpu->run->mmio.is_write = 1; memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len)); vcpu->run->exit_reason = KVM_EXIT_MMIO; vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; return 0; } EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_write); int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, void *data) { int handled; struct kvm_mmio_fragment *frag; if (!data) return -EINVAL; handled = read_emultor.read_write_mmio(vcpu, gpa, bytes, data); if (handled == bytes) return 1; bytes -= handled; gpa += handled; data += handled; /*TODO: Check if need to increment number of frags */ frag = vcpu->mmio_fragments; vcpu->mmio_nr_fragments = 1; frag->len = bytes; frag->gpa = gpa; frag->data = data; vcpu->mmio_needed = 1; vcpu->mmio_cur_fragment = 0; vcpu->run->mmio.phys_addr = gpa; vcpu->run->mmio.len = min(8u, frag->len); vcpu->run->mmio.is_write = 0; vcpu->run->exit_reason = KVM_EXIT_MMIO; vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; return 0; } EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read); static void advance_sev_es_emulated_pio(struct kvm_vcpu *vcpu, unsigned count, int size) { vcpu->arch.sev_pio_count -= count; vcpu->arch.sev_pio_data += count * size; } static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port); static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu) { int size = vcpu->arch.pio.size; int port = vcpu->arch.pio.port; vcpu->arch.pio.count = 0; if (vcpu->arch.sev_pio_count) return kvm_sev_es_outs(vcpu, size, port); return 1; } static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port) { for (;;) { unsigned int count = min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count); /* memcpy done already by emulator_pio_out. */ advance_sev_es_emulated_pio(vcpu, count, size); if (!ret) break; /* Emulation done by the kernel. */ if (!vcpu->arch.sev_pio_count) return 1; } vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs; return 0; } static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port); static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu) { unsigned count = vcpu->arch.pio.count; int size = vcpu->arch.pio.size; int port = vcpu->arch.pio.port; complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data); advance_sev_es_emulated_pio(vcpu, count, size); if (vcpu->arch.sev_pio_count) return kvm_sev_es_ins(vcpu, size, port); return 1; } static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port) { for (;;) { unsigned int count = min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); if (!emulator_pio_in(vcpu, size, port, vcpu->arch.sev_pio_data, count)) break; /* Emulation done by the kernel. */ advance_sev_es_emulated_pio(vcpu, count, size); if (!vcpu->arch.sev_pio_count) return 1; } vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins; return 0; } int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port, void *data, unsigned int count, int in) { vcpu->arch.sev_pio_data = data; vcpu->arch.sev_pio_count = count; return in ? kvm_sev_es_ins(vcpu, size, port) : kvm_sev_es_outs(vcpu, size, port); } EXPORT_SYMBOL_GPL(kvm_sev_es_string_io); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter_failed); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_kick_vcpu_slowpath); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_doorbell); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_accept_irq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit); static int __init kvm_x86_init(void) { kvm_mmu_x86_module_init(); mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible(); return 0; } module_init(kvm_x86_init); static void __exit kvm_x86_exit(void) { WARN_ON_ONCE(static_branch_unlikely(&kvm_has_noapic_vcpu)); } module_exit(kvm_x86_exit); |
| 2 1582 1581 3 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * * Authors: * (C) 2015 Pengutronix, Alexander Aring <aar@pengutronix.de> */ #include <linux/if_arp.h> #include <linux/module.h> #include <net/6lowpan.h> #include <net/addrconf.h> #include "6lowpan_i.h" int lowpan_register_netdevice(struct net_device *dev, enum lowpan_lltypes lltype) { int i, ret; switch (lltype) { case LOWPAN_LLTYPE_IEEE802154: dev->addr_len = EUI64_ADDR_LEN; break; case LOWPAN_LLTYPE_BTLE: dev->addr_len = ETH_ALEN; break; } dev->type = ARPHRD_6LOWPAN; dev->mtu = IPV6_MIN_MTU; lowpan_dev(dev)->lltype = lltype; spin_lock_init(&lowpan_dev(dev)->ctx.lock); for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) lowpan_dev(dev)->ctx.table[i].id = i; dev->ndisc_ops = &lowpan_ndisc_ops; ret = register_netdevice(dev); if (ret < 0) return ret; lowpan_dev_debugfs_init(dev); return ret; } EXPORT_SYMBOL(lowpan_register_netdevice); int lowpan_register_netdev(struct net_device *dev, enum lowpan_lltypes lltype) { int ret; rtnl_lock(); ret = lowpan_register_netdevice(dev, lltype); rtnl_unlock(); return ret; } EXPORT_SYMBOL(lowpan_register_netdev); void lowpan_unregister_netdevice(struct net_device *dev) { unregister_netdevice(dev); lowpan_dev_debugfs_exit(dev); } EXPORT_SYMBOL(lowpan_unregister_netdevice); void lowpan_unregister_netdev(struct net_device *dev) { rtnl_lock(); lowpan_unregister_netdevice(dev); rtnl_unlock(); } EXPORT_SYMBOL(lowpan_unregister_netdev); int addrconf_ifid_802154_6lowpan(u8 *eui, struct net_device *dev) { struct wpan_dev *wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr; /* Set short_addr autoconfiguration if short_addr is present only */ if (!lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr)) return -1; /* For either address format, all zero addresses MUST NOT be used */ if (wpan_dev->pan_id == cpu_to_le16(0x0000) && wpan_dev->short_addr == cpu_to_le16(0x0000)) return -1; /* Alternatively, if no PAN ID is known, 16 zero bits may be used */ if (wpan_dev->pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST)) memset(eui, 0, 2); else ieee802154_le16_to_be16(eui, &wpan_dev->pan_id); /* The "Universal/Local" (U/L) bit shall be set to zero */ eui[0] &= ~2; eui[2] = 0; eui[3] = 0xFF; eui[4] = 0xFE; eui[5] = 0; ieee802154_le16_to_be16(&eui[6], &wpan_dev->short_addr); return 0; } static int lowpan_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev; struct in6_addr addr; int i; if (dev->type != ARPHRD_6LOWPAN) return NOTIFY_DONE; idev = __in6_dev_get(dev); if (!idev) return NOTIFY_DONE; switch (event) { case NETDEV_UP: case NETDEV_CHANGE: /* (802.15.4 6LoWPAN short address slaac handling */ if (lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154) && addrconf_ifid_802154_6lowpan(addr.s6_addr + 8, dev) == 0) { __ipv6_addr_set_half(&addr.s6_addr32[0], htonl(0xFE800000), 0); addrconf_add_linklocal(idev, &addr, 0); } break; case NETDEV_DOWN: for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) clear_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, &lowpan_dev(dev)->ctx.table[i].flags); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block lowpan_notifier = { .notifier_call = lowpan_event, }; static int __init lowpan_module_init(void) { int ret; lowpan_debugfs_init(); ret = register_netdevice_notifier(&lowpan_notifier); if (ret < 0) { lowpan_debugfs_exit(); return ret; } request_module_nowait("nhc_dest"); request_module_nowait("nhc_fragment"); request_module_nowait("nhc_hop"); request_module_nowait("nhc_ipv6"); request_module_nowait("nhc_mobility"); request_module_nowait("nhc_routing"); request_module_nowait("nhc_udp"); return 0; } static void __exit lowpan_module_exit(void) { lowpan_debugfs_exit(); unregister_netdevice_notifier(&lowpan_notifier); } module_init(lowpan_module_init); module_exit(lowpan_module_exit); MODULE_DESCRIPTION("IPv6 over Low-Power Wireless Personal Area Network core module"); MODULE_LICENSE("GPL"); |
| 6 2 4 2 4 4 7 7 2 3 1 4 6 6 4 4 4 4 6 6 4 4 3 3 2 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Glue Code for assembler optimized version of Camellia * * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> * * Camellia parts based on code by: * Copyright (C) 2006 NTT (Nippon Telegraph and Telephone Corporation) */ #include <asm/unaligned.h> #include <linux/crypto.h> #include <linux/init.h> #include <linux/module.h> #include <linux/types.h> #include <crypto/algapi.h> #include "camellia.h" #include "ecb_cbc_helpers.h" /* regular block cipher functions */ asmlinkage void __camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src, bool xor); EXPORT_SYMBOL_GPL(__camellia_enc_blk); asmlinkage void camellia_dec_blk(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(camellia_dec_blk); /* 2-way parallel cipher functions */ asmlinkage void __camellia_enc_blk_2way(const void *ctx, u8 *dst, const u8 *src, bool xor); EXPORT_SYMBOL_GPL(__camellia_enc_blk_2way); asmlinkage void camellia_dec_blk_2way(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(camellia_dec_blk_2way); static void camellia_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { camellia_enc_blk(crypto_tfm_ctx(tfm), dst, src); } static void camellia_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { camellia_dec_blk(crypto_tfm_ctx(tfm), dst, src); } /* camellia sboxes */ __visible const u64 camellia_sp10011110[256] = { 0x7000007070707000ULL, 0x8200008282828200ULL, 0x2c00002c2c2c2c00ULL, 0xec0000ecececec00ULL, 0xb30000b3b3b3b300ULL, 0x2700002727272700ULL, 0xc00000c0c0c0c000ULL, 0xe50000e5e5e5e500ULL, 0xe40000e4e4e4e400ULL, 0x8500008585858500ULL, 0x5700005757575700ULL, 0x3500003535353500ULL, 0xea0000eaeaeaea00ULL, 0x0c00000c0c0c0c00ULL, 0xae0000aeaeaeae00ULL, 0x4100004141414100ULL, 0x2300002323232300ULL, 0xef0000efefefef00ULL, 0x6b00006b6b6b6b00ULL, 0x9300009393939300ULL, 0x4500004545454500ULL, 0x1900001919191900ULL, 0xa50000a5a5a5a500ULL, 0x2100002121212100ULL, 0xed0000edededed00ULL, 0x0e00000e0e0e0e00ULL, 0x4f00004f4f4f4f00ULL, 0x4e00004e4e4e4e00ULL, 0x1d00001d1d1d1d00ULL, 0x6500006565656500ULL, 0x9200009292929200ULL, 0xbd0000bdbdbdbd00ULL, 0x8600008686868600ULL, 0xb80000b8b8b8b800ULL, 0xaf0000afafafaf00ULL, 0x8f00008f8f8f8f00ULL, 0x7c00007c7c7c7c00ULL, 0xeb0000ebebebeb00ULL, 0x1f00001f1f1f1f00ULL, 0xce0000cececece00ULL, 0x3e00003e3e3e3e00ULL, 0x3000003030303000ULL, 0xdc0000dcdcdcdc00ULL, 0x5f00005f5f5f5f00ULL, 0x5e00005e5e5e5e00ULL, 0xc50000c5c5c5c500ULL, 0x0b00000b0b0b0b00ULL, 0x1a00001a1a1a1a00ULL, 0xa60000a6a6a6a600ULL, 0xe10000e1e1e1e100ULL, 0x3900003939393900ULL, 0xca0000cacacaca00ULL, 0xd50000d5d5d5d500ULL, 0x4700004747474700ULL, 0x5d00005d5d5d5d00ULL, 0x3d00003d3d3d3d00ULL, 0xd90000d9d9d9d900ULL, 0x0100000101010100ULL, 0x5a00005a5a5a5a00ULL, 0xd60000d6d6d6d600ULL, 0x5100005151515100ULL, 0x5600005656565600ULL, 0x6c00006c6c6c6c00ULL, 0x4d00004d4d4d4d00ULL, 0x8b00008b8b8b8b00ULL, 0x0d00000d0d0d0d00ULL, 0x9a00009a9a9a9a00ULL, 0x6600006666666600ULL, 0xfb0000fbfbfbfb00ULL, 0xcc0000cccccccc00ULL, 0xb00000b0b0b0b000ULL, 0x2d00002d2d2d2d00ULL, 0x7400007474747400ULL, 0x1200001212121200ULL, 0x2b00002b2b2b2b00ULL, 0x2000002020202000ULL, 0xf00000f0f0f0f000ULL, 0xb10000b1b1b1b100ULL, 0x8400008484848400ULL, 0x9900009999999900ULL, 0xdf0000dfdfdfdf00ULL, 0x4c00004c4c4c4c00ULL, 0xcb0000cbcbcbcb00ULL, 0xc20000c2c2c2c200ULL, 0x3400003434343400ULL, 0x7e00007e7e7e7e00ULL, 0x7600007676767600ULL, 0x0500000505050500ULL, 0x6d00006d6d6d6d00ULL, 0xb70000b7b7b7b700ULL, 0xa90000a9a9a9a900ULL, 0x3100003131313100ULL, 0xd10000d1d1d1d100ULL, 0x1700001717171700ULL, 0x0400000404040400ULL, 0xd70000d7d7d7d700ULL, 0x1400001414141400ULL, 0x5800005858585800ULL, 0x3a00003a3a3a3a00ULL, 0x6100006161616100ULL, 0xde0000dededede00ULL, 0x1b00001b1b1b1b00ULL, 0x1100001111111100ULL, 0x1c00001c1c1c1c00ULL, 0x3200003232323200ULL, 0x0f00000f0f0f0f00ULL, 0x9c00009c9c9c9c00ULL, 0x1600001616161600ULL, 0x5300005353535300ULL, 0x1800001818181800ULL, 0xf20000f2f2f2f200ULL, 0x2200002222222200ULL, 0xfe0000fefefefe00ULL, 0x4400004444444400ULL, 0xcf0000cfcfcfcf00ULL, 0xb20000b2b2b2b200ULL, 0xc30000c3c3c3c300ULL, 0xb50000b5b5b5b500ULL, 0x7a00007a7a7a7a00ULL, 0x9100009191919100ULL, 0x2400002424242400ULL, 0x0800000808080800ULL, 0xe80000e8e8e8e800ULL, 0xa80000a8a8a8a800ULL, 0x6000006060606000ULL, 0xfc0000fcfcfcfc00ULL, 0x6900006969696900ULL, 0x5000005050505000ULL, 0xaa0000aaaaaaaa00ULL, 0xd00000d0d0d0d000ULL, 0xa00000a0a0a0a000ULL, 0x7d00007d7d7d7d00ULL, 0xa10000a1a1a1a100ULL, 0x8900008989898900ULL, 0x6200006262626200ULL, 0x9700009797979700ULL, 0x5400005454545400ULL, 0x5b00005b5b5b5b00ULL, 0x1e00001e1e1e1e00ULL, 0x9500009595959500ULL, 0xe00000e0e0e0e000ULL, 0xff0000ffffffff00ULL, 0x6400006464646400ULL, 0xd20000d2d2d2d200ULL, 0x1000001010101000ULL, 0xc40000c4c4c4c400ULL, 0x0000000000000000ULL, 0x4800004848484800ULL, 0xa30000a3a3a3a300ULL, 0xf70000f7f7f7f700ULL, 0x7500007575757500ULL, 0xdb0000dbdbdbdb00ULL, 0x8a00008a8a8a8a00ULL, 0x0300000303030300ULL, 0xe60000e6e6e6e600ULL, 0xda0000dadadada00ULL, 0x0900000909090900ULL, 0x3f00003f3f3f3f00ULL, 0xdd0000dddddddd00ULL, 0x9400009494949400ULL, 0x8700008787878700ULL, 0x5c00005c5c5c5c00ULL, 0x8300008383838300ULL, 0x0200000202020200ULL, 0xcd0000cdcdcdcd00ULL, 0x4a00004a4a4a4a00ULL, 0x9000009090909000ULL, 0x3300003333333300ULL, 0x7300007373737300ULL, 0x6700006767676700ULL, 0xf60000f6f6f6f600ULL, 0xf30000f3f3f3f300ULL, 0x9d00009d9d9d9d00ULL, 0x7f00007f7f7f7f00ULL, 0xbf0000bfbfbfbf00ULL, 0xe20000e2e2e2e200ULL, 0x5200005252525200ULL, 0x9b00009b9b9b9b00ULL, 0xd80000d8d8d8d800ULL, 0x2600002626262600ULL, 0xc80000c8c8c8c800ULL, 0x3700003737373700ULL, 0xc60000c6c6c6c600ULL, 0x3b00003b3b3b3b00ULL, 0x8100008181818100ULL, 0x9600009696969600ULL, 0x6f00006f6f6f6f00ULL, 0x4b00004b4b4b4b00ULL, 0x1300001313131300ULL, 0xbe0000bebebebe00ULL, 0x6300006363636300ULL, 0x2e00002e2e2e2e00ULL, 0xe90000e9e9e9e900ULL, 0x7900007979797900ULL, 0xa70000a7a7a7a700ULL, 0x8c00008c8c8c8c00ULL, 0x9f00009f9f9f9f00ULL, 0x6e00006e6e6e6e00ULL, 0xbc0000bcbcbcbc00ULL, 0x8e00008e8e8e8e00ULL, 0x2900002929292900ULL, 0xf50000f5f5f5f500ULL, 0xf90000f9f9f9f900ULL, 0xb60000b6b6b6b600ULL, 0x2f00002f2f2f2f00ULL, 0xfd0000fdfdfdfd00ULL, 0xb40000b4b4b4b400ULL, 0x5900005959595900ULL, 0x7800007878787800ULL, 0x9800009898989800ULL, 0x0600000606060600ULL, 0x6a00006a6a6a6a00ULL, 0xe70000e7e7e7e700ULL, 0x4600004646464600ULL, 0x7100007171717100ULL, 0xba0000babababa00ULL, 0xd40000d4d4d4d400ULL, 0x2500002525252500ULL, 0xab0000abababab00ULL, 0x4200004242424200ULL, 0x8800008888888800ULL, 0xa20000a2a2a2a200ULL, 0x8d00008d8d8d8d00ULL, 0xfa0000fafafafa00ULL, 0x7200007272727200ULL, 0x0700000707070700ULL, 0xb90000b9b9b9b900ULL, 0x5500005555555500ULL, 0xf80000f8f8f8f800ULL, 0xee0000eeeeeeee00ULL, 0xac0000acacacac00ULL, 0x0a00000a0a0a0a00ULL, 0x3600003636363600ULL, 0x4900004949494900ULL, 0x2a00002a2a2a2a00ULL, 0x6800006868686800ULL, 0x3c00003c3c3c3c00ULL, 0x3800003838383800ULL, 0xf10000f1f1f1f100ULL, 0xa40000a4a4a4a400ULL, 0x4000004040404000ULL, 0x2800002828282800ULL, 0xd30000d3d3d3d300ULL, 0x7b00007b7b7b7b00ULL, 0xbb0000bbbbbbbb00ULL, 0xc90000c9c9c9c900ULL, 0x4300004343434300ULL, 0xc10000c1c1c1c100ULL, 0x1500001515151500ULL, 0xe30000e3e3e3e300ULL, 0xad0000adadadad00ULL, 0xf40000f4f4f4f400ULL, 0x7700007777777700ULL, 0xc70000c7c7c7c700ULL, 0x8000008080808000ULL, 0x9e00009e9e9e9e00ULL, }; __visible const u64 camellia_sp22000222[256] = { 0xe0e0000000e0e0e0ULL, 0x0505000000050505ULL, 0x5858000000585858ULL, 0xd9d9000000d9d9d9ULL, 0x6767000000676767ULL, 0x4e4e0000004e4e4eULL, 0x8181000000818181ULL, 0xcbcb000000cbcbcbULL, 0xc9c9000000c9c9c9ULL, 0x0b0b0000000b0b0bULL, 0xaeae000000aeaeaeULL, 0x6a6a0000006a6a6aULL, 0xd5d5000000d5d5d5ULL, 0x1818000000181818ULL, 0x5d5d0000005d5d5dULL, 0x8282000000828282ULL, 0x4646000000464646ULL, 0xdfdf000000dfdfdfULL, 0xd6d6000000d6d6d6ULL, 0x2727000000272727ULL, 0x8a8a0000008a8a8aULL, 0x3232000000323232ULL, 0x4b4b0000004b4b4bULL, 0x4242000000424242ULL, 0xdbdb000000dbdbdbULL, 0x1c1c0000001c1c1cULL, 0x9e9e0000009e9e9eULL, 0x9c9c0000009c9c9cULL, 0x3a3a0000003a3a3aULL, 0xcaca000000cacacaULL, 0x2525000000252525ULL, 0x7b7b0000007b7b7bULL, 0x0d0d0000000d0d0dULL, 0x7171000000717171ULL, 0x5f5f0000005f5f5fULL, 0x1f1f0000001f1f1fULL, 0xf8f8000000f8f8f8ULL, 0xd7d7000000d7d7d7ULL, 0x3e3e0000003e3e3eULL, 0x9d9d0000009d9d9dULL, 0x7c7c0000007c7c7cULL, 0x6060000000606060ULL, 0xb9b9000000b9b9b9ULL, 0xbebe000000bebebeULL, 0xbcbc000000bcbcbcULL, 0x8b8b0000008b8b8bULL, 0x1616000000161616ULL, 0x3434000000343434ULL, 0x4d4d0000004d4d4dULL, 0xc3c3000000c3c3c3ULL, 0x7272000000727272ULL, 0x9595000000959595ULL, 0xabab000000abababULL, 0x8e8e0000008e8e8eULL, 0xbaba000000bababaULL, 0x7a7a0000007a7a7aULL, 0xb3b3000000b3b3b3ULL, 0x0202000000020202ULL, 0xb4b4000000b4b4b4ULL, 0xadad000000adadadULL, 0xa2a2000000a2a2a2ULL, 0xacac000000acacacULL, 0xd8d8000000d8d8d8ULL, 0x9a9a0000009a9a9aULL, 0x1717000000171717ULL, 0x1a1a0000001a1a1aULL, 0x3535000000353535ULL, 0xcccc000000ccccccULL, 0xf7f7000000f7f7f7ULL, 0x9999000000999999ULL, 0x6161000000616161ULL, 0x5a5a0000005a5a5aULL, 0xe8e8000000e8e8e8ULL, 0x2424000000242424ULL, 0x5656000000565656ULL, 0x4040000000404040ULL, 0xe1e1000000e1e1e1ULL, 0x6363000000636363ULL, 0x0909000000090909ULL, 0x3333000000333333ULL, 0xbfbf000000bfbfbfULL, 0x9898000000989898ULL, 0x9797000000979797ULL, 0x8585000000858585ULL, 0x6868000000686868ULL, 0xfcfc000000fcfcfcULL, 0xecec000000ecececULL, 0x0a0a0000000a0a0aULL, 0xdada000000dadadaULL, 0x6f6f0000006f6f6fULL, 0x5353000000535353ULL, 0x6262000000626262ULL, 0xa3a3000000a3a3a3ULL, 0x2e2e0000002e2e2eULL, 0x0808000000080808ULL, 0xafaf000000afafafULL, 0x2828000000282828ULL, 0xb0b0000000b0b0b0ULL, 0x7474000000747474ULL, 0xc2c2000000c2c2c2ULL, 0xbdbd000000bdbdbdULL, 0x3636000000363636ULL, 0x2222000000222222ULL, 0x3838000000383838ULL, 0x6464000000646464ULL, 0x1e1e0000001e1e1eULL, 0x3939000000393939ULL, 0x2c2c0000002c2c2cULL, 0xa6a6000000a6a6a6ULL, 0x3030000000303030ULL, 0xe5e5000000e5e5e5ULL, 0x4444000000444444ULL, 0xfdfd000000fdfdfdULL, 0x8888000000888888ULL, 0x9f9f0000009f9f9fULL, 0x6565000000656565ULL, 0x8787000000878787ULL, 0x6b6b0000006b6b6bULL, 0xf4f4000000f4f4f4ULL, 0x2323000000232323ULL, 0x4848000000484848ULL, 0x1010000000101010ULL, 0xd1d1000000d1d1d1ULL, 0x5151000000515151ULL, 0xc0c0000000c0c0c0ULL, 0xf9f9000000f9f9f9ULL, 0xd2d2000000d2d2d2ULL, 0xa0a0000000a0a0a0ULL, 0x5555000000555555ULL, 0xa1a1000000a1a1a1ULL, 0x4141000000414141ULL, 0xfafa000000fafafaULL, 0x4343000000434343ULL, 0x1313000000131313ULL, 0xc4c4000000c4c4c4ULL, 0x2f2f0000002f2f2fULL, 0xa8a8000000a8a8a8ULL, 0xb6b6000000b6b6b6ULL, 0x3c3c0000003c3c3cULL, 0x2b2b0000002b2b2bULL, 0xc1c1000000c1c1c1ULL, 0xffff000000ffffffULL, 0xc8c8000000c8c8c8ULL, 0xa5a5000000a5a5a5ULL, 0x2020000000202020ULL, 0x8989000000898989ULL, 0x0000000000000000ULL, 0x9090000000909090ULL, 0x4747000000474747ULL, 0xefef000000efefefULL, 0xeaea000000eaeaeaULL, 0xb7b7000000b7b7b7ULL, 0x1515000000151515ULL, 0x0606000000060606ULL, 0xcdcd000000cdcdcdULL, 0xb5b5000000b5b5b5ULL, 0x1212000000121212ULL, 0x7e7e0000007e7e7eULL, 0xbbbb000000bbbbbbULL, 0x2929000000292929ULL, 0x0f0f0000000f0f0fULL, 0xb8b8000000b8b8b8ULL, 0x0707000000070707ULL, 0x0404000000040404ULL, 0x9b9b0000009b9b9bULL, 0x9494000000949494ULL, 0x2121000000212121ULL, 0x6666000000666666ULL, 0xe6e6000000e6e6e6ULL, 0xcece000000cececeULL, 0xeded000000edededULL, 0xe7e7000000e7e7e7ULL, 0x3b3b0000003b3b3bULL, 0xfefe000000fefefeULL, 0x7f7f0000007f7f7fULL, 0xc5c5000000c5c5c5ULL, 0xa4a4000000a4a4a4ULL, 0x3737000000373737ULL, 0xb1b1000000b1b1b1ULL, 0x4c4c0000004c4c4cULL, 0x9191000000919191ULL, 0x6e6e0000006e6e6eULL, 0x8d8d0000008d8d8dULL, 0x7676000000767676ULL, 0x0303000000030303ULL, 0x2d2d0000002d2d2dULL, 0xdede000000dededeULL, 0x9696000000969696ULL, 0x2626000000262626ULL, 0x7d7d0000007d7d7dULL, 0xc6c6000000c6c6c6ULL, 0x5c5c0000005c5c5cULL, 0xd3d3000000d3d3d3ULL, 0xf2f2000000f2f2f2ULL, 0x4f4f0000004f4f4fULL, 0x1919000000191919ULL, 0x3f3f0000003f3f3fULL, 0xdcdc000000dcdcdcULL, 0x7979000000797979ULL, 0x1d1d0000001d1d1dULL, 0x5252000000525252ULL, 0xebeb000000ebebebULL, 0xf3f3000000f3f3f3ULL, 0x6d6d0000006d6d6dULL, 0x5e5e0000005e5e5eULL, 0xfbfb000000fbfbfbULL, 0x6969000000696969ULL, 0xb2b2000000b2b2b2ULL, 0xf0f0000000f0f0f0ULL, 0x3131000000313131ULL, 0x0c0c0000000c0c0cULL, 0xd4d4000000d4d4d4ULL, 0xcfcf000000cfcfcfULL, 0x8c8c0000008c8c8cULL, 0xe2e2000000e2e2e2ULL, 0x7575000000757575ULL, 0xa9a9000000a9a9a9ULL, 0x4a4a0000004a4a4aULL, 0x5757000000575757ULL, 0x8484000000848484ULL, 0x1111000000111111ULL, 0x4545000000454545ULL, 0x1b1b0000001b1b1bULL, 0xf5f5000000f5f5f5ULL, 0xe4e4000000e4e4e4ULL, 0x0e0e0000000e0e0eULL, 0x7373000000737373ULL, 0xaaaa000000aaaaaaULL, 0xf1f1000000f1f1f1ULL, 0xdddd000000ddddddULL, 0x5959000000595959ULL, 0x1414000000141414ULL, 0x6c6c0000006c6c6cULL, 0x9292000000929292ULL, 0x5454000000545454ULL, 0xd0d0000000d0d0d0ULL, 0x7878000000787878ULL, 0x7070000000707070ULL, 0xe3e3000000e3e3e3ULL, 0x4949000000494949ULL, 0x8080000000808080ULL, 0x5050000000505050ULL, 0xa7a7000000a7a7a7ULL, 0xf6f6000000f6f6f6ULL, 0x7777000000777777ULL, 0x9393000000939393ULL, 0x8686000000868686ULL, 0x8383000000838383ULL, 0x2a2a0000002a2a2aULL, 0xc7c7000000c7c7c7ULL, 0x5b5b0000005b5b5bULL, 0xe9e9000000e9e9e9ULL, 0xeeee000000eeeeeeULL, 0x8f8f0000008f8f8fULL, 0x0101000000010101ULL, 0x3d3d0000003d3d3dULL, }; __visible const u64 camellia_sp03303033[256] = { 0x0038380038003838ULL, 0x0041410041004141ULL, 0x0016160016001616ULL, 0x0076760076007676ULL, 0x00d9d900d900d9d9ULL, 0x0093930093009393ULL, 0x0060600060006060ULL, 0x00f2f200f200f2f2ULL, 0x0072720072007272ULL, 0x00c2c200c200c2c2ULL, 0x00abab00ab00ababULL, 0x009a9a009a009a9aULL, 0x0075750075007575ULL, 0x0006060006000606ULL, 0x0057570057005757ULL, 0x00a0a000a000a0a0ULL, 0x0091910091009191ULL, 0x00f7f700f700f7f7ULL, 0x00b5b500b500b5b5ULL, 0x00c9c900c900c9c9ULL, 0x00a2a200a200a2a2ULL, 0x008c8c008c008c8cULL, 0x00d2d200d200d2d2ULL, 0x0090900090009090ULL, 0x00f6f600f600f6f6ULL, 0x0007070007000707ULL, 0x00a7a700a700a7a7ULL, 0x0027270027002727ULL, 0x008e8e008e008e8eULL, 0x00b2b200b200b2b2ULL, 0x0049490049004949ULL, 0x00dede00de00dedeULL, 0x0043430043004343ULL, 0x005c5c005c005c5cULL, 0x00d7d700d700d7d7ULL, 0x00c7c700c700c7c7ULL, 0x003e3e003e003e3eULL, 0x00f5f500f500f5f5ULL, 0x008f8f008f008f8fULL, 0x0067670067006767ULL, 0x001f1f001f001f1fULL, 0x0018180018001818ULL, 0x006e6e006e006e6eULL, 0x00afaf00af00afafULL, 0x002f2f002f002f2fULL, 0x00e2e200e200e2e2ULL, 0x0085850085008585ULL, 0x000d0d000d000d0dULL, 0x0053530053005353ULL, 0x00f0f000f000f0f0ULL, 0x009c9c009c009c9cULL, 0x0065650065006565ULL, 0x00eaea00ea00eaeaULL, 0x00a3a300a300a3a3ULL, 0x00aeae00ae00aeaeULL, 0x009e9e009e009e9eULL, 0x00ecec00ec00ececULL, 0x0080800080008080ULL, 0x002d2d002d002d2dULL, 0x006b6b006b006b6bULL, 0x00a8a800a800a8a8ULL, 0x002b2b002b002b2bULL, 0x0036360036003636ULL, 0x00a6a600a600a6a6ULL, 0x00c5c500c500c5c5ULL, 0x0086860086008686ULL, 0x004d4d004d004d4dULL, 0x0033330033003333ULL, 0x00fdfd00fd00fdfdULL, 0x0066660066006666ULL, 0x0058580058005858ULL, 0x0096960096009696ULL, 0x003a3a003a003a3aULL, 0x0009090009000909ULL, 0x0095950095009595ULL, 0x0010100010001010ULL, 0x0078780078007878ULL, 0x00d8d800d800d8d8ULL, 0x0042420042004242ULL, 0x00cccc00cc00ccccULL, 0x00efef00ef00efefULL, 0x0026260026002626ULL, 0x00e5e500e500e5e5ULL, 0x0061610061006161ULL, 0x001a1a001a001a1aULL, 0x003f3f003f003f3fULL, 0x003b3b003b003b3bULL, 0x0082820082008282ULL, 0x00b6b600b600b6b6ULL, 0x00dbdb00db00dbdbULL, 0x00d4d400d400d4d4ULL, 0x0098980098009898ULL, 0x00e8e800e800e8e8ULL, 0x008b8b008b008b8bULL, 0x0002020002000202ULL, 0x00ebeb00eb00ebebULL, 0x000a0a000a000a0aULL, 0x002c2c002c002c2cULL, 0x001d1d001d001d1dULL, 0x00b0b000b000b0b0ULL, 0x006f6f006f006f6fULL, 0x008d8d008d008d8dULL, 0x0088880088008888ULL, 0x000e0e000e000e0eULL, 0x0019190019001919ULL, 0x0087870087008787ULL, 0x004e4e004e004e4eULL, 0x000b0b000b000b0bULL, 0x00a9a900a900a9a9ULL, 0x000c0c000c000c0cULL, 0x0079790079007979ULL, 0x0011110011001111ULL, 0x007f7f007f007f7fULL, 0x0022220022002222ULL, 0x00e7e700e700e7e7ULL, 0x0059590059005959ULL, 0x00e1e100e100e1e1ULL, 0x00dada00da00dadaULL, 0x003d3d003d003d3dULL, 0x00c8c800c800c8c8ULL, 0x0012120012001212ULL, 0x0004040004000404ULL, 0x0074740074007474ULL, 0x0054540054005454ULL, 0x0030300030003030ULL, 0x007e7e007e007e7eULL, 0x00b4b400b400b4b4ULL, 0x0028280028002828ULL, 0x0055550055005555ULL, 0x0068680068006868ULL, 0x0050500050005050ULL, 0x00bebe00be00bebeULL, 0x00d0d000d000d0d0ULL, 0x00c4c400c400c4c4ULL, 0x0031310031003131ULL, 0x00cbcb00cb00cbcbULL, 0x002a2a002a002a2aULL, 0x00adad00ad00adadULL, 0x000f0f000f000f0fULL, 0x00caca00ca00cacaULL, 0x0070700070007070ULL, 0x00ffff00ff00ffffULL, 0x0032320032003232ULL, 0x0069690069006969ULL, 0x0008080008000808ULL, 0x0062620062006262ULL, 0x0000000000000000ULL, 0x0024240024002424ULL, 0x00d1d100d100d1d1ULL, 0x00fbfb00fb00fbfbULL, 0x00baba00ba00babaULL, 0x00eded00ed00ededULL, 0x0045450045004545ULL, 0x0081810081008181ULL, 0x0073730073007373ULL, 0x006d6d006d006d6dULL, 0x0084840084008484ULL, 0x009f9f009f009f9fULL, 0x00eeee00ee00eeeeULL, 0x004a4a004a004a4aULL, 0x00c3c300c300c3c3ULL, 0x002e2e002e002e2eULL, 0x00c1c100c100c1c1ULL, 0x0001010001000101ULL, 0x00e6e600e600e6e6ULL, 0x0025250025002525ULL, 0x0048480048004848ULL, 0x0099990099009999ULL, 0x00b9b900b900b9b9ULL, 0x00b3b300b300b3b3ULL, 0x007b7b007b007b7bULL, 0x00f9f900f900f9f9ULL, 0x00cece00ce00ceceULL, 0x00bfbf00bf00bfbfULL, 0x00dfdf00df00dfdfULL, 0x0071710071007171ULL, 0x0029290029002929ULL, 0x00cdcd00cd00cdcdULL, 0x006c6c006c006c6cULL, 0x0013130013001313ULL, 0x0064640064006464ULL, 0x009b9b009b009b9bULL, 0x0063630063006363ULL, 0x009d9d009d009d9dULL, 0x00c0c000c000c0c0ULL, 0x004b4b004b004b4bULL, 0x00b7b700b700b7b7ULL, 0x00a5a500a500a5a5ULL, 0x0089890089008989ULL, 0x005f5f005f005f5fULL, 0x00b1b100b100b1b1ULL, 0x0017170017001717ULL, 0x00f4f400f400f4f4ULL, 0x00bcbc00bc00bcbcULL, 0x00d3d300d300d3d3ULL, 0x0046460046004646ULL, 0x00cfcf00cf00cfcfULL, 0x0037370037003737ULL, 0x005e5e005e005e5eULL, 0x0047470047004747ULL, 0x0094940094009494ULL, 0x00fafa00fa00fafaULL, 0x00fcfc00fc00fcfcULL, 0x005b5b005b005b5bULL, 0x0097970097009797ULL, 0x00fefe00fe00fefeULL, 0x005a5a005a005a5aULL, 0x00acac00ac00acacULL, 0x003c3c003c003c3cULL, 0x004c4c004c004c4cULL, 0x0003030003000303ULL, 0x0035350035003535ULL, 0x00f3f300f300f3f3ULL, 0x0023230023002323ULL, 0x00b8b800b800b8b8ULL, 0x005d5d005d005d5dULL, 0x006a6a006a006a6aULL, 0x0092920092009292ULL, 0x00d5d500d500d5d5ULL, 0x0021210021002121ULL, 0x0044440044004444ULL, 0x0051510051005151ULL, 0x00c6c600c600c6c6ULL, 0x007d7d007d007d7dULL, 0x0039390039003939ULL, 0x0083830083008383ULL, 0x00dcdc00dc00dcdcULL, 0x00aaaa00aa00aaaaULL, 0x007c7c007c007c7cULL, 0x0077770077007777ULL, 0x0056560056005656ULL, 0x0005050005000505ULL, 0x001b1b001b001b1bULL, 0x00a4a400a400a4a4ULL, 0x0015150015001515ULL, 0x0034340034003434ULL, 0x001e1e001e001e1eULL, 0x001c1c001c001c1cULL, 0x00f8f800f800f8f8ULL, 0x0052520052005252ULL, 0x0020200020002020ULL, 0x0014140014001414ULL, 0x00e9e900e900e9e9ULL, 0x00bdbd00bd00bdbdULL, 0x00dddd00dd00ddddULL, 0x00e4e400e400e4e4ULL, 0x00a1a100a100a1a1ULL, 0x00e0e000e000e0e0ULL, 0x008a8a008a008a8aULL, 0x00f1f100f100f1f1ULL, 0x00d6d600d600d6d6ULL, 0x007a7a007a007a7aULL, 0x00bbbb00bb00bbbbULL, 0x00e3e300e300e3e3ULL, 0x0040400040004040ULL, 0x004f4f004f004f4fULL, }; __visible const u64 camellia_sp00444404[256] = { 0x0000707070700070ULL, 0x00002c2c2c2c002cULL, 0x0000b3b3b3b300b3ULL, 0x0000c0c0c0c000c0ULL, 0x0000e4e4e4e400e4ULL, 0x0000575757570057ULL, 0x0000eaeaeaea00eaULL, 0x0000aeaeaeae00aeULL, 0x0000232323230023ULL, 0x00006b6b6b6b006bULL, 0x0000454545450045ULL, 0x0000a5a5a5a500a5ULL, 0x0000edededed00edULL, 0x00004f4f4f4f004fULL, 0x00001d1d1d1d001dULL, 0x0000929292920092ULL, 0x0000868686860086ULL, 0x0000afafafaf00afULL, 0x00007c7c7c7c007cULL, 0x00001f1f1f1f001fULL, 0x00003e3e3e3e003eULL, 0x0000dcdcdcdc00dcULL, 0x00005e5e5e5e005eULL, 0x00000b0b0b0b000bULL, 0x0000a6a6a6a600a6ULL, 0x0000393939390039ULL, 0x0000d5d5d5d500d5ULL, 0x00005d5d5d5d005dULL, 0x0000d9d9d9d900d9ULL, 0x00005a5a5a5a005aULL, 0x0000515151510051ULL, 0x00006c6c6c6c006cULL, 0x00008b8b8b8b008bULL, 0x00009a9a9a9a009aULL, 0x0000fbfbfbfb00fbULL, 0x0000b0b0b0b000b0ULL, 0x0000747474740074ULL, 0x00002b2b2b2b002bULL, 0x0000f0f0f0f000f0ULL, 0x0000848484840084ULL, 0x0000dfdfdfdf00dfULL, 0x0000cbcbcbcb00cbULL, 0x0000343434340034ULL, 0x0000767676760076ULL, 0x00006d6d6d6d006dULL, 0x0000a9a9a9a900a9ULL, 0x0000d1d1d1d100d1ULL, 0x0000040404040004ULL, 0x0000141414140014ULL, 0x00003a3a3a3a003aULL, 0x0000dededede00deULL, 0x0000111111110011ULL, 0x0000323232320032ULL, 0x00009c9c9c9c009cULL, 0x0000535353530053ULL, 0x0000f2f2f2f200f2ULL, 0x0000fefefefe00feULL, 0x0000cfcfcfcf00cfULL, 0x0000c3c3c3c300c3ULL, 0x00007a7a7a7a007aULL, 0x0000242424240024ULL, 0x0000e8e8e8e800e8ULL, 0x0000606060600060ULL, 0x0000696969690069ULL, 0x0000aaaaaaaa00aaULL, 0x0000a0a0a0a000a0ULL, 0x0000a1a1a1a100a1ULL, 0x0000626262620062ULL, 0x0000545454540054ULL, 0x00001e1e1e1e001eULL, 0x0000e0e0e0e000e0ULL, 0x0000646464640064ULL, 0x0000101010100010ULL, 0x0000000000000000ULL, 0x0000a3a3a3a300a3ULL, 0x0000757575750075ULL, 0x00008a8a8a8a008aULL, 0x0000e6e6e6e600e6ULL, 0x0000090909090009ULL, 0x0000dddddddd00ddULL, 0x0000878787870087ULL, 0x0000838383830083ULL, 0x0000cdcdcdcd00cdULL, 0x0000909090900090ULL, 0x0000737373730073ULL, 0x0000f6f6f6f600f6ULL, 0x00009d9d9d9d009dULL, 0x0000bfbfbfbf00bfULL, 0x0000525252520052ULL, 0x0000d8d8d8d800d8ULL, 0x0000c8c8c8c800c8ULL, 0x0000c6c6c6c600c6ULL, 0x0000818181810081ULL, 0x00006f6f6f6f006fULL, 0x0000131313130013ULL, 0x0000636363630063ULL, 0x0000e9e9e9e900e9ULL, 0x0000a7a7a7a700a7ULL, 0x00009f9f9f9f009fULL, 0x0000bcbcbcbc00bcULL, 0x0000292929290029ULL, 0x0000f9f9f9f900f9ULL, 0x00002f2f2f2f002fULL, 0x0000b4b4b4b400b4ULL, 0x0000787878780078ULL, 0x0000060606060006ULL, 0x0000e7e7e7e700e7ULL, 0x0000717171710071ULL, 0x0000d4d4d4d400d4ULL, 0x0000abababab00abULL, 0x0000888888880088ULL, 0x00008d8d8d8d008dULL, 0x0000727272720072ULL, 0x0000b9b9b9b900b9ULL, 0x0000f8f8f8f800f8ULL, 0x0000acacacac00acULL, 0x0000363636360036ULL, 0x00002a2a2a2a002aULL, 0x00003c3c3c3c003cULL, 0x0000f1f1f1f100f1ULL, 0x0000404040400040ULL, 0x0000d3d3d3d300d3ULL, 0x0000bbbbbbbb00bbULL, 0x0000434343430043ULL, 0x0000151515150015ULL, 0x0000adadadad00adULL, 0x0000777777770077ULL, 0x0000808080800080ULL, 0x0000828282820082ULL, 0x0000ecececec00ecULL, 0x0000272727270027ULL, 0x0000e5e5e5e500e5ULL, 0x0000858585850085ULL, 0x0000353535350035ULL, 0x00000c0c0c0c000cULL, 0x0000414141410041ULL, 0x0000efefefef00efULL, 0x0000939393930093ULL, 0x0000191919190019ULL, 0x0000212121210021ULL, 0x00000e0e0e0e000eULL, 0x00004e4e4e4e004eULL, 0x0000656565650065ULL, 0x0000bdbdbdbd00bdULL, 0x0000b8b8b8b800b8ULL, 0x00008f8f8f8f008fULL, 0x0000ebebebeb00ebULL, 0x0000cececece00ceULL, 0x0000303030300030ULL, 0x00005f5f5f5f005fULL, 0x0000c5c5c5c500c5ULL, 0x00001a1a1a1a001aULL, 0x0000e1e1e1e100e1ULL, 0x0000cacacaca00caULL, 0x0000474747470047ULL, 0x00003d3d3d3d003dULL, 0x0000010101010001ULL, 0x0000d6d6d6d600d6ULL, 0x0000565656560056ULL, 0x00004d4d4d4d004dULL, 0x00000d0d0d0d000dULL, 0x0000666666660066ULL, 0x0000cccccccc00ccULL, 0x00002d2d2d2d002dULL, 0x0000121212120012ULL, 0x0000202020200020ULL, 0x0000b1b1b1b100b1ULL, 0x0000999999990099ULL, 0x00004c4c4c4c004cULL, 0x0000c2c2c2c200c2ULL, 0x00007e7e7e7e007eULL, 0x0000050505050005ULL, 0x0000b7b7b7b700b7ULL, 0x0000313131310031ULL, 0x0000171717170017ULL, 0x0000d7d7d7d700d7ULL, 0x0000585858580058ULL, 0x0000616161610061ULL, 0x00001b1b1b1b001bULL, 0x00001c1c1c1c001cULL, 0x00000f0f0f0f000fULL, 0x0000161616160016ULL, 0x0000181818180018ULL, 0x0000222222220022ULL, 0x0000444444440044ULL, 0x0000b2b2b2b200b2ULL, 0x0000b5b5b5b500b5ULL, 0x0000919191910091ULL, 0x0000080808080008ULL, 0x0000a8a8a8a800a8ULL, 0x0000fcfcfcfc00fcULL, 0x0000505050500050ULL, 0x0000d0d0d0d000d0ULL, 0x00007d7d7d7d007dULL, 0x0000898989890089ULL, 0x0000979797970097ULL, 0x00005b5b5b5b005bULL, 0x0000959595950095ULL, 0x0000ffffffff00ffULL, 0x0000d2d2d2d200d2ULL, 0x0000c4c4c4c400c4ULL, 0x0000484848480048ULL, 0x0000f7f7f7f700f7ULL, 0x0000dbdbdbdb00dbULL, 0x0000030303030003ULL, 0x0000dadadada00daULL, 0x00003f3f3f3f003fULL, 0x0000949494940094ULL, 0x00005c5c5c5c005cULL, 0x0000020202020002ULL, 0x00004a4a4a4a004aULL, 0x0000333333330033ULL, 0x0000676767670067ULL, 0x0000f3f3f3f300f3ULL, 0x00007f7f7f7f007fULL, 0x0000e2e2e2e200e2ULL, 0x00009b9b9b9b009bULL, 0x0000262626260026ULL, 0x0000373737370037ULL, 0x00003b3b3b3b003bULL, 0x0000969696960096ULL, 0x00004b4b4b4b004bULL, 0x0000bebebebe00beULL, 0x00002e2e2e2e002eULL, 0x0000797979790079ULL, 0x00008c8c8c8c008cULL, 0x00006e6e6e6e006eULL, 0x00008e8e8e8e008eULL, 0x0000f5f5f5f500f5ULL, 0x0000b6b6b6b600b6ULL, 0x0000fdfdfdfd00fdULL, 0x0000595959590059ULL, 0x0000989898980098ULL, 0x00006a6a6a6a006aULL, 0x0000464646460046ULL, 0x0000babababa00baULL, 0x0000252525250025ULL, 0x0000424242420042ULL, 0x0000a2a2a2a200a2ULL, 0x0000fafafafa00faULL, 0x0000070707070007ULL, 0x0000555555550055ULL, 0x0000eeeeeeee00eeULL, 0x00000a0a0a0a000aULL, 0x0000494949490049ULL, 0x0000686868680068ULL, 0x0000383838380038ULL, 0x0000a4a4a4a400a4ULL, 0x0000282828280028ULL, 0x00007b7b7b7b007bULL, 0x0000c9c9c9c900c9ULL, 0x0000c1c1c1c100c1ULL, 0x0000e3e3e3e300e3ULL, 0x0000f4f4f4f400f4ULL, 0x0000c7c7c7c700c7ULL, 0x00009e9e9e9e009eULL, }; __visible const u64 camellia_sp02220222[256] = { 0x00e0e0e000e0e0e0ULL, 0x0005050500050505ULL, 0x0058585800585858ULL, 0x00d9d9d900d9d9d9ULL, 0x0067676700676767ULL, 0x004e4e4e004e4e4eULL, 0x0081818100818181ULL, 0x00cbcbcb00cbcbcbULL, 0x00c9c9c900c9c9c9ULL, 0x000b0b0b000b0b0bULL, 0x00aeaeae00aeaeaeULL, 0x006a6a6a006a6a6aULL, 0x00d5d5d500d5d5d5ULL, 0x0018181800181818ULL, 0x005d5d5d005d5d5dULL, 0x0082828200828282ULL, 0x0046464600464646ULL, 0x00dfdfdf00dfdfdfULL, 0x00d6d6d600d6d6d6ULL, 0x0027272700272727ULL, 0x008a8a8a008a8a8aULL, 0x0032323200323232ULL, 0x004b4b4b004b4b4bULL, 0x0042424200424242ULL, 0x00dbdbdb00dbdbdbULL, 0x001c1c1c001c1c1cULL, 0x009e9e9e009e9e9eULL, 0x009c9c9c009c9c9cULL, 0x003a3a3a003a3a3aULL, 0x00cacaca00cacacaULL, 0x0025252500252525ULL, 0x007b7b7b007b7b7bULL, 0x000d0d0d000d0d0dULL, 0x0071717100717171ULL, 0x005f5f5f005f5f5fULL, 0x001f1f1f001f1f1fULL, 0x00f8f8f800f8f8f8ULL, 0x00d7d7d700d7d7d7ULL, 0x003e3e3e003e3e3eULL, 0x009d9d9d009d9d9dULL, 0x007c7c7c007c7c7cULL, 0x0060606000606060ULL, 0x00b9b9b900b9b9b9ULL, 0x00bebebe00bebebeULL, 0x00bcbcbc00bcbcbcULL, 0x008b8b8b008b8b8bULL, 0x0016161600161616ULL, 0x0034343400343434ULL, 0x004d4d4d004d4d4dULL, 0x00c3c3c300c3c3c3ULL, 0x0072727200727272ULL, 0x0095959500959595ULL, 0x00ababab00abababULL, 0x008e8e8e008e8e8eULL, 0x00bababa00bababaULL, 0x007a7a7a007a7a7aULL, 0x00b3b3b300b3b3b3ULL, 0x0002020200020202ULL, 0x00b4b4b400b4b4b4ULL, 0x00adadad00adadadULL, 0x00a2a2a200a2a2a2ULL, 0x00acacac00acacacULL, 0x00d8d8d800d8d8d8ULL, 0x009a9a9a009a9a9aULL, 0x0017171700171717ULL, 0x001a1a1a001a1a1aULL, 0x0035353500353535ULL, 0x00cccccc00ccccccULL, 0x00f7f7f700f7f7f7ULL, 0x0099999900999999ULL, 0x0061616100616161ULL, 0x005a5a5a005a5a5aULL, 0x00e8e8e800e8e8e8ULL, 0x0024242400242424ULL, 0x0056565600565656ULL, 0x0040404000404040ULL, 0x00e1e1e100e1e1e1ULL, 0x0063636300636363ULL, 0x0009090900090909ULL, 0x0033333300333333ULL, 0x00bfbfbf00bfbfbfULL, 0x0098989800989898ULL, 0x0097979700979797ULL, 0x0085858500858585ULL, 0x0068686800686868ULL, 0x00fcfcfc00fcfcfcULL, 0x00ececec00ecececULL, 0x000a0a0a000a0a0aULL, 0x00dadada00dadadaULL, 0x006f6f6f006f6f6fULL, 0x0053535300535353ULL, 0x0062626200626262ULL, 0x00a3a3a300a3a3a3ULL, 0x002e2e2e002e2e2eULL, 0x0008080800080808ULL, 0x00afafaf00afafafULL, 0x0028282800282828ULL, 0x00b0b0b000b0b0b0ULL, 0x0074747400747474ULL, 0x00c2c2c200c2c2c2ULL, 0x00bdbdbd00bdbdbdULL, 0x0036363600363636ULL, 0x0022222200222222ULL, 0x0038383800383838ULL, 0x0064646400646464ULL, 0x001e1e1e001e1e1eULL, 0x0039393900393939ULL, 0x002c2c2c002c2c2cULL, 0x00a6a6a600a6a6a6ULL, 0x0030303000303030ULL, 0x00e5e5e500e5e5e5ULL, 0x0044444400444444ULL, 0x00fdfdfd00fdfdfdULL, 0x0088888800888888ULL, 0x009f9f9f009f9f9fULL, 0x0065656500656565ULL, 0x0087878700878787ULL, 0x006b6b6b006b6b6bULL, 0x00f4f4f400f4f4f4ULL, 0x0023232300232323ULL, 0x0048484800484848ULL, 0x0010101000101010ULL, 0x00d1d1d100d1d1d1ULL, 0x0051515100515151ULL, 0x00c0c0c000c0c0c0ULL, 0x00f9f9f900f9f9f9ULL, 0x00d2d2d200d2d2d2ULL, 0x00a0a0a000a0a0a0ULL, 0x0055555500555555ULL, 0x00a1a1a100a1a1a1ULL, 0x0041414100414141ULL, 0x00fafafa00fafafaULL, 0x0043434300434343ULL, 0x0013131300131313ULL, 0x00c4c4c400c4c4c4ULL, 0x002f2f2f002f2f2fULL, 0x00a8a8a800a8a8a8ULL, 0x00b6b6b600b6b6b6ULL, 0x003c3c3c003c3c3cULL, 0x002b2b2b002b2b2bULL, 0x00c1c1c100c1c1c1ULL, 0x00ffffff00ffffffULL, 0x00c8c8c800c8c8c8ULL, 0x00a5a5a500a5a5a5ULL, 0x0020202000202020ULL, 0x0089898900898989ULL, 0x0000000000000000ULL, 0x0090909000909090ULL, 0x0047474700474747ULL, 0x00efefef00efefefULL, 0x00eaeaea00eaeaeaULL, 0x00b7b7b700b7b7b7ULL, 0x0015151500151515ULL, 0x0006060600060606ULL, 0x00cdcdcd00cdcdcdULL, 0x00b5b5b500b5b5b5ULL, 0x0012121200121212ULL, 0x007e7e7e007e7e7eULL, 0x00bbbbbb00bbbbbbULL, 0x0029292900292929ULL, 0x000f0f0f000f0f0fULL, 0x00b8b8b800b8b8b8ULL, 0x0007070700070707ULL, 0x0004040400040404ULL, 0x009b9b9b009b9b9bULL, 0x0094949400949494ULL, 0x0021212100212121ULL, 0x0066666600666666ULL, 0x00e6e6e600e6e6e6ULL, 0x00cecece00cececeULL, 0x00ededed00edededULL, 0x00e7e7e700e7e7e7ULL, 0x003b3b3b003b3b3bULL, 0x00fefefe00fefefeULL, 0x007f7f7f007f7f7fULL, 0x00c5c5c500c5c5c5ULL, 0x00a4a4a400a4a4a4ULL, 0x0037373700373737ULL, 0x00b1b1b100b1b1b1ULL, 0x004c4c4c004c4c4cULL, 0x0091919100919191ULL, 0x006e6e6e006e6e6eULL, 0x008d8d8d008d8d8dULL, 0x0076767600767676ULL, 0x0003030300030303ULL, 0x002d2d2d002d2d2dULL, 0x00dedede00dededeULL, 0x0096969600969696ULL, 0x0026262600262626ULL, 0x007d7d7d007d7d7dULL, 0x00c6c6c600c6c6c6ULL, 0x005c5c5c005c5c5cULL, 0x00d3d3d300d3d3d3ULL, 0x00f2f2f200f2f2f2ULL, 0x004f4f4f004f4f4fULL, 0x0019191900191919ULL, 0x003f3f3f003f3f3fULL, 0x00dcdcdc00dcdcdcULL, 0x0079797900797979ULL, 0x001d1d1d001d1d1dULL, 0x0052525200525252ULL, 0x00ebebeb00ebebebULL, 0x00f3f3f300f3f3f3ULL, 0x006d6d6d006d6d6dULL, 0x005e5e5e005e5e5eULL, 0x00fbfbfb00fbfbfbULL, 0x0069696900696969ULL, 0x00b2b2b200b2b2b2ULL, 0x00f0f0f000f0f0f0ULL, 0x0031313100313131ULL, 0x000c0c0c000c0c0cULL, 0x00d4d4d400d4d4d4ULL, 0x00cfcfcf00cfcfcfULL, 0x008c8c8c008c8c8cULL, 0x00e2e2e200e2e2e2ULL, 0x0075757500757575ULL, 0x00a9a9a900a9a9a9ULL, 0x004a4a4a004a4a4aULL, 0x0057575700575757ULL, 0x0084848400848484ULL, 0x0011111100111111ULL, 0x0045454500454545ULL, 0x001b1b1b001b1b1bULL, 0x00f5f5f500f5f5f5ULL, 0x00e4e4e400e4e4e4ULL, 0x000e0e0e000e0e0eULL, 0x0073737300737373ULL, 0x00aaaaaa00aaaaaaULL, 0x00f1f1f100f1f1f1ULL, 0x00dddddd00ddddddULL, 0x0059595900595959ULL, 0x0014141400141414ULL, 0x006c6c6c006c6c6cULL, 0x0092929200929292ULL, 0x0054545400545454ULL, 0x00d0d0d000d0d0d0ULL, 0x0078787800787878ULL, 0x0070707000707070ULL, 0x00e3e3e300e3e3e3ULL, 0x0049494900494949ULL, 0x0080808000808080ULL, 0x0050505000505050ULL, 0x00a7a7a700a7a7a7ULL, 0x00f6f6f600f6f6f6ULL, 0x0077777700777777ULL, 0x0093939300939393ULL, 0x0086868600868686ULL, 0x0083838300838383ULL, 0x002a2a2a002a2a2aULL, 0x00c7c7c700c7c7c7ULL, 0x005b5b5b005b5b5bULL, 0x00e9e9e900e9e9e9ULL, 0x00eeeeee00eeeeeeULL, 0x008f8f8f008f8f8fULL, 0x0001010100010101ULL, 0x003d3d3d003d3d3dULL, }; __visible const u64 camellia_sp30333033[256] = { 0x3800383838003838ULL, 0x4100414141004141ULL, 0x1600161616001616ULL, 0x7600767676007676ULL, 0xd900d9d9d900d9d9ULL, 0x9300939393009393ULL, 0x6000606060006060ULL, 0xf200f2f2f200f2f2ULL, 0x7200727272007272ULL, 0xc200c2c2c200c2c2ULL, 0xab00ababab00ababULL, 0x9a009a9a9a009a9aULL, 0x7500757575007575ULL, 0x0600060606000606ULL, 0x5700575757005757ULL, 0xa000a0a0a000a0a0ULL, 0x9100919191009191ULL, 0xf700f7f7f700f7f7ULL, 0xb500b5b5b500b5b5ULL, 0xc900c9c9c900c9c9ULL, 0xa200a2a2a200a2a2ULL, 0x8c008c8c8c008c8cULL, 0xd200d2d2d200d2d2ULL, 0x9000909090009090ULL, 0xf600f6f6f600f6f6ULL, 0x0700070707000707ULL, 0xa700a7a7a700a7a7ULL, 0x2700272727002727ULL, 0x8e008e8e8e008e8eULL, 0xb200b2b2b200b2b2ULL, 0x4900494949004949ULL, 0xde00dedede00dedeULL, 0x4300434343004343ULL, 0x5c005c5c5c005c5cULL, 0xd700d7d7d700d7d7ULL, 0xc700c7c7c700c7c7ULL, 0x3e003e3e3e003e3eULL, 0xf500f5f5f500f5f5ULL, 0x8f008f8f8f008f8fULL, 0x6700676767006767ULL, 0x1f001f1f1f001f1fULL, 0x1800181818001818ULL, 0x6e006e6e6e006e6eULL, 0xaf00afafaf00afafULL, 0x2f002f2f2f002f2fULL, 0xe200e2e2e200e2e2ULL, 0x8500858585008585ULL, 0x0d000d0d0d000d0dULL, 0x5300535353005353ULL, 0xf000f0f0f000f0f0ULL, 0x9c009c9c9c009c9cULL, 0x6500656565006565ULL, 0xea00eaeaea00eaeaULL, 0xa300a3a3a300a3a3ULL, 0xae00aeaeae00aeaeULL, 0x9e009e9e9e009e9eULL, 0xec00ececec00ececULL, 0x8000808080008080ULL, 0x2d002d2d2d002d2dULL, 0x6b006b6b6b006b6bULL, 0xa800a8a8a800a8a8ULL, 0x2b002b2b2b002b2bULL, 0x3600363636003636ULL, 0xa600a6a6a600a6a6ULL, 0xc500c5c5c500c5c5ULL, 0x8600868686008686ULL, 0x4d004d4d4d004d4dULL, 0x3300333333003333ULL, 0xfd00fdfdfd00fdfdULL, 0x6600666666006666ULL, 0x5800585858005858ULL, 0x9600969696009696ULL, 0x3a003a3a3a003a3aULL, 0x0900090909000909ULL, 0x9500959595009595ULL, 0x1000101010001010ULL, 0x7800787878007878ULL, 0xd800d8d8d800d8d8ULL, 0x4200424242004242ULL, 0xcc00cccccc00ccccULL, 0xef00efefef00efefULL, 0x2600262626002626ULL, 0xe500e5e5e500e5e5ULL, 0x6100616161006161ULL, 0x1a001a1a1a001a1aULL, 0x3f003f3f3f003f3fULL, 0x3b003b3b3b003b3bULL, 0x8200828282008282ULL, 0xb600b6b6b600b6b6ULL, 0xdb00dbdbdb00dbdbULL, 0xd400d4d4d400d4d4ULL, 0x9800989898009898ULL, 0xe800e8e8e800e8e8ULL, 0x8b008b8b8b008b8bULL, 0x0200020202000202ULL, 0xeb00ebebeb00ebebULL, 0x0a000a0a0a000a0aULL, 0x2c002c2c2c002c2cULL, 0x1d001d1d1d001d1dULL, 0xb000b0b0b000b0b0ULL, 0x6f006f6f6f006f6fULL, 0x8d008d8d8d008d8dULL, 0x8800888888008888ULL, 0x0e000e0e0e000e0eULL, 0x1900191919001919ULL, 0x8700878787008787ULL, 0x4e004e4e4e004e4eULL, 0x0b000b0b0b000b0bULL, 0xa900a9a9a900a9a9ULL, 0x0c000c0c0c000c0cULL, 0x7900797979007979ULL, 0x1100111111001111ULL, 0x7f007f7f7f007f7fULL, 0x2200222222002222ULL, 0xe700e7e7e700e7e7ULL, 0x5900595959005959ULL, 0xe100e1e1e100e1e1ULL, 0xda00dadada00dadaULL, 0x3d003d3d3d003d3dULL, 0xc800c8c8c800c8c8ULL, 0x1200121212001212ULL, 0x0400040404000404ULL, 0x7400747474007474ULL, 0x5400545454005454ULL, 0x3000303030003030ULL, 0x7e007e7e7e007e7eULL, 0xb400b4b4b400b4b4ULL, 0x2800282828002828ULL, 0x5500555555005555ULL, 0x6800686868006868ULL, 0x5000505050005050ULL, 0xbe00bebebe00bebeULL, 0xd000d0d0d000d0d0ULL, 0xc400c4c4c400c4c4ULL, 0x3100313131003131ULL, 0xcb00cbcbcb00cbcbULL, 0x2a002a2a2a002a2aULL, 0xad00adadad00adadULL, 0x0f000f0f0f000f0fULL, 0xca00cacaca00cacaULL, 0x7000707070007070ULL, 0xff00ffffff00ffffULL, 0x3200323232003232ULL, 0x6900696969006969ULL, 0x0800080808000808ULL, 0x6200626262006262ULL, 0x0000000000000000ULL, 0x2400242424002424ULL, 0xd100d1d1d100d1d1ULL, 0xfb00fbfbfb00fbfbULL, 0xba00bababa00babaULL, 0xed00ededed00ededULL, 0x4500454545004545ULL, 0x8100818181008181ULL, 0x7300737373007373ULL, 0x6d006d6d6d006d6dULL, 0x8400848484008484ULL, 0x9f009f9f9f009f9fULL, 0xee00eeeeee00eeeeULL, 0x4a004a4a4a004a4aULL, 0xc300c3c3c300c3c3ULL, 0x2e002e2e2e002e2eULL, 0xc100c1c1c100c1c1ULL, 0x0100010101000101ULL, 0xe600e6e6e600e6e6ULL, 0x2500252525002525ULL, 0x4800484848004848ULL, 0x9900999999009999ULL, 0xb900b9b9b900b9b9ULL, 0xb300b3b3b300b3b3ULL, 0x7b007b7b7b007b7bULL, 0xf900f9f9f900f9f9ULL, 0xce00cecece00ceceULL, 0xbf00bfbfbf00bfbfULL, 0xdf00dfdfdf00dfdfULL, 0x7100717171007171ULL, 0x2900292929002929ULL, 0xcd00cdcdcd00cdcdULL, 0x6c006c6c6c006c6cULL, 0x1300131313001313ULL, 0x6400646464006464ULL, 0x9b009b9b9b009b9bULL, 0x6300636363006363ULL, 0x9d009d9d9d009d9dULL, 0xc000c0c0c000c0c0ULL, 0x4b004b4b4b004b4bULL, 0xb700b7b7b700b7b7ULL, 0xa500a5a5a500a5a5ULL, 0x8900898989008989ULL, 0x5f005f5f5f005f5fULL, 0xb100b1b1b100b1b1ULL, 0x1700171717001717ULL, 0xf400f4f4f400f4f4ULL, 0xbc00bcbcbc00bcbcULL, 0xd300d3d3d300d3d3ULL, 0x4600464646004646ULL, 0xcf00cfcfcf00cfcfULL, 0x3700373737003737ULL, 0x5e005e5e5e005e5eULL, 0x4700474747004747ULL, 0x9400949494009494ULL, 0xfa00fafafa00fafaULL, 0xfc00fcfcfc00fcfcULL, 0x5b005b5b5b005b5bULL, 0x9700979797009797ULL, 0xfe00fefefe00fefeULL, 0x5a005a5a5a005a5aULL, 0xac00acacac00acacULL, 0x3c003c3c3c003c3cULL, 0x4c004c4c4c004c4cULL, 0x0300030303000303ULL, 0x3500353535003535ULL, 0xf300f3f3f300f3f3ULL, 0x2300232323002323ULL, 0xb800b8b8b800b8b8ULL, 0x5d005d5d5d005d5dULL, 0x6a006a6a6a006a6aULL, 0x9200929292009292ULL, 0xd500d5d5d500d5d5ULL, 0x2100212121002121ULL, 0x4400444444004444ULL, 0x5100515151005151ULL, 0xc600c6c6c600c6c6ULL, 0x7d007d7d7d007d7dULL, 0x3900393939003939ULL, 0x8300838383008383ULL, 0xdc00dcdcdc00dcdcULL, 0xaa00aaaaaa00aaaaULL, 0x7c007c7c7c007c7cULL, 0x7700777777007777ULL, 0x5600565656005656ULL, 0x0500050505000505ULL, 0x1b001b1b1b001b1bULL, 0xa400a4a4a400a4a4ULL, 0x1500151515001515ULL, 0x3400343434003434ULL, 0x1e001e1e1e001e1eULL, 0x1c001c1c1c001c1cULL, 0xf800f8f8f800f8f8ULL, 0x5200525252005252ULL, 0x2000202020002020ULL, 0x1400141414001414ULL, 0xe900e9e9e900e9e9ULL, 0xbd00bdbdbd00bdbdULL, 0xdd00dddddd00ddddULL, 0xe400e4e4e400e4e4ULL, 0xa100a1a1a100a1a1ULL, 0xe000e0e0e000e0e0ULL, 0x8a008a8a8a008a8aULL, 0xf100f1f1f100f1f1ULL, 0xd600d6d6d600d6d6ULL, 0x7a007a7a7a007a7aULL, 0xbb00bbbbbb00bbbbULL, 0xe300e3e3e300e3e3ULL, 0x4000404040004040ULL, 0x4f004f4f4f004f4fULL, }; __visible const u64 camellia_sp44044404[256] = { 0x7070007070700070ULL, 0x2c2c002c2c2c002cULL, 0xb3b300b3b3b300b3ULL, 0xc0c000c0c0c000c0ULL, 0xe4e400e4e4e400e4ULL, 0x5757005757570057ULL, 0xeaea00eaeaea00eaULL, 0xaeae00aeaeae00aeULL, 0x2323002323230023ULL, 0x6b6b006b6b6b006bULL, 0x4545004545450045ULL, 0xa5a500a5a5a500a5ULL, 0xeded00ededed00edULL, 0x4f4f004f4f4f004fULL, 0x1d1d001d1d1d001dULL, 0x9292009292920092ULL, 0x8686008686860086ULL, 0xafaf00afafaf00afULL, 0x7c7c007c7c7c007cULL, 0x1f1f001f1f1f001fULL, 0x3e3e003e3e3e003eULL, 0xdcdc00dcdcdc00dcULL, 0x5e5e005e5e5e005eULL, 0x0b0b000b0b0b000bULL, 0xa6a600a6a6a600a6ULL, 0x3939003939390039ULL, 0xd5d500d5d5d500d5ULL, 0x5d5d005d5d5d005dULL, 0xd9d900d9d9d900d9ULL, 0x5a5a005a5a5a005aULL, 0x5151005151510051ULL, 0x6c6c006c6c6c006cULL, 0x8b8b008b8b8b008bULL, 0x9a9a009a9a9a009aULL, 0xfbfb00fbfbfb00fbULL, 0xb0b000b0b0b000b0ULL, 0x7474007474740074ULL, 0x2b2b002b2b2b002bULL, 0xf0f000f0f0f000f0ULL, 0x8484008484840084ULL, 0xdfdf00dfdfdf00dfULL, 0xcbcb00cbcbcb00cbULL, 0x3434003434340034ULL, 0x7676007676760076ULL, 0x6d6d006d6d6d006dULL, 0xa9a900a9a9a900a9ULL, 0xd1d100d1d1d100d1ULL, 0x0404000404040004ULL, 0x1414001414140014ULL, 0x3a3a003a3a3a003aULL, 0xdede00dedede00deULL, 0x1111001111110011ULL, 0x3232003232320032ULL, 0x9c9c009c9c9c009cULL, 0x5353005353530053ULL, 0xf2f200f2f2f200f2ULL, 0xfefe00fefefe00feULL, 0xcfcf00cfcfcf00cfULL, 0xc3c300c3c3c300c3ULL, 0x7a7a007a7a7a007aULL, 0x2424002424240024ULL, 0xe8e800e8e8e800e8ULL, 0x6060006060600060ULL, 0x6969006969690069ULL, 0xaaaa00aaaaaa00aaULL, 0xa0a000a0a0a000a0ULL, 0xa1a100a1a1a100a1ULL, 0x6262006262620062ULL, 0x5454005454540054ULL, 0x1e1e001e1e1e001eULL, 0xe0e000e0e0e000e0ULL, 0x6464006464640064ULL, 0x1010001010100010ULL, 0x0000000000000000ULL, 0xa3a300a3a3a300a3ULL, 0x7575007575750075ULL, 0x8a8a008a8a8a008aULL, 0xe6e600e6e6e600e6ULL, 0x0909000909090009ULL, 0xdddd00dddddd00ddULL, 0x8787008787870087ULL, 0x8383008383830083ULL, 0xcdcd00cdcdcd00cdULL, 0x9090009090900090ULL, 0x7373007373730073ULL, 0xf6f600f6f6f600f6ULL, 0x9d9d009d9d9d009dULL, 0xbfbf00bfbfbf00bfULL, 0x5252005252520052ULL, 0xd8d800d8d8d800d8ULL, 0xc8c800c8c8c800c8ULL, 0xc6c600c6c6c600c6ULL, 0x8181008181810081ULL, 0x6f6f006f6f6f006fULL, 0x1313001313130013ULL, 0x6363006363630063ULL, 0xe9e900e9e9e900e9ULL, 0xa7a700a7a7a700a7ULL, 0x9f9f009f9f9f009fULL, 0xbcbc00bcbcbc00bcULL, 0x2929002929290029ULL, 0xf9f900f9f9f900f9ULL, 0x2f2f002f2f2f002fULL, 0xb4b400b4b4b400b4ULL, 0x7878007878780078ULL, 0x0606000606060006ULL, 0xe7e700e7e7e700e7ULL, 0x7171007171710071ULL, 0xd4d400d4d4d400d4ULL, 0xabab00ababab00abULL, 0x8888008888880088ULL, 0x8d8d008d8d8d008dULL, 0x7272007272720072ULL, 0xb9b900b9b9b900b9ULL, 0xf8f800f8f8f800f8ULL, 0xacac00acacac00acULL, 0x3636003636360036ULL, 0x2a2a002a2a2a002aULL, 0x3c3c003c3c3c003cULL, 0xf1f100f1f1f100f1ULL, 0x4040004040400040ULL, 0xd3d300d3d3d300d3ULL, 0xbbbb00bbbbbb00bbULL, 0x4343004343430043ULL, 0x1515001515150015ULL, 0xadad00adadad00adULL, 0x7777007777770077ULL, 0x8080008080800080ULL, 0x8282008282820082ULL, 0xecec00ececec00ecULL, 0x2727002727270027ULL, 0xe5e500e5e5e500e5ULL, 0x8585008585850085ULL, 0x3535003535350035ULL, 0x0c0c000c0c0c000cULL, 0x4141004141410041ULL, 0xefef00efefef00efULL, 0x9393009393930093ULL, 0x1919001919190019ULL, 0x2121002121210021ULL, 0x0e0e000e0e0e000eULL, 0x4e4e004e4e4e004eULL, 0x6565006565650065ULL, 0xbdbd00bdbdbd00bdULL, 0xb8b800b8b8b800b8ULL, 0x8f8f008f8f8f008fULL, 0xebeb00ebebeb00ebULL, 0xcece00cecece00ceULL, 0x3030003030300030ULL, 0x5f5f005f5f5f005fULL, 0xc5c500c5c5c500c5ULL, 0x1a1a001a1a1a001aULL, 0xe1e100e1e1e100e1ULL, 0xcaca00cacaca00caULL, 0x4747004747470047ULL, 0x3d3d003d3d3d003dULL, 0x0101000101010001ULL, 0xd6d600d6d6d600d6ULL, 0x5656005656560056ULL, 0x4d4d004d4d4d004dULL, 0x0d0d000d0d0d000dULL, 0x6666006666660066ULL, 0xcccc00cccccc00ccULL, 0x2d2d002d2d2d002dULL, 0x1212001212120012ULL, 0x2020002020200020ULL, 0xb1b100b1b1b100b1ULL, 0x9999009999990099ULL, 0x4c4c004c4c4c004cULL, 0xc2c200c2c2c200c2ULL, 0x7e7e007e7e7e007eULL, 0x0505000505050005ULL, 0xb7b700b7b7b700b7ULL, 0x3131003131310031ULL, 0x1717001717170017ULL, 0xd7d700d7d7d700d7ULL, 0x5858005858580058ULL, 0x6161006161610061ULL, 0x1b1b001b1b1b001bULL, 0x1c1c001c1c1c001cULL, 0x0f0f000f0f0f000fULL, 0x1616001616160016ULL, 0x1818001818180018ULL, 0x2222002222220022ULL, 0x4444004444440044ULL, 0xb2b200b2b2b200b2ULL, 0xb5b500b5b5b500b5ULL, 0x9191009191910091ULL, 0x0808000808080008ULL, 0xa8a800a8a8a800a8ULL, 0xfcfc00fcfcfc00fcULL, 0x5050005050500050ULL, 0xd0d000d0d0d000d0ULL, 0x7d7d007d7d7d007dULL, 0x8989008989890089ULL, 0x9797009797970097ULL, 0x5b5b005b5b5b005bULL, 0x9595009595950095ULL, 0xffff00ffffff00ffULL, 0xd2d200d2d2d200d2ULL, 0xc4c400c4c4c400c4ULL, 0x4848004848480048ULL, 0xf7f700f7f7f700f7ULL, 0xdbdb00dbdbdb00dbULL, 0x0303000303030003ULL, 0xdada00dadada00daULL, 0x3f3f003f3f3f003fULL, 0x9494009494940094ULL, 0x5c5c005c5c5c005cULL, 0x0202000202020002ULL, 0x4a4a004a4a4a004aULL, 0x3333003333330033ULL, 0x6767006767670067ULL, 0xf3f300f3f3f300f3ULL, 0x7f7f007f7f7f007fULL, 0xe2e200e2e2e200e2ULL, 0x9b9b009b9b9b009bULL, 0x2626002626260026ULL, 0x3737003737370037ULL, 0x3b3b003b3b3b003bULL, 0x9696009696960096ULL, 0x4b4b004b4b4b004bULL, 0xbebe00bebebe00beULL, 0x2e2e002e2e2e002eULL, 0x7979007979790079ULL, 0x8c8c008c8c8c008cULL, 0x6e6e006e6e6e006eULL, 0x8e8e008e8e8e008eULL, 0xf5f500f5f5f500f5ULL, 0xb6b600b6b6b600b6ULL, 0xfdfd00fdfdfd00fdULL, 0x5959005959590059ULL, 0x9898009898980098ULL, 0x6a6a006a6a6a006aULL, 0x4646004646460046ULL, 0xbaba00bababa00baULL, 0x2525002525250025ULL, 0x4242004242420042ULL, 0xa2a200a2a2a200a2ULL, 0xfafa00fafafa00faULL, 0x0707000707070007ULL, 0x5555005555550055ULL, 0xeeee00eeeeee00eeULL, 0x0a0a000a0a0a000aULL, 0x4949004949490049ULL, 0x6868006868680068ULL, 0x3838003838380038ULL, 0xa4a400a4a4a400a4ULL, 0x2828002828280028ULL, 0x7b7b007b7b7b007bULL, 0xc9c900c9c9c900c9ULL, 0xc1c100c1c1c100c1ULL, 0xe3e300e3e3e300e3ULL, 0xf4f400f4f4f400f4ULL, 0xc7c700c7c7c700c7ULL, 0x9e9e009e9e9e009eULL, }; __visible const u64 camellia_sp11101110[256] = { 0x7070700070707000ULL, 0x8282820082828200ULL, 0x2c2c2c002c2c2c00ULL, 0xececec00ececec00ULL, 0xb3b3b300b3b3b300ULL, 0x2727270027272700ULL, 0xc0c0c000c0c0c000ULL, 0xe5e5e500e5e5e500ULL, 0xe4e4e400e4e4e400ULL, 0x8585850085858500ULL, 0x5757570057575700ULL, 0x3535350035353500ULL, 0xeaeaea00eaeaea00ULL, 0x0c0c0c000c0c0c00ULL, 0xaeaeae00aeaeae00ULL, 0x4141410041414100ULL, 0x2323230023232300ULL, 0xefefef00efefef00ULL, 0x6b6b6b006b6b6b00ULL, 0x9393930093939300ULL, 0x4545450045454500ULL, 0x1919190019191900ULL, 0xa5a5a500a5a5a500ULL, 0x2121210021212100ULL, 0xededed00ededed00ULL, 0x0e0e0e000e0e0e00ULL, 0x4f4f4f004f4f4f00ULL, 0x4e4e4e004e4e4e00ULL, 0x1d1d1d001d1d1d00ULL, 0x6565650065656500ULL, 0x9292920092929200ULL, 0xbdbdbd00bdbdbd00ULL, 0x8686860086868600ULL, 0xb8b8b800b8b8b800ULL, 0xafafaf00afafaf00ULL, 0x8f8f8f008f8f8f00ULL, 0x7c7c7c007c7c7c00ULL, 0xebebeb00ebebeb00ULL, 0x1f1f1f001f1f1f00ULL, 0xcecece00cecece00ULL, 0x3e3e3e003e3e3e00ULL, 0x3030300030303000ULL, 0xdcdcdc00dcdcdc00ULL, 0x5f5f5f005f5f5f00ULL, 0x5e5e5e005e5e5e00ULL, 0xc5c5c500c5c5c500ULL, 0x0b0b0b000b0b0b00ULL, 0x1a1a1a001a1a1a00ULL, 0xa6a6a600a6a6a600ULL, 0xe1e1e100e1e1e100ULL, 0x3939390039393900ULL, 0xcacaca00cacaca00ULL, 0xd5d5d500d5d5d500ULL, 0x4747470047474700ULL, 0x5d5d5d005d5d5d00ULL, 0x3d3d3d003d3d3d00ULL, 0xd9d9d900d9d9d900ULL, 0x0101010001010100ULL, 0x5a5a5a005a5a5a00ULL, 0xd6d6d600d6d6d600ULL, 0x5151510051515100ULL, 0x5656560056565600ULL, 0x6c6c6c006c6c6c00ULL, 0x4d4d4d004d4d4d00ULL, 0x8b8b8b008b8b8b00ULL, 0x0d0d0d000d0d0d00ULL, 0x9a9a9a009a9a9a00ULL, 0x6666660066666600ULL, 0xfbfbfb00fbfbfb00ULL, 0xcccccc00cccccc00ULL, 0xb0b0b000b0b0b000ULL, 0x2d2d2d002d2d2d00ULL, 0x7474740074747400ULL, 0x1212120012121200ULL, 0x2b2b2b002b2b2b00ULL, 0x2020200020202000ULL, 0xf0f0f000f0f0f000ULL, 0xb1b1b100b1b1b100ULL, 0x8484840084848400ULL, 0x9999990099999900ULL, 0xdfdfdf00dfdfdf00ULL, 0x4c4c4c004c4c4c00ULL, 0xcbcbcb00cbcbcb00ULL, 0xc2c2c200c2c2c200ULL, 0x3434340034343400ULL, 0x7e7e7e007e7e7e00ULL, 0x7676760076767600ULL, 0x0505050005050500ULL, 0x6d6d6d006d6d6d00ULL, 0xb7b7b700b7b7b700ULL, 0xa9a9a900a9a9a900ULL, 0x3131310031313100ULL, 0xd1d1d100d1d1d100ULL, 0x1717170017171700ULL, 0x0404040004040400ULL, 0xd7d7d700d7d7d700ULL, 0x1414140014141400ULL, 0x5858580058585800ULL, 0x3a3a3a003a3a3a00ULL, 0x6161610061616100ULL, 0xdedede00dedede00ULL, 0x1b1b1b001b1b1b00ULL, 0x1111110011111100ULL, 0x1c1c1c001c1c1c00ULL, 0x3232320032323200ULL, 0x0f0f0f000f0f0f00ULL, 0x9c9c9c009c9c9c00ULL, 0x1616160016161600ULL, 0x5353530053535300ULL, 0x1818180018181800ULL, 0xf2f2f200f2f2f200ULL, 0x2222220022222200ULL, 0xfefefe00fefefe00ULL, 0x4444440044444400ULL, 0xcfcfcf00cfcfcf00ULL, 0xb2b2b200b2b2b200ULL, 0xc3c3c300c3c3c300ULL, 0xb5b5b500b5b5b500ULL, 0x7a7a7a007a7a7a00ULL, 0x9191910091919100ULL, 0x2424240024242400ULL, 0x0808080008080800ULL, 0xe8e8e800e8e8e800ULL, 0xa8a8a800a8a8a800ULL, 0x6060600060606000ULL, 0xfcfcfc00fcfcfc00ULL, 0x6969690069696900ULL, 0x5050500050505000ULL, 0xaaaaaa00aaaaaa00ULL, 0xd0d0d000d0d0d000ULL, 0xa0a0a000a0a0a000ULL, 0x7d7d7d007d7d7d00ULL, 0xa1a1a100a1a1a100ULL, 0x8989890089898900ULL, 0x6262620062626200ULL, 0x9797970097979700ULL, 0x5454540054545400ULL, 0x5b5b5b005b5b5b00ULL, 0x1e1e1e001e1e1e00ULL, 0x9595950095959500ULL, 0xe0e0e000e0e0e000ULL, 0xffffff00ffffff00ULL, 0x6464640064646400ULL, 0xd2d2d200d2d2d200ULL, 0x1010100010101000ULL, 0xc4c4c400c4c4c400ULL, 0x0000000000000000ULL, 0x4848480048484800ULL, 0xa3a3a300a3a3a300ULL, 0xf7f7f700f7f7f700ULL, 0x7575750075757500ULL, 0xdbdbdb00dbdbdb00ULL, 0x8a8a8a008a8a8a00ULL, 0x0303030003030300ULL, 0xe6e6e600e6e6e600ULL, 0xdadada00dadada00ULL, 0x0909090009090900ULL, 0x3f3f3f003f3f3f00ULL, 0xdddddd00dddddd00ULL, 0x9494940094949400ULL, 0x8787870087878700ULL, 0x5c5c5c005c5c5c00ULL, 0x8383830083838300ULL, 0x0202020002020200ULL, 0xcdcdcd00cdcdcd00ULL, 0x4a4a4a004a4a4a00ULL, 0x9090900090909000ULL, 0x3333330033333300ULL, 0x7373730073737300ULL, 0x6767670067676700ULL, 0xf6f6f600f6f6f600ULL, 0xf3f3f300f3f3f300ULL, 0x9d9d9d009d9d9d00ULL, 0x7f7f7f007f7f7f00ULL, 0xbfbfbf00bfbfbf00ULL, 0xe2e2e200e2e2e200ULL, 0x5252520052525200ULL, 0x9b9b9b009b9b9b00ULL, 0xd8d8d800d8d8d800ULL, 0x2626260026262600ULL, 0xc8c8c800c8c8c800ULL, 0x3737370037373700ULL, 0xc6c6c600c6c6c600ULL, 0x3b3b3b003b3b3b00ULL, 0x8181810081818100ULL, 0x9696960096969600ULL, 0x6f6f6f006f6f6f00ULL, 0x4b4b4b004b4b4b00ULL, 0x1313130013131300ULL, 0xbebebe00bebebe00ULL, 0x6363630063636300ULL, 0x2e2e2e002e2e2e00ULL, 0xe9e9e900e9e9e900ULL, 0x7979790079797900ULL, 0xa7a7a700a7a7a700ULL, 0x8c8c8c008c8c8c00ULL, 0x9f9f9f009f9f9f00ULL, 0x6e6e6e006e6e6e00ULL, 0xbcbcbc00bcbcbc00ULL, 0x8e8e8e008e8e8e00ULL, 0x2929290029292900ULL, 0xf5f5f500f5f5f500ULL, 0xf9f9f900f9f9f900ULL, 0xb6b6b600b6b6b600ULL, 0x2f2f2f002f2f2f00ULL, 0xfdfdfd00fdfdfd00ULL, 0xb4b4b400b4b4b400ULL, 0x5959590059595900ULL, 0x7878780078787800ULL, 0x9898980098989800ULL, 0x0606060006060600ULL, 0x6a6a6a006a6a6a00ULL, 0xe7e7e700e7e7e700ULL, 0x4646460046464600ULL, 0x7171710071717100ULL, 0xbababa00bababa00ULL, 0xd4d4d400d4d4d400ULL, 0x2525250025252500ULL, 0xababab00ababab00ULL, 0x4242420042424200ULL, 0x8888880088888800ULL, 0xa2a2a200a2a2a200ULL, 0x8d8d8d008d8d8d00ULL, 0xfafafa00fafafa00ULL, 0x7272720072727200ULL, 0x0707070007070700ULL, 0xb9b9b900b9b9b900ULL, 0x5555550055555500ULL, 0xf8f8f800f8f8f800ULL, 0xeeeeee00eeeeee00ULL, 0xacacac00acacac00ULL, 0x0a0a0a000a0a0a00ULL, 0x3636360036363600ULL, 0x4949490049494900ULL, 0x2a2a2a002a2a2a00ULL, 0x6868680068686800ULL, 0x3c3c3c003c3c3c00ULL, 0x3838380038383800ULL, 0xf1f1f100f1f1f100ULL, 0xa4a4a400a4a4a400ULL, 0x4040400040404000ULL, 0x2828280028282800ULL, 0xd3d3d300d3d3d300ULL, 0x7b7b7b007b7b7b00ULL, 0xbbbbbb00bbbbbb00ULL, 0xc9c9c900c9c9c900ULL, 0x4343430043434300ULL, 0xc1c1c100c1c1c100ULL, 0x1515150015151500ULL, 0xe3e3e300e3e3e300ULL, 0xadadad00adadad00ULL, 0xf4f4f400f4f4f400ULL, 0x7777770077777700ULL, 0xc7c7c700c7c7c700ULL, 0x8080800080808000ULL, 0x9e9e9e009e9e9e00ULL, }; /* key constants */ #define CAMELLIA_SIGMA1L (0xA09E667FL) #define CAMELLIA_SIGMA1R (0x3BCC908BL) #define CAMELLIA_SIGMA2L (0xB67AE858L) #define CAMELLIA_SIGMA2R (0x4CAA73B2L) #define CAMELLIA_SIGMA3L (0xC6EF372FL) #define CAMELLIA_SIGMA3R (0xE94F82BEL) #define CAMELLIA_SIGMA4L (0x54FF53A5L) #define CAMELLIA_SIGMA4R (0xF1D36F1CL) #define CAMELLIA_SIGMA5L (0x10E527FAL) #define CAMELLIA_SIGMA5R (0xDE682D1DL) #define CAMELLIA_SIGMA6L (0xB05688C2L) #define CAMELLIA_SIGMA6R (0xB3E6C1FDL) /* macros */ #define ROLDQ(l, r, bits) ({ \ u64 t = l; \ l = (l << bits) | (r >> (64 - bits)); \ r = (r << bits) | (t >> (64 - bits)); \ }) #define CAMELLIA_F(x, kl, kr, y) ({ \ u64 ii = x ^ (((u64)kl << 32) | kr); \ y = camellia_sp11101110[(uint8_t)ii]; \ y ^= camellia_sp44044404[(uint8_t)(ii >> 8)]; \ ii >>= 16; \ y ^= camellia_sp30333033[(uint8_t)ii]; \ y ^= camellia_sp02220222[(uint8_t)(ii >> 8)]; \ ii >>= 16; \ y ^= camellia_sp00444404[(uint8_t)ii]; \ y ^= camellia_sp03303033[(uint8_t)(ii >> 8)]; \ ii >>= 16; \ y ^= camellia_sp22000222[(uint8_t)ii]; \ y ^= camellia_sp10011110[(uint8_t)(ii >> 8)]; \ y = ror64(y, 32); \ }) #define SET_SUBKEY_LR(INDEX, sRL) (subkey[(INDEX)] = ror64((sRL), 32)) static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max) { u64 kw4, tt; u32 dw, tl, tr; /* absorb kw2 to other subkeys */ /* round 2 */ subRL[3] ^= subRL[1]; /* round 4 */ subRL[5] ^= subRL[1]; /* round 6 */ subRL[7] ^= subRL[1]; subRL[1] ^= (subRL[1] & ~subRL[9]) << 32; /* modified for FLinv(kl2) */ dw = (subRL[1] & subRL[9]) >> 32; subRL[1] ^= rol32(dw, 1); /* round 8 */ subRL[11] ^= subRL[1]; /* round 10 */ subRL[13] ^= subRL[1]; /* round 12 */ subRL[15] ^= subRL[1]; subRL[1] ^= (subRL[1] & ~subRL[17]) << 32; /* modified for FLinv(kl4) */ dw = (subRL[1] & subRL[17]) >> 32; subRL[1] ^= rol32(dw, 1); /* round 14 */ subRL[19] ^= subRL[1]; /* round 16 */ subRL[21] ^= subRL[1]; /* round 18 */ subRL[23] ^= subRL[1]; if (max == 24) { /* kw3 */ subRL[24] ^= subRL[1]; /* absorb kw4 to other subkeys */ kw4 = subRL[25]; } else { subRL[1] ^= (subRL[1] & ~subRL[25]) << 32; /* modified for FLinv(kl6) */ dw = (subRL[1] & subRL[25]) >> 32; subRL[1] ^= rol32(dw, 1); /* round 20 */ subRL[27] ^= subRL[1]; /* round 22 */ subRL[29] ^= subRL[1]; /* round 24 */ subRL[31] ^= subRL[1]; /* kw3 */ subRL[32] ^= subRL[1]; /* absorb kw4 to other subkeys */ kw4 = subRL[33]; /* round 23 */ subRL[30] ^= kw4; /* round 21 */ subRL[28] ^= kw4; /* round 19 */ subRL[26] ^= kw4; kw4 ^= (kw4 & ~subRL[24]) << 32; /* modified for FL(kl5) */ dw = (kw4 & subRL[24]) >> 32; kw4 ^= rol32(dw, 1); } /* round 17 */ subRL[22] ^= kw4; /* round 15 */ subRL[20] ^= kw4; /* round 13 */ subRL[18] ^= kw4; kw4 ^= (kw4 & ~subRL[16]) << 32; /* modified for FL(kl3) */ dw = (kw4 & subRL[16]) >> 32; kw4 ^= rol32(dw, 1); /* round 11 */ subRL[14] ^= kw4; /* round 9 */ subRL[12] ^= kw4; /* round 7 */ subRL[10] ^= kw4; kw4 ^= (kw4 & ~subRL[8]) << 32; /* modified for FL(kl1) */ dw = (kw4 & subRL[8]) >> 32; kw4 ^= rol32(dw, 1); /* round 5 */ subRL[6] ^= kw4; /* round 3 */ subRL[4] ^= kw4; /* round 1 */ subRL[2] ^= kw4; /* kw1 */ subRL[0] ^= kw4; /* key XOR is end of F-function */ SET_SUBKEY_LR(0, subRL[0] ^ subRL[2]); /* kw1 */ SET_SUBKEY_LR(2, subRL[3]); /* round 1 */ SET_SUBKEY_LR(3, subRL[2] ^ subRL[4]); /* round 2 */ SET_SUBKEY_LR(4, subRL[3] ^ subRL[5]); /* round 3 */ SET_SUBKEY_LR(5, subRL[4] ^ subRL[6]); /* round 4 */ SET_SUBKEY_LR(6, subRL[5] ^ subRL[7]); /* round 5 */ tl = (subRL[10] >> 32) ^ (subRL[10] & ~subRL[8]); dw = tl & (subRL[8] >> 32); /* FL(kl1) */ tr = subRL[10] ^ rol32(dw, 1); tt = (tr | ((u64)tl << 32)); SET_SUBKEY_LR(7, subRL[6] ^ tt); /* round 6 */ SET_SUBKEY_LR(8, subRL[8]); /* FL(kl1) */ SET_SUBKEY_LR(9, subRL[9]); /* FLinv(kl2) */ tl = (subRL[7] >> 32) ^ (subRL[7] & ~subRL[9]); dw = tl & (subRL[9] >> 32); /* FLinv(kl2) */ tr = subRL[7] ^ rol32(dw, 1); tt = (tr | ((u64)tl << 32)); SET_SUBKEY_LR(10, subRL[11] ^ tt); /* round 7 */ SET_SUBKEY_LR(11, subRL[10] ^ subRL[12]); /* round 8 */ SET_SUBKEY_LR(12, subRL[11] ^ subRL[13]); /* round 9 */ SET_SUBKEY_LR(13, subRL[12] ^ subRL[14]); /* round 10 */ SET_SUBKEY_LR(14, subRL[13] ^ subRL[15]); /* round 11 */ tl = (subRL[18] >> 32) ^ (subRL[18] & ~subRL[16]); dw = tl & (subRL[16] >> 32); /* FL(kl3) */ tr = subRL[18] ^ rol32(dw, 1); tt = (tr | ((u64)tl << 32)); SET_SUBKEY_LR(15, subRL[14] ^ tt); /* round 12 */ SET_SUBKEY_LR(16, subRL[16]); /* FL(kl3) */ SET_SUBKEY_LR(17, subRL[17]); /* FLinv(kl4) */ tl = (subRL[15] >> 32) ^ (subRL[15] & ~subRL[17]); dw = tl & (subRL[17] >> 32); /* FLinv(kl4) */ tr = subRL[15] ^ rol32(dw, 1); tt = (tr | ((u64)tl << 32)); SET_SUBKEY_LR(18, subRL[19] ^ tt); /* round 13 */ SET_SUBKEY_LR(19, subRL[18] ^ subRL[20]); /* round 14 */ SET_SUBKEY_LR(20, subRL[19] ^ subRL[21]); /* round 15 */ SET_SUBKEY_LR(21, subRL[20] ^ subRL[22]); /* round 16 */ SET_SUBKEY_LR(22, subRL[21] ^ subRL[23]); /* round 17 */ if (max == 24) { SET_SUBKEY_LR(23, subRL[22]); /* round 18 */ SET_SUBKEY_LR(24, subRL[24] ^ subRL[23]); /* kw3 */ } else { tl = (subRL[26] >> 32) ^ (subRL[26] & ~subRL[24]); dw = tl & (subRL[24] >> 32); /* FL(kl5) */ tr = subRL[26] ^ rol32(dw, 1); tt = (tr | ((u64)tl << 32)); SET_SUBKEY_LR(23, subRL[22] ^ tt); /* round 18 */ SET_SUBKEY_LR(24, subRL[24]); /* FL(kl5) */ SET_SUBKEY_LR(25, subRL[25]); /* FLinv(kl6) */ tl = (subRL[23] >> 32) ^ (subRL[23] & ~subRL[25]); dw = tl & (subRL[25] >> 32); /* FLinv(kl6) */ tr = subRL[23] ^ rol32(dw, 1); tt = (tr | ((u64)tl << 32)); SET_SUBKEY_LR(26, subRL[27] ^ tt); /* round 19 */ SET_SUBKEY_LR(27, subRL[26] ^ subRL[28]); /* round 20 */ SET_SUBKEY_LR(28, subRL[27] ^ subRL[29]); /* round 21 */ SET_SUBKEY_LR(29, subRL[28] ^ subRL[30]); /* round 22 */ SET_SUBKEY_LR(30, subRL[29] ^ subRL[31]); /* round 23 */ SET_SUBKEY_LR(31, subRL[30]); /* round 24 */ SET_SUBKEY_LR(32, subRL[32] ^ subRL[31]); /* kw3 */ } } static void camellia_setup128(const unsigned char *key, u64 *subkey) { u64 kl, kr, ww; u64 subRL[26]; /** * k == kl || kr (|| is concatenation) */ kl = get_unaligned_be64(key); kr = get_unaligned_be64(key + 8); /* generate KL dependent subkeys */ /* kw1 */ subRL[0] = kl; /* kw2 */ subRL[1] = kr; /* rotation left shift 15bit */ ROLDQ(kl, kr, 15); /* k3 */ subRL[4] = kl; /* k4 */ subRL[5] = kr; /* rotation left shift 15+30bit */ ROLDQ(kl, kr, 30); /* k7 */ subRL[10] = kl; /* k8 */ subRL[11] = kr; /* rotation left shift 15+30+15bit */ ROLDQ(kl, kr, 15); /* k10 */ subRL[13] = kr; /* rotation left shift 15+30+15+17 bit */ ROLDQ(kl, kr, 17); /* kl3 */ subRL[16] = kl; /* kl4 */ subRL[17] = kr; /* rotation left shift 15+30+15+17+17 bit */ ROLDQ(kl, kr, 17); /* k13 */ subRL[18] = kl; /* k14 */ subRL[19] = kr; /* rotation left shift 15+30+15+17+17+17 bit */ ROLDQ(kl, kr, 17); /* k17 */ subRL[22] = kl; /* k18 */ subRL[23] = kr; /* generate KA */ kl = subRL[0]; kr = subRL[1]; CAMELLIA_F(kl, CAMELLIA_SIGMA1L, CAMELLIA_SIGMA1R, ww); kr ^= ww; CAMELLIA_F(kr, CAMELLIA_SIGMA2L, CAMELLIA_SIGMA2R, kl); /* current status == (kll, klr, w0, w1) */ CAMELLIA_F(kl, CAMELLIA_SIGMA3L, CAMELLIA_SIGMA3R, kr); kr ^= ww; CAMELLIA_F(kr, CAMELLIA_SIGMA4L, CAMELLIA_SIGMA4R, ww); kl ^= ww; /* generate KA dependent subkeys */ /* k1, k2 */ subRL[2] = kl; subRL[3] = kr; ROLDQ(kl, kr, 15); /* k5,k6 */ subRL[6] = kl; subRL[7] = kr; ROLDQ(kl, kr, 15); /* kl1, kl2 */ subRL[8] = kl; subRL[9] = kr; ROLDQ(kl, kr, 15); /* k9 */ subRL[12] = kl; ROLDQ(kl, kr, 15); /* k11, k12 */ subRL[14] = kl; subRL[15] = kr; ROLDQ(kl, kr, 34); /* k15, k16 */ subRL[20] = kl; subRL[21] = kr; ROLDQ(kl, kr, 17); /* kw3, kw4 */ subRL[24] = kl; subRL[25] = kr; camellia_setup_tail(subkey, subRL, 24); } static void camellia_setup256(const unsigned char *key, u64 *subkey) { u64 kl, kr; /* left half of key */ u64 krl, krr; /* right half of key */ u64 ww; /* temporary variables */ u64 subRL[34]; /** * key = (kl || kr || krl || krr) (|| is concatenation) */ kl = get_unaligned_be64(key); kr = get_unaligned_be64(key + 8); krl = get_unaligned_be64(key + 16); krr = get_unaligned_be64(key + 24); /* generate KL dependent subkeys */ /* kw1 */ subRL[0] = kl; /* kw2 */ subRL[1] = kr; ROLDQ(kl, kr, 45); /* k9 */ subRL[12] = kl; /* k10 */ subRL[13] = kr; ROLDQ(kl, kr, 15); /* kl3 */ subRL[16] = kl; /* kl4 */ subRL[17] = kr; ROLDQ(kl, kr, 17); /* k17 */ subRL[22] = kl; /* k18 */ subRL[23] = kr; ROLDQ(kl, kr, 34); /* k23 */ subRL[30] = kl; /* k24 */ subRL[31] = kr; /* generate KR dependent subkeys */ ROLDQ(krl, krr, 15); /* k3 */ subRL[4] = krl; /* k4 */ subRL[5] = krr; ROLDQ(krl, krr, 15); /* kl1 */ subRL[8] = krl; /* kl2 */ subRL[9] = krr; ROLDQ(krl, krr, 30); /* k13 */ subRL[18] = krl; /* k14 */ subRL[19] = krr; ROLDQ(krl, krr, 34); /* k19 */ subRL[26] = krl; /* k20 */ subRL[27] = krr; ROLDQ(krl, krr, 34); /* generate KA */ kl = subRL[0] ^ krl; kr = subRL[1] ^ krr; CAMELLIA_F(kl, CAMELLIA_SIGMA1L, CAMELLIA_SIGMA1R, ww); kr ^= ww; CAMELLIA_F(kr, CAMELLIA_SIGMA2L, CAMELLIA_SIGMA2R, kl); kl ^= krl; CAMELLIA_F(kl, CAMELLIA_SIGMA3L, CAMELLIA_SIGMA3R, kr); kr ^= ww ^ krr; CAMELLIA_F(kr, CAMELLIA_SIGMA4L, CAMELLIA_SIGMA4R, ww); kl ^= ww; /* generate KB */ krl ^= kl; krr ^= kr; CAMELLIA_F(krl, CAMELLIA_SIGMA5L, CAMELLIA_SIGMA5R, ww); krr ^= ww; CAMELLIA_F(krr, CAMELLIA_SIGMA6L, CAMELLIA_SIGMA6R, ww); krl ^= ww; /* generate KA dependent subkeys */ ROLDQ(kl, kr, 15); /* k5 */ subRL[6] = kl; /* k6 */ subRL[7] = kr; ROLDQ(kl, kr, 30); /* k11 */ subRL[14] = kl; /* k12 */ subRL[15] = kr; /* rotation left shift 32bit */ ROLDQ(kl, kr, 32); /* kl5 */ subRL[24] = kl; /* kl6 */ subRL[25] = kr; /* rotation left shift 17 from k11,k12 -> k21,k22 */ ROLDQ(kl, kr, 17); /* k21 */ subRL[28] = kl; /* k22 */ subRL[29] = kr; /* generate KB dependent subkeys */ /* k1 */ subRL[2] = krl; /* k2 */ subRL[3] = krr; ROLDQ(krl, krr, 30); /* k7 */ subRL[10] = krl; /* k8 */ subRL[11] = krr; ROLDQ(krl, krr, 30); /* k15 */ subRL[20] = krl; /* k16 */ subRL[21] = krr; ROLDQ(krl, krr, 51); /* kw3 */ subRL[32] = krl; /* kw4 */ subRL[33] = krr; camellia_setup_tail(subkey, subRL, 32); } static void camellia_setup192(const unsigned char *key, u64 *subkey) { unsigned char kk[32]; u64 krl, krr; memcpy(kk, key, 24); memcpy((unsigned char *)&krl, key+16, 8); krr = ~krl; memcpy(kk+24, (unsigned char *)&krr, 8); camellia_setup256(kk, subkey); } int __camellia_setkey(struct camellia_ctx *cctx, const unsigned char *key, unsigned int key_len) { if (key_len != 16 && key_len != 24 && key_len != 32) return -EINVAL; cctx->key_length = key_len; switch (key_len) { case 16: camellia_setup128(key, cctx->key_table); break; case 24: camellia_setup192(key, cctx->key_table); break; case 32: camellia_setup256(key, cctx->key_table); break; } return 0; } EXPORT_SYMBOL_GPL(__camellia_setkey); static int camellia_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int key_len) { return __camellia_setkey(crypto_tfm_ctx(tfm), key, key_len); } static int camellia_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int key_len) { return camellia_setkey(&tfm->base, key, key_len); } void camellia_decrypt_cbc_2way(const void *ctx, u8 *dst, const u8 *src) { u8 buf[CAMELLIA_BLOCK_SIZE]; const u8 *iv = src; if (dst == src) iv = memcpy(buf, iv, sizeof(buf)); camellia_dec_blk_2way(ctx, dst, src); crypto_xor(dst + CAMELLIA_BLOCK_SIZE, iv, CAMELLIA_BLOCK_SIZE); } EXPORT_SYMBOL_GPL(camellia_decrypt_cbc_2way); static int ecb_encrypt(struct skcipher_request *req) { ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); ECB_BLOCK(2, camellia_enc_blk_2way); ECB_BLOCK(1, camellia_enc_blk); ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); ECB_BLOCK(2, camellia_dec_blk_2way); ECB_BLOCK(1, camellia_dec_blk); ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); CBC_ENC_BLOCK(camellia_enc_blk); CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); CBC_DEC_BLOCK(2, camellia_decrypt_cbc_2way); CBC_DEC_BLOCK(1, camellia_dec_blk); CBC_WALK_END(); } static struct crypto_alg camellia_cipher_alg = { .cra_name = "camellia", .cra_driver_name = "camellia-asm", .cra_priority = 200, .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = CAMELLIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct camellia_ctx), .cra_alignmask = 0, .cra_module = THIS_MODULE, .cra_u = { .cipher = { .cia_min_keysize = CAMELLIA_MIN_KEY_SIZE, .cia_max_keysize = CAMELLIA_MAX_KEY_SIZE, .cia_setkey = camellia_setkey, .cia_encrypt = camellia_encrypt, .cia_decrypt = camellia_decrypt } } }; static struct skcipher_alg camellia_skcipher_algs[] = { { .base.cra_name = "ecb(camellia)", .base.cra_driver_name = "ecb-camellia-asm", .base.cra_priority = 300, .base.cra_blocksize = CAMELLIA_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct camellia_ctx), .base.cra_module = THIS_MODULE, .min_keysize = CAMELLIA_MIN_KEY_SIZE, .max_keysize = CAMELLIA_MAX_KEY_SIZE, .setkey = camellia_setkey_skcipher, .encrypt = ecb_encrypt, .decrypt = ecb_decrypt, }, { .base.cra_name = "cbc(camellia)", .base.cra_driver_name = "cbc-camellia-asm", .base.cra_priority = 300, .base.cra_blocksize = CAMELLIA_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct camellia_ctx), .base.cra_module = THIS_MODULE, .min_keysize = CAMELLIA_MIN_KEY_SIZE, .max_keysize = CAMELLIA_MAX_KEY_SIZE, .ivsize = CAMELLIA_BLOCK_SIZE, .setkey = camellia_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, } }; static bool is_blacklisted_cpu(void) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return false; if (boot_cpu_data.x86 == 0x0f) { /* * On Pentium 4, camellia-asm is slower than original assembler * implementation because excessive uses of 64bit rotate and * left-shifts (which are really slow on P4) needed to store and * handle 128bit block in two 64bit registers. */ return true; } return false; } static int force; module_param(force, int, 0); MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist"); static int __init camellia_init(void) { int err; if (!force && is_blacklisted_cpu()) { printk(KERN_INFO "camellia-x86_64: performance on this CPU " "would be suboptimal: disabling " "camellia-x86_64.\n"); return -ENODEV; } err = crypto_register_alg(&camellia_cipher_alg); if (err) return err; err = crypto_register_skciphers(camellia_skcipher_algs, ARRAY_SIZE(camellia_skcipher_algs)); if (err) crypto_unregister_alg(&camellia_cipher_alg); return err; } static void __exit camellia_fini(void) { crypto_unregister_alg(&camellia_cipher_alg); crypto_unregister_skciphers(camellia_skcipher_algs, ARRAY_SIZE(camellia_skcipher_algs)); } module_init(camellia_init); module_exit(camellia_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, asm optimized"); MODULE_ALIAS_CRYPTO("camellia"); MODULE_ALIAS_CRYPTO("camellia-asm"); |
| 868 24 24 24 11961 20 11966 11960 11962 5 12149 427 11956 11980 427 6 426 427 131 55 24 24 24 24 24 24 24 24 51 51 51 50 5438 5438 5428 80 5436 10617 10620 10615 10612 10617 17 76 77 76 77 77 2 2 2 2 191 190 190 12 190 268 269 4058 4 4 4 24 24 24 24 24 24 24 24 24 15 24 24 24 24 24 24 23 24 24 24 24 24 24 24 24 825 824 822 820 47 47 47 2 81 81 82 82 82 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles); static inline u64 timekeeping_debug_get_ns(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; /* Check for multiplication overflows */ if (unlikely(delta > max)) tk->overflow_seen = 1; /* timekeeping_cycles_to_ns() handles both under and overflow */ return timekeeping_cycles_to_ns(tkr, now); } #else static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) { BUG(); } #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 noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta) { return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift); } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { /* Calculate the delta since the last update_wall_time() */ u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask; /* * This detects both negative motion and the case where the delta * overflows the multiplication with tkr->mult. */ if (unlikely(delta > tkr->clock->max_cycles)) { /* * Handle clocksource inconsistency between CPUs to prevent * time from going backwards by checking for the MSB of the * mask being set in the delta. */ if (delta & ~(mask >> 1)) return tkr->xtime_nsec >> tkr->shift; return delta_to_ns_safe(tkr, delta); } return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } static __always_inline u64 __timekeeping_get_ns(const struct tk_read_base *tkr) { return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { if (IS_ENABLED(CONFIG_DEBUG_TIMEKEEPING)) return timekeeping_debug_get_ns(tkr); return __timekeeping_get_ns(tkr); } /** * 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 __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 += __timekeeping_get_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 = __timekeeping_get_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; while (delta > 0) { u64 max = tk->tkr_mono.clock->max_cycles; u64 incr = delta < max ? delta : max; tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult; tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult; tk_normalize_xtime(tk); delta -= incr; } } /** * 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; unsigned int seq; ktime_t base_raw; ktime_t base_real; 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_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); } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } 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 ID associated with the captured * system counter value is the same as for the currently * installed timekeeper clocksource */ if (system_counterval.cs_id == CSID_GENERIC || tk->tkr_mono.clock->id != system_counterval.cs_id) 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. * @wall_time: current time as returned by persistent clock * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. * * 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_REALTIME); 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 */ |
| 31 31 31 31 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This only handles 32bit MTRR on 32bit hosts. This is strictly wrong * because MTRRs can span up to 40 bits (36bits on most modern x86) */ #include <linux/export.h> #include <linux/init.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/cc_platform.h> #include <asm/processor-flags.h> #include <asm/cacheinfo.h> #include <asm/cpufeature.h> #include <asm/hypervisor.h> #include <asm/mshyperv.h> #include <asm/tlbflush.h> #include <asm/mtrr.h> #include <asm/msr.h> #include <asm/memtype.h> #include "mtrr.h" struct fixed_range_block { int base_msr; /* start address of an MTRR block */ int ranges; /* number of MTRRs in this block */ }; static struct fixed_range_block fixed_range_blocks[] = { { MSR_MTRRfix64K_00000, 1 }, /* one 64k MTRR */ { MSR_MTRRfix16K_80000, 2 }, /* two 16k MTRRs */ { MSR_MTRRfix4K_C0000, 8 }, /* eight 4k MTRRs */ {} }; struct cache_map { u64 start; u64 end; u64 flags; u64 type:8; u64 fixed:1; }; bool mtrr_debug; static int __init mtrr_param_setup(char *str) { int rc = 0; if (!str) return -EINVAL; if (!strcmp(str, "debug")) mtrr_debug = true; else rc = -EINVAL; return rc; } early_param("mtrr", mtrr_param_setup); /* * CACHE_MAP_MAX is the maximum number of memory ranges in cache_map, where * no 2 adjacent ranges have the same cache mode (those would be merged). * The number is based on the worst case: * - no two adjacent fixed MTRRs share the same cache mode * - one variable MTRR is spanning a huge area with mode WB * - 255 variable MTRRs with mode UC all overlap with the WB MTRR, creating 2 * additional ranges each (result like "ababababa...aba" with a = WB, b = UC), * accounting for MTRR_MAX_VAR_RANGES * 2 - 1 range entries * - a TOP_MEM2 area (even with overlapping an UC MTRR can't add 2 range entries * to the possible maximum, as it always starts at 4GB, thus it can't be in * the middle of that MTRR, unless that MTRR starts at 0, which would remove * the initial "a" from the "abababa" pattern above) * The map won't contain ranges with no matching MTRR (those fall back to the * default cache mode). */ #define CACHE_MAP_MAX (MTRR_NUM_FIXED_RANGES + MTRR_MAX_VAR_RANGES * 2) static struct cache_map init_cache_map[CACHE_MAP_MAX] __initdata; static struct cache_map *cache_map __refdata = init_cache_map; static unsigned int cache_map_size = CACHE_MAP_MAX; static unsigned int cache_map_n; static unsigned int cache_map_fixed; static unsigned long smp_changes_mask; static int mtrr_state_set; u64 mtrr_tom2; struct mtrr_state_type mtrr_state; EXPORT_SYMBOL_GPL(mtrr_state); /* Reserved bits in the high portion of the MTRRphysBaseN MSR. */ u32 phys_hi_rsvd; /* * BIOS is expected to clear MtrrFixDramModEn bit, see for example * "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD * Opteron Processors" (26094 Rev. 3.30 February 2006), section * "13.2.1.2 SYSCFG Register": "The MtrrFixDramModEn bit should be set * to 1 during BIOS initialization of the fixed MTRRs, then cleared to * 0 for operation." */ static inline void k8_check_syscfg_dram_mod_en(void) { u32 lo, hi; if (!((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0x0f))) return; if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return; rdmsr(MSR_AMD64_SYSCFG, lo, hi); if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) { pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" " not cleared by BIOS, clearing this bit\n", smp_processor_id()); lo &= ~K8_MTRRFIXRANGE_DRAM_MODIFY; mtrr_wrmsr(MSR_AMD64_SYSCFG, lo, hi); } } /* Get the size of contiguous MTRR range */ static u64 get_mtrr_size(u64 mask) { u64 size; mask |= (u64)phys_hi_rsvd << 32; size = -mask; return size; } static u8 get_var_mtrr_state(unsigned int reg, u64 *start, u64 *size) { struct mtrr_var_range *mtrr = mtrr_state.var_ranges + reg; if (!(mtrr->mask_lo & MTRR_PHYSMASK_V)) return MTRR_TYPE_INVALID; *start = (((u64)mtrr->base_hi) << 32) + (mtrr->base_lo & PAGE_MASK); *size = get_mtrr_size((((u64)mtrr->mask_hi) << 32) + (mtrr->mask_lo & PAGE_MASK)); return mtrr->base_lo & MTRR_PHYSBASE_TYPE; } static u8 get_effective_type(u8 type1, u8 type2) { if (type1 == MTRR_TYPE_UNCACHABLE || type2 == MTRR_TYPE_UNCACHABLE) return MTRR_TYPE_UNCACHABLE; if ((type1 == MTRR_TYPE_WRBACK && type2 == MTRR_TYPE_WRTHROUGH) || (type1 == MTRR_TYPE_WRTHROUGH && type2 == MTRR_TYPE_WRBACK)) return MTRR_TYPE_WRTHROUGH; if (type1 != type2) return MTRR_TYPE_UNCACHABLE; return type1; } static void rm_map_entry_at(int idx) { cache_map_n--; if (cache_map_n > idx) { memmove(cache_map + idx, cache_map + idx + 1, sizeof(*cache_map) * (cache_map_n - idx)); } } /* * Add an entry into cache_map at a specific index. Merges adjacent entries if * appropriate. Return the number of merges for correcting the scan index * (this is needed as merging will reduce the number of entries, which will * result in skipping entries in future iterations if the scan index isn't * corrected). * Note that the corrected index can never go below -1 (resulting in being 0 in * the next scan iteration), as "2" is returned only if the current index is * larger than zero. */ static int add_map_entry_at(u64 start, u64 end, u8 type, int idx) { bool merge_prev = false, merge_next = false; if (start >= end) return 0; if (idx > 0) { struct cache_map *prev = cache_map + idx - 1; if (!prev->fixed && start == prev->end && type == prev->type) merge_prev = true; } if (idx < cache_map_n) { struct cache_map *next = cache_map + idx; if (!next->fixed && end == next->start && type == next->type) merge_next = true; } if (merge_prev && merge_next) { cache_map[idx - 1].end = cache_map[idx].end; rm_map_entry_at(idx); return 2; } if (merge_prev) { cache_map[idx - 1].end = end; return 1; } if (merge_next) { cache_map[idx].start = start; return 1; } /* Sanity check: the array should NEVER be too small! */ if (cache_map_n == cache_map_size) { WARN(1, "MTRR cache mode memory map exhausted!\n"); cache_map_n = cache_map_fixed; return 0; } if (cache_map_n > idx) { memmove(cache_map + idx + 1, cache_map + idx, sizeof(*cache_map) * (cache_map_n - idx)); } cache_map[idx].start = start; cache_map[idx].end = end; cache_map[idx].type = type; cache_map[idx].fixed = 0; cache_map_n++; return 0; } /* Clear a part of an entry. Return 1 if start of entry is still valid. */ static int clr_map_range_at(u64 start, u64 end, int idx) { int ret = start != cache_map[idx].start; u64 tmp; if (start == cache_map[idx].start && end == cache_map[idx].end) { rm_map_entry_at(idx); } else if (start == cache_map[idx].start) { cache_map[idx].start = end; } else if (end == cache_map[idx].end) { cache_map[idx].end = start; } else { tmp = cache_map[idx].end; cache_map[idx].end = start; add_map_entry_at(end, tmp, cache_map[idx].type, idx + 1); } return ret; } /* * Add MTRR to the map. The current map is scanned and each part of the MTRR * either overlapping with an existing entry or with a hole in the map is * handled separately. */ static void add_map_entry(u64 start, u64 end, u8 type) { u8 new_type, old_type; u64 tmp; int i; for (i = 0; i < cache_map_n && start < end; i++) { if (start >= cache_map[i].end) continue; if (start < cache_map[i].start) { /* Region start has no overlap. */ tmp = min(end, cache_map[i].start); i -= add_map_entry_at(start, tmp, type, i); start = tmp; continue; } new_type = get_effective_type(type, cache_map[i].type); old_type = cache_map[i].type; if (cache_map[i].fixed || new_type == old_type) { /* Cut off start of new entry. */ start = cache_map[i].end; continue; } /* Handle only overlapping part of region. */ tmp = min(end, cache_map[i].end); i += clr_map_range_at(start, tmp, i); i -= add_map_entry_at(start, tmp, new_type, i); start = tmp; } /* Add rest of region after last map entry (rest might be empty). */ add_map_entry_at(start, end, type, i); } /* Add variable MTRRs to cache map. */ static void map_add_var(void) { u64 start, size; unsigned int i; u8 type; /* * Add AMD TOP_MEM2 area. Can't be added in mtrr_build_map(), as it * needs to be added again when rebuilding the map due to potentially * having moved as a result of variable MTRRs for memory below 4GB. */ if (mtrr_tom2) { add_map_entry(BIT_ULL(32), mtrr_tom2, MTRR_TYPE_WRBACK); cache_map[cache_map_n - 1].fixed = 1; } for (i = 0; i < num_var_ranges; i++) { type = get_var_mtrr_state(i, &start, &size); if (type != MTRR_TYPE_INVALID) add_map_entry(start, start + size, type); } } /* * Rebuild map by replacing variable entries. Needs to be called when MTRR * registers are being changed after boot, as such changes could include * removals of registers, which are complicated to handle without rebuild of * the map. */ void generic_rebuild_map(void) { if (mtrr_if != &generic_mtrr_ops) return; cache_map_n = cache_map_fixed; map_add_var(); } static unsigned int __init get_cache_map_size(void) { return cache_map_fixed + 2 * num_var_ranges + (mtrr_tom2 != 0); } /* Build the cache_map containing the cache modes per memory range. */ void __init mtrr_build_map(void) { u64 start, end, size; unsigned int i; u8 type; /* Add fixed MTRRs, optimize for adjacent entries with same type. */ if (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED) { /* * Start with 64k size fixed entries, preset 1st one (hence the * loop below is starting with index 1). */ start = 0; end = size = 0x10000; type = mtrr_state.fixed_ranges[0]; for (i = 1; i < MTRR_NUM_FIXED_RANGES; i++) { /* 8 64k entries, then 16 16k ones, rest 4k. */ if (i == 8 || i == 24) size >>= 2; if (mtrr_state.fixed_ranges[i] != type) { add_map_entry(start, end, type); start = end; type = mtrr_state.fixed_ranges[i]; } end += size; } add_map_entry(start, end, type); } /* Mark fixed, they take precedence. */ for (i = 0; i < cache_map_n; i++) cache_map[i].fixed = 1; cache_map_fixed = cache_map_n; map_add_var(); pr_info("MTRR map: %u entries (%u fixed + %u variable; max %u), built from %u variable MTRRs\n", cache_map_n, cache_map_fixed, cache_map_n - cache_map_fixed, get_cache_map_size(), num_var_ranges + (mtrr_tom2 != 0)); if (mtrr_debug) { for (i = 0; i < cache_map_n; i++) { pr_info("%3u: %016llx-%016llx %s\n", i, cache_map[i].start, cache_map[i].end - 1, mtrr_attrib_to_str(cache_map[i].type)); } } } /* Copy the cache_map from __initdata memory to dynamically allocated one. */ void __init mtrr_copy_map(void) { unsigned int new_size = get_cache_map_size(); if (!mtrr_state.enabled || !new_size) { cache_map = NULL; return; } mutex_lock(&mtrr_mutex); cache_map = kcalloc(new_size, sizeof(*cache_map), GFP_KERNEL); if (cache_map) { memmove(cache_map, init_cache_map, cache_map_n * sizeof(*cache_map)); cache_map_size = new_size; } else { mtrr_state.enabled = 0; pr_err("MTRRs disabled due to allocation failure for lookup map.\n"); } mutex_unlock(&mtrr_mutex); } /** * mtrr_overwrite_state - set static MTRR state * * Used to set MTRR state via different means (e.g. with data obtained from * a hypervisor). * Is allowed only for special cases when running virtualized. Must be called * from the x86_init.hyper.init_platform() hook. It can be called only once. * The MTRR state can't be changed afterwards. To ensure that, X86_FEATURE_MTRR * is cleared. * * @var: MTRR variable range array to use * @num_var: length of the @var array * @def_type: default caching type */ void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, mtrr_type def_type) { unsigned int i; /* Only allowed to be called once before mtrr_bp_init(). */ if (WARN_ON_ONCE(mtrr_state_set)) return; /* Only allowed when running virtualized. */ if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) return; /* * Only allowed for special virtualization cases: * - when running as Hyper-V, SEV-SNP guest using vTOM * - when running as Xen PV guest * - when running as SEV-SNP or TDX guest to avoid unnecessary * VMM communication/Virtualization exceptions (#VC, #VE) */ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !hv_is_isolation_supported() && !cpu_feature_enabled(X86_FEATURE_XENPV) && !cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) return; /* Disable MTRR in order to disable MTRR modifications. */ setup_clear_cpu_cap(X86_FEATURE_MTRR); if (var) { if (num_var > MTRR_MAX_VAR_RANGES) { pr_warn("Trying to overwrite MTRR state with %u variable entries\n", num_var); num_var = MTRR_MAX_VAR_RANGES; } for (i = 0; i < num_var; i++) mtrr_state.var_ranges[i] = var[i]; num_var_ranges = num_var; } mtrr_state.def_type = def_type; mtrr_state.enabled |= MTRR_STATE_MTRR_ENABLED; mtrr_state_set = 1; } static u8 type_merge(u8 type, u8 new_type, u8 *uniform) { u8 effective_type; if (type == MTRR_TYPE_INVALID) return new_type; effective_type = get_effective_type(type, new_type); if (type != effective_type) *uniform = 0; return effective_type; } /** * mtrr_type_lookup - look up memory type in MTRR * * @start: Begin of the physical address range * @end: End of the physical address range * @uniform: output argument: * - 1: the returned MTRR type is valid for the whole region * - 0: otherwise * * Return Values: * MTRR_TYPE_(type) - The effective MTRR type for the region * MTRR_TYPE_INVALID - MTRR is disabled */ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) { u8 type = MTRR_TYPE_INVALID; unsigned int i; if (!mtrr_state_set) { /* Uniformity is unknown. */ *uniform = 0; return MTRR_TYPE_UNCACHABLE; } *uniform = 1; if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED)) return MTRR_TYPE_UNCACHABLE; for (i = 0; i < cache_map_n && start < end; i++) { /* Region after current map entry? -> continue with next one. */ if (start >= cache_map[i].end) continue; /* Start of region not covered by current map entry? */ if (start < cache_map[i].start) { /* At least some part of region has default type. */ type = type_merge(type, mtrr_state.def_type, uniform); /* End of region not covered, too? -> lookup done. */ if (end <= cache_map[i].start) return type; } /* At least part of region covered by map entry. */ type = type_merge(type, cache_map[i].type, uniform); start = cache_map[i].end; } /* End of region past last entry in map? -> use default type. */ if (start < end) type = type_merge(type, mtrr_state.def_type, uniform); return type; } /* Get the MSR pair relating to a var range */ static void get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr) { rdmsr(MTRRphysBase_MSR(index), vr->base_lo, vr->base_hi); rdmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi); } /* Fill the MSR pair relating to a var range */ void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi) { struct mtrr_var_range *vr; vr = mtrr_state.var_ranges; vr[index].base_lo = base_lo; vr[index].base_hi = base_hi; vr[index].mask_lo = mask_lo; vr[index].mask_hi = mask_hi; } static void get_fixed_ranges(mtrr_type *frs) { unsigned int *p = (unsigned int *)frs; int i; k8_check_syscfg_dram_mod_en(); rdmsr(MSR_MTRRfix64K_00000, p[0], p[1]); for (i = 0; i < 2; i++) rdmsr(MSR_MTRRfix16K_80000 + i, p[2 + i * 2], p[3 + i * 2]); for (i = 0; i < 8; i++) rdmsr(MSR_MTRRfix4K_C0000 + i, p[6 + i * 2], p[7 + i * 2]); } void mtrr_save_fixed_ranges(void *info) { if (boot_cpu_has(X86_FEATURE_MTRR)) get_fixed_ranges(mtrr_state.fixed_ranges); } static unsigned __initdata last_fixed_start; static unsigned __initdata last_fixed_end; static mtrr_type __initdata last_fixed_type; static void __init print_fixed_last(void) { if (!last_fixed_end) return; pr_info(" %05X-%05X %s\n", last_fixed_start, last_fixed_end - 1, mtrr_attrib_to_str(last_fixed_type)); last_fixed_end = 0; } static void __init update_fixed_last(unsigned base, unsigned end, mtrr_type type) { last_fixed_start = base; last_fixed_end = end; last_fixed_type = type; } static void __init print_fixed(unsigned base, unsigned step, const mtrr_type *types) { unsigned i; for (i = 0; i < 8; ++i, ++types, base += step) { if (last_fixed_end == 0) { update_fixed_last(base, base + step, *types); continue; } if (last_fixed_end == base && last_fixed_type == *types) { last_fixed_end = base + step; continue; } /* new segments: gap or different type */ print_fixed_last(); update_fixed_last(base, base + step, *types); } } static void __init print_mtrr_state(void) { unsigned int i; int high_width; pr_info("MTRR default type: %s\n", mtrr_attrib_to_str(mtrr_state.def_type)); if (mtrr_state.have_fixed) { pr_info("MTRR fixed ranges %sabled:\n", ((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ? "en" : "dis"); print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0); for (i = 0; i < 2; ++i) print_fixed(0x80000 + i * 0x20000, 0x04000, mtrr_state.fixed_ranges + (i + 1) * 8); for (i = 0; i < 8; ++i) print_fixed(0xC0000 + i * 0x08000, 0x01000, mtrr_state.fixed_ranges + (i + 3) * 8); /* tail */ print_fixed_last(); } pr_info("MTRR variable ranges %sabled:\n", mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis"); high_width = (boot_cpu_data.x86_phys_bits - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { if (mtrr_state.var_ranges[i].mask_lo & MTRR_PHYSMASK_V) pr_info(" %u base %0*X%05X000 mask %0*X%05X000 %s\n", i, high_width, mtrr_state.var_ranges[i].base_hi, mtrr_state.var_ranges[i].base_lo >> 12, high_width, mtrr_state.var_ranges[i].mask_hi, mtrr_state.var_ranges[i].mask_lo >> 12, mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & MTRR_PHYSBASE_TYPE)); else pr_info(" %u disabled\n", i); } if (mtrr_tom2) pr_info("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } /* Grab all of the MTRR state for this CPU into *state */ bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; unsigned lo, dummy; unsigned int i; vrs = mtrr_state.var_ranges; rdmsr(MSR_MTRRcap, lo, dummy); mtrr_state.have_fixed = lo & MTRR_CAP_FIX; for (i = 0; i < num_var_ranges; i++) get_mtrr_var_range(i, &vrs[i]); if (mtrr_state.have_fixed) get_fixed_ranges(mtrr_state.fixed_ranges); rdmsr(MSR_MTRRdefType, lo, dummy); mtrr_state.def_type = lo & MTRR_DEF_TYPE_TYPE; mtrr_state.enabled = (lo & MTRR_DEF_TYPE_ENABLE) >> MTRR_STATE_SHIFT; if (amd_special_default_mtrr()) { unsigned low, high; /* TOP_MEM2 */ rdmsr(MSR_K8_TOP_MEM2, low, high); mtrr_tom2 = high; mtrr_tom2 <<= 32; mtrr_tom2 |= low; mtrr_tom2 &= 0xffffff800000ULL; } if (mtrr_debug) print_mtrr_state(); mtrr_state_set = 1; return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } /* Some BIOS's are messed up and don't set all MTRRs the same! */ void __init mtrr_state_warn(void) { unsigned long mask = smp_changes_mask; if (!mask) return; if (mask & MTRR_CHANGE_MASK_FIXED) pr_warn("mtrr: your CPUs had inconsistent fixed MTRR settings\n"); if (mask & MTRR_CHANGE_MASK_VARIABLE) pr_warn("mtrr: your CPUs had inconsistent variable MTRR settings\n"); if (mask & MTRR_CHANGE_MASK_DEFTYPE) pr_warn("mtrr: your CPUs had inconsistent MTRRdefType settings\n"); pr_info("mtrr: probably your BIOS does not setup all CPUs.\n"); pr_info("mtrr: corrected configuration.\n"); } /* * Doesn't attempt to pass an error out to MTRR users * because it's quite complicated in some cases and probably not * worth it because the best error handling is to ignore it. */ void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b) { if (wrmsr_safe(msr, a, b) < 0) { pr_err("MTRR: CPU %u: Writing MSR %x to %x:%x failed\n", smp_processor_id(), msr, a, b); } } /** * set_fixed_range - checks & updates a fixed-range MTRR if it * differs from the value it should have * @msr: MSR address of the MTTR which should be checked and updated * @changed: pointer which indicates whether the MTRR needed to be changed * @msrwords: pointer to the MSR values which the MSR should have */ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords) { unsigned lo, hi; rdmsr(msr, lo, hi); if (lo != msrwords[0] || hi != msrwords[1]) { mtrr_wrmsr(msr, msrwords[0], msrwords[1]); *changed = true; } } /** * generic_get_free_region - Get a free MTRR. * @base: The starting (base) address of the region. * @size: The size (in bytes) of the region. * @replace_reg: mtrr index to be replaced; set to invalid value if none. * * Returns: The index of the region on success, else negative on error. */ int generic_get_free_region(unsigned long base, unsigned long size, int replace_reg) { unsigned long lbase, lsize; mtrr_type ltype; int i, max; max = num_var_ranges; if (replace_reg >= 0 && replace_reg < max) return replace_reg; for (i = 0; i < max; ++i) { mtrr_if->get(i, &lbase, &lsize, <ype); if (lsize == 0) return i; } return -ENOSPC; } static void generic_get_mtrr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type *type) { u32 mask_lo, mask_hi, base_lo, base_hi; unsigned int hi; u64 tmp, mask; /* * get_mtrr doesn't need to update mtrr_state, also it could be called * from any cpu, so try to print it out directly. */ get_cpu(); rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi); if (!(mask_lo & MTRR_PHYSMASK_V)) { /* Invalid (i.e. free) range */ *base = 0; *size = 0; *type = 0; goto out_put_cpu; } rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); /* Work out the shifted address mask: */ tmp = (u64)mask_hi << 32 | (mask_lo & PAGE_MASK); mask = (u64)phys_hi_rsvd << 32 | tmp; /* Expand tmp with high bits to all 1s: */ hi = fls64(tmp); if (hi > 0) { tmp |= ~((1ULL<<(hi - 1)) - 1); if (tmp != mask) { pr_warn("mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); mask = tmp; } } /* * This works correctly if size is a power of two, i.e. a * contiguous range: */ *size = -mask >> PAGE_SHIFT; *base = (u64)base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; *type = base_lo & MTRR_PHYSBASE_TYPE; out_put_cpu: put_cpu(); } /** * set_fixed_ranges - checks & updates the fixed-range MTRRs if they * differ from the saved set * @frs: pointer to fixed-range MTRR values, saved by get_fixed_ranges() */ static int set_fixed_ranges(mtrr_type *frs) { unsigned long long *saved = (unsigned long long *)frs; bool changed = false; int block = -1, range; k8_check_syscfg_dram_mod_en(); while (fixed_range_blocks[++block].ranges) { for (range = 0; range < fixed_range_blocks[block].ranges; range++) set_fixed_range(fixed_range_blocks[block].base_msr + range, &changed, (unsigned int *)saved++); } return changed; } /* * Set the MSR pair relating to a var range. * Returns true if changes are made. */ static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr) { unsigned int lo, hi; bool changed = false; rdmsr(MTRRphysBase_MSR(index), lo, hi); if ((vr->base_lo & ~MTRR_PHYSBASE_RSVD) != (lo & ~MTRR_PHYSBASE_RSVD) || (vr->base_hi & ~phys_hi_rsvd) != (hi & ~phys_hi_rsvd)) { mtrr_wrmsr(MTRRphysBase_MSR(index), vr->base_lo, vr->base_hi); changed = true; } rdmsr(MTRRphysMask_MSR(index), lo, hi); if ((vr->mask_lo & ~MTRR_PHYSMASK_RSVD) != (lo & ~MTRR_PHYSMASK_RSVD) || (vr->mask_hi & ~phys_hi_rsvd) != (hi & ~phys_hi_rsvd)) { mtrr_wrmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi); changed = true; } return changed; } static u32 deftype_lo, deftype_hi; /** * set_mtrr_state - Set the MTRR state for this CPU. * * NOTE: The CPU must already be in a safe state for MTRR changes, including * measures that only a single CPU can be active in set_mtrr_state() in * order to not be subject to races for usage of deftype_lo. This is * accomplished by taking cache_disable_lock. * RETURNS: 0 if no changes made, else a mask indicating what was changed. */ static unsigned long set_mtrr_state(void) { unsigned long change_mask = 0; unsigned int i; for (i = 0; i < num_var_ranges; i++) { if (set_mtrr_var_ranges(i, &mtrr_state.var_ranges[i])) change_mask |= MTRR_CHANGE_MASK_VARIABLE; } if (mtrr_state.have_fixed && set_fixed_ranges(mtrr_state.fixed_ranges)) change_mask |= MTRR_CHANGE_MASK_FIXED; /* * Set_mtrr_restore restores the old value of MTRRdefType, * so to set it we fiddle with the saved value: */ if ((deftype_lo & MTRR_DEF_TYPE_TYPE) != mtrr_state.def_type || ((deftype_lo & MTRR_DEF_TYPE_ENABLE) >> MTRR_STATE_SHIFT) != mtrr_state.enabled) { deftype_lo = (deftype_lo & MTRR_DEF_TYPE_DISABLE) | mtrr_state.def_type | (mtrr_state.enabled << MTRR_STATE_SHIFT); change_mask |= MTRR_CHANGE_MASK_DEFTYPE; } return change_mask; } void mtrr_disable(void) { /* Save MTRR state */ rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); /* Disable MTRRs, and set the default type to uncached */ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & MTRR_DEF_TYPE_DISABLE, deftype_hi); } void mtrr_enable(void) { /* Intel (P6) standard MTRRs */ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); } void mtrr_generic_set_state(void) { unsigned long mask, count; /* Actually set the state */ mask = set_mtrr_state(); /* Use the atomic bitops to update the global mask */ for (count = 0; count < sizeof(mask) * 8; ++count) { if (mask & 0x01) set_bit(count, &smp_changes_mask); mask >>= 1; } } /** * generic_set_mtrr - set variable MTRR register on the local CPU. * * @reg: The register to set. * @base: The base address of the region. * @size: The size of the region. If this is 0 the region is disabled. * @type: The type of the region. * * Returns nothing. */ static void generic_set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type) { unsigned long flags; struct mtrr_var_range *vr; vr = &mtrr_state.var_ranges[reg]; local_irq_save(flags); cache_disable(); if (size == 0) { /* * The invalid bit is kept in the mask, so we simply * clear the relevant mask register to disable a range. */ mtrr_wrmsr(MTRRphysMask_MSR(reg), 0, 0); memset(vr, 0, sizeof(struct mtrr_var_range)); } else { vr->base_lo = base << PAGE_SHIFT | type; vr->base_hi = (base >> (32 - PAGE_SHIFT)) & ~phys_hi_rsvd; vr->mask_lo = -size << PAGE_SHIFT | MTRR_PHYSMASK_V; vr->mask_hi = (-size >> (32 - PAGE_SHIFT)) & ~phys_hi_rsvd; mtrr_wrmsr(MTRRphysBase_MSR(reg), vr->base_lo, vr->base_hi); mtrr_wrmsr(MTRRphysMask_MSR(reg), vr->mask_lo, vr->mask_hi); } cache_enable(); local_irq_restore(flags); } int generic_validate_add_page(unsigned long base, unsigned long size, unsigned int type) { unsigned long lbase, last; /* * For Intel PPro stepping <= 7 * must be 4 MiB aligned and not touch 0x70000000 -> 0x7003FFFF */ if (mtrr_if == &generic_mtrr_ops && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && boot_cpu_data.x86_stepping <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; } if (!(base + size < 0x70000 || base > 0x7003F) && (type == MTRR_TYPE_WRCOMB || type == MTRR_TYPE_WRBACK)) { pr_warn("mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n"); return -EINVAL; } } /* * Check upper bits of base and last are equal and lower bits are 0 * for base and 1 for last */ last = base + size - 1; for (lbase = base; !(lbase & 1) && (last & 1); lbase = lbase >> 1, last = last >> 1) ; if (lbase != last) { pr_warn("mtrr: base(0x%lx000) is not aligned on a size(0x%lx000) boundary\n", base, size); return -EINVAL; } return 0; } static int generic_have_wrcomb(void) { unsigned long config, dummy; rdmsr(MSR_MTRRcap, config, dummy); return config & MTRR_CAP_WC; } int positive_have_wrcomb(void) { return 1; } /* * Generic structure... */ const struct mtrr_ops generic_mtrr_ops = { .get = generic_get_mtrr, .get_free_region = generic_get_free_region, .set = generic_set_mtrr, .validate_add_page = generic_validate_add_page, .have_wrcomb = generic_have_wrcomb, }; |
| 3 3 3 3 3 3 3 3 3 5 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * ext4.h * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/include/linux/minix_fs.h * * Copyright (C) 1991, 1992 Linus Torvalds */ #ifndef _EXT4_H #define _EXT4_H #include <linux/refcount.h> #include <linux/types.h> #include <linux/blkdev.h> #include <linux/magic.h> #include <linux/jbd2.h> #include <linux/quota.h> #include <linux/rwsem.h> #include <linux/rbtree.h> #include <linux/seqlock.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/wait.h> #include <linux/sched/signal.h> #include <linux/blockgroup_lock.h> #include <linux/percpu_counter.h> #include <linux/ratelimit.h> #include <crypto/hash.h> #include <linux/falloc.h> #include <linux/percpu-rwsem.h> #include <linux/fiemap.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif #include <uapi/linux/ext4.h> #include <linux/fscrypt.h> #include <linux/fsverity.h> #include <linux/compiler.h> /* * The fourth extended filesystem constants/structures */ /* * with AGGRESSIVE_CHECK allocator runs consistency checks over * structures. these checks slow things down a lot */ #define AGGRESSIVE_CHECK__ /* * with DOUBLE_CHECK defined mballoc creates persistent in-core * bitmaps, maintains and uses them to check for double allocations */ #define DOUBLE_CHECK__ /* * Define EXT4FS_DEBUG to produce debug messages */ #undef EXT4FS_DEBUG /* * Debug code */ #ifdef EXT4FS_DEBUG #define ext4_debug(f, a...) \ do { \ printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:", \ __FILE__, __LINE__, __func__); \ printk(KERN_DEBUG f, ## a); \ } while (0) #else #define ext4_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif /* * Turn on EXT_DEBUG to enable ext4_ext_show_path/leaf/move in extents.c */ #define EXT_DEBUG__ /* * Dynamic printk for controlled extents debugging. */ #ifdef CONFIG_EXT4_DEBUG #define ext_debug(ino, fmt, ...) \ pr_debug("[%s/%d] EXT4-fs (%s): ino %lu: (%s, %d): %s:" fmt, \ current->comm, task_pid_nr(current), \ ino->i_sb->s_id, ino->i_ino, __FILE__, __LINE__, \ __func__, ##__VA_ARGS__) #else #define ext_debug(ino, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif #define ASSERT(assert) \ do { \ if (unlikely(!(assert))) { \ printk(KERN_EMERG \ "Assertion failure in %s() at %s:%d: '%s'\n", \ __func__, __FILE__, __LINE__, #assert); \ BUG(); \ } \ } while (0) /* data type for block offset of block group */ typedef int ext4_grpblk_t; /* data type for filesystem-wide blocks number */ typedef unsigned long long ext4_fsblk_t; /* data type for file logical block number */ typedef __u32 ext4_lblk_t; /* data type for block group number */ typedef unsigned int ext4_group_t; enum SHIFT_DIRECTION { SHIFT_LEFT = 0, SHIFT_RIGHT, }; /* * For each criteria, mballoc has slightly different way of finding * the required blocks nad usually, higher the criteria the slower the * allocation. We start at lower criterias and keep falling back to * higher ones if we are not able to find any blocks. Lower (earlier) * criteria are faster. */ enum criteria { /* * Used when number of blocks needed is a power of 2. This * doesn't trigger any disk IO except prefetch and is the * fastest criteria. */ CR_POWER2_ALIGNED, /* * Tries to lookup in-memory data structures to find the most * suitable group that satisfies goal request. No disk IO * except block prefetch. */ CR_GOAL_LEN_FAST, /* * Same as CR_GOAL_LEN_FAST but is allowed to reduce the goal * length to the best available length for faster allocation. */ CR_BEST_AVAIL_LEN, /* * Reads each block group sequentially, performing disk IO if * necessary, to find find_suitable block group. Tries to * allocate goal length but might trim the request if nothing * is found after enough tries. */ CR_GOAL_LEN_SLOW, /* * Finds the first free set of blocks and allocates * those. This is only used in rare cases when * CR_GOAL_LEN_SLOW also fails to allocate anything. */ CR_ANY_FREE, /* * Number of criterias defined. */ EXT4_MB_NUM_CRS }; /* * Flags used in mballoc's allocation_context flags field. * * Also used to show what's going on for debugging purposes when the * flag field is exported via the traceport interface */ /* prefer goal again. length */ #define EXT4_MB_HINT_MERGE 0x0001 /* blocks already reserved */ #define EXT4_MB_HINT_RESERVED 0x0002 /* metadata is being allocated */ #define EXT4_MB_HINT_METADATA 0x0004 /* first blocks in the file */ #define EXT4_MB_HINT_FIRST 0x0008 /* search for the best chunk */ #define EXT4_MB_HINT_BEST 0x0010 /* data is being allocated */ #define EXT4_MB_HINT_DATA 0x0020 /* don't preallocate (for tails) */ #define EXT4_MB_HINT_NOPREALLOC 0x0040 /* allocate for locality group */ #define EXT4_MB_HINT_GROUP_ALLOC 0x0080 /* allocate goal blocks or none */ #define EXT4_MB_HINT_GOAL_ONLY 0x0100 /* goal is meaningful */ #define EXT4_MB_HINT_TRY_GOAL 0x0200 /* blocks already pre-reserved by delayed allocation */ #define EXT4_MB_DELALLOC_RESERVED 0x0400 /* We are doing stream allocation */ #define EXT4_MB_STREAM_ALLOC 0x0800 /* Use reserved root blocks if needed */ #define EXT4_MB_USE_ROOT_BLOCKS 0x1000 /* Use blocks from reserved pool */ #define EXT4_MB_USE_RESERVED 0x2000 /* Do strict check for free blocks while retrying block allocation */ #define EXT4_MB_STRICT_CHECK 0x4000 /* Large fragment size list lookup succeeded at least once for * CR_POWER2_ALIGNED */ #define EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED 0x8000 /* Avg fragment size rb tree lookup succeeded at least once for * CR_GOAL_LEN_FAST */ #define EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED 0x00010000 /* Avg fragment size rb tree lookup succeeded at least once for * CR_BEST_AVAIL_LEN */ #define EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED 0x00020000 struct ext4_allocation_request { /* target inode for block we're allocating */ struct inode *inode; /* how many blocks we want to allocate */ unsigned int len; /* logical block in target inode */ ext4_lblk_t logical; /* the closest logical allocated block to the left */ ext4_lblk_t lleft; /* the closest logical allocated block to the right */ ext4_lblk_t lright; /* phys. target (a hint) */ ext4_fsblk_t goal; /* phys. block for the closest logical allocated block to the left */ ext4_fsblk_t pleft; /* phys. block for the closest logical allocated block to the right */ ext4_fsblk_t pright; /* flags. see above EXT4_MB_HINT_* */ unsigned int flags; }; /* * Logical to physical block mapping, used by ext4_map_blocks() * * This structure is used to pass requests into ext4_map_blocks() as * well as to store the information returned by ext4_map_blocks(). It * takes less room on the stack than a struct buffer_head. */ #define EXT4_MAP_NEW BIT(BH_New) #define EXT4_MAP_MAPPED BIT(BH_Mapped) #define EXT4_MAP_UNWRITTEN BIT(BH_Unwritten) #define EXT4_MAP_BOUNDARY BIT(BH_Boundary) #define EXT4_MAP_DELAYED BIT(BH_Delay) #define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\ EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\ EXT4_MAP_DELAYED) struct ext4_map_blocks { ext4_fsblk_t m_pblk; ext4_lblk_t m_lblk; unsigned int m_len; unsigned int m_flags; }; /* * Block validity checking, system zone rbtree. */ struct ext4_system_blocks { struct rb_root root; struct rcu_head rcu; }; /* * Flags for ext4_io_end->flags */ #define EXT4_IO_END_UNWRITTEN 0x0001 struct ext4_io_end_vec { struct list_head list; /* list of io_end_vec */ loff_t offset; /* offset in the file */ ssize_t size; /* size of the extent */ }; /* * For converting unwritten extents on a work queue. 'handle' is used for * buffered writeback. */ typedef struct ext4_io_end { struct list_head list; /* per-file finished IO list */ handle_t *handle; /* handle reserved for extent * conversion */ struct inode *inode; /* file being written to */ struct bio *bio; /* Linked list of completed * bios covering the extent */ unsigned int flag; /* unwritten or not */ refcount_t count; /* reference counter */ struct list_head list_vec; /* list of ext4_io_end_vec */ } ext4_io_end_t; struct ext4_io_submit { struct writeback_control *io_wbc; struct bio *io_bio; ext4_io_end_t *io_end; sector_t io_next_block; }; /* * Special inodes numbers */ #define EXT4_BAD_INO 1 /* Bad blocks inode */ #define EXT4_ROOT_INO 2 /* Root inode */ #define EXT4_USR_QUOTA_INO 3 /* User quota inode */ #define EXT4_GRP_QUOTA_INO 4 /* Group quota inode */ #define EXT4_BOOT_LOADER_INO 5 /* Boot loader inode */ #define EXT4_UNDEL_DIR_INO 6 /* Undelete directory inode */ #define EXT4_RESIZE_INO 7 /* Reserved group descriptors inode */ #define EXT4_JOURNAL_INO 8 /* Journal inode */ /* First non-reserved inode for old ext4 filesystems */ #define EXT4_GOOD_OLD_FIRST_INO 11 /* * Maximal count of links to a file */ #define EXT4_LINK_MAX 65000 /* * Macro-instructions used to manage several block sizes */ #define EXT4_MIN_BLOCK_SIZE 1024 #define EXT4_MAX_BLOCK_SIZE 65536 #define EXT4_MIN_BLOCK_LOG_SIZE 10 #define EXT4_MAX_BLOCK_LOG_SIZE 16 #define EXT4_MAX_CLUSTER_LOG_SIZE 30 #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) #else # define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size) #endif #define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof(__u32)) #define EXT4_CLUSTER_SIZE(s) (EXT4_BLOCK_SIZE(s) << \ EXT4_SB(s)->s_cluster_bits) #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) # define EXT4_CLUSTER_BITS(s) (EXT4_SB(s)->s_cluster_bits) #else # define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10) #endif #ifdef __KERNEL__ #define EXT4_ADDR_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_addr_per_block_bits) #define EXT4_INODE_SIZE(s) (EXT4_SB(s)->s_inode_size) #define EXT4_FIRST_INO(s) (EXT4_SB(s)->s_first_ino) #else #define EXT4_INODE_SIZE(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \ EXT4_GOOD_OLD_INODE_SIZE : \ (s)->s_inode_size) #define EXT4_FIRST_INO(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \ EXT4_GOOD_OLD_FIRST_INO : \ (s)->s_first_ino) #endif #define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits))) #define EXT4_MAX_BLOCKS(size, offset, blkbits) \ ((EXT4_BLOCK_ALIGN(size + offset, blkbits) >> blkbits) - (offset >> \ blkbits)) /* Translate a block number to a cluster number */ #define EXT4_B2C(sbi, blk) ((blk) >> (sbi)->s_cluster_bits) /* Translate a cluster number to a block number */ #define EXT4_C2B(sbi, cluster) ((cluster) << (sbi)->s_cluster_bits) /* Translate # of blks to # of clusters */ #define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \ (sbi)->s_cluster_bits) /* Mask out the low bits to get the starting block of the cluster */ #define EXT4_PBLK_CMASK(s, pblk) ((pblk) & \ ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1)) #define EXT4_LBLK_CMASK(s, lblk) ((lblk) & \ ~((ext4_lblk_t) (s)->s_cluster_ratio - 1)) /* Fill in the low bits to get the last block of the cluster */ #define EXT4_LBLK_CFILL(sbi, lblk) ((lblk) | \ ((ext4_lblk_t) (sbi)->s_cluster_ratio - 1)) /* Get the cluster offset */ #define EXT4_PBLK_COFF(s, pblk) ((pblk) & \ ((ext4_fsblk_t) (s)->s_cluster_ratio - 1)) #define EXT4_LBLK_COFF(s, lblk) ((lblk) & \ ((ext4_lblk_t) (s)->s_cluster_ratio - 1)) /* * Structure of a blocks group descriptor */ struct ext4_group_desc { __le32 bg_block_bitmap_lo; /* Blocks bitmap block */ __le32 bg_inode_bitmap_lo; /* Inodes bitmap block */ __le32 bg_inode_table_lo; /* Inodes table block */ __le16 bg_free_blocks_count_lo;/* Free blocks count */ __le16 bg_free_inodes_count_lo;/* Free inodes count */ __le16 bg_used_dirs_count_lo; /* Directories count */ __le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */ __le32 bg_exclude_bitmap_lo; /* Exclude bitmap for snapshots */ __le16 bg_block_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+bbitmap) LE */ __le16 bg_inode_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+ibitmap) LE */ __le16 bg_itable_unused_lo; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ __le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ __le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */ __le32 bg_inode_table_hi; /* Inodes table block MSB */ __le16 bg_free_blocks_count_hi;/* Free blocks count MSB */ __le16 bg_free_inodes_count_hi;/* Free inodes count MSB */ __le16 bg_used_dirs_count_hi; /* Directories count MSB */ __le16 bg_itable_unused_hi; /* Unused inodes count MSB */ __le32 bg_exclude_bitmap_hi; /* Exclude bitmap block MSB */ __le16 bg_block_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+bbitmap) BE */ __le16 bg_inode_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+ibitmap) BE */ __u32 bg_reserved; }; #define EXT4_BG_INODE_BITMAP_CSUM_HI_END \ (offsetof(struct ext4_group_desc, bg_inode_bitmap_csum_hi) + \ sizeof(__le16)) #define EXT4_BG_BLOCK_BITMAP_CSUM_HI_END \ (offsetof(struct ext4_group_desc, bg_block_bitmap_csum_hi) + \ sizeof(__le16)) /* * Structure of a flex block group info */ struct flex_groups { atomic64_t free_clusters; atomic_t free_inodes; atomic_t used_dirs; }; #define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */ #define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */ #define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */ /* * Macro-instructions used to manage group descriptors */ #define EXT4_MIN_DESC_SIZE 32 #define EXT4_MIN_DESC_SIZE_64BIT 64 #define EXT4_MAX_DESC_SIZE EXT4_MIN_BLOCK_SIZE #define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size) #ifdef __KERNEL__ # define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group) # define EXT4_CLUSTERS_PER_GROUP(s) (EXT4_SB(s)->s_clusters_per_group) # define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block) # define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group) # define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits) #else # define EXT4_BLOCKS_PER_GROUP(s) ((s)->s_blocks_per_group) # define EXT4_DESC_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s)) # define EXT4_INODES_PER_GROUP(s) ((s)->s_inodes_per_group) #endif /* * Constants relative to the data blocks */ #define EXT4_NDIR_BLOCKS 12 #define EXT4_IND_BLOCK EXT4_NDIR_BLOCKS #define EXT4_DIND_BLOCK (EXT4_IND_BLOCK + 1) #define EXT4_TIND_BLOCK (EXT4_DIND_BLOCK + 1) #define EXT4_N_BLOCKS (EXT4_TIND_BLOCK + 1) /* * Inode flags */ #define EXT4_SECRM_FL 0x00000001 /* Secure deletion */ #define EXT4_UNRM_FL 0x00000002 /* Undelete */ #define EXT4_COMPR_FL 0x00000004 /* Compress file */ #define EXT4_SYNC_FL 0x00000008 /* Synchronous updates */ #define EXT4_IMMUTABLE_FL 0x00000010 /* Immutable file */ #define EXT4_APPEND_FL 0x00000020 /* writes to file may only append */ #define EXT4_NODUMP_FL 0x00000040 /* do not dump file */ #define EXT4_NOATIME_FL 0x00000080 /* do not update atime */ /* Reserved for compression usage... */ #define EXT4_DIRTY_FL 0x00000100 #define EXT4_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ #define EXT4_NOCOMPR_FL 0x00000400 /* Don't compress */ /* nb: was previously EXT2_ECOMPR_FL */ #define EXT4_ENCRYPT_FL 0x00000800 /* encrypted file */ /* End compression flags --- maybe not all used */ #define EXT4_INDEX_FL 0x00001000 /* hash-indexed directory */ #define EXT4_IMAGIC_FL 0x00002000 /* AFS directory */ #define EXT4_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ #define EXT4_NOTAIL_FL 0x00008000 /* file tail should not be merged */ #define EXT4_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ #define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ #define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */ #define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ #define EXT4_VERITY_FL 0x00100000 /* Verity protected inode */ #define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */ /* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */ #define EXT4_DAX_FL 0x02000000 /* Inode is DAX */ #define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ #define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded directory */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ /* User modifiable flags */ #define EXT4_FL_USER_MODIFIABLE (EXT4_SECRM_FL | \ EXT4_UNRM_FL | \ EXT4_COMPR_FL | \ EXT4_SYNC_FL | \ EXT4_IMMUTABLE_FL | \ EXT4_APPEND_FL | \ EXT4_NODUMP_FL | \ EXT4_NOATIME_FL | \ EXT4_JOURNAL_DATA_FL | \ EXT4_NOTAIL_FL | \ EXT4_DIRSYNC_FL | \ EXT4_TOPDIR_FL | \ EXT4_EXTENTS_FL | \ 0x00400000 /* EXT4_EOFBLOCKS_FL */ | \ EXT4_DAX_FL | \ EXT4_PROJINHERIT_FL | \ EXT4_CASEFOLD_FL) /* User visible flags */ #define EXT4_FL_USER_VISIBLE (EXT4_FL_USER_MODIFIABLE | \ EXT4_DIRTY_FL | \ EXT4_COMPRBLK_FL | \ EXT4_NOCOMPR_FL | \ EXT4_ENCRYPT_FL | \ EXT4_INDEX_FL | \ EXT4_VERITY_FL | \ EXT4_INLINE_DATA_FL) /* Flags that should be inherited by new inodes from their parent. */ #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\ EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\ EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\ EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\ EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\ EXT4_DAX_FL) /* Flags that are appropriate for regular files (all but dir-specific ones). */ #define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\ EXT4_PROJINHERIT_FL)) /* Flags that are appropriate for non-directories/regular files. */ #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL) /* The only flags that should be swapped */ #define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL) /* Flags which are mutually exclusive to DAX */ #define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\ EXT4_JOURNAL_DATA_FL | EXT4_INLINE_DATA_FL) /* Mask out flags that are inappropriate for the given type of inode. */ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags) { if (S_ISDIR(mode)) return flags; else if (S_ISREG(mode)) return flags & EXT4_REG_FLMASK; else return flags & EXT4_OTHER_FLMASK; } /* * Inode flags used for atomic set/get */ enum { EXT4_INODE_SECRM = 0, /* Secure deletion */ EXT4_INODE_UNRM = 1, /* Undelete */ EXT4_INODE_COMPR = 2, /* Compress file */ EXT4_INODE_SYNC = 3, /* Synchronous updates */ EXT4_INODE_IMMUTABLE = 4, /* Immutable file */ EXT4_INODE_APPEND = 5, /* writes to file may only append */ EXT4_INODE_NODUMP = 6, /* do not dump file */ EXT4_INODE_NOATIME = 7, /* do not update atime */ /* Reserved for compression usage... */ EXT4_INODE_DIRTY = 8, EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */ EXT4_INODE_NOCOMPR = 10, /* Don't compress */ EXT4_INODE_ENCRYPT = 11, /* Encrypted file */ /* End compression flags --- maybe not all used */ EXT4_INODE_INDEX = 12, /* hash-indexed directory */ EXT4_INODE_IMAGIC = 13, /* AFS directory */ EXT4_INODE_JOURNAL_DATA = 14, /* file data should be journaled */ EXT4_INODE_NOTAIL = 15, /* file tail should not be merged */ EXT4_INODE_DIRSYNC = 16, /* dirsync behaviour (directories only) */ EXT4_INODE_TOPDIR = 17, /* Top of directory hierarchies*/ EXT4_INODE_HUGE_FILE = 18, /* Set to each huge file */ EXT4_INODE_EXTENTS = 19, /* Inode uses extents */ EXT4_INODE_VERITY = 20, /* Verity protected inode */ EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */ /* 22 was formerly EXT4_INODE_EOFBLOCKS */ EXT4_INODE_DAX = 25, /* Inode is DAX */ EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */ EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */ EXT4_INODE_CASEFOLD = 30, /* Casefolded directory */ EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */ }; /* * Since it's pretty easy to mix up bit numbers and hex values, we use a * build-time check to make sure that EXT4_XXX_FL is consistent with respect to * EXT4_INODE_XXX. If all is well, the macros will be dropped, so, it won't cost * any extra space in the compiled kernel image, otherwise, the build will fail. * It's important that these values are the same, since we are using * EXT4_INODE_XXX to test for flag values, but EXT4_XXX_FL must be consistent * with the values of FS_XXX_FL defined in include/linux/fs.h and the on-disk * values found in ext2, ext3 and ext4 filesystems, and of course the values * defined in e2fsprogs. * * It's not paranoia if the Murphy's Law really *is* out to get you. :-) */ #define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1U << EXT4_INODE_##FLAG)) #define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG)) static inline void ext4_check_flag_values(void) { CHECK_FLAG_VALUE(SECRM); CHECK_FLAG_VALUE(UNRM); CHECK_FLAG_VALUE(COMPR); CHECK_FLAG_VALUE(SYNC); CHECK_FLAG_VALUE(IMMUTABLE); CHECK_FLAG_VALUE(APPEND); CHECK_FLAG_VALUE(NODUMP); CHECK_FLAG_VALUE(NOATIME); CHECK_FLAG_VALUE(DIRTY); CHECK_FLAG_VALUE(COMPRBLK); CHECK_FLAG_VALUE(NOCOMPR); CHECK_FLAG_VALUE(ENCRYPT); CHECK_FLAG_VALUE(INDEX); CHECK_FLAG_VALUE(IMAGIC); CHECK_FLAG_VALUE(JOURNAL_DATA); CHECK_FLAG_VALUE(NOTAIL); CHECK_FLAG_VALUE(DIRSYNC); CHECK_FLAG_VALUE(TOPDIR); CHECK_FLAG_VALUE(HUGE_FILE); CHECK_FLAG_VALUE(EXTENTS); CHECK_FLAG_VALUE(VERITY); CHECK_FLAG_VALUE(EA_INODE); CHECK_FLAG_VALUE(INLINE_DATA); CHECK_FLAG_VALUE(PROJINHERIT); CHECK_FLAG_VALUE(CASEFOLD); CHECK_FLAG_VALUE(RESERVED); } #if defined(__KERNEL__) && defined(CONFIG_COMPAT) struct compat_ext4_new_group_input { u32 group; compat_u64 block_bitmap; compat_u64 inode_bitmap; compat_u64 inode_table; u32 blocks_count; u16 reserved_blocks; u16 unused; }; #endif /* The struct ext4_new_group_input in kernel space, with free_blocks_count */ struct ext4_new_group_data { __u32 group; __u64 block_bitmap; __u64 inode_bitmap; __u64 inode_table; __u32 blocks_count; __u16 reserved_blocks; __u16 mdata_blocks; __u32 free_clusters_count; }; /* Indexes used to index group tables in ext4_new_group_data */ enum { BLOCK_BITMAP = 0, /* block bitmap */ INODE_BITMAP, /* inode bitmap */ INODE_TABLE, /* inode tables */ GROUP_TABLE_COUNT, }; /* * Flags used by ext4_map_blocks() */ /* Allocate any needed blocks and/or convert an unwritten extent to be an initialized ext4 */ #define EXT4_GET_BLOCKS_CREATE 0x0001 /* Request the creation of an unwritten extent */ #define EXT4_GET_BLOCKS_UNWRIT_EXT 0x0002 #define EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT (EXT4_GET_BLOCKS_UNWRIT_EXT|\ EXT4_GET_BLOCKS_CREATE) /* Caller is from the delayed allocation writeout path * finally doing the actual allocation of delayed blocks */ #define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004 /* caller is from the direct IO path, request to creation of an unwritten extents if not allocated, split the unwritten extent if blocks has been preallocated already*/ #define EXT4_GET_BLOCKS_PRE_IO 0x0008 #define EXT4_GET_BLOCKS_CONVERT 0x0010 #define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT) /* Convert extent to initialized after IO complete */ #define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT) /* Eventual metadata allocation (due to growing extent tree) * should not fail, so try to use reserved blocks for that.*/ #define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020 /* Don't normalize allocation size (used for fallocate) */ #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 /* Convert written extents to unwritten */ #define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0100 /* Write zeros to newly created written extents */ #define EXT4_GET_BLOCKS_ZERO 0x0200 #define EXT4_GET_BLOCKS_CREATE_ZERO (EXT4_GET_BLOCKS_CREATE |\ EXT4_GET_BLOCKS_ZERO) /* Caller will submit data before dropping transaction handle. This * allows jbd2 to avoid submitting data before commit. */ #define EXT4_GET_BLOCKS_IO_SUBMIT 0x0400 /* Caller is in the atomic contex, find extent if it has been cached */ #define EXT4_GET_BLOCKS_CACHED_NOWAIT 0x0800 /* * The bit position of these flags must not overlap with any of the * EXT4_GET_BLOCKS_*. They are used by ext4_find_extent(), * read_extent_tree_block(), ext4_split_extent_at(), * ext4_ext_insert_extent(), and ext4_ext_create_new_leaf(). * EXT4_EX_NOCACHE is used to indicate that the we shouldn't be * caching the extents when reading from the extent tree while a * truncate or punch hole operation is in progress. */ #define EXT4_EX_NOCACHE 0x40000000 #define EXT4_EX_FORCE_CACHE 0x20000000 #define EXT4_EX_NOFAIL 0x10000000 /* * Flags used by ext4_free_blocks */ #define EXT4_FREE_BLOCKS_METADATA 0x0001 #define EXT4_FREE_BLOCKS_FORGET 0x0002 #define EXT4_FREE_BLOCKS_VALIDATED 0x0004 #define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008 #define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020 #define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER 0x0040 #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* * ioctl commands in 32 bit emulation */ #define EXT4_IOC32_GETVERSION _IOR('f', 3, int) #define EXT4_IOC32_SETVERSION _IOW('f', 4, int) #define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int) #define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int) #define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) #define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input) #define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION #define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION #endif /* Max physical block we can address w/o extents */ #define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF /* Max logical block we can support */ #define EXT4_MAX_LOGICAL_BLOCK 0xFFFFFFFE /* * Structure of an inode on the disk */ struct ext4_inode { __le16 i_mode; /* File mode */ __le16 i_uid; /* Low 16 bits of Owner Uid */ __le32 i_size_lo; /* Size in bytes */ __le32 i_atime; /* Access time */ __le32 i_ctime; /* Inode Change time */ __le32 i_mtime; /* Modification time */ __le32 i_dtime; /* Deletion Time */ __le16 i_gid; /* Low 16 bits of Group Id */ __le16 i_links_count; /* Links count */ __le32 i_blocks_lo; /* Blocks count */ __le32 i_flags; /* File flags */ union { struct { __le32 l_i_version; } linux1; struct { __u32 h_i_translator; } hurd1; struct { __u32 m_i_reserved1; } masix1; } osd1; /* OS dependent 1 */ __le32 i_block[EXT4_N_BLOCKS];/* Pointers to blocks */ __le32 i_generation; /* File version (for NFS) */ __le32 i_file_acl_lo; /* File ACL */ __le32 i_size_high; __le32 i_obso_faddr; /* Obsoleted fragment address */ union { struct { __le16 l_i_blocks_high; /* were l_i_reserved1 */ __le16 l_i_file_acl_high; __le16 l_i_uid_high; /* these 2 fields */ __le16 l_i_gid_high; /* were reserved2[0] */ __le16 l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */ __le16 l_i_reserved; } linux2; struct { __le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */ __u16 h_i_mode_high; __u16 h_i_uid_high; __u16 h_i_gid_high; __u32 h_i_author; } hurd2; struct { __le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */ __le16 m_i_file_acl_high; __u32 m_i_reserved2[2]; } masix2; } osd2; /* OS dependent 2 */ __le16 i_extra_isize; __le16 i_checksum_hi; /* crc32c(uuid+inum+inode) BE */ __le32 i_ctime_extra; /* extra Change time (nsec << 2 | epoch) */ __le32 i_mtime_extra; /* extra Modification time(nsec << 2 | epoch) */ __le32 i_atime_extra; /* extra Access time (nsec << 2 | epoch) */ __le32 i_crtime; /* File Creation time */ __le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */ __le32 i_version_hi; /* high 32 bits for 64-bit version */ __le32 i_projid; /* Project ID */ }; #define EXT4_EPOCH_BITS 2 #define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1) #define EXT4_NSEC_MASK (~0UL << EXT4_EPOCH_BITS) /* * Extended fields will fit into an inode if the filesystem was formatted * with large inodes (-I 256 or larger) and there are not currently any EAs * consuming all of the available space. For new inodes we always reserve * enough space for the kernel's known extended fields, but for inodes * created with an old kernel this might not have been the case. None of * the extended inode fields is critical for correct filesystem operation. * This macro checks if a certain field fits in the inode. Note that * inode-size = GOOD_OLD_INODE_SIZE + i_extra_isize */ #define EXT4_FITS_IN_INODE(ext4_inode, einode, field) \ ((offsetof(typeof(*ext4_inode), field) + \ sizeof((ext4_inode)->field)) \ <= (EXT4_GOOD_OLD_INODE_SIZE + \ (einode)->i_extra_isize)) \ /* * We use an encoding that preserves the times for extra epoch "00": * * extra msb of adjust for signed * epoch 32-bit 32-bit tv_sec to * bits time decoded 64-bit tv_sec 64-bit tv_sec valid time range * 0 0 1 -0x80000000..-0x00000001 0x000000000 1901-12-13..1969-12-31 * 0 0 0 0x000000000..0x07fffffff 0x000000000 1970-01-01..2038-01-19 * 0 1 1 0x080000000..0x0ffffffff 0x100000000 2038-01-19..2106-02-07 * 0 1 0 0x100000000..0x17fffffff 0x100000000 2106-02-07..2174-02-25 * 1 0 1 0x180000000..0x1ffffffff 0x200000000 2174-02-25..2242-03-16 * 1 0 0 0x200000000..0x27fffffff 0x200000000 2242-03-16..2310-04-04 * 1 1 1 0x280000000..0x2ffffffff 0x300000000 2310-04-04..2378-04-22 * 1 1 0 0x300000000..0x37fffffff 0x300000000 2378-04-22..2446-05-10 * * Note that previous versions of the kernel on 64-bit systems would * incorrectly use extra epoch bits 1,1 for dates between 1901 and * 1970. e2fsck will correct this, assuming that it is run on the * affected filesystem before 2242. */ static inline __le32 ext4_encode_extra_time(struct timespec64 ts) { u32 extra = ((ts.tv_sec - (s32)ts.tv_sec) >> 32) & EXT4_EPOCH_MASK; return cpu_to_le32(extra | (ts.tv_nsec << EXT4_EPOCH_BITS)); } static inline struct timespec64 ext4_decode_extra_time(__le32 base, __le32 extra) { struct timespec64 ts = { .tv_sec = (signed)le32_to_cpu(base) }; if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK))) ts.tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32; ts.tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; return ts; } #define EXT4_INODE_SET_XTIME_VAL(xtime, inode, raw_inode, ts) \ do { \ if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) { \ (raw_inode)->xtime = cpu_to_le32((ts).tv_sec); \ (raw_inode)->xtime ## _extra = ext4_encode_extra_time(ts); \ } else \ (raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (ts).tv_sec, S32_MIN, S32_MAX)); \ } while (0) #define EXT4_INODE_SET_ATIME(inode, raw_inode) \ EXT4_INODE_SET_XTIME_VAL(i_atime, inode, raw_inode, inode_get_atime(inode)) #define EXT4_INODE_SET_MTIME(inode, raw_inode) \ EXT4_INODE_SET_XTIME_VAL(i_mtime, inode, raw_inode, inode_get_mtime(inode)) #define EXT4_INODE_SET_CTIME(inode, raw_inode) \ EXT4_INODE_SET_XTIME_VAL(i_ctime, inode, raw_inode, inode_get_ctime(inode)) #define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ EXT4_INODE_SET_XTIME_VAL(xtime, &((einode)->vfs_inode), \ raw_inode, (einode)->xtime) #define EXT4_INODE_GET_XTIME_VAL(xtime, inode, raw_inode) \ (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra) ? \ ext4_decode_extra_time((raw_inode)->xtime, \ (raw_inode)->xtime ## _extra) : \ (struct timespec64) { \ .tv_sec = (signed)le32_to_cpu((raw_inode)->xtime) \ }) #define EXT4_INODE_GET_ATIME(inode, raw_inode) \ do { \ inode_set_atime_to_ts(inode, \ EXT4_INODE_GET_XTIME_VAL(i_atime, inode, raw_inode)); \ } while (0) #define EXT4_INODE_GET_MTIME(inode, raw_inode) \ do { \ inode_set_mtime_to_ts(inode, \ EXT4_INODE_GET_XTIME_VAL(i_mtime, inode, raw_inode)); \ } while (0) #define EXT4_INODE_GET_CTIME(inode, raw_inode) \ do { \ inode_set_ctime_to_ts(inode, \ EXT4_INODE_GET_XTIME_VAL(i_ctime, inode, raw_inode)); \ } while (0) #define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \ do { \ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ (einode)->xtime = \ EXT4_INODE_GET_XTIME_VAL(xtime, &(einode->vfs_inode), \ raw_inode); \ else \ (einode)->xtime = (struct timespec64){0, 0}; \ } while (0) #define i_disk_version osd1.linux1.l_i_version #if defined(__KERNEL__) || defined(__linux__) #define i_reserved1 osd1.linux1.l_i_reserved1 #define i_file_acl_high osd2.linux2.l_i_file_acl_high #define i_blocks_high osd2.linux2.l_i_blocks_high #define i_uid_low i_uid #define i_gid_low i_gid #define i_uid_high osd2.linux2.l_i_uid_high #define i_gid_high osd2.linux2.l_i_gid_high #define i_checksum_lo osd2.linux2.l_i_checksum_lo #elif defined(__GNU__) #define i_translator osd1.hurd1.h_i_translator #define i_uid_high osd2.hurd2.h_i_uid_high #define i_gid_high osd2.hurd2.h_i_gid_high #define i_author osd2.hurd2.h_i_author #elif defined(__masix__) #define i_reserved1 osd1.masix1.m_i_reserved1 #define i_file_acl_high osd2.masix2.m_i_file_acl_high #define i_reserved2 osd2.masix2.m_i_reserved2 #endif /* defined(__KERNEL__) || defined(__linux__) */ #include "extents_status.h" #include "fast_commit.h" /* * Lock subclasses for i_data_sem in the ext4_inode_info structure. * * These are needed to avoid lockdep false positives when we need to * allocate blocks to the quota inode during ext4_map_blocks(), while * holding i_data_sem for a normal (non-quota) inode. Since we don't * do quota tracking for the quota inode, this avoids deadlock (as * well as infinite recursion, since it isn't turtles all the way * down...) * * I_DATA_SEM_NORMAL - Used for most inodes * I_DATA_SEM_OTHER - Used by move_inode.c for the second normal inode * where the second inode has larger inode number * than the first * I_DATA_SEM_QUOTA - Used for quota inodes only * I_DATA_SEM_EA - Used for ea_inodes only */ enum { I_DATA_SEM_NORMAL = 0, I_DATA_SEM_OTHER, I_DATA_SEM_QUOTA, I_DATA_SEM_EA }; /* * fourth extended file system inode data in memory */ struct ext4_inode_info { __le32 i_data[15]; /* unconverted */ __u32 i_dtime; ext4_fsblk_t i_file_acl; /* * i_block_group is the number of the block group which contains * this file's inode. Constant across the lifetime of the inode, * it is used for making block allocation decisions - we try to * place a file's data blocks near its inode block, and new inodes * near to their parent directory's inode. */ ext4_group_t i_block_group; ext4_lblk_t i_dir_start_lookup; #if (BITS_PER_LONG < 64) unsigned long i_state_flags; /* Dynamic state flags */ #endif unsigned long i_flags; /* * Extended attributes can be read independently of the main file * data. Taking i_rwsem even when reading would cause contention * between readers of EAs and writers of regular file data, so * instead we synchronize on xattr_sem when reading or changing * EAs. */ struct rw_semaphore xattr_sem; /* * Inodes with EXT4_STATE_ORPHAN_FILE use i_orphan_idx. Otherwise * i_orphan is used. */ union { struct list_head i_orphan; /* unlinked but open inodes */ unsigned int i_orphan_idx; /* Index in orphan file */ }; /* Fast commit related info */ /* For tracking dentry create updates */ struct list_head i_fc_dilist; struct list_head i_fc_list; /* * inodes that need fast commit * protected by sbi->s_fc_lock. */ /* Start of lblk range that needs to be committed in this fast commit */ ext4_lblk_t i_fc_lblk_start; /* End of lblk range that needs to be committed in this fast commit */ ext4_lblk_t i_fc_lblk_len; /* Number of ongoing updates on this inode */ atomic_t i_fc_updates; /* Fast commit wait queue for this inode */ wait_queue_head_t i_fc_wait; /* Protect concurrent accesses on i_fc_lblk_start, i_fc_lblk_len */ struct mutex i_fc_lock; /* * i_disksize keeps track of what the inode size is ON DISK, not * in memory. During truncate, i_size is set to the new size by * the VFS prior to calling ext4_truncate(), but the filesystem won't * set i_disksize to 0 until the truncate is actually under way. * * The intent is that i_disksize always represents the blocks which * are used by this file. This allows recovery to restart truncate * on orphans if we crash during truncate. We actually write i_disksize * into the on-disk inode when writing inodes out, instead of i_size. * * The only time when i_disksize and i_size may be different is when * a truncate is in progress. The only things which change i_disksize * are ext4_get_block (growth) and ext4_truncate (shrinkth). */ loff_t i_disksize; /* * i_data_sem is for serialising ext4_truncate() against * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's * data tree are chopped off during truncate. We can't do that in * ext4 because whenever we perform intermediate commits during * truncate, the inode and all the metadata blocks *must* be in a * consistent state which allows truncation of the orphans to restart * during recovery. Hence we must fix the get_block-vs-truncate race * by other means, so we have i_data_sem. */ struct rw_semaphore i_data_sem; struct inode vfs_inode; struct jbd2_inode *jinode; spinlock_t i_raw_lock; /* protects updates to the raw inode */ /* * File creation time. Its function is same as that of * struct timespec64 i_{a,c,m}time in the generic inode. */ struct timespec64 i_crtime; /* mballoc */ atomic_t i_prealloc_active; struct rb_root i_prealloc_node; rwlock_t i_prealloc_lock; /* extents status tree */ struct ext4_es_tree i_es_tree; rwlock_t i_es_lock; struct list_head i_es_list; unsigned int i_es_all_nr; /* protected by i_es_lock */ unsigned int i_es_shk_nr; /* protected by i_es_lock */ ext4_lblk_t i_es_shrink_lblk; /* Offset where we start searching for extents to shrink. Protected by i_es_lock */ /* ialloc */ ext4_group_t i_last_alloc_group; /* allocation reservation info for delalloc */ /* In case of bigalloc, this refer to clusters rather than blocks */ unsigned int i_reserved_data_blocks; /* pending cluster reservations for bigalloc file systems */ struct ext4_pending_tree i_pending_tree; /* on-disk additional length */ __u16 i_extra_isize; /* Indicate the inline data space. */ u16 i_inline_off; u16 i_inline_size; #ifdef CONFIG_QUOTA /* quota space reservation, managed internally by quota code */ qsize_t i_reserved_quota; #endif /* Lock protecting lists below */ spinlock_t i_completed_io_lock; /* * Completed IOs that need unwritten extents handling and have * transaction reserved */ struct list_head i_rsv_conversion_list; struct work_struct i_rsv_conversion_work; atomic_t i_unwritten; /* Nr. of inflight conversions pending */ spinlock_t i_block_reservation_lock; /* * Transactions that contain inode's metadata needed to complete * fsync and fdatasync, respectively. */ tid_t i_sync_tid; tid_t i_datasync_tid; #ifdef CONFIG_QUOTA struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif /* Precomputed uuid+inum+igen checksum for seeding inode checksums */ __u32 i_csum_seed; kprojid_t i_projid; }; /* * File system states */ #define EXT4_VALID_FS 0x0001 /* Unmounted cleanly */ #define EXT4_ERROR_FS 0x0002 /* Errors detected */ #define EXT4_ORPHAN_FS 0x0004 /* Orphans being recovered */ #define EXT4_FC_REPLAY 0x0020 /* Fast commit replay ongoing */ /* * Misc. filesystem flags */ #define EXT2_FLAGS_SIGNED_HASH 0x0001 /* Signed dirhash in use */ #define EXT2_FLAGS_UNSIGNED_HASH 0x0002 /* Unsigned dirhash in use */ #define EXT2_FLAGS_TEST_FILESYS 0x0004 /* to test development code */ /* * Mount flags set via mount options or defaults */ #define EXT4_MOUNT_NO_MBCACHE 0x00001 /* Do not use mbcache */ #define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ #define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ #define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ #define EXT4_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */ #define EXT4_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */ #define EXT4_MOUNT_ERRORS_MASK 0x00070 #define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ #define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ #ifdef CONFIG_FS_DAX #define EXT4_MOUNT_DAX_ALWAYS 0x00200 /* Direct Access */ #else #define EXT4_MOUNT_DAX_ALWAYS 0 #endif #define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ #define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ #define EXT4_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ #define EXT4_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */ #define EXT4_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */ #define EXT4_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ #define EXT4_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ #define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ #define EXT4_MOUNT_NO_AUTO_DA_ALLOC 0x10000 /* No auto delalloc mapping */ #define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */ #define EXT4_MOUNT_QUOTA 0x40000 /* Some quota option set */ #define EXT4_MOUNT_USRQUOTA 0x80000 /* "old" user quota, * enable enforcement for hidden * quota files */ #define EXT4_MOUNT_GRPQUOTA 0x100000 /* "old" group quota, enable * enforcement for hidden quota * files */ #define EXT4_MOUNT_PRJQUOTA 0x200000 /* Enable project quota * enforcement */ #define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */ #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */ #define EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS 0x4000000 #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ #define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */ #define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */ /* * Mount flags set either automatically (could not be set by mount option) * based on per file system feature or property or in special cases such as * distinguishing between explicit mount option definition and default. */ #define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly specified delalloc */ #define EXT4_MOUNT2_STD_GROUP_SIZE 0x00000002 /* We have standard group size of blocksize * 8 blocks */ #define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated file systems */ #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly specified journal checksum */ #define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */ #define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */ #define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */ #define EXT4_MOUNT2_MB_OPTIMIZE_SCAN 0x00000080 /* Optimize group * scanning in mballoc */ #define EXT4_MOUNT2_ABORT 0x00000100 /* Abort filesystem */ #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt #define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \ EXT4_MOUNT_##opt #define test_opt(sb, opt) (EXT4_SB(sb)->s_mount_opt & \ EXT4_MOUNT_##opt) #define clear_opt2(sb, opt) EXT4_SB(sb)->s_mount_opt2 &= \ ~EXT4_MOUNT2_##opt #define set_opt2(sb, opt) EXT4_SB(sb)->s_mount_opt2 |= \ EXT4_MOUNT2_##opt #define test_opt2(sb, opt) (EXT4_SB(sb)->s_mount_opt2 & \ EXT4_MOUNT2_##opt) #define ext4_test_and_set_bit __test_and_set_bit_le #define ext4_set_bit __set_bit_le #define ext4_test_and_clear_bit __test_and_clear_bit_le #define ext4_clear_bit __clear_bit_le #define ext4_test_bit test_bit_le #define ext4_find_next_zero_bit find_next_zero_bit_le #define ext4_find_next_bit find_next_bit_le extern void mb_set_bits(void *bm, int cur, int len); /* * Maximal mount counts between two filesystem checks */ #define EXT4_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */ #define EXT4_DFL_CHECKINTERVAL 0 /* Don't use interval check */ /* * Behaviour when detecting errors */ #define EXT4_ERRORS_CONTINUE 1 /* Continue execution */ #define EXT4_ERRORS_RO 2 /* Remount fs read-only */ #define EXT4_ERRORS_PANIC 3 /* Panic */ #define EXT4_ERRORS_DEFAULT EXT4_ERRORS_CONTINUE /* Metadata checksum algorithm codes */ #define EXT4_CRC32C_CHKSUM 1 #define EXT4_LABEL_MAX 16 /* * Structure of the super block */ struct ext4_super_block { /*00*/ __le32 s_inodes_count; /* Inodes count */ __le32 s_blocks_count_lo; /* Blocks count */ __le32 s_r_blocks_count_lo; /* Reserved blocks count */ __le32 s_free_blocks_count_lo; /* Free blocks count */ /*10*/ __le32 s_free_inodes_count; /* Free inodes count */ __le32 s_first_data_block; /* First Data Block */ __le32 s_log_block_size; /* Block size */ __le32 s_log_cluster_size; /* Allocation cluster size */ /*20*/ __le32 s_blocks_per_group; /* # Blocks per group */ __le32 s_clusters_per_group; /* # Clusters per group */ __le32 s_inodes_per_group; /* # Inodes per group */ __le32 s_mtime; /* Mount time */ /*30*/ __le32 s_wtime; /* Write time */ __le16 s_mnt_count; /* Mount count */ __le16 s_max_mnt_count; /* Maximal mount count */ __le16 s_magic; /* Magic signature */ __le16 s_state; /* File system state */ __le16 s_errors; /* Behaviour when detecting errors */ __le16 s_minor_rev_level; /* minor revision level */ /*40*/ __le32 s_lastcheck; /* time of last check */ __le32 s_checkinterval; /* max. time between checks */ __le32 s_creator_os; /* OS */ __le32 s_rev_level; /* Revision level */ /*50*/ __le16 s_def_resuid; /* Default uid for reserved blocks */ __le16 s_def_resgid; /* Default gid for reserved blocks */ /* * These fields are for EXT4_DYNAMIC_REV superblocks only. * * Note: the difference between the compatible feature set and * the incompatible feature set is that if there is a bit set * in the incompatible feature set that the kernel doesn't * know about, it should refuse to mount the filesystem. * * e2fsck's requirements are more strict; if it doesn't know * about a feature in either the compatible or incompatible * feature set, it must abort and not try to meddle with * things it doesn't understand... */ __le32 s_first_ino; /* First non-reserved inode */ __le16 s_inode_size; /* size of inode structure */ __le16 s_block_group_nr; /* block group # of this superblock */ __le32 s_feature_compat; /* compatible feature set */ /*60*/ __le32 s_feature_incompat; /* incompatible feature set */ __le32 s_feature_ro_compat; /* readonly-compatible feature set */ /*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ /*78*/ char s_volume_name[EXT4_LABEL_MAX]; /* volume name */ /*88*/ char s_last_mounted[64] __nonstring; /* directory where last mounted */ /*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ /* * Performance hints. Directory preallocation should only * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on. */ __u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/ __u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */ __le16 s_reserved_gdt_blocks; /* Per group desc for online growth */ /* * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set. */ /*D0*/ __u8 s_journal_uuid[16]; /* uuid of journal superblock */ /*E0*/ __le32 s_journal_inum; /* inode number of journal file */ __le32 s_journal_dev; /* device number of journal file */ __le32 s_last_orphan; /* start of list of inodes to delete */ __le32 s_hash_seed[4]; /* HTREE hash seed */ __u8 s_def_hash_version; /* Default hash version to use */ __u8 s_jnl_backup_type; __le16 s_desc_size; /* size of group descriptor */ /*100*/ __le32 s_default_mount_opts; __le32 s_first_meta_bg; /* First metablock block group */ __le32 s_mkfs_time; /* When the filesystem was created */ __le32 s_jnl_blocks[17]; /* Backup of the journal inode */ /* 64bit support valid if EXT4_FEATURE_INCOMPAT_64BIT */ /*150*/ __le32 s_blocks_count_hi; /* Blocks count */ __le32 s_r_blocks_count_hi; /* Reserved blocks count */ __le32 s_free_blocks_count_hi; /* Free blocks count */ __le16 s_min_extra_isize; /* All inodes have at least # bytes */ __le16 s_want_extra_isize; /* New inodes should reserve # bytes */ __le32 s_flags; /* Miscellaneous flags */ __le16 s_raid_stride; /* RAID stride */ __le16 s_mmp_update_interval; /* # seconds to wait in MMP checking */ __le64 s_mmp_block; /* Block for multi-mount protection */ __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ __u8 s_log_groups_per_flex; /* FLEX_BG group size */ __u8 s_checksum_type; /* metadata checksum algorithm used */ __u8 s_encryption_level; /* versioning level for encryption */ __u8 s_reserved_pad; /* Padding to next 32bits */ __le64 s_kbytes_written; /* nr of lifetime kilobytes written */ __le32 s_snapshot_inum; /* Inode number of active snapshot */ __le32 s_snapshot_id; /* sequential ID of active snapshot */ __le64 s_snapshot_r_blocks_count; /* reserved blocks for active snapshot's future use */ __le32 s_snapshot_list; /* inode number of the head of the on-disk snapshot list */ #define EXT4_S_ERR_START offsetof(struct ext4_super_block, s_error_count) __le32 s_error_count; /* number of fs errors */ __le32 s_first_error_time; /* first time an error happened */ __le32 s_first_error_ino; /* inode involved in first error */ __le64 s_first_error_block; /* block involved of first error */ __u8 s_first_error_func[32] __nonstring; /* function where the error happened */ __le32 s_first_error_line; /* line number where error happened */ __le32 s_last_error_time; /* most recent time of an error */ __le32 s_last_error_ino; /* inode involved in last error */ __le32 s_last_error_line; /* line number where error happened */ __le64 s_last_error_block; /* block involved of last error */ __u8 s_last_error_func[32] __nonstring; /* function where the error happened */ #define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts) __u8 s_mount_opts[64]; __le32 s_usr_quota_inum; /* inode for tracking user quota */ __le32 s_grp_quota_inum; /* inode for tracking group quota */ __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */ __le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */ __u8 s_encrypt_algos[4]; /* Encryption algorithms in use */ __u8 s_encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ __le32 s_lpf_ino; /* Location of the lost+found inode */ __le32 s_prj_quota_inum; /* inode for tracking project quota */ __le32 s_checksum_seed; /* crc32c(uuid) if csum_seed set */ __u8 s_wtime_hi; __u8 s_mtime_hi; __u8 s_mkfs_time_hi; __u8 s_lastcheck_hi; __u8 s_first_error_time_hi; __u8 s_last_error_time_hi; __u8 s_first_error_errcode; __u8 s_last_error_errcode; __le16 s_encoding; /* Filename charset encoding */ __le16 s_encoding_flags; /* Filename charset encoding flags */ __le32 s_orphan_file_inum; /* Inode for tracking orphan inodes */ __le32 s_reserved[94]; /* Padding to the end of the block */ __le32 s_checksum; /* crc32c(superblock) */ }; #define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START) #ifdef __KERNEL__ /* Number of quota types we support */ #define EXT4_MAXQUOTAS 3 #define EXT4_ENC_UTF8_12_1 1 /* Types of ext4 journal triggers */ enum ext4_journal_trigger_type { EXT4_JTR_ORPHAN_FILE, EXT4_JTR_NONE /* This must be the last entry for indexing to work! */ }; #define EXT4_JOURNAL_TRIGGER_COUNT EXT4_JTR_NONE struct ext4_journal_trigger { struct jbd2_buffer_trigger_type tr_triggers; struct super_block *sb; }; static inline struct ext4_journal_trigger *EXT4_TRIGGER( struct jbd2_buffer_trigger_type *trigger) { return container_of(trigger, struct ext4_journal_trigger, tr_triggers); } #define EXT4_ORPHAN_BLOCK_MAGIC 0x0b10ca04 /* Structure at the tail of orphan block */ struct ext4_orphan_block_tail { __le32 ob_magic; __le32 ob_checksum; }; static inline int ext4_inodes_per_orphan_block(struct super_block *sb) { return (sb->s_blocksize - sizeof(struct ext4_orphan_block_tail)) / sizeof(u32); } struct ext4_orphan_block { atomic_t ob_free_entries; /* Number of free orphan entries in block */ struct buffer_head *ob_bh; /* Buffer for orphan block */ }; /* * Info about orphan file. */ struct ext4_orphan_info { int of_blocks; /* Number of orphan blocks in a file */ __u32 of_csum_seed; /* Checksum seed for orphan file */ struct ext4_orphan_block *of_binfo; /* Array with info about orphan * file blocks */ }; /* * fourth extended-fs super-block data in memory */ struct ext4_sb_info { unsigned long s_desc_size; /* Size of a group descriptor in bytes */ unsigned long s_inodes_per_block;/* Number of inodes per block */ unsigned long s_blocks_per_group;/* Number of blocks in a group */ unsigned long s_clusters_per_group; /* Number of clusters in a group */ unsigned long s_inodes_per_group;/* Number of inodes in a group */ unsigned long s_itb_per_group; /* Number of inode table blocks per group */ unsigned long s_gdb_count; /* Number of group descriptor blocks */ unsigned long s_desc_per_block; /* Number of group descriptors per block */ ext4_group_t s_groups_count; /* Number of groups in the fs */ ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */ unsigned long s_overhead; /* # of fs overhead clusters */ unsigned int s_cluster_ratio; /* Number of blocks per cluster */ unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */ loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ /* Array of bh's for the block group descriptors */ struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; unsigned long s_mount_flags; unsigned int s_def_mount_opt; unsigned int s_def_mount_opt2; ext4_fsblk_t s_sb_block; atomic64_t s_resv_clusters; kuid_t s_resuid; kgid_t s_resgid; unsigned short s_mount_state; unsigned short s_pad; int s_addr_per_block_bits; int s_desc_per_block_bits; int s_inode_size; int s_first_ino; unsigned int s_inode_readahead_blks; unsigned int s_inode_goal; u32 s_hash_seed[4]; int s_def_hash_version; int s_hash_unsigned; /* 3 if hash should be unsigned, 0 if not */ struct percpu_counter s_freeclusters_counter; struct percpu_counter s_freeinodes_counter; struct percpu_counter s_dirs_counter; struct percpu_counter s_dirtyclusters_counter; struct percpu_counter s_sra_exceeded_retry_limit; struct blockgroup_lock *s_blockgroup_lock; struct proc_dir_entry *s_proc; struct kobject s_kobj; struct completion s_kobj_unregister; struct super_block *s_sb; struct buffer_head *s_mmp_bh; /* Journaling */ struct journal_s *s_journal; unsigned long s_ext4_flags; /* Ext4 superblock flags */ struct mutex s_orphan_lock; /* Protects on disk list changes */ struct list_head s_orphan; /* List of orphaned inodes in on disk list */ struct ext4_orphan_info s_orphan_info; unsigned long s_commit_interval; u32 s_max_batch_time; u32 s_min_batch_time; struct file *s_journal_bdev_file; #ifdef CONFIG_QUOTA /* Names of quota files with journalled quota */ char __rcu *s_qf_names[EXT4_MAXQUOTAS]; int s_jquota_fmt; /* Format of quota to use */ #endif unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ struct ext4_system_blocks __rcu *s_system_blks; #ifdef EXTENTS_STATS /* ext4 extents stats */ unsigned long s_ext_min; unsigned long s_ext_max; unsigned long s_depth_max; spinlock_t s_ext_stats_lock; unsigned long s_ext_blocks; unsigned long s_ext_extents; #endif /* for buddy allocator */ struct ext4_group_info ** __rcu *s_group_info; struct inode *s_buddy_cache; spinlock_t s_md_lock; unsigned short *s_mb_offsets; unsigned int *s_mb_maxs; unsigned int s_group_info_size; unsigned int s_mb_free_pending; struct list_head s_freed_data_list[2]; /* List of blocks to be freed after commit completed */ struct list_head s_discard_list; struct work_struct s_discard_work; atomic_t s_retry_alloc_pending; struct list_head *s_mb_avg_fragment_size; rwlock_t *s_mb_avg_fragment_size_locks; struct list_head *s_mb_largest_free_orders; rwlock_t *s_mb_largest_free_orders_locks; /* tunables */ unsigned long s_stripe; unsigned int s_mb_max_linear_groups; unsigned int s_mb_stream_request; unsigned int s_mb_max_to_scan; unsigned int s_mb_min_to_scan; unsigned int s_mb_stats; unsigned int s_mb_order2_reqs; unsigned int s_mb_group_prealloc; unsigned int s_max_dir_size_kb; /* where last allocation was done - for stream allocation */ unsigned long s_mb_last_group; unsigned long s_mb_last_start; unsigned int s_mb_prefetch; unsigned int s_mb_prefetch_limit; unsigned int s_mb_best_avail_max_trim_order; /* stats for buddy allocator */ atomic_t s_bal_reqs; /* number of reqs with len > 1 */ atomic_t s_bal_success; /* we found long enough chunks */ atomic_t s_bal_allocated; /* in blocks */ atomic_t s_bal_ex_scanned; /* total extents scanned */ atomic_t s_bal_cX_ex_scanned[EXT4_MB_NUM_CRS]; /* total extents scanned */ atomic_t s_bal_groups_scanned; /* number of groups scanned */ atomic_t s_bal_goals; /* goal hits */ atomic_t s_bal_len_goals; /* len goal hits */ atomic_t s_bal_breaks; /* too long searches */ atomic_t s_bal_2orders; /* 2^order hits */ atomic_t s_bal_p2_aligned_bad_suggestions; atomic_t s_bal_goal_fast_bad_suggestions; atomic_t s_bal_best_avail_bad_suggestions; atomic64_t s_bal_cX_groups_considered[EXT4_MB_NUM_CRS]; atomic64_t s_bal_cX_hits[EXT4_MB_NUM_CRS]; atomic64_t s_bal_cX_failed[EXT4_MB_NUM_CRS]; /* cX loop didn't find blocks */ atomic_t s_mb_buddies_generated; /* number of buddies generated */ atomic64_t s_mb_generation_time; atomic_t s_mb_lost_chunks; atomic_t s_mb_preallocated; atomic_t s_mb_discarded; atomic_t s_lock_busy; /* locality groups */ struct ext4_locality_group __percpu *s_locality_groups; /* for write statistics */ unsigned long s_sectors_written_start; u64 s_kbytes_written; /* the size of zero-out chunk */ unsigned int s_extent_max_zeroout_kb; unsigned int s_log_groups_per_flex; struct flex_groups * __rcu *s_flex_groups; ext4_group_t s_flex_groups_allocated; /* workqueue for reserved extent conversions (buffered io) */ struct workqueue_struct *rsv_conversion_wq; /* timer for periodic error stats printing */ struct timer_list s_err_report; /* Lazy inode table initialization info */ struct ext4_li_request *s_li_request; /* Wait multiplier for lazy initialization thread */ unsigned int s_li_wait_mult; /* Kernel thread for multiple mount protection */ struct task_struct *s_mmp_tsk; /* record the last minlen when FITRIM is called. */ unsigned long s_last_trim_minblks; /* Reference to checksum algorithm driver via cryptoapi */ struct crypto_shash *s_chksum_driver; /* Precomputed FS UUID checksum for seeding other checksums */ __u32 s_csum_seed; /* Reclaim extents from extent status tree */ struct shrinker *s_es_shrinker; struct list_head s_es_list; /* List of inodes with reclaimable extents */ long s_es_nr_inode; struct ext4_es_stats s_es_stats; struct mb_cache *s_ea_block_cache; struct mb_cache *s_ea_inode_cache; spinlock_t s_es_lock ____cacheline_aligned_in_smp; /* Journal triggers for checksum computation */ struct ext4_journal_trigger s_journal_triggers[EXT4_JOURNAL_TRIGGER_COUNT]; /* Ratelimit ext4 messages. */ struct ratelimit_state s_err_ratelimit_state; struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; atomic_t s_warning_count; atomic_t s_msg_count; /* Encryption policy for '-o test_dummy_encryption' */ struct fscrypt_dummy_policy s_dummy_enc_policy; /* * Barrier between writepages ops and changing any inode's JOURNAL_DATA * or EXTENTS flag or between writepages ops and changing DELALLOC or * DIOREAD_NOLOCK mount options on remount. */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; u64 s_dax_part_off; #ifdef CONFIG_EXT4_DEBUG unsigned long s_simulate_fail; #endif /* Record the errseq of the backing block device */ errseq_t s_bdev_wb_err; spinlock_t s_bdev_wb_lock; /* Information about errors that happened during this mount */ spinlock_t s_error_lock; int s_add_error_count; int s_first_error_code; __u32 s_first_error_line; __u32 s_first_error_ino; __u64 s_first_error_block; const char *s_first_error_func; time64_t s_first_error_time; int s_last_error_code; __u32 s_last_error_line; __u32 s_last_error_ino; __u64 s_last_error_block; const char *s_last_error_func; time64_t s_last_error_time; /* * If we are in a context where we cannot update the on-disk * superblock, we queue the work here. This is used to update * the error information in the superblock, and for periodic * updates of the superblock called from the commit callback * function. */ struct work_struct s_sb_upd_work; /* Ext4 fast commit sub transaction ID */ atomic_t s_fc_subtid; /* * After commit starts, the main queue gets locked, and the further * updates get added in the staging queue. */ #define FC_Q_MAIN 0 #define FC_Q_STAGING 1 struct list_head s_fc_q[2]; /* Inodes staged for fast commit * that have data changes in them. */ struct list_head s_fc_dentry_q[2]; /* directory entry updates */ unsigned int s_fc_bytes; /* * Main fast commit lock. This lock protects accesses to the * following fields: * ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh. */ spinlock_t s_fc_lock; struct buffer_head *s_fc_bh; struct ext4_fc_stats s_fc_stats; tid_t s_fc_ineligible_tid; #ifdef CONFIG_EXT4_DEBUG int s_fc_debug_max_replay; #endif struct ext4_fc_replay_state s_fc_replay_state; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) { return sb->s_fs_info; } static inline struct ext4_inode_info *EXT4_I(struct inode *inode) { return container_of(inode, struct ext4_inode_info, vfs_inode); } static inline int ext4_writepages_down_read(struct super_block *sb) { percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); return memalloc_nofs_save(); } static inline void ext4_writepages_up_read(struct super_block *sb, int ctx) { memalloc_nofs_restore(ctx); percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); } static inline int ext4_writepages_down_write(struct super_block *sb) { percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem); return memalloc_nofs_save(); } static inline void ext4_writepages_up_write(struct super_block *sb, int ctx) { memalloc_nofs_restore(ctx); percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem); } static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || (ino >= EXT4_FIRST_INO(sb) && ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } /* * Returns: sbi->field[index] * Used to access an array element from the following sbi fields which require * rcu protection to avoid dereferencing an invalid pointer due to reassignment * - s_group_desc * - s_group_info * - s_flex_group */ #define sbi_array_rcu_deref(sbi, field, index) \ ({ \ typeof(*((sbi)->field)) _v; \ rcu_read_lock(); \ _v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index]; \ rcu_read_unlock(); \ _v; \ }) /* * run-time mount flags */ enum { EXT4_MF_MNTDIR_SAMPLED, EXT4_MF_FC_INELIGIBLE /* Fast commit ineligible */ }; static inline void ext4_set_mount_flag(struct super_block *sb, int bit) { set_bit(bit, &EXT4_SB(sb)->s_mount_flags); } static inline void ext4_clear_mount_flag(struct super_block *sb, int bit) { clear_bit(bit, &EXT4_SB(sb)->s_mount_flags); } static inline int ext4_test_mount_flag(struct super_block *sb, int bit) { return test_bit(bit, &EXT4_SB(sb)->s_mount_flags); } /* * Simulate_fail codes */ #define EXT4_SIM_BBITMAP_EIO 1 #define EXT4_SIM_BBITMAP_CRC 2 #define EXT4_SIM_IBITMAP_EIO 3 #define EXT4_SIM_IBITMAP_CRC 4 #define EXT4_SIM_INODE_EIO 5 #define EXT4_SIM_INODE_CRC 6 #define EXT4_SIM_DIRBLOCK_EIO 7 #define EXT4_SIM_DIRBLOCK_CRC 8 static inline bool ext4_simulate_fail(struct super_block *sb, unsigned long code) { #ifdef CONFIG_EXT4_DEBUG struct ext4_sb_info *sbi = EXT4_SB(sb); if (unlikely(sbi->s_simulate_fail == code)) { sbi->s_simulate_fail = 0; return true; } #endif return false; } static inline void ext4_simulate_fail_bh(struct super_block *sb, struct buffer_head *bh, unsigned long code) { if (!IS_ERR(bh) && ext4_simulate_fail(sb, code)) clear_buffer_uptodate(bh); } /* * Error number codes for s_{first,last}_error_errno * * Linux errno numbers are architecture specific, so we need to translate * them into something which is architecture independent. We don't define * codes for all errno's; just the ones which are most likely to be the cause * of an ext4_error() call. */ #define EXT4_ERR_UNKNOWN 1 #define EXT4_ERR_EIO 2 #define EXT4_ERR_ENOMEM 3 #define EXT4_ERR_EFSBADCRC 4 #define EXT4_ERR_EFSCORRUPTED 5 #define EXT4_ERR_ENOSPC 6 #define EXT4_ERR_ENOKEY 7 #define EXT4_ERR_EROFS 8 #define EXT4_ERR_EFBIG 9 #define EXT4_ERR_EEXIST 10 #define EXT4_ERR_ERANGE 11 #define EXT4_ERR_EOVERFLOW 12 #define EXT4_ERR_EBUSY 13 #define EXT4_ERR_ENOTDIR 14 #define EXT4_ERR_ENOTEMPTY 15 #define EXT4_ERR_ESHUTDOWN 16 #define EXT4_ERR_EFAULT 17 /* * Inode dynamic state flags */ enum { EXT4_STATE_NEW, /* inode is newly created */ EXT4_STATE_XATTR, /* has in-inode xattrs */ EXT4_STATE_NO_EXPAND, /* No space for expansion */ EXT4_STATE_DA_ALLOC_CLOSE, /* Alloc DA blks on close */ EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */ EXT4_STATE_NEWENTRY, /* File just added to dir */ EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */ EXT4_STATE_EXT_PRECACHED, /* extents have been precached */ EXT4_STATE_LUSTRE_EA_INODE, /* Lustre-style ea_inode */ EXT4_STATE_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */ EXT4_STATE_FC_COMMITTING, /* Fast commit ongoing */ EXT4_STATE_ORPHAN_FILE, /* Inode orphaned in orphan file */ }; #define EXT4_INODE_BIT_FNS(name, field, offset) \ static inline int ext4_test_inode_##name(struct inode *inode, int bit) \ { \ return test_bit(bit + (offset), &EXT4_I(inode)->i_##field); \ } \ static inline void ext4_set_inode_##name(struct inode *inode, int bit) \ { \ set_bit(bit + (offset), &EXT4_I(inode)->i_##field); \ } \ static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \ { \ clear_bit(bit + (offset), &EXT4_I(inode)->i_##field); \ } /* Add these declarations here only so that these functions can be * found by name. Otherwise, they are very hard to locate. */ static inline int ext4_test_inode_flag(struct inode *inode, int bit); static inline void ext4_set_inode_flag(struct inode *inode, int bit); static inline void ext4_clear_inode_flag(struct inode *inode, int bit); EXT4_INODE_BIT_FNS(flag, flags, 0) /* Add these declarations here only so that these functions can be * found by name. Otherwise, they are very hard to locate. */ static inline int ext4_test_inode_state(struct inode *inode, int bit); static inline void ext4_set_inode_state(struct inode *inode, int bit); static inline void ext4_clear_inode_state(struct inode *inode, int bit); #if (BITS_PER_LONG < 64) EXT4_INODE_BIT_FNS(state, state_flags, 0) static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) { (ei)->i_state_flags = 0; } #else EXT4_INODE_BIT_FNS(state, flags, 32) static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) { /* We depend on the fact that callers will set i_flags */ } #endif #else /* Assume that user mode programs are passing in an ext4fs superblock, not * a kernel struct super_block. This will allow us to call the feature-test * macros from user land. */ #define EXT4_SB(sb) (sb) #endif static inline bool ext4_verity_in_progress(struct inode *inode) { return IS_ENABLED(CONFIG_FS_VERITY) && ext4_test_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); } #define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime /* * Codes for operating systems */ #define EXT4_OS_LINUX 0 #define EXT4_OS_HURD 1 #define EXT4_OS_MASIX 2 #define EXT4_OS_FREEBSD 3 #define EXT4_OS_LITES 4 /* * Revision levels */ #define EXT4_GOOD_OLD_REV 0 /* The good old (original) format */ #define EXT4_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ #define EXT4_MAX_SUPP_REV EXT4_DYNAMIC_REV #define EXT4_GOOD_OLD_INODE_SIZE 128 #define EXT4_EXTRA_TIMESTAMP_MAX (((s64)1 << 34) - 1 + S32_MIN) #define EXT4_NON_EXTRA_TIMESTAMP_MAX S32_MAX #define EXT4_TIMESTAMP_MIN S32_MIN /* * Feature set definitions */ #define EXT4_FEATURE_COMPAT_DIR_PREALLOC 0x0001 #define EXT4_FEATURE_COMPAT_IMAGIC_INODES 0x0002 #define EXT4_FEATURE_COMPAT_HAS_JOURNAL 0x0004 #define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008 #define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 #define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200 /* * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes * incompatible only if fast commit blocks are present in the FS. Since we * clear the journal (and thus the fast commit blocks), we don't mark FS as * incompatible. We also have a JBD2 incompat feature, which gets set when * there are fast commit blocks present in the journal. */ #define EXT4_FEATURE_COMPAT_FAST_COMMIT 0x0400 #define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800 #define EXT4_FEATURE_COMPAT_ORPHAN_FILE 0x1000 /* Orphan file exists */ #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 #define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 #define EXT4_FEATURE_RO_COMPAT_HUGE_FILE 0x0008 #define EXT4_FEATURE_RO_COMPAT_GDT_CSUM 0x0010 #define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020 #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040 #define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100 #define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200 /* * METADATA_CSUM also enables group descriptor checksums (GDT_CSUM). When * METADATA_CSUM is set, group descriptor checksums use the same algorithm as * all other data structures' checksums. However, the METADATA_CSUM and * GDT_CSUM bits are mutually exclusive. */ #define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400 #define EXT4_FEATURE_RO_COMPAT_READONLY 0x1000 #define EXT4_FEATURE_RO_COMPAT_PROJECT 0x2000 #define EXT4_FEATURE_RO_COMPAT_VERITY 0x8000 #define EXT4_FEATURE_RO_COMPAT_ORPHAN_PRESENT 0x10000 /* Orphan file may be non-empty */ #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 #define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 #define EXT4_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */ #define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */ #define EXT4_FEATURE_INCOMPAT_META_BG 0x0010 #define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */ #define EXT4_FEATURE_INCOMPAT_64BIT 0x0080 #define EXT4_FEATURE_INCOMPAT_MMP 0x0100 #define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200 #define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */ #define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */ #define EXT4_FEATURE_INCOMPAT_CSUM_SEED 0x2000 #define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */ #define EXT4_FEATURE_INCOMPAT_INLINE_DATA 0x8000 /* data in inode */ #define EXT4_FEATURE_INCOMPAT_ENCRYPT 0x10000 #define EXT4_FEATURE_INCOMPAT_CASEFOLD 0x20000 extern void ext4_update_dynamic_rev(struct super_block *sb); #define EXT4_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool ext4_has_feature_##name(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_compat & \ cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname)) != 0); \ } \ static inline void ext4_set_feature_##name(struct super_block *sb) \ { \ ext4_update_dynamic_rev(sb); \ EXT4_SB(sb)->s_es->s_feature_compat |= \ cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \ } \ static inline void ext4_clear_feature_##name(struct super_block *sb) \ { \ EXT4_SB(sb)->s_es->s_feature_compat &= \ ~cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \ } #define EXT4_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline bool ext4_has_feature_##name(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \ cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname)) != 0); \ } \ static inline void ext4_set_feature_##name(struct super_block *sb) \ { \ ext4_update_dynamic_rev(sb); \ EXT4_SB(sb)->s_es->s_feature_ro_compat |= \ cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \ } \ static inline void ext4_clear_feature_##name(struct super_block *sb) \ { \ EXT4_SB(sb)->s_es->s_feature_ro_compat &= \ ~cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \ } #define EXT4_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline bool ext4_has_feature_##name(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_incompat & \ cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname)) != 0); \ } \ static inline void ext4_set_feature_##name(struct super_block *sb) \ { \ ext4_update_dynamic_rev(sb); \ EXT4_SB(sb)->s_es->s_feature_incompat |= \ cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \ } \ static inline void ext4_clear_feature_##name(struct super_block *sb) \ { \ EXT4_SB(sb)->s_es->s_feature_incompat &= \ ~cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \ } EXT4_FEATURE_COMPAT_FUNCS(dir_prealloc, DIR_PREALLOC) EXT4_FEATURE_COMPAT_FUNCS(imagic_inodes, IMAGIC_INODES) EXT4_FEATURE_COMPAT_FUNCS(journal, HAS_JOURNAL) EXT4_FEATURE_COMPAT_FUNCS(xattr, EXT_ATTR) EXT4_FEATURE_COMPAT_FUNCS(resize_inode, RESIZE_INODE) EXT4_FEATURE_COMPAT_FUNCS(dir_index, DIR_INDEX) EXT4_FEATURE_COMPAT_FUNCS(sparse_super2, SPARSE_SUPER2) EXT4_FEATURE_COMPAT_FUNCS(fast_commit, FAST_COMMIT) EXT4_FEATURE_COMPAT_FUNCS(stable_inodes, STABLE_INODES) EXT4_FEATURE_COMPAT_FUNCS(orphan_file, ORPHAN_FILE) EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super, SPARSE_SUPER) EXT4_FEATURE_RO_COMPAT_FUNCS(large_file, LARGE_FILE) EXT4_FEATURE_RO_COMPAT_FUNCS(btree_dir, BTREE_DIR) EXT4_FEATURE_RO_COMPAT_FUNCS(huge_file, HUGE_FILE) EXT4_FEATURE_RO_COMPAT_FUNCS(gdt_csum, GDT_CSUM) EXT4_FEATURE_RO_COMPAT_FUNCS(dir_nlink, DIR_NLINK) EXT4_FEATURE_RO_COMPAT_FUNCS(extra_isize, EXTRA_ISIZE) EXT4_FEATURE_RO_COMPAT_FUNCS(quota, QUOTA) EXT4_FEATURE_RO_COMPAT_FUNCS(bigalloc, BIGALLOC) EXT4_FEATURE_RO_COMPAT_FUNCS(metadata_csum, METADATA_CSUM) EXT4_FEATURE_RO_COMPAT_FUNCS(readonly, READONLY) EXT4_FEATURE_RO_COMPAT_FUNCS(project, PROJECT) EXT4_FEATURE_RO_COMPAT_FUNCS(verity, VERITY) EXT4_FEATURE_RO_COMPAT_FUNCS(orphan_present, ORPHAN_PRESENT) EXT4_FEATURE_INCOMPAT_FUNCS(compression, COMPRESSION) EXT4_FEATURE_INCOMPAT_FUNCS(filetype, FILETYPE) EXT4_FEATURE_INCOMPAT_FUNCS(journal_needs_recovery, RECOVER) EXT4_FEATURE_INCOMPAT_FUNCS(journal_dev, JOURNAL_DEV) EXT4_FEATURE_INCOMPAT_FUNCS(meta_bg, META_BG) EXT4_FEATURE_INCOMPAT_FUNCS(extents, EXTENTS) EXT4_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) EXT4_FEATURE_INCOMPAT_FUNCS(mmp, MMP) EXT4_FEATURE_INCOMPAT_FUNCS(flex_bg, FLEX_BG) EXT4_FEATURE_INCOMPAT_FUNCS(ea_inode, EA_INODE) EXT4_FEATURE_INCOMPAT_FUNCS(dirdata, DIRDATA) EXT4_FEATURE_INCOMPAT_FUNCS(csum_seed, CSUM_SEED) EXT4_FEATURE_INCOMPAT_FUNCS(largedir, LARGEDIR) EXT4_FEATURE_INCOMPAT_FUNCS(inline_data, INLINE_DATA) EXT4_FEATURE_INCOMPAT_FUNCS(encrypt, ENCRYPT) EXT4_FEATURE_INCOMPAT_FUNCS(casefold, CASEFOLD) #define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR #define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_META_BG) #define EXT2_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) #define EXT3_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR #define EXT3_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_RECOVER| \ EXT4_FEATURE_INCOMPAT_META_BG) #define EXT3_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) #define EXT4_FEATURE_COMPAT_SUPP (EXT4_FEATURE_COMPAT_EXT_ATTR| \ EXT4_FEATURE_COMPAT_ORPHAN_FILE) #define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_RECOVER| \ EXT4_FEATURE_INCOMPAT_META_BG| \ EXT4_FEATURE_INCOMPAT_EXTENTS| \ EXT4_FEATURE_INCOMPAT_64BIT| \ EXT4_FEATURE_INCOMPAT_FLEX_BG| \ EXT4_FEATURE_INCOMPAT_EA_INODE| \ EXT4_FEATURE_INCOMPAT_MMP | \ EXT4_FEATURE_INCOMPAT_INLINE_DATA | \ EXT4_FEATURE_INCOMPAT_ENCRYPT | \ EXT4_FEATURE_INCOMPAT_CASEFOLD | \ EXT4_FEATURE_INCOMPAT_CSUM_SEED | \ EXT4_FEATURE_INCOMPAT_LARGEDIR) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \ EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \ EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\ EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\ EXT4_FEATURE_RO_COMPAT_QUOTA |\ EXT4_FEATURE_RO_COMPAT_PROJECT |\ EXT4_FEATURE_RO_COMPAT_VERITY |\ EXT4_FEATURE_RO_COMPAT_ORPHAN_PRESENT) #define EXTN_FEATURE_FUNCS(ver) \ static inline bool ext4_has_unknown_ext##ver##_compat_features(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_compat & \ cpu_to_le32(~EXT##ver##_FEATURE_COMPAT_SUPP)) != 0); \ } \ static inline bool ext4_has_unknown_ext##ver##_ro_compat_features(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \ cpu_to_le32(~EXT##ver##_FEATURE_RO_COMPAT_SUPP)) != 0); \ } \ static inline bool ext4_has_unknown_ext##ver##_incompat_features(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_incompat & \ cpu_to_le32(~EXT##ver##_FEATURE_INCOMPAT_SUPP)) != 0); \ } EXTN_FEATURE_FUNCS(2) EXTN_FEATURE_FUNCS(3) EXTN_FEATURE_FUNCS(4) static inline bool ext4_has_compat_features(struct super_block *sb) { return (EXT4_SB(sb)->s_es->s_feature_compat != 0); } static inline bool ext4_has_ro_compat_features(struct super_block *sb) { return (EXT4_SB(sb)->s_es->s_feature_ro_compat != 0); } static inline bool ext4_has_incompat_features(struct super_block *sb) { return (EXT4_SB(sb)->s_es->s_feature_incompat != 0); } extern int ext4_feature_set_ok(struct super_block *sb, int readonly); /* * Superblock flags */ #define EXT4_FLAGS_RESIZING 0 #define EXT4_FLAGS_SHUTDOWN 1 #define EXT4_FLAGS_BDEV_IS_DAX 2 static inline int ext4_forced_shutdown(struct super_block *sb) { return test_bit(EXT4_FLAGS_SHUTDOWN, &EXT4_SB(sb)->s_ext4_flags); } /* * Default values for user and/or group using reserved blocks */ #define EXT4_DEF_RESUID 0 #define EXT4_DEF_RESGID 0 /* * Default project ID */ #define EXT4_DEF_PROJID 0 #define EXT4_DEF_INODE_READAHEAD_BLKS 32 /* * Default mount options */ #define EXT4_DEFM_DEBUG 0x0001 #define EXT4_DEFM_BSDGROUPS 0x0002 #define EXT4_DEFM_XATTR_USER 0x0004 #define EXT4_DEFM_ACL 0x0008 #define EXT4_DEFM_UID16 0x0010 #define EXT4_DEFM_JMODE 0x0060 #define EXT4_DEFM_JMODE_DATA 0x0020 #define EXT4_DEFM_JMODE_ORDERED 0x0040 #define EXT4_DEFM_JMODE_WBACK 0x0060 #define EXT4_DEFM_NOBARRIER 0x0100 #define EXT4_DEFM_BLOCK_VALIDITY 0x0200 #define EXT4_DEFM_DISCARD 0x0400 #define EXT4_DEFM_NODELALLOC 0x0800 /* * Default journal batch times */ #define EXT4_DEF_MIN_BATCH_TIME 0 #define EXT4_DEF_MAX_BATCH_TIME 15000 /* 15ms */ /* * Minimum number of groups in a flexgroup before we separate out * directories into the first block group of a flexgroup */ #define EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME 4 /* * Structure of a directory entry */ #define EXT4_NAME_LEN 255 /* * Base length of the ext4 directory entry excluding the name length */ #define EXT4_BASE_DIR_LEN (sizeof(struct ext4_dir_entry_2) - EXT4_NAME_LEN) struct ext4_dir_entry { __le32 inode; /* Inode number */ __le16 rec_len; /* Directory entry length */ __le16 name_len; /* Name length */ char name[EXT4_NAME_LEN]; /* File name */ }; /* * Encrypted Casefolded entries require saving the hash on disk. This structure * followed ext4_dir_entry_2's name[name_len] at the next 4 byte aligned * boundary. */ struct ext4_dir_entry_hash { __le32 hash; __le32 minor_hash; }; /* * The new version of the directory entry. Since EXT4 structures are * stored in intel byte order, and the name_len field could never be * bigger than 255 chars, it's safe to reclaim the extra byte for the * file_type field. */ struct ext4_dir_entry_2 { __le32 inode; /* Inode number */ __le16 rec_len; /* Directory entry length */ __u8 name_len; /* Name length */ __u8 file_type; /* See file type macros EXT4_FT_* below */ char name[EXT4_NAME_LEN]; /* File name */ }; /* * Access the hashes at the end of ext4_dir_entry_2 */ #define EXT4_DIRENT_HASHES(entry) \ ((struct ext4_dir_entry_hash *) \ (((void *)(entry)) + \ ((8 + (entry)->name_len + EXT4_DIR_ROUND) & ~EXT4_DIR_ROUND))) #define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(de)->hash) #define EXT4_DIRENT_MINOR_HASH(entry) \ le32_to_cpu(EXT4_DIRENT_HASHES(de)->minor_hash) static inline bool ext4_hash_in_dirent(const struct inode *inode) { return IS_CASEFOLDED(inode) && IS_ENCRYPTED(inode); } /* * This is a bogus directory entry at the end of each leaf block that * records checksums. */ struct ext4_dir_entry_tail { __le32 det_reserved_zero1; /* Pretend to be unused */ __le16 det_rec_len; /* 12 */ __u8 det_reserved_zero2; /* Zero name length */ __u8 det_reserved_ft; /* 0xDE, fake file type */ __le32 det_checksum; /* crc32c(uuid+inum+dirblock) */ }; #define EXT4_DIRENT_TAIL(block, blocksize) \ ((struct ext4_dir_entry_tail *)(((void *)(block)) + \ ((blocksize) - \ sizeof(struct ext4_dir_entry_tail)))) /* * Ext4 directory file types. Only the low 3 bits are used. The * other bits are reserved for now. */ #define EXT4_FT_UNKNOWN 0 #define EXT4_FT_REG_FILE 1 #define EXT4_FT_DIR 2 #define EXT4_FT_CHRDEV 3 #define EXT4_FT_BLKDEV 4 #define EXT4_FT_FIFO 5 #define EXT4_FT_SOCK 6 #define EXT4_FT_SYMLINK 7 #define EXT4_FT_MAX 8 #define EXT4_FT_DIR_CSUM 0xDE /* * EXT4_DIR_PAD defines the directory entries boundaries * * NOTE: It must be a multiple of 4 */ #define EXT4_DIR_PAD 4 #define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) #define EXT4_MAX_REC_LEN ((1<<16)-1) /* * The rec_len is dependent on the type of directory. Directories that are * casefolded and encrypted need to store the hash as well, so we add room for * ext4_extended_dir_entry_2. For all entries related to '.' or '..' you should * pass NULL for dir, as those entries do not use the extra fields. */ static inline unsigned int ext4_dir_rec_len(__u8 name_len, const struct inode *dir) { int rec_len = (name_len + 8 + EXT4_DIR_ROUND); if (dir && ext4_hash_in_dirent(dir)) rec_len += sizeof(struct ext4_dir_entry_hash); return (rec_len & ~EXT4_DIR_ROUND); } /* * If we ever get support for fs block sizes > page_size, we'll need * to remove the #if statements in the next two functions... */ static inline unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize) { unsigned len = le16_to_cpu(dlen); #if (PAGE_SIZE >= 65536) if (len == EXT4_MAX_REC_LEN || len == 0) return blocksize; return (len & 65532) | ((len & 3) << 16); #else return len; #endif } static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) { BUG_ON((len > blocksize) || (blocksize > (1 << 18)) || (len & 3)); #if (PAGE_SIZE >= 65536) if (len < 65536) return cpu_to_le16(len); if (len == blocksize) { if (blocksize == 65536) return cpu_to_le16(EXT4_MAX_REC_LEN); else return cpu_to_le16(0); } return cpu_to_le16((len & 65532) | ((len >> 16) & 3)); #else return cpu_to_le16(len); #endif } /* * Hash Tree Directory indexing * (c) Daniel Phillips, 2001 */ #define is_dx(dir) (ext4_has_feature_dir_index((dir)->i_sb) && \ ext4_test_inode_flag((dir), EXT4_INODE_INDEX)) #define EXT4_DIR_LINK_MAX(dir) unlikely((dir)->i_nlink >= EXT4_LINK_MAX && \ !(ext4_has_feature_dir_nlink((dir)->i_sb) && is_dx(dir))) #define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) /* Legal values for the dx_root hash_version field: */ #define DX_HASH_LEGACY 0 #define DX_HASH_HALF_MD4 1 #define DX_HASH_TEA 2 #define DX_HASH_LEGACY_UNSIGNED 3 #define DX_HASH_HALF_MD4_UNSIGNED 4 #define DX_HASH_TEA_UNSIGNED 5 #define DX_HASH_SIPHASH 6 static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, const void *address, unsigned int length) { struct { struct shash_desc shash; char ctx[4]; } desc; BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx)); desc.shash.tfm = sbi->s_chksum_driver; *(u32 *)desc.ctx = crc; BUG_ON(crypto_shash_update(&desc.shash, address, length)); return *(u32 *)desc.ctx; } #ifdef __KERNEL__ /* hash info structure used by the directory hash */ struct dx_hash_info { u32 hash; u32 minor_hash; int hash_version; u32 *seed; }; /* 32 and 64 bit signed EOF for dx directories */ #define EXT4_HTREE_EOF_32BIT ((1UL << (32 - 1)) - 1) #define EXT4_HTREE_EOF_64BIT ((1ULL << (64 - 1)) - 1) /* * Control parameters used by ext4_htree_next_block */ #define HASH_NB_ALWAYS 1 struct ext4_filename { const struct qstr *usr_fname; struct fscrypt_str disk_name; struct dx_hash_info hinfo; #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_str crypto_buf; #endif #if IS_ENABLED(CONFIG_UNICODE) struct fscrypt_str cf_name; #endif }; #define fname_name(p) ((p)->disk_name.name) #define fname_usr_name(p) ((p)->usr_fname->name) #define fname_len(p) ((p)->disk_name.len) /* * Describe an inode's exact location on disk and in memory */ struct ext4_iloc { struct buffer_head *bh; unsigned long offset; ext4_group_t block_group; }; static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc) { return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset); } static inline bool ext4_is_quota_file(struct inode *inode) { return IS_NOQUOTA(inode) && !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL); } /* * This structure is stuffed into the struct file's private_data field * for directories. It is where we put information so that we can do * readdir operations in hash tree order. */ struct dir_private_info { struct rb_root root; struct rb_node *curr_node; struct fname *extra_fname; loff_t last_pos; __u32 curr_hash; __u32 curr_minor_hash; __u32 next_hash; }; /* calculate the first block number of the group */ static inline ext4_fsblk_t ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no) { return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); } /* * Special error return code only used by dx_probe() and its callers. */ #define ERR_BAD_DX_DIR (-(MAX_ERRNO - 1)) /* htree levels for ext4 */ #define EXT4_HTREE_LEVEL_COMPAT 2 #define EXT4_HTREE_LEVEL 3 static inline int ext4_dir_htree_level(struct super_block *sb) { return ext4_has_feature_largedir(sb) ? EXT4_HTREE_LEVEL : EXT4_HTREE_LEVEL_COMPAT; } /* * Timeout and state flag for lazy initialization inode thread. */ #define EXT4_DEF_LI_WAIT_MULT 10 #define EXT4_DEF_LI_MAX_START_DELAY 5 #define EXT4_LAZYINIT_QUIT 0x0001 #define EXT4_LAZYINIT_RUNNING 0x0002 /* * Lazy inode table initialization info */ struct ext4_lazy_init { unsigned long li_state; struct list_head li_request_list; struct mutex li_list_mtx; }; enum ext4_li_mode { EXT4_LI_MODE_PREFETCH_BBITMAP, EXT4_LI_MODE_ITABLE, }; struct ext4_li_request { struct super_block *lr_super; enum ext4_li_mode lr_mode; ext4_group_t lr_first_not_zeroed; ext4_group_t lr_next_group; struct list_head lr_request; unsigned long lr_next_sched; unsigned long lr_timeout; }; struct ext4_features { struct kobject f_kobj; struct completion f_kobj_unregister; }; /* * This structure will be used for multiple mount protection. It will be * written into the block number saved in the s_mmp_block field in the * superblock. Programs that check MMP should assume that if * SEQ_FSCK (or any unknown code above SEQ_MAX) is present then it is NOT safe * to use the filesystem, regardless of how old the timestamp is. */ #define EXT4_MMP_MAGIC 0x004D4D50U /* ASCII for MMP */ #define EXT4_MMP_SEQ_CLEAN 0xFF4D4D50U /* mmp_seq value for clean unmount */ #define EXT4_MMP_SEQ_FSCK 0xE24D4D50U /* mmp_seq value when being fscked */ #define EXT4_MMP_SEQ_MAX 0xE24D4D4FU /* maximum valid mmp_seq value */ struct mmp_struct { __le32 mmp_magic; /* Magic number for MMP */ __le32 mmp_seq; /* Sequence no. updated periodically */ /* * mmp_time, mmp_nodename & mmp_bdevname are only used for information * purposes and do not affect the correctness of the algorithm */ __le64 mmp_time; /* Time last updated */ char mmp_nodename[64]; /* Node which last updated MMP block */ char mmp_bdevname[32]; /* Bdev which last updated MMP block */ /* * mmp_check_interval is used to verify if the MMP block has been * updated on the block device. The value is updated based on the * maximum time to write the MMP block during an update cycle. */ __le16 mmp_check_interval; __le16 mmp_pad1; __le32 mmp_pad2[226]; __le32 mmp_checksum; /* crc32c(uuid+mmp_block) */ }; /* arguments passed to the mmp thread */ struct mmpd_data { struct buffer_head *bh; /* bh from initial read_mmp_block() */ struct super_block *sb; /* super block of the fs */ }; /* * Check interval multiplier * The MMP block is written every update interval and initially checked every * update interval x the multiplier (the value is then adapted based on the * write latency). The reason is that writes can be delayed under load and we * don't want readers to incorrectly assume that the filesystem is no longer * in use. */ #define EXT4_MMP_CHECK_MULT 2UL /* * Minimum interval for MMP checking in seconds. */ #define EXT4_MMP_MIN_CHECK_INTERVAL 5UL /* * Maximum interval for MMP checking in seconds. */ #define EXT4_MMP_MAX_CHECK_INTERVAL 300UL /* * Function prototypes */ /* * Ok, these declarations are also in <linux/kernel.h> but none of the * ext4 source programs needs to include it so they are duplicated here. */ # define NORET_TYPE /**/ # define ATTRIB_NORET __attribute__((noreturn)) # define NORET_AND noreturn, /* bitmap.c */ extern unsigned int ext4_count_free(char *bitmap, unsigned numchars); void ext4_inode_bitmap_csum_set(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh, int sz); int ext4_inode_bitmap_csum_verify(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh, int sz); void ext4_block_bitmap_csum_set(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh); int ext4_block_bitmap_csum_verify(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh); /* balloc.c */ extern void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp); extern ext4_group_t ext4_get_group_number(struct super_block *sb, ext4_fsblk_t block); extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group); extern unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group); extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, ext4_fsblk_t goal, unsigned int flags, unsigned long *count, int *errp); extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi, s64 nclusters, unsigned int flags); extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, ext4_group_t block_group, struct buffer_head ** bh); extern struct ext4_group_info *ext4_get_group_info(struct super_block *sb, ext4_group_t group); extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group, bool ignore_locked); extern int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, struct buffer_head *bh); extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group); extern unsigned ext4_free_clusters_after_init(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); #if IS_ENABLED(CONFIG_UNICODE) extern int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, struct ext4_filename *fname); #endif /* ext4 encryption related stuff goes here crypto.c */ #ifdef CONFIG_FS_ENCRYPTION extern const struct fscrypt_operations ext4_cryptops; int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct ext4_filename *fname); int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, struct ext4_filename *fname); void ext4_fname_free_filename(struct ext4_filename *fname); int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg); #else /* !CONFIG_FS_ENCRYPTION */ static inline int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct ext4_filename *fname) { int err = 0; fname->usr_fname = iname; fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; #if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif return err; } static inline int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, struct ext4_filename *fname) { return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname); } static inline void ext4_fname_free_filename(struct ext4_filename *fname) { #if IS_ENABLED(CONFIG_UNICODE) kfree(fname->cf_name.name); fname->cf_name.name = NULL; #endif } static inline int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg) { return -EOPNOTSUPP; } #endif /* !CONFIG_FS_ENCRYPTION */ /* dir.c */ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, struct file *, struct ext4_dir_entry_2 *, struct buffer_head *, char *, int, unsigned int); #define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \ unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \ (de), (bh), (buf), (size), (offset))) extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, struct ext4_dir_entry_2 *dirent, struct fscrypt_str *ent_name); extern void ext4_htree_free_dir_info(struct dir_private_info *p); extern int ext4_find_dest_de(struct inode *dir, struct inode *inode, struct buffer_head *bh, void *buf, int buf_size, struct ext4_filename *fname, struct ext4_dir_entry_2 **dest_de); void ext4_insert_dentry(struct inode *dir, struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { if (!ext4_has_feature_dir_index(inode->i_sb) && ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { /* ext4_iget() should have caught this... */ WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); } } static const unsigned char ext4_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK }; static inline unsigned char get_dtype(struct super_block *sb, int filetype) { if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX) return DT_UNKNOWN; return ext4_filetype_table[filetype]; } extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size); /* fsync.c */ extern int ext4_sync_file(struct file *, loff_t, loff_t, int); /* hash.c */ extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len, struct dx_hash_info *hinfo); /* ialloc.c */ extern int ext4_mark_inode_used(struct super_block *sb, int ino); extern struct inode *__ext4_new_inode(struct mnt_idmap *, handle_t *, struct inode *, umode_t, const struct qstr *qstr, __u32 goal, uid_t *owner, __u32 i_flags, int handle_type, unsigned int line_no, int nblocks); #define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \ __ext4_new_inode(&nop_mnt_idmap, (handle), (dir), (mode), (qstr), \ (goal), (owner), i_flags, 0, 0, 0) #define ext4_new_inode_start_handle(idmap, dir, mode, qstr, goal, owner, \ type, nblocks) \ __ext4_new_inode((idmap), NULL, (dir), (mode), (qstr), (goal), (owner), \ 0, (type), __LINE__, (nblocks)) extern void ext4_free_inode(handle_t *, struct inode *); extern struct inode * ext4_orphan_get(struct super_block *, unsigned long); extern unsigned long ext4_count_free_inodes(struct super_block *); extern unsigned long ext4_count_dirs(struct super_block *); extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap); extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, int barrier); extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate); /* fast_commit.c */ int ext4_fc_info_show(struct seq_file *seq, void *v); void ext4_fc_init(struct super_block *sb, journal_t *journal); void ext4_fc_init_inode(struct inode *inode); void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end); void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode, struct dentry *dentry); void __ext4_fc_track_link(handle_t *handle, struct inode *inode, struct dentry *dentry); void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry); void ext4_fc_track_link(handle_t *handle, struct dentry *dentry); void __ext4_fc_track_create(handle_t *handle, struct inode *inode, struct dentry *dentry); void ext4_fc_track_create(handle_t *handle, struct dentry *dentry); void ext4_fc_track_inode(handle_t *handle, struct inode *inode); void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle); void ext4_fc_start_update(struct inode *inode); void ext4_fc_stop_update(struct inode *inode); void ext4_fc_del(struct inode *inode); bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block); void ext4_fc_replay_cleanup(struct super_block *sb); int ext4_fc_commit(journal_t *journal, tid_t commit_tid); int __init ext4_fc_init_dentry_cache(void); void ext4_fc_destroy_dentry_cache(void); int ext4_fc_record_regions(struct super_block *sb, int ino, ext4_lblk_t lblk, ext4_fsblk_t pblk, int len, int replay); /* mballoc.c */ extern const struct seq_operations ext4_mb_seq_groups_ops; extern const struct seq_operations ext4_mb_seq_structs_summary_ops; extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset); extern int ext4_mb_init(struct super_block *); extern void ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); extern void ext4_discard_preallocations(struct inode *); extern int __init ext4_init_mballoc(void); extern void ext4_exit_mballoc(void); extern ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, unsigned int nr, int *cnt); extern void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, unsigned int nr); extern void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags); extern int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups); extern int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t i, struct ext4_group_desc *desc); extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count); extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid); extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, int len, bool state); static inline bool ext4_mb_cr_expensive(enum criteria cr) { return cr >= CR_GOAL_LEN_SLOW; } /* inode.c */ void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei); int ext4_inode_is_fast_symlink(struct inode *inode); struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int); struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int); int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count, bool wait, struct buffer_head **bhs); int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create); int ext4_walk_page_buffers(handle_t *handle, struct inode *inode, struct buffer_head *head, unsigned from, unsigned to, int *partial, int (*fn)(handle_t *handle, struct inode *inode, struct buffer_head *bh)); int do_journal_get_write_access(handle_t *handle, struct inode *inode, struct buffer_head *bh); #define FALL_BACK_TO_NONDELALLOC 1 #define CONVERT_INLINE_DATA 2 typedef enum { EXT4_IGET_NORMAL = 0, EXT4_IGET_SPECIAL = 0x0001, /* OK to iget a system inode */ EXT4_IGET_HANDLE = 0x0002, /* Inode # is from a handle */ EXT4_IGET_BAD = 0x0004, /* Allow to iget a bad inode */ EXT4_IGET_EA_INODE = 0x0008 /* Inode should contain an EA value */ } ext4_iget_flags; extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ext4_iget_flags flags, const char *function, unsigned int line); #define ext4_iget(sb, ino, flags) \ __ext4_iget((sb), (ino), (flags), __func__, __LINE__) extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern u32 ext4_dio_alignment(struct inode *inode); extern int ext4_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern void ext4_evict_inode(struct inode *); extern void ext4_clear_inode(struct inode *); extern int ext4_file_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern void ext4_dirty_inode(struct inode *, int); extern int ext4_change_inode_journal_flag(struct inode *, int); extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); extern int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino, struct ext4_iloc *iloc); extern int ext4_inode_attach_jinode(struct inode *inode); extern int ext4_can_truncate(struct inode *inode); extern int ext4_truncate(struct inode *); extern int ext4_break_layouts(struct inode *); extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length); extern void ext4_set_inode_flags(struct inode *, bool init); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); extern int ext4_writepage_trans_blocks(struct inode *); extern int ext4_normal_submit_inode_data_buffers(struct jbd2_inode *jinode); extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t lend); extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern int ext4_get_projid(struct inode *inode, kprojid_t *projid); extern void ext4_da_release_space(struct inode *inode, int to_free); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, ext4_lblk_t len); /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks); extern void ext4_ind_truncate(handle_t *, struct inode *inode); extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end); /* ioctl.c */ extern long ext4_ioctl(struct file *, unsigned int, unsigned long); extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); int ext4_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); int ext4_update_overhead(struct super_block *sb, bool force); int ext4_force_shutdown(struct super_block *sb, u32 flags); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); extern int ext4_ind_migrate(struct inode *inode); /* namei.c */ extern int ext4_init_new_dir(handle_t *handle, struct inode *dir, struct inode *inode); extern int ext4_dirblock_csum_verify(struct inode *inode, struct buffer_head *bh); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, __u32 start_minor_hash, __u32 *next_hash); extern int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, struct inode *dir, struct ext4_filename *fname, unsigned int offset, struct ext4_dir_entry_2 **res_dir); extern int ext4_generic_delete_entry(struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, void *entry_buf, int buf_size, int csum_size); extern bool ext4_empty_dir(struct inode *inode); /* resize.c */ extern void ext4_kvfree_array_rcu(void *to_free); extern int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input); extern int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, ext4_fsblk_t n_blocks_count); extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count); extern unsigned int ext4_list_backups(struct super_block *sb, unsigned int *three, unsigned int *five, unsigned int *seven); /* super.c */ extern struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, blk_opf_t op_flags); extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block); extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io); extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io); extern int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait); extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block); extern int ext4_seq_options_show(struct seq_file *seq, void *offset); extern int ext4_calculate_overhead(struct super_block *sb); extern __le32 ext4_superblock_csum(struct super_block *sb, struct ext4_super_block *es); extern void ext4_superblock_csum_set(struct super_block *sb); extern int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup); extern const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]); extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t block_group, unsigned int flags); extern unsigned int ext4_num_base_meta_blocks(struct super_block *sb, ext4_group_t block_group); extern __printf(7, 8) void __ext4_error(struct super_block *, const char *, unsigned int, bool, int, __u64, const char *, ...); extern __printf(6, 7) void __ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t, int, const char *, ...); extern __printf(5, 6) void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t, const char *, ...); extern void __ext4_std_error(struct super_block *, const char *, unsigned int, int); extern __printf(4, 5) void __ext4_warning(struct super_block *, const char *, unsigned int, const char *, ...); extern __printf(4, 5) void __ext4_warning_inode(const struct inode *inode, const char *function, unsigned int line, const char *fmt, ...); extern __printf(3, 4) void __ext4_msg(struct super_block *, const char *, const char *, ...); extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp, const char *, unsigned int, const char *); extern __printf(7, 8) void __ext4_grp_locked_error(const char *, unsigned int, struct super_block *, ext4_group_t, unsigned long, ext4_fsblk_t, const char *, ...); #define EXT4_ERROR_INODE(inode, fmt, a...) \ ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a) #define EXT4_ERROR_INODE_ERR(inode, err, fmt, a...) \ __ext4_error_inode((inode), __func__, __LINE__, 0, (err), (fmt), ## a) #define ext4_error_inode_block(inode, block, err, fmt, a...) \ __ext4_error_inode((inode), __func__, __LINE__, (block), (err), \ (fmt), ## a) #define EXT4_ERROR_FILE(file, block, fmt, a...) \ ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a) #define ext4_abort(sb, err, fmt, a...) \ __ext4_error((sb), __func__, __LINE__, true, (err), 0, (fmt), ## a) #ifdef CONFIG_PRINTK #define ext4_error_inode(inode, func, line, block, fmt, ...) \ __ext4_error_inode(inode, func, line, block, 0, fmt, ##__VA_ARGS__) #define ext4_error_inode_err(inode, func, line, block, err, fmt, ...) \ __ext4_error_inode((inode), (func), (line), (block), \ (err), (fmt), ##__VA_ARGS__) #define ext4_error_file(file, func, line, block, fmt, ...) \ __ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__) #define ext4_error(sb, fmt, ...) \ __ext4_error((sb), __func__, __LINE__, false, 0, 0, (fmt), \ ##__VA_ARGS__) #define ext4_error_err(sb, err, fmt, ...) \ __ext4_error((sb), __func__, __LINE__, false, (err), 0, (fmt), \ ##__VA_ARGS__) #define ext4_warning(sb, fmt, ...) \ __ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__) #define ext4_warning_inode(inode, fmt, ...) \ __ext4_warning_inode(inode, __func__, __LINE__, fmt, ##__VA_ARGS__) #define ext4_msg(sb, level, fmt, ...) \ __ext4_msg(sb, level, fmt, ##__VA_ARGS__) #define dump_mmp_msg(sb, mmp, msg) \ __dump_mmp_msg(sb, mmp, __func__, __LINE__, msg) #define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...) \ __ext4_grp_locked_error(__func__, __LINE__, sb, grp, ino, block, \ fmt, ##__VA_ARGS__) #else #define ext4_error_inode(inode, func, line, block, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_error_inode(inode, "", 0, block, 0, " "); \ } while (0) #define ext4_error_inode_err(inode, func, line, block, err, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_error_inode(inode, "", 0, block, err, " "); \ } while (0) #define ext4_error_file(file, func, line, block, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_error_file(file, "", 0, block, " "); \ } while (0) #define ext4_error(sb, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_error(sb, "", 0, false, 0, 0, " "); \ } while (0) #define ext4_error_err(sb, err, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_error(sb, "", 0, false, err, 0, " "); \ } while (0) #define ext4_warning(sb, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_warning(sb, "", 0, " "); \ } while (0) #define ext4_warning_inode(inode, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_warning_inode(inode, "", 0, " "); \ } while (0) #define ext4_msg(sb, level, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_msg(sb, "", " "); \ } while (0) #define dump_mmp_msg(sb, mmp, msg) \ __dump_mmp_msg(sb, mmp, "", 0, "") #define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_grp_locked_error("", 0, sb, grp, ino, block, " "); \ } while (0) #endif extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg); extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, struct ext4_group_desc *bg); extern ext4_fsblk_t ext4_inode_table(struct super_block *sb, struct ext4_group_desc *bg); extern __u32 ext4_free_group_clusters(struct super_block *sb, struct ext4_group_desc *bg); extern __u32 ext4_free_inodes_count(struct super_block *sb, struct ext4_group_desc *bg); extern __u32 ext4_used_dirs_count(struct super_block *sb, struct ext4_group_desc *bg); extern __u32 ext4_itable_unused_count(struct super_block *sb, struct ext4_group_desc *bg); extern void ext4_block_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk); extern void ext4_inode_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk); extern void ext4_inode_table_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk); extern void ext4_free_group_clusters_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_free_inodes_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group, struct ext4_group_desc *gdp); extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group, struct ext4_group_desc *gdp); extern int ext4_register_li_request(struct super_block *sb, ext4_group_t first_not_zeroed); static inline int ext4_has_metadata_csum(struct super_block *sb) { WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) && !EXT4_SB(sb)->s_chksum_driver); return ext4_has_feature_metadata_csum(sb) && (EXT4_SB(sb)->s_chksum_driver != NULL); } static inline int ext4_has_group_desc_csum(struct super_block *sb) { return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb); } #define ext4_read_incompat_64bit_val(es, name) \ (((es)->s_feature_incompat & cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT) \ ? (ext4_fsblk_t)le32_to_cpu(es->name##_hi) << 32 : 0) | \ le32_to_cpu(es->name##_lo)) static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { return ext4_read_incompat_64bit_val(es, s_blocks_count); } static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es) { return ext4_read_incompat_64bit_val(es, s_r_blocks_count); } static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es) { return ext4_read_incompat_64bit_val(es, s_free_blocks_count); } static inline void ext4_blocks_count_set(struct ext4_super_block *es, ext4_fsblk_t blk) { es->s_blocks_count_lo = cpu_to_le32((u32)blk); es->s_blocks_count_hi = cpu_to_le32(blk >> 32); } static inline void ext4_free_blocks_count_set(struct ext4_super_block *es, ext4_fsblk_t blk) { es->s_free_blocks_count_lo = cpu_to_le32((u32)blk); es->s_free_blocks_count_hi = cpu_to_le32(blk >> 32); } static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, ext4_fsblk_t blk) { es->s_r_blocks_count_lo = cpu_to_le32((u32)blk); es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32); } static inline loff_t ext4_isize(struct super_block *sb, struct ext4_inode *raw_inode) { if (ext4_has_feature_largedir(sb) || S_ISREG(le16_to_cpu(raw_inode->i_mode))) return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) | le32_to_cpu(raw_inode->i_size_lo); return (loff_t) le32_to_cpu(raw_inode->i_size_lo); } static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size) { raw_inode->i_size_lo = cpu_to_le32(i_size); raw_inode->i_size_high = cpu_to_le32(i_size >> 32); } /* * Reading s_groups_count requires using smp_rmb() afterwards. See * the locking protocol documented in the comments of ext4_group_add() * in resize.c */ static inline ext4_group_t ext4_get_groups_count(struct super_block *sb) { ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; smp_rmb(); return ngroups; } static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi, ext4_group_t block_group) { return block_group >> sbi->s_log_groups_per_flex; } static inline unsigned int ext4_flex_bg_size(struct ext4_sb_info *sbi) { return 1 << sbi->s_log_groups_per_flex; } #define ext4_std_error(sb, errno) \ do { \ if ((errno)) \ __ext4_std_error((sb), __func__, __LINE__, (errno)); \ } while (0) #ifdef CONFIG_SMP /* Each CPU can accumulate percpu_counter_batch clusters in their local * counters. So we need to make sure we have free clusters more * than percpu_counter_batch * nr_cpu_ids. Also add a window of 4 times. */ #define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids)) #else #define EXT4_FREECLUSTERS_WATERMARK 0 #endif /* Update i_disksize. Requires i_rwsem to avoid races with truncate */ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) { WARN_ON_ONCE(S_ISREG(inode->i_mode) && !inode_is_locked(inode)); down_write(&EXT4_I(inode)->i_data_sem); if (newsize > EXT4_I(inode)->i_disksize) WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize); up_write(&EXT4_I(inode)->i_data_sem); } /* Update i_size, i_disksize. Requires i_rwsem to avoid races with truncate */ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize) { int changed = 0; if (newsize > inode->i_size) { i_size_write(inode, newsize); changed = 1; } if (newsize > EXT4_I(inode)->i_disksize) { ext4_update_i_disksize(inode, newsize); changed |= 2; } return changed; } int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, loff_t len); struct ext4_group_info { unsigned long bb_state; #ifdef AGGRESSIVE_CHECK unsigned long bb_check_counter; #endif struct rb_root bb_free_root; ext4_grpblk_t bb_first_free; /* first free block */ ext4_grpblk_t bb_free; /* total free blocks */ ext4_grpblk_t bb_fragments; /* nr of freespace fragments */ int bb_avg_fragment_size_order; /* order of average fragment in BG */ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */ ext4_group_t bb_group; /* Group number */ struct list_head bb_prealloc_list; #ifdef DOUBLE_CHECK void *bb_bitmap; #endif struct rw_semaphore alloc_sem; struct list_head bb_avg_fragment_size_node; struct list_head bb_largest_free_order_node; ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block * regions, index is order. * bb_counters[3] = 5 means * 5 free 8-block regions. */ }; #define EXT4_GROUP_INFO_NEED_INIT_BIT 0 #define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1 #define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2 #define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT 3 #define EXT4_GROUP_INFO_BBITMAP_CORRUPT \ (1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT) #define EXT4_GROUP_INFO_IBITMAP_CORRUPT \ (1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT) #define EXT4_GROUP_INFO_BBITMAP_READ_BIT 4 #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_BBITMAP_CORRUPT(grp) \ (test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_IBITMAP_CORRUPT(grp) \ (test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_WAS_TRIMMED(grp) \ (test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_SET_TRIMMED(grp) \ (set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \ (clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_TEST_AND_SET_READ(grp) \ (test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state))) #define EXT4_MAX_CONTENTION 8 #define EXT4_CONTENTION_THRESHOLD 2 static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb, ext4_group_t group) { return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group); } /* * Returns true if the filesystem is busy enough that attempts to * access the block group locks has run into contention. */ static inline int ext4_fs_is_busy(struct ext4_sb_info *sbi) { return (atomic_read(&sbi->s_lock_busy) > EXT4_CONTENTION_THRESHOLD); } static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group) { spinlock_t *lock = ext4_group_lock_ptr(sb, group); if (spin_trylock(lock)) /* * We're able to grab the lock right away, so drop the * lock contention counter. */ atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, -1, 0); else { /* * The lock is busy, so bump the contention counter, * and then wait on the spin lock. */ atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, 1, EXT4_MAX_CONTENTION); spin_lock(lock); } } static inline void ext4_unlock_group(struct super_block *sb, ext4_group_t group) { spin_unlock(ext4_group_lock_ptr(sb, group)); } #ifdef CONFIG_QUOTA static inline bool ext4_quota_capable(struct super_block *sb) { return (test_opt(sb, QUOTA) || ext4_has_feature_quota(sb)); } static inline bool ext4_is_quota_journalled(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); return (ext4_has_feature_quota(sb) || sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]); } int ext4_enable_quotas(struct super_block *sb); #endif /* * Block validity checking */ #define ext4_check_indirect_blockref(inode, bh) \ ext4_check_blockref(__func__, __LINE__, inode, \ (__le32 *)(bh)->b_data, \ EXT4_ADDR_PER_BLOCK((inode)->i_sb)) #define ext4_ind_check_inode(inode) \ ext4_check_blockref(__func__, __LINE__, inode, \ EXT4_I(inode)->i_data, \ EXT4_NDIR_BLOCKS) /* * Inodes and files operations */ /* dir.c */ extern const struct file_operations ext4_dir_operations; /* file.c */ extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); /* inline.c */ extern int ext4_get_max_inline_size(struct inode *inode); extern int ext4_find_inline_data_nolock(struct inode *inode); extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode); int ext4_readpage_inline(struct inode *inode, struct folio *folio); extern int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, struct page **pagep); int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct folio *folio); extern int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, struct page **pagep, void **fsdata); extern int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode); extern int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent, struct inode *inode); extern int ext4_read_inline_dir(struct file *filp, struct dir_context *ctx, int *has_inline_data); extern int ext4_inlinedir_to_tree(struct file *dir_file, struct inode *dir, ext4_lblk_t block, struct dx_hash_info *hinfo, __u32 start_hash, __u32 start_minor_hash, int *has_inline_data); extern struct buffer_head *ext4_find_inline_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir, int *has_inline_data); extern int ext4_delete_inline_entry(handle_t *handle, struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, int *has_inline_data); extern bool empty_inline_dir(struct inode *dir, int *has_inline_data); extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode, struct ext4_dir_entry_2 **parent_de, int *retval); extern void *ext4_read_inline_link(struct inode *inode); struct iomap; extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap); extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline); extern int ext4_convert_inline_data(struct inode *inode); static inline int ext4_has_inline_data(struct inode *inode) { return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) && EXT4_I(inode)->i_inline_off; } /* namei.c */ extern const struct inode_operations ext4_dir_inode_operations; extern const struct inode_operations ext4_special_inode_operations; extern struct dentry *ext4_get_parent(struct dentry *child); extern struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, struct ext4_dir_entry_2 *de, int blocksize, int csum_size, unsigned int parent_ino, int dotdot_real_len); extern void ext4_initialize_dirent_tail(struct buffer_head *bh, unsigned int blocksize); extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode, struct buffer_head *bh); extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name, struct inode *inode, struct dentry *dentry); extern int __ext4_link(struct inode *dir, struct inode *inode, struct dentry *dentry); #define S_SHIFT 12 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { [S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = EXT4_FT_DIR, [S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV, [S_IFBLK >> S_SHIFT] = EXT4_FT_BLKDEV, [S_IFIFO >> S_SHIFT] = EXT4_FT_FIFO, [S_IFSOCK >> S_SHIFT] = EXT4_FT_SOCK, [S_IFLNK >> S_SHIFT] = EXT4_FT_SYMLINK, }; static inline void ext4_set_de_type(struct super_block *sb, struct ext4_dir_entry_2 *de, umode_t mode) { if (ext4_has_feature_filetype(sb)) de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; } /* readpages.c */ extern int ext4_mpage_readpages(struct inode *inode, struct readahead_control *rac, struct folio *folio); extern int __init ext4_init_post_read_processing(void); extern void ext4_exit_post_read_processing(void); /* symlink.c */ extern const struct inode_operations ext4_encrypted_symlink_inode_operations; extern const struct inode_operations ext4_symlink_inode_operations; extern const struct inode_operations ext4_fast_symlink_inode_operations; /* sysfs.c */ extern void ext4_notify_error_sysfs(struct ext4_sb_info *sbi); extern int ext4_register_sysfs(struct super_block *sb); extern void ext4_unregister_sysfs(struct super_block *sb); extern int __init ext4_init_sysfs(void); extern void ext4_exit_sysfs(void); /* block_validity */ extern void ext4_release_system_zone(struct super_block *sb); extern int ext4_setup_system_zone(struct super_block *sb); extern int __init ext4_init_system_zone(void); extern void ext4_exit_system_zone(void); extern int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, unsigned int count); extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int); extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode, ext4_fsblk_t start_blk, unsigned int count); /* extents.c */ struct ext4_ext_path; struct ext4_extent; /* * Maximum number of logical blocks in a file; ext4_extent's ee_block is * __le32. */ #define EXT_MAX_BLOCKS 0xffffffff extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode); extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents); extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); extern int ext4_ext_truncate(handle_t *, struct inode *); extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end); extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); extern long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len); extern int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end); extern int ext4_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, struct ext4_ext_path *path); extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path **, struct ext4_extent *, int); extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t, struct ext4_ext_path **, int flags); extern void ext4_free_ext_path(struct ext4_ext_path *); extern int ext4_ext_check_inode(struct inode *inode); extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); extern int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); extern int ext4_ext_precache(struct inode *inode); extern int ext4_swap_extents(handle_t *handle, struct inode *inode1, struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2, ext4_lblk_t count, int mark_unwritten,int *err); extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu); extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode, int check_cred, int restart_cred, int revoke_cred); extern void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end); extern int ext4_ext_replay_set_iblocks(struct inode *inode); extern int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start, int len, int unwritten, ext4_fsblk_t pblk); extern int ext4_ext_clear_bb(struct inode *inode); /* move_extent.c */ extern void ext4_double_down_write_data_sem(struct inode *first, struct inode *second); extern void ext4_double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode); extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 start_orig, __u64 start_donor, __u64 len, __u64 *moved_len); /* page-io.c */ extern int __init ext4_init_pageio(void); extern void ext4_exit_pageio(void); extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags); extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end); extern int ext4_put_io_end(ext4_io_end_t *io_end); extern void ext4_put_io_end_defer(ext4_io_end_t *io_end); extern void ext4_io_submit_init(struct ext4_io_submit *io, struct writeback_control *wbc); extern void ext4_end_io_rsv_work(struct work_struct *work); extern void ext4_io_submit(struct ext4_io_submit *io); int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *page, size_t len); extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end); extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end); /* mmp.c */ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); /* mmp.c */ extern void ext4_stop_mmpd(struct ext4_sb_info *sbi); /* verity.c */ extern const struct fsverity_operations ext4_verityops; /* orphan.c */ extern int ext4_orphan_add(handle_t *, struct inode *); extern int ext4_orphan_del(handle_t *, struct inode *); extern void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es); extern void ext4_release_orphan_info(struct super_block *sb); extern int ext4_init_orphan_info(struct super_block *sb); extern int ext4_orphan_file_empty(struct super_block *sb); extern void ext4_orphan_file_block_trigger( struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh, void *data, size_t size); /* * Add new method to test whether block and inode bitmaps are properly * initialized. With uninit_bg reading the block from disk is not enough * to mark the bitmap uptodate. We need to also zero-out the bitmap */ #define BH_BITMAP_UPTODATE BH_JBDPrivateStart static inline int bitmap_uptodate(struct buffer_head *bh) { return (buffer_uptodate(bh) && test_bit(BH_BITMAP_UPTODATE, &(bh)->b_state)); } static inline void set_bitmap_uptodate(struct buffer_head *bh) { set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state); } /* For ioend & aio unwritten conversion wait queues */ #define EXT4_WQ_HASH_SZ 37 #define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\ EXT4_WQ_HASH_SZ]) extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; extern int ext4_resize_begin(struct super_block *sb); extern int ext4_resize_end(struct super_block *sb, bool update_backups); static inline void ext4_set_io_unwritten_flag(struct inode *inode, struct ext4_io_end *io_end) { if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { io_end->flag |= EXT4_IO_END_UNWRITTEN; atomic_inc(&EXT4_I(inode)->i_unwritten); } } static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) { struct inode *inode = io_end->inode; if (io_end->flag & EXT4_IO_END_UNWRITTEN) { io_end->flag &= ~EXT4_IO_END_UNWRITTEN; /* Wake up anyone waiting on unwritten extent conversion */ if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) wake_up_all(ext4_ioend_wq(inode)); } } extern const struct iomap_ops ext4_iomap_ops; extern const struct iomap_ops ext4_iomap_overwrite_ops; extern const struct iomap_ops ext4_iomap_report_ops; static inline int ext4_buffer_uptodate(struct buffer_head *bh) { /* * If the buffer has the write error flag, we have failed * to write out data in the block. In this case, we don't * have to read the block because we may read the old data * successfully. */ if (buffer_write_io_error(bh)) set_buffer_uptodate(bh); return buffer_uptodate(bh); } #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _EXT4_H */ |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 | #ifndef _NF_FLOW_TABLE_H #define _NF_FLOW_TABLE_H #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/rhashtable-types.h> #include <linux/rcupdate.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> #include <net/flow_offload.h> #include <net/dst.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> struct nf_flowtable; struct nf_flow_rule; struct flow_offload; enum flow_offload_tuple_dir; struct nf_flow_key { struct flow_dissector_key_meta meta; struct flow_dissector_key_control control; struct flow_dissector_key_control enc_control; struct flow_dissector_key_basic basic; struct flow_dissector_key_vlan vlan; struct flow_dissector_key_vlan cvlan; union { struct flow_dissector_key_ipv4_addrs ipv4; struct flow_dissector_key_ipv6_addrs ipv6; }; struct flow_dissector_key_keyid enc_key_id; union { struct flow_dissector_key_ipv4_addrs enc_ipv4; struct flow_dissector_key_ipv6_addrs enc_ipv6; }; struct flow_dissector_key_tcp tcp; struct flow_dissector_key_ports tp; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct nf_flow_match { struct flow_dissector dissector; struct nf_flow_key key; struct nf_flow_key mask; }; struct nf_flow_rule { struct nf_flow_match match; struct flow_rule *rule; }; struct nf_flowtable_type { struct list_head list; int family; int (*init)(struct nf_flowtable *ft); bool (*gc)(const struct flow_offload *flow); int (*setup)(struct nf_flowtable *ft, struct net_device *dev, enum flow_block_command cmd); int (*action)(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); void (*free)(struct nf_flowtable *ft); void (*get)(struct nf_flowtable *ft); void (*put)(struct nf_flowtable *ft); nf_hookfn *hook; struct module *owner; }; enum nf_flowtable_flags { NF_FLOWTABLE_HW_OFFLOAD = 0x1, /* NFT_FLOWTABLE_HW_OFFLOAD */ NF_FLOWTABLE_COUNTER = 0x2, /* NFT_FLOWTABLE_COUNTER */ }; struct nf_flowtable { unsigned int flags; /* readonly in datapath */ int priority; /* control path (padding hole) */ struct rhashtable rhashtable; /* datapath, read-mostly members come first */ struct list_head list; /* slowpath parts */ const struct nf_flowtable_type *type; struct delayed_work gc_work; struct flow_block flow_block; struct rw_semaphore flow_block_lock; /* Guards flow_block */ possible_net_t net; }; static inline bool nf_flowtable_hw_offload(struct nf_flowtable *flowtable) { return flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD; } enum flow_offload_tuple_dir { FLOW_OFFLOAD_DIR_ORIGINAL = IP_CT_DIR_ORIGINAL, FLOW_OFFLOAD_DIR_REPLY = IP_CT_DIR_REPLY, }; #define FLOW_OFFLOAD_DIR_MAX IP_CT_DIR_MAX enum flow_offload_xmit_type { FLOW_OFFLOAD_XMIT_UNSPEC = 0, FLOW_OFFLOAD_XMIT_NEIGH, FLOW_OFFLOAD_XMIT_XFRM, FLOW_OFFLOAD_XMIT_DIRECT, FLOW_OFFLOAD_XMIT_TC, }; #define NF_FLOW_TABLE_ENCAP_MAX 2 struct flow_offload_tuple { union { struct in_addr src_v4; struct in6_addr src_v6; }; union { struct in_addr dst_v4; struct in6_addr dst_v6; }; struct { __be16 src_port; __be16 dst_port; }; int iifidx; u8 l3proto; u8 l4proto; struct { u16 id; __be16 proto; } encap[NF_FLOW_TABLE_ENCAP_MAX]; /* All members above are keys for lookups, see flow_offload_hash(). */ struct { } __hash; u8 dir:2, xmit_type:3, encap_num:2, in_vlan_ingress:2; u16 mtu; union { struct { struct dst_entry *dst_cache; u32 dst_cookie; }; struct { u32 ifidx; u32 hw_ifidx; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; } out; struct { u32 iifidx; } tc; }; }; struct flow_offload_tuple_rhash { struct rhash_head node; struct flow_offload_tuple tuple; }; enum nf_flow_flags { NF_FLOW_SNAT, NF_FLOW_DNAT, NF_FLOW_TEARDOWN, NF_FLOW_HW, NF_FLOW_HW_DYING, NF_FLOW_HW_DEAD, NF_FLOW_HW_PENDING, NF_FLOW_HW_BIDIRECTIONAL, NF_FLOW_HW_ESTABLISHED, }; enum flow_offload_type { NF_FLOW_OFFLOAD_UNSPEC = 0, NF_FLOW_OFFLOAD_ROUTE, }; struct flow_offload { struct flow_offload_tuple_rhash tuplehash[FLOW_OFFLOAD_DIR_MAX]; struct nf_conn *ct; unsigned long flags; u16 type; u32 timeout; struct rcu_head rcu_head; }; #define NF_FLOW_TIMEOUT (30 * HZ) #define nf_flowtable_time_stamp (u32)jiffies unsigned long flow_offload_get_timeout(struct flow_offload *flow); static inline __s32 nf_flow_timeout_delta(unsigned int timeout) { return (__s32)(timeout - nf_flowtable_time_stamp); } struct nf_flow_route { struct { struct dst_entry *dst; struct { u32 ifindex; struct { u16 id; __be16 proto; } encap[NF_FLOW_TABLE_ENCAP_MAX]; u8 num_encaps:2, ingress_vlans:2; } in; struct { u32 ifindex; u32 hw_ifindex; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; } out; enum flow_offload_xmit_type xmit_type; } tuple[FLOW_OFFLOAD_DIR_MAX]; }; struct flow_offload *flow_offload_alloc(struct nf_conn *ct); void flow_offload_free(struct flow_offload *flow); static inline int nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, flow_setup_cb_t *cb, void *cb_priv) { struct flow_block *block = &flow_table->flow_block; struct flow_block_cb *block_cb; int err = 0; down_write(&flow_table->flow_block_lock); block_cb = flow_block_cb_lookup(block, cb, cb_priv); if (block_cb) { err = -EEXIST; goto unlock; } block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL); if (IS_ERR(block_cb)) { err = PTR_ERR(block_cb); goto unlock; } list_add_tail(&block_cb->list, &block->cb_list); up_write(&flow_table->flow_block_lock); if (flow_table->type->get) flow_table->type->get(flow_table); return 0; unlock: up_write(&flow_table->flow_block_lock); return err; } static inline void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, flow_setup_cb_t *cb, void *cb_priv) { struct flow_block *block = &flow_table->flow_block; struct flow_block_cb *block_cb; down_write(&flow_table->flow_block_lock); block_cb = flow_block_cb_lookup(block, cb, cb_priv); if (block_cb) { list_del(&block_cb->list); flow_block_cb_free(block_cb); } else { WARN_ON(true); } up_write(&flow_table->flow_block_lock); if (flow_table->type->put) flow_table->type->put(flow_table); } void flow_offload_route_init(struct flow_offload *flow, struct nf_flow_route *route); int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, struct flow_offload *flow, bool force); struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); void nf_flow_table_gc_run(struct nf_flowtable *flow_table); void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable, struct net_device *dev); void nf_flow_table_cleanup(struct net_device *dev); int nf_flow_table_init(struct nf_flowtable *flow_table); void nf_flow_table_free(struct nf_flowtable *flow_table); void flow_offload_teardown(struct flow_offload *flow); void nf_flow_snat_port(const struct flow_offload *flow, struct sk_buff *skb, unsigned int thoff, u8 protocol, enum flow_offload_tuple_dir dir); void nf_flow_dnat_port(const struct flow_offload *flow, struct sk_buff *skb, unsigned int thoff, u8 protocol, enum flow_offload_tuple_dir dir); struct flow_ports { __be16 source, dest; }; struct nf_flowtable *nf_flowtable_by_dev(const struct net_device *dev); int nf_flow_offload_xdp_setup(struct nf_flowtable *flowtable, struct net_device *dev, enum flow_block_command cmd); unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); #if (IS_BUILTIN(CONFIG_NF_FLOW_TABLE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ (IS_MODULE(CONFIG_NF_FLOW_TABLE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) extern int nf_flow_register_bpf(void); #else static inline int nf_flow_register_bpf(void) { return 0; } #endif #define MODULE_ALIAS_NF_FLOWTABLE(family) \ MODULE_ALIAS("nf-flowtable-" __stringify(family)) void nf_flow_offload_add(struct nf_flowtable *flowtable, struct flow_offload *flow); void nf_flow_offload_del(struct nf_flowtable *flowtable, struct flow_offload *flow); void nf_flow_offload_stats(struct nf_flowtable *flowtable, struct flow_offload *flow); void nf_flow_table_offload_flush(struct nf_flowtable *flowtable); void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable); int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, struct net_device *dev, enum flow_block_command cmd); int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); int nf_flow_table_offload_init(void); void nf_flow_table_offload_exit(void); static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb) { __be16 proto; proto = *((__be16 *)(skb_mac_header(skb) + ETH_HLEN + sizeof(struct pppoe_hdr))); switch (proto) { case htons(PPP_IP): return htons(ETH_P_IP); case htons(PPP_IPV6): return htons(ETH_P_IPV6); } return 0; } static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto) { if (!pskb_may_pull(skb, PPPOE_SES_HLEN)) return false; *inner_proto = __nf_flow_pppoe_proto(skb); return true; } #define NF_FLOW_TABLE_STAT_INC(net, count) __this_cpu_inc((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_DEC(net, count) __this_cpu_dec((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count) \ this_cpu_inc((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_DEC_ATOMIC(net, count) \ this_cpu_dec((net)->ft.stat->count) #ifdef CONFIG_NF_FLOW_TABLE_PROCFS int nf_flow_table_init_proc(struct net *net); void nf_flow_table_fini_proc(struct net *net); #else static inline int nf_flow_table_init_proc(struct net *net) { return 0; } static inline void nf_flow_table_fini_proc(struct net *net) { } #endif /* CONFIG_NF_FLOW_TABLE_PROCFS */ #endif /* _NF_FLOW_TABLE_H */ |
| 60 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 | /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/xattr.h Extended attributes handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved. Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #ifndef _LINUX_XATTR_H #define _LINUX_XATTR_H #include <linux/slab.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/user_namespace.h> #include <uapi/linux/xattr.h> struct inode; struct dentry; static inline bool is_posix_acl_xattr(const char *name) { return (strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0); } /* * struct xattr_handler: When @name is set, match attributes with exactly that * name. When @prefix is set instead, match attributes with that prefix and * with a non-empty suffix. */ struct xattr_handler { const char *name; const char *prefix; int flags; /* fs private flags */ bool (*list)(struct dentry *dentry); int (*get)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; /** * xattr_handler_can_list - check whether xattr can be listed * @handler: handler for this type of xattr * @dentry: dentry whose inode xattr to list * * Determine whether the xattr associated with @dentry can be listed given * @handler. * * Return: true if xattr can be listed, false if not. */ static inline bool xattr_handler_can_list(const struct xattr_handler *handler, struct dentry *dentry) { return handler && (!handler->list || handler->list(dentry)); } const char *xattr_full_name(const struct xattr_handler *, const char *); struct xattr { const char *name; void *value; size_t value_len; }; ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); ssize_t vfs_getxattr(struct mnt_idmap *, struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); int __vfs_setxattr(struct mnt_idmap *, struct dentry *, struct inode *, const char *, const void *, size_t, int); int __vfs_setxattr_noperm(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); int __vfs_setxattr_locked(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int, struct inode **); int vfs_setxattr(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); int __vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); int __vfs_removexattr_locked(struct mnt_idmap *, struct dentry *, const char *, struct inode **); int vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); int vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); int xattr_supports_user_prefix(struct inode *inode); static inline const char *xattr_prefix(const struct xattr_handler *handler) { return handler->prefix ?: handler->name; } struct simple_xattrs { struct rb_root rb_root; rwlock_t lock; }; struct simple_xattr { struct rb_node rb_node; char *name; size_t size; char value[]; }; void simple_xattrs_init(struct simple_xattrs *xattrs); void simple_xattrs_free(struct simple_xattrs *xattrs, size_t *freed_space); size_t simple_xattr_space(const char *name, size_t size); struct simple_xattr *simple_xattr_alloc(const void *value, size_t size); void simple_xattr_free(struct simple_xattr *xattr); int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); struct simple_xattr *simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags); ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name); #endif /* _LINUX_XATTR_H */ |
| 2 1853 2018 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _NET_RPS_H #define _NET_RPS_H #include <linux/types.h> #include <linux/static_key.h> #include <net/sock.h> #include <net/hotdata.h> #ifdef CONFIG_RPS extern struct static_key_false rps_needed; extern struct static_key_false rfs_needed; /* * This structure holds an RPS map which can be of variable length. The * map is an array of CPUs. */ struct rps_map { unsigned int len; struct rcu_head rcu; u16 cpus[]; }; #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) /* * The rps_dev_flow structure contains the mapping of a flow to a CPU, the * tail pointer for that CPU's input queue at the time of last enqueue, and * a hardware filter index. */ struct rps_dev_flow { u16 cpu; u16 filter; unsigned int last_qtail; }; #define RPS_NO_FILTER 0xffff /* * The rps_dev_flow_table structure contains a table of flow mappings. */ struct rps_dev_flow_table { unsigned int mask; struct rcu_head rcu; struct rps_dev_flow flows[]; }; #define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ ((_num) * sizeof(struct rps_dev_flow))) /* * The rps_sock_flow_table contains mappings of flows to the last CPU * on which they were processed by the application (set in recvmsg). * Each entry is a 32bit value. Upper part is the high-order bits * of flow hash, lower part is CPU number. * rps_cpu_mask is used to partition the space, depending on number of * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, * meaning we use 32-6=26 bits for the hash. */ struct rps_sock_flow_table { u32 mask; u32 ents[] ____cacheline_aligned_in_smp; }; #define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) #define RPS_NO_CPU 0xffff static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, u32 hash) { unsigned int index = hash & table->mask; u32 val = hash & ~net_hotdata.rps_cpu_mask; /* We only give a hint, preemption can change CPU under us */ val |= raw_smp_processor_id(); /* The following WRITE_ONCE() is paired with the READ_ONCE() * here, and another one in get_rps_cpu(). */ if (READ_ONCE(table->ents[index]) != val) WRITE_ONCE(table->ents[index], val); } #endif /* CONFIG_RPS */ static inline void sock_rps_record_flow_hash(__u32 hash) { #ifdef CONFIG_RPS struct rps_sock_flow_table *sock_flow_table; if (!hash) return; rcu_read_lock(); sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); if (sock_flow_table) rps_record_sock_flow(sock_flow_table, hash); rcu_read_unlock(); #endif } static inline void sock_rps_record_flow(const struct sock *sk) { #ifdef CONFIG_RPS if (static_branch_unlikely(&rfs_needed)) { /* Reading sk->sk_rxhash might incur an expensive cache line * miss. * * TCP_ESTABLISHED does cover almost all states where RFS * might be useful, and is cheaper [1] than testing : * IPv4: inet_sk(sk)->inet_daddr * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) * OR an additional socket flag * [1] : sk_state and sk_prot are in the same cache line. */ if (sk->sk_state == TCP_ESTABLISHED) { /* This READ_ONCE() is paired with the WRITE_ONCE() * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). */ sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); } } #endif } static inline u32 rps_input_queue_tail_incr(struct softnet_data *sd) { #ifdef CONFIG_RPS return ++sd->input_queue_tail; #else return 0; #endif } static inline void rps_input_queue_tail_save(u32 *dest, u32 tail) { #ifdef CONFIG_RPS WRITE_ONCE(*dest, tail); #endif } static inline void rps_input_queue_head_add(struct softnet_data *sd, int val) { #ifdef CONFIG_RPS WRITE_ONCE(sd->input_queue_head, sd->input_queue_head + val); #endif } static inline void rps_input_queue_head_incr(struct softnet_data *sd) { rps_input_queue_head_add(sd, 1); } #endif /* _NET_RPS_H */ |
| 2 2 2 2 2 6 1 3 2 2 5 3 1 2 1 1 1 1 2 2 9 1 5 4 2 1 2 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> #include <linux/bpf-netns.h> #include <linux/filter.h> #include <net/net_namespace.h> /* * Functions to manage BPF programs attached to netns */ struct bpf_netns_link { struct bpf_link link; enum bpf_attach_type type; enum netns_bpf_attach_type netns_type; /* We don't hold a ref to net in order to auto-detach the link * when netns is going away. Instead we rely on pernet * pre_exit callback to clear this pointer. Must be accessed * with netns_bpf_mutex held. */ struct net *net; struct list_head node; /* node in list of links attached to net */ }; /* Protects updates to netns_bpf */ DEFINE_MUTEX(netns_bpf_mutex); static void netns_bpf_attach_type_unneed(enum netns_bpf_attach_type type) { switch (type) { #ifdef CONFIG_INET case NETNS_BPF_SK_LOOKUP: static_branch_dec(&bpf_sk_lookup_enabled); break; #endif default: break; } } static void netns_bpf_attach_type_need(enum netns_bpf_attach_type type) { switch (type) { #ifdef CONFIG_INET case NETNS_BPF_SK_LOOKUP: static_branch_inc(&bpf_sk_lookup_enabled); break; #endif default: break; } } /* Must be called with netns_bpf_mutex held. */ static void netns_bpf_run_array_detach(struct net *net, enum netns_bpf_attach_type type) { struct bpf_prog_array *run_array; run_array = rcu_replace_pointer(net->bpf.run_array[type], NULL, lockdep_is_held(&netns_bpf_mutex)); bpf_prog_array_free(run_array); } static int link_index(struct net *net, enum netns_bpf_attach_type type, struct bpf_netns_link *link) { struct bpf_netns_link *pos; int i = 0; list_for_each_entry(pos, &net->bpf.links[type], node) { if (pos == link) return i; i++; } return -ENOENT; } static int link_count(struct net *net, enum netns_bpf_attach_type type) { struct list_head *pos; int i = 0; list_for_each(pos, &net->bpf.links[type]) i++; return i; } static void fill_prog_array(struct net *net, enum netns_bpf_attach_type type, struct bpf_prog_array *prog_array) { struct bpf_netns_link *pos; unsigned int i = 0; list_for_each_entry(pos, &net->bpf.links[type], node) { prog_array->items[i].prog = pos->link.prog; i++; } } static void bpf_netns_link_release(struct bpf_link *link) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); enum netns_bpf_attach_type type = net_link->netns_type; struct bpf_prog_array *old_array, *new_array; struct net *net; int cnt, idx; mutex_lock(&netns_bpf_mutex); /* We can race with cleanup_net, but if we see a non-NULL * struct net pointer, pre_exit has not run yet and wait for * netns_bpf_mutex. */ net = net_link->net; if (!net) goto out_unlock; /* Mark attach point as unused */ netns_bpf_attach_type_unneed(type); /* Remember link position in case of safe delete */ idx = link_index(net, type, net_link); list_del(&net_link->node); cnt = link_count(net, type); if (!cnt) { netns_bpf_run_array_detach(net, type); goto out_unlock; } old_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); new_array = bpf_prog_array_alloc(cnt, GFP_KERNEL); if (!new_array) { WARN_ON(bpf_prog_array_delete_safe_at(old_array, idx)); goto out_unlock; } fill_prog_array(net, type, new_array); rcu_assign_pointer(net->bpf.run_array[type], new_array); bpf_prog_array_free(old_array); out_unlock: net_link->net = NULL; mutex_unlock(&netns_bpf_mutex); } static int bpf_netns_link_detach(struct bpf_link *link) { bpf_netns_link_release(link); return 0; } static void bpf_netns_link_dealloc(struct bpf_link *link) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); kfree(net_link); } static int bpf_netns_link_update_prog(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); enum netns_bpf_attach_type type = net_link->netns_type; struct bpf_prog_array *run_array; struct net *net; int idx, ret; if (old_prog && old_prog != link->prog) return -EPERM; if (new_prog->type != link->prog->type) return -EINVAL; mutex_lock(&netns_bpf_mutex); net = net_link->net; if (!net || !check_net(net)) { /* Link auto-detached or netns dying */ ret = -ENOLINK; goto out_unlock; } run_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); idx = link_index(net, type, net_link); ret = bpf_prog_array_update_at(run_array, idx, new_prog); if (ret) goto out_unlock; old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); out_unlock: mutex_unlock(&netns_bpf_mutex); return ret; } static int bpf_netns_link_fill_info(const struct bpf_link *link, struct bpf_link_info *info) { const struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); unsigned int inum = 0; struct net *net; mutex_lock(&netns_bpf_mutex); net = net_link->net; if (net && check_net(net)) inum = net->ns.inum; mutex_unlock(&netns_bpf_mutex); info->netns.netns_ino = inum; info->netns.attach_type = net_link->type; return 0; } static void bpf_netns_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_link_info info = {}; bpf_netns_link_fill_info(link, &info); seq_printf(seq, "netns_ino:\t%u\n" "attach_type:\t%u\n", info.netns.netns_ino, info.netns.attach_type); } static const struct bpf_link_ops bpf_netns_link_ops = { .release = bpf_netns_link_release, .dealloc = bpf_netns_link_dealloc, .detach = bpf_netns_link_detach, .update_prog = bpf_netns_link_update_prog, .fill_link_info = bpf_netns_link_fill_info, .show_fdinfo = bpf_netns_link_show_fdinfo, }; /* Must be called with netns_bpf_mutex held. */ static int __netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, struct net *net, enum netns_bpf_attach_type type) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); struct bpf_prog_array *run_array; u32 prog_cnt = 0, flags = 0; run_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); if (run_array) prog_cnt = bpf_prog_array_length(run_array); if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) return -EFAULT; if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) return -EFAULT; if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) return 0; return bpf_prog_array_copy_to_user(run_array, prog_ids, attr->query.prog_cnt); } int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { enum netns_bpf_attach_type type; struct net *net; int ret; if (attr->query.query_flags) return -EINVAL; type = to_netns_bpf_attach_type(attr->query.attach_type); if (type < 0) return -EINVAL; net = get_net_ns_by_fd(attr->query.target_fd); if (IS_ERR(net)) return PTR_ERR(net); mutex_lock(&netns_bpf_mutex); ret = __netns_bpf_prog_query(attr, uattr, net, type); mutex_unlock(&netns_bpf_mutex); put_net(net); return ret; } int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_prog_array *run_array; enum netns_bpf_attach_type type; struct bpf_prog *attached; struct net *net; int ret; if (attr->target_fd || attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; net = current->nsproxy->net_ns; mutex_lock(&netns_bpf_mutex); /* Attaching prog directly is not compatible with links */ if (!list_empty(&net->bpf.links[type])) { ret = -EEXIST; goto out_unlock; } switch (type) { case NETNS_BPF_FLOW_DISSECTOR: ret = flow_dissector_bpf_prog_attach_check(net, prog); break; default: ret = -EINVAL; break; } if (ret) goto out_unlock; attached = net->bpf.progs[type]; if (attached == prog) { /* The same program cannot be attached twice */ ret = -EINVAL; goto out_unlock; } run_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); if (run_array) { WRITE_ONCE(run_array->items[0].prog, prog); } else { run_array = bpf_prog_array_alloc(1, GFP_KERNEL); if (!run_array) { ret = -ENOMEM; goto out_unlock; } run_array->items[0].prog = prog; rcu_assign_pointer(net->bpf.run_array[type], run_array); } net->bpf.progs[type] = prog; if (attached) bpf_prog_put(attached); out_unlock: mutex_unlock(&netns_bpf_mutex); return ret; } /* Must be called with netns_bpf_mutex held. */ static int __netns_bpf_prog_detach(struct net *net, enum netns_bpf_attach_type type, struct bpf_prog *old) { struct bpf_prog *attached; /* Progs attached via links cannot be detached */ if (!list_empty(&net->bpf.links[type])) return -EINVAL; attached = net->bpf.progs[type]; if (!attached || attached != old) return -ENOENT; netns_bpf_run_array_detach(net, type); net->bpf.progs[type] = NULL; bpf_prog_put(attached); return 0; } int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { enum netns_bpf_attach_type type; struct bpf_prog *prog; int ret; if (attr->target_fd) return -EINVAL; type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); mutex_lock(&netns_bpf_mutex); ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type, prog); mutex_unlock(&netns_bpf_mutex); bpf_prog_put(prog); return ret; } static int netns_bpf_max_progs(enum netns_bpf_attach_type type) { switch (type) { case NETNS_BPF_FLOW_DISSECTOR: return 1; case NETNS_BPF_SK_LOOKUP: return 64; default: return 0; } } static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, enum netns_bpf_attach_type type) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); struct bpf_prog_array *run_array; int cnt, err; mutex_lock(&netns_bpf_mutex); cnt = link_count(net, type); if (cnt >= netns_bpf_max_progs(type)) { err = -E2BIG; goto out_unlock; } /* Links are not compatible with attaching prog directly */ if (net->bpf.progs[type]) { err = -EEXIST; goto out_unlock; } switch (type) { case NETNS_BPF_FLOW_DISSECTOR: err = flow_dissector_bpf_prog_attach_check(net, link->prog); break; case NETNS_BPF_SK_LOOKUP: err = 0; /* nothing to check */ break; default: err = -EINVAL; break; } if (err) goto out_unlock; run_array = bpf_prog_array_alloc(cnt + 1, GFP_KERNEL); if (!run_array) { err = -ENOMEM; goto out_unlock; } list_add_tail(&net_link->node, &net->bpf.links[type]); fill_prog_array(net, type, run_array); run_array = rcu_replace_pointer(net->bpf.run_array[type], run_array, lockdep_is_held(&netns_bpf_mutex)); bpf_prog_array_free(run_array); /* Mark attach point as used */ netns_bpf_attach_type_need(type); out_unlock: mutex_unlock(&netns_bpf_mutex); return err; } int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog) { enum netns_bpf_attach_type netns_type; struct bpf_link_primer link_primer; struct bpf_netns_link *net_link; enum bpf_attach_type type; struct net *net; int err; if (attr->link_create.flags) return -EINVAL; type = attr->link_create.attach_type; netns_type = to_netns_bpf_attach_type(type); if (netns_type < 0) return -EINVAL; net = get_net_ns_by_fd(attr->link_create.target_fd); if (IS_ERR(net)) return PTR_ERR(net); net_link = kzalloc(sizeof(*net_link), GFP_USER); if (!net_link) { err = -ENOMEM; goto out_put_net; } bpf_link_init(&net_link->link, BPF_LINK_TYPE_NETNS, &bpf_netns_link_ops, prog); net_link->net = net; net_link->type = type; net_link->netns_type = netns_type; err = bpf_link_prime(&net_link->link, &link_primer); if (err) { kfree(net_link); goto out_put_net; } err = netns_bpf_link_attach(net, &net_link->link, netns_type); if (err) { bpf_link_cleanup(&link_primer); goto out_put_net; } put_net(net); return bpf_link_settle(&link_primer); out_put_net: put_net(net); return err; } static int __net_init netns_bpf_pernet_init(struct net *net) { int type; for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) INIT_LIST_HEAD(&net->bpf.links[type]); return 0; } static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) { enum netns_bpf_attach_type type; struct bpf_netns_link *net_link; mutex_lock(&netns_bpf_mutex); for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) { netns_bpf_run_array_detach(net, type); list_for_each_entry(net_link, &net->bpf.links[type], node) { net_link->net = NULL; /* auto-detach link */ netns_bpf_attach_type_unneed(type); } if (net->bpf.progs[type]) bpf_prog_put(net->bpf.progs[type]); } mutex_unlock(&netns_bpf_mutex); } static struct pernet_operations netns_bpf_pernet_ops __net_initdata = { .init = netns_bpf_pernet_init, .pre_exit = netns_bpf_pernet_pre_exit, }; static int __init netns_bpf_init(void) { return register_pernet_subsys(&netns_bpf_pernet_ops); } subsys_initcall(netns_bpf_init); |
| 13 13 3 10 13 13 6 6 5 5 5 5 5 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" struct linkinfo_req_info { struct ethnl_req_info base; }; struct linkinfo_reply_data { struct ethnl_reply_data base; struct ethtool_link_ksettings ksettings; struct ethtool_link_settings *lsettings; }; #define LINKINFO_REPDATA(__reply_base) \ container_of(__reply_base, struct linkinfo_reply_data, base) const struct nla_policy ethnl_linkinfo_get_policy[] = { [ETHTOOL_A_LINKINFO_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int linkinfo_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct linkinfo_reply_data *data = LINKINFO_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; data->lsettings = &data->ksettings.base; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = __ethtool_get_link_ksettings(dev, &data->ksettings); if (ret < 0 && info) GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); ethnl_ops_complete(dev); return ret; } static int linkinfo_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u8)) /* LINKINFO_PORT */ + nla_total_size(sizeof(u8)) /* LINKINFO_PHYADDR */ + nla_total_size(sizeof(u8)) /* LINKINFO_TP_MDIX */ + nla_total_size(sizeof(u8)) /* LINKINFO_TP_MDIX_CTRL */ + nla_total_size(sizeof(u8)) /* LINKINFO_TRANSCEIVER */ + 0; } static int linkinfo_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct linkinfo_reply_data *data = LINKINFO_REPDATA(reply_base); if (nla_put_u8(skb, ETHTOOL_A_LINKINFO_PORT, data->lsettings->port) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_PHYADDR, data->lsettings->phy_address) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_TP_MDIX, data->lsettings->eth_tp_mdix) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_TP_MDIX_CTRL, data->lsettings->eth_tp_mdix_ctrl) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_TRANSCEIVER, data->lsettings->transceiver)) return -EMSGSIZE; return 0; } /* LINKINFO_SET */ const struct nla_policy ethnl_linkinfo_set_policy[] = { [ETHTOOL_A_LINKINFO_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_LINKINFO_PORT] = { .type = NLA_U8 }, [ETHTOOL_A_LINKINFO_PHYADDR] = { .type = NLA_U8 }, [ETHTOOL_A_LINKINFO_TP_MDIX_CTRL] = { .type = NLA_U8 }, }; static int ethnl_set_linkinfo_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; if (!ops->get_link_ksettings || !ops->set_link_ksettings) return -EOPNOTSUPP; return 1; } static int ethnl_set_linkinfo(struct ethnl_req_info *req_info, struct genl_info *info) { struct ethtool_link_ksettings ksettings = {}; struct ethtool_link_settings *lsettings; struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; bool mod = false; int ret; ret = __ethtool_get_link_ksettings(dev, &ksettings); if (ret < 0) { GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); return ret; } lsettings = &ksettings.base; ethnl_update_u8(&lsettings->port, tb[ETHTOOL_A_LINKINFO_PORT], &mod); ethnl_update_u8(&lsettings->phy_address, tb[ETHTOOL_A_LINKINFO_PHYADDR], &mod); ethnl_update_u8(&lsettings->eth_tp_mdix_ctrl, tb[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL], &mod); if (!mod) return 0; ret = dev->ethtool_ops->set_link_ksettings(dev, &ksettings); if (ret < 0) { GENL_SET_ERR_MSG(info, "link settings update failed"); return ret; } return 1; } const struct ethnl_request_ops ethnl_linkinfo_request_ops = { .request_cmd = ETHTOOL_MSG_LINKINFO_GET, .reply_cmd = ETHTOOL_MSG_LINKINFO_GET_REPLY, .hdr_attr = ETHTOOL_A_LINKINFO_HEADER, .req_info_size = sizeof(struct linkinfo_req_info), .reply_data_size = sizeof(struct linkinfo_reply_data), .prepare_data = linkinfo_prepare_data, .reply_size = linkinfo_reply_size, .fill_reply = linkinfo_fill_reply, .set_validate = ethnl_set_linkinfo_validate, .set = ethnl_set_linkinfo, .set_ntf_cmd = ETHTOOL_MSG_LINKINFO_NTF, }; |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the hash:ip,port,net type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <net/tcp.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 /* 0 Comments support added */ /* 1 Forceadd support added */ /* 2 skbinfo support added */ #define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>"); IP_SET_MODULE_DESC("hash:net,port,net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:net,port,net"); /* Type specific function prefix */ #define HTYPE hash_netportnet #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS #define IPSET_NET_COUNT 2 #define IP_SET_HASH_WITH_NET0 /* IPv4 variant */ /* Member elements */ struct hash_netportnet4_elem { union { __be32 ip[2]; __be64 ipcmp; }; __be16 port; union { u8 cidr[2]; u16 ccmp; }; u16 padding; u8 nomatch; u8 proto; }; /* Common functions */ static bool hash_netportnet4_data_equal(const struct hash_netportnet4_elem *ip1, const struct hash_netportnet4_elem *ip2, u32 *multi) { return ip1->ipcmp == ip2->ipcmp && ip1->ccmp == ip2->ccmp && ip1->port == ip2->port && ip1->proto == ip2->proto; } static int hash_netportnet4_do_data_match(const struct hash_netportnet4_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_netportnet4_data_set_flags(struct hash_netportnet4_elem *elem, u32 flags) { elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH); } static void hash_netportnet4_data_reset_flags(struct hash_netportnet4_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_netportnet4_data_reset_elem(struct hash_netportnet4_elem *elem, struct hash_netportnet4_elem *orig) { elem->ip[1] = orig->ip[1]; } static void hash_netportnet4_data_netmask(struct hash_netportnet4_elem *elem, u8 cidr, bool inner) { if (inner) { elem->ip[1] &= ip_set_netmask(cidr); elem->cidr[1] = cidr; } else { elem->ip[0] &= ip_set_netmask(cidr); elem->cidr[0] = cidr; } } static bool hash_netportnet4_data_list(struct sk_buff *skb, const struct hash_netportnet4_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip[0]) || nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip[1]) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) || nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_netportnet4_data_next(struct hash_netportnet4_elem *next, const struct hash_netportnet4_elem *d) { next->ipcmp = d->ipcmp; next->port = d->port; } #define MTYPE hash_netportnet4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static void hash_netportnet4_init(struct hash_netportnet4_elem *e) { e->cidr[0] = HOST_MASK; e->cidr[1] = HOST_MASK; } static int hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netportnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK; if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0]); ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip[1]); e.ip[0] &= ip_set_netmask(e.cidr[0]); e.ip[1] &= ip_set_netmask(e.cidr[1]); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static u32 hash_netportnet4_range_to_cidr(u32 from, u32 to, u8 *cidr) { if (from == 0 && to == UINT_MAX) { *cidr = 0; return to; } return ip_set_range_to_cidr(from, to, cidr); } static int hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct hash_netportnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; u32 ip2_from = 0, ip2_to = 0, ip2, i = 0; bool with_ports = false; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); hash_netportnet4_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); if (ret) return ret; ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } with_ports = with_ports && tb[IPSET_ATTR_PORT_TO]; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || with_ports || tb[IPSET_ATTR_IP2_TO])) { e.ip[0] = htonl(ip & ip_set_hostmask(e.cidr[0])); e.ip[1] = htonl(ip2_from & ip_set_hostmask(e.cidr[1])); ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } ip_to = ip; if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; if (ip > ip_to) swap(ip, ip_to); if (unlikely(ip + UINT_MAX == ip_to)) return -IPSET_ERR_HASH_RANGE; } else { ip_set_mask_from_to(ip, ip_to, e.cidr[0]); } port_to = port = ntohs(e.port); if (tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); } ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); if (ret) return ret; if (ip2_from > ip2_to) swap(ip2_from, ip2_to); if (unlikely(ip2_from + UINT_MAX == ip2_to)) return -IPSET_ERR_HASH_RANGE; } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } if (retried) { ip = ntohl(h->next.ip[0]); p = ntohs(h->next.port); ip2 = ntohl(h->next.ip[1]); } else { p = port; ip2 = ip2_from; } do { e.ip[0] = htonl(ip); ip = hash_netportnet4_range_to_cidr(ip, ip_to, &e.cidr[0]); for (; p <= port_to; p++) { e.port = htons(p); do { i++; e.ip[1] = htonl(ip2); if (i > IPSET_MAX_RANGE) { hash_netportnet4_data_next(&h->next, &e); return -ERANGE; } ip2 = hash_netportnet4_range_to_cidr(ip2, ip2_to, &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } while (ip2++ < ip2_to); ip2 = ip2_from; } p = port; } while (ip++ < ip_to); return ret; } /* IPv6 variant */ struct hash_netportnet6_elem { union nf_inet_addr ip[2]; __be16 port; union { u8 cidr[2]; u16 ccmp; }; u16 padding; u8 nomatch; u8 proto; }; /* Common functions */ static bool hash_netportnet6_data_equal(const struct hash_netportnet6_elem *ip1, const struct hash_netportnet6_elem *ip2, u32 *multi) { return ipv6_addr_equal(&ip1->ip[0].in6, &ip2->ip[0].in6) && ipv6_addr_equal(&ip1->ip[1].in6, &ip2->ip[1].in6) && ip1->ccmp == ip2->ccmp && ip1->port == ip2->port && ip1->proto == ip2->proto; } static int hash_netportnet6_do_data_match(const struct hash_netportnet6_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_netportnet6_data_set_flags(struct hash_netportnet6_elem *elem, u32 flags) { elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH); } static void hash_netportnet6_data_reset_flags(struct hash_netportnet6_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_netportnet6_data_reset_elem(struct hash_netportnet6_elem *elem, struct hash_netportnet6_elem *orig) { elem->ip[1] = orig->ip[1]; } static void hash_netportnet6_data_netmask(struct hash_netportnet6_elem *elem, u8 cidr, bool inner) { if (inner) { ip6_netmask(&elem->ip[1], cidr); elem->cidr[1] = cidr; } else { ip6_netmask(&elem->ip[0], cidr); elem->cidr[0] = cidr; } } static bool hash_netportnet6_data_list(struct sk_buff *skb, const struct hash_netportnet6_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip[0].in6) || nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip[1].in6) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) || nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_netportnet6_data_next(struct hash_netportnet6_elem *next, const struct hash_netportnet6_elem *d) { next->port = d->port; } #undef MTYPE #undef HOST_MASK #define MTYPE hash_netportnet6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static void hash_netportnet6_init(struct hash_netportnet6_elem *e) { e->cidr[0] = HOST_MASK; e->cidr[1] = HOST_MASK; } static int hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netportnet6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netportnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK; if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0].in6); ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip[1].in6); ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_netportnet6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netportnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); hash_netportnet6_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]); if (ret) return ret; ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } port = ntohs(e.port); port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); if (retried) port = ntohs(h->next.port); for (; port <= port_to; port++) { e.port = htons(port); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } return ret; } static struct ip_set_type hash_netportnet_type __read_mostly = { .name = "hash:net,port,net", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2 | IPSET_TYPE_NOMATCH, .dimension = IPSET_DIM_THREE, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netportnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_IP2] = { .type = NLA_NESTED }, [IPSET_ATTR_IP2_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_CIDR2] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_netportnet_init(void) { return ip_set_type_register(&hash_netportnet_type); } static void __exit hash_netportnet_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_netportnet_type); } module_init(hash_netportnet_init); module_exit(hash_netportnet_fini); |
| 3 4 1518 30 32 32 32 32 1696 1183 1182 586 8 28 29 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_INETDEVICE_H #define _LINUX_INETDEVICE_H #ifdef __KERNEL__ #include <linux/bitmap.h> #include <linux/if.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; #define MC_HASH_SZ_LOG 9 struct in_device { struct net_device *dev; netdevice_tracker dev_tracker; refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; unsigned long mr_qi; /* Query Interval */ unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ struct neigh_parms *arp_parms; struct ipv4_devconf cnf; struct rcu_head rcu_head; }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr)) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) #define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr)) static inline int ipv4_devconf_get(const struct in_device *in_dev, int index) { index--; return READ_ONCE(in_dev->cnf.data[index]); } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, int val) { index--; set_bit(index, in_dev->cnf.state); WRITE_ONCE(in_dev->cnf.data[index], val); } static inline void ipv4_devconf_setall(struct in_device *in_dev) { bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ (IPV4_DEVCONF_ALL_RO(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) #define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ SECURE_REDIRECTS) #define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG) #define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \ || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) #define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node hash; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 ifa_valid_lft; __u32 ifa_preferred_lft; unsigned long ifa_cstamp; /* created timestamp */ unsigned long ifa_tstamp; /* updated timestamp */ }; struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); int register_inetaddr_validator_notifier(struct notifier_block *nb); int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) { return __ip_dev_find(net, addr, true); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); #ifdef CONFIG_INET int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); #else static inline int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { return 0; } #endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } /* * Check if a mask is acceptable. */ static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) return true; hmask = ntohl(mask); if (hmask & (hmask+1)) return true; return false; } #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); } static inline struct in_device *in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->ip_ptr); } /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { struct in_device *in_dev; bool rc = false; in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rc = true; return rc; } static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); return in_dev ? in_dev->arp_parms : NULL; } void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1U<<(32-logmask))-1)); return 0; } static __inline__ int inet_mask_len(__be32 mask) { __u32 hmask = ntohl(mask); if (!hmask) return 0; return 32 - ffz(~hmask); } #endif /* _LINUX_INETDEVICE_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 | // SPDX-License-Identifier: GPL-2.0-only /* * "security" table for IPv6 * * This is for use by Mandatory Access Control (MAC) security models, * which need to be able to manage security policy in separate context * to DAC. * * Based on iptable_mangle.c * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2004 Netfilter Core Team <coreteam <at> netfilter.org> * Copyright (C) 2008 Red Hat, Inc., James Morris <jmorris <at> redhat.com> */ #include <linux/module.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/slab.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Morris <jmorris <at> redhat.com>"); MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); #define SECURITY_VALID_HOOKS (1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_SECURITY, }; static struct nf_hook_ops *sectbl_ops __read_mostly; static int ip6table_security_table_init(struct net *net) { struct ip6t_replace *repl; int ret; repl = ip6t_alloc_initial_table(&security_table); if (repl == NULL) return -ENOMEM; ret = ip6t_register_table(net, &security_table, repl, sectbl_ops); kfree(repl); return ret; } static void __net_exit ip6table_security_net_pre_exit(struct net *net) { ip6t_unregister_table_pre_exit(net, "security"); } static void __net_exit ip6table_security_net_exit(struct net *net) { ip6t_unregister_table_exit(net, "security"); } static struct pernet_operations ip6table_security_net_ops = { .pre_exit = ip6table_security_net_pre_exit, .exit = ip6table_security_net_exit, }; static int __init ip6table_security_init(void) { int ret = xt_register_template(&security_table, ip6table_security_table_init); if (ret < 0) return ret; sectbl_ops = xt_hook_ops_alloc(&security_table, ip6t_do_table); if (IS_ERR(sectbl_ops)) { xt_unregister_template(&security_table); return PTR_ERR(sectbl_ops); } ret = register_pernet_subsys(&ip6table_security_net_ops); if (ret < 0) { kfree(sectbl_ops); xt_unregister_template(&security_table); return ret; } return ret; } static void __exit ip6table_security_fini(void) { unregister_pernet_subsys(&ip6table_security_net_ops); xt_unregister_template(&security_table); kfree(sectbl_ops); } module_init(ip6table_security_init); module_exit(ip6table_security_fini); |
| 6276 3424 9204 5 57 9164 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk). * * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. * (C) Linux Foundation 2008-2013 * Unified interface for all slab allocators */ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H #include <linux/cache.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> #include <linux/cleanup.h> #include <linux/hash.h> enum _slab_flag_bits { _SLAB_CONSISTENCY_CHECKS, _SLAB_RED_ZONE, _SLAB_POISON, _SLAB_KMALLOC, _SLAB_HWCACHE_ALIGN, _SLAB_CACHE_DMA, _SLAB_CACHE_DMA32, _SLAB_STORE_USER, _SLAB_PANIC, _SLAB_TYPESAFE_BY_RCU, _SLAB_TRACE, #ifdef CONFIG_DEBUG_OBJECTS _SLAB_DEBUG_OBJECTS, #endif _SLAB_NOLEAKTRACE, _SLAB_NO_MERGE, #ifdef CONFIG_FAILSLAB _SLAB_FAILSLAB, #endif #ifdef CONFIG_MEMCG_KMEM _SLAB_ACCOUNT, #endif #ifdef CONFIG_KASAN_GENERIC _SLAB_KASAN, #endif _SLAB_NO_USER_FLAGS, #ifdef CONFIG_KFENCE _SLAB_SKIP_KFENCE, #endif #ifndef CONFIG_SLUB_TINY _SLAB_RECLAIM_ACCOUNT, #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, #ifdef CONFIG_SLAB_OBJ_EXT _SLAB_NO_OBJ_EXT, #endif _SLAB_FLAGS_LAST_BIT }; #define __SLAB_FLAG_BIT(nr) ((slab_flags_t __force)(1U << (nr))) #define __SLAB_FLAG_UNUSED ((slab_flags_t __force)(0U)) /* * Flags to pass to kmem_cache_create(). * The ones marked DEBUG need CONFIG_SLUB_DEBUG enabled, otherwise are no-op */ /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_CONSISTENCY_CHECKS __SLAB_FLAG_BIT(_SLAB_CONSISTENCY_CHECKS) /* DEBUG: Red zone objs in a cache */ #define SLAB_RED_ZONE __SLAB_FLAG_BIT(_SLAB_RED_ZONE) /* DEBUG: Poison objects */ #define SLAB_POISON __SLAB_FLAG_BIT(_SLAB_POISON) /* Indicate a kmalloc slab */ #define SLAB_KMALLOC __SLAB_FLAG_BIT(_SLAB_KMALLOC) /* Align objs on cache lines */ #define SLAB_HWCACHE_ALIGN __SLAB_FLAG_BIT(_SLAB_HWCACHE_ALIGN) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA __SLAB_FLAG_BIT(_SLAB_CACHE_DMA) /* Use GFP_DMA32 memory */ #define SLAB_CACHE_DMA32 __SLAB_FLAG_BIT(_SLAB_CACHE_DMA32) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER __SLAB_FLAG_BIT(_SLAB_STORE_USER) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC __SLAB_FLAG_BIT(_SLAB_PANIC) /* * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() * that memory location is free to be reused at any time. Thus it may * be possible to see another object there in the same RCU grace period. * * This feature only ensures the memory location backing the object * stays valid, the trick to using this is relying on an independent * object validation pass. Something like: * * begin: * rcu_read_lock(); * obj = lockless_lookup(key); * if (obj) { * if (!try_get_ref(obj)) // might fail for free objects * rcu_read_unlock(); * goto begin; * * if (obj->key != key) { // not the object we expected * put_ref(obj); * rcu_read_unlock(); * goto begin; * } * } * rcu_read_unlock(); * * This is useful if we need to approach a kernel structure obliquely, * from its address obtained without the usual locking. We can lock * the structure to stabilize it and check it's still at the given address, * only if we can be sure that the memory has not been meanwhile reused * for some other kind of object (which our subsystem's lock might corrupt). * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * * Note that it is not possible to acquire a lock within a structure * allocated with SLAB_TYPESAFE_BY_RCU without first acquiring a reference * as described above. The reason is that SLAB_TYPESAFE_BY_RCU pages * are not zeroed before being given to the slab, which means that any * locks must be initialized after each and every kmem_struct_alloc(). * Alternatively, make the ctor passed to kmem_cache_create() initialize * the locks at page-allocation time, as is done in __i915_request_ctor(), * sighand_ctor(), and anon_vma_ctor(). Such a ctor permits readers * to safely acquire those ctor-initialized locks under rcu_read_lock() * protection. * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ /* Defer freeing slabs to RCU */ #define SLAB_TYPESAFE_BY_RCU __SLAB_FLAG_BIT(_SLAB_TYPESAFE_BY_RCU) /* Trace allocations and frees */ #define SLAB_TRACE __SLAB_FLAG_BIT(_SLAB_TRACE) /* Flag to prevent checks on free */ #ifdef CONFIG_DEBUG_OBJECTS # define SLAB_DEBUG_OBJECTS __SLAB_FLAG_BIT(_SLAB_DEBUG_OBJECTS) #else # define SLAB_DEBUG_OBJECTS __SLAB_FLAG_UNUSED #endif /* Avoid kmemleak tracing */ #define SLAB_NOLEAKTRACE __SLAB_FLAG_BIT(_SLAB_NOLEAKTRACE) /* * Prevent merging with compatible kmem caches. This flag should be used * cautiously. Valid use cases: * * - caches created for self-tests (e.g. kunit) * - general caches created and used by a subsystem, only when a * (subsystem-specific) debug option is enabled * - performance critical caches, should be very rare and consulted with slab * maintainers, and not used together with CONFIG_SLUB_TINY */ #define SLAB_NO_MERGE __SLAB_FLAG_BIT(_SLAB_NO_MERGE) /* Fault injection mark */ #ifdef CONFIG_FAILSLAB # define SLAB_FAILSLAB __SLAB_FLAG_BIT(_SLAB_FAILSLAB) #else # define SLAB_FAILSLAB __SLAB_FLAG_UNUSED #endif /* Account to memcg */ #ifdef CONFIG_MEMCG_KMEM # define SLAB_ACCOUNT __SLAB_FLAG_BIT(_SLAB_ACCOUNT) #else # define SLAB_ACCOUNT __SLAB_FLAG_UNUSED #endif #ifdef CONFIG_KASAN_GENERIC #define SLAB_KASAN __SLAB_FLAG_BIT(_SLAB_KASAN) #else #define SLAB_KASAN __SLAB_FLAG_UNUSED #endif /* * Ignore user specified debugging flags. * Intended for caches created for self-tests so they have only flags * specified in the code and other flags are ignored. */ #define SLAB_NO_USER_FLAGS __SLAB_FLAG_BIT(_SLAB_NO_USER_FLAGS) #ifdef CONFIG_KFENCE #define SLAB_SKIP_KFENCE __SLAB_FLAG_BIT(_SLAB_SKIP_KFENCE) #else #define SLAB_SKIP_KFENCE __SLAB_FLAG_UNUSED #endif /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #ifndef CONFIG_SLUB_TINY #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_BIT(_SLAB_RECLAIM_ACCOUNT) #else #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_UNUSED #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* Slab created using create_boot_cache */ #ifdef CONFIG_SLAB_OBJ_EXT #define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) #else #define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED #endif /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. * * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. * Both make kfree a no-op. */ #define ZERO_SIZE_PTR ((void *)16) #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) #include <linux/kasan.h> struct list_lru; struct mem_cgroup; /* * struct kmem_cache related prototypes */ bool slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); struct kmem_cache *kmem_cache_create_usercopy(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); void kmem_cache_destroy(struct kmem_cache *s); int kmem_cache_shrink(struct kmem_cache *s); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. * * The alignment of the struct determines object alignment. If you * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ #define KMEM_CACHE(__struct, __flags) \ kmem_cache_create(#__struct, sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), NULL) /* * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ #define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ kmem_cache_create_usercopy(#__struct, \ sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), \ offsetof(struct __struct, __field), \ sizeof_field(struct __struct, __field), NULL) /* * Common kmalloc functions provided by all allocators */ void * __must_check krealloc_noprof(const void *objp, size_t new_size, gfp_t flags) __realloc_size(2); #define krealloc(...) alloc_hooks(krealloc_noprof(__VA_ARGS__)) void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) /** * ksize - Report actual allocation size of associated object * * @objp: Pointer returned from a prior kmalloc()-family allocation. * * This should not be used for writing beyond the originally requested * allocation size. Either use krealloc() or round up the allocation size * with kmalloc_size_roundup() prior to allocation. If this is used to * access beyond the originally requested allocation size, UBSAN_BOUNDS * and/or FORTIFY_SOURCE may trip, since they only know about the * originally allocated size via the __alloc_size attribute. */ size_t ksize(const void *objp); #ifdef CONFIG_PRINTK bool kmem_dump_obj(void *object); #else static inline bool kmem_dump_obj(void *object) { return false; } #endif /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. * Setting ARCH_DMA_MINALIGN in arch headers allows that. */ #ifdef ARCH_HAS_DMA_MINALIGN #if ARCH_DMA_MINALIGN > 8 && !defined(ARCH_KMALLOC_MINALIGN) #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #endif #endif #ifndef ARCH_KMALLOC_MINALIGN #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #elif ARCH_KMALLOC_MINALIGN > 8 #define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) #endif /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer * aligned buffers. */ #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif /* * Arches can define this function if they want to decide the minimum slab * alignment at runtime. The value returned by the function must be a power * of two and >= ARCH_SLAB_MINALIGN. */ #ifndef arch_slab_minalign static inline unsigned int arch_slab_minalign(void) { return ARCH_SLAB_MINALIGN; } #endif /* * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN. * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) #define __assume_page_alignment __assume_aligned(PAGE_SIZE) /* * Kmalloc array related definitions */ /* * SLUB directly allocates requests fitting in to an order-1 page * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_PAGE_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ #define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) /* Maximum order allocatable via the slab allocator */ #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. */ #ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif /* * This restriction comes from byte sized index implementation. * Page size is normally 2^12 bytes and, in this case, if we want to use * byte sized index which can represent 2^8 entries, the size of the object * should be equal or greater to 2^12 / 2^8 = 2^4 = 16. * If minimum size of kmalloc is less than 16, we use it as minimum object * size and give up to use byte sized index. */ #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) #ifdef CONFIG_RANDOM_KMALLOC_CACHES #define RANDOM_KMALLOC_CACHES_NR 15 // # of cache copies #else #define RANDOM_KMALLOC_CACHES_NR 0 #endif /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. * * KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP * is for accounted but unreclaimable and non-dma objects. All the other * kmem caches can have both accounted and unaccounted objects. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, #ifndef CONFIG_ZONE_DMA KMALLOC_DMA = KMALLOC_NORMAL, #endif #ifndef CONFIG_MEMCG_KMEM KMALLOC_CGROUP = KMALLOC_NORMAL, #endif KMALLOC_RANDOM_START = KMALLOC_NORMAL, KMALLOC_RANDOM_END = KMALLOC_RANDOM_START + RANDOM_KMALLOC_CACHES_NR, #ifdef CONFIG_SLUB_TINY KMALLOC_RECLAIM = KMALLOC_NORMAL, #else KMALLOC_RECLAIM, #endif #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif #ifdef CONFIG_MEMCG_KMEM KMALLOC_CGROUP, #endif NR_KMALLOC_TYPES }; extern struct kmem_cache * kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; /* * Define gfp bits that should not be set for KMALLOC_NORMAL. */ #define KMALLOC_NOT_NORMAL_BITS \ (__GFP_RECLAIMABLE | \ (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ (IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0)) extern unsigned long random_kmalloc_seed; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigned long caller) { /* * The most common case is KMALLOC_NORMAL, so test for it * with a single branch for all the relevant flags. */ if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0)) #ifdef CONFIG_RANDOM_KMALLOC_CACHES /* RANDOM_KMALLOC_CACHES_NR (=15) copies + the KMALLOC_NORMAL */ return KMALLOC_RANDOM_START + hash_64(caller ^ random_kmalloc_seed, ilog2(RANDOM_KMALLOC_CACHES_NR + 1)); #else return KMALLOC_NORMAL; #endif /* * At least one of the flags has to be set. Their priorities in * decreasing order are: * 1) __GFP_DMA * 2) __GFP_RECLAIMABLE * 3) __GFP_ACCOUNT */ if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) return KMALLOC_DMA; if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || (flags & __GFP_RECLAIMABLE)) return KMALLOC_RECLAIM; else return KMALLOC_CGROUP; } /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n * * Note: __kmalloc_index() is compile-time optimized, and not runtime optimized; * typical usage is via kmalloc_index() and therefore evaluated at compile-time. * Callers where !size_is_constant should only be test modules, where runtime * overheads of __kmalloc_index() can be tolerated. Also see kmalloc_slab(). */ static __always_inline unsigned int __kmalloc_index(size_t size, bool size_is_constant) { if (!size) return 0; if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) return 1; if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) return 2; if (size <= 8) return 3; if (size <= 16) return 4; if (size <= 32) return 5; if (size <= 64) return 6; if (size <= 128) return 7; if (size <= 256) return 8; if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; if (size <= 32 * 1024) return 15; if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); else BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) #include <linux/alloc_tag.h> void *__kmalloc_noprof(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); #define __kmalloc(...) alloc_hooks(__kmalloc_noprof(__VA_ARGS__)) /** * kmem_cache_alloc - Allocate an object * @cachep: The cache to allocate from. * @flags: See kmalloc(). * * Allocate an object from this cache. * See kmem_cache_zalloc() for a shortcut of adding __GFP_ZERO to flags. * * Return: pointer to the new object or %NULL in case of error */ void *kmem_cache_alloc_noprof(struct kmem_cache *cachep, gfp_t flags) __assume_slab_alignment __malloc; #define kmem_cache_alloc(...) alloc_hooks(kmem_cache_alloc_noprof(__VA_ARGS__)) void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, gfp_t gfpflags) __assume_slab_alignment __malloc; #define kmem_cache_alloc_lru(...) alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__)) void kmem_cache_free(struct kmem_cache *s, void *objp); /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building * metadata structures unnecessarily. * * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size, void **p); #define kmem_cache_alloc_bulk(...) alloc_hooks(kmem_cache_alloc_bulk_noprof(__VA_ARGS__)) static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } void *__kmalloc_node_noprof(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __alloc_size(1); #define __kmalloc_node(...) alloc_hooks(__kmalloc_node_noprof(__VA_ARGS__)) void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; #define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__)) void *kmalloc_trace_noprof(struct kmem_cache *s, gfp_t flags, size_t size) __assume_kmalloc_alignment __alloc_size(3); void *kmalloc_node_trace_noprof(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_kmalloc_alignment __alloc_size(4); #define kmalloc_trace(...) alloc_hooks(kmalloc_trace_noprof(__VA_ARGS__)) #define kmalloc_node_trace(...) alloc_hooks(kmalloc_node_trace_noprof(__VA_ARGS__)) void *kmalloc_large_noprof(size_t size, gfp_t flags) __assume_page_alignment __alloc_size(1); #define kmalloc_large(...) alloc_hooks(kmalloc_large_noprof(__VA_ARGS__)) void *kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) __assume_page_alignment __alloc_size(1); #define kmalloc_large_node(...) alloc_hooks(kmalloc_large_node_noprof(__VA_ARGS__)) /** * kmalloc - allocate kernel memory * @size: how many bytes of memory are required. * @flags: describe the allocation context * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed * to be at least to the size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp_types.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` * * The recommended usage of the @flags is described at * :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>` * * Below is a brief outline of the most useful GFP flags * * %GFP_KERNEL * Allocate normal kernel ram. May sleep. * * %GFP_NOWAIT * Allocation will not sleep. * * %GFP_ATOMIC * Allocation will not sleep. May use emergency pools. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * * %__GFP_ZERO * Zero the allocated memory before returning. Also see kzalloc(). * * %__GFP_HIGH * This allocation has high priority and may use emergency pools. * * %__GFP_NOFAIL * Indicate that this allocation is in no way allowed to fail * (think twice before using). * * %__GFP_NORETRY * If memory is not immediately available, * then give up at once. * * %__GFP_NOWARN * If allocation fails, don't issue any warnings. * * %__GFP_RETRY_MAYFAIL * Try really hard to succeed the allocation but fail * eventually. */ static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t flags) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large_noprof(size, flags); index = kmalloc_index(size); return kmalloc_trace_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, size); } return __kmalloc_noprof(size, flags); } #define kmalloc(...) alloc_hooks(kmalloc_noprof(__VA_ARGS__)) static __always_inline __alloc_size(1) void *kmalloc_node_noprof(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large_node_noprof(size, flags, node); index = kmalloc_index(size); return kmalloc_node_trace_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, node, size); } return __kmalloc_node_noprof(size, flags, node); } #define kmalloc_node(...) alloc_hooks(kmalloc_node_noprof(__VA_ARGS__)) /** * kmalloc_array - allocate memory for an array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline __alloc_size(1, 2) void *kmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_noprof(bytes, flags); return kmalloc_noprof(bytes, flags); } #define kmalloc_array(...) alloc_hooks(kmalloc_array_noprof(__VA_ARGS__)) /** * krealloc_array - reallocate memory for an array. * @p: pointer to the memory chunk to reallocate * @new_n: new number of elements to alloc * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ static inline __realloc_size(2, 3) void * __must_check krealloc_array_noprof(void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return krealloc_noprof(p, bytes, flags); } #define krealloc_array(...) alloc_hooks(krealloc_array_noprof(__VA_ARGS__)) /** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ #define kcalloc(n, size, flags) kmalloc_array(n, size, (flags) | __GFP_ZERO) void *kmalloc_node_track_caller_noprof(size_t size, gfp_t flags, int node, unsigned long caller) __alloc_size(1); #define kmalloc_node_track_caller(...) \ alloc_hooks(kmalloc_node_track_caller_noprof(__VA_ARGS__, _RET_IP_)) /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead * of just the calling function (confusing, eh?). * It's useful when the call to kmalloc comes from a widely-used standard * allocator where we care about the real place the memory allocation * request comes from. */ #define kmalloc_track_caller(...) kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE) #define kmalloc_track_caller_noprof(...) \ kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_) static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_node_noprof(bytes, flags, node); return __kmalloc_node_noprof(bytes, flags, node); } #define kmalloc_array_node(...) alloc_hooks(kmalloc_array_node_noprof(__VA_ARGS__)) #define kcalloc_node(_n, _size, _flags, _node) \ kmalloc_array_node(_n, _size, (_flags) | __GFP_ZERO, _node) /* * Shortcuts */ #define kmem_cache_zalloc(_k, _flags) kmem_cache_alloc(_k, (_flags)|__GFP_ZERO) /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ static inline __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags) { return kmalloc_noprof(size, flags | __GFP_ZERO); } #define kzalloc(...) alloc_hooks(kzalloc_noprof(__VA_ARGS__)) #define kzalloc_node(_size, _flags, _node) kmalloc_node(_size, (_flags)|__GFP_ZERO, _node) extern void *kvmalloc_node_noprof(size_t size, gfp_t flags, int node) __alloc_size(1); #define kvmalloc_node(...) alloc_hooks(kvmalloc_node_noprof(__VA_ARGS__)) #define kvmalloc(_size, _flags) kvmalloc_node(_size, _flags, NUMA_NO_NODE) #define kvmalloc_noprof(_size, _flags) kvmalloc_node_noprof(_size, _flags, NUMA_NO_NODE) #define kvzalloc(_size, _flags) kvmalloc(_size, (_flags)|__GFP_ZERO) #define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node) static inline __alloc_size(1, 2) void * kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kvmalloc_node_noprof(bytes, flags, node); } #define kvmalloc_array_noprof(...) kvmalloc_array_node_noprof(__VA_ARGS__, NUMA_NO_NODE) #define kvcalloc_node_noprof(_n,_s,_f,_node) kvmalloc_array_node_noprof(_n,_s,(_f)|__GFP_ZERO,_node) #define kvcalloc_noprof(...) kvcalloc_node_noprof(__VA_ARGS__, NUMA_NO_NODE) #define kvmalloc_array(...) alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__)) #define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__)) #define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__)) extern void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags) __realloc_size(3); #define kvrealloc(...) alloc_hooks(kvrealloc_noprof(__VA_ARGS__)) extern void kvfree(const void *addr); DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) extern void kvfree_sensitive(const void *addr, size_t len); unsigned int kmem_cache_size(struct kmem_cache *s); /** * kmalloc_size_roundup - Report allocation bucket size for the given size * * @size: Number of bytes to round up from. * * This returns the number of bytes that would be available in a kmalloc() * allocation of @size bytes. For example, a 126 byte request would be * rounded up to the next sized kmalloc bucket, 128 bytes. (This is strictly * for the general-purpose kmalloc()-based allocations, and is not for the * pre-sized kmem_cache_alloc()-based allocations.) * * Use this to kmalloc() the full bucket size ahead of time instead of using * ksize() to query the size after an allocation. */ size_t kmalloc_size_roundup(size_t size); void __init kmem_cache_init_late(void); #endif /* _LINUX_SLAB_H */ |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Voltaire, Inc. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2008 Cisco. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #define pr_fmt(fmt) "user_mad: " fmt #include <linux/module.h> #include <linux/init.h> #include <linux/device.h> #include <linux/err.h> #include <linux/fs.h> #include <linux/cdev.h> #include <linux/dma-mapping.h> #include <linux/poll.h> #include <linux/mutex.h> #include <linux/kref.h> #include <linux/compat.h> #include <linux/sched.h> #include <linux/semaphore.h> #include <linux/slab.h> #include <linux/nospec.h> #include <linux/uaccess.h> #include <rdma/ib_mad.h> #include <rdma/ib_user_mad.h> #include <rdma/rdma_netlink.h> #include "core_priv.h" MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("InfiniBand userspace MAD packet access"); MODULE_LICENSE("Dual BSD/GPL"); #define MAX_UMAD_RECV_LIST_SIZE 200000 enum { IB_UMAD_MAX_PORTS = RDMA_MAX_PORTS, IB_UMAD_MAX_AGENTS = 32, IB_UMAD_MAJOR = 231, IB_UMAD_MINOR_BASE = 0, IB_UMAD_NUM_FIXED_MINOR = 64, IB_UMAD_NUM_DYNAMIC_MINOR = IB_UMAD_MAX_PORTS - IB_UMAD_NUM_FIXED_MINOR, IB_ISSM_MINOR_BASE = IB_UMAD_NUM_FIXED_MINOR, }; /* * Our lifetime rules for these structs are the following: * device special file is opened, we take a reference on the * ib_umad_port's struct ib_umad_device. We drop these * references in the corresponding close(). * * In addition to references coming from open character devices, there * is one more reference to each ib_umad_device representing the * module's reference taken when allocating the ib_umad_device in * ib_umad_add_one(). * * When destroying an ib_umad_device, we drop the module's reference. */ struct ib_umad_port { struct cdev cdev; struct device dev; struct cdev sm_cdev; struct device sm_dev; struct semaphore sm_sem; struct mutex file_mutex; struct list_head file_list; struct ib_device *ib_dev; struct ib_umad_device *umad_dev; int dev_num; u32 port_num; }; struct ib_umad_device { struct kref kref; struct ib_umad_port ports[]; }; struct ib_umad_file { struct mutex mutex; struct ib_umad_port *port; struct list_head recv_list; atomic_t recv_list_size; struct list_head send_list; struct list_head port_list; spinlock_t send_lock; wait_queue_head_t recv_wait; struct ib_mad_agent *agent[IB_UMAD_MAX_AGENTS]; int agents_dead; u8 use_pkey_index; u8 already_used; }; struct ib_umad_packet { struct ib_mad_send_buf *msg; struct ib_mad_recv_wc *recv_wc; struct list_head list; int length; struct ib_user_mad mad; }; struct ib_rmpp_mad_hdr { struct ib_mad_hdr mad_hdr; struct ib_rmpp_hdr rmpp_hdr; } __packed; #define CREATE_TRACE_POINTS #include <trace/events/ib_umad.h> static const dev_t base_umad_dev = MKDEV(IB_UMAD_MAJOR, IB_UMAD_MINOR_BASE); static const dev_t base_issm_dev = MKDEV(IB_UMAD_MAJOR, IB_UMAD_MINOR_BASE) + IB_UMAD_NUM_FIXED_MINOR; static dev_t dynamic_umad_dev; static dev_t dynamic_issm_dev; static DEFINE_IDA(umad_ida); static int ib_umad_add_one(struct ib_device *device); static void ib_umad_remove_one(struct ib_device *device, void *client_data); static void ib_umad_dev_free(struct kref *kref) { struct ib_umad_device *dev = container_of(kref, struct ib_umad_device, kref); kfree(dev); } static void ib_umad_dev_get(struct ib_umad_device *dev) { kref_get(&dev->kref); } static void ib_umad_dev_put(struct ib_umad_device *dev) { kref_put(&dev->kref, ib_umad_dev_free); } static int hdr_size(struct ib_umad_file *file) { return file->use_pkey_index ? sizeof(struct ib_user_mad_hdr) : sizeof(struct ib_user_mad_hdr_old); } /* caller must hold file->mutex */ static struct ib_mad_agent *__get_agent(struct ib_umad_file *file, int id) { return file->agents_dead ? NULL : file->agent[id]; } static int queue_packet(struct ib_umad_file *file, struct ib_mad_agent *agent, struct ib_umad_packet *packet, bool is_recv_mad) { int ret = 1; mutex_lock(&file->mutex); if (is_recv_mad && atomic_read(&file->recv_list_size) > MAX_UMAD_RECV_LIST_SIZE) goto unlock; for (packet->mad.hdr.id = 0; packet->mad.hdr.id < IB_UMAD_MAX_AGENTS; packet->mad.hdr.id++) if (agent == __get_agent(file, packet->mad.hdr.id)) { list_add_tail(&packet->list, &file->recv_list); atomic_inc(&file->recv_list_size); wake_up_interruptible(&file->recv_wait); ret = 0; break; } unlock: mutex_unlock(&file->mutex); return ret; } static void dequeue_send(struct ib_umad_file *file, struct ib_umad_packet *packet) { spin_lock_irq(&file->send_lock); list_del(&packet->list); spin_unlock_irq(&file->send_lock); } static void send_handler(struct ib_mad_agent *agent, struct ib_mad_send_wc *send_wc) { struct ib_umad_file *file = agent->context; struct ib_umad_packet *packet = send_wc->send_buf->context[0]; dequeue_send(file, packet); rdma_destroy_ah(packet->msg->ah, RDMA_DESTROY_AH_SLEEPABLE); ib_free_send_mad(packet->msg); if (send_wc->status == IB_WC_RESP_TIMEOUT_ERR) { packet->length = IB_MGMT_MAD_HDR; packet->mad.hdr.status = ETIMEDOUT; if (!queue_packet(file, agent, packet, false)) return; } kfree(packet); } static void recv_handler(struct ib_mad_agent *agent, struct ib_mad_send_buf *send_buf, struct ib_mad_recv_wc *mad_recv_wc) { struct ib_umad_file *file = agent->context; struct ib_umad_packet *packet; if (mad_recv_wc->wc->status != IB_WC_SUCCESS) goto err1; packet = kzalloc(sizeof *packet, GFP_KERNEL); if (!packet) goto err1; packet->length = mad_recv_wc->mad_len; packet->recv_wc = mad_recv_wc; packet->mad.hdr.status = 0; packet->mad.hdr.length = hdr_size(file) + mad_recv_wc->mad_len; packet->mad.hdr.qpn = cpu_to_be32(mad_recv_wc->wc->src_qp); /* * On OPA devices it is okay to lose the upper 16 bits of LID as this * information is obtained elsewhere. Mask off the upper 16 bits. */ if (rdma_cap_opa_mad(agent->device, agent->port_num)) packet->mad.hdr.lid = ib_lid_be16(0xFFFF & mad_recv_wc->wc->slid); else packet->mad.hdr.lid = ib_lid_be16(mad_recv_wc->wc->slid); packet->mad.hdr.sl = mad_recv_wc->wc->sl; packet->mad.hdr.path_bits = mad_recv_wc->wc->dlid_path_bits; packet->mad.hdr.pkey_index = mad_recv_wc->wc->pkey_index; packet->mad.hdr.grh_present = !!(mad_recv_wc->wc->wc_flags & IB_WC_GRH); if (packet->mad.hdr.grh_present) { struct rdma_ah_attr ah_attr; const struct ib_global_route *grh; int ret; ret = ib_init_ah_attr_from_wc(agent->device, agent->port_num, mad_recv_wc->wc, mad_recv_wc->recv_buf.grh, &ah_attr); if (ret) goto err2; grh = rdma_ah_read_grh(&ah_attr); packet->mad.hdr.gid_index = grh->sgid_index; packet->mad.hdr.hop_limit = grh->hop_limit; packet->mad.hdr.traffic_class = grh->traffic_class; memcpy(packet->mad.hdr.gid, &grh->dgid, 16); packet->mad.hdr.flow_label = cpu_to_be32(grh->flow_label); rdma_destroy_ah_attr(&ah_attr); } if (queue_packet(file, agent, packet, true)) goto err2; return; err2: kfree(packet); err1: ib_free_recv_mad(mad_recv_wc); } static ssize_t copy_recv_mad(struct ib_umad_file *file, char __user *buf, struct ib_umad_packet *packet, size_t count) { struct ib_mad_recv_buf *recv_buf; int left, seg_payload, offset, max_seg_payload; size_t seg_size; recv_buf = &packet->recv_wc->recv_buf; seg_size = packet->recv_wc->mad_seg_size; /* We need enough room to copy the first (or only) MAD segment. */ if ((packet->length <= seg_size && count < hdr_size(file) + packet->length) || (packet->length > seg_size && count < hdr_size(file) + seg_size)) return -EINVAL; if (copy_to_user(buf, &packet->mad, hdr_size(file))) return -EFAULT; buf += hdr_size(file); seg_payload = min_t(int, packet->length, seg_size); if (copy_to_user(buf, recv_buf->mad, seg_payload)) return -EFAULT; if (seg_payload < packet->length) { /* * Multipacket RMPP MAD message. Copy remainder of message. * Note that last segment may have a shorter payload. */ if (count < hdr_size(file) + packet->length) { /* * The buffer is too small, return the first RMPP segment, * which includes the RMPP message length. */ return -ENOSPC; } offset = ib_get_mad_data_offset(recv_buf->mad->mad_hdr.mgmt_class); max_seg_payload = seg_size - offset; for (left = packet->length - seg_payload, buf += seg_payload; left; left -= seg_payload, buf += seg_payload) { recv_buf = container_of(recv_buf->list.next, struct ib_mad_recv_buf, list); seg_payload = min(left, max_seg_payload); if (copy_to_user(buf, ((void *) recv_buf->mad) + offset, seg_payload)) return -EFAULT; } } trace_ib_umad_read_recv(file, &packet->mad.hdr, &recv_buf->mad->mad_hdr); return hdr_size(file) + packet->length; } static ssize_t copy_send_mad(struct ib_umad_file *file, char __user *buf, struct ib_umad_packet *packet, size_t count) { ssize_t size = hdr_size(file) + packet->length; if (count < size) return -EINVAL; if (copy_to_user(buf, &packet->mad, hdr_size(file))) return -EFAULT; buf += hdr_size(file); if (copy_to_user(buf, packet->mad.data, packet->length)) return -EFAULT; trace_ib_umad_read_send(file, &packet->mad.hdr, (struct ib_mad_hdr *)&packet->mad.data); return size; } static ssize_t ib_umad_read(struct file *filp, char __user *buf, size_t count, loff_t *pos) { struct ib_umad_file *file = filp->private_data; struct ib_umad_packet *packet; ssize_t ret; if (count < hdr_size(file)) return -EINVAL; mutex_lock(&file->mutex); if (file->agents_dead) { mutex_unlock(&file->mutex); return -EIO; } while (list_empty(&file->recv_list)) { mutex_unlock(&file->mutex); if (filp->f_flags & O_NONBLOCK) return -EAGAIN; if (wait_event_interruptible(file->recv_wait, !list_empty(&file->recv_list))) return -ERESTARTSYS; mutex_lock(&file->mutex); } if (file->agents_dead) { mutex_unlock(&file->mutex); return -EIO; } packet = list_entry(file->recv_list.next, struct ib_umad_packet, list); list_del(&packet->list); atomic_dec(&file->recv_list_size); mutex_unlock(&file->mutex); if (packet->recv_wc) ret = copy_recv_mad(file, buf, packet, count); else ret = copy_send_mad(file, buf, packet, count); if (ret < 0) { /* Requeue packet */ mutex_lock(&file->mutex); list_add(&packet->list, &file->recv_list); atomic_inc(&file->recv_list_size); mutex_unlock(&file->mutex); } else { if (packet->recv_wc) ib_free_recv_mad(packet->recv_wc); kfree(packet); } return ret; } static int copy_rmpp_mad(struct ib_mad_send_buf *msg, const char __user *buf) { int left, seg; /* Copy class specific header */ if ((msg->hdr_len > IB_MGMT_RMPP_HDR) && copy_from_user(msg->mad + IB_MGMT_RMPP_HDR, buf + IB_MGMT_RMPP_HDR, msg->hdr_len - IB_MGMT_RMPP_HDR)) return -EFAULT; /* All headers are in place. Copy data segments. */ for (seg = 1, left = msg->data_len, buf += msg->hdr_len; left > 0; seg++, left -= msg->seg_size, buf += msg->seg_size) { if (copy_from_user(ib_get_rmpp_segment(msg, seg), buf, min(left, msg->seg_size))) return -EFAULT; } return 0; } static int same_destination(struct ib_user_mad_hdr *hdr1, struct ib_user_mad_hdr *hdr2) { if (!hdr1->grh_present && !hdr2->grh_present) return (hdr1->lid == hdr2->lid); if (hdr1->grh_present && hdr2->grh_present) return !memcmp(hdr1->gid, hdr2->gid, 16); return 0; } static int is_duplicate(struct ib_umad_file *file, struct ib_umad_packet *packet) { struct ib_umad_packet *sent_packet; struct ib_mad_hdr *sent_hdr, *hdr; hdr = (struct ib_mad_hdr *) packet->mad.data; list_for_each_entry(sent_packet, &file->send_list, list) { sent_hdr = (struct ib_mad_hdr *) sent_packet->mad.data; if ((hdr->tid != sent_hdr->tid) || (hdr->mgmt_class != sent_hdr->mgmt_class)) continue; /* * No need to be overly clever here. If two new operations have * the same TID, reject the second as a duplicate. This is more * restrictive than required by the spec. */ if (!ib_response_mad(hdr)) { if (!ib_response_mad(sent_hdr)) return 1; continue; } else if (!ib_response_mad(sent_hdr)) continue; if (same_destination(&packet->mad.hdr, &sent_packet->mad.hdr)) return 1; } return 0; } static ssize_t ib_umad_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_umad_file *file = filp->private_data; struct ib_rmpp_mad_hdr *rmpp_mad_hdr; struct ib_umad_packet *packet; struct ib_mad_agent *agent; struct rdma_ah_attr ah_attr; struct ib_ah *ah; __be64 *tid; int ret, data_len, hdr_len, copy_offset, rmpp_active; u8 base_version; if (count < hdr_size(file) + IB_MGMT_RMPP_HDR) return -EINVAL; packet = kzalloc(sizeof(*packet) + IB_MGMT_RMPP_HDR, GFP_KERNEL); if (!packet) return -ENOMEM; if (copy_from_user(&packet->mad, buf, hdr_size(file))) { ret = -EFAULT; goto err; } if (packet->mad.hdr.id >= IB_UMAD_MAX_AGENTS) { ret = -EINVAL; goto err; } buf += hdr_size(file); if (copy_from_user(packet->mad.data, buf, IB_MGMT_RMPP_HDR)) { ret = -EFAULT; goto err; } mutex_lock(&file->mutex); trace_ib_umad_write(file, &packet->mad.hdr, (struct ib_mad_hdr *)&packet->mad.data); agent = __get_agent(file, packet->mad.hdr.id); if (!agent) { ret = -EIO; goto err_up; } memset(&ah_attr, 0, sizeof ah_attr); ah_attr.type = rdma_ah_find_type(agent->device, file->port->port_num); rdma_ah_set_dlid(&ah_attr, be16_to_cpu(packet->mad.hdr.lid)); rdma_ah_set_sl(&ah_attr, packet->mad.hdr.sl); rdma_ah_set_path_bits(&ah_attr, packet->mad.hdr.path_bits); rdma_ah_set_port_num(&ah_attr, file->port->port_num); if (packet->mad.hdr.grh_present) { rdma_ah_set_grh(&ah_attr, NULL, be32_to_cpu(packet->mad.hdr.flow_label), packet->mad.hdr.gid_index, packet->mad.hdr.hop_limit, packet->mad.hdr.traffic_class); rdma_ah_set_dgid_raw(&ah_attr, packet->mad.hdr.gid); } ah = rdma_create_user_ah(agent->qp->pd, &ah_attr, NULL); if (IS_ERR(ah)) { ret = PTR_ERR(ah); goto err_up; } rmpp_mad_hdr = (struct ib_rmpp_mad_hdr *)packet->mad.data; hdr_len = ib_get_mad_data_offset(rmpp_mad_hdr->mad_hdr.mgmt_class); if (ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class) && ib_mad_kernel_rmpp_agent(agent)) { copy_offset = IB_MGMT_RMPP_HDR; rmpp_active = ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE; } else { copy_offset = IB_MGMT_MAD_HDR; rmpp_active = 0; } base_version = ((struct ib_mad_hdr *)&packet->mad.data)->base_version; data_len = count - hdr_size(file) - hdr_len; packet->msg = ib_create_send_mad(agent, be32_to_cpu(packet->mad.hdr.qpn), packet->mad.hdr.pkey_index, rmpp_active, hdr_len, data_len, GFP_KERNEL, base_version); if (IS_ERR(packet->msg)) { ret = PTR_ERR(packet->msg); goto err_ah; } packet->msg->ah = ah; packet->msg->timeout_ms = packet->mad.hdr.timeout_ms; packet->msg->retries = packet->mad.hdr.retries; packet->msg->context[0] = packet; /* Copy MAD header. Any RMPP header is already in place. */ memcpy(packet->msg->mad, packet->mad.data, IB_MGMT_MAD_HDR); if (!rmpp_active) { if (copy_from_user(packet->msg->mad + copy_offset, buf + copy_offset, hdr_len + data_len - copy_offset)) { ret = -EFAULT; goto err_msg; } } else { ret = copy_rmpp_mad(packet->msg, buf); if (ret) goto err_msg; } /* * Set the high-order part of the transaction ID to make MADs from * different agents unique, and allow routing responses back to the * original requestor. */ if (!ib_response_mad(packet->msg->mad)) { tid = &((struct ib_mad_hdr *) packet->msg->mad)->tid; *tid = cpu_to_be64(((u64) agent->hi_tid) << 32 | (be64_to_cpup(tid) & 0xffffffff)); rmpp_mad_hdr->mad_hdr.tid = *tid; } if (!ib_mad_kernel_rmpp_agent(agent) && ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class) && (ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) { spin_lock_irq(&file->send_lock); list_add_tail(&packet->list, &file->send_list); spin_unlock_irq(&file->send_lock); } else { spin_lock_irq(&file->send_lock); ret = is_duplicate(file, packet); if (!ret) list_add_tail(&packet->list, &file->send_list); spin_unlock_irq(&file->send_lock); if (ret) { ret = -EINVAL; goto err_msg; } } ret = ib_post_send_mad(packet->msg, NULL); if (ret) goto err_send; mutex_unlock(&file->mutex); return count; err_send: dequeue_send(file, packet); err_msg: ib_free_send_mad(packet->msg); err_ah: rdma_destroy_ah(ah, RDMA_DESTROY_AH_SLEEPABLE); err_up: mutex_unlock(&file->mutex); err: kfree(packet); return ret; } static __poll_t ib_umad_poll(struct file *filp, struct poll_table_struct *wait) { struct ib_umad_file *file = filp->private_data; /* we will always be able to post a MAD send */ __poll_t mask = EPOLLOUT | EPOLLWRNORM; mutex_lock(&file->mutex); poll_wait(filp, &file->recv_wait, wait); if (!list_empty(&file->recv_list)) mask |= EPOLLIN | EPOLLRDNORM; if (file->agents_dead) mask = EPOLLERR; mutex_unlock(&file->mutex); return mask; } static int ib_umad_reg_agent(struct ib_umad_file *file, void __user *arg, int compat_method_mask) { struct ib_user_mad_reg_req ureq; struct ib_mad_reg_req req; struct ib_mad_agent *agent = NULL; int agent_id; int ret; mutex_lock(&file->port->file_mutex); mutex_lock(&file->mutex); if (!file->port->ib_dev) { dev_notice(&file->port->dev, "%s: invalid device\n", __func__); ret = -EPIPE; goto out; } if (copy_from_user(&ureq, arg, sizeof ureq)) { ret = -EFAULT; goto out; } if (ureq.qpn != 0 && ureq.qpn != 1) { dev_notice(&file->port->dev, "%s: invalid QPN %u specified\n", __func__, ureq.qpn); ret = -EINVAL; goto out; } for (agent_id = 0; agent_id < IB_UMAD_MAX_AGENTS; ++agent_id) if (!__get_agent(file, agent_id)) goto found; dev_notice(&file->port->dev, "%s: Max Agents (%u) reached\n", __func__, IB_UMAD_MAX_AGENTS); ret = -ENOMEM; goto out; found: if (ureq.mgmt_class) { memset(&req, 0, sizeof(req)); req.mgmt_class = ureq.mgmt_class; req.mgmt_class_version = ureq.mgmt_class_version; memcpy(req.oui, ureq.oui, sizeof req.oui); if (compat_method_mask) { u32 *umm = (u32 *) ureq.method_mask; int i; for (i = 0; i < BITS_TO_LONGS(IB_MGMT_MAX_METHODS); ++i) req.method_mask[i] = umm[i * 2] | ((u64) umm[i * 2 + 1] << 32); } else memcpy(req.method_mask, ureq.method_mask, sizeof req.method_mask); } agent = ib_register_mad_agent(file->port->ib_dev, file->port->port_num, ureq.qpn ? IB_QPT_GSI : IB_QPT_SMI, ureq.mgmt_class ? &req : NULL, ureq.rmpp_version, send_handler, recv_handler, file, 0); if (IS_ERR(agent)) { ret = PTR_ERR(agent); agent = NULL; goto out; } if (put_user(agent_id, (u32 __user *) (arg + offsetof(struct ib_user_mad_reg_req, id)))) { ret = -EFAULT; goto out; } if (!file->already_used) { file->already_used = 1; if (!file->use_pkey_index) { dev_warn(&file->port->dev, "process %s did not enable P_Key index support.\n", current->comm); dev_warn(&file->port->dev, " Documentation/infiniband/user_mad.rst has info on the new ABI.\n"); } } file->agent[agent_id] = agent; ret = 0; out: mutex_unlock(&file->mutex); if (ret && agent) ib_unregister_mad_agent(agent); mutex_unlock(&file->port->file_mutex); return ret; } static int ib_umad_reg_agent2(struct ib_umad_file *file, void __user *arg) { struct ib_user_mad_reg_req2 ureq; struct ib_mad_reg_req req; struct ib_mad_agent *agent = NULL; int agent_id; int ret; mutex_lock(&file->port->file_mutex); mutex_lock(&file->mutex); if (!file->port->ib_dev) { dev_notice(&file->port->dev, "%s: invalid device\n", __func__); ret = -EPIPE; goto out; } if (copy_from_user(&ureq, arg, sizeof(ureq))) { ret = -EFAULT; goto out; } if (ureq.qpn != 0 && ureq.qpn != 1) { dev_notice(&file->port->dev, "%s: invalid QPN %u specified\n", __func__, ureq.qpn); ret = -EINVAL; goto out; } if (ureq.flags & ~IB_USER_MAD_REG_FLAGS_CAP) { dev_notice(&file->port->dev, "%s failed: invalid registration flags specified 0x%x; supported 0x%x\n", __func__, ureq.flags, IB_USER_MAD_REG_FLAGS_CAP); ret = -EINVAL; if (put_user((u32)IB_USER_MAD_REG_FLAGS_CAP, (u32 __user *) (arg + offsetof(struct ib_user_mad_reg_req2, flags)))) ret = -EFAULT; goto out; } for (agent_id = 0; agent_id < IB_UMAD_MAX_AGENTS; ++agent_id) if (!__get_agent(file, agent_id)) goto found; dev_notice(&file->port->dev, "%s: Max Agents (%u) reached\n", __func__, IB_UMAD_MAX_AGENTS); ret = -ENOMEM; goto out; found: if (ureq.mgmt_class) { memset(&req, 0, sizeof(req)); req.mgmt_class = ureq.mgmt_class; req.mgmt_class_version = ureq.mgmt_class_version; if (ureq.oui & 0xff000000) { dev_notice(&file->port->dev, "%s failed: oui invalid 0x%08x\n", __func__, ureq.oui); ret = -EINVAL; goto out; } req.oui[2] = ureq.oui & 0x0000ff; req.oui[1] = (ureq.oui & 0x00ff00) >> 8; req.oui[0] = (ureq.oui & 0xff0000) >> 16; memcpy(req.method_mask, ureq.method_mask, sizeof(req.method_mask)); } agent = ib_register_mad_agent(file->port->ib_dev, file->port->port_num, ureq.qpn ? IB_QPT_GSI : IB_QPT_SMI, ureq.mgmt_class ? &req : NULL, ureq.rmpp_version, send_handler, recv_handler, file, ureq.flags); if (IS_ERR(agent)) { ret = PTR_ERR(agent); agent = NULL; goto out; } if (put_user(agent_id, (u32 __user *)(arg + offsetof(struct ib_user_mad_reg_req2, id)))) { ret = -EFAULT; goto out; } if (!file->already_used) { file->already_used = 1; file->use_pkey_index = 1; } file->agent[agent_id] = agent; ret = 0; out: mutex_unlock(&file->mutex); if (ret && agent) ib_unregister_mad_agent(agent); mutex_unlock(&file->port->file_mutex); return ret; } static int ib_umad_unreg_agent(struct ib_umad_file *file, u32 __user *arg) { struct ib_mad_agent *agent = NULL; u32 id; int ret = 0; if (get_user(id, arg)) return -EFAULT; if (id >= IB_UMAD_MAX_AGENTS) return -EINVAL; mutex_lock(&file->port->file_mutex); mutex_lock(&file->mutex); id = array_index_nospec(id, IB_UMAD_MAX_AGENTS); if (!__get_agent(file, id)) { ret = -EINVAL; goto out; } agent = file->agent[id]; file->agent[id] = NULL; out: mutex_unlock(&file->mutex); if (agent) ib_unregister_mad_agent(agent); mutex_unlock(&file->port->file_mutex); return ret; } static long ib_umad_enable_pkey(struct ib_umad_file *file) { int ret = 0; mutex_lock(&file->mutex); if (file->already_used) ret = -EINVAL; else file->use_pkey_index = 1; mutex_unlock(&file->mutex); return ret; } static long ib_umad_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { switch (cmd) { case IB_USER_MAD_REGISTER_AGENT: return ib_umad_reg_agent(filp->private_data, (void __user *) arg, 0); case IB_USER_MAD_UNREGISTER_AGENT: return ib_umad_unreg_agent(filp->private_data, (__u32 __user *) arg); case IB_USER_MAD_ENABLE_PKEY: return ib_umad_enable_pkey(filp->private_data); case IB_USER_MAD_REGISTER_AGENT2: return ib_umad_reg_agent2(filp->private_data, (void __user *) arg); default: return -ENOIOCTLCMD; } } #ifdef CONFIG_COMPAT static long ib_umad_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { switch (cmd) { case IB_USER_MAD_REGISTER_AGENT: return ib_umad_reg_agent(filp->private_data, compat_ptr(arg), 1); case IB_USER_MAD_UNREGISTER_AGENT: return ib_umad_unreg_agent(filp->private_data, compat_ptr(arg)); case IB_USER_MAD_ENABLE_PKEY: return ib_umad_enable_pkey(filp->private_data); case IB_USER_MAD_REGISTER_AGENT2: return ib_umad_reg_agent2(filp->private_data, compat_ptr(arg)); default: return -ENOIOCTLCMD; } } #endif /* * ib_umad_open() does not need the BKL: * * - the ib_umad_port structures are properly reference counted, and * everything else is purely local to the file being created, so * races against other open calls are not a problem; * - the ioctl method does not affect any global state outside of the * file structure being operated on; */ static int ib_umad_open(struct inode *inode, struct file *filp) { struct ib_umad_port *port; struct ib_umad_file *file; int ret = 0; port = container_of(inode->i_cdev, struct ib_umad_port, cdev); mutex_lock(&port->file_mutex); if (!port->ib_dev) { ret = -ENXIO; goto out; } if (!rdma_dev_access_netns(port->ib_dev, current->nsproxy->net_ns)) { ret = -EPERM; goto out; } file = kzalloc(sizeof(*file), GFP_KERNEL); if (!file) { ret = -ENOMEM; goto out; } mutex_init(&file->mutex); spin_lock_init(&file->send_lock); INIT_LIST_HEAD(&file->recv_list); INIT_LIST_HEAD(&file->send_list); init_waitqueue_head(&file->recv_wait); file->port = port; filp->private_data = file; list_add_tail(&file->port_list, &port->file_list); stream_open(inode, filp); out: mutex_unlock(&port->file_mutex); return ret; } static int ib_umad_close(struct inode *inode, struct file *filp) { struct ib_umad_file *file = filp->private_data; struct ib_umad_packet *packet, *tmp; int already_dead; int i; mutex_lock(&file->port->file_mutex); mutex_lock(&file->mutex); already_dead = file->agents_dead; file->agents_dead = 1; list_for_each_entry_safe(packet, tmp, &file->recv_list, list) { if (packet->recv_wc) ib_free_recv_mad(packet->recv_wc); kfree(packet); } list_del(&file->port_list); mutex_unlock(&file->mutex); if (!already_dead) for (i = 0; i < IB_UMAD_MAX_AGENTS; ++i) if (file->agent[i]) ib_unregister_mad_agent(file->agent[i]); mutex_unlock(&file->port->file_mutex); mutex_destroy(&file->mutex); kfree(file); return 0; } static const struct file_operations umad_fops = { .owner = THIS_MODULE, .read = ib_umad_read, .write = ib_umad_write, .poll = ib_umad_poll, .unlocked_ioctl = ib_umad_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ib_umad_compat_ioctl, #endif .open = ib_umad_open, .release = ib_umad_close, .llseek = no_llseek, }; static int ib_umad_sm_open(struct inode *inode, struct file *filp) { struct ib_umad_port *port; struct ib_port_modify props = { .set_port_cap_mask = IB_PORT_SM }; int ret; port = container_of(inode->i_cdev, struct ib_umad_port, sm_cdev); if (filp->f_flags & O_NONBLOCK) { if (down_trylock(&port->sm_sem)) { ret = -EAGAIN; goto fail; } } else { if (down_interruptible(&port->sm_sem)) { ret = -ERESTARTSYS; goto fail; } } if (!rdma_dev_access_netns(port->ib_dev, current->nsproxy->net_ns)) { ret = -EPERM; goto err_up_sem; } ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props); if (ret) goto err_up_sem; filp->private_data = port; nonseekable_open(inode, filp); return 0; err_up_sem: up(&port->sm_sem); fail: return ret; } static int ib_umad_sm_close(struct inode *inode, struct file *filp) { struct ib_umad_port *port = filp->private_data; struct ib_port_modify props = { .clr_port_cap_mask = IB_PORT_SM }; int ret = 0; mutex_lock(&port->file_mutex); if (port->ib_dev) ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props); mutex_unlock(&port->file_mutex); up(&port->sm_sem); return ret; } static const struct file_operations umad_sm_fops = { .owner = THIS_MODULE, .open = ib_umad_sm_open, .release = ib_umad_sm_close, .llseek = no_llseek, }; static struct ib_umad_port *get_port(struct ib_device *ibdev, struct ib_umad_device *umad_dev, u32 port) { if (!umad_dev) return ERR_PTR(-EOPNOTSUPP); if (!rdma_is_port_valid(ibdev, port)) return ERR_PTR(-EINVAL); if (!rdma_cap_ib_mad(ibdev, port)) return ERR_PTR(-EOPNOTSUPP); return &umad_dev->ports[port - rdma_start_port(ibdev)]; } static int ib_umad_get_nl_info(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res) { struct ib_umad_port *port = get_port(ibdev, client_data, res->port); if (IS_ERR(port)) return PTR_ERR(port); res->abi = IB_USER_MAD_ABI_VERSION; res->cdev = &port->dev; return 0; } static struct ib_client umad_client = { .name = "umad", .add = ib_umad_add_one, .remove = ib_umad_remove_one, .get_nl_info = ib_umad_get_nl_info, }; MODULE_ALIAS_RDMA_CLIENT("umad"); static int ib_issm_get_nl_info(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res) { struct ib_umad_port *port = get_port(ibdev, client_data, res->port); if (IS_ERR(port)) return PTR_ERR(port); res->abi = IB_USER_MAD_ABI_VERSION; res->cdev = &port->sm_dev; return 0; } static struct ib_client issm_client = { .name = "issm", .get_nl_info = ib_issm_get_nl_info, }; MODULE_ALIAS_RDMA_CLIENT("issm"); static ssize_t ibdev_show(struct device *dev, struct device_attribute *attr, char *buf) { struct ib_umad_port *port = dev_get_drvdata(dev); if (!port) return -ENODEV; return sysfs_emit(buf, "%s\n", dev_name(&port->ib_dev->dev)); } static DEVICE_ATTR_RO(ibdev); static ssize_t port_show(struct device *dev, struct device_attribute *attr, char *buf) { struct ib_umad_port *port = dev_get_drvdata(dev); if (!port) return -ENODEV; return sysfs_emit(buf, "%d\n", port->port_num); } static DEVICE_ATTR_RO(port); static struct attribute *umad_class_dev_attrs[] = { &dev_attr_ibdev.attr, &dev_attr_port.attr, NULL, }; ATTRIBUTE_GROUPS(umad_class_dev); static char *umad_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev)); } static ssize_t abi_version_show(const struct class *class, const struct class_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", IB_USER_MAD_ABI_VERSION); } static CLASS_ATTR_RO(abi_version); static struct attribute *umad_class_attrs[] = { &class_attr_abi_version.attr, NULL, }; ATTRIBUTE_GROUPS(umad_class); static struct class umad_class = { .name = "infiniband_mad", .devnode = umad_devnode, .class_groups = umad_class_groups, .dev_groups = umad_class_dev_groups, }; static void ib_umad_release_port(struct device *device) { struct ib_umad_port *port = dev_get_drvdata(device); struct ib_umad_device *umad_dev = port->umad_dev; ib_umad_dev_put(umad_dev); } static void ib_umad_init_port_dev(struct device *dev, struct ib_umad_port *port, const struct ib_device *device) { device_initialize(dev); ib_umad_dev_get(port->umad_dev); dev->class = &umad_class; dev->parent = device->dev.parent; dev_set_drvdata(dev, port); dev->release = ib_umad_release_port; } static int ib_umad_init_port(struct ib_device *device, int port_num, struct ib_umad_device *umad_dev, struct ib_umad_port *port) { int devnum; dev_t base_umad; dev_t base_issm; int ret; devnum = ida_alloc_max(&umad_ida, IB_UMAD_MAX_PORTS - 1, GFP_KERNEL); if (devnum < 0) return -1; port->dev_num = devnum; if (devnum >= IB_UMAD_NUM_FIXED_MINOR) { base_umad = dynamic_umad_dev + devnum - IB_UMAD_NUM_FIXED_MINOR; base_issm = dynamic_issm_dev + devnum - IB_UMAD_NUM_FIXED_MINOR; } else { base_umad = devnum + base_umad_dev; base_issm = devnum + base_issm_dev; } port->ib_dev = device; port->umad_dev = umad_dev; port->port_num = port_num; sema_init(&port->sm_sem, 1); mutex_init(&port->file_mutex); INIT_LIST_HEAD(&port->file_list); ib_umad_init_port_dev(&port->dev, port, device); port->dev.devt = base_umad; dev_set_name(&port->dev, "umad%d", port->dev_num); cdev_init(&port->cdev, &umad_fops); port->cdev.owner = THIS_MODULE; ret = cdev_device_add(&port->cdev, &port->dev); if (ret) goto err_cdev; ib_umad_init_port_dev(&port->sm_dev, port, device); port->sm_dev.devt = base_issm; dev_set_name(&port->sm_dev, "issm%d", port->dev_num); cdev_init(&port->sm_cdev, &umad_sm_fops); port->sm_cdev.owner = THIS_MODULE; ret = cdev_device_add(&port->sm_cdev, &port->sm_dev); if (ret) goto err_dev; return 0; err_dev: put_device(&port->sm_dev); cdev_device_del(&port->cdev, &port->dev); err_cdev: put_device(&port->dev); ida_free(&umad_ida, devnum); return ret; } static void ib_umad_kill_port(struct ib_umad_port *port) { struct ib_umad_file *file; int id; cdev_device_del(&port->sm_cdev, &port->sm_dev); cdev_device_del(&port->cdev, &port->dev); mutex_lock(&port->file_mutex); /* Mark ib_dev NULL and block ioctl or other file ops to progress * further. */ port->ib_dev = NULL; list_for_each_entry(file, &port->file_list, port_list) { mutex_lock(&file->mutex); file->agents_dead = 1; wake_up_interruptible(&file->recv_wait); mutex_unlock(&file->mutex); for (id = 0; id < IB_UMAD_MAX_AGENTS; ++id) if (file->agent[id]) ib_unregister_mad_agent(file->agent[id]); } mutex_unlock(&port->file_mutex); ida_free(&umad_ida, port->dev_num); /* balances device_initialize() */ put_device(&port->sm_dev); put_device(&port->dev); } static int ib_umad_add_one(struct ib_device *device) { struct ib_umad_device *umad_dev; int s, e, i; int count = 0; int ret; s = rdma_start_port(device); e = rdma_end_port(device); umad_dev = kzalloc(struct_size(umad_dev, ports, size_add(size_sub(e, s), 1)), GFP_KERNEL); if (!umad_dev) return -ENOMEM; kref_init(&umad_dev->kref); for (i = s; i <= e; ++i) { if (!rdma_cap_ib_mad(device, i)) continue; ret = ib_umad_init_port(device, i, umad_dev, &umad_dev->ports[i - s]); if (ret) goto err; count++; } if (!count) { ret = -EOPNOTSUPP; goto free; } ib_set_client_data(device, &umad_client, umad_dev); return 0; err: while (--i >= s) { if (!rdma_cap_ib_mad(device, i)) continue; ib_umad_kill_port(&umad_dev->ports[i - s]); } free: /* balances kref_init */ ib_umad_dev_put(umad_dev); return ret; } static void ib_umad_remove_one(struct ib_device *device, void *client_data) { struct ib_umad_device *umad_dev = client_data; unsigned int i; rdma_for_each_port (device, i) { if (rdma_cap_ib_mad(device, i)) ib_umad_kill_port( &umad_dev->ports[i - rdma_start_port(device)]); } /* balances kref_init() */ ib_umad_dev_put(umad_dev); } static int __init ib_umad_init(void) { int ret; ret = register_chrdev_region(base_umad_dev, IB_UMAD_NUM_FIXED_MINOR * 2, umad_class.name); if (ret) { pr_err("couldn't register device number\n"); goto out; } ret = alloc_chrdev_region(&dynamic_umad_dev, 0, IB_UMAD_NUM_DYNAMIC_MINOR * 2, umad_class.name); if (ret) { pr_err("couldn't register dynamic device number\n"); goto out_alloc; } dynamic_issm_dev = dynamic_umad_dev + IB_UMAD_NUM_DYNAMIC_MINOR; ret = class_register(&umad_class); if (ret) { pr_err("couldn't create class infiniband_mad\n"); goto out_chrdev; } ret = ib_register_client(&umad_client); if (ret) goto out_class; ret = ib_register_client(&issm_client); if (ret) goto out_client; return 0; out_client: ib_unregister_client(&umad_client); out_class: class_unregister(&umad_class); out_chrdev: unregister_chrdev_region(dynamic_umad_dev, IB_UMAD_NUM_DYNAMIC_MINOR * 2); out_alloc: unregister_chrdev_region(base_umad_dev, IB_UMAD_NUM_FIXED_MINOR * 2); out: return ret; } static void __exit ib_umad_cleanup(void) { ib_unregister_client(&issm_client); ib_unregister_client(&umad_client); class_unregister(&umad_class); unregister_chrdev_region(base_umad_dev, IB_UMAD_NUM_FIXED_MINOR * 2); unregister_chrdev_region(dynamic_umad_dev, IB_UMAD_NUM_DYNAMIC_MINOR * 2); } module_init(ib_umad_init); module_exit(ib_umad_cleanup); |
| 2565 2426 208 2 177 103 2273 1501 2 1502 17 9 44 616 3715 41 3343 3044 486 184 184 3 3 4 4 4 4 4 4 99 10 158 158 70 3 3 67 136 138 67 517 33 2681 187 873 17 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_NOTIFY_H #define _LINUX_FS_NOTIFY_H /* * include/linux/fsnotify.h - generic hooks for filesystem notification, to * reduce in-source duplication from both dnotify and inotify. * * We don't compile any of this away in some complicated menagerie of ifdefs. * Instead, we rely on the code inside to optimize away as needed. * * (C) Copyright 2005 Robert Love */ #include <linux/fsnotify_backend.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/bug.h> /* Are there any inode/mount/sb objects watched with priority prio or above? */ static inline bool fsnotify_sb_has_priority_watchers(struct super_block *sb, int prio) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); /* Were any marks ever added to any object on this sb? */ if (!sbinfo) return false; return atomic_long_read(&sbinfo->watched_objects[prio]); } /* Are there any inode/mount/sb objects that are being watched at all? */ static inline bool fsnotify_sb_has_watchers(struct super_block *sb) { return fsnotify_sb_has_priority_watchers(sb, 0); } /* * Notify this @dir inode about a change in a child directory entry. * The directory entry may have turned positive or negative or its inode may * have changed (i.e. renamed over). * * Unlike fsnotify_parent(), the event will be reported regardless of the * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { if (!fsnotify_sb_has_watchers(dir->i_sb)) return 0; return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) { if (!fsnotify_sb_has_watchers(inode->i_sb)) return; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0); } /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { struct inode *inode = d_inode(dentry); if (!fsnotify_sb_has_watchers(inode->i_sb)) return 0; if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; /* sb/mount marks are not interested in name of directory */ if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) goto notify_child; } /* disconnected dentry cannot notify parent */ if (IS_ROOT(dentry)) goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); notify_child: return fsnotify(mask, data, data_type, NULL, NULL, inode, 0); } /* * Simple wrappers to consolidate calls to fsnotify_parent() when an event * is on a file/dentry. */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_file(struct file *file, __u32 mask) { const struct path *path; /* * FMODE_NONOTIFY are fds generated by fanotify itself which should not * generate new events. We also don't want to generate events for * FMODE_PATH fds (involves open & close events) as they are just * handle creation / destruction events and not "real" file events. */ if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH)) return 0; path = &file->f_path; /* Permission events require group prio >= FSNOTIFY_PRIO_CONTENT */ if (mask & ALL_FSNOTIFY_PERM_EVENTS && !fsnotify_sb_has_priority_watchers(path->dentry->d_sb, FSNOTIFY_PRIO_CONTENT)) return 0; return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* * fsnotify_file_area_perm - permission hook before access to file range */ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { __u32 fsnotify_mask = FS_ACCESS_PERM; /* * filesystem may be modified in the context of permission events * (e.g. by HSM filling a file on access), so sb freeze protection * must not be held. */ lockdep_assert_once(file_write_not_started(file)); if (!(perm_mask & MAY_READ)) return 0; return fsnotify_file(file, fsnotify_mask); } /* * fsnotify_file_perm - permission hook before file access */ static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return fsnotify_file_area_perm(file, perm_mask, NULL, 0); } /* * fsnotify_open_perm - permission hook before file open */ static inline int fsnotify_open_perm(struct file *file) { int ret; if (file->f_flags & __FMODE_EXEC) { ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); if (ret) return ret; } return fsnotify_file(file, FS_OPEN_PERM); } #else static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { return 0; } static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return 0; } static inline int fsnotify_open_perm(struct file *file) { return 0; } #endif /* * fsnotify_link_count - inode's link count changed */ static inline void fsnotify_link_count(struct inode *inode) { fsnotify_inode(inode, FS_ATTRIB); } /* * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const struct qstr *old_name, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; rename_mask |= FS_ISDIR; } /* Event with information about both old and new parent+name */ fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, old_dir, old_name, 0); fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } /* * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed */ static inline void fsnotify_inode_delete(struct inode *inode) { __fsnotify_inode_delete(inode); } /* * fsnotify_vfsmount_delete - a vfsmount is being destroyed, clean up is needed */ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) { __fsnotify_vfsmount_delete(mnt); } /* * fsnotify_inoderemove - an inode is going away */ static inline void fsnotify_inoderemove(struct inode *inode) { fsnotify_inode(inode, FS_DELETE_SELF); __fsnotify_inode_delete(inode); } /* * fsnotify_create - 'name' was linked in * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory * * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, dir, &new_dentry->d_name, 0); } /* * fsnotify_delete - @dentry was unlinked and unhashed * * Caller must make sure that dentry->d_name is stable. * * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode * as this may be called after d_delete() and old_dentry may be negative. */ static inline void fsnotify_delete(struct inode *dir, struct inode *inode, struct dentry *dentry) { __u32 mask = FS_DELETE; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, 0); } /** * d_delete_notify - delete a dentry and call fsnotify_delete() * @dentry: The dentry to delete * * This helper is used to guaranty that the unlinked inode cannot be found * by lookup of this name after fsnotify_delete() event has been delivered. */ static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); ihold(inode); d_delete(dentry); fsnotify_delete(dir, inode, dentry); iput(inode); } /* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_mkdir - directory 'name' was created * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* * fsnotify_rmdir - directory 'name' was removed * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_access - file was read */ static inline void fsnotify_access(struct file *file) { fsnotify_file(file, FS_ACCESS); } /* * fsnotify_modify - file was modified */ static inline void fsnotify_modify(struct file *file) { fsnotify_file(file, FS_MODIFY); } /* * fsnotify_open - file was opened */ static inline void fsnotify_open(struct file *file) { __u32 mask = FS_OPEN; if (file->f_flags & __FMODE_EXEC) mask |= FS_OPEN_EXEC; fsnotify_file(file, mask); } /* * fsnotify_close - file was closed */ static inline void fsnotify_close(struct file *file) { __u32 mask = (file->f_mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; fsnotify_file(file, mask); } /* * fsnotify_xattr - extended attributes were changed */ static inline void fsnotify_xattr(struct dentry *dentry) { fsnotify_dentry(dentry, FS_ATTRIB); } /* * fsnotify_change - notify_change event. file was modified and/or metadata * was changed. */ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) { __u32 mask = 0; if (ia_valid & ATTR_UID) mask |= FS_ATTRIB; if (ia_valid & ATTR_GID) mask |= FS_ATTRIB; if (ia_valid & ATTR_SIZE) mask |= FS_MODIFY; /* both times implies a utime(s) call */ if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) mask |= FS_ATTRIB; else if (ia_valid & ATTR_ATIME) mask |= FS_ACCESS; else if (ia_valid & ATTR_MTIME) mask |= FS_MODIFY; if (ia_valid & ATTR_MODE) mask |= FS_ATTRIB; if (mask) fsnotify_dentry(dentry, mask); } static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, int error) { struct fs_error_report report = { .error = error, .inode = inode, .sb = sb, }; return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, NULL, NULL, NULL, 0); } #endif /* _LINUX_FS_NOTIFY_H */ |
| 1 1 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef RQ_QOS_H #define RQ_QOS_H #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/blk_types.h> #include <linux/atomic.h> #include <linux/wait.h> #include <linux/blk-mq.h> #include "blk-mq-debugfs.h" struct blk_mq_debugfs_attr; enum rq_qos_id { RQ_QOS_WBT, RQ_QOS_LATENCY, RQ_QOS_COST, }; struct rq_wait { wait_queue_head_t wait; atomic_t inflight; }; struct rq_qos { const struct rq_qos_ops *ops; struct gendisk *disk; enum rq_qos_id id; struct rq_qos *next; #ifdef CONFIG_BLK_DEBUG_FS struct dentry *debugfs_dir; #endif }; struct rq_qos_ops { void (*throttle)(struct rq_qos *, struct bio *); void (*track)(struct rq_qos *, struct request *, struct bio *); void (*merge)(struct rq_qos *, struct request *, struct bio *); void (*issue)(struct rq_qos *, struct request *); void (*requeue)(struct rq_qos *, struct request *); void (*done)(struct rq_qos *, struct request *); void (*done_bio)(struct rq_qos *, struct bio *); void (*cleanup)(struct rq_qos *, struct bio *); void (*queue_depth_changed)(struct rq_qos *); void (*exit)(struct rq_qos *); const struct blk_mq_debugfs_attr *debugfs_attrs; }; struct rq_depth { unsigned int max_depth; int scale_step; bool scaled_max; unsigned int queue_depth; unsigned int default_depth; }; static inline struct rq_qos *rq_qos_id(struct request_queue *q, enum rq_qos_id id) { struct rq_qos *rqos; for (rqos = q->rq_qos; rqos; rqos = rqos->next) { if (rqos->id == id) break; } return rqos; } static inline struct rq_qos *wbt_rq_qos(struct request_queue *q) { return rq_qos_id(q, RQ_QOS_WBT); } static inline struct rq_qos *iolat_rq_qos(struct request_queue *q) { return rq_qos_id(q, RQ_QOS_LATENCY); } static inline void rq_wait_init(struct rq_wait *rq_wait) { atomic_set(&rq_wait->inflight, 0); init_waitqueue_head(&rq_wait->wait); } int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, const struct rq_qos_ops *ops); void rq_qos_del(struct rq_qos *rqos); typedef bool (acquire_inflight_cb_t)(struct rq_wait *rqw, void *private_data); typedef void (cleanup_cb_t)(struct rq_wait *rqw, void *private_data); void rq_qos_wait(struct rq_wait *rqw, void *private_data, acquire_inflight_cb_t *acquire_inflight_cb, cleanup_cb_t *cleanup_cb); bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit); bool rq_depth_scale_up(struct rq_depth *rqd); bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle); bool rq_depth_calc_max_depth(struct rq_depth *rqd); void __rq_qos_cleanup(struct rq_qos *rqos, struct bio *bio); void __rq_qos_done(struct rq_qos *rqos, struct request *rq); void __rq_qos_issue(struct rq_qos *rqos, struct request *rq); void __rq_qos_requeue(struct rq_qos *rqos, struct request *rq); void __rq_qos_throttle(struct rq_qos *rqos, struct bio *bio); void __rq_qos_track(struct rq_qos *rqos, struct request *rq, struct bio *bio); void __rq_qos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio); void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio); void __rq_qos_queue_depth_changed(struct rq_qos *rqos); static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio) { if (q->rq_qos) __rq_qos_cleanup(q->rq_qos, bio); } static inline void rq_qos_done(struct request_queue *q, struct request *rq) { if (q->rq_qos && !blk_rq_is_passthrough(rq)) __rq_qos_done(q->rq_qos, rq); } static inline void rq_qos_issue(struct request_queue *q, struct request *rq) { if (q->rq_qos) __rq_qos_issue(q->rq_qos, rq); } static inline void rq_qos_requeue(struct request_queue *q, struct request *rq) { if (q->rq_qos) __rq_qos_requeue(q->rq_qos, rq); } static inline void rq_qos_done_bio(struct bio *bio) { if (bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) || bio_flagged(bio, BIO_QOS_MERGED))) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); if (q->rq_qos) __rq_qos_done_bio(q->rq_qos, bio); } } static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) { if (q->rq_qos) { bio_set_flag(bio, BIO_QOS_THROTTLED); __rq_qos_throttle(q->rq_qos, bio); } } static inline void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio) { if (q->rq_qos) __rq_qos_track(q->rq_qos, rq, bio); } static inline void rq_qos_merge(struct request_queue *q, struct request *rq, struct bio *bio) { if (q->rq_qos) { bio_set_flag(bio, BIO_QOS_MERGED); __rq_qos_merge(q->rq_qos, rq, bio); } } static inline void rq_qos_queue_depth_changed(struct request_queue *q) { if (q->rq_qos) __rq_qos_queue_depth_changed(q->rq_qos); } void rq_qos_exit(struct request_queue *); #endif |
| 4 4 5 5 5 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 | // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Authors: Bernard Metzler <bmt@zurich.ibm.com> */ /* Copyright (c) 2008-2019, IBM Corporation */ #include <linux/errno.h> #include <linux/types.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/xarray.h> #include <net/addrconf.h> #include <rdma/iw_cm.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> #include <rdma/uverbs_ioctl.h> #include "siw.h" #include "siw_verbs.h" #include "siw_mem.h" static int siw_qp_state_to_ib_qp_state[SIW_QP_STATE_COUNT] = { [SIW_QP_STATE_IDLE] = IB_QPS_INIT, [SIW_QP_STATE_RTR] = IB_QPS_RTR, [SIW_QP_STATE_RTS] = IB_QPS_RTS, [SIW_QP_STATE_CLOSING] = IB_QPS_SQD, [SIW_QP_STATE_TERMINATE] = IB_QPS_SQE, [SIW_QP_STATE_ERROR] = IB_QPS_ERR }; static int ib_qp_state_to_siw_qp_state[IB_QPS_ERR + 1] = { [IB_QPS_RESET] = SIW_QP_STATE_IDLE, [IB_QPS_INIT] = SIW_QP_STATE_IDLE, [IB_QPS_RTR] = SIW_QP_STATE_RTR, [IB_QPS_RTS] = SIW_QP_STATE_RTS, [IB_QPS_SQD] = SIW_QP_STATE_CLOSING, [IB_QPS_SQE] = SIW_QP_STATE_TERMINATE, [IB_QPS_ERR] = SIW_QP_STATE_ERROR }; static char ib_qp_state_to_string[IB_QPS_ERR + 1][sizeof("RESET")] = { [IB_QPS_RESET] = "RESET", [IB_QPS_INIT] = "INIT", [IB_QPS_RTR] = "RTR", [IB_QPS_RTS] = "RTS", [IB_QPS_SQD] = "SQD", [IB_QPS_SQE] = "SQE", [IB_QPS_ERR] = "ERR" }; void siw_mmap_free(struct rdma_user_mmap_entry *rdma_entry) { struct siw_user_mmap_entry *entry = to_siw_mmap_entry(rdma_entry); kfree(entry); } int siw_mmap(struct ib_ucontext *ctx, struct vm_area_struct *vma) { struct siw_ucontext *uctx = to_siw_ctx(ctx); size_t size = vma->vm_end - vma->vm_start; struct rdma_user_mmap_entry *rdma_entry; struct siw_user_mmap_entry *entry; int rv = -EINVAL; /* * Must be page aligned */ if (vma->vm_start & (PAGE_SIZE - 1)) { pr_warn("siw: mmap not page aligned\n"); return -EINVAL; } rdma_entry = rdma_user_mmap_entry_get(&uctx->base_ucontext, vma); if (!rdma_entry) { siw_dbg(&uctx->sdev->base_dev, "mmap lookup failed: %lu, %#zx\n", vma->vm_pgoff, size); return -EINVAL; } entry = to_siw_mmap_entry(rdma_entry); rv = remap_vmalloc_range(vma, entry->address, 0); if (rv) pr_warn("remap_vmalloc_range failed: %lu, %zu\n", vma->vm_pgoff, size); rdma_user_mmap_entry_put(rdma_entry); return rv; } int siw_alloc_ucontext(struct ib_ucontext *base_ctx, struct ib_udata *udata) { struct siw_device *sdev = to_siw_dev(base_ctx->device); struct siw_ucontext *ctx = to_siw_ctx(base_ctx); struct siw_uresp_alloc_ctx uresp = {}; int rv; if (atomic_inc_return(&sdev->num_ctx) > SIW_MAX_CONTEXT) { rv = -ENOMEM; goto err_out; } ctx->sdev = sdev; uresp.dev_id = sdev->vendor_part_id; if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; goto err_out; } rv = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (rv) goto err_out; siw_dbg(base_ctx->device, "success. now %d context(s)\n", atomic_read(&sdev->num_ctx)); return 0; err_out: atomic_dec(&sdev->num_ctx); siw_dbg(base_ctx->device, "failure %d. now %d context(s)\n", rv, atomic_read(&sdev->num_ctx)); return rv; } void siw_dealloc_ucontext(struct ib_ucontext *base_ctx) { struct siw_ucontext *uctx = to_siw_ctx(base_ctx); atomic_dec(&uctx->sdev->num_ctx); } int siw_query_device(struct ib_device *base_dev, struct ib_device_attr *attr, struct ib_udata *udata) { struct siw_device *sdev = to_siw_dev(base_dev); if (udata->inlen || udata->outlen) return -EINVAL; memset(attr, 0, sizeof(*attr)); /* Revisit atomic caps if RFC 7306 gets supported */ attr->atomic_cap = 0; attr->device_cap_flags = IB_DEVICE_MEM_MGT_EXTENSIONS; attr->kernel_cap_flags = IBK_ALLOW_USER_UNREG; attr->max_cq = sdev->attrs.max_cq; attr->max_cqe = sdev->attrs.max_cqe; attr->max_fast_reg_page_list_len = SIW_MAX_SGE_PBL; attr->max_mr = sdev->attrs.max_mr; attr->max_mw = sdev->attrs.max_mw; attr->max_mr_size = ~0ull; attr->max_pd = sdev->attrs.max_pd; attr->max_qp = sdev->attrs.max_qp; attr->max_qp_init_rd_atom = sdev->attrs.max_ird; attr->max_qp_rd_atom = sdev->attrs.max_ord; attr->max_qp_wr = sdev->attrs.max_qp_wr; attr->max_recv_sge = sdev->attrs.max_sge; attr->max_res_rd_atom = sdev->attrs.max_qp * sdev->attrs.max_ird; attr->max_send_sge = sdev->attrs.max_sge; attr->max_sge_rd = sdev->attrs.max_sge_rd; attr->max_srq = sdev->attrs.max_srq; attr->max_srq_sge = sdev->attrs.max_srq_sge; attr->max_srq_wr = sdev->attrs.max_srq_wr; attr->page_size_cap = PAGE_SIZE; attr->vendor_id = SIW_VENDOR_ID; attr->vendor_part_id = sdev->vendor_part_id; addrconf_addr_eui48((u8 *)&attr->sys_image_guid, sdev->raw_gid); return 0; } int siw_query_port(struct ib_device *base_dev, u32 port, struct ib_port_attr *attr) { struct siw_device *sdev = to_siw_dev(base_dev); int rv; memset(attr, 0, sizeof(*attr)); rv = ib_get_eth_speed(base_dev, port, &attr->active_speed, &attr->active_width); attr->gid_tbl_len = 1; attr->max_msg_sz = -1; attr->max_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); attr->active_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); attr->phys_state = sdev->state == IB_PORT_ACTIVE ? IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED; attr->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_DEVICE_MGMT_SUP; attr->state = sdev->state; /* * All zero * * attr->lid = 0; * attr->bad_pkey_cntr = 0; * attr->qkey_viol_cntr = 0; * attr->sm_lid = 0; * attr->lmc = 0; * attr->max_vl_num = 0; * attr->sm_sl = 0; * attr->subnet_timeout = 0; * attr->init_type_repy = 0; */ return rv; } int siw_get_port_immutable(struct ib_device *base_dev, u32 port, struct ib_port_immutable *port_immutable) { struct ib_port_attr attr; int rv = siw_query_port(base_dev, port, &attr); if (rv) return rv; port_immutable->gid_tbl_len = attr.gid_tbl_len; port_immutable->core_cap_flags = RDMA_CORE_PORT_IWARP; return 0; } int siw_query_gid(struct ib_device *base_dev, u32 port, int idx, union ib_gid *gid) { struct siw_device *sdev = to_siw_dev(base_dev); /* subnet_prefix == interface_id == 0; */ memset(gid, 0, sizeof(*gid)); memcpy(gid->raw, sdev->raw_gid, ETH_ALEN); return 0; } int siw_alloc_pd(struct ib_pd *pd, struct ib_udata *udata) { struct siw_device *sdev = to_siw_dev(pd->device); if (atomic_inc_return(&sdev->num_pd) > SIW_MAX_PD) { atomic_dec(&sdev->num_pd); return -ENOMEM; } siw_dbg_pd(pd, "now %d PD's(s)\n", atomic_read(&sdev->num_pd)); return 0; } int siw_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata) { struct siw_device *sdev = to_siw_dev(pd->device); siw_dbg_pd(pd, "free PD\n"); atomic_dec(&sdev->num_pd); return 0; } void siw_qp_get_ref(struct ib_qp *base_qp) { siw_qp_get(to_siw_qp(base_qp)); } void siw_qp_put_ref(struct ib_qp *base_qp) { siw_qp_put(to_siw_qp(base_qp)); } static struct rdma_user_mmap_entry * siw_mmap_entry_insert(struct siw_ucontext *uctx, void *address, size_t length, u64 *offset) { struct siw_user_mmap_entry *entry = kzalloc(sizeof(*entry), GFP_KERNEL); int rv; *offset = SIW_INVAL_UOBJ_KEY; if (!entry) return NULL; entry->address = address; rv = rdma_user_mmap_entry_insert(&uctx->base_ucontext, &entry->rdma_entry, length); if (rv) { kfree(entry); return NULL; } *offset = rdma_user_mmap_get_offset(&entry->rdma_entry); return &entry->rdma_entry; } /* * siw_create_qp() * * Create QP of requested size on given device. * * @qp: Queue pait * @attrs: Initial QP attributes. * @udata: used to provide QP ID, SQ and RQ size back to user. */ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, struct ib_udata *udata) { struct ib_pd *pd = ibqp->pd; struct siw_qp *qp = to_siw_qp(ibqp); struct ib_device *base_dev = pd->device; struct siw_device *sdev = to_siw_dev(base_dev); struct siw_ucontext *uctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); unsigned long flags; int num_sqe, num_rqe, rv = 0; size_t length; siw_dbg(base_dev, "create new QP\n"); if (attrs->create_flags) return -EOPNOTSUPP; if (atomic_inc_return(&sdev->num_qp) > SIW_MAX_QP) { siw_dbg(base_dev, "too many QP's\n"); rv = -ENOMEM; goto err_atomic; } if (attrs->qp_type != IB_QPT_RC) { siw_dbg(base_dev, "only RC QP's supported\n"); rv = -EOPNOTSUPP; goto err_atomic; } if ((attrs->cap.max_send_wr > SIW_MAX_QP_WR) || (attrs->cap.max_recv_wr > SIW_MAX_QP_WR) || (attrs->cap.max_send_sge > SIW_MAX_SGE) || (attrs->cap.max_recv_sge > SIW_MAX_SGE)) { siw_dbg(base_dev, "QP size error\n"); rv = -EINVAL; goto err_atomic; } if (attrs->cap.max_inline_data > SIW_MAX_INLINE) { siw_dbg(base_dev, "max inline send: %d > %d\n", attrs->cap.max_inline_data, (int)SIW_MAX_INLINE); rv = -EINVAL; goto err_atomic; } /* * NOTE: we don't allow for a QP unable to hold any SQ WQE */ if (attrs->cap.max_send_wr == 0) { siw_dbg(base_dev, "QP must have send queue\n"); rv = -EINVAL; goto err_atomic; } if (!attrs->send_cq || (!attrs->recv_cq && !attrs->srq)) { siw_dbg(base_dev, "send CQ or receive CQ invalid\n"); rv = -EINVAL; goto err_atomic; } init_rwsem(&qp->state_lock); spin_lock_init(&qp->sq_lock); spin_lock_init(&qp->rq_lock); spin_lock_init(&qp->orq_lock); rv = siw_qp_add(sdev, qp); if (rv) goto err_atomic; /* All queue indices are derived from modulo operations * on a free running 'get' (consumer) and 'put' (producer) * unsigned counter. Having queue sizes at power of two * avoids handling counter wrap around. */ num_sqe = roundup_pow_of_two(attrs->cap.max_send_wr); num_rqe = attrs->cap.max_recv_wr; if (num_rqe) num_rqe = roundup_pow_of_two(num_rqe); if (udata) qp->sendq = vmalloc_user(num_sqe * sizeof(struct siw_sqe)); else qp->sendq = vcalloc(num_sqe, sizeof(struct siw_sqe)); if (qp->sendq == NULL) { rv = -ENOMEM; goto err_out_xa; } if (attrs->sq_sig_type != IB_SIGNAL_REQ_WR) { if (attrs->sq_sig_type == IB_SIGNAL_ALL_WR) qp->attrs.flags |= SIW_SIGNAL_ALL_WR; else { rv = -EINVAL; goto err_out_xa; } } qp->pd = pd; qp->scq = to_siw_cq(attrs->send_cq); qp->rcq = to_siw_cq(attrs->recv_cq); if (attrs->srq) { /* * SRQ support. * Verbs 6.3.7: ignore RQ size, if SRQ present * Verbs 6.3.5: do not check PD of SRQ against PD of QP */ qp->srq = to_siw_srq(attrs->srq); qp->attrs.rq_size = 0; siw_dbg(base_dev, "QP [%u]: SRQ attached\n", qp->base_qp.qp_num); } else if (num_rqe) { if (udata) qp->recvq = vmalloc_user(num_rqe * sizeof(struct siw_rqe)); else qp->recvq = vcalloc(num_rqe, sizeof(struct siw_rqe)); if (qp->recvq == NULL) { rv = -ENOMEM; goto err_out_xa; } qp->attrs.rq_size = num_rqe; } qp->attrs.sq_size = num_sqe; qp->attrs.sq_max_sges = attrs->cap.max_send_sge; qp->attrs.rq_max_sges = attrs->cap.max_recv_sge; /* Make those two tunables fixed for now. */ qp->tx_ctx.gso_seg_limit = 1; qp->tx_ctx.zcopy_tx = zcopy_tx; qp->attrs.state = SIW_QP_STATE_IDLE; if (udata) { struct siw_uresp_create_qp uresp = {}; uresp.num_sqe = num_sqe; uresp.num_rqe = num_rqe; uresp.qp_id = qp_id(qp); if (qp->sendq) { length = num_sqe * sizeof(struct siw_sqe); qp->sq_entry = siw_mmap_entry_insert(uctx, qp->sendq, length, &uresp.sq_key); if (!qp->sq_entry) { rv = -ENOMEM; goto err_out_xa; } } if (qp->recvq) { length = num_rqe * sizeof(struct siw_rqe); qp->rq_entry = siw_mmap_entry_insert(uctx, qp->recvq, length, &uresp.rq_key); if (!qp->rq_entry) { uresp.sq_key = SIW_INVAL_UOBJ_KEY; rv = -ENOMEM; goto err_out_xa; } } if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; goto err_out_xa; } rv = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (rv) goto err_out_xa; } qp->tx_cpu = siw_get_tx_cpu(sdev); if (qp->tx_cpu < 0) { rv = -EINVAL; goto err_out_xa; } INIT_LIST_HEAD(&qp->devq); spin_lock_irqsave(&sdev->lock, flags); list_add_tail(&qp->devq, &sdev->qp_list); spin_unlock_irqrestore(&sdev->lock, flags); init_completion(&qp->qp_free); return 0; err_out_xa: xa_erase(&sdev->qp_xa, qp_id(qp)); if (uctx) { rdma_user_mmap_entry_remove(qp->sq_entry); rdma_user_mmap_entry_remove(qp->rq_entry); } vfree(qp->sendq); vfree(qp->recvq); err_atomic: atomic_dec(&sdev->num_qp); return rv; } /* * Minimum siw_query_qp() verb interface. * * @qp_attr_mask is not used but all available information is provided */ int siw_query_qp(struct ib_qp *base_qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) { struct siw_qp *qp; struct siw_device *sdev; if (base_qp && qp_attr && qp_init_attr) { qp = to_siw_qp(base_qp); sdev = to_siw_dev(base_qp->device); } else { return -EINVAL; } qp_attr->qp_state = siw_qp_state_to_ib_qp_state[qp->attrs.state]; qp_attr->cap.max_inline_data = SIW_MAX_INLINE; qp_attr->cap.max_send_wr = qp->attrs.sq_size; qp_attr->cap.max_send_sge = qp->attrs.sq_max_sges; qp_attr->cap.max_recv_wr = qp->attrs.rq_size; qp_attr->cap.max_recv_sge = qp->attrs.rq_max_sges; qp_attr->path_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); qp_attr->max_rd_atomic = qp->attrs.irq_size; qp_attr->max_dest_rd_atomic = qp->attrs.orq_size; qp_attr->qp_access_flags = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ; qp_init_attr->qp_type = base_qp->qp_type; qp_init_attr->send_cq = base_qp->send_cq; qp_init_attr->recv_cq = base_qp->recv_cq; qp_init_attr->srq = base_qp->srq; qp_init_attr->cap = qp_attr->cap; return 0; } int siw_verbs_modify_qp(struct ib_qp *base_qp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) { struct siw_qp_attrs new_attrs; enum siw_qp_attr_mask siw_attr_mask = 0; struct siw_qp *qp = to_siw_qp(base_qp); int rv = 0; if (!attr_mask) return 0; if (attr_mask & ~IB_QP_ATTR_STANDARD_BITS) return -EOPNOTSUPP; memset(&new_attrs, 0, sizeof(new_attrs)); if (attr_mask & IB_QP_ACCESS_FLAGS) { siw_attr_mask = SIW_QP_ATTR_ACCESS_FLAGS; if (attr->qp_access_flags & IB_ACCESS_REMOTE_READ) new_attrs.flags |= SIW_RDMA_READ_ENABLED; if (attr->qp_access_flags & IB_ACCESS_REMOTE_WRITE) new_attrs.flags |= SIW_RDMA_WRITE_ENABLED; if (attr->qp_access_flags & IB_ACCESS_MW_BIND) new_attrs.flags |= SIW_RDMA_BIND_ENABLED; } if (attr_mask & IB_QP_STATE) { siw_dbg_qp(qp, "desired IB QP state: %s\n", ib_qp_state_to_string[attr->qp_state]); new_attrs.state = ib_qp_state_to_siw_qp_state[attr->qp_state]; if (new_attrs.state > SIW_QP_STATE_RTS) qp->tx_ctx.tx_suspend = 1; siw_attr_mask |= SIW_QP_ATTR_STATE; } if (!siw_attr_mask) goto out; down_write(&qp->state_lock); rv = siw_qp_modify(qp, &new_attrs, siw_attr_mask); up_write(&qp->state_lock); out: return rv; } int siw_destroy_qp(struct ib_qp *base_qp, struct ib_udata *udata) { struct siw_qp *qp = to_siw_qp(base_qp); struct siw_ucontext *uctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); struct siw_qp_attrs qp_attrs; siw_dbg_qp(qp, "state %d\n", qp->attrs.state); /* * Mark QP as in process of destruction to prevent from * any async callbacks to RDMA core */ qp->attrs.flags |= SIW_QP_IN_DESTROY; qp->rx_stream.rx_suspend = 1; if (uctx) { rdma_user_mmap_entry_remove(qp->sq_entry); rdma_user_mmap_entry_remove(qp->rq_entry); } down_write(&qp->state_lock); qp_attrs.state = SIW_QP_STATE_ERROR; siw_qp_modify(qp, &qp_attrs, SIW_QP_ATTR_STATE); if (qp->cep) { siw_cep_put(qp->cep); qp->cep = NULL; } up_write(&qp->state_lock); kfree(qp->tx_ctx.mpa_crc_hd); kfree(qp->rx_stream.mpa_crc_hd); qp->scq = qp->rcq = NULL; siw_qp_put(qp); wait_for_completion(&qp->qp_free); return 0; } /* * siw_copy_inline_sgl() * * Prepare sgl of inlined data for sending. For userland callers * function checks if given buffer addresses and len's are within * process context bounds. * Data from all provided sge's are copied together into the wqe, * referenced by a single sge. */ static int siw_copy_inline_sgl(const struct ib_send_wr *core_wr, struct siw_sqe *sqe) { struct ib_sge *core_sge = core_wr->sg_list; void *kbuf = &sqe->sge[1]; int num_sge = core_wr->num_sge, bytes = 0; sqe->sge[0].laddr = (uintptr_t)kbuf; sqe->sge[0].lkey = 0; while (num_sge--) { if (!core_sge->length) { core_sge++; continue; } bytes += core_sge->length; if (bytes > SIW_MAX_INLINE) { bytes = -EINVAL; break; } memcpy(kbuf, ib_virt_dma_to_ptr(core_sge->addr), core_sge->length); kbuf += core_sge->length; core_sge++; } sqe->sge[0].length = max(bytes, 0); sqe->num_sge = bytes > 0 ? 1 : 0; return bytes; } /* Complete SQ WR's without processing */ static int siw_sq_flush_wr(struct siw_qp *qp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr) { int rv = 0; while (wr) { struct siw_sqe sqe = {}; switch (wr->opcode) { case IB_WR_RDMA_WRITE: sqe.opcode = SIW_OP_WRITE; break; case IB_WR_RDMA_READ: sqe.opcode = SIW_OP_READ; break; case IB_WR_RDMA_READ_WITH_INV: sqe.opcode = SIW_OP_READ_LOCAL_INV; break; case IB_WR_SEND: sqe.opcode = SIW_OP_SEND; break; case IB_WR_SEND_WITH_IMM: sqe.opcode = SIW_OP_SEND_WITH_IMM; break; case IB_WR_SEND_WITH_INV: sqe.opcode = SIW_OP_SEND_REMOTE_INV; break; case IB_WR_LOCAL_INV: sqe.opcode = SIW_OP_INVAL_STAG; break; case IB_WR_REG_MR: sqe.opcode = SIW_OP_REG_MR; break; default: rv = -EINVAL; break; } if (!rv) { sqe.id = wr->wr_id; rv = siw_sqe_complete(qp, &sqe, 0, SIW_WC_WR_FLUSH_ERR); } if (rv) { if (bad_wr) *bad_wr = wr; break; } wr = wr->next; } return rv; } /* Complete RQ WR's without processing */ static int siw_rq_flush_wr(struct siw_qp *qp, const struct ib_recv_wr *wr, const struct ib_recv_wr **bad_wr) { struct siw_rqe rqe = {}; int rv = 0; while (wr) { rqe.id = wr->wr_id; rv = siw_rqe_complete(qp, &rqe, 0, 0, SIW_WC_WR_FLUSH_ERR); if (rv) { if (bad_wr) *bad_wr = wr; break; } wr = wr->next; } return rv; } /* * siw_post_send() * * Post a list of S-WR's to a SQ. * * @base_qp: Base QP contained in siw QP * @wr: Null terminated list of user WR's * @bad_wr: Points to failing WR in case of synchronous failure. */ int siw_post_send(struct ib_qp *base_qp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr) { struct siw_qp *qp = to_siw_qp(base_qp); struct siw_wqe *wqe = tx_wqe(qp); unsigned long flags; int rv = 0; if (wr && !rdma_is_kernel_res(&qp->base_qp.res)) { siw_dbg_qp(qp, "wr must be empty for user mapped sq\n"); *bad_wr = wr; return -EINVAL; } /* * Try to acquire QP state lock. Must be non-blocking * to accommodate kernel clients needs. */ if (!down_read_trylock(&qp->state_lock)) { if (qp->attrs.state == SIW_QP_STATE_ERROR) { /* * ERROR state is final, so we can be sure * this state will not change as long as the QP * exists. * * This handles an ib_drain_sq() call with * a concurrent request to set the QP state * to ERROR. */ rv = siw_sq_flush_wr(qp, wr, bad_wr); } else { siw_dbg_qp(qp, "QP locked, state %d\n", qp->attrs.state); *bad_wr = wr; rv = -ENOTCONN; } return rv; } if (unlikely(qp->attrs.state != SIW_QP_STATE_RTS)) { if (qp->attrs.state == SIW_QP_STATE_ERROR) { /* * Immediately flush this WR to CQ, if QP * is in ERROR state. SQ is guaranteed to * be empty, so WR complets in-order. * * Typically triggered by ib_drain_sq(). */ rv = siw_sq_flush_wr(qp, wr, bad_wr); } else { siw_dbg_qp(qp, "QP out of state %d\n", qp->attrs.state); *bad_wr = wr; rv = -ENOTCONN; } up_read(&qp->state_lock); return rv; } spin_lock_irqsave(&qp->sq_lock, flags); while (wr) { u32 idx = qp->sq_put % qp->attrs.sq_size; struct siw_sqe *sqe = &qp->sendq[idx]; if (sqe->flags) { siw_dbg_qp(qp, "sq full\n"); rv = -ENOMEM; break; } if (wr->num_sge > qp->attrs.sq_max_sges) { siw_dbg_qp(qp, "too many sge's: %d\n", wr->num_sge); rv = -EINVAL; break; } sqe->id = wr->wr_id; if ((wr->send_flags & IB_SEND_SIGNALED) || (qp->attrs.flags & SIW_SIGNAL_ALL_WR)) sqe->flags |= SIW_WQE_SIGNALLED; if (wr->send_flags & IB_SEND_FENCE) sqe->flags |= SIW_WQE_READ_FENCE; switch (wr->opcode) { case IB_WR_SEND: case IB_WR_SEND_WITH_INV: if (wr->send_flags & IB_SEND_SOLICITED) sqe->flags |= SIW_WQE_SOLICITED; if (!(wr->send_flags & IB_SEND_INLINE)) { siw_copy_sgl(wr->sg_list, sqe->sge, wr->num_sge); sqe->num_sge = wr->num_sge; } else { rv = siw_copy_inline_sgl(wr, sqe); if (rv <= 0) { rv = -EINVAL; break; } sqe->flags |= SIW_WQE_INLINE; sqe->num_sge = 1; } if (wr->opcode == IB_WR_SEND) sqe->opcode = SIW_OP_SEND; else { sqe->opcode = SIW_OP_SEND_REMOTE_INV; sqe->rkey = wr->ex.invalidate_rkey; } break; case IB_WR_RDMA_READ_WITH_INV: case IB_WR_RDMA_READ: /* * iWarp restricts RREAD sink to SGL containing * 1 SGE only. we could relax to SGL with multiple * elements referring the SAME ltag or even sending * a private per-rreq tag referring to a checked * local sgl with MULTIPLE ltag's. */ if (unlikely(wr->num_sge != 1)) { rv = -EINVAL; break; } siw_copy_sgl(wr->sg_list, &sqe->sge[0], 1); /* * NOTE: zero length RREAD is allowed! */ sqe->raddr = rdma_wr(wr)->remote_addr; sqe->rkey = rdma_wr(wr)->rkey; sqe->num_sge = 1; if (wr->opcode == IB_WR_RDMA_READ) sqe->opcode = SIW_OP_READ; else sqe->opcode = SIW_OP_READ_LOCAL_INV; break; case IB_WR_RDMA_WRITE: if (!(wr->send_flags & IB_SEND_INLINE)) { siw_copy_sgl(wr->sg_list, &sqe->sge[0], wr->num_sge); sqe->num_sge = wr->num_sge; } else { rv = siw_copy_inline_sgl(wr, sqe); if (unlikely(rv < 0)) { rv = -EINVAL; break; } sqe->flags |= SIW_WQE_INLINE; sqe->num_sge = 1; } sqe->raddr = rdma_wr(wr)->remote_addr; sqe->rkey = rdma_wr(wr)->rkey; sqe->opcode = SIW_OP_WRITE; break; case IB_WR_REG_MR: sqe->base_mr = (uintptr_t)reg_wr(wr)->mr; sqe->rkey = reg_wr(wr)->key; sqe->access = reg_wr(wr)->access & IWARP_ACCESS_MASK; sqe->opcode = SIW_OP_REG_MR; break; case IB_WR_LOCAL_INV: sqe->rkey = wr->ex.invalidate_rkey; sqe->opcode = SIW_OP_INVAL_STAG; break; default: siw_dbg_qp(qp, "ib wr type %d unsupported\n", wr->opcode); rv = -EINVAL; break; } siw_dbg_qp(qp, "opcode %d, flags 0x%x, wr_id 0x%pK\n", sqe->opcode, sqe->flags, (void *)(uintptr_t)sqe->id); if (unlikely(rv < 0)) break; /* make SQE only valid after completely written */ smp_wmb(); sqe->flags |= SIW_WQE_VALID; qp->sq_put++; wr = wr->next; } /* * Send directly if SQ processing is not in progress. * Eventual immediate errors (rv < 0) do not affect the involved * RI resources (Verbs, 8.3.1) and thus do not prevent from SQ * processing, if new work is already pending. But rv must be passed * to caller. */ if (wqe->wr_status != SIW_WR_IDLE) { spin_unlock_irqrestore(&qp->sq_lock, flags); goto skip_direct_sending; } rv = siw_activate_tx(qp); spin_unlock_irqrestore(&qp->sq_lock, flags); if (rv <= 0) goto skip_direct_sending; if (rdma_is_kernel_res(&qp->base_qp.res)) { rv = siw_sq_start(qp); } else { qp->tx_ctx.in_syscall = 1; if (siw_qp_sq_process(qp) != 0 && !(qp->tx_ctx.tx_suspend)) siw_qp_cm_drop(qp, 0); qp->tx_ctx.in_syscall = 0; } skip_direct_sending: up_read(&qp->state_lock); if (rv >= 0) return 0; /* * Immediate error */ siw_dbg_qp(qp, "error %d\n", rv); *bad_wr = wr; return rv; } /* * siw_post_receive() * * Post a list of R-WR's to a RQ. * * @base_qp: Base QP contained in siw QP * @wr: Null terminated list of user WR's * @bad_wr: Points to failing WR in case of synchronous failure. */ int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr, const struct ib_recv_wr **bad_wr) { struct siw_qp *qp = to_siw_qp(base_qp); unsigned long flags; int rv = 0; if (qp->srq || qp->attrs.rq_size == 0) { *bad_wr = wr; return -EINVAL; } if (!rdma_is_kernel_res(&qp->base_qp.res)) { siw_dbg_qp(qp, "no kernel post_recv for user mapped rq\n"); *bad_wr = wr; return -EINVAL; } /* * Try to acquire QP state lock. Must be non-blocking * to accommodate kernel clients needs. */ if (!down_read_trylock(&qp->state_lock)) { if (qp->attrs.state == SIW_QP_STATE_ERROR) { /* * ERROR state is final, so we can be sure * this state will not change as long as the QP * exists. * * This handles an ib_drain_rq() call with * a concurrent request to set the QP state * to ERROR. */ rv = siw_rq_flush_wr(qp, wr, bad_wr); } else { siw_dbg_qp(qp, "QP locked, state %d\n", qp->attrs.state); *bad_wr = wr; rv = -ENOTCONN; } return rv; } if (qp->attrs.state > SIW_QP_STATE_RTS) { if (qp->attrs.state == SIW_QP_STATE_ERROR) { /* * Immediately flush this WR to CQ, if QP * is in ERROR state. RQ is guaranteed to * be empty, so WR complets in-order. * * Typically triggered by ib_drain_rq(). */ rv = siw_rq_flush_wr(qp, wr, bad_wr); } else { siw_dbg_qp(qp, "QP out of state %d\n", qp->attrs.state); *bad_wr = wr; rv = -ENOTCONN; } up_read(&qp->state_lock); return rv; } /* * Serialize potentially multiple producers. * Not needed for single threaded consumer side. */ spin_lock_irqsave(&qp->rq_lock, flags); while (wr) { u32 idx = qp->rq_put % qp->attrs.rq_size; struct siw_rqe *rqe = &qp->recvq[idx]; if (rqe->flags) { siw_dbg_qp(qp, "RQ full\n"); rv = -ENOMEM; break; } if (wr->num_sge > qp->attrs.rq_max_sges) { siw_dbg_qp(qp, "too many sge's: %d\n", wr->num_sge); rv = -EINVAL; break; } rqe->id = wr->wr_id; rqe->num_sge = wr->num_sge; siw_copy_sgl(wr->sg_list, rqe->sge, wr->num_sge); /* make sure RQE is completely written before valid */ smp_wmb(); rqe->flags = SIW_WQE_VALID; qp->rq_put++; wr = wr->next; } spin_unlock_irqrestore(&qp->rq_lock, flags); up_read(&qp->state_lock); if (rv < 0) { siw_dbg_qp(qp, "error %d\n", rv); *bad_wr = wr; } return rv > 0 ? 0 : rv; } int siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata) { struct siw_cq *cq = to_siw_cq(base_cq); struct siw_device *sdev = to_siw_dev(base_cq->device); struct siw_ucontext *ctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); siw_dbg_cq(cq, "free CQ resources\n"); siw_cq_flush(cq); if (ctx) rdma_user_mmap_entry_remove(cq->cq_entry); atomic_dec(&sdev->num_cq); vfree(cq->queue); return 0; } /* * siw_create_cq() * * Populate CQ of requested size * * @base_cq: CQ as allocated by RDMA midlayer * @attr: Initial CQ attributes * @udata: relates to user context */ int siw_create_cq(struct ib_cq *base_cq, const struct ib_cq_init_attr *attr, struct ib_udata *udata) { struct siw_device *sdev = to_siw_dev(base_cq->device); struct siw_cq *cq = to_siw_cq(base_cq); int rv, size = attr->cqe; if (attr->flags) return -EOPNOTSUPP; if (atomic_inc_return(&sdev->num_cq) > SIW_MAX_CQ) { siw_dbg(base_cq->device, "too many CQ's\n"); rv = -ENOMEM; goto err_out; } if (size < 1 || size > sdev->attrs.max_cqe) { siw_dbg(base_cq->device, "CQ size error: %d\n", size); rv = -EINVAL; goto err_out; } size = roundup_pow_of_two(size); cq->base_cq.cqe = size; cq->num_cqe = size; if (udata) cq->queue = vmalloc_user(size * sizeof(struct siw_cqe) + sizeof(struct siw_cq_ctrl)); else cq->queue = vzalloc(size * sizeof(struct siw_cqe) + sizeof(struct siw_cq_ctrl)); if (cq->queue == NULL) { rv = -ENOMEM; goto err_out; } get_random_bytes(&cq->id, 4); siw_dbg(base_cq->device, "new CQ [%u]\n", cq->id); spin_lock_init(&cq->lock); cq->notify = (struct siw_cq_ctrl *)&cq->queue[size]; if (udata) { struct siw_uresp_create_cq uresp = {}; struct siw_ucontext *ctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); size_t length = size * sizeof(struct siw_cqe) + sizeof(struct siw_cq_ctrl); cq->cq_entry = siw_mmap_entry_insert(ctx, cq->queue, length, &uresp.cq_key); if (!cq->cq_entry) { rv = -ENOMEM; goto err_out; } uresp.cq_id = cq->id; uresp.num_cqe = size; if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; goto err_out; } rv = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (rv) goto err_out; } return 0; err_out: siw_dbg(base_cq->device, "CQ creation failed: %d", rv); if (cq->queue) { struct siw_ucontext *ctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); if (ctx) rdma_user_mmap_entry_remove(cq->cq_entry); vfree(cq->queue); } atomic_dec(&sdev->num_cq); return rv; } /* * siw_poll_cq() * * Reap CQ entries if available and copy work completion status into * array of WC's provided by caller. Returns number of reaped CQE's. * * @base_cq: Base CQ contained in siw CQ. * @num_cqe: Maximum number of CQE's to reap. * @wc: Array of work completions to be filled by siw. */ int siw_poll_cq(struct ib_cq *base_cq, int num_cqe, struct ib_wc *wc) { struct siw_cq *cq = to_siw_cq(base_cq); int i; for (i = 0; i < num_cqe; i++) { if (!siw_reap_cqe(cq, wc)) break; wc++; } return i; } /* * siw_req_notify_cq() * * Request notification for new CQE's added to that CQ. * Defined flags: * o SIW_CQ_NOTIFY_SOLICITED lets siw trigger a notification * event if a WQE with notification flag set enters the CQ * o SIW_CQ_NOTIFY_NEXT_COMP lets siw trigger a notification * event if a WQE enters the CQ. * o IB_CQ_REPORT_MISSED_EVENTS: return value will provide the * number of not reaped CQE's regardless of its notification * type and current or new CQ notification settings. * * @base_cq: Base CQ contained in siw CQ. * @flags: Requested notification flags. */ int siw_req_notify_cq(struct ib_cq *base_cq, enum ib_cq_notify_flags flags) { struct siw_cq *cq = to_siw_cq(base_cq); siw_dbg_cq(cq, "flags: 0x%02x\n", flags); if ((flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED) /* * Enable CQ event for next solicited completion. * and make it visible to all associated producers. */ smp_store_mb(cq->notify->flags, SIW_NOTIFY_SOLICITED); else /* * Enable CQ event for any signalled completion. * and make it visible to all associated producers. */ smp_store_mb(cq->notify->flags, SIW_NOTIFY_ALL); if (flags & IB_CQ_REPORT_MISSED_EVENTS) return cq->cq_put - cq->cq_get; return 0; } /* * siw_dereg_mr() * * Release Memory Region. * * @base_mr: Base MR contained in siw MR. * @udata: points to user context, unused. */ int siw_dereg_mr(struct ib_mr *base_mr, struct ib_udata *udata) { struct siw_mr *mr = to_siw_mr(base_mr); struct siw_device *sdev = to_siw_dev(base_mr->device); siw_dbg_mem(mr->mem, "deregister MR\n"); atomic_dec(&sdev->num_mr); siw_mr_drop_mem(mr); kfree_rcu(mr, rcu); return 0; } /* * siw_reg_user_mr() * * Register Memory Region. * * @pd: Protection Domain * @start: starting address of MR (virtual address) * @len: len of MR * @rnic_va: not used by siw * @rights: MR access rights * @udata: user buffer to communicate STag and Key. */ struct ib_mr *siw_reg_user_mr(struct ib_pd *pd, u64 start, u64 len, u64 rnic_va, int rights, struct ib_udata *udata) { struct siw_mr *mr = NULL; struct siw_umem *umem = NULL; struct siw_ureq_reg_mr ureq; struct siw_device *sdev = to_siw_dev(pd->device); int rv; siw_dbg_pd(pd, "start: 0x%pK, va: 0x%pK, len: %llu\n", (void *)(uintptr_t)start, (void *)(uintptr_t)rnic_va, (unsigned long long)len); if (atomic_inc_return(&sdev->num_mr) > SIW_MAX_MR) { siw_dbg_pd(pd, "too many mr's\n"); rv = -ENOMEM; goto err_out; } if (!len) { rv = -EINVAL; goto err_out; } umem = siw_umem_get(pd->device, start, len, rights); if (IS_ERR(umem)) { rv = PTR_ERR(umem); siw_dbg_pd(pd, "getting user memory failed: %d\n", rv); umem = NULL; goto err_out; } mr = kzalloc(sizeof(*mr), GFP_KERNEL); if (!mr) { rv = -ENOMEM; goto err_out; } rv = siw_mr_add_mem(mr, pd, umem, start, len, rights); if (rv) goto err_out; if (udata) { struct siw_uresp_reg_mr uresp = {}; struct siw_mem *mem = mr->mem; if (udata->inlen < sizeof(ureq)) { rv = -EINVAL; goto err_out; } rv = ib_copy_from_udata(&ureq, udata, sizeof(ureq)); if (rv) goto err_out; mr->base_mr.lkey |= ureq.stag_key; mr->base_mr.rkey |= ureq.stag_key; mem->stag |= ureq.stag_key; uresp.stag = mem->stag; if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; goto err_out; } rv = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (rv) goto err_out; } mr->mem->stag_valid = 1; return &mr->base_mr; err_out: atomic_dec(&sdev->num_mr); if (mr) { if (mr->mem) siw_mr_drop_mem(mr); kfree_rcu(mr, rcu); } else { if (umem) siw_umem_release(umem); } return ERR_PTR(rv); } struct ib_mr *siw_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_sge) { struct siw_device *sdev = to_siw_dev(pd->device); struct siw_mr *mr = NULL; struct siw_pbl *pbl = NULL; int rv; if (atomic_inc_return(&sdev->num_mr) > SIW_MAX_MR) { siw_dbg_pd(pd, "too many mr's\n"); rv = -ENOMEM; goto err_out; } if (mr_type != IB_MR_TYPE_MEM_REG) { siw_dbg_pd(pd, "mr type %d unsupported\n", mr_type); rv = -EOPNOTSUPP; goto err_out; } if (max_sge > SIW_MAX_SGE_PBL) { siw_dbg_pd(pd, "too many sge's: %d\n", max_sge); rv = -ENOMEM; goto err_out; } pbl = siw_pbl_alloc(max_sge); if (IS_ERR(pbl)) { rv = PTR_ERR(pbl); siw_dbg_pd(pd, "pbl allocation failed: %d\n", rv); pbl = NULL; goto err_out; } mr = kzalloc(sizeof(*mr), GFP_KERNEL); if (!mr) { rv = -ENOMEM; goto err_out; } rv = siw_mr_add_mem(mr, pd, pbl, 0, max_sge * PAGE_SIZE, 0); if (rv) goto err_out; mr->mem->is_pbl = 1; siw_dbg_pd(pd, "[MEM %u]: success\n", mr->mem->stag); return &mr->base_mr; err_out: atomic_dec(&sdev->num_mr); if (!mr) { kfree(pbl); } else { if (mr->mem) siw_mr_drop_mem(mr); kfree_rcu(mr, rcu); } siw_dbg_pd(pd, "failed: %d\n", rv); return ERR_PTR(rv); } /* Just used to count number of pages being mapped */ static int siw_set_pbl_page(struct ib_mr *base_mr, u64 buf_addr) { return 0; } int siw_map_mr_sg(struct ib_mr *base_mr, struct scatterlist *sl, int num_sle, unsigned int *sg_off) { struct scatterlist *slp; struct siw_mr *mr = to_siw_mr(base_mr); struct siw_mem *mem = mr->mem; struct siw_pbl *pbl = mem->pbl; struct siw_pble *pble; unsigned long pbl_size; int i, rv; if (!pbl) { siw_dbg_mem(mem, "no PBL allocated\n"); return -EINVAL; } pble = pbl->pbe; if (pbl->max_buf < num_sle) { siw_dbg_mem(mem, "too many SGE's: %d > %d\n", num_sle, pbl->max_buf); return -ENOMEM; } for_each_sg(sl, slp, num_sle, i) { if (sg_dma_len(slp) == 0) { siw_dbg_mem(mem, "empty SGE\n"); return -EINVAL; } if (i == 0) { pble->addr = sg_dma_address(slp); pble->size = sg_dma_len(slp); pble->pbl_off = 0; pbl_size = pble->size; pbl->num_buf = 1; } else { /* Merge PBL entries if adjacent */ if (pble->addr + pble->size == sg_dma_address(slp)) { pble->size += sg_dma_len(slp); } else { pble++; pbl->num_buf++; pble->addr = sg_dma_address(slp); pble->size = sg_dma_len(slp); pble->pbl_off = pbl_size; } pbl_size += sg_dma_len(slp); } siw_dbg_mem(mem, "sge[%d], size %u, addr 0x%p, total %lu\n", i, pble->size, ib_virt_dma_to_ptr(pble->addr), pbl_size); } rv = ib_sg_to_pages(base_mr, sl, num_sle, sg_off, siw_set_pbl_page); if (rv > 0) { mem->len = base_mr->length; mem->va = base_mr->iova; siw_dbg_mem(mem, "%llu bytes, start 0x%pK, %u SLE to %u entries\n", mem->len, (void *)(uintptr_t)mem->va, num_sle, pbl->num_buf); } return rv; } /* * siw_get_dma_mr() * * Create a (empty) DMA memory region, where no umem is attached. */ struct ib_mr *siw_get_dma_mr(struct ib_pd *pd, int rights) { struct siw_device *sdev = to_siw_dev(pd->device); struct siw_mr *mr = NULL; int rv; if (atomic_inc_return(&sdev->num_mr) > SIW_MAX_MR) { siw_dbg_pd(pd, "too many mr's\n"); rv = -ENOMEM; goto err_out; } mr = kzalloc(sizeof(*mr), GFP_KERNEL); if (!mr) { rv = -ENOMEM; goto err_out; } rv = siw_mr_add_mem(mr, pd, NULL, 0, ULONG_MAX, rights); if (rv) goto err_out; mr->mem->stag_valid = 1; siw_dbg_pd(pd, "[MEM %u]: success\n", mr->mem->stag); return &mr->base_mr; err_out: if (rv) kfree(mr); atomic_dec(&sdev->num_mr); return ERR_PTR(rv); } /* * siw_create_srq() * * Create Shared Receive Queue of attributes @init_attrs * within protection domain given by @pd. * * @base_srq: Base SRQ contained in siw SRQ. * @init_attrs: SRQ init attributes. * @udata: points to user context */ int siw_create_srq(struct ib_srq *base_srq, struct ib_srq_init_attr *init_attrs, struct ib_udata *udata) { struct siw_srq *srq = to_siw_srq(base_srq); struct ib_srq_attr *attrs = &init_attrs->attr; struct siw_device *sdev = to_siw_dev(base_srq->device); struct siw_ucontext *ctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); int rv; if (init_attrs->srq_type != IB_SRQT_BASIC) return -EOPNOTSUPP; if (atomic_inc_return(&sdev->num_srq) > SIW_MAX_SRQ) { siw_dbg_pd(base_srq->pd, "too many SRQ's\n"); rv = -ENOMEM; goto err_out; } if (attrs->max_wr == 0 || attrs->max_wr > SIW_MAX_SRQ_WR || attrs->max_sge > SIW_MAX_SGE || attrs->srq_limit > attrs->max_wr) { rv = -EINVAL; goto err_out; } srq->max_sge = attrs->max_sge; srq->num_rqe = roundup_pow_of_two(attrs->max_wr); srq->limit = attrs->srq_limit; if (srq->limit) srq->armed = true; srq->is_kernel_res = !udata; if (udata) srq->recvq = vmalloc_user(srq->num_rqe * sizeof(struct siw_rqe)); else srq->recvq = vcalloc(srq->num_rqe, sizeof(struct siw_rqe)); if (srq->recvq == NULL) { rv = -ENOMEM; goto err_out; } if (udata) { struct siw_uresp_create_srq uresp = {}; size_t length = srq->num_rqe * sizeof(struct siw_rqe); srq->srq_entry = siw_mmap_entry_insert(ctx, srq->recvq, length, &uresp.srq_key); if (!srq->srq_entry) { rv = -ENOMEM; goto err_out; } uresp.num_rqe = srq->num_rqe; if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; goto err_out; } rv = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (rv) goto err_out; } spin_lock_init(&srq->lock); siw_dbg_pd(base_srq->pd, "[SRQ]: success\n"); return 0; err_out: if (srq->recvq) { if (ctx) rdma_user_mmap_entry_remove(srq->srq_entry); vfree(srq->recvq); } atomic_dec(&sdev->num_srq); return rv; } /* * siw_modify_srq() * * Modify SRQ. The caller may resize SRQ and/or set/reset notification * limit and (re)arm IB_EVENT_SRQ_LIMIT_REACHED notification. * * NOTE: it is unclear if RDMA core allows for changing the MAX_SGE * parameter. siw_modify_srq() does not check the attrs->max_sge param. */ int siw_modify_srq(struct ib_srq *base_srq, struct ib_srq_attr *attrs, enum ib_srq_attr_mask attr_mask, struct ib_udata *udata) { struct siw_srq *srq = to_siw_srq(base_srq); unsigned long flags; int rv = 0; spin_lock_irqsave(&srq->lock, flags); if (attr_mask & IB_SRQ_MAX_WR) { /* resize request not yet supported */ rv = -EOPNOTSUPP; goto out; } if (attr_mask & IB_SRQ_LIMIT) { if (attrs->srq_limit) { if (unlikely(attrs->srq_limit > srq->num_rqe)) { rv = -EINVAL; goto out; } srq->armed = true; } else { srq->armed = false; } srq->limit = attrs->srq_limit; } out: spin_unlock_irqrestore(&srq->lock, flags); return rv; } /* * siw_query_srq() * * Query SRQ attributes. */ int siw_query_srq(struct ib_srq *base_srq, struct ib_srq_attr *attrs) { struct siw_srq *srq = to_siw_srq(base_srq); unsigned long flags; spin_lock_irqsave(&srq->lock, flags); attrs->max_wr = srq->num_rqe; attrs->max_sge = srq->max_sge; attrs->srq_limit = srq->limit; spin_unlock_irqrestore(&srq->lock, flags); return 0; } /* * siw_destroy_srq() * * Destroy SRQ. * It is assumed that the SRQ is not referenced by any * QP anymore - the code trusts the RDMA core environment to keep track * of QP references. */ int siw_destroy_srq(struct ib_srq *base_srq, struct ib_udata *udata) { struct siw_srq *srq = to_siw_srq(base_srq); struct siw_device *sdev = to_siw_dev(base_srq->device); struct siw_ucontext *ctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); if (ctx) rdma_user_mmap_entry_remove(srq->srq_entry); vfree(srq->recvq); atomic_dec(&sdev->num_srq); return 0; } /* * siw_post_srq_recv() * * Post a list of receive queue elements to SRQ. * NOTE: The function does not check or lock a certain SRQ state * during the post operation. The code simply trusts the * RDMA core environment. * * @base_srq: Base SRQ contained in siw SRQ * @wr: List of R-WR's * @bad_wr: Updated to failing WR if posting fails. */ int siw_post_srq_recv(struct ib_srq *base_srq, const struct ib_recv_wr *wr, const struct ib_recv_wr **bad_wr) { struct siw_srq *srq = to_siw_srq(base_srq); unsigned long flags; int rv = 0; if (unlikely(!srq->is_kernel_res)) { siw_dbg_pd(base_srq->pd, "[SRQ]: no kernel post_recv for mapped srq\n"); rv = -EINVAL; goto out; } /* * Serialize potentially multiple producers. * Also needed to serialize potentially multiple * consumers. */ spin_lock_irqsave(&srq->lock, flags); while (wr) { u32 idx = srq->rq_put % srq->num_rqe; struct siw_rqe *rqe = &srq->recvq[idx]; if (rqe->flags) { siw_dbg_pd(base_srq->pd, "SRQ full\n"); rv = -ENOMEM; break; } if (unlikely(wr->num_sge > srq->max_sge)) { siw_dbg_pd(base_srq->pd, "[SRQ]: too many sge's: %d\n", wr->num_sge); rv = -EINVAL; break; } rqe->id = wr->wr_id; rqe->num_sge = wr->num_sge; siw_copy_sgl(wr->sg_list, rqe->sge, wr->num_sge); /* Make sure S-RQE is completely written before valid */ smp_wmb(); rqe->flags = SIW_WQE_VALID; srq->rq_put++; wr = wr->next; } spin_unlock_irqrestore(&srq->lock, flags); out: if (unlikely(rv < 0)) { siw_dbg_pd(base_srq->pd, "[SRQ]: error %d\n", rv); *bad_wr = wr; } return rv; } void siw_qp_event(struct siw_qp *qp, enum ib_event_type etype) { struct ib_event event; struct ib_qp *base_qp = &qp->base_qp; /* * Do not report asynchronous errors on QP which gets * destroyed via verbs interface (siw_destroy_qp()) */ if (qp->attrs.flags & SIW_QP_IN_DESTROY) return; event.event = etype; event.device = base_qp->device; event.element.qp = base_qp; if (base_qp->event_handler) { siw_dbg_qp(qp, "reporting event %d\n", etype); base_qp->event_handler(&event, base_qp->qp_context); } } void siw_cq_event(struct siw_cq *cq, enum ib_event_type etype) { struct ib_event event; struct ib_cq *base_cq = &cq->base_cq; event.event = etype; event.device = base_cq->device; event.element.cq = base_cq; if (base_cq->event_handler) { siw_dbg_cq(cq, "reporting CQ event %d\n", etype); base_cq->event_handler(&event, base_cq->cq_context); } } void siw_srq_event(struct siw_srq *srq, enum ib_event_type etype) { struct ib_event event; struct ib_srq *base_srq = &srq->base_srq; event.event = etype; event.device = base_srq->device; event.element.srq = base_srq; if (base_srq->event_handler) { siw_dbg_pd(srq->base_srq.pd, "reporting SRQ event %d\n", etype); base_srq->event_handler(&event, base_srq->srq_context); } } void siw_port_event(struct siw_device *sdev, u32 port, enum ib_event_type etype) { struct ib_event event; event.event = etype; event.device = &sdev->base_dev; event.element.port_num = port; siw_dbg(&sdev->base_dev, "reporting port event %d\n", etype); ib_dispatch_event(&event); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 | // SPDX-License-Identifier: GPL-2.0-only #ifndef _NFT_SET_PIPAPO_H #include <linux/log2.h> #include <net/ipv6.h> /* For the maximum length of a field */ /* Count of concatenated fields depends on count of 32-bit nftables registers */ #define NFT_PIPAPO_MAX_FIELDS NFT_REG32_COUNT /* Restrict usage to multiple fields, make sure rbtree is used otherwise */ #define NFT_PIPAPO_MIN_FIELDS 2 /* Largest supported field size */ #define NFT_PIPAPO_MAX_BYTES (sizeof(struct in6_addr)) #define NFT_PIPAPO_MAX_BITS (NFT_PIPAPO_MAX_BYTES * BITS_PER_BYTE) /* Bits to be grouped together in table buckets depending on set size */ #define NFT_PIPAPO_GROUP_BITS_INIT NFT_PIPAPO_GROUP_BITS_SMALL_SET #define NFT_PIPAPO_GROUP_BITS_SMALL_SET 8 #define NFT_PIPAPO_GROUP_BITS_LARGE_SET 4 #define NFT_PIPAPO_GROUP_BITS_ARE_8_OR_4 \ BUILD_BUG_ON((NFT_PIPAPO_GROUP_BITS_SMALL_SET != 8) || \ (NFT_PIPAPO_GROUP_BITS_LARGE_SET != 4)) #define NFT_PIPAPO_GROUPS_PER_BYTE(f) (BITS_PER_BYTE / (f)->bb) /* If a lookup table gets bigger than NFT_PIPAPO_LT_SIZE_HIGH, switch to the * small group width, and switch to the big group width if the table gets * smaller than NFT_PIPAPO_LT_SIZE_LOW. * * Picking 2MiB as threshold (for a single table) avoids as much as possible * crossing page boundaries on most architectures (x86-64 and MIPS huge pages, * ARMv7 supersections, POWER "large" pages, SPARC Level 1 regions, etc.), which * keeps performance nice in case kvmalloc() gives us non-contiguous areas. */ #define NFT_PIPAPO_LT_SIZE_THRESHOLD (1 << 21) #define NFT_PIPAPO_LT_SIZE_HYSTERESIS (1 << 16) #define NFT_PIPAPO_LT_SIZE_HIGH NFT_PIPAPO_LT_SIZE_THRESHOLD #define NFT_PIPAPO_LT_SIZE_LOW NFT_PIPAPO_LT_SIZE_THRESHOLD - \ NFT_PIPAPO_LT_SIZE_HYSTERESIS /* Fields are padded to 32 bits in input registers */ #define NFT_PIPAPO_GROUPS_PADDED_SIZE(f) \ (round_up((f)->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f), sizeof(u32))) #define NFT_PIPAPO_GROUPS_PADDING(f) \ (NFT_PIPAPO_GROUPS_PADDED_SIZE(f) - (f)->groups / \ NFT_PIPAPO_GROUPS_PER_BYTE(f)) /* Number of buckets given by 2 ^ n, with n bucket bits */ #define NFT_PIPAPO_BUCKETS(bb) (1 << (bb)) /* Each n-bit range maps to up to n * 2 rules */ #define NFT_PIPAPO_MAP_NBITS (const_ilog2(NFT_PIPAPO_MAX_BITS * 2)) /* Use the rest of mapping table buckets for rule indices, but it makes no sense * to exceed 32 bits */ #if BITS_PER_LONG == 64 #define NFT_PIPAPO_MAP_TOBITS 32 #else #define NFT_PIPAPO_MAP_TOBITS (BITS_PER_LONG - NFT_PIPAPO_MAP_NBITS) #endif /* ...which gives us the highest allowed index for a rule */ #define NFT_PIPAPO_RULE0_MAX ((1UL << (NFT_PIPAPO_MAP_TOBITS - 1)) \ - (1UL << NFT_PIPAPO_MAP_NBITS)) /* Definitions for vectorised implementations */ #ifdef NFT_PIPAPO_ALIGN #define NFT_PIPAPO_ALIGN_HEADROOM \ (NFT_PIPAPO_ALIGN - ARCH_KMALLOC_MINALIGN) #define NFT_PIPAPO_LT_ALIGN(lt) (PTR_ALIGN((lt), NFT_PIPAPO_ALIGN)) #else #define NFT_PIPAPO_ALIGN_HEADROOM 0 #define NFT_PIPAPO_LT_ALIGN(lt) (lt) #endif /* NFT_PIPAPO_ALIGN */ #define nft_pipapo_for_each_field(field, index, match) \ for ((field) = (match)->f, (index) = 0; \ (index) < (match)->field_count; \ (index)++, (field)++) /** * union nft_pipapo_map_bucket - Bucket of mapping table * @to: First rule number (in next field) this rule maps to * @n: Number of rules (in next field) this rule maps to * @e: If there's no next field, pointer to element this rule maps to */ union nft_pipapo_map_bucket { struct { #if BITS_PER_LONG == 64 static_assert(NFT_PIPAPO_MAP_TOBITS <= 32); u32 to; static_assert(NFT_PIPAPO_MAP_NBITS <= 32); u32 n; #else unsigned long to:NFT_PIPAPO_MAP_TOBITS; unsigned long n:NFT_PIPAPO_MAP_NBITS; #endif }; struct nft_pipapo_elem *e; }; /** * struct nft_pipapo_field - Lookup, mapping tables and related data for a field * @rules: Number of inserted rules * @bsize: Size of each bucket in lookup table, in longs * @rules_alloc: Number of allocated rules, always >= rules * @groups: Amount of bit groups * @bb: Number of bits grouped together in lookup table buckets * @lt: Lookup table: 'groups' rows of buckets * @mt: Mapping table: one bucket per rule */ struct nft_pipapo_field { unsigned int rules; unsigned int bsize; unsigned int rules_alloc; u8 groups; u8 bb; unsigned long *lt; union nft_pipapo_map_bucket *mt; }; /** * struct nft_pipapo_scratch - percpu data used for lookup and matching * @map_index: Current working bitmap index, toggled between field matches * @align_off: Offset to get the originally allocated address * @map: store partial matching results during lookup */ struct nft_pipapo_scratch { u8 map_index; u32 align_off; unsigned long map[]; }; /** * struct nft_pipapo_match - Data used for lookup and matching * @field_count: Amount of fields in set * @bsize_max: Maximum lookup table bucket size of all fields, in longs * @scratch: Preallocated per-CPU maps for partial matching results * @rcu: Matching data is swapped on commits * @f: Fields, with lookup and mapping tables */ struct nft_pipapo_match { u8 field_count; unsigned int bsize_max; struct nft_pipapo_scratch * __percpu *scratch; struct rcu_head rcu; struct nft_pipapo_field f[] __counted_by(field_count); }; /** * struct nft_pipapo - Representation of a set * @match: Currently in-use matching data * @clone: Copy where pending insertions and deletions are kept * @width: Total bytes to be matched for one packet, including padding * @last_gc: Timestamp of last garbage collection run, jiffies */ struct nft_pipapo { struct nft_pipapo_match __rcu *match; struct nft_pipapo_match *clone; int width; unsigned long last_gc; }; struct nft_pipapo_elem; /** * struct nft_pipapo_elem - API-facing representation of single set element * @priv: element placeholder * @ext: nftables API extensions */ struct nft_pipapo_elem { struct nft_elem_priv priv; struct nft_set_ext ext; }; int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules, unsigned long *dst, const union nft_pipapo_map_bucket *mt, bool match_only); /** * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets * @f: Field including lookup table * @dst: Area to store result * @data: Input data selecting table buckets */ static inline void pipapo_and_field_buckets_4bit(const struct nft_pipapo_field *f, unsigned long *dst, const u8 *data) { unsigned long *lt = NFT_PIPAPO_LT_ALIGN(f->lt); int group; for (group = 0; group < f->groups; group += BITS_PER_BYTE / 4, data++) { u8 v; v = *data >> 4; __bitmap_and(dst, dst, lt + v * f->bsize, f->bsize * BITS_PER_LONG); lt += f->bsize * NFT_PIPAPO_BUCKETS(4); v = *data & 0x0f; __bitmap_and(dst, dst, lt + v * f->bsize, f->bsize * BITS_PER_LONG); lt += f->bsize * NFT_PIPAPO_BUCKETS(4); } } /** * pipapo_and_field_buckets_8bit() - Intersect 8-bit buckets * @f: Field including lookup table * @dst: Area to store result * @data: Input data selecting table buckets */ static inline void pipapo_and_field_buckets_8bit(const struct nft_pipapo_field *f, unsigned long *dst, const u8 *data) { unsigned long *lt = NFT_PIPAPO_LT_ALIGN(f->lt); int group; for (group = 0; group < f->groups; group++, data++) { __bitmap_and(dst, dst, lt + *data * f->bsize, f->bsize * BITS_PER_LONG); lt += f->bsize * NFT_PIPAPO_BUCKETS(8); } } /** * pipapo_estimate_size() - Estimate worst-case for set size * @desc: Set description, element count and field description used here * * The size for this set type can vary dramatically, as it depends on the number * of rules (composing netmasks) the entries expand to. We compute the worst * case here. * * In general, for a non-ranged entry or a single composing netmask, we need * one bit in each of the sixteen NFT_PIPAPO_BUCKETS, for each 4-bit group (that * is, each input bit needs four bits of matching data), plus a bucket in the * mapping table for each field. * * Return: worst-case set size in bytes, 0 on any overflow */ static u64 pipapo_estimate_size(const struct nft_set_desc *desc) { unsigned long entry_size; u64 size; int i; for (i = 0, entry_size = 0; i < desc->field_count; i++) { unsigned long rules; if (desc->field_len[i] > NFT_PIPAPO_MAX_BYTES) return 0; /* Worst-case ranges for each concatenated field: each n-bit * field can expand to up to n * 2 rules in each bucket, and * each rule also needs a mapping bucket. */ rules = ilog2(desc->field_len[i] * BITS_PER_BYTE) * 2; entry_size += rules * NFT_PIPAPO_BUCKETS(NFT_PIPAPO_GROUP_BITS_INIT) / BITS_PER_BYTE; entry_size += rules * sizeof(union nft_pipapo_map_bucket); } /* Rules in lookup and mapping tables are needed for each entry */ size = desc->size * entry_size; if (size && div_u64(size, desc->size) != entry_size) return 0; size += sizeof(struct nft_pipapo) + sizeof(struct nft_pipapo_match) * 2; size += sizeof(struct nft_pipapo_field) * desc->field_count; return size; } #endif /* _NFT_SET_PIPAPO_H */ |
| 48 161 209 207 202 209 208 202 203 203 202 2 203 11 201 206 16 203 204 201 1 1 1 1 208 209 209 209 211 211 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS An implementation of the IP virtual server support for the * LINUX operating system. IPVS is now implemented as a module * over the Netfilter framework. IPVS can be used to build a * high-performance and highly available server based on a * cluster of servers. * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Peter Kese <peter.kese@ijs.si> * Julian Anastasov <ja@ssi.bg> * * The IPVS code for kernel 2.2 was done by Wensong Zhang and Peter Kese, * with changes/fixes from Julian Anastasov, Lars Marowsky-Bree, Horms * and others. Many code here is taken from IP MASQ code of kernel 2.2. * * Changes: */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/interrupt.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/net.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/proc_fs.h> /* for proc_net_* */ #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/jhash.h> #include <linux/random.h> #include <linux/rcupdate_wait.h> #include <net/net_namespace.h> #include <net/ip_vs.h> #ifndef CONFIG_IP_VS_TAB_BITS #define CONFIG_IP_VS_TAB_BITS 12 #endif /* * Connection hash size. Default is what was selected at compile time. */ static int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444); MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size"); /* size and mask values */ int ip_vs_conn_tab_size __read_mostly; static int ip_vs_conn_tab_mask __read_mostly; /* * Connection hash table: for input and output packets lookups of IPVS */ static struct hlist_head *ip_vs_conn_tab __read_mostly; /* SLAB cache for IPVS connections */ static struct kmem_cache *ip_vs_conn_cachep __read_mostly; /* counter for no client port connections */ static atomic_t ip_vs_conn_no_cport_cnt = ATOMIC_INIT(0); /* random value for IPVS connection hash */ static unsigned int ip_vs_conn_rnd __read_mostly; /* * Fine locking granularity for big connection hash table */ #define CT_LOCKARRAY_BITS 5 #define CT_LOCKARRAY_SIZE (1<<CT_LOCKARRAY_BITS) #define CT_LOCKARRAY_MASK (CT_LOCKARRAY_SIZE-1) /* We need an addrstrlen that works with or without v6 */ #ifdef CONFIG_IP_VS_IPV6 #define IP_VS_ADDRSTRLEN INET6_ADDRSTRLEN #else #define IP_VS_ADDRSTRLEN (8+1) #endif struct ip_vs_aligned_lock { spinlock_t l; } __attribute__((__aligned__(SMP_CACHE_BYTES))); /* lock array for conn table */ static struct ip_vs_aligned_lock __ip_vs_conntbl_lock_array[CT_LOCKARRAY_SIZE] __cacheline_aligned; static inline void ct_write_lock_bh(unsigned int key) { spin_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } static inline void ct_write_unlock_bh(unsigned int key) { spin_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } static void ip_vs_conn_expire(struct timer_list *t); /* * Returns hash value for IPVS connection entry */ static unsigned int ip_vs_conn_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto, const union nf_inet_addr *addr, __be16 port) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) return (jhash_3words(jhash(addr, 16, ip_vs_conn_rnd), (__force u32)port, proto, ip_vs_conn_rnd) ^ ((size_t)ipvs>>8)) & ip_vs_conn_tab_mask; #endif return (jhash_3words((__force u32)addr->ip, (__force u32)port, proto, ip_vs_conn_rnd) ^ ((size_t)ipvs>>8)) & ip_vs_conn_tab_mask; } static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p, bool inverse) { const union nf_inet_addr *addr; __be16 port; if (p->pe_data && p->pe->hashkey_raw) return p->pe->hashkey_raw(p, ip_vs_conn_rnd, inverse) & ip_vs_conn_tab_mask; if (likely(!inverse)) { addr = p->caddr; port = p->cport; } else { addr = p->vaddr; port = p->vport; } return ip_vs_conn_hashkey(p->ipvs, p->af, p->protocol, addr, port); } static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) { struct ip_vs_conn_param p; ip_vs_conn_fill_param(cp->ipvs, cp->af, cp->protocol, &cp->caddr, cp->cport, NULL, 0, &p); if (cp->pe) { p.pe = cp->pe; p.pe_data = cp->pe_data; p.pe_data_len = cp->pe_data_len; } return ip_vs_conn_hashkey_param(&p, false); } /* * Hashes ip_vs_conn in ip_vs_conn_tab by netns,proto,addr,port. * returns bool success. */ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) { unsigned int hash; int ret; if (cp->flags & IP_VS_CONN_F_ONE_PACKET) return 0; /* Hash by protocol, client address and port */ hash = ip_vs_conn_hashkey_conn(cp); ct_write_lock_bh(hash); spin_lock(&cp->lock); if (!(cp->flags & IP_VS_CONN_F_HASHED)) { cp->flags |= IP_VS_CONN_F_HASHED; refcount_inc(&cp->refcnt); hlist_add_head_rcu(&cp->c_list, &ip_vs_conn_tab[hash]); ret = 1; } else { pr_err("%s(): request for already hashed, called from %pS\n", __func__, __builtin_return_address(0)); ret = 0; } spin_unlock(&cp->lock); ct_write_unlock_bh(hash); return ret; } /* * UNhashes ip_vs_conn from ip_vs_conn_tab. * returns bool success. Caller should hold conn reference. */ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) { unsigned int hash; int ret; /* unhash it and decrease its reference counter */ hash = ip_vs_conn_hashkey_conn(cp); ct_write_lock_bh(hash); spin_lock(&cp->lock); if (cp->flags & IP_VS_CONN_F_HASHED) { hlist_del_rcu(&cp->c_list); cp->flags &= ~IP_VS_CONN_F_HASHED; refcount_dec(&cp->refcnt); ret = 1; } else ret = 0; spin_unlock(&cp->lock); ct_write_unlock_bh(hash); return ret; } /* Try to unlink ip_vs_conn from ip_vs_conn_tab. * returns bool success. */ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) { unsigned int hash; bool ret = false; if (cp->flags & IP_VS_CONN_F_ONE_PACKET) return refcount_dec_if_one(&cp->refcnt); hash = ip_vs_conn_hashkey_conn(cp); ct_write_lock_bh(hash); spin_lock(&cp->lock); if (cp->flags & IP_VS_CONN_F_HASHED) { /* Decrease refcnt and unlink conn only if we are last user */ if (refcount_dec_if_one(&cp->refcnt)) { hlist_del_rcu(&cp->c_list); cp->flags &= ~IP_VS_CONN_F_HASHED; ret = true; } } spin_unlock(&cp->lock); ct_write_unlock_bh(hash); return ret; } /* * Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab. * Called for pkts coming from OUTside-to-INside. * p->caddr, p->cport: pkt source address (foreign host) * p->vaddr, p->vport: pkt dest address (load balancer) */ static inline struct ip_vs_conn * __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) { unsigned int hash; struct ip_vs_conn *cp; hash = ip_vs_conn_hashkey_param(p, false); rcu_read_lock(); hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (p->cport == cp->cport && p->vport == cp->vport && cp->af == p->af && ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) && ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) && p->protocol == cp->protocol && cp->ipvs == p->ipvs) { if (!__ip_vs_conn_get(cp)) continue; /* HIT */ rcu_read_unlock(); return cp; } } rcu_read_unlock(); return NULL; } struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p) { struct ip_vs_conn *cp; cp = __ip_vs_conn_in_get(p); if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt)) { struct ip_vs_conn_param cport_zero_p = *p; cport_zero_p.cport = 0; cp = __ip_vs_conn_in_get(&cport_zero_p); } IP_VS_DBG_BUF(9, "lookup/in %s %s:%d->%s:%d %s\n", ip_vs_proto_name(p->protocol), IP_VS_DBG_ADDR(p->af, p->caddr), ntohs(p->cport), IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport), cp ? "hit" : "not hit"); return cp; } static int ip_vs_conn_fill_param_proto(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph, struct ip_vs_conn_param *p) { __be16 _ports[2], *pptr; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (pptr == NULL) return 1; if (likely(!ip_vs_iph_inverse(iph))) ip_vs_conn_fill_param(ipvs, af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], p); else ip_vs_conn_fill_param(ipvs, af, iph->protocol, &iph->daddr, pptr[1], &iph->saddr, pptr[0], p); return 0; } struct ip_vs_conn * ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_conn_param p; if (ip_vs_conn_fill_param_proto(ipvs, af, skb, iph, &p)) return NULL; return ip_vs_conn_in_get(&p); } EXPORT_SYMBOL_GPL(ip_vs_conn_in_get_proto); /* Get reference to connection template */ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) { unsigned int hash; struct ip_vs_conn *cp; hash = ip_vs_conn_hashkey_param(p, false); rcu_read_lock(); hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (unlikely(p->pe_data && p->pe->ct_match)) { if (cp->ipvs != p->ipvs) continue; if (p->pe == cp->pe && p->pe->ct_match(p, cp)) { if (__ip_vs_conn_get(cp)) goto out; } continue; } if (cp->af == p->af && ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) && /* protocol should only be IPPROTO_IP if * p->vaddr is a fwmark */ ip_vs_addr_equal(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, p->vaddr, &cp->vaddr) && p->vport == cp->vport && p->cport == cp->cport && cp->flags & IP_VS_CONN_F_TEMPLATE && p->protocol == cp->protocol && cp->ipvs == p->ipvs) { if (__ip_vs_conn_get(cp)) goto out; } } cp = NULL; out: rcu_read_unlock(); IP_VS_DBG_BUF(9, "template lookup/in %s %s:%d->%s:%d %s\n", ip_vs_proto_name(p->protocol), IP_VS_DBG_ADDR(p->af, p->caddr), ntohs(p->cport), IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport), cp ? "hit" : "not hit"); return cp; } /* Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab. * Called for pkts coming from inside-to-OUTside. * p->caddr, p->cport: pkt source address (inside host) * p->vaddr, p->vport: pkt dest address (foreign host) */ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) { unsigned int hash; struct ip_vs_conn *cp, *ret=NULL; const union nf_inet_addr *saddr; __be16 sport; /* * Check for "full" addressed entries */ hash = ip_vs_conn_hashkey_param(p, true); rcu_read_lock(); hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (p->vport != cp->cport) continue; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { sport = cp->vport; saddr = &cp->vaddr; } else { sport = cp->dport; saddr = &cp->daddr; } if (p->cport == sport && cp->af == p->af && ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->caddr, saddr) && p->protocol == cp->protocol && cp->ipvs == p->ipvs) { if (!__ip_vs_conn_get(cp)) continue; /* HIT */ ret = cp; break; } } rcu_read_unlock(); IP_VS_DBG_BUF(9, "lookup/out %s %s:%d->%s:%d %s\n", ip_vs_proto_name(p->protocol), IP_VS_DBG_ADDR(p->af, p->caddr), ntohs(p->cport), IP_VS_DBG_ADDR(p->af, p->vaddr), ntohs(p->vport), ret ? "hit" : "not hit"); return ret; } struct ip_vs_conn * ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_conn_param p; if (ip_vs_conn_fill_param_proto(ipvs, af, skb, iph, &p)) return NULL; return ip_vs_conn_out_get(&p); } EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto); /* * Put back the conn and restart its timer with its timeout */ static void __ip_vs_conn_put_timer(struct ip_vs_conn *cp) { unsigned long t = (cp->flags & IP_VS_CONN_F_ONE_PACKET) ? 0 : cp->timeout; mod_timer(&cp->timer, jiffies+t); __ip_vs_conn_put(cp); } void ip_vs_conn_put(struct ip_vs_conn *cp) { if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && (refcount_read(&cp->refcnt) == 1) && !timer_pending(&cp->timer)) /* expire connection immediately */ ip_vs_conn_expire(&cp->timer); else __ip_vs_conn_put_timer(cp); } /* * Fill a no_client_port connection with a client port number */ void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport) { if (ip_vs_conn_unhash(cp)) { spin_lock_bh(&cp->lock); if (cp->flags & IP_VS_CONN_F_NO_CPORT) { atomic_dec(&ip_vs_conn_no_cport_cnt); cp->flags &= ~IP_VS_CONN_F_NO_CPORT; cp->cport = cport; } spin_unlock_bh(&cp->lock); /* hash on new dport */ ip_vs_conn_hash(cp); } } /* * Bind a connection entry with the corresponding packet_xmit. * Called by ip_vs_conn_new. */ static inline void ip_vs_bind_xmit(struct ip_vs_conn *cp) { switch (IP_VS_FWD_METHOD(cp)) { case IP_VS_CONN_F_MASQ: cp->packet_xmit = ip_vs_nat_xmit; break; case IP_VS_CONN_F_TUNNEL: #ifdef CONFIG_IP_VS_IPV6 if (cp->daf == AF_INET6) cp->packet_xmit = ip_vs_tunnel_xmit_v6; else #endif cp->packet_xmit = ip_vs_tunnel_xmit; break; case IP_VS_CONN_F_DROUTE: cp->packet_xmit = ip_vs_dr_xmit; break; case IP_VS_CONN_F_LOCALNODE: cp->packet_xmit = ip_vs_null_xmit; break; case IP_VS_CONN_F_BYPASS: cp->packet_xmit = ip_vs_bypass_xmit; break; } } #ifdef CONFIG_IP_VS_IPV6 static inline void ip_vs_bind_xmit_v6(struct ip_vs_conn *cp) { switch (IP_VS_FWD_METHOD(cp)) { case IP_VS_CONN_F_MASQ: cp->packet_xmit = ip_vs_nat_xmit_v6; break; case IP_VS_CONN_F_TUNNEL: if (cp->daf == AF_INET6) cp->packet_xmit = ip_vs_tunnel_xmit_v6; else cp->packet_xmit = ip_vs_tunnel_xmit; break; case IP_VS_CONN_F_DROUTE: cp->packet_xmit = ip_vs_dr_xmit_v6; break; case IP_VS_CONN_F_LOCALNODE: cp->packet_xmit = ip_vs_null_xmit; break; case IP_VS_CONN_F_BYPASS: cp->packet_xmit = ip_vs_bypass_xmit_v6; break; } } #endif static inline int ip_vs_dest_totalconns(struct ip_vs_dest *dest) { return atomic_read(&dest->activeconns) + atomic_read(&dest->inactconns); } /* * Bind a connection entry with a virtual service destination * Called just after a new connection entry is created. */ static inline void ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) { unsigned int conn_flags; __u32 flags; /* if dest is NULL, then return directly */ if (!dest) return; /* Increase the refcnt counter of the dest */ ip_vs_dest_hold(dest); conn_flags = atomic_read(&dest->conn_flags); if (cp->protocol != IPPROTO_UDP) conn_flags &= ~IP_VS_CONN_F_ONE_PACKET; flags = cp->flags; /* Bind with the destination and its corresponding transmitter */ if (flags & IP_VS_CONN_F_SYNC) { /* if the connection is not template and is created * by sync, preserve the activity flag. */ if (!(flags & IP_VS_CONN_F_TEMPLATE)) conn_flags &= ~IP_VS_CONN_F_INACTIVE; /* connections inherit forwarding method from dest */ flags &= ~(IP_VS_CONN_F_FWD_MASK | IP_VS_CONN_F_NOOUTPUT); } flags |= conn_flags; cp->flags = flags; cp->dest = dest; IP_VS_DBG_BUF(7, "Bind-dest %s c:%s:%d v:%s:%d " "d:%s:%d fwd:%c s:%u conn->flags:%X conn->refcnt:%d " "dest->refcnt:%d\n", ip_vs_proto_name(cp->protocol), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), ip_vs_fwd_tag(cp), cp->state, cp->flags, refcount_read(&cp->refcnt), refcount_read(&dest->refcnt)); /* Update the connection counters */ if (!(flags & IP_VS_CONN_F_TEMPLATE)) { /* It is a normal connection, so modify the counters * according to the flags, later the protocol can * update them on state change */ if (!(flags & IP_VS_CONN_F_INACTIVE)) atomic_inc(&dest->activeconns); else atomic_inc(&dest->inactconns); } else { /* It is a persistent connection/template, so increase the persistent connection counter */ atomic_inc(&dest->persistconns); } if (dest->u_threshold != 0 && ip_vs_dest_totalconns(dest) >= dest->u_threshold) dest->flags |= IP_VS_DEST_F_OVERLOAD; } /* * Check if there is a destination for the connection, if so * bind the connection to the destination. */ void ip_vs_try_bind_dest(struct ip_vs_conn *cp) { struct ip_vs_dest *dest; rcu_read_lock(); /* This function is only invoked by the synchronization code. We do * not currently support heterogeneous pools with synchronization, * so we can make the assumption that the svc_af is the same as the * dest_af */ dest = ip_vs_find_dest(cp->ipvs, cp->af, cp->af, &cp->daddr, cp->dport, &cp->vaddr, cp->vport, cp->protocol, cp->fwmark, cp->flags); if (dest) { struct ip_vs_proto_data *pd; spin_lock_bh(&cp->lock); if (cp->dest) { spin_unlock_bh(&cp->lock); rcu_read_unlock(); return; } /* Applications work depending on the forwarding method * but better to reassign them always when binding dest */ if (cp->app) ip_vs_unbind_app(cp); ip_vs_bind_dest(cp, dest); spin_unlock_bh(&cp->lock); /* Update its packet transmitter */ cp->packet_xmit = NULL; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) ip_vs_bind_xmit_v6(cp); else #endif ip_vs_bind_xmit(cp); pd = ip_vs_proto_data_get(cp->ipvs, cp->protocol); if (pd && atomic_read(&pd->appcnt)) ip_vs_bind_app(cp, pd->pp); } rcu_read_unlock(); } /* * Unbind a connection entry with its VS destination * Called by the ip_vs_conn_expire function. */ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) { struct ip_vs_dest *dest = cp->dest; if (!dest) return; IP_VS_DBG_BUF(7, "Unbind-dest %s c:%s:%d v:%s:%d " "d:%s:%d fwd:%c s:%u conn->flags:%X conn->refcnt:%d " "dest->refcnt:%d\n", ip_vs_proto_name(cp->protocol), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), ip_vs_fwd_tag(cp), cp->state, cp->flags, refcount_read(&cp->refcnt), refcount_read(&dest->refcnt)); /* Update the connection counters */ if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) { /* It is a normal connection, so decrease the inactconns or activeconns counter */ if (cp->flags & IP_VS_CONN_F_INACTIVE) { atomic_dec(&dest->inactconns); } else { atomic_dec(&dest->activeconns); } } else { /* It is a persistent connection/template, so decrease the persistent connection counter */ atomic_dec(&dest->persistconns); } if (dest->l_threshold != 0) { if (ip_vs_dest_totalconns(dest) < dest->l_threshold) dest->flags &= ~IP_VS_DEST_F_OVERLOAD; } else if (dest->u_threshold != 0) { if (ip_vs_dest_totalconns(dest) * 4 < dest->u_threshold * 3) dest->flags &= ~IP_VS_DEST_F_OVERLOAD; } else { if (dest->flags & IP_VS_DEST_F_OVERLOAD) dest->flags &= ~IP_VS_DEST_F_OVERLOAD; } ip_vs_dest_put(dest); } static int expire_quiescent_template(struct netns_ipvs *ipvs, struct ip_vs_dest *dest) { #ifdef CONFIG_SYSCTL return ipvs->sysctl_expire_quiescent_template && (atomic_read(&dest->weight) == 0); #else return 0; #endif } /* * Checking if the destination of a connection template is available. * If available, return 1, otherwise invalidate this connection * template and return 0. */ int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest) { struct ip_vs_dest *dest = ct->dest; struct netns_ipvs *ipvs = ct->ipvs; /* * Checking the dest server status. */ if ((dest == NULL) || !(dest->flags & IP_VS_DEST_F_AVAILABLE) || expire_quiescent_template(ipvs, dest) || (cdest && (dest != cdest))) { IP_VS_DBG_BUF(9, "check_template: dest not available for " "protocol %s s:%s:%d v:%s:%d " "-> d:%s:%d\n", ip_vs_proto_name(ct->protocol), IP_VS_DBG_ADDR(ct->af, &ct->caddr), ntohs(ct->cport), IP_VS_DBG_ADDR(ct->af, &ct->vaddr), ntohs(ct->vport), IP_VS_DBG_ADDR(ct->daf, &ct->daddr), ntohs(ct->dport)); /* * Invalidate the connection template */ if (ct->vport != htons(0xffff)) { if (ip_vs_conn_unhash(ct)) { ct->dport = htons(0xffff); ct->vport = htons(0xffff); ct->cport = 0; ip_vs_conn_hash(ct); } } /* * Simply decrease the refcnt of the template, * don't restart its timer. */ __ip_vs_conn_put(ct); return 0; } return 1; } static void ip_vs_conn_rcu_free(struct rcu_head *head) { struct ip_vs_conn *cp = container_of(head, struct ip_vs_conn, rcu_head); ip_vs_pe_put(cp->pe); kfree(cp->pe_data); kmem_cache_free(ip_vs_conn_cachep, cp); } /* Try to delete connection while not holding reference */ static void ip_vs_conn_del(struct ip_vs_conn *cp) { if (del_timer(&cp->timer)) { /* Drop cp->control chain too */ if (cp->control) cp->timeout = 0; ip_vs_conn_expire(&cp->timer); } } /* Try to delete connection while holding reference */ static void ip_vs_conn_del_put(struct ip_vs_conn *cp) { if (del_timer(&cp->timer)) { /* Drop cp->control chain too */ if (cp->control) cp->timeout = 0; __ip_vs_conn_put(cp); ip_vs_conn_expire(&cp->timer); } else { __ip_vs_conn_put(cp); } } static void ip_vs_conn_expire(struct timer_list *t) { struct ip_vs_conn *cp = from_timer(cp, t, timer); struct netns_ipvs *ipvs = cp->ipvs; /* * do I control anybody? */ if (atomic_read(&cp->n_control)) goto expire_later; /* Unlink conn if not referenced anymore */ if (likely(ip_vs_conn_unlink(cp))) { struct ip_vs_conn *ct = cp->control; /* delete the timer if it is activated by other users */ del_timer(&cp->timer); /* does anybody control me? */ if (ct) { bool has_ref = !cp->timeout && __ip_vs_conn_get(ct); ip_vs_control_del(cp); /* Drop CTL or non-assured TPL if not used anymore */ if (has_ref && !atomic_read(&ct->n_control) && (!(ct->flags & IP_VS_CONN_F_TEMPLATE) || !(ct->state & IP_VS_CTPL_S_ASSURED))) { IP_VS_DBG(4, "drop controlling connection\n"); ip_vs_conn_del_put(ct); } else if (has_ref) { __ip_vs_conn_put(ct); } } if ((cp->flags & IP_VS_CONN_F_NFCT) && !(cp->flags & IP_VS_CONN_F_ONE_PACKET)) { /* Do not access conntracks during subsys cleanup * because nf_conntrack_find_get can not be used after * conntrack cleanup for the net. */ smp_rmb(); if (ipvs->enable) ip_vs_conn_drop_conntrack(cp); } if (unlikely(cp->app != NULL)) ip_vs_unbind_app(cp); ip_vs_unbind_dest(cp); if (cp->flags & IP_VS_CONN_F_NO_CPORT) atomic_dec(&ip_vs_conn_no_cport_cnt); if (cp->flags & IP_VS_CONN_F_ONE_PACKET) ip_vs_conn_rcu_free(&cp->rcu_head); else call_rcu(&cp->rcu_head, ip_vs_conn_rcu_free); atomic_dec(&ipvs->conn_count); return; } expire_later: IP_VS_DBG(7, "delayed: conn->refcnt=%d conn->n_control=%d\n", refcount_read(&cp->refcnt), atomic_read(&cp->n_control)); refcount_inc(&cp->refcnt); cp->timeout = 60*HZ; if (ipvs->sync_state & IP_VS_STATE_MASTER) ip_vs_sync_conn(ipvs, cp, sysctl_sync_threshold(ipvs)); __ip_vs_conn_put_timer(cp); } /* Modify timer, so that it expires as soon as possible. * Can be called without reference only if under RCU lock. * We can have such chain of conns linked with ->control: DATA->CTL->TPL * - DATA (eg. FTP) and TPL (persistence) can be present depending on setup * - cp->timeout=0 indicates all conns from chain should be dropped but * TPL is not dropped if in assured state */ void ip_vs_conn_expire_now(struct ip_vs_conn *cp) { /* Using mod_timer_pending will ensure the timer is not * modified after the final del_timer in ip_vs_conn_expire. */ if (timer_pending(&cp->timer) && time_after(cp->timer.expires, jiffies)) mod_timer_pending(&cp->timer, jiffies); } /* * Create a new connection entry and hash it into the ip_vs_conn_tab */ struct ip_vs_conn * ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, const union nf_inet_addr *daddr, __be16 dport, unsigned int flags, struct ip_vs_dest *dest, __u32 fwmark) { struct ip_vs_conn *cp; struct netns_ipvs *ipvs = p->ipvs; struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->ipvs, p->protocol); cp = kmem_cache_alloc(ip_vs_conn_cachep, GFP_ATOMIC); if (cp == NULL) { IP_VS_ERR_RL("%s(): no memory\n", __func__); return NULL; } INIT_HLIST_NODE(&cp->c_list); timer_setup(&cp->timer, ip_vs_conn_expire, 0); cp->ipvs = ipvs; cp->af = p->af; cp->daf = dest_af; cp->protocol = p->protocol; ip_vs_addr_set(p->af, &cp->caddr, p->caddr); cp->cport = p->cport; /* proto should only be IPPROTO_IP if p->vaddr is a fwmark */ ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, &cp->vaddr, p->vaddr); cp->vport = p->vport; ip_vs_addr_set(cp->daf, &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; cp->fwmark = fwmark; if (flags & IP_VS_CONN_F_TEMPLATE && p->pe) { ip_vs_pe_get(p->pe); cp->pe = p->pe; cp->pe_data = p->pe_data; cp->pe_data_len = p->pe_data_len; } else { cp->pe = NULL; cp->pe_data = NULL; cp->pe_data_len = 0; } spin_lock_init(&cp->lock); /* * Set the entry is referenced by the current thread before hashing * it in the table, so that other thread run ip_vs_random_dropentry * but cannot drop this entry. */ refcount_set(&cp->refcnt, 1); cp->control = NULL; atomic_set(&cp->n_control, 0); atomic_set(&cp->in_pkts, 0); cp->packet_xmit = NULL; cp->app = NULL; cp->app_data = NULL; /* reset struct ip_vs_seq */ cp->in_seq.delta = 0; cp->out_seq.delta = 0; atomic_inc(&ipvs->conn_count); if (flags & IP_VS_CONN_F_NO_CPORT) atomic_inc(&ip_vs_conn_no_cport_cnt); /* Bind the connection with a destination server */ cp->dest = NULL; ip_vs_bind_dest(cp, dest); /* Set its state and timeout */ cp->state = 0; cp->old_state = 0; cp->timeout = 3*HZ; cp->sync_endtime = jiffies & ~3UL; /* Bind its packet transmitter */ #ifdef CONFIG_IP_VS_IPV6 if (p->af == AF_INET6) ip_vs_bind_xmit_v6(cp); else #endif ip_vs_bind_xmit(cp); if (unlikely(pd && atomic_read(&pd->appcnt))) ip_vs_bind_app(cp, pd->pp); /* * Allow conntrack to be preserved. By default, conntrack * is created and destroyed for every packet. * Sometimes keeping conntrack can be useful for * IP_VS_CONN_F_ONE_PACKET too. */ if (ip_vs_conntrack_enabled(ipvs)) cp->flags |= IP_VS_CONN_F_NFCT; /* Hash it in the ip_vs_conn_tab finally */ ip_vs_conn_hash(cp); return cp; } /* * /proc/net/ip_vs_conn entries */ #ifdef CONFIG_PROC_FS struct ip_vs_iter_state { struct seq_net_private p; struct hlist_head *l; }; static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) { int idx; struct ip_vs_conn *cp; struct ip_vs_iter_state *iter = seq->private; for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { /* __ip_vs_conn_get() is not needed by * ip_vs_conn_seq_show and ip_vs_conn_sync_seq_show */ if (pos-- == 0) { iter->l = &ip_vs_conn_tab[idx]; return cp; } } cond_resched_rcu(); } return NULL; } static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct ip_vs_iter_state *iter = seq->private; iter->l = NULL; rcu_read_lock(); return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN; } static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_vs_conn *cp = v; struct ip_vs_iter_state *iter = seq->private; struct hlist_node *e; struct hlist_head *l = iter->l; int idx; ++*pos; if (v == SEQ_START_TOKEN) return ip_vs_conn_array(seq, 0); /* more on same hash chain? */ e = rcu_dereference(hlist_next_rcu(&cp->c_list)); if (e) return hlist_entry(e, struct ip_vs_conn, c_list); idx = l - ip_vs_conn_tab; while (++idx < ip_vs_conn_tab_size) { hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { iter->l = &ip_vs_conn_tab[idx]; return cp; } cond_resched_rcu(); } iter->l = NULL; return NULL; } static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Expires PEName PEData\n"); else { const struct ip_vs_conn *cp = v; struct net *net = seq_file_net(seq); char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3]; size_t len = 0; char dbuf[IP_VS_ADDRSTRLEN]; if (!net_eq(cp->ipvs->net, net)) return 0; if (cp->pe_data) { pe_data[0] = ' '; len = strlen(cp->pe->name); memcpy(pe_data + 1, cp->pe->name, len); pe_data[len + 1] = ' '; len += 2; len += cp->pe->show_pe_data(cp, pe_data + len); } pe_data[len] = '\0'; #ifdef CONFIG_IP_VS_IPV6 if (cp->daf == AF_INET6) snprintf(dbuf, sizeof(dbuf), "%pI6", &cp->daddr.in6); else #endif snprintf(dbuf, sizeof(dbuf), "%08X", ntohl(cp->daddr.ip)); #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X " "%s %04X %-11s %7u%s\n", ip_vs_proto_name(cp->protocol), &cp->caddr.in6, ntohs(cp->cport), &cp->vaddr.in6, ntohs(cp->vport), dbuf, ntohs(cp->dport), ip_vs_state_name(cp), jiffies_delta_to_msecs(cp->timer.expires - jiffies) / 1000, pe_data); else #endif seq_printf(seq, "%-3s %08X %04X %08X %04X" " %s %04X %-11s %7u%s\n", ip_vs_proto_name(cp->protocol), ntohl(cp->caddr.ip), ntohs(cp->cport), ntohl(cp->vaddr.ip), ntohs(cp->vport), dbuf, ntohs(cp->dport), ip_vs_state_name(cp), jiffies_delta_to_msecs(cp->timer.expires - jiffies) / 1000, pe_data); } return 0; } static const struct seq_operations ip_vs_conn_seq_ops = { .start = ip_vs_conn_seq_start, .next = ip_vs_conn_seq_next, .stop = ip_vs_conn_seq_stop, .show = ip_vs_conn_seq_show, }; static const char *ip_vs_origin_name(unsigned int flags) { if (flags & IP_VS_CONN_F_SYNC) return "SYNC"; else return "LOCAL"; } static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) { char dbuf[IP_VS_ADDRSTRLEN]; if (v == SEQ_START_TOKEN) seq_puts(seq, "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Origin Expires\n"); else { const struct ip_vs_conn *cp = v; struct net *net = seq_file_net(seq); if (!net_eq(cp->ipvs->net, net)) return 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->daf == AF_INET6) snprintf(dbuf, sizeof(dbuf), "%pI6", &cp->daddr.in6); else #endif snprintf(dbuf, sizeof(dbuf), "%08X", ntohl(cp->daddr.ip)); #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X " "%s %04X %-11s %-6s %7u\n", ip_vs_proto_name(cp->protocol), &cp->caddr.in6, ntohs(cp->cport), &cp->vaddr.in6, ntohs(cp->vport), dbuf, ntohs(cp->dport), ip_vs_state_name(cp), ip_vs_origin_name(cp->flags), jiffies_delta_to_msecs(cp->timer.expires - jiffies) / 1000); else #endif seq_printf(seq, "%-3s %08X %04X %08X %04X " "%s %04X %-11s %-6s %7u\n", ip_vs_proto_name(cp->protocol), ntohl(cp->caddr.ip), ntohs(cp->cport), ntohl(cp->vaddr.ip), ntohs(cp->vport), dbuf, ntohs(cp->dport), ip_vs_state_name(cp), ip_vs_origin_name(cp->flags), jiffies_delta_to_msecs(cp->timer.expires - jiffies) / 1000); } return 0; } static const struct seq_operations ip_vs_conn_sync_seq_ops = { .start = ip_vs_conn_seq_start, .next = ip_vs_conn_seq_next, .stop = ip_vs_conn_seq_stop, .show = ip_vs_conn_sync_seq_show, }; #endif /* Randomly drop connection entries before running out of memory * Can be used for DATA and CTL conns. For TPL conns there are exceptions: * - traffic for services in OPS mode increases ct->in_pkts, so it is supported * - traffic for services not in OPS mode does not increase ct->in_pkts in * all cases, so it is not supported */ static inline int todrop_entry(struct ip_vs_conn *cp) { /* * The drop rate array needs tuning for real environments. * Called from timer bh only => no locking */ static const signed char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; static signed char todrop_counter[9] = {0}; int i; /* if the conn entry hasn't lasted for 60 seconds, don't drop it. This will leave enough time for normal connection to get through. */ if (time_before(cp->timeout + jiffies, cp->timer.expires + 60*HZ)) return 0; /* Don't drop the entry if its number of incoming packets is not located in [0, 8] */ i = atomic_read(&cp->in_pkts); if (i > 8 || i < 0) return 0; if (!todrop_rate[i]) return 0; if (--todrop_counter[i] > 0) return 0; todrop_counter[i] = todrop_rate[i]; return 1; } static inline bool ip_vs_conn_ops_mode(struct ip_vs_conn *cp) { struct ip_vs_service *svc; if (!cp->dest) return false; svc = rcu_dereference(cp->dest->svc); return svc && (svc->flags & IP_VS_SVC_F_ONEPACKET); } /* Called from keventd and must protect itself from softirqs */ void ip_vs_random_dropentry(struct netns_ipvs *ipvs) { int idx; struct ip_vs_conn *cp; rcu_read_lock(); /* * Randomly scan 1/32 of the whole table every second */ for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { unsigned int hash = get_random_u32() & ip_vs_conn_tab_mask; hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->ipvs != ipvs) continue; if (atomic_read(&cp->n_control)) continue; if (cp->flags & IP_VS_CONN_F_TEMPLATE) { /* connection template of OPS */ if (ip_vs_conn_ops_mode(cp)) goto try_drop; if (!(cp->state & IP_VS_CTPL_S_ASSURED)) goto drop; continue; } if (cp->protocol == IPPROTO_TCP) { switch(cp->state) { case IP_VS_TCP_S_SYN_RECV: case IP_VS_TCP_S_SYNACK: break; case IP_VS_TCP_S_ESTABLISHED: if (todrop_entry(cp)) break; continue; default: continue; } } else if (cp->protocol == IPPROTO_SCTP) { switch (cp->state) { case IP_VS_SCTP_S_INIT1: case IP_VS_SCTP_S_INIT: break; case IP_VS_SCTP_S_ESTABLISHED: if (todrop_entry(cp)) break; continue; default: continue; } } else { try_drop: if (!todrop_entry(cp)) continue; } drop: IP_VS_DBG(4, "drop connection\n"); ip_vs_conn_del(cp); } cond_resched_rcu(); } rcu_read_unlock(); } /* * Flush all the connection entries in the ip_vs_conn_tab */ static void ip_vs_conn_flush(struct netns_ipvs *ipvs) { int idx; struct ip_vs_conn *cp, *cp_c; flush_again: rcu_read_lock(); for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { if (cp->ipvs != ipvs) continue; if (atomic_read(&cp->n_control)) continue; cp_c = cp->control; IP_VS_DBG(4, "del connection\n"); ip_vs_conn_del(cp); if (cp_c && !atomic_read(&cp_c->n_control)) { IP_VS_DBG(4, "del controlling connection\n"); ip_vs_conn_del(cp_c); } } cond_resched_rcu(); } rcu_read_unlock(); /* the counter may be not NULL, because maybe some conn entries are run by slow timer handler or unhashed but still referred */ if (atomic_read(&ipvs->conn_count) != 0) { schedule(); goto flush_again; } } #ifdef CONFIG_SYSCTL void ip_vs_expire_nodest_conn_flush(struct netns_ipvs *ipvs) { int idx; struct ip_vs_conn *cp, *cp_c; struct ip_vs_dest *dest; rcu_read_lock(); for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { if (cp->ipvs != ipvs) continue; dest = cp->dest; if (!dest || (dest->flags & IP_VS_DEST_F_AVAILABLE)) continue; if (atomic_read(&cp->n_control)) continue; cp_c = cp->control; IP_VS_DBG(4, "del connection\n"); ip_vs_conn_del(cp); if (cp_c && !atomic_read(&cp_c->n_control)) { IP_VS_DBG(4, "del controlling connection\n"); ip_vs_conn_del(cp_c); } } cond_resched_rcu(); /* netns clean up started, abort delayed work */ if (!ipvs->enable) break; } rcu_read_unlock(); } #endif /* * per netns init and exit */ int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs) { atomic_set(&ipvs->conn_count, 0); #ifdef CONFIG_PROC_FS if (!proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, &ip_vs_conn_seq_ops, sizeof(struct ip_vs_iter_state))) goto err_conn; if (!proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, &ip_vs_conn_sync_seq_ops, sizeof(struct ip_vs_iter_state))) goto err_conn_sync; #endif return 0; #ifdef CONFIG_PROC_FS err_conn_sync: remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); err_conn: return -ENOMEM; #endif } void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs) { /* flush all the connection entries first */ ip_vs_conn_flush(ipvs); #ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); remove_proc_entry("ip_vs_conn_sync", ipvs->net->proc_net); #endif } int __init ip_vs_conn_init(void) { size_t tab_array_size; int max_avail; #if BITS_PER_LONG > 32 int max = 27; #else int max = 20; #endif int min = 8; int idx; max_avail = order_base_2(totalram_pages()) + PAGE_SHIFT; max_avail -= 2; /* ~4 in hash row */ max_avail -= 1; /* IPVS up to 1/2 of mem */ max_avail -= order_base_2(sizeof(struct ip_vs_conn)); max = clamp(max, min, max_avail); ip_vs_conn_tab_bits = clamp_val(ip_vs_conn_tab_bits, min, max); ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; /* * Allocate the connection hash table and initialize its list heads */ tab_array_size = array_size(ip_vs_conn_tab_size, sizeof(*ip_vs_conn_tab)); ip_vs_conn_tab = kvmalloc_array(ip_vs_conn_tab_size, sizeof(*ip_vs_conn_tab), GFP_KERNEL); if (!ip_vs_conn_tab) return -ENOMEM; /* Allocate ip_vs_conn slab cache */ ip_vs_conn_cachep = KMEM_CACHE(ip_vs_conn, SLAB_HWCACHE_ALIGN); if (!ip_vs_conn_cachep) { kvfree(ip_vs_conn_tab); return -ENOMEM; } pr_info("Connection hash table configured (size=%d, memory=%zdKbytes)\n", ip_vs_conn_tab_size, tab_array_size / 1024); IP_VS_DBG(0, "Each connection entry needs %zd bytes at least\n", sizeof(struct ip_vs_conn)); for (idx = 0; idx < ip_vs_conn_tab_size; idx++) INIT_HLIST_HEAD(&ip_vs_conn_tab[idx]); for (idx = 0; idx < CT_LOCKARRAY_SIZE; idx++) { spin_lock_init(&__ip_vs_conntbl_lock_array[idx].l); } /* calculate the random value for connection hash */ get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); return 0; } void ip_vs_conn_cleanup(void) { /* Wait all ip_vs_conn_rcu_free() callbacks to complete */ rcu_barrier(); /* Release the empty cache */ kmem_cache_destroy(ip_vs_conn_cachep); kvfree(ip_vs_conn_tab); } |
| 9 8 2 6 8 8 9 9 9 9 9 9 9 9 9 9 9 9 9 7 7 1 1 1 1 10 14 13 13 12 13 13 8 7 8 8 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * CCM: Counter with CBC-MAC * * (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com> */ #include <crypto/internal/aead.h> #include <crypto/internal/cipher.h> #include <crypto/internal/hash.h> #include <crypto/internal/skcipher.h> #include <crypto/scatterwalk.h> #include <linux/err.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> struct ccm_instance_ctx { struct crypto_skcipher_spawn ctr; struct crypto_ahash_spawn mac; }; struct crypto_ccm_ctx { struct crypto_ahash *mac; struct crypto_skcipher *ctr; }; struct crypto_rfc4309_ctx { struct crypto_aead *child; u8 nonce[3]; }; struct crypto_rfc4309_req_ctx { struct scatterlist src[3]; struct scatterlist dst[3]; struct aead_request subreq; }; struct crypto_ccm_req_priv_ctx { u8 odata[16]; u8 idata[16]; u8 auth_tag[16]; u32 flags; struct scatterlist src[3]; struct scatterlist dst[3]; union { struct ahash_request ahreq; struct skcipher_request skreq; }; }; struct cbcmac_tfm_ctx { struct crypto_cipher *child; }; struct cbcmac_desc_ctx { unsigned int len; u8 dg[]; }; static inline struct crypto_ccm_req_priv_ctx *crypto_ccm_reqctx( struct aead_request *req) { unsigned long align = crypto_aead_alignmask(crypto_aead_reqtfm(req)); return (void *)PTR_ALIGN((u8 *)aead_request_ctx(req), align + 1); } static int set_msg_len(u8 *block, unsigned int msglen, int csize) { __be32 data; memset(block, 0, csize); block += csize; if (csize >= 4) csize = 4; else if (msglen > (1 << (8 * csize))) return -EOVERFLOW; data = cpu_to_be32(msglen); memcpy(block - csize, (u8 *)&data + 4 - csize, csize); return 0; } static int crypto_ccm_setkey(struct crypto_aead *aead, const u8 *key, unsigned int keylen) { struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct crypto_skcipher *ctr = ctx->ctr; struct crypto_ahash *mac = ctx->mac; int err; crypto_skcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK); crypto_skcipher_set_flags(ctr, crypto_aead_get_flags(aead) & CRYPTO_TFM_REQ_MASK); err = crypto_skcipher_setkey(ctr, key, keylen); if (err) return err; crypto_ahash_clear_flags(mac, CRYPTO_TFM_REQ_MASK); crypto_ahash_set_flags(mac, crypto_aead_get_flags(aead) & CRYPTO_TFM_REQ_MASK); return crypto_ahash_setkey(mac, key, keylen); } static int crypto_ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize) { switch (authsize) { case 4: case 6: case 8: case 10: case 12: case 14: case 16: break; default: return -EINVAL; } return 0; } static int format_input(u8 *info, struct aead_request *req, unsigned int cryptlen) { struct crypto_aead *aead = crypto_aead_reqtfm(req); unsigned int lp = req->iv[0]; unsigned int l = lp + 1; unsigned int m; m = crypto_aead_authsize(aead); memcpy(info, req->iv, 16); /* format control info per RFC 3610 and * NIST Special Publication 800-38C */ *info |= (8 * ((m - 2) / 2)); if (req->assoclen) *info |= 64; return set_msg_len(info + 16 - l, cryptlen, l); } static int format_adata(u8 *adata, unsigned int a) { int len = 0; /* add control info for associated data * RFC 3610 and NIST Special Publication 800-38C */ if (a < 65280) { *(__be16 *)adata = cpu_to_be16(a); len = 2; } else { *(__be16 *)adata = cpu_to_be16(0xfffe); *(__be32 *)&adata[2] = cpu_to_be32(a); len = 6; } return len; } static int crypto_ccm_auth(struct aead_request *req, struct scatterlist *plain, unsigned int cryptlen) { struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct ahash_request *ahreq = &pctx->ahreq; unsigned int assoclen = req->assoclen; struct scatterlist sg[3]; u8 *odata = pctx->odata; u8 *idata = pctx->idata; int ilen, err; /* format control data for input */ err = format_input(odata, req, cryptlen); if (err) goto out; sg_init_table(sg, 3); sg_set_buf(&sg[0], odata, 16); /* format associated data and compute into mac */ if (assoclen) { ilen = format_adata(idata, assoclen); sg_set_buf(&sg[1], idata, ilen); sg_chain(sg, 3, req->src); } else { ilen = 0; sg_chain(sg, 2, req->src); } ahash_request_set_tfm(ahreq, ctx->mac); ahash_request_set_callback(ahreq, pctx->flags, NULL, NULL); ahash_request_set_crypt(ahreq, sg, NULL, assoclen + ilen + 16); err = crypto_ahash_init(ahreq); if (err) goto out; err = crypto_ahash_update(ahreq); if (err) goto out; /* we need to pad the MAC input to a round multiple of the block size */ ilen = 16 - (assoclen + ilen) % 16; if (ilen < 16) { memset(idata, 0, ilen); sg_init_table(sg, 2); sg_set_buf(&sg[0], idata, ilen); if (plain) sg_chain(sg, 2, plain); plain = sg; cryptlen += ilen; } ahash_request_set_crypt(ahreq, plain, odata, cryptlen); err = crypto_ahash_finup(ahreq); out: return err; } static void crypto_ccm_encrypt_done(void *data, int err) { struct aead_request *req = data; struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); u8 *odata = pctx->odata; if (!err) scatterwalk_map_and_copy(odata, req->dst, req->assoclen + req->cryptlen, crypto_aead_authsize(aead), 1); aead_request_complete(req, err); } static inline int crypto_ccm_check_iv(const u8 *iv) { /* 2 <= L <= 8, so 1 <= L' <= 7. */ if (1 > iv[0] || iv[0] > 7) return -EINVAL; return 0; } static int crypto_ccm_init_crypt(struct aead_request *req, u8 *tag) { struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct scatterlist *sg; u8 *iv = req->iv; int err; err = crypto_ccm_check_iv(iv); if (err) return err; pctx->flags = aead_request_flags(req); /* Note: rfc 3610 and NIST 800-38C require counter of * zero to encrypt auth tag. */ memset(iv + 15 - iv[0], 0, iv[0] + 1); sg_init_table(pctx->src, 3); sg_set_buf(pctx->src, tag, 16); sg = scatterwalk_ffwd(pctx->src + 1, req->src, req->assoclen); if (sg != pctx->src + 1) sg_chain(pctx->src, 2, sg); if (req->src != req->dst) { sg_init_table(pctx->dst, 3); sg_set_buf(pctx->dst, tag, 16); sg = scatterwalk_ffwd(pctx->dst + 1, req->dst, req->assoclen); if (sg != pctx->dst + 1) sg_chain(pctx->dst, 2, sg); } return 0; } static int crypto_ccm_encrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct skcipher_request *skreq = &pctx->skreq; struct scatterlist *dst; unsigned int cryptlen = req->cryptlen; u8 *odata = pctx->odata; u8 *iv = req->iv; int err; err = crypto_ccm_init_crypt(req, odata); if (err) return err; err = crypto_ccm_auth(req, sg_next(pctx->src), cryptlen); if (err) return err; dst = pctx->src; if (req->src != req->dst) dst = pctx->dst; skcipher_request_set_tfm(skreq, ctx->ctr); skcipher_request_set_callback(skreq, pctx->flags, crypto_ccm_encrypt_done, req); skcipher_request_set_crypt(skreq, pctx->src, dst, cryptlen + 16, iv); err = crypto_skcipher_encrypt(skreq); if (err) return err; /* copy authtag to end of dst */ scatterwalk_map_and_copy(odata, sg_next(dst), cryptlen, crypto_aead_authsize(aead), 1); return err; } static void crypto_ccm_decrypt_done(void *data, int err) { struct aead_request *req = data; struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct crypto_aead *aead = crypto_aead_reqtfm(req); unsigned int authsize = crypto_aead_authsize(aead); unsigned int cryptlen = req->cryptlen - authsize; struct scatterlist *dst; pctx->flags = 0; dst = sg_next(req->src == req->dst ? pctx->src : pctx->dst); if (!err) { err = crypto_ccm_auth(req, dst, cryptlen); if (!err && crypto_memneq(pctx->auth_tag, pctx->odata, authsize)) err = -EBADMSG; } aead_request_complete(req, err); } static int crypto_ccm_decrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct skcipher_request *skreq = &pctx->skreq; struct scatterlist *dst; unsigned int authsize = crypto_aead_authsize(aead); unsigned int cryptlen = req->cryptlen; u8 *authtag = pctx->auth_tag; u8 *odata = pctx->odata; u8 *iv = pctx->idata; int err; cryptlen -= authsize; err = crypto_ccm_init_crypt(req, authtag); if (err) return err; scatterwalk_map_and_copy(authtag, sg_next(pctx->src), cryptlen, authsize, 0); dst = pctx->src; if (req->src != req->dst) dst = pctx->dst; memcpy(iv, req->iv, 16); skcipher_request_set_tfm(skreq, ctx->ctr); skcipher_request_set_callback(skreq, pctx->flags, crypto_ccm_decrypt_done, req); skcipher_request_set_crypt(skreq, pctx->src, dst, cryptlen + 16, iv); err = crypto_skcipher_decrypt(skreq); if (err) return err; err = crypto_ccm_auth(req, sg_next(dst), cryptlen); if (err) return err; /* verify */ if (crypto_memneq(authtag, odata, authsize)) return -EBADMSG; return err; } static int crypto_ccm_init_tfm(struct crypto_aead *tfm) { struct aead_instance *inst = aead_alg_instance(tfm); struct ccm_instance_ctx *ictx = aead_instance_ctx(inst); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm); struct crypto_ahash *mac; struct crypto_skcipher *ctr; unsigned long align; int err; mac = crypto_spawn_ahash(&ictx->mac); if (IS_ERR(mac)) return PTR_ERR(mac); ctr = crypto_spawn_skcipher(&ictx->ctr); err = PTR_ERR(ctr); if (IS_ERR(ctr)) goto err_free_mac; ctx->mac = mac; ctx->ctr = ctr; align = crypto_aead_alignmask(tfm); align &= ~(crypto_tfm_ctx_alignment() - 1); crypto_aead_set_reqsize( tfm, align + sizeof(struct crypto_ccm_req_priv_ctx) + max(crypto_ahash_reqsize(mac), crypto_skcipher_reqsize(ctr))); return 0; err_free_mac: crypto_free_ahash(mac); return err; } static void crypto_ccm_exit_tfm(struct crypto_aead *tfm) { struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm); crypto_free_ahash(ctx->mac); crypto_free_skcipher(ctx->ctr); } static void crypto_ccm_free(struct aead_instance *inst) { struct ccm_instance_ctx *ctx = aead_instance_ctx(inst); crypto_drop_ahash(&ctx->mac); crypto_drop_skcipher(&ctx->ctr); kfree(inst); } static int crypto_ccm_create_common(struct crypto_template *tmpl, struct rtattr **tb, const char *ctr_name, const char *mac_name) { struct skcipher_alg_common *ctr; u32 mask; struct aead_instance *inst; struct ccm_instance_ctx *ictx; struct hash_alg_common *mac; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_AEAD, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL); if (!inst) return -ENOMEM; ictx = aead_instance_ctx(inst); err = crypto_grab_ahash(&ictx->mac, aead_crypto_instance(inst), mac_name, 0, mask | CRYPTO_ALG_ASYNC); if (err) goto err_free_inst; mac = crypto_spawn_ahash_alg(&ictx->mac); err = -EINVAL; if (strncmp(mac->base.cra_name, "cbcmac(", 7) != 0 || mac->digestsize != 16) goto err_free_inst; err = crypto_grab_skcipher(&ictx->ctr, aead_crypto_instance(inst), ctr_name, 0, mask); if (err) goto err_free_inst; ctr = crypto_spawn_skcipher_alg_common(&ictx->ctr); /* The skcipher algorithm must be CTR mode, using 16-byte blocks. */ err = -EINVAL; if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 || ctr->ivsize != 16 || ctr->base.cra_blocksize != 1) goto err_free_inst; /* ctr and cbcmac must use the same underlying block cipher. */ if (strcmp(ctr->base.cra_name + 4, mac->base.cra_name + 7) != 0) goto err_free_inst; err = -ENAMETOOLONG; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, "ccm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "ccm_base(%s,%s)", ctr->base.cra_driver_name, mac->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; inst->alg.base.cra_priority = (mac->base.cra_priority + ctr->base.cra_priority) / 2; inst->alg.base.cra_blocksize = 1; inst->alg.base.cra_alignmask = ctr->base.cra_alignmask; inst->alg.ivsize = 16; inst->alg.chunksize = ctr->chunksize; inst->alg.maxauthsize = 16; inst->alg.base.cra_ctxsize = sizeof(struct crypto_ccm_ctx); inst->alg.init = crypto_ccm_init_tfm; inst->alg.exit = crypto_ccm_exit_tfm; inst->alg.setkey = crypto_ccm_setkey; inst->alg.setauthsize = crypto_ccm_setauthsize; inst->alg.encrypt = crypto_ccm_encrypt; inst->alg.decrypt = crypto_ccm_decrypt; inst->free = crypto_ccm_free; err = aead_register_instance(tmpl, inst); if (err) { err_free_inst: crypto_ccm_free(inst); } return err; } static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb) { const char *cipher_name; char ctr_name[CRYPTO_MAX_ALG_NAME]; char mac_name[CRYPTO_MAX_ALG_NAME]; cipher_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(cipher_name)) return PTR_ERR(cipher_name); if (snprintf(ctr_name, CRYPTO_MAX_ALG_NAME, "ctr(%s)", cipher_name) >= CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; if (snprintf(mac_name, CRYPTO_MAX_ALG_NAME, "cbcmac(%s)", cipher_name) >= CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name); } static int crypto_ccm_base_create(struct crypto_template *tmpl, struct rtattr **tb) { const char *ctr_name; const char *mac_name; ctr_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(ctr_name)) return PTR_ERR(ctr_name); mac_name = crypto_attr_alg_name(tb[2]); if (IS_ERR(mac_name)) return PTR_ERR(mac_name); return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name); } static int crypto_rfc4309_setkey(struct crypto_aead *parent, const u8 *key, unsigned int keylen) { struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(parent); struct crypto_aead *child = ctx->child; if (keylen < 3) return -EINVAL; keylen -= 3; memcpy(ctx->nonce, key + keylen, 3); crypto_aead_clear_flags(child, CRYPTO_TFM_REQ_MASK); crypto_aead_set_flags(child, crypto_aead_get_flags(parent) & CRYPTO_TFM_REQ_MASK); return crypto_aead_setkey(child, key, keylen); } static int crypto_rfc4309_setauthsize(struct crypto_aead *parent, unsigned int authsize) { struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(parent); switch (authsize) { case 8: case 12: case 16: break; default: return -EINVAL; } return crypto_aead_setauthsize(ctx->child, authsize); } static struct aead_request *crypto_rfc4309_crypt(struct aead_request *req) { struct crypto_rfc4309_req_ctx *rctx = aead_request_ctx(req); struct aead_request *subreq = &rctx->subreq; struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(aead); struct crypto_aead *child = ctx->child; struct scatterlist *sg; u8 *iv = PTR_ALIGN((u8 *)(subreq + 1) + crypto_aead_reqsize(child), crypto_aead_alignmask(child) + 1); /* L' */ iv[0] = 3; memcpy(iv + 1, ctx->nonce, 3); memcpy(iv + 4, req->iv, 8); scatterwalk_map_and_copy(iv + 16, req->src, 0, req->assoclen - 8, 0); sg_init_table(rctx->src, 3); sg_set_buf(rctx->src, iv + 16, req->assoclen - 8); sg = scatterwalk_ffwd(rctx->src + 1, req->src, req->assoclen); if (sg != rctx->src + 1) sg_chain(rctx->src, 2, sg); if (req->src != req->dst) { sg_init_table(rctx->dst, 3); sg_set_buf(rctx->dst, iv + 16, req->assoclen - 8); sg = scatterwalk_ffwd(rctx->dst + 1, req->dst, req->assoclen); if (sg != rctx->dst + 1) sg_chain(rctx->dst, 2, sg); } aead_request_set_tfm(subreq, child); aead_request_set_callback(subreq, req->base.flags, req->base.complete, req->base.data); aead_request_set_crypt(subreq, rctx->src, req->src == req->dst ? rctx->src : rctx->dst, req->cryptlen, iv); aead_request_set_ad(subreq, req->assoclen - 8); return subreq; } static int crypto_rfc4309_encrypt(struct aead_request *req) { if (req->assoclen != 16 && req->assoclen != 20) return -EINVAL; req = crypto_rfc4309_crypt(req); return crypto_aead_encrypt(req); } static int crypto_rfc4309_decrypt(struct aead_request *req) { if (req->assoclen != 16 && req->assoclen != 20) return -EINVAL; req = crypto_rfc4309_crypt(req); return crypto_aead_decrypt(req); } static int crypto_rfc4309_init_tfm(struct crypto_aead *tfm) { struct aead_instance *inst = aead_alg_instance(tfm); struct crypto_aead_spawn *spawn = aead_instance_ctx(inst); struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(tfm); struct crypto_aead *aead; unsigned long align; aead = crypto_spawn_aead(spawn); if (IS_ERR(aead)) return PTR_ERR(aead); ctx->child = aead; align = crypto_aead_alignmask(aead); align &= ~(crypto_tfm_ctx_alignment() - 1); crypto_aead_set_reqsize( tfm, sizeof(struct crypto_rfc4309_req_ctx) + ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) + align + 32); return 0; } static void crypto_rfc4309_exit_tfm(struct crypto_aead *tfm) { struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(tfm); crypto_free_aead(ctx->child); } static void crypto_rfc4309_free(struct aead_instance *inst) { crypto_drop_aead(aead_instance_ctx(inst)); kfree(inst); } static int crypto_rfc4309_create(struct crypto_template *tmpl, struct rtattr **tb) { u32 mask; struct aead_instance *inst; struct crypto_aead_spawn *spawn; struct aead_alg *alg; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_AEAD, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = aead_instance_ctx(inst); err = crypto_grab_aead(spawn, aead_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; alg = crypto_spawn_aead_alg(spawn); err = -EINVAL; /* We only support 16-byte blocks. */ if (crypto_aead_alg_ivsize(alg) != 16) goto err_free_inst; /* Not a stream cipher? */ if (alg->base.cra_blocksize != 1) goto err_free_inst; err = -ENAMETOOLONG; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, "rfc4309(%s)", alg->base.cra_name) >= CRYPTO_MAX_ALG_NAME || snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "rfc4309(%s)", alg->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; inst->alg.base.cra_priority = alg->base.cra_priority; inst->alg.base.cra_blocksize = 1; inst->alg.base.cra_alignmask = alg->base.cra_alignmask; inst->alg.ivsize = 8; inst->alg.chunksize = crypto_aead_alg_chunksize(alg); inst->alg.maxauthsize = 16; inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4309_ctx); inst->alg.init = crypto_rfc4309_init_tfm; inst->alg.exit = crypto_rfc4309_exit_tfm; inst->alg.setkey = crypto_rfc4309_setkey; inst->alg.setauthsize = crypto_rfc4309_setauthsize; inst->alg.encrypt = crypto_rfc4309_encrypt; inst->alg.decrypt = crypto_rfc4309_decrypt; inst->free = crypto_rfc4309_free; err = aead_register_instance(tmpl, inst); if (err) { err_free_inst: crypto_rfc4309_free(inst); } return err; } static int crypto_cbcmac_digest_setkey(struct crypto_shash *parent, const u8 *inkey, unsigned int keylen) { struct cbcmac_tfm_ctx *ctx = crypto_shash_ctx(parent); return crypto_cipher_setkey(ctx->child, inkey, keylen); } static int crypto_cbcmac_digest_init(struct shash_desc *pdesc) { struct cbcmac_desc_ctx *ctx = shash_desc_ctx(pdesc); int bs = crypto_shash_digestsize(pdesc->tfm); ctx->len = 0; memset(ctx->dg, 0, bs); return 0; } static int crypto_cbcmac_digest_update(struct shash_desc *pdesc, const u8 *p, unsigned int len) { struct crypto_shash *parent = pdesc->tfm; struct cbcmac_tfm_ctx *tctx = crypto_shash_ctx(parent); struct cbcmac_desc_ctx *ctx = shash_desc_ctx(pdesc); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_digestsize(parent); while (len > 0) { unsigned int l = min(len, bs - ctx->len); crypto_xor(&ctx->dg[ctx->len], p, l); ctx->len +=l; len -= l; p += l; if (ctx->len == bs) { crypto_cipher_encrypt_one(tfm, ctx->dg, ctx->dg); ctx->len = 0; } } return 0; } static int crypto_cbcmac_digest_final(struct shash_desc *pdesc, u8 *out) { struct crypto_shash *parent = pdesc->tfm; struct cbcmac_tfm_ctx *tctx = crypto_shash_ctx(parent); struct cbcmac_desc_ctx *ctx = shash_desc_ctx(pdesc); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_digestsize(parent); if (ctx->len) crypto_cipher_encrypt_one(tfm, ctx->dg, ctx->dg); memcpy(out, ctx->dg, bs); return 0; } static int cbcmac_init_tfm(struct crypto_tfm *tfm) { struct crypto_cipher *cipher; struct crypto_instance *inst = (void *)tfm->__crt_alg; struct crypto_cipher_spawn *spawn = crypto_instance_ctx(inst); struct cbcmac_tfm_ctx *ctx = crypto_tfm_ctx(tfm); cipher = crypto_spawn_cipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->child = cipher; return 0; }; static void cbcmac_exit_tfm(struct crypto_tfm *tfm) { struct cbcmac_tfm_ctx *ctx = crypto_tfm_ctx(tfm); crypto_free_cipher(ctx->child); } static int cbcmac_create(struct crypto_template *tmpl, struct rtattr **tb) { struct shash_instance *inst; struct crypto_cipher_spawn *spawn; struct crypto_alg *alg; u32 mask; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SHASH, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = shash_instance_ctx(inst); err = crypto_grab_cipher(spawn, shash_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; alg = crypto_spawn_cipher_alg(spawn); err = crypto_inst_setname(shash_crypto_instance(inst), tmpl->name, alg); if (err) goto err_free_inst; inst->alg.base.cra_priority = alg->cra_priority; inst->alg.base.cra_blocksize = 1; inst->alg.digestsize = alg->cra_blocksize; inst->alg.descsize = sizeof(struct cbcmac_desc_ctx) + alg->cra_blocksize; inst->alg.base.cra_ctxsize = sizeof(struct cbcmac_tfm_ctx); inst->alg.base.cra_init = cbcmac_init_tfm; inst->alg.base.cra_exit = cbcmac_exit_tfm; inst->alg.init = crypto_cbcmac_digest_init; inst->alg.update = crypto_cbcmac_digest_update; inst->alg.final = crypto_cbcmac_digest_final; inst->alg.setkey = crypto_cbcmac_digest_setkey; inst->free = shash_free_singlespawn_instance; err = shash_register_instance(tmpl, inst); if (err) { err_free_inst: shash_free_singlespawn_instance(inst); } return err; } static struct crypto_template crypto_ccm_tmpls[] = { { .name = "cbcmac", .create = cbcmac_create, .module = THIS_MODULE, }, { .name = "ccm_base", .create = crypto_ccm_base_create, .module = THIS_MODULE, }, { .name = "ccm", .create = crypto_ccm_create, .module = THIS_MODULE, }, { .name = "rfc4309", .create = crypto_rfc4309_create, .module = THIS_MODULE, }, }; static int __init crypto_ccm_module_init(void) { return crypto_register_templates(crypto_ccm_tmpls, ARRAY_SIZE(crypto_ccm_tmpls)); } static void __exit crypto_ccm_module_exit(void) { crypto_unregister_templates(crypto_ccm_tmpls, ARRAY_SIZE(crypto_ccm_tmpls)); } subsys_initcall(crypto_ccm_module_init); module_exit(crypto_ccm_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Counter with CBC MAC"); MODULE_ALIAS_CRYPTO("ccm_base"); MODULE_ALIAS_CRYPTO("rfc4309"); MODULE_ALIAS_CRYPTO("ccm"); MODULE_ALIAS_CRYPTO("cbcmac"); MODULE_IMPORT_NS(CRYPTO_INTERNAL); |
| 4 3 1 3 3 1 1 1 1 1 1 1 1 1 8 8 8 7 7 1 3 4 3 3 8 8 8 8 58 58 3 56 35 23 2 33 18 15 15 15 15 34 2 33 21 16 6 3 3 70 6 83 6 38 2 2 2 360 360 61 174 360 71 229 133 49 161 210 204 4 2 210 203 191 4 1 3 3 3 1 2 2 36 36 2 35 25 12 2 23 21 1 1 2 9 4 3 7 7 15 15 15 15 26 2 26 17 13 5 1 3 3 359 359 297 296 59 174 80 64 200 91 203 203 143 143 203 14 14 9 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS An implementation of the IP virtual server support for the * LINUX operating system. IPVS is now implemented as a module * over the Netfilter framework. IPVS can be used to build a * high-performance and highly available server based on a * cluster of servers. * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Peter Kese <peter.kese@ijs.si> * Julian Anastasov <ja@ssi.bg> * * The IPVS code for kernel 2.2 was done by Wensong Zhang and Peter Kese, * with changes/fixes from Julian Anastasov, Lars Marowsky-Bree, Horms * and others. * * Changes: * Paul `Rusty' Russell properly handle non-linear skbs * Harald Welte don't use nfcache */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/sctp.h> #include <linux/icmp.h> #include <linux/slab.h> #include <net/ip.h> #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> /* for icmp_send */ #include <net/gue.h> #include <net/gre.h> #include <net/route.h> #include <net/ip6_checksum.h> #include <net/netns/generic.h> /* net_generic() */ #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <linux/netfilter_ipv6.h> #include <net/ip6_route.h> #endif #include <net/ip_vs.h> #include <linux/indirect_call_wrapper.h> EXPORT_SYMBOL(register_ip_vs_scheduler); EXPORT_SYMBOL(unregister_ip_vs_scheduler); EXPORT_SYMBOL(ip_vs_proto_name); EXPORT_SYMBOL(ip_vs_conn_new); EXPORT_SYMBOL(ip_vs_conn_in_get); EXPORT_SYMBOL(ip_vs_conn_out_get); #ifdef CONFIG_IP_VS_PROTO_TCP EXPORT_SYMBOL(ip_vs_tcp_conn_listen); #endif EXPORT_SYMBOL(ip_vs_conn_put); #ifdef CONFIG_IP_VS_DEBUG EXPORT_SYMBOL(ip_vs_get_debug_level); #endif EXPORT_SYMBOL(ip_vs_new_conn_out); #if defined(CONFIG_IP_VS_PROTO_TCP) && defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) \ INDIRECT_CALL_2(f, tcp_snat_handler, udp_snat_handler, __VA_ARGS__) #elif defined(CONFIG_IP_VS_PROTO_TCP) #define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, tcp_snat_handler, __VA_ARGS__) #elif defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, udp_snat_handler, __VA_ARGS__) #else #define SNAT_CALL(f, ...) f(__VA_ARGS__) #endif static unsigned int ip_vs_net_id __read_mostly; /* netns cnt used for uniqueness */ static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0); /* ID used in ICMP lookups */ #define icmp_id(icmph) (((icmph)->un).echo.id) #define icmpv6_id(icmph) (icmph->icmp6_dataun.u_echo.identifier) const char *ip_vs_proto_name(unsigned int proto) { static char buf[20]; switch (proto) { case IPPROTO_IP: return "IP"; case IPPROTO_UDP: return "UDP"; case IPPROTO_TCP: return "TCP"; case IPPROTO_SCTP: return "SCTP"; case IPPROTO_ICMP: return "ICMP"; #ifdef CONFIG_IP_VS_IPV6 case IPPROTO_ICMPV6: return "ICMPv6"; #endif default: sprintf(buf, "IP_%u", proto); return buf; } } void ip_vs_init_hash_table(struct list_head *table, int rows) { while (--rows >= 0) INIT_LIST_HEAD(&table[rows]); } static inline void ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; local_bh_disable(); s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.inpkts); u64_stats_add(&s->cnt.inbytes, skb->len); u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.inpkts); u64_stats_add(&s->cnt.inbytes, skb->len); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.inpkts); u64_stats_add(&s->cnt.inbytes, skb->len); u64_stats_update_end(&s->syncp); local_bh_enable(); } } static inline void ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; local_bh_disable(); s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.outpkts); u64_stats_add(&s->cnt.outbytes, skb->len); u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.outpkts); u64_stats_add(&s->cnt.outbytes, skb->len); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.outpkts); u64_stats_add(&s->cnt.outbytes, skb->len); u64_stats_update_end(&s->syncp); local_bh_enable(); } } static inline void ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) { struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_cpu_stats *s; local_bh_disable(); s = this_cpu_ptr(cp->dest->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.conns); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.conns); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.conns); u64_stats_update_end(&s->syncp); local_bh_enable(); } static inline void ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { if (likely(pd->pp->state_transition)) pd->pp->state_transition(cp, direction, skb, pd); } static inline int ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, struct sk_buff *skb, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { ip_vs_conn_fill_param(svc->ipvs, svc->af, protocol, caddr, cport, vaddr, vport, p); p->pe = rcu_dereference(svc->pe); if (p->pe && p->pe->fill_param) return p->pe->fill_param(p, skb); return 0; } /* * IPVS persistent scheduling function * It creates a connection entry according to its template if exists, * or selects a server and creates a connection entry plus a template. * Locking: we are svc user (svc->refcnt), so we hold all dests too * Protocols supported: TCP, UDP */ static struct ip_vs_conn * ip_vs_sched_persist(struct ip_vs_service *svc, struct sk_buff *skb, __be16 src_port, __be16 dst_port, int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp = NULL; struct ip_vs_dest *dest; struct ip_vs_conn *ct; __be16 dport = 0; /* destination port to forward */ unsigned int flags; struct ip_vs_conn_param param; const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; union nf_inet_addr snet; /* source network of the client, after masking */ const union nf_inet_addr *src_addr, *dst_addr; if (likely(!ip_vs_iph_inverse(iph))) { src_addr = &iph->saddr; dst_addr = &iph->daddr; } else { src_addr = &iph->daddr; dst_addr = &iph->saddr; } /* Mask saddr with the netmask to adjust template granularity */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) ipv6_addr_prefix(&snet.in6, &src_addr->in6, (__force __u32) svc->netmask); else #endif snet.ip = src_addr->ip & svc->netmask; IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u " "mnet %s\n", IP_VS_DBG_ADDR(svc->af, src_addr), ntohs(src_port), IP_VS_DBG_ADDR(svc->af, dst_addr), ntohs(dst_port), IP_VS_DBG_ADDR(svc->af, &snet)); /* * As far as we know, FTP is a very complicated network protocol, and * it uses control connection and data connections. For active FTP, * FTP server initialize data connection to the client, its source port * is often 20. For passive FTP, FTP server tells the clients the port * that it passively listens to, and the client issues the data * connection. In the tunneling or direct routing mode, the load * balancer is on the client-to-server half of connection, the port * number is unknown to the load balancer. So, a conn template like * <caddr, 0, vaddr, 0, daddr, 0> is created for persistent FTP * service, and a template like <caddr, 0, vaddr, vport, daddr, dport> * is created for other persistent services. */ { int protocol = iph->protocol; const union nf_inet_addr *vaddr = dst_addr; __be16 vport = 0; if (dst_port == svc->port) { /* non-FTP template: * <protocol, caddr, 0, vaddr, vport, daddr, dport> * FTP template: * <protocol, caddr, 0, vaddr, 0, daddr, 0> */ if (svc->port != FTPPORT) vport = dst_port; } else { /* Note: persistent fwmark-based services and * persistent port zero service are handled here. * fwmark template: * <IPPROTO_IP,caddr,0,fwmark,0,daddr,0> * port zero template: * <protocol,caddr,0,vaddr,0,daddr,0> */ if (svc->fwmark) { protocol = IPPROTO_IP; vaddr = &fwmark; } } /* return *ignored = -1 so NF_DROP can be used */ if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, vaddr, vport, ¶m) < 0) { *ignored = -1; return NULL; } } /* Check if a template already exists */ ct = ip_vs_ct_in_get(¶m); if (!ct || !ip_vs_check_template(ct, NULL)) { struct ip_vs_scheduler *sched; /* * No template found or the dest of the connection * template is not available. * return *ignored=0 i.e. ICMP and NF_DROP */ sched = rcu_dereference(svc->scheduler); if (sched) { /* read svc->sched_data after svc->scheduler */ smp_rmb(); dest = sched->schedule(svc, skb, iph); } else { dest = NULL; } if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); *ignored = 0; return NULL; } if (dst_port == svc->port && svc->port != FTPPORT) dport = dest->port; /* Create a template * This adds param.pe_data to the template, * and thus param.pe_data will be destroyed * when the template expires */ ct = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, IP_VS_CONN_F_TEMPLATE, dest, skb->mark); if (ct == NULL) { kfree(param.pe_data); *ignored = -1; return NULL; } ct->timeout = svc->timeout; } else { /* set destination with the found template */ dest = ct->dest; kfree(param.pe_data); } dport = dst_port; if (dport == svc->port && dest->port) dport = dest->port; flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a new connection according to the template */ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, src_addr, src_port, dst_addr, dst_port, ¶m); cp = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, flags, dest, skb->mark); if (cp == NULL) { ip_vs_conn_put(ct); *ignored = -1; return NULL; } /* * Add its control */ ip_vs_control_add(cp, ct); ip_vs_conn_put(ct); ip_vs_conn_stats(cp, svc); return cp; } /* * IPVS main scheduling function * It selects a server according to the virtual service, and * creates a connection entry. * Protocols supported: TCP, UDP * * Usage of *ignored * * 1 : protocol tried to schedule (eg. on SYN), found svc but the * svc/scheduler decides that this packet should be accepted with * NF_ACCEPT because it must not be scheduled. * * 0 : scheduler can not find destination, so try bypass or * return ICMP and then NF_DROP (ip_vs_leave). * * -1 : scheduler tried to schedule but fatal error occurred, eg. * ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param * failure such as missing Call-ID, ENOMEM on skb_linearize * or pe_data. In this case we should return NF_DROP without * any attempts to send ICMP with ip_vs_leave. */ struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; struct ip_vs_conn *cp = NULL; struct ip_vs_scheduler *sched; struct ip_vs_dest *dest; __be16 _ports[2], *pptr, cport, vport; const void *caddr, *vaddr; unsigned int flags; *ignored = 1; /* * IPv6 frags, only the first hit here. */ pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (pptr == NULL) return NULL; if (likely(!ip_vs_iph_inverse(iph))) { cport = pptr[0]; caddr = &iph->saddr; vport = pptr[1]; vaddr = &iph->daddr; } else { cport = pptr[1]; caddr = &iph->daddr; vport = pptr[0]; vaddr = &iph->saddr; } /* * FTPDATA needs this check when using local real server. * Never schedule Active FTPDATA connections from real server. * For LVS-NAT they must be already created. For other methods * with persistence the connection is created on SYN+ACK. */ if (cport == FTPDATA) { IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling FTPDATA"); return NULL; } /* * Do not schedule replies from local real server. */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) { iph->hdr_flags ^= IP_VS_HDR_INVERSE; cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, svc->ipvs, svc->af, skb, iph); iph->hdr_flags ^= IP_VS_HDR_INVERSE; if (cp) { IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling reply for existing" " connection"); __ip_vs_conn_put(cp); return NULL; } } /* * Persistent service */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) return ip_vs_sched_persist(svc, skb, cport, vport, ignored, iph); *ignored = 0; /* * Non-persistent service */ if (!svc->fwmark && vport != svc->port) { if (!svc->port) pr_err("Schedule: port zero only supported " "in persistent services, " "check your ipvs configuration\n"); return NULL; } sched = rcu_dereference(svc->scheduler); if (sched) { /* read svc->sched_data after svc->scheduler */ smp_rmb(); dest = sched->schedule(svc, skb, iph); } else { dest = NULL; } if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); return NULL; } flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a connection entry. */ { struct ip_vs_conn_param p; ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, &p); cp = ip_vs_conn_new(&p, dest->af, &dest->addr, dest->port ? dest->port : vport, flags, dest, skb->mark); if (!cp) { *ignored = -1; return NULL; } } IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", ip_vs_fwd_tag(cp), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); ip_vs_conn_stats(cp, svc); return cp; } static inline int ip_vs_addr_is_unicast(struct net *net, int af, union nf_inet_addr *addr) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) return ipv6_addr_type(&addr->in6) & IPV6_ADDR_UNICAST; #endif return (inet_addr_type(net, addr->ip) == RTN_UNICAST); } /* * Pass or drop the packet. * Called by ip_vs_in, when the virtual service is available but * no destination is available for a new connection. */ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph) { __be16 _ports[2], *pptr, dport; struct netns_ipvs *ipvs = svc->ipvs; struct net *net = ipvs->net; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (!pptr) return NF_DROP; dport = likely(!ip_vs_iph_inverse(iph)) ? pptr[1] : pptr[0]; /* if it is fwmark-based service, the cache_bypass sysctl is up and the destination is a non-local unicast, then create a cache_bypass connection entry */ if (sysctl_cache_bypass(ipvs) && svc->fwmark && !(iph->hdr_flags & (IP_VS_HDR_INVERSE | IP_VS_HDR_ICMP)) && ip_vs_addr_is_unicast(net, svc->af, &iph->daddr)) { int ret; struct ip_vs_conn *cp; unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } }; /* create a new connection entry */ IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, svc->af, &daddr, 0, IP_VS_CONN_F_BYPASS | flags, NULL, skb->mark); if (!cp) return NF_DROP; } /* statistics */ ip_vs_in_stats(cp, skb); /* set state */ ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); /* transmit the first SYN packet */ ret = cp->packet_xmit(skb, cp, pd->pp, iph); /* do not touch skb anymore */ if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control) atomic_inc(&cp->control->in_pkts); else atomic_inc(&cp->in_pkts); ip_vs_conn_put(cp); return ret; } /* * When the virtual ftp service is presented, packets destined * for other services on the VIP may get here (except services * listed in the ipvs table), pass the packets, because it is * not ipvs job to decide to drop the packets. */ if (svc->port == FTPPORT && dport != FTPPORT) return NF_ACCEPT; if (unlikely(ip_vs_iph_icmp(iph))) return NF_DROP; /* * Notify the client that the destination is unreachable, and * release the socket buffer. * Since it is in IP layer, the TCP socket is not actually * created, the TCP RST packet cannot be sent, instead that * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) { if (!skb->dev) skb->dev = net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); return NF_DROP; } #ifdef CONFIG_SYSCTL static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return ipvs->sysctl_snat_reroute; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return ipvs->sysctl_nat_icmp_send; } #else static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return 0; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; } #endif __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); } static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum) { if (NF_INET_LOCAL_IN == hooknum) return IP_DEFRAG_VS_IN; if (NF_INET_FORWARD == hooknum) return IP_DEFRAG_VS_FWD; return IP_DEFRAG_VS_OUT; } static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs, struct sk_buff *skb, u_int32_t user) { int err; local_bh_disable(); err = ip_defrag(ipvs->net, skb, user); local_bh_enable(); if (!err) ip_send_check(ip_hdr(skb)); return err; } static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, unsigned int hooknum) { if (!sysctl_snat_reroute(ipvs)) return 0; /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */ if (NF_INET_LOCAL_IN == hooknum) return 0; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0) return 1; } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0) return 1; return 0; } /* * Packet has been made sufficiently writable in caller * - inout: 1=in->out, 0=out->in */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct iphdr *iph = ip_hdr(skb); unsigned int icmp_offset = iph->ihl*4; struct icmphdr *icmph = (struct icmphdr *)(skb_network_header(skb) + icmp_offset); struct iphdr *ciph = (struct iphdr *)(icmph + 1); if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); ciph->daddr = cp->vaddr.ip; ip_send_check(ciph); } else { iph->daddr = cp->daddr.ip; ip_send_check(iph); ciph->saddr = cp->daddr.ip; ip_send_check(ciph); } /* the TCP/UDP/SCTP port */ if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol || IPPROTO_SCTP == ciph->protocol) { __be16 *ports = (void *)ciph + ciph->ihl*4; if (inout) ports[1] = cp->vport; else ports[0] = cp->dport; } /* And finally the ICMP checksum */ icmph->checksum = 0; icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset); skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMP"); else IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMP"); } #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct ipv6hdr *iph = ipv6_hdr(skb); unsigned int icmp_offset = 0; unsigned int offs = 0; /* header offset*/ int protocol; struct icmp6hdr *icmph; struct ipv6hdr *ciph; unsigned short fragoffs; ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL); icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset); offs = icmp_offset + sizeof(struct icmp6hdr); ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs); protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL); if (inout) { iph->saddr = cp->vaddr.in6; ciph->daddr = cp->vaddr.in6; } else { iph->daddr = cp->daddr.in6; ciph->saddr = cp->daddr.in6; } /* the TCP/UDP/SCTP port */ if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol)) { __be16 *ports = (void *)(skb_network_header(skb) + offs); IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__, ntohs(inout ? ports[1] : ports[0]), ntohs(inout ? cp->vport : cp->dport)); if (inout) ports[1] = cp->vport; else ports[0] = cp->dport; } /* And finally the ICMP checksum */ icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, skb->len - icmp_offset, IPPROTO_ICMPV6, 0); skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset; skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum); skb->ip_summed = CHECKSUM_PARTIAL; if (inout) IP_VS_DBG_PKT(11, AF_INET6, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMPv6"); else IP_VS_DBG_PKT(11, AF_INET6, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMPv6"); } #endif /* Handle relevant response ICMP messages - forward to the right * destination host. */ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, __u8 protocol, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, unsigned int offset, unsigned int ihl, unsigned int hooknum) { unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { /* Failed checksum! */ IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n", IP_VS_DBG_ADDR(af, snet)); goto out; } if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol) offset += 2 * sizeof(__u16); if (skb_ensure_writable(skb, offset)) goto out; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_nat_icmp_v6(skb, pp, cp, 1); else #endif ip_vs_nat_icmp(skb, pp, cp, 1); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; after_nat: /* do the statistics and put it back */ ip_vs_out_stats(cp, skb); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); verdict = NF_ACCEPT; out: __ip_vs_conn_put(cp); return verdict; } /* * Handle ICMP messages in the inside-to-outside direction (outgoing). * Find any that might be relevant, check against existing connections. * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; unsigned int offset, ihl; union nf_inet_addr snet; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } iph = ip_hdr(skb); offset = ihl = iph->ihl * 4; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), &iph->saddr, &iph->daddr); /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if ((ic->type != ICMP_DEST_UNREACH) && (ic->type != ICMP_SOURCE_QUENCH) && (ic->type != ICMP_TIME_EXCEEDED)) { *related = 0; return NF_ACCEPT; } /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(cih->protocol); if (!pp) return NF_ACCEPT; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET, skb, &ciph); if (!cp) return NF_ACCEPT; snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, pp, ciph.len, ihl, hooknum); } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *ipvsh) { struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; union nf_inet_addr snet; unsigned int offset; *related = 1; ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } /* Fragment header that is before ICMP header tells us that: * it's not an error message since they can't be fragmented. */ if (ipvsh->flags & IP6_FH_F_FRAG) return NF_DROP; IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n", ic->icmp6_type, ntohs(icmpv6_id(ic)), &ipvsh->saddr, &ipvsh->daddr); if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, ipvsh->len + sizeof(_icmph), true, &ciph)) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET6, skb, &ciph); if (!cp) return NF_ACCEPT; snet.in6 = ciph.saddr.in6; offset = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, pp, offset, sizeof(struct ipv6hdr), hooknum); } #endif /* * Check if sctp chunc is ABORT chunk */ static inline int is_sctp_abort(const struct sk_buff *skb, int nh_len) { struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, nh_len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return 0; if (sch->type == SCTP_CID_ABORT) return 1; return 0; } static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len) { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, nh_len, sizeof(_tcph), &_tcph); if (th == NULL) return 0; return th->rst; } static inline bool is_new_conn(const struct sk_buff *skb, struct ip_vs_iphdr *iph) { switch (iph->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); if (th == NULL) return false; return th->syn; } case IPPROTO_SCTP: { struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, iph->len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return false; return sch->type == SCTP_CID_INIT; } default: return false; } } static inline bool is_new_conn_expected(const struct ip_vs_conn *cp, int conn_reuse_mode) { /* Controlled (FTP DATA or persistence)? */ if (cp->control) return false; switch (cp->protocol) { case IPPROTO_TCP: return (cp->state == IP_VS_TCP_S_TIME_WAIT) || (cp->state == IP_VS_TCP_S_CLOSE) || ((conn_reuse_mode & 2) && (cp->state == IP_VS_TCP_S_FIN_WAIT) && (cp->flags & IP_VS_CONN_F_NOOUTPUT)); case IPPROTO_SCTP: return cp->state == IP_VS_SCTP_S_CLOSED; default: return false; } } /* Generic function to create new connections for outgoing RS packets * * Pre-requisites for successful connection creation: * 1) Virtual Service is NOT fwmark based: * In fwmark-VS actual vaddr and vport are unknown to IPVS * 2) Real Server and Virtual Service were NOT configured without port: * This is to allow match of different VS to the same RS ip-addr */ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct sk_buff *skb, const struct ip_vs_iphdr *iph, __be16 dport, __be16 cport) { struct ip_vs_conn_param param; struct ip_vs_conn *ct = NULL, *cp = NULL; const union nf_inet_addr *vaddr, *daddr, *caddr; union nf_inet_addr snet; __be16 vport; unsigned int flags; vaddr = &svc->addr; vport = svc->port; daddr = &iph->saddr; caddr = &iph->daddr; /* check pre-requisites are satisfied */ if (svc->fwmark) return NULL; if (!vport || !dport) return NULL; /* for persistent service first create connection template */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) { /* apply netmask the same way ingress-side does */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) ipv6_addr_prefix(&snet.in6, &caddr->in6, (__force __u32)svc->netmask); else #endif snet.ip = caddr->ip & svc->netmask; /* fill params and create template if not existent */ if (ip_vs_conn_fill_param_persist(svc, skb, iph->protocol, &snet, 0, vaddr, vport, ¶m) < 0) return NULL; ct = ip_vs_ct_in_get(¶m); /* check if template exists and points to the same dest */ if (!ct || !ip_vs_check_template(ct, dest)) { ct = ip_vs_conn_new(¶m, dest->af, daddr, dport, IP_VS_CONN_F_TEMPLATE, dest, 0); if (!ct) { kfree(param.pe_data); return NULL; } ct->timeout = svc->timeout; } else { kfree(param.pe_data); } } /* connection flags */ flags = ((svc->flags & IP_VS_SVC_F_ONEPACKET) && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* create connection */ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, ¶m); cp = ip_vs_conn_new(¶m, dest->af, daddr, dport, flags, dest, 0); if (!cp) { if (ct) ip_vs_conn_put(ct); return NULL; } if (ct) { ip_vs_control_add(cp, ct); ip_vs_conn_put(ct); } ip_vs_conn_stats(cp, svc); /* return connection (will be used to handle outgoing packet) */ IP_VS_DBG_BUF(6, "New connection RS-initiated:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", ip_vs_fwd_tag(cp), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); return cp; } /* Handle outgoing packets which are considered requests initiated by * real servers, so that subsequent responses from external client can be * routed to the right real server. * Used also for outgoing responses in OPS mode. * * Connection management is handled by persistent-engine specific callback. */ static struct ip_vs_conn *__ip_vs_rs_conn_out(unsigned int hooknum, struct netns_ipvs *ipvs, int af, struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest; struct ip_vs_conn *cp = NULL; __be16 _ports[2], *pptr; if (hooknum == NF_INET_LOCAL_IN) return NULL; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (!pptr) return NULL; dest = ip_vs_find_real_service(ipvs, af, iph->protocol, &iph->saddr, pptr[0]); if (dest) { struct ip_vs_service *svc; struct ip_vs_pe *pe; svc = rcu_dereference(dest->svc); if (svc) { pe = rcu_dereference(svc->pe); if (pe && pe->conn_out) cp = pe->conn_out(svc, dest, skb, iph, pptr[0], pptr[1]); } } return cp; } /* Handle response packets: rewrite addresses and send away... */ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph, unsigned int hooknum) { struct ip_vs_protocol *pp = pd->pp; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet"); if (skb_ensure_writable(skb, iph->len)) goto drop; /* mangle the packet */ if (pp->snat_handler && !SNAT_CALL(pp->snat_handler, skb, pp, cp, iph)) goto drop; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ipv6_hdr(skb)->saddr = cp->vaddr.in6; else #endif { ip_hdr(skb)->saddr = cp->vaddr.ip; ip_send_check(ip_hdr(skb)); } /* * nf_iterate does not expect change in the skb->dst->dev. * It looks like it is not fatal to enable this code for hooks * where our handlers are at the end of the chain list and * when all next handlers use skb->dst->dev and not outdev. * It will definitely route properly the inout NAT traffic * when multiple paths are used. */ /* For policy routing, packets originating from this * machine itself may be routed differently to packets * passing through. We want this packet to be routed as * if it came from this machine itself. So re-compute * the routing information. */ if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto drop; IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT"); after_nat: ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); return NF_ACCEPT; drop: ip_vs_conn_put(cp); kfree_skb(skb); return NF_STOLEN; } /* * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct netns_ipvs *ipvs = net_ipvs(state->net); unsigned int hooknum = state->hook; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int af = state->pf; struct sock *sk; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; sk = skb_to_full_sk(skb); /* Bad... Do not break raw sockets */ if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { if (sk->sk_family == PF_INET && inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; } if (unlikely(!skb_dst(skb))) return NF_ACCEPT; if (!ipvs->enable) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_out_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) return verdict; } } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) return NF_ACCEPT; pp = pd->pp; /* reassemble IP fragments */ #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET) #endif if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; ip_vs_fill_iph_skb(AF_INET, skb, false, &iph); } /* * Check if the packet belongs to an existing entry */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); /* Check for real-server-started requests */ if (atomic_read(&ipvs->conn_out_counter)) { /* Currently only for UDP: * connection oriented protocols typically use * ephemeral ports for outgoing connections, so * related incoming responses would not match any VS */ if (pp->protocol == IPPROTO_UDP) { cp = __ip_vs_rs_conn_out(hooknum, ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); } } if (sysctl_nat_icmp_send(ipvs) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || pp->protocol == IPPROTO_SCTP)) { __be16 _ports[2], *pptr; pptr = frag_safe_skb_hp(skb, iph.len, sizeof(_ports), _ports); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ if (ip_vs_has_real_service(ipvs, af, iph.protocol, &iph.saddr, pptr[0])) { /* * Notify the real server: there is no * existing entry if it is not RST * packet or not TCP packet. */ if ((iph.protocol != IPPROTO_TCP && iph.protocol != IPPROTO_SCTP) || ((iph.protocol == IPPROTO_TCP && !is_tcp_reset(skb, iph.len)) || (iph.protocol == IPPROTO_SCTP && !is_sctp_abort(skb, iph.len)))) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (!skb->dev) skb->dev = ipvs->net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); return NF_DROP; } } } IP_VS_DBG_PKT(12, af, pp, skb, iph.off, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; } static unsigned int ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; if (!iph->fragoffs) { /* No (second) fragments need to enter here, as nf_defrag_ipv6 * replayed fragment zero will already have created the cp */ /* Schedule and create new connection entry into cpp */ if (!pp->conn_schedule(ipvs, af, skb, pd, verdict, cpp, iph)) return 0; } if (unlikely(!*cpp)) { /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, iph->off, "ip_vs_in: packet continues traversal as normal"); /* Fragment couldn't be mapped to a conn entry */ if (iph->fragoffs) IP_VS_DBG_PKT(7, af, pp, skb, iph->off, "unhandled fragment"); *verdict = NF_ACCEPT; return 0; } return 1; } /* Check the UDP tunnel and return its header length */ static int ipvs_udp_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, unsigned int offset, __u16 af, const union nf_inet_addr *daddr, __u8 *proto) { struct udphdr _udph, *udph; struct ip_vs_dest *dest; udph = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (!udph) goto unk; offset += sizeof(struct udphdr); dest = ip_vs_find_tunnel(ipvs, af, daddr, udph->dest); if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { struct guehdr _gueh, *gueh; gueh = skb_header_pointer(skb, offset, sizeof(_gueh), &_gueh); if (!gueh) goto unk; if (gueh->control != 0 || gueh->version != 0) goto unk; /* Later we can support also IPPROTO_IPV6 */ if (gueh->proto_ctype != IPPROTO_IPIP) goto unk; *proto = gueh->proto_ctype; return sizeof(struct udphdr) + sizeof(struct guehdr) + (gueh->hlen << 2); } unk: return 0; } /* Check the GRE tunnel and return its header length */ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, unsigned int offset, __u16 af, const union nf_inet_addr *daddr, __u8 *proto) { struct gre_base_hdr _greh, *greh; struct ip_vs_dest *dest; greh = skb_header_pointer(skb, offset, sizeof(_greh), &_greh); if (!greh) goto unk; dest = ip_vs_find_tunnel(ipvs, af, daddr, 0); if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { IP_TUNNEL_DECLARE_FLAGS(flags); __be16 type; /* Only support version 0 and C (csum) */ if ((greh->flags & ~GRE_CSUM) != 0) goto unk; type = greh->protocol; /* Later we can support also IPPROTO_IPV6 */ if (type != htons(ETH_P_IP)) goto unk; *proto = IPPROTO_IPIP; gre_flags_to_tnl_flags(flags, greh->flags); return gre_calc_hlen(flags); } unk: return 0; } /* * Handle ICMP messages in the outside-to-inside direction (incoming). * Find any that might be relevant, check against existing connections, * forward to the right destination host if relevant. * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, offset2, ihl, verdict; bool tunnel, new_cp = false; union nf_inet_addr *raddr; char *outer_proto = "IPIP"; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } iph = ip_hdr(skb); offset = ihl = iph->ihl * 4; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), &iph->saddr, &iph->daddr); /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if ((ic->type != ICMP_DEST_UNREACH) && (ic->type != ICMP_SOURCE_QUENCH) && (ic->type != ICMP_TIME_EXCEEDED)) { *related = 0; return NF_ACCEPT; } /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ raddr = (union nf_inet_addr *)&cih->daddr; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; if (cih->protocol == IPPROTO_IPIP) { struct ip_vs_dest *dest; if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; /* Error for our IPIP must arrive at LOCAL_IN */ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) return NF_ACCEPT; dest = ip_vs_find_tunnel(ipvs, AF_INET, raddr, 0); /* Only for known tunnel */ if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; offset += cih->ihl * 4; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ cih->protocol == IPPROTO_GRE) && /* Can be GRE encap */ /* Error for our tunnel must arrive at LOCAL_IN */ (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { __u8 iproto; int ulen; /* Non-first fragment has no UDP/GRE header */ if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; offset2 = offset + cih->ihl * 4; if (cih->protocol == IPPROTO_UDP) { ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); outer_proto = "UDP"; } else { ulen = ipvs_gre_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); outer_proto = "GRE"; } if (ulen > 0) { /* Skip IP and UDP/GRE tunnel headers */ offset = offset2 + ulen; /* Now we should be at the original IP header */ cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih && cih->version == 4 && cih->ihl >= 5 && iproto == IPPROTO_IPIP) tunnel = true; else return NF_ACCEPT; } } pd = ip_vs_proto_data_get(ipvs, cih->protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); offset2 = offset; ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); offset = ciph.len; /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, AF_INET, skb, &ciph); if (!cp) { int v; if (tunnel || !sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } verdict = NF_DROP; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { /* Failed checksum! */ IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n", &iph->saddr); goto out; } if (tunnel) { __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { struct ip_vs_dest *dest = cp->dest; u32 mtu = ntohs(ic->un.frag.mtu); __be16 frag_off = cih->frag_off; /* Strip outer IP and ICMP, go to IPIP/UDP/GRE header */ if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL) goto ignore_tunnel; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for %s %pI4->%pI4: mtu=%u\n", outer_proto, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); ipv4_update_pmtu(skb, ipvs->net, mtu, 0, 0); /* Client uses PMTUD? */ if (!(frag_off & htons(IP_DF))) goto ignore_tunnel; /* Prefer the resulting PMTU */ if (dest) { struct ip_vs_dest_dst *dest_dst; dest_dst = rcu_dereference(dest->dest_dst); if (dest_dst) mtu = dst_mtu(dest_dst->dst_cache); } if (mtu > 68 + sizeof(struct iphdr)) mtu -= sizeof(struct iphdr); info = htonl(mtu); } /* Strip outer IP, ICMP and IPIP/UDP/GRE, go to IP header of * original request. */ if (pskb_pull(skb, offset2) == NULL) goto ignore_tunnel; skb_reset_network_header(skb); IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, type, code, ntohl(info)); icmp_send(skb, type, code, info); /* ICMP can be shorter but anyways, account it */ ip_vs_out_stats(cp, skb); ignore_tunnel: consume_skb(skb); verdict = NF_STOLEN; goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol || IPPROTO_SCTP == cih->protocol) offset += 2 * sizeof(__u16); verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); out: if (likely(!new_cp)) __ip_vs_conn_put(cp); else ip_vs_conn_put(cp); return verdict; } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *iph) { struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, verdict; bool new_cp = false; *related = 1; ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } /* Fragment header that is before ICMP header tells us that: * it's not an error message since they can't be fragmented. */ if (iph->flags & IP6_FH_F_FRAG) return NF_DROP; IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n", ic->icmp6_type, ntohs(icmpv6_id(ic)), &iph->saddr, &iph->daddr); offset = iph->len + sizeof(_icmph); if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, offset, true, &ciph)) return NF_ACCEPT; pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; /* Cannot handle fragmented embedded protocol */ if (ciph.fragoffs) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, "Checking incoming ICMPv6 for"); /* The embedded headers contain source and dest in reverse order * if not from localhost */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, AF_INET6, skb, &ciph); if (!cp) { int v; if (!sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET6, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } /* VS/TUN, VS/DR and LOCALNODE just let it go */ if ((hooknum == NF_INET_LOCAL_OUT) && (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) { verdict = NF_ACCEPT; goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); /* Need to mangle contained IPv6 header in ICMPv6 packet */ offset = ciph.len; if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || IPPROTO_SCTP == ciph.protocol) offset += 2 * sizeof(__u16); /* Also mangle ports */ verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph); out: if (likely(!new_cp)) __ip_vs_conn_put(cp); else ip_vs_conn_put(cp); return verdict; } #endif /* * Check if it's for virtual services, look it up, * and send it on its way... */ static unsigned int ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct netns_ipvs *ipvs = net_ipvs(state->net); unsigned int hooknum = state->hook; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; struct sock *sk; int af = state->pf; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; /* * Big tappo: * - remote client: only PACKET_HOST * - route: used for struct net when skb->dev is unset */ if (unlikely((skb->pkt_type != PACKET_HOST && hooknum != NF_INET_LOCAL_OUT) || !skb_dst(skb))) { ip_vs_fill_iph_skb(af, skb, false, &iph); IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s" " ignored in hook %u\n", skb->pkt_type, iph.protocol, IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); /* Bad... Do not break raw sockets */ sk = skb_to_full_sk(skb); if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { if (sk->sk_family == PF_INET && inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; } #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_in_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) return verdict; } } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_in_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } /* Protocol supported? */ pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) { /* The only way we'll see this packet again is if it's * encapsulated, so mark it with ipvs_property=1 so we * skip it if we're ignoring tunneled packets */ if (sysctl_ignore_tunneled(ipvs)) skb->ipvs_property = 1; return NF_ACCEPT; } pp = pd->pp; /* * Check if the packet belongs to an existing connection entry */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, af, skb, &iph); if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); } else if (conn_reuse_mode && is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; } else { /* Do not reschedule controlling connection * that uses conntrack while it is still * referenced by controlled connection(s). */ resched = !old_ct; } } if (resched) { if (!old_ct) cp->flags &= ~IP_VS_CONN_F_NFCT; if (!atomic_read(&cp->n_control)) ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); if (old_ct) return NF_DROP; cp = NULL; } } /* Check the server status */ if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ if (sysctl_expire_nodest_conn(ipvs)) { bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!old_ct) cp->flags &= ~IP_VS_CONN_F_NFCT; ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); if (old_ct) return NF_DROP; cp = NULL; } else { __ip_vs_conn_put(cp); return NF_DROP; } } if (unlikely(!cp)) { int v; if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph)) return v; } IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); ip_vs_in_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp, &iph); /* do not touch skb anymore */ else { IP_VS_DBG_RL("warning: packet_xmit is null"); ret = NF_ACCEPT; } /* Increase its packet counter and check if it is needed * to be synchronized * * Sync connection if it is about to close to * encorage the standby servers to update the connections timeout * * For ONE_PKT let ip_vs_sync_conn() do the filter work. */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) pkts = sysctl_sync_threshold(ipvs); else pkts = atomic_inc_return(&cp->in_pkts); if (ipvs->sync_state & IP_VS_STATE_MASTER) ip_vs_sync_conn(ipvs, cp, pkts); else if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control) /* increment is done inside ip_vs_sync_conn too */ atomic_inc(&cp->control->in_pkts); ip_vs_conn_put(cp); return ret; } /* * It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP * related packets destined for 0.0.0.0/0. * When fwmark-based virtual service is used, such as transparent * cache cluster, TCP packets can be marked and routed to ip_vs_in, * but ICMP destined for 0.0.0.0/0 cannot not be easily marked and * sent to ip_vs_in_icmp. So, catch them at the NF_INET_FORWARD chain * and send them to ip_vs_in_icmp. */ static unsigned int ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct netns_ipvs *ipvs = net_ipvs(state->net); int r; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; if (state->pf == NFPROTO_IPV4) { if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; #ifdef CONFIG_IP_VS_IPV6 } else { struct ip_vs_iphdr iphdr; ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); if (iphdr.protocol != IPPROTO_ICMPV6) return NF_ACCEPT; return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); #endif } return ip_vs_in_icmp(ipvs, skb, &r, state->hook); } static const struct nf_hook_ops ip_vs_ops4[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { .hook = ip_vs_in_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { .hook = ip_vs_in_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 100, }, }; #ifdef CONFIG_IP_VS_IPV6 static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { .hook = ip_vs_in_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { .hook = ip_vs_in_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 100, }, }; #endif int ip_vs_register_hooks(struct netns_ipvs *ipvs, unsigned int af) { const struct nf_hook_ops *ops; unsigned int count; unsigned int afmask; int ret = 0; if (af == AF_INET6) { #ifdef CONFIG_IP_VS_IPV6 ops = ip_vs_ops6; count = ARRAY_SIZE(ip_vs_ops6); afmask = 2; #else return -EINVAL; #endif } else { ops = ip_vs_ops4; count = ARRAY_SIZE(ip_vs_ops4); afmask = 1; } if (!(ipvs->hooks_afmask & afmask)) { ret = nf_register_net_hooks(ipvs->net, ops, count); if (ret >= 0) ipvs->hooks_afmask |= afmask; } return ret; } void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af) { const struct nf_hook_ops *ops; unsigned int count; unsigned int afmask; if (af == AF_INET6) { #ifdef CONFIG_IP_VS_IPV6 ops = ip_vs_ops6; count = ARRAY_SIZE(ip_vs_ops6); afmask = 2; #else return; #endif } else { ops = ip_vs_ops4; count = ARRAY_SIZE(ip_vs_ops4); afmask = 1; } if (ipvs->hooks_afmask & afmask) { nf_unregister_net_hooks(ipvs->net, ops, count); ipvs->hooks_afmask &= ~afmask; } } /* * Initialize IP Virtual Server netns mem. */ static int __net_init __ip_vs_init(struct net *net) { struct netns_ipvs *ipvs; ipvs = net_generic(net, ip_vs_net_id); if (ipvs == NULL) return -ENOMEM; /* Hold the beast until a service is registered */ ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; if (ip_vs_estimator_net_init(ipvs) < 0) goto estimator_fail; if (ip_vs_control_net_init(ipvs) < 0) goto control_fail; if (ip_vs_protocol_net_init(ipvs) < 0) goto protocol_fail; if (ip_vs_app_net_init(ipvs) < 0) goto app_fail; if (ip_vs_conn_net_init(ipvs) < 0) goto conn_fail; if (ip_vs_sync_net_init(ipvs) < 0) goto sync_fail; return 0; /* * Error handling */ sync_fail: ip_vs_conn_net_cleanup(ipvs); conn_fail: ip_vs_app_net_cleanup(ipvs); app_fail: ip_vs_protocol_net_cleanup(ipvs); protocol_fail: ip_vs_control_net_cleanup(ipvs); control_fail: ip_vs_estimator_net_cleanup(ipvs); estimator_fail: net->ipvs = NULL; return -ENOMEM; } static void __net_exit __ip_vs_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; ip_vs_service_nets_cleanup(net_list); /* ip_vs_flush() with locks */ list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_conn_net_cleanup(ipvs); ip_vs_app_net_cleanup(ipvs); ip_vs_protocol_net_cleanup(ipvs); ip_vs_control_net_cleanup(ipvs); ip_vs_estimator_net_cleanup(ipvs); IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen); net->ipvs = NULL; } } static void __net_exit __ip_vs_dev_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_unregister_hooks(ipvs, AF_INET); ip_vs_unregister_hooks(ipvs, AF_INET6); ipvs->enable = 0; /* Disable packet reception */ smp_wmb(); ip_vs_sync_net_cleanup(ipvs); } } static struct pernet_operations ipvs_core_ops = { .init = __ip_vs_init, .exit_batch = __ip_vs_cleanup_batch, .id = &ip_vs_net_id, .size = sizeof(struct netns_ipvs), }; static struct pernet_operations ipvs_core_dev_ops = { .exit_batch = __ip_vs_dev_cleanup_batch, }; /* * Initialize IP Virtual Server */ static int __init ip_vs_init(void) { int ret; ret = ip_vs_control_init(); if (ret < 0) { pr_err("can't setup control.\n"); goto exit; } ip_vs_protocol_init(); ret = ip_vs_conn_init(); if (ret < 0) { pr_err("can't setup connection table.\n"); goto cleanup_protocol; } ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ if (ret < 0) goto cleanup_conn; ret = register_pernet_device(&ipvs_core_dev_ops); if (ret < 0) goto cleanup_sub; ret = ip_vs_register_nl_ioctl(); if (ret < 0) { pr_err("can't register netlink/ioctl.\n"); goto cleanup_dev; } pr_info("ipvs loaded.\n"); return ret; cleanup_dev: unregister_pernet_device(&ipvs_core_dev_ops); cleanup_sub: unregister_pernet_subsys(&ipvs_core_ops); cleanup_conn: ip_vs_conn_cleanup(); cleanup_protocol: ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); exit: return ret; } static void __exit ip_vs_cleanup(void) { ip_vs_unregister_nl_ioctl(); unregister_pernet_device(&ipvs_core_dev_ops); unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_conn_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); /* common rcu_barrier() used by: * - ip_vs_control_cleanup() */ rcu_barrier(); pr_info("ipvs unloaded.\n"); } module_init(ip_vs_init); module_exit(ip_vs_cleanup); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IP Virtual Server"); |
| 11 4 4 4 2 17 17 17 6 6 3 11 15 16 15 15 15 4 1 1 3 3 3 3 3 3 3 3 3 3 1 1 1 2 2 2 1 1 1 1 1 2 1 24 2 2 1 10 7 3 10 10 13 7 7 14 14 14 7 7 7 7 14 46 1 1 1 2 18 2 34 1 24 26 9 17 2 28 29 10 33 19 17 13 3 2 14 14 65 65 3 11 11 11 1 11 12 11 1 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 | // SPDX-License-Identifier: GPL-2.0 /* * device_cgroup.c - device cgroup subsystem * * Copyright 2007 IBM Corp */ #include <linux/bpf-cgroup.h> #include <linux/device_cgroup.h> #include <linux/cgroup.h> #include <linux/ctype.h> #include <linux/list.h> #include <linux/uaccess.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/mutex.h> #ifdef CONFIG_CGROUP_DEVICE static DEFINE_MUTEX(devcgroup_mutex); enum devcg_behavior { DEVCG_DEFAULT_NONE, DEVCG_DEFAULT_ALLOW, DEVCG_DEFAULT_DENY, }; /* * exception list locking rules: * hold devcgroup_mutex for update/read. * hold rcu_read_lock() for read. */ struct dev_exception_item { u32 major, minor; short type; short access; struct list_head list; struct rcu_head rcu; }; struct dev_cgroup { struct cgroup_subsys_state css; struct list_head exceptions; enum devcg_behavior behavior; }; static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s) { return s ? container_of(s, struct dev_cgroup, css) : NULL; } static inline struct dev_cgroup *task_devcgroup(struct task_struct *task) { return css_to_devcgroup(task_css(task, devices_cgrp_id)); } /* * called under devcgroup_mutex */ static int dev_exceptions_copy(struct list_head *dest, struct list_head *orig) { struct dev_exception_item *ex, *tmp, *new; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry(ex, orig, list) { new = kmemdup(ex, sizeof(*ex), GFP_KERNEL); if (!new) goto free_and_exit; list_add_tail(&new->list, dest); } return 0; free_and_exit: list_for_each_entry_safe(ex, tmp, dest, list) { list_del(&ex->list); kfree(ex); } return -ENOMEM; } static void dev_exceptions_move(struct list_head *dest, struct list_head *orig) { struct dev_exception_item *ex, *tmp; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry_safe(ex, tmp, orig, list) { list_move_tail(&ex->list, dest); } } /* * called under devcgroup_mutex */ static int dev_exception_add(struct dev_cgroup *dev_cgroup, struct dev_exception_item *ex) { struct dev_exception_item *excopy, *walk; lockdep_assert_held(&devcgroup_mutex); excopy = kmemdup(ex, sizeof(*ex), GFP_KERNEL); if (!excopy) return -ENOMEM; list_for_each_entry(walk, &dev_cgroup->exceptions, list) { if (walk->type != ex->type) continue; if (walk->major != ex->major) continue; if (walk->minor != ex->minor) continue; walk->access |= ex->access; kfree(excopy); excopy = NULL; } if (excopy != NULL) list_add_tail_rcu(&excopy->list, &dev_cgroup->exceptions); return 0; } /* * called under devcgroup_mutex */ static void dev_exception_rm(struct dev_cgroup *dev_cgroup, struct dev_exception_item *ex) { struct dev_exception_item *walk, *tmp; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry_safe(walk, tmp, &dev_cgroup->exceptions, list) { if (walk->type != ex->type) continue; if (walk->major != ex->major) continue; if (walk->minor != ex->minor) continue; walk->access &= ~ex->access; if (!walk->access) { list_del_rcu(&walk->list); kfree_rcu(walk, rcu); } } } static void __dev_exception_clean(struct dev_cgroup *dev_cgroup) { struct dev_exception_item *ex, *tmp; list_for_each_entry_safe(ex, tmp, &dev_cgroup->exceptions, list) { list_del_rcu(&ex->list); kfree_rcu(ex, rcu); } } /** * dev_exception_clean - frees all entries of the exception list * @dev_cgroup: dev_cgroup with the exception list to be cleaned * * called under devcgroup_mutex */ static void dev_exception_clean(struct dev_cgroup *dev_cgroup) { lockdep_assert_held(&devcgroup_mutex); __dev_exception_clean(dev_cgroup); } static inline bool is_devcg_online(const struct dev_cgroup *devcg) { return (devcg->behavior != DEVCG_DEFAULT_NONE); } /** * devcgroup_online - initializes devcgroup's behavior and exceptions based on * parent's * @css: css getting online * returns 0 in case of success, error code otherwise */ static int devcgroup_online(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css->parent); int ret = 0; mutex_lock(&devcgroup_mutex); if (parent_dev_cgroup == NULL) dev_cgroup->behavior = DEVCG_DEFAULT_ALLOW; else { ret = dev_exceptions_copy(&dev_cgroup->exceptions, &parent_dev_cgroup->exceptions); if (!ret) dev_cgroup->behavior = parent_dev_cgroup->behavior; } mutex_unlock(&devcgroup_mutex); return ret; } static void devcgroup_offline(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); mutex_lock(&devcgroup_mutex); dev_cgroup->behavior = DEVCG_DEFAULT_NONE; mutex_unlock(&devcgroup_mutex); } /* * called from kernel/cgroup/cgroup.c with cgroup_lock() held. */ static struct cgroup_subsys_state * devcgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct dev_cgroup *dev_cgroup; dev_cgroup = kzalloc(sizeof(*dev_cgroup), GFP_KERNEL); if (!dev_cgroup) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&dev_cgroup->exceptions); dev_cgroup->behavior = DEVCG_DEFAULT_NONE; return &dev_cgroup->css; } static void devcgroup_css_free(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); __dev_exception_clean(dev_cgroup); kfree(dev_cgroup); } #define DEVCG_ALLOW 1 #define DEVCG_DENY 2 #define DEVCG_LIST 3 #define MAJMINLEN 13 #define ACCLEN 4 static void set_access(char *acc, short access) { int idx = 0; memset(acc, 0, ACCLEN); if (access & DEVCG_ACC_READ) acc[idx++] = 'r'; if (access & DEVCG_ACC_WRITE) acc[idx++] = 'w'; if (access & DEVCG_ACC_MKNOD) acc[idx++] = 'm'; } static char type_to_char(short type) { if (type == DEVCG_DEV_ALL) return 'a'; if (type == DEVCG_DEV_CHAR) return 'c'; if (type == DEVCG_DEV_BLOCK) return 'b'; return 'X'; } static void set_majmin(char *str, unsigned m) { if (m == ~0) strcpy(str, "*"); else sprintf(str, "%u", m); } static int devcgroup_seq_show(struct seq_file *m, void *v) { struct dev_cgroup *devcgroup = css_to_devcgroup(seq_css(m)); struct dev_exception_item *ex; char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN]; rcu_read_lock(); /* * To preserve the compatibility: * - Only show the "all devices" when the default policy is to allow * - List the exceptions in case the default policy is to deny * This way, the file remains as a "whitelist of devices" */ if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) { set_access(acc, DEVCG_ACC_MASK); set_majmin(maj, ~0); set_majmin(min, ~0); seq_printf(m, "%c %s:%s %s\n", type_to_char(DEVCG_DEV_ALL), maj, min, acc); } else { list_for_each_entry_rcu(ex, &devcgroup->exceptions, list) { set_access(acc, ex->access); set_majmin(maj, ex->major); set_majmin(min, ex->minor); seq_printf(m, "%c %s:%s %s\n", type_to_char(ex->type), maj, min, acc); } } rcu_read_unlock(); return 0; } /** * match_exception - iterates the exception list trying to find a complete match * @exceptions: list of exceptions * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR) * @major: device file major number, ~0 to match all * @minor: device file minor number, ~0 to match all * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD) * * It is considered a complete match if an exception is found that will * contain the entire range of provided parameters. * * Return: true in case it matches an exception completely */ static bool match_exception(struct list_head *exceptions, short type, u32 major, u32 minor, short access) { struct dev_exception_item *ex; list_for_each_entry_rcu(ex, exceptions, list) { if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK)) continue; if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR)) continue; if (ex->major != ~0 && ex->major != major) continue; if (ex->minor != ~0 && ex->minor != minor) continue; /* provided access cannot have more than the exception rule */ if (access & (~ex->access)) continue; return true; } return false; } /** * match_exception_partial - iterates the exception list trying to find a partial match * @exceptions: list of exceptions * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR) * @major: device file major number, ~0 to match all * @minor: device file minor number, ~0 to match all * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD) * * It is considered a partial match if an exception's range is found to * contain *any* of the devices specified by provided parameters. This is * used to make sure no extra access is being granted that is forbidden by * any of the exception list. * * Return: true in case the provided range mat matches an exception completely */ static bool match_exception_partial(struct list_head *exceptions, short type, u32 major, u32 minor, short access) { struct dev_exception_item *ex; list_for_each_entry_rcu(ex, exceptions, list, lockdep_is_held(&devcgroup_mutex)) { if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK)) continue; if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR)) continue; /* * We must be sure that both the exception and the provided * range aren't masking all devices */ if (ex->major != ~0 && major != ~0 && ex->major != major) continue; if (ex->minor != ~0 && minor != ~0 && ex->minor != minor) continue; /* * In order to make sure the provided range isn't matching * an exception, all its access bits shouldn't match the * exception's access bits */ if (!(access & ex->access)) continue; return true; } return false; } /** * verify_new_ex - verifies if a new exception is allowed by parent cgroup's permissions * @dev_cgroup: dev cgroup to be tested against * @refex: new exception * @behavior: behavior of the exception's dev_cgroup * * This is used to make sure a child cgroup won't have more privileges * than its parent */ static bool verify_new_ex(struct dev_cgroup *dev_cgroup, struct dev_exception_item *refex, enum devcg_behavior behavior) { bool match = false; RCU_LOCKDEP_WARN(!rcu_read_lock_held() && !lockdep_is_held(&devcgroup_mutex), "device_cgroup:verify_new_ex called without proper synchronization"); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) { if (behavior == DEVCG_DEFAULT_ALLOW) { /* * new exception in the child doesn't matter, only * adding extra restrictions */ return true; } else { /* * new exception in the child will add more devices * that can be accessed, so it can't match any of * parent's exceptions, even slightly */ match = match_exception_partial(&dev_cgroup->exceptions, refex->type, refex->major, refex->minor, refex->access); if (match) return false; return true; } } else { /* * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore * the new exception will add access to more devices and must * be contained completely in an parent's exception to be * allowed */ match = match_exception(&dev_cgroup->exceptions, refex->type, refex->major, refex->minor, refex->access); if (match) /* parent has an exception that matches the proposed */ return true; else return false; } return false; } /* * parent_has_perm: * when adding a new allow rule to a device exception list, the rule * must be allowed in the parent device */ static int parent_has_perm(struct dev_cgroup *childcg, struct dev_exception_item *ex) { struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent); if (!parent) return 1; return verify_new_ex(parent, ex, childcg->behavior); } /** * parent_allows_removal - verify if it's ok to remove an exception * @childcg: child cgroup from where the exception will be removed * @ex: exception being removed * * When removing an exception in cgroups with default ALLOW policy, it must * be checked if removing it will give the child cgroup more access than the * parent. * * Return: true if it's ok to remove exception, false otherwise */ static bool parent_allows_removal(struct dev_cgroup *childcg, struct dev_exception_item *ex) { struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent); if (!parent) return true; /* It's always allowed to remove access to devices */ if (childcg->behavior == DEVCG_DEFAULT_DENY) return true; /* * Make sure you're not removing part or a whole exception existing in * the parent cgroup */ return !match_exception_partial(&parent->exceptions, ex->type, ex->major, ex->minor, ex->access); } /** * may_allow_all - checks if it's possible to change the behavior to * allow based on parent's rules. * @parent: device cgroup's parent * returns: != 0 in case it's allowed, 0 otherwise */ static inline int may_allow_all(struct dev_cgroup *parent) { if (!parent) return 1; return parent->behavior == DEVCG_DEFAULT_ALLOW; } /** * revalidate_active_exceptions - walks through the active exception list and * revalidates the exceptions based on parent's * behavior and exceptions. The exceptions that * are no longer valid will be removed. * Called with devcgroup_mutex held. * @devcg: cgroup which exceptions will be checked * * This is one of the three key functions for hierarchy implementation. * This function is responsible for re-evaluating all the cgroup's active * exceptions due to a parent's exception change. * Refer to Documentation/admin-guide/cgroup-v1/devices.rst for more details. */ static void revalidate_active_exceptions(struct dev_cgroup *devcg) { struct dev_exception_item *ex; struct list_head *this, *tmp; list_for_each_safe(this, tmp, &devcg->exceptions) { ex = container_of(this, struct dev_exception_item, list); if (!parent_has_perm(devcg, ex)) dev_exception_rm(devcg, ex); } } /** * propagate_exception - propagates a new exception to the children * @devcg_root: device cgroup that added a new exception * @ex: new exception to be propagated * * returns: 0 in case of success, != 0 in case of error */ static int propagate_exception(struct dev_cgroup *devcg_root, struct dev_exception_item *ex) { struct cgroup_subsys_state *pos; int rc = 0; rcu_read_lock(); css_for_each_descendant_pre(pos, &devcg_root->css) { struct dev_cgroup *devcg = css_to_devcgroup(pos); /* * Because devcgroup_mutex is held, no devcg will become * online or offline during the tree walk (see on/offline * methods), and online ones are safe to access outside RCU * read lock without bumping refcnt. */ if (pos == &devcg_root->css || !is_devcg_online(devcg)) continue; rcu_read_unlock(); /* * in case both root's behavior and devcg is allow, a new * restriction means adding to the exception list */ if (devcg_root->behavior == DEVCG_DEFAULT_ALLOW && devcg->behavior == DEVCG_DEFAULT_ALLOW) { rc = dev_exception_add(devcg, ex); if (rc) return rc; } else { /* * in the other possible cases: * root's behavior: allow, devcg's: deny * root's behavior: deny, devcg's: deny * the exception will be removed */ dev_exception_rm(devcg, ex); } revalidate_active_exceptions(devcg); rcu_read_lock(); } rcu_read_unlock(); return rc; } /* * Modify the exception list using allow/deny rules. * CAP_SYS_ADMIN is needed for this. It's at least separate from CAP_MKNOD * so we can give a container CAP_MKNOD to let it create devices but not * modify the exception list. * It seems likely we'll want to add a CAP_CONTAINER capability to allow * us to also grant CAP_SYS_ADMIN to containers without giving away the * device exception list controls, but for now we'll stick with CAP_SYS_ADMIN * * Taking rules away is always allowed (given CAP_SYS_ADMIN). Granting * new access is only allowed if you're in the top-level cgroup, or your * parent cgroup has the access you're asking for. */ static int devcgroup_update_access(struct dev_cgroup *devcgroup, int filetype, char *buffer) { const char *b; char temp[12]; /* 11 + 1 characters needed for a u32 */ int count, rc = 0; struct dev_exception_item ex; struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent); struct dev_cgroup tmp_devcgrp; if (!capable(CAP_SYS_ADMIN)) return -EPERM; memset(&ex, 0, sizeof(ex)); memset(&tmp_devcgrp, 0, sizeof(tmp_devcgrp)); b = buffer; switch (*b) { case 'a': switch (filetype) { case DEVCG_ALLOW: if (css_has_online_children(&devcgroup->css)) return -EINVAL; if (!may_allow_all(parent)) return -EPERM; if (!parent) { devcgroup->behavior = DEVCG_DEFAULT_ALLOW; dev_exception_clean(devcgroup); break; } INIT_LIST_HEAD(&tmp_devcgrp.exceptions); rc = dev_exceptions_copy(&tmp_devcgrp.exceptions, &devcgroup->exceptions); if (rc) return rc; dev_exception_clean(devcgroup); rc = dev_exceptions_copy(&devcgroup->exceptions, &parent->exceptions); if (rc) { dev_exceptions_move(&devcgroup->exceptions, &tmp_devcgrp.exceptions); return rc; } devcgroup->behavior = DEVCG_DEFAULT_ALLOW; dev_exception_clean(&tmp_devcgrp); break; case DEVCG_DENY: if (css_has_online_children(&devcgroup->css)) return -EINVAL; dev_exception_clean(devcgroup); devcgroup->behavior = DEVCG_DEFAULT_DENY; break; default: return -EINVAL; } return 0; case 'b': ex.type = DEVCG_DEV_BLOCK; break; case 'c': ex.type = DEVCG_DEV_CHAR; break; default: return -EINVAL; } b++; if (!isspace(*b)) return -EINVAL; b++; if (*b == '*') { ex.major = ~0; b++; } else if (isdigit(*b)) { memset(temp, 0, sizeof(temp)); for (count = 0; count < sizeof(temp) - 1; count++) { temp[count] = *b; b++; if (!isdigit(*b)) break; } rc = kstrtou32(temp, 10, &ex.major); if (rc) return -EINVAL; } else { return -EINVAL; } if (*b != ':') return -EINVAL; b++; /* read minor */ if (*b == '*') { ex.minor = ~0; b++; } else if (isdigit(*b)) { memset(temp, 0, sizeof(temp)); for (count = 0; count < sizeof(temp) - 1; count++) { temp[count] = *b; b++; if (!isdigit(*b)) break; } rc = kstrtou32(temp, 10, &ex.minor); if (rc) return -EINVAL; } else { return -EINVAL; } if (!isspace(*b)) return -EINVAL; for (b++, count = 0; count < 3; count++, b++) { switch (*b) { case 'r': ex.access |= DEVCG_ACC_READ; break; case 'w': ex.access |= DEVCG_ACC_WRITE; break; case 'm': ex.access |= DEVCG_ACC_MKNOD; break; case '\n': case '\0': count = 3; break; default: return -EINVAL; } } switch (filetype) { case DEVCG_ALLOW: /* * If the default policy is to allow by default, try to remove * an matching exception instead. And be silent about it: we * don't want to break compatibility */ if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) { /* Check if the parent allows removing it first */ if (!parent_allows_removal(devcgroup, &ex)) return -EPERM; dev_exception_rm(devcgroup, &ex); break; } if (!parent_has_perm(devcgroup, &ex)) return -EPERM; rc = dev_exception_add(devcgroup, &ex); break; case DEVCG_DENY: /* * If the default policy is to deny by default, try to remove * an matching exception instead. And be silent about it: we * don't want to break compatibility */ if (devcgroup->behavior == DEVCG_DEFAULT_DENY) dev_exception_rm(devcgroup, &ex); else rc = dev_exception_add(devcgroup, &ex); if (rc) break; /* we only propagate new restrictions */ rc = propagate_exception(devcgroup, &ex); break; default: rc = -EINVAL; } return rc; } static ssize_t devcgroup_access_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { int retval; mutex_lock(&devcgroup_mutex); retval = devcgroup_update_access(css_to_devcgroup(of_css(of)), of_cft(of)->private, strstrip(buf)); mutex_unlock(&devcgroup_mutex); return retval ?: nbytes; } static struct cftype dev_cgroup_files[] = { { .name = "allow", .write = devcgroup_access_write, .private = DEVCG_ALLOW, }, { .name = "deny", .write = devcgroup_access_write, .private = DEVCG_DENY, }, { .name = "list", .seq_show = devcgroup_seq_show, .private = DEVCG_LIST, }, { } /* terminate */ }; struct cgroup_subsys devices_cgrp_subsys = { .css_alloc = devcgroup_css_alloc, .css_free = devcgroup_css_free, .css_online = devcgroup_online, .css_offline = devcgroup_offline, .legacy_cftypes = dev_cgroup_files, }; /** * devcgroup_legacy_check_permission - checks if an inode operation is permitted * @type: device type * @major: device major number * @minor: device minor number * @access: combination of DEVCG_ACC_WRITE, DEVCG_ACC_READ and DEVCG_ACC_MKNOD * * returns 0 on success, -EPERM case the operation is not permitted */ static int devcgroup_legacy_check_permission(short type, u32 major, u32 minor, short access) { struct dev_cgroup *dev_cgroup; bool rc; rcu_read_lock(); dev_cgroup = task_devcgroup(current); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) /* Can't match any of the exceptions, even partially */ rc = !match_exception_partial(&dev_cgroup->exceptions, type, major, minor, access); else /* Need to match completely one exception to be allowed */ rc = match_exception(&dev_cgroup->exceptions, type, major, minor, access); rcu_read_unlock(); if (!rc) return -EPERM; return 0; } #endif /* CONFIG_CGROUP_DEVICE */ #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) int devcgroup_check_permission(short type, u32 major, u32 minor, short access) { int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); if (rc) return rc; #ifdef CONFIG_CGROUP_DEVICE return devcgroup_legacy_check_permission(type, major, minor, access); #else /* CONFIG_CGROUP_DEVICE */ return 0; #endif /* CONFIG_CGROUP_DEVICE */ } EXPORT_SYMBOL(devcgroup_check_permission); #endif /* defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) */ |
| 1 2 3 5 3 5 4 4 5 3 4 2 2 4 4 2 3 5 4 4 4 2 5 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * TCP Westwood+: end-to-end bandwidth estimation for TCP * * Angelo Dell'Aera: author of the first version of TCP Westwood+ in Linux 2.4 * * Support at http://c3lab.poliba.it/index.php/Westwood * Main references in literature: * * - Mascolo S, Casetti, M. Gerla et al. * "TCP Westwood: bandwidth estimation for TCP" Proc. ACM Mobicom 2001 * * - A. Grieco, s. Mascolo * "Performance evaluation of New Reno, Vegas, Westwood+ TCP" ACM Computer * Comm. Review, 2004 * * - A. Dell'Aera, L. Grieco, S. Mascolo. * "Linux 2.4 Implementation of Westwood+ TCP with Rate-Halving : * A Performance Evaluation Over the Internet" (ICC 2004), Paris, June 2004 * * Westwood+ employs end-to-end bandwidth measurement to set cwnd and * ssthresh after packet loss. The probing phase is as the original Reno. */ #include <linux/mm.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/inet_diag.h> #include <net/tcp.h> /* TCP Westwood structure */ struct westwood { u32 bw_ns_est; /* first bandwidth estimation..not too smoothed 8) */ u32 bw_est; /* bandwidth estimate */ u32 rtt_win_sx; /* here starts a new evaluation... */ u32 bk; u32 snd_una; /* used for evaluating the number of acked bytes */ u32 cumul_ack; u32 accounted; u32 rtt; u32 rtt_min; /* minimum observed RTT */ u8 first_ack; /* flag which infers that this is the first ack */ u8 reset_rtt_min; /* Reset RTT min to next RTT sample*/ }; /* TCP Westwood functions and constants */ #define TCP_WESTWOOD_RTT_MIN (HZ/20) /* 50ms */ #define TCP_WESTWOOD_INIT_RTT (20*HZ) /* maybe too conservative?! */ /* * @tcp_westwood_create * This function initializes fields used in TCP Westwood+, * it is called after the initial SYN, so the sequence numbers * are correct but new passive connections we have no * information about RTTmin at this time so we simply set it to * TCP_WESTWOOD_INIT_RTT. This value was chosen to be too conservative * since in this way we're sure it will be updated in a consistent * way as soon as possible. It will reasonably happen within the first * RTT period of the connection lifetime. */ static void tcp_westwood_init(struct sock *sk) { struct westwood *w = inet_csk_ca(sk); w->bk = 0; w->bw_ns_est = 0; w->bw_est = 0; w->accounted = 0; w->cumul_ack = 0; w->reset_rtt_min = 1; w->rtt_min = w->rtt = TCP_WESTWOOD_INIT_RTT; w->rtt_win_sx = tcp_jiffies32; w->snd_una = tcp_sk(sk)->snd_una; w->first_ack = 1; } /* * @westwood_do_filter * Low-pass filter. Implemented using constant coefficients. */ static inline u32 westwood_do_filter(u32 a, u32 b) { return ((7 * a) + b) >> 3; } static void westwood_filter(struct westwood *w, u32 delta) { /* If the filter is empty fill it with the first sample of bandwidth */ if (w->bw_ns_est == 0 && w->bw_est == 0) { w->bw_ns_est = w->bk / delta; w->bw_est = w->bw_ns_est; } else { w->bw_ns_est = westwood_do_filter(w->bw_ns_est, w->bk / delta); w->bw_est = westwood_do_filter(w->bw_est, w->bw_ns_est); } } /* * @westwood_pkts_acked * Called after processing group of packets. * but all westwood needs is the last sample of srtt. */ static void tcp_westwood_pkts_acked(struct sock *sk, const struct ack_sample *sample) { struct westwood *w = inet_csk_ca(sk); if (sample->rtt_us > 0) w->rtt = usecs_to_jiffies(sample->rtt_us); } /* * @westwood_update_window * It updates RTT evaluation window if it is the right moment to do * it. If so it calls filter for evaluating bandwidth. */ static void westwood_update_window(struct sock *sk) { struct westwood *w = inet_csk_ca(sk); s32 delta = tcp_jiffies32 - w->rtt_win_sx; /* Initialize w->snd_una with the first acked sequence number in order * to fix mismatch between tp->snd_una and w->snd_una for the first * bandwidth sample */ if (w->first_ack) { w->snd_una = tcp_sk(sk)->snd_una; w->first_ack = 0; } /* * See if a RTT-window has passed. * Be careful since if RTT is less than * 50ms we don't filter but we continue 'building the sample'. * This minimum limit was chosen since an estimation on small * time intervals is better to avoid... * Obviously on a LAN we reasonably will always have * right_bound = left_bound + WESTWOOD_RTT_MIN */ if (w->rtt && delta > max_t(u32, w->rtt, TCP_WESTWOOD_RTT_MIN)) { westwood_filter(w, delta); w->bk = 0; w->rtt_win_sx = tcp_jiffies32; } } static inline void update_rtt_min(struct westwood *w) { if (w->reset_rtt_min) { w->rtt_min = w->rtt; w->reset_rtt_min = 0; } else w->rtt_min = min(w->rtt, w->rtt_min); } /* * @westwood_fast_bw * It is called when we are in fast path. In particular it is called when * header prediction is successful. In such case in fact update is * straight forward and doesn't need any particular care. */ static inline void westwood_fast_bw(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct westwood *w = inet_csk_ca(sk); westwood_update_window(sk); w->bk += tp->snd_una - w->snd_una; w->snd_una = tp->snd_una; update_rtt_min(w); } /* * @westwood_acked_count * This function evaluates cumul_ack for evaluating bk in case of * delayed or partial acks. */ static inline u32 westwood_acked_count(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct westwood *w = inet_csk_ca(sk); w->cumul_ack = tp->snd_una - w->snd_una; /* If cumul_ack is 0 this is a dupack since it's not moving * tp->snd_una. */ if (!w->cumul_ack) { w->accounted += tp->mss_cache; w->cumul_ack = tp->mss_cache; } if (w->cumul_ack > tp->mss_cache) { /* Partial or delayed ack */ if (w->accounted >= w->cumul_ack) { w->accounted -= w->cumul_ack; w->cumul_ack = tp->mss_cache; } else { w->cumul_ack -= w->accounted; w->accounted = 0; } } w->snd_una = tp->snd_una; return w->cumul_ack; } /* * TCP Westwood * Here limit is evaluated as Bw estimation*RTTmin (for obtaining it * in packets we use mss_cache). Rttmin is guaranteed to be >= 2 * so avoids ever returning 0. */ static u32 tcp_westwood_bw_rttmin(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); const struct westwood *w = inet_csk_ca(sk); return max_t(u32, (w->bw_est * w->rtt_min) / tp->mss_cache, 2); } static void tcp_westwood_ack(struct sock *sk, u32 ack_flags) { if (ack_flags & CA_ACK_SLOWPATH) { struct westwood *w = inet_csk_ca(sk); westwood_update_window(sk); w->bk += westwood_acked_count(sk); update_rtt_min(w); return; } westwood_fast_bw(sk); } static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event) { struct tcp_sock *tp = tcp_sk(sk); struct westwood *w = inet_csk_ca(sk); switch (event) { case CA_EVENT_COMPLETE_CWR: tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk); tcp_snd_cwnd_set(tp, tp->snd_ssthresh); break; case CA_EVENT_LOSS: tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk); /* Update RTT_min when next ack arrives */ w->reset_rtt_min = 1; break; default: /* don't care */ break; } } /* Extract info for Tcp socket info provided via netlink. */ static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { const struct westwood *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { info->vegas.tcpv_enabled = 1; info->vegas.tcpv_rttcnt = 0; info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt); info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min); *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); } return 0; } static struct tcp_congestion_ops tcp_westwood __read_mostly = { .init = tcp_westwood_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, .undo_cwnd = tcp_reno_undo_cwnd, .cwnd_event = tcp_westwood_event, .in_ack_event = tcp_westwood_ack, .get_info = tcp_westwood_info, .pkts_acked = tcp_westwood_pkts_acked, .owner = THIS_MODULE, .name = "westwood" }; static int __init tcp_westwood_register(void) { BUILD_BUG_ON(sizeof(struct westwood) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcp_westwood); } static void __exit tcp_westwood_unregister(void) { tcp_unregister_congestion_control(&tcp_westwood); } module_init(tcp_westwood_register); module_exit(tcp_westwood_unregister); MODULE_AUTHOR("Stephen Hemminger, Angelo Dell'Aera"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("TCP Westwood+"); |
| 25 2 23 23 23 23 23 23 23 23 22 23 23 23 23 23 23 23 23 18 17 18 18 18 18 18 18 10 10 10 10 10 10 10 10 10 10 10 8 8 8 6 6 6 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Common Twofish algorithm parts shared between the c and assembler * implementations * * Originally Twofish for GPG * By Matthew Skala <mskala@ansuz.sooke.bc.ca>, July 26, 1998 * 256-bit key length added March 20, 1999 * Some modifications to reduce the text size by Werner Koch, April, 1998 * Ported to the kerneli patch by Marc Mutz <Marc@Mutz.com> * Ported to CryptoAPI by Colin Slater <hoho@tacomeat.net> * * The original author has disclaimed all copyright interest in this * code and thus put it in the public domain. The subsequent authors * have put this under the GNU General Public License. * * This code is a "clean room" implementation, written from the paper * _Twofish: A 128-Bit Block Cipher_ by Bruce Schneier, John Kelsey, * Doug Whiting, David Wagner, Chris Hall, and Niels Ferguson, available * through http://www.counterpane.com/twofish.html * * For background information on multiplication in finite fields, used for * the matrix operations in the key schedule, see the book _Contemporary * Abstract Algebra_ by Joseph A. Gallian, especially chapter 22 in the * Third Edition. */ #include <crypto/algapi.h> #include <crypto/twofish.h> #include <linux/bitops.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> /* The large precomputed tables for the Twofish cipher (twofish.c) * Taken from the same source as twofish.c * Marc Mutz <Marc@Mutz.com> */ /* These two tables are the q0 and q1 permutations, exactly as described in * the Twofish paper. */ static const u8 q0[256] = { 0xA9, 0x67, 0xB3, 0xE8, 0x04, 0xFD, 0xA3, 0x76, 0x9A, 0x92, 0x80, 0x78, 0xE4, 0xDD, 0xD1, 0x38, 0x0D, 0xC6, 0x35, 0x98, 0x18, 0xF7, 0xEC, 0x6C, 0x43, 0x75, 0x37, 0x26, 0xFA, 0x13, 0x94, 0x48, 0xF2, 0xD0, 0x8B, 0x30, 0x84, 0x54, 0xDF, 0x23, 0x19, 0x5B, 0x3D, 0x59, 0xF3, 0xAE, 0xA2, 0x82, 0x63, 0x01, 0x83, 0x2E, 0xD9, 0x51, 0x9B, 0x7C, 0xA6, 0xEB, 0xA5, 0xBE, 0x16, 0x0C, 0xE3, 0x61, 0xC0, 0x8C, 0x3A, 0xF5, 0x73, 0x2C, 0x25, 0x0B, 0xBB, 0x4E, 0x89, 0x6B, 0x53, 0x6A, 0xB4, 0xF1, 0xE1, 0xE6, 0xBD, 0x45, 0xE2, 0xF4, 0xB6, 0x66, 0xCC, 0x95, 0x03, 0x56, 0xD4, 0x1C, 0x1E, 0xD7, 0xFB, 0xC3, 0x8E, 0xB5, 0xE9, 0xCF, 0xBF, 0xBA, 0xEA, 0x77, 0x39, 0xAF, 0x33, 0xC9, 0x62, 0x71, 0x81, 0x79, 0x09, 0xAD, 0x24, 0xCD, 0xF9, 0xD8, 0xE5, 0xC5, 0xB9, 0x4D, 0x44, 0x08, 0x86, 0xE7, 0xA1, 0x1D, 0xAA, 0xED, 0x06, 0x70, 0xB2, 0xD2, 0x41, 0x7B, 0xA0, 0x11, 0x31, 0xC2, 0x27, 0x90, 0x20, 0xF6, 0x60, 0xFF, 0x96, 0x5C, 0xB1, 0xAB, 0x9E, 0x9C, 0x52, 0x1B, 0x5F, 0x93, 0x0A, 0xEF, 0x91, 0x85, 0x49, 0xEE, 0x2D, 0x4F, 0x8F, 0x3B, 0x47, 0x87, 0x6D, 0x46, 0xD6, 0x3E, 0x69, 0x64, 0x2A, 0xCE, 0xCB, 0x2F, 0xFC, 0x97, 0x05, 0x7A, 0xAC, 0x7F, 0xD5, 0x1A, 0x4B, 0x0E, 0xA7, 0x5A, 0x28, 0x14, 0x3F, 0x29, 0x88, 0x3C, 0x4C, 0x02, 0xB8, 0xDA, 0xB0, 0x17, 0x55, 0x1F, 0x8A, 0x7D, 0x57, 0xC7, 0x8D, 0x74, 0xB7, 0xC4, 0x9F, 0x72, 0x7E, 0x15, 0x22, 0x12, 0x58, 0x07, 0x99, 0x34, 0x6E, 0x50, 0xDE, 0x68, 0x65, 0xBC, 0xDB, 0xF8, 0xC8, 0xA8, 0x2B, 0x40, 0xDC, 0xFE, 0x32, 0xA4, 0xCA, 0x10, 0x21, 0xF0, 0xD3, 0x5D, 0x0F, 0x00, 0x6F, 0x9D, 0x36, 0x42, 0x4A, 0x5E, 0xC1, 0xE0 }; static const u8 q1[256] = { 0x75, 0xF3, 0xC6, 0xF4, 0xDB, 0x7B, 0xFB, 0xC8, 0x4A, 0xD3, 0xE6, 0x6B, 0x45, 0x7D, 0xE8, 0x4B, 0xD6, 0x32, 0xD8, 0xFD, 0x37, 0x71, 0xF1, 0xE1, 0x30, 0x0F, 0xF8, 0x1B, 0x87, 0xFA, 0x06, 0x3F, 0x5E, 0xBA, 0xAE, 0x5B, 0x8A, 0x00, 0xBC, 0x9D, 0x6D, 0xC1, 0xB1, 0x0E, 0x80, 0x5D, 0xD2, 0xD5, 0xA0, 0x84, 0x07, 0x14, 0xB5, 0x90, 0x2C, 0xA3, 0xB2, 0x73, 0x4C, 0x54, 0x92, 0x74, 0x36, 0x51, 0x38, 0xB0, 0xBD, 0x5A, 0xFC, 0x60, 0x62, 0x96, 0x6C, 0x42, 0xF7, 0x10, 0x7C, 0x28, 0x27, 0x8C, 0x13, 0x95, 0x9C, 0xC7, 0x24, 0x46, 0x3B, 0x70, 0xCA, 0xE3, 0x85, 0xCB, 0x11, 0xD0, 0x93, 0xB8, 0xA6, 0x83, 0x20, 0xFF, 0x9F, 0x77, 0xC3, 0xCC, 0x03, 0x6F, 0x08, 0xBF, 0x40, 0xE7, 0x2B, 0xE2, 0x79, 0x0C, 0xAA, 0x82, 0x41, 0x3A, 0xEA, 0xB9, 0xE4, 0x9A, 0xA4, 0x97, 0x7E, 0xDA, 0x7A, 0x17, 0x66, 0x94, 0xA1, 0x1D, 0x3D, 0xF0, 0xDE, 0xB3, 0x0B, 0x72, 0xA7, 0x1C, 0xEF, 0xD1, 0x53, 0x3E, 0x8F, 0x33, 0x26, 0x5F, 0xEC, 0x76, 0x2A, 0x49, 0x81, 0x88, 0xEE, 0x21, 0xC4, 0x1A, 0xEB, 0xD9, 0xC5, 0x39, 0x99, 0xCD, 0xAD, 0x31, 0x8B, 0x01, 0x18, 0x23, 0xDD, 0x1F, 0x4E, 0x2D, 0xF9, 0x48, 0x4F, 0xF2, 0x65, 0x8E, 0x78, 0x5C, 0x58, 0x19, 0x8D, 0xE5, 0x98, 0x57, 0x67, 0x7F, 0x05, 0x64, 0xAF, 0x63, 0xB6, 0xFE, 0xF5, 0xB7, 0x3C, 0xA5, 0xCE, 0xE9, 0x68, 0x44, 0xE0, 0x4D, 0x43, 0x69, 0x29, 0x2E, 0xAC, 0x15, 0x59, 0xA8, 0x0A, 0x9E, 0x6E, 0x47, 0xDF, 0x34, 0x35, 0x6A, 0xCF, 0xDC, 0x22, 0xC9, 0xC0, 0x9B, 0x89, 0xD4, 0xED, 0xAB, 0x12, 0xA2, 0x0D, 0x52, 0xBB, 0x02, 0x2F, 0xA9, 0xD7, 0x61, 0x1E, 0xB4, 0x50, 0x04, 0xF6, 0xC2, 0x16, 0x25, 0x86, 0x56, 0x55, 0x09, 0xBE, 0x91 }; /* These MDS tables are actually tables of MDS composed with q0 and q1, * because it is only ever used that way and we can save some time by * precomputing. Of course the main saving comes from precomputing the * GF(2^8) multiplication involved in the MDS matrix multiply; by looking * things up in these tables we reduce the matrix multiply to four lookups * and three XORs. Semi-formally, the definition of these tables is: * mds[0][i] = MDS (q1[i] 0 0 0)^T mds[1][i] = MDS (0 q0[i] 0 0)^T * mds[2][i] = MDS (0 0 q1[i] 0)^T mds[3][i] = MDS (0 0 0 q0[i])^T * where ^T means "transpose", the matrix multiply is performed in GF(2^8) * represented as GF(2)[x]/v(x) where v(x)=x^8+x^6+x^5+x^3+1 as described * by Schneier et al, and I'm casually glossing over the byte/word * conversion issues. */ static const u32 mds[4][256] = { { 0xBCBC3275, 0xECEC21F3, 0x202043C6, 0xB3B3C9F4, 0xDADA03DB, 0x02028B7B, 0xE2E22BFB, 0x9E9EFAC8, 0xC9C9EC4A, 0xD4D409D3, 0x18186BE6, 0x1E1E9F6B, 0x98980E45, 0xB2B2387D, 0xA6A6D2E8, 0x2626B74B, 0x3C3C57D6, 0x93938A32, 0x8282EED8, 0x525298FD, 0x7B7BD437, 0xBBBB3771, 0x5B5B97F1, 0x474783E1, 0x24243C30, 0x5151E20F, 0xBABAC6F8, 0x4A4AF31B, 0xBFBF4887, 0x0D0D70FA, 0xB0B0B306, 0x7575DE3F, 0xD2D2FD5E, 0x7D7D20BA, 0x666631AE, 0x3A3AA35B, 0x59591C8A, 0x00000000, 0xCDCD93BC, 0x1A1AE09D, 0xAEAE2C6D, 0x7F7FABC1, 0x2B2BC7B1, 0xBEBEB90E, 0xE0E0A080, 0x8A8A105D, 0x3B3B52D2, 0x6464BAD5, 0xD8D888A0, 0xE7E7A584, 0x5F5FE807, 0x1B1B1114, 0x2C2CC2B5, 0xFCFCB490, 0x3131272C, 0x808065A3, 0x73732AB2, 0x0C0C8173, 0x79795F4C, 0x6B6B4154, 0x4B4B0292, 0x53536974, 0x94948F36, 0x83831F51, 0x2A2A3638, 0xC4C49CB0, 0x2222C8BD, 0xD5D5F85A, 0xBDBDC3FC, 0x48487860, 0xFFFFCE62, 0x4C4C0796, 0x4141776C, 0xC7C7E642, 0xEBEB24F7, 0x1C1C1410, 0x5D5D637C, 0x36362228, 0x6767C027, 0xE9E9AF8C, 0x4444F913, 0x1414EA95, 0xF5F5BB9C, 0xCFCF18C7, 0x3F3F2D24, 0xC0C0E346, 0x7272DB3B, 0x54546C70, 0x29294CCA, 0xF0F035E3, 0x0808FE85, 0xC6C617CB, 0xF3F34F11, 0x8C8CE4D0, 0xA4A45993, 0xCACA96B8, 0x68683BA6, 0xB8B84D83, 0x38382820, 0xE5E52EFF, 0xADAD569F, 0x0B0B8477, 0xC8C81DC3, 0x9999FFCC, 0x5858ED03, 0x19199A6F, 0x0E0E0A08, 0x95957EBF, 0x70705040, 0xF7F730E7, 0x6E6ECF2B, 0x1F1F6EE2, 0xB5B53D79, 0x09090F0C, 0x616134AA, 0x57571682, 0x9F9F0B41, 0x9D9D803A, 0x111164EA, 0x2525CDB9, 0xAFAFDDE4, 0x4545089A, 0xDFDF8DA4, 0xA3A35C97, 0xEAEAD57E, 0x353558DA, 0xEDEDD07A, 0x4343FC17, 0xF8F8CB66, 0xFBFBB194, 0x3737D3A1, 0xFAFA401D, 0xC2C2683D, 0xB4B4CCF0, 0x32325DDE, 0x9C9C71B3, 0x5656E70B, 0xE3E3DA72, 0x878760A7, 0x15151B1C, 0xF9F93AEF, 0x6363BFD1, 0x3434A953, 0x9A9A853E, 0xB1B1428F, 0x7C7CD133, 0x88889B26, 0x3D3DA65F, 0xA1A1D7EC, 0xE4E4DF76, 0x8181942A, 0x91910149, 0x0F0FFB81, 0xEEEEAA88, 0x161661EE, 0xD7D77321, 0x9797F5C4, 0xA5A5A81A, 0xFEFE3FEB, 0x6D6DB5D9, 0x7878AEC5, 0xC5C56D39, 0x1D1DE599, 0x7676A4CD, 0x3E3EDCAD, 0xCBCB6731, 0xB6B6478B, 0xEFEF5B01, 0x12121E18, 0x6060C523, 0x6A6AB0DD, 0x4D4DF61F, 0xCECEE94E, 0xDEDE7C2D, 0x55559DF9, 0x7E7E5A48, 0x2121B24F, 0x03037AF2, 0xA0A02665, 0x5E5E198E, 0x5A5A6678, 0x65654B5C, 0x62624E58, 0xFDFD4519, 0x0606F48D, 0x404086E5, 0xF2F2BE98, 0x3333AC57, 0x17179067, 0x05058E7F, 0xE8E85E05, 0x4F4F7D64, 0x89896AAF, 0x10109563, 0x74742FB6, 0x0A0A75FE, 0x5C5C92F5, 0x9B9B74B7, 0x2D2D333C, 0x3030D6A5, 0x2E2E49CE, 0x494989E9, 0x46467268, 0x77775544, 0xA8A8D8E0, 0x9696044D, 0x2828BD43, 0xA9A92969, 0xD9D97929, 0x8686912E, 0xD1D187AC, 0xF4F44A15, 0x8D8D1559, 0xD6D682A8, 0xB9B9BC0A, 0x42420D9E, 0xF6F6C16E, 0x2F2FB847, 0xDDDD06DF, 0x23233934, 0xCCCC6235, 0xF1F1C46A, 0xC1C112CF, 0x8585EBDC, 0x8F8F9E22, 0x7171A1C9, 0x9090F0C0, 0xAAAA539B, 0x0101F189, 0x8B8BE1D4, 0x4E4E8CED, 0x8E8E6FAB, 0xABABA212, 0x6F6F3EA2, 0xE6E6540D, 0xDBDBF252, 0x92927BBB, 0xB7B7B602, 0x6969CA2F, 0x3939D9A9, 0xD3D30CD7, 0xA7A72361, 0xA2A2AD1E, 0xC3C399B4, 0x6C6C4450, 0x07070504, 0x04047FF6, 0x272746C2, 0xACACA716, 0xD0D07625, 0x50501386, 0xDCDCF756, 0x84841A55, 0xE1E15109, 0x7A7A25BE, 0x1313EF91}, { 0xA9D93939, 0x67901717, 0xB3719C9C, 0xE8D2A6A6, 0x04050707, 0xFD985252, 0xA3658080, 0x76DFE4E4, 0x9A084545, 0x92024B4B, 0x80A0E0E0, 0x78665A5A, 0xE4DDAFAF, 0xDDB06A6A, 0xD1BF6363, 0x38362A2A, 0x0D54E6E6, 0xC6432020, 0x3562CCCC, 0x98BEF2F2, 0x181E1212, 0xF724EBEB, 0xECD7A1A1, 0x6C774141, 0x43BD2828, 0x7532BCBC, 0x37D47B7B, 0x269B8888, 0xFA700D0D, 0x13F94444, 0x94B1FBFB, 0x485A7E7E, 0xF27A0303, 0xD0E48C8C, 0x8B47B6B6, 0x303C2424, 0x84A5E7E7, 0x54416B6B, 0xDF06DDDD, 0x23C56060, 0x1945FDFD, 0x5BA33A3A, 0x3D68C2C2, 0x59158D8D, 0xF321ECEC, 0xAE316666, 0xA23E6F6F, 0x82165757, 0x63951010, 0x015BEFEF, 0x834DB8B8, 0x2E918686, 0xD9B56D6D, 0x511F8383, 0x9B53AAAA, 0x7C635D5D, 0xA63B6868, 0xEB3FFEFE, 0xA5D63030, 0xBE257A7A, 0x16A7ACAC, 0x0C0F0909, 0xE335F0F0, 0x6123A7A7, 0xC0F09090, 0x8CAFE9E9, 0x3A809D9D, 0xF5925C5C, 0x73810C0C, 0x2C273131, 0x2576D0D0, 0x0BE75656, 0xBB7B9292, 0x4EE9CECE, 0x89F10101, 0x6B9F1E1E, 0x53A93434, 0x6AC4F1F1, 0xB499C3C3, 0xF1975B5B, 0xE1834747, 0xE66B1818, 0xBDC82222, 0x450E9898, 0xE26E1F1F, 0xF4C9B3B3, 0xB62F7474, 0x66CBF8F8, 0xCCFF9999, 0x95EA1414, 0x03ED5858, 0x56F7DCDC, 0xD4E18B8B, 0x1C1B1515, 0x1EADA2A2, 0xD70CD3D3, 0xFB2BE2E2, 0xC31DC8C8, 0x8E195E5E, 0xB5C22C2C, 0xE9894949, 0xCF12C1C1, 0xBF7E9595, 0xBA207D7D, 0xEA641111, 0x77840B0B, 0x396DC5C5, 0xAF6A8989, 0x33D17C7C, 0xC9A17171, 0x62CEFFFF, 0x7137BBBB, 0x81FB0F0F, 0x793DB5B5, 0x0951E1E1, 0xADDC3E3E, 0x242D3F3F, 0xCDA47676, 0xF99D5555, 0xD8EE8282, 0xE5864040, 0xC5AE7878, 0xB9CD2525, 0x4D049696, 0x44557777, 0x080A0E0E, 0x86135050, 0xE730F7F7, 0xA1D33737, 0x1D40FAFA, 0xAA346161, 0xED8C4E4E, 0x06B3B0B0, 0x706C5454, 0xB22A7373, 0xD2523B3B, 0x410B9F9F, 0x7B8B0202, 0xA088D8D8, 0x114FF3F3, 0x3167CBCB, 0xC2462727, 0x27C06767, 0x90B4FCFC, 0x20283838, 0xF67F0404, 0x60784848, 0xFF2EE5E5, 0x96074C4C, 0x5C4B6565, 0xB1C72B2B, 0xAB6F8E8E, 0x9E0D4242, 0x9CBBF5F5, 0x52F2DBDB, 0x1BF34A4A, 0x5FA63D3D, 0x9359A4A4, 0x0ABCB9B9, 0xEF3AF9F9, 0x91EF1313, 0x85FE0808, 0x49019191, 0xEE611616, 0x2D7CDEDE, 0x4FB22121, 0x8F42B1B1, 0x3BDB7272, 0x47B82F2F, 0x8748BFBF, 0x6D2CAEAE, 0x46E3C0C0, 0xD6573C3C, 0x3E859A9A, 0x6929A9A9, 0x647D4F4F, 0x2A948181, 0xCE492E2E, 0xCB17C6C6, 0x2FCA6969, 0xFCC3BDBD, 0x975CA3A3, 0x055EE8E8, 0x7AD0EDED, 0xAC87D1D1, 0x7F8E0505, 0xD5BA6464, 0x1AA8A5A5, 0x4BB72626, 0x0EB9BEBE, 0xA7608787, 0x5AF8D5D5, 0x28223636, 0x14111B1B, 0x3FDE7575, 0x2979D9D9, 0x88AAEEEE, 0x3C332D2D, 0x4C5F7979, 0x02B6B7B7, 0xB896CACA, 0xDA583535, 0xB09CC4C4, 0x17FC4343, 0x551A8484, 0x1FF64D4D, 0x8A1C5959, 0x7D38B2B2, 0x57AC3333, 0xC718CFCF, 0x8DF40606, 0x74695353, 0xB7749B9B, 0xC4F59797, 0x9F56ADAD, 0x72DAE3E3, 0x7ED5EAEA, 0x154AF4F4, 0x229E8F8F, 0x12A2ABAB, 0x584E6262, 0x07E85F5F, 0x99E51D1D, 0x34392323, 0x6EC1F6F6, 0x50446C6C, 0xDE5D3232, 0x68724646, 0x6526A0A0, 0xBC93CDCD, 0xDB03DADA, 0xF8C6BABA, 0xC8FA9E9E, 0xA882D6D6, 0x2BCF6E6E, 0x40507070, 0xDCEB8585, 0xFE750A0A, 0x328A9393, 0xA48DDFDF, 0xCA4C2929, 0x10141C1C, 0x2173D7D7, 0xF0CCB4B4, 0xD309D4D4, 0x5D108A8A, 0x0FE25151, 0x00000000, 0x6F9A1919, 0x9DE01A1A, 0x368F9494, 0x42E6C7C7, 0x4AECC9C9, 0x5EFDD2D2, 0xC1AB7F7F, 0xE0D8A8A8}, { 0xBC75BC32, 0xECF3EC21, 0x20C62043, 0xB3F4B3C9, 0xDADBDA03, 0x027B028B, 0xE2FBE22B, 0x9EC89EFA, 0xC94AC9EC, 0xD4D3D409, 0x18E6186B, 0x1E6B1E9F, 0x9845980E, 0xB27DB238, 0xA6E8A6D2, 0x264B26B7, 0x3CD63C57, 0x9332938A, 0x82D882EE, 0x52FD5298, 0x7B377BD4, 0xBB71BB37, 0x5BF15B97, 0x47E14783, 0x2430243C, 0x510F51E2, 0xBAF8BAC6, 0x4A1B4AF3, 0xBF87BF48, 0x0DFA0D70, 0xB006B0B3, 0x753F75DE, 0xD25ED2FD, 0x7DBA7D20, 0x66AE6631, 0x3A5B3AA3, 0x598A591C, 0x00000000, 0xCDBCCD93, 0x1A9D1AE0, 0xAE6DAE2C, 0x7FC17FAB, 0x2BB12BC7, 0xBE0EBEB9, 0xE080E0A0, 0x8A5D8A10, 0x3BD23B52, 0x64D564BA, 0xD8A0D888, 0xE784E7A5, 0x5F075FE8, 0x1B141B11, 0x2CB52CC2, 0xFC90FCB4, 0x312C3127, 0x80A38065, 0x73B2732A, 0x0C730C81, 0x794C795F, 0x6B546B41, 0x4B924B02, 0x53745369, 0x9436948F, 0x8351831F, 0x2A382A36, 0xC4B0C49C, 0x22BD22C8, 0xD55AD5F8, 0xBDFCBDC3, 0x48604878, 0xFF62FFCE, 0x4C964C07, 0x416C4177, 0xC742C7E6, 0xEBF7EB24, 0x1C101C14, 0x5D7C5D63, 0x36283622, 0x672767C0, 0xE98CE9AF, 0x441344F9, 0x149514EA, 0xF59CF5BB, 0xCFC7CF18, 0x3F243F2D, 0xC046C0E3, 0x723B72DB, 0x5470546C, 0x29CA294C, 0xF0E3F035, 0x088508FE, 0xC6CBC617, 0xF311F34F, 0x8CD08CE4, 0xA493A459, 0xCAB8CA96, 0x68A6683B, 0xB883B84D, 0x38203828, 0xE5FFE52E, 0xAD9FAD56, 0x0B770B84, 0xC8C3C81D, 0x99CC99FF, 0x580358ED, 0x196F199A, 0x0E080E0A, 0x95BF957E, 0x70407050, 0xF7E7F730, 0x6E2B6ECF, 0x1FE21F6E, 0xB579B53D, 0x090C090F, 0x61AA6134, 0x57825716, 0x9F419F0B, 0x9D3A9D80, 0x11EA1164, 0x25B925CD, 0xAFE4AFDD, 0x459A4508, 0xDFA4DF8D, 0xA397A35C, 0xEA7EEAD5, 0x35DA3558, 0xED7AEDD0, 0x431743FC, 0xF866F8CB, 0xFB94FBB1, 0x37A137D3, 0xFA1DFA40, 0xC23DC268, 0xB4F0B4CC, 0x32DE325D, 0x9CB39C71, 0x560B56E7, 0xE372E3DA, 0x87A78760, 0x151C151B, 0xF9EFF93A, 0x63D163BF, 0x345334A9, 0x9A3E9A85, 0xB18FB142, 0x7C337CD1, 0x8826889B, 0x3D5F3DA6, 0xA1ECA1D7, 0xE476E4DF, 0x812A8194, 0x91499101, 0x0F810FFB, 0xEE88EEAA, 0x16EE1661, 0xD721D773, 0x97C497F5, 0xA51AA5A8, 0xFEEBFE3F, 0x6DD96DB5, 0x78C578AE, 0xC539C56D, 0x1D991DE5, 0x76CD76A4, 0x3EAD3EDC, 0xCB31CB67, 0xB68BB647, 0xEF01EF5B, 0x1218121E, 0x602360C5, 0x6ADD6AB0, 0x4D1F4DF6, 0xCE4ECEE9, 0xDE2DDE7C, 0x55F9559D, 0x7E487E5A, 0x214F21B2, 0x03F2037A, 0xA065A026, 0x5E8E5E19, 0x5A785A66, 0x655C654B, 0x6258624E, 0xFD19FD45, 0x068D06F4, 0x40E54086, 0xF298F2BE, 0x335733AC, 0x17671790, 0x057F058E, 0xE805E85E, 0x4F644F7D, 0x89AF896A, 0x10631095, 0x74B6742F, 0x0AFE0A75, 0x5CF55C92, 0x9BB79B74, 0x2D3C2D33, 0x30A530D6, 0x2ECE2E49, 0x49E94989, 0x46684672, 0x77447755, 0xA8E0A8D8, 0x964D9604, 0x284328BD, 0xA969A929, 0xD929D979, 0x862E8691, 0xD1ACD187, 0xF415F44A, 0x8D598D15, 0xD6A8D682, 0xB90AB9BC, 0x429E420D, 0xF66EF6C1, 0x2F472FB8, 0xDDDFDD06, 0x23342339, 0xCC35CC62, 0xF16AF1C4, 0xC1CFC112, 0x85DC85EB, 0x8F228F9E, 0x71C971A1, 0x90C090F0, 0xAA9BAA53, 0x018901F1, 0x8BD48BE1, 0x4EED4E8C, 0x8EAB8E6F, 0xAB12ABA2, 0x6FA26F3E, 0xE60DE654, 0xDB52DBF2, 0x92BB927B, 0xB702B7B6, 0x692F69CA, 0x39A939D9, 0xD3D7D30C, 0xA761A723, 0xA21EA2AD, 0xC3B4C399, 0x6C506C44, 0x07040705, 0x04F6047F, 0x27C22746, 0xAC16ACA7, 0xD025D076, 0x50865013, 0xDC56DCF7, 0x8455841A, 0xE109E151, 0x7ABE7A25, 0x139113EF}, { 0xD939A9D9, 0x90176790, 0x719CB371, 0xD2A6E8D2, 0x05070405, 0x9852FD98, 0x6580A365, 0xDFE476DF, 0x08459A08, 0x024B9202, 0xA0E080A0, 0x665A7866, 0xDDAFE4DD, 0xB06ADDB0, 0xBF63D1BF, 0x362A3836, 0x54E60D54, 0x4320C643, 0x62CC3562, 0xBEF298BE, 0x1E12181E, 0x24EBF724, 0xD7A1ECD7, 0x77416C77, 0xBD2843BD, 0x32BC7532, 0xD47B37D4, 0x9B88269B, 0x700DFA70, 0xF94413F9, 0xB1FB94B1, 0x5A7E485A, 0x7A03F27A, 0xE48CD0E4, 0x47B68B47, 0x3C24303C, 0xA5E784A5, 0x416B5441, 0x06DDDF06, 0xC56023C5, 0x45FD1945, 0xA33A5BA3, 0x68C23D68, 0x158D5915, 0x21ECF321, 0x3166AE31, 0x3E6FA23E, 0x16578216, 0x95106395, 0x5BEF015B, 0x4DB8834D, 0x91862E91, 0xB56DD9B5, 0x1F83511F, 0x53AA9B53, 0x635D7C63, 0x3B68A63B, 0x3FFEEB3F, 0xD630A5D6, 0x257ABE25, 0xA7AC16A7, 0x0F090C0F, 0x35F0E335, 0x23A76123, 0xF090C0F0, 0xAFE98CAF, 0x809D3A80, 0x925CF592, 0x810C7381, 0x27312C27, 0x76D02576, 0xE7560BE7, 0x7B92BB7B, 0xE9CE4EE9, 0xF10189F1, 0x9F1E6B9F, 0xA93453A9, 0xC4F16AC4, 0x99C3B499, 0x975BF197, 0x8347E183, 0x6B18E66B, 0xC822BDC8, 0x0E98450E, 0x6E1FE26E, 0xC9B3F4C9, 0x2F74B62F, 0xCBF866CB, 0xFF99CCFF, 0xEA1495EA, 0xED5803ED, 0xF7DC56F7, 0xE18BD4E1, 0x1B151C1B, 0xADA21EAD, 0x0CD3D70C, 0x2BE2FB2B, 0x1DC8C31D, 0x195E8E19, 0xC22CB5C2, 0x8949E989, 0x12C1CF12, 0x7E95BF7E, 0x207DBA20, 0x6411EA64, 0x840B7784, 0x6DC5396D, 0x6A89AF6A, 0xD17C33D1, 0xA171C9A1, 0xCEFF62CE, 0x37BB7137, 0xFB0F81FB, 0x3DB5793D, 0x51E10951, 0xDC3EADDC, 0x2D3F242D, 0xA476CDA4, 0x9D55F99D, 0xEE82D8EE, 0x8640E586, 0xAE78C5AE, 0xCD25B9CD, 0x04964D04, 0x55774455, 0x0A0E080A, 0x13508613, 0x30F7E730, 0xD337A1D3, 0x40FA1D40, 0x3461AA34, 0x8C4EED8C, 0xB3B006B3, 0x6C54706C, 0x2A73B22A, 0x523BD252, 0x0B9F410B, 0x8B027B8B, 0x88D8A088, 0x4FF3114F, 0x67CB3167, 0x4627C246, 0xC06727C0, 0xB4FC90B4, 0x28382028, 0x7F04F67F, 0x78486078, 0x2EE5FF2E, 0x074C9607, 0x4B655C4B, 0xC72BB1C7, 0x6F8EAB6F, 0x0D429E0D, 0xBBF59CBB, 0xF2DB52F2, 0xF34A1BF3, 0xA63D5FA6, 0x59A49359, 0xBCB90ABC, 0x3AF9EF3A, 0xEF1391EF, 0xFE0885FE, 0x01914901, 0x6116EE61, 0x7CDE2D7C, 0xB2214FB2, 0x42B18F42, 0xDB723BDB, 0xB82F47B8, 0x48BF8748, 0x2CAE6D2C, 0xE3C046E3, 0x573CD657, 0x859A3E85, 0x29A96929, 0x7D4F647D, 0x94812A94, 0x492ECE49, 0x17C6CB17, 0xCA692FCA, 0xC3BDFCC3, 0x5CA3975C, 0x5EE8055E, 0xD0ED7AD0, 0x87D1AC87, 0x8E057F8E, 0xBA64D5BA, 0xA8A51AA8, 0xB7264BB7, 0xB9BE0EB9, 0x6087A760, 0xF8D55AF8, 0x22362822, 0x111B1411, 0xDE753FDE, 0x79D92979, 0xAAEE88AA, 0x332D3C33, 0x5F794C5F, 0xB6B702B6, 0x96CAB896, 0x5835DA58, 0x9CC4B09C, 0xFC4317FC, 0x1A84551A, 0xF64D1FF6, 0x1C598A1C, 0x38B27D38, 0xAC3357AC, 0x18CFC718, 0xF4068DF4, 0x69537469, 0x749BB774, 0xF597C4F5, 0x56AD9F56, 0xDAE372DA, 0xD5EA7ED5, 0x4AF4154A, 0x9E8F229E, 0xA2AB12A2, 0x4E62584E, 0xE85F07E8, 0xE51D99E5, 0x39233439, 0xC1F66EC1, 0x446C5044, 0x5D32DE5D, 0x72466872, 0x26A06526, 0x93CDBC93, 0x03DADB03, 0xC6BAF8C6, 0xFA9EC8FA, 0x82D6A882, 0xCF6E2BCF, 0x50704050, 0xEB85DCEB, 0x750AFE75, 0x8A93328A, 0x8DDFA48D, 0x4C29CA4C, 0x141C1014, 0x73D72173, 0xCCB4F0CC, 0x09D4D309, 0x108A5D10, 0xE2510FE2, 0x00000000, 0x9A196F9A, 0xE01A9DE0, 0x8F94368F, 0xE6C742E6, 0xECC94AEC, 0xFDD25EFD, 0xAB7FC1AB, 0xD8A8E0D8} }; /* The exp_to_poly and poly_to_exp tables are used to perform efficient * operations in GF(2^8) represented as GF(2)[x]/w(x) where * w(x)=x^8+x^6+x^3+x^2+1. We care about doing that because it's part of the * definition of the RS matrix in the key schedule. Elements of that field * are polynomials of degree not greater than 7 and all coefficients 0 or 1, * which can be represented naturally by bytes (just substitute x=2). In that * form, GF(2^8) addition is the same as bitwise XOR, but GF(2^8) * multiplication is inefficient without hardware support. To multiply * faster, I make use of the fact x is a generator for the nonzero elements, * so that every element p of GF(2)[x]/w(x) is either 0 or equal to (x)^n for * some n in 0..254. Note that caret is exponentiation in GF(2^8), * *not* polynomial notation. So if I want to compute pq where p and q are * in GF(2^8), I can just say: * 1. if p=0 or q=0 then pq=0 * 2. otherwise, find m and n such that p=x^m and q=x^n * 3. pq=(x^m)(x^n)=x^(m+n), so add m and n and find pq * The translations in steps 2 and 3 are looked up in the tables * poly_to_exp (for step 2) and exp_to_poly (for step 3). To see this * in action, look at the CALC_S macro. As additional wrinkles, note that * one of my operands is always a constant, so the poly_to_exp lookup on it * is done in advance; I included the original values in the comments so * readers can have some chance of recognizing that this *is* the RS matrix * from the Twofish paper. I've only included the table entries I actually * need; I never do a lookup on a variable input of zero and the biggest * exponents I'll ever see are 254 (variable) and 237 (constant), so they'll * never sum to more than 491. I'm repeating part of the exp_to_poly table * so that I don't have to do mod-255 reduction in the exponent arithmetic. * Since I know my constant operands are never zero, I only have to worry * about zero values in the variable operand, and I do it with a simple * conditional branch. I know conditionals are expensive, but I couldn't * see a non-horrible way of avoiding them, and I did manage to group the * statements so that each if covers four group multiplications. */ static const u8 poly_to_exp[255] = { 0x00, 0x01, 0x17, 0x02, 0x2E, 0x18, 0x53, 0x03, 0x6A, 0x2F, 0x93, 0x19, 0x34, 0x54, 0x45, 0x04, 0x5C, 0x6B, 0xB6, 0x30, 0xA6, 0x94, 0x4B, 0x1A, 0x8C, 0x35, 0x81, 0x55, 0xAA, 0x46, 0x0D, 0x05, 0x24, 0x5D, 0x87, 0x6C, 0x9B, 0xB7, 0xC1, 0x31, 0x2B, 0xA7, 0xA3, 0x95, 0x98, 0x4C, 0xCA, 0x1B, 0xE6, 0x8D, 0x73, 0x36, 0xCD, 0x82, 0x12, 0x56, 0x62, 0xAB, 0xF0, 0x47, 0x4F, 0x0E, 0xBD, 0x06, 0xD4, 0x25, 0xD2, 0x5E, 0x27, 0x88, 0x66, 0x6D, 0xD6, 0x9C, 0x79, 0xB8, 0x08, 0xC2, 0xDF, 0x32, 0x68, 0x2C, 0xFD, 0xA8, 0x8A, 0xA4, 0x5A, 0x96, 0x29, 0x99, 0x22, 0x4D, 0x60, 0xCB, 0xE4, 0x1C, 0x7B, 0xE7, 0x3B, 0x8E, 0x9E, 0x74, 0xF4, 0x37, 0xD8, 0xCE, 0xF9, 0x83, 0x6F, 0x13, 0xB2, 0x57, 0xE1, 0x63, 0xDC, 0xAC, 0xC4, 0xF1, 0xAF, 0x48, 0x0A, 0x50, 0x42, 0x0F, 0xBA, 0xBE, 0xC7, 0x07, 0xDE, 0xD5, 0x78, 0x26, 0x65, 0xD3, 0xD1, 0x5F, 0xE3, 0x28, 0x21, 0x89, 0x59, 0x67, 0xFC, 0x6E, 0xB1, 0xD7, 0xF8, 0x9D, 0xF3, 0x7A, 0x3A, 0xB9, 0xC6, 0x09, 0x41, 0xC3, 0xAE, 0xE0, 0xDB, 0x33, 0x44, 0x69, 0x92, 0x2D, 0x52, 0xFE, 0x16, 0xA9, 0x0C, 0x8B, 0x80, 0xA5, 0x4A, 0x5B, 0xB5, 0x97, 0xC9, 0x2A, 0xA2, 0x9A, 0xC0, 0x23, 0x86, 0x4E, 0xBC, 0x61, 0xEF, 0xCC, 0x11, 0xE5, 0x72, 0x1D, 0x3D, 0x7C, 0xEB, 0xE8, 0xE9, 0x3C, 0xEA, 0x8F, 0x7D, 0x9F, 0xEC, 0x75, 0x1E, 0xF5, 0x3E, 0x38, 0xF6, 0xD9, 0x3F, 0xCF, 0x76, 0xFA, 0x1F, 0x84, 0xA0, 0x70, 0xED, 0x14, 0x90, 0xB3, 0x7E, 0x58, 0xFB, 0xE2, 0x20, 0x64, 0xD0, 0xDD, 0x77, 0xAD, 0xDA, 0xC5, 0x40, 0xF2, 0x39, 0xB0, 0xF7, 0x49, 0xB4, 0x0B, 0x7F, 0x51, 0x15, 0x43, 0x91, 0x10, 0x71, 0xBB, 0xEE, 0xBF, 0x85, 0xC8, 0xA1 }; static const u8 exp_to_poly[492] = { 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x4D, 0x9A, 0x79, 0xF2, 0xA9, 0x1F, 0x3E, 0x7C, 0xF8, 0xBD, 0x37, 0x6E, 0xDC, 0xF5, 0xA7, 0x03, 0x06, 0x0C, 0x18, 0x30, 0x60, 0xC0, 0xCD, 0xD7, 0xE3, 0x8B, 0x5B, 0xB6, 0x21, 0x42, 0x84, 0x45, 0x8A, 0x59, 0xB2, 0x29, 0x52, 0xA4, 0x05, 0x0A, 0x14, 0x28, 0x50, 0xA0, 0x0D, 0x1A, 0x34, 0x68, 0xD0, 0xED, 0x97, 0x63, 0xC6, 0xC1, 0xCF, 0xD3, 0xEB, 0x9B, 0x7B, 0xF6, 0xA1, 0x0F, 0x1E, 0x3C, 0x78, 0xF0, 0xAD, 0x17, 0x2E, 0x5C, 0xB8, 0x3D, 0x7A, 0xF4, 0xA5, 0x07, 0x0E, 0x1C, 0x38, 0x70, 0xE0, 0x8D, 0x57, 0xAE, 0x11, 0x22, 0x44, 0x88, 0x5D, 0xBA, 0x39, 0x72, 0xE4, 0x85, 0x47, 0x8E, 0x51, 0xA2, 0x09, 0x12, 0x24, 0x48, 0x90, 0x6D, 0xDA, 0xF9, 0xBF, 0x33, 0x66, 0xCC, 0xD5, 0xE7, 0x83, 0x4B, 0x96, 0x61, 0xC2, 0xC9, 0xDF, 0xF3, 0xAB, 0x1B, 0x36, 0x6C, 0xD8, 0xFD, 0xB7, 0x23, 0x46, 0x8C, 0x55, 0xAA, 0x19, 0x32, 0x64, 0xC8, 0xDD, 0xF7, 0xA3, 0x0B, 0x16, 0x2C, 0x58, 0xB0, 0x2D, 0x5A, 0xB4, 0x25, 0x4A, 0x94, 0x65, 0xCA, 0xD9, 0xFF, 0xB3, 0x2B, 0x56, 0xAC, 0x15, 0x2A, 0x54, 0xA8, 0x1D, 0x3A, 0x74, 0xE8, 0x9D, 0x77, 0xEE, 0x91, 0x6F, 0xDE, 0xF1, 0xAF, 0x13, 0x26, 0x4C, 0x98, 0x7D, 0xFA, 0xB9, 0x3F, 0x7E, 0xFC, 0xB5, 0x27, 0x4E, 0x9C, 0x75, 0xEA, 0x99, 0x7F, 0xFE, 0xB1, 0x2F, 0x5E, 0xBC, 0x35, 0x6A, 0xD4, 0xE5, 0x87, 0x43, 0x86, 0x41, 0x82, 0x49, 0x92, 0x69, 0xD2, 0xE9, 0x9F, 0x73, 0xE6, 0x81, 0x4F, 0x9E, 0x71, 0xE2, 0x89, 0x5F, 0xBE, 0x31, 0x62, 0xC4, 0xC5, 0xC7, 0xC3, 0xCB, 0xDB, 0xFB, 0xBB, 0x3B, 0x76, 0xEC, 0x95, 0x67, 0xCE, 0xD1, 0xEF, 0x93, 0x6B, 0xD6, 0xE1, 0x8F, 0x53, 0xA6, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x4D, 0x9A, 0x79, 0xF2, 0xA9, 0x1F, 0x3E, 0x7C, 0xF8, 0xBD, 0x37, 0x6E, 0xDC, 0xF5, 0xA7, 0x03, 0x06, 0x0C, 0x18, 0x30, 0x60, 0xC0, 0xCD, 0xD7, 0xE3, 0x8B, 0x5B, 0xB6, 0x21, 0x42, 0x84, 0x45, 0x8A, 0x59, 0xB2, 0x29, 0x52, 0xA4, 0x05, 0x0A, 0x14, 0x28, 0x50, 0xA0, 0x0D, 0x1A, 0x34, 0x68, 0xD0, 0xED, 0x97, 0x63, 0xC6, 0xC1, 0xCF, 0xD3, 0xEB, 0x9B, 0x7B, 0xF6, 0xA1, 0x0F, 0x1E, 0x3C, 0x78, 0xF0, 0xAD, 0x17, 0x2E, 0x5C, 0xB8, 0x3D, 0x7A, 0xF4, 0xA5, 0x07, 0x0E, 0x1C, 0x38, 0x70, 0xE0, 0x8D, 0x57, 0xAE, 0x11, 0x22, 0x44, 0x88, 0x5D, 0xBA, 0x39, 0x72, 0xE4, 0x85, 0x47, 0x8E, 0x51, 0xA2, 0x09, 0x12, 0x24, 0x48, 0x90, 0x6D, 0xDA, 0xF9, 0xBF, 0x33, 0x66, 0xCC, 0xD5, 0xE7, 0x83, 0x4B, 0x96, 0x61, 0xC2, 0xC9, 0xDF, 0xF3, 0xAB, 0x1B, 0x36, 0x6C, 0xD8, 0xFD, 0xB7, 0x23, 0x46, 0x8C, 0x55, 0xAA, 0x19, 0x32, 0x64, 0xC8, 0xDD, 0xF7, 0xA3, 0x0B, 0x16, 0x2C, 0x58, 0xB0, 0x2D, 0x5A, 0xB4, 0x25, 0x4A, 0x94, 0x65, 0xCA, 0xD9, 0xFF, 0xB3, 0x2B, 0x56, 0xAC, 0x15, 0x2A, 0x54, 0xA8, 0x1D, 0x3A, 0x74, 0xE8, 0x9D, 0x77, 0xEE, 0x91, 0x6F, 0xDE, 0xF1, 0xAF, 0x13, 0x26, 0x4C, 0x98, 0x7D, 0xFA, 0xB9, 0x3F, 0x7E, 0xFC, 0xB5, 0x27, 0x4E, 0x9C, 0x75, 0xEA, 0x99, 0x7F, 0xFE, 0xB1, 0x2F, 0x5E, 0xBC, 0x35, 0x6A, 0xD4, 0xE5, 0x87, 0x43, 0x86, 0x41, 0x82, 0x49, 0x92, 0x69, 0xD2, 0xE9, 0x9F, 0x73, 0xE6, 0x81, 0x4F, 0x9E, 0x71, 0xE2, 0x89, 0x5F, 0xBE, 0x31, 0x62, 0xC4, 0xC5, 0xC7, 0xC3, 0xCB }; /* The table constants are indices of * S-box entries, preprocessed through q0 and q1. */ static const u8 calc_sb_tbl[512] = { 0xA9, 0x75, 0x67, 0xF3, 0xB3, 0xC6, 0xE8, 0xF4, 0x04, 0xDB, 0xFD, 0x7B, 0xA3, 0xFB, 0x76, 0xC8, 0x9A, 0x4A, 0x92, 0xD3, 0x80, 0xE6, 0x78, 0x6B, 0xE4, 0x45, 0xDD, 0x7D, 0xD1, 0xE8, 0x38, 0x4B, 0x0D, 0xD6, 0xC6, 0x32, 0x35, 0xD8, 0x98, 0xFD, 0x18, 0x37, 0xF7, 0x71, 0xEC, 0xF1, 0x6C, 0xE1, 0x43, 0x30, 0x75, 0x0F, 0x37, 0xF8, 0x26, 0x1B, 0xFA, 0x87, 0x13, 0xFA, 0x94, 0x06, 0x48, 0x3F, 0xF2, 0x5E, 0xD0, 0xBA, 0x8B, 0xAE, 0x30, 0x5B, 0x84, 0x8A, 0x54, 0x00, 0xDF, 0xBC, 0x23, 0x9D, 0x19, 0x6D, 0x5B, 0xC1, 0x3D, 0xB1, 0x59, 0x0E, 0xF3, 0x80, 0xAE, 0x5D, 0xA2, 0xD2, 0x82, 0xD5, 0x63, 0xA0, 0x01, 0x84, 0x83, 0x07, 0x2E, 0x14, 0xD9, 0xB5, 0x51, 0x90, 0x9B, 0x2C, 0x7C, 0xA3, 0xA6, 0xB2, 0xEB, 0x73, 0xA5, 0x4C, 0xBE, 0x54, 0x16, 0x92, 0x0C, 0x74, 0xE3, 0x36, 0x61, 0x51, 0xC0, 0x38, 0x8C, 0xB0, 0x3A, 0xBD, 0xF5, 0x5A, 0x73, 0xFC, 0x2C, 0x60, 0x25, 0x62, 0x0B, 0x96, 0xBB, 0x6C, 0x4E, 0x42, 0x89, 0xF7, 0x6B, 0x10, 0x53, 0x7C, 0x6A, 0x28, 0xB4, 0x27, 0xF1, 0x8C, 0xE1, 0x13, 0xE6, 0x95, 0xBD, 0x9C, 0x45, 0xC7, 0xE2, 0x24, 0xF4, 0x46, 0xB6, 0x3B, 0x66, 0x70, 0xCC, 0xCA, 0x95, 0xE3, 0x03, 0x85, 0x56, 0xCB, 0xD4, 0x11, 0x1C, 0xD0, 0x1E, 0x93, 0xD7, 0xB8, 0xFB, 0xA6, 0xC3, 0x83, 0x8E, 0x20, 0xB5, 0xFF, 0xE9, 0x9F, 0xCF, 0x77, 0xBF, 0xC3, 0xBA, 0xCC, 0xEA, 0x03, 0x77, 0x6F, 0x39, 0x08, 0xAF, 0xBF, 0x33, 0x40, 0xC9, 0xE7, 0x62, 0x2B, 0x71, 0xE2, 0x81, 0x79, 0x79, 0x0C, 0x09, 0xAA, 0xAD, 0x82, 0x24, 0x41, 0xCD, 0x3A, 0xF9, 0xEA, 0xD8, 0xB9, 0xE5, 0xE4, 0xC5, 0x9A, 0xB9, 0xA4, 0x4D, 0x97, 0x44, 0x7E, 0x08, 0xDA, 0x86, 0x7A, 0xE7, 0x17, 0xA1, 0x66, 0x1D, 0x94, 0xAA, 0xA1, 0xED, 0x1D, 0x06, 0x3D, 0x70, 0xF0, 0xB2, 0xDE, 0xD2, 0xB3, 0x41, 0x0B, 0x7B, 0x72, 0xA0, 0xA7, 0x11, 0x1C, 0x31, 0xEF, 0xC2, 0xD1, 0x27, 0x53, 0x90, 0x3E, 0x20, 0x8F, 0xF6, 0x33, 0x60, 0x26, 0xFF, 0x5F, 0x96, 0xEC, 0x5C, 0x76, 0xB1, 0x2A, 0xAB, 0x49, 0x9E, 0x81, 0x9C, 0x88, 0x52, 0xEE, 0x1B, 0x21, 0x5F, 0xC4, 0x93, 0x1A, 0x0A, 0xEB, 0xEF, 0xD9, 0x91, 0xC5, 0x85, 0x39, 0x49, 0x99, 0xEE, 0xCD, 0x2D, 0xAD, 0x4F, 0x31, 0x8F, 0x8B, 0x3B, 0x01, 0x47, 0x18, 0x87, 0x23, 0x6D, 0xDD, 0x46, 0x1F, 0xD6, 0x4E, 0x3E, 0x2D, 0x69, 0xF9, 0x64, 0x48, 0x2A, 0x4F, 0xCE, 0xF2, 0xCB, 0x65, 0x2F, 0x8E, 0xFC, 0x78, 0x97, 0x5C, 0x05, 0x58, 0x7A, 0x19, 0xAC, 0x8D, 0x7F, 0xE5, 0xD5, 0x98, 0x1A, 0x57, 0x4B, 0x67, 0x0E, 0x7F, 0xA7, 0x05, 0x5A, 0x64, 0x28, 0xAF, 0x14, 0x63, 0x3F, 0xB6, 0x29, 0xFE, 0x88, 0xF5, 0x3C, 0xB7, 0x4C, 0x3C, 0x02, 0xA5, 0xB8, 0xCE, 0xDA, 0xE9, 0xB0, 0x68, 0x17, 0x44, 0x55, 0xE0, 0x1F, 0x4D, 0x8A, 0x43, 0x7D, 0x69, 0x57, 0x29, 0xC7, 0x2E, 0x8D, 0xAC, 0x74, 0x15, 0xB7, 0x59, 0xC4, 0xA8, 0x9F, 0x0A, 0x72, 0x9E, 0x7E, 0x6E, 0x15, 0x47, 0x22, 0xDF, 0x12, 0x34, 0x58, 0x35, 0x07, 0x6A, 0x99, 0xCF, 0x34, 0xDC, 0x6E, 0x22, 0x50, 0xC9, 0xDE, 0xC0, 0x68, 0x9B, 0x65, 0x89, 0xBC, 0xD4, 0xDB, 0xED, 0xF8, 0xAB, 0xC8, 0x12, 0xA8, 0xA2, 0x2B, 0x0D, 0x40, 0x52, 0xDC, 0xBB, 0xFE, 0x02, 0x32, 0x2F, 0xA4, 0xA9, 0xCA, 0xD7, 0x10, 0x61, 0x21, 0x1E, 0xF0, 0xB4, 0xD3, 0x50, 0x5D, 0x04, 0x0F, 0xF6, 0x00, 0xC2, 0x6F, 0x16, 0x9D, 0x25, 0x36, 0x86, 0x42, 0x56, 0x4A, 0x55, 0x5E, 0x09, 0xC1, 0xBE, 0xE0, 0x91 }; /* Macro to perform one column of the RS matrix multiplication. The * parameters a, b, c, and d are the four bytes of output; i is the index * of the key bytes, and w, x, y, and z, are the column of constants from * the RS matrix, preprocessed through the poly_to_exp table. */ #define CALC_S(a, b, c, d, i, w, x, y, z) \ if (key[i]) { \ tmp = poly_to_exp[key[i] - 1]; \ (a) ^= exp_to_poly[tmp + (w)]; \ (b) ^= exp_to_poly[tmp + (x)]; \ (c) ^= exp_to_poly[tmp + (y)]; \ (d) ^= exp_to_poly[tmp + (z)]; \ } /* Macros to calculate the key-dependent S-boxes for a 128-bit key using * the S vector from CALC_S. CALC_SB_2 computes a single entry in all * four S-boxes, where i is the index of the entry to compute, and a and b * are the index numbers preprocessed through the q0 and q1 tables * respectively. */ #define CALC_SB_2(i, a, b) \ ctx->s[0][i] = mds[0][q0[(a) ^ sa] ^ se]; \ ctx->s[1][i] = mds[1][q0[(b) ^ sb] ^ sf]; \ ctx->s[2][i] = mds[2][q1[(a) ^ sc] ^ sg]; \ ctx->s[3][i] = mds[3][q1[(b) ^ sd] ^ sh] /* Macro exactly like CALC_SB_2, but for 192-bit keys. */ #define CALC_SB192_2(i, a, b) \ ctx->s[0][i] = mds[0][q0[q0[(b) ^ sa] ^ se] ^ si]; \ ctx->s[1][i] = mds[1][q0[q1[(b) ^ sb] ^ sf] ^ sj]; \ ctx->s[2][i] = mds[2][q1[q0[(a) ^ sc] ^ sg] ^ sk]; \ ctx->s[3][i] = mds[3][q1[q1[(a) ^ sd] ^ sh] ^ sl]; /* Macro exactly like CALC_SB_2, but for 256-bit keys. */ #define CALC_SB256_2(i, a, b) \ ctx->s[0][i] = mds[0][q0[q0[q1[(b) ^ sa] ^ se] ^ si] ^ sm]; \ ctx->s[1][i] = mds[1][q0[q1[q1[(a) ^ sb] ^ sf] ^ sj] ^ sn]; \ ctx->s[2][i] = mds[2][q1[q0[q0[(a) ^ sc] ^ sg] ^ sk] ^ so]; \ ctx->s[3][i] = mds[3][q1[q1[q0[(b) ^ sd] ^ sh] ^ sl] ^ sp]; /* Macros to calculate the whitening and round subkeys. CALC_K_2 computes the * last two stages of the h() function for a given index (either 2i or 2i+1). * a, b, c, and d are the four bytes going into the last two stages. For * 128-bit keys, this is the entire h() function and a and c are the index * preprocessed through q0 and q1 respectively; for longer keys they are the * output of previous stages. j is the index of the first key byte to use. * CALC_K computes a pair of subkeys for 128-bit Twofish, by calling CALC_K_2 * twice, doing the Pseudo-Hadamard Transform, and doing the necessary * rotations. Its parameters are: a, the array to write the results into, * j, the index of the first output entry, k and l, the preprocessed indices * for index 2i, and m and n, the preprocessed indices for index 2i+1. * CALC_K192_2 expands CALC_K_2 to handle 192-bit keys, by doing an * additional lookup-and-XOR stage. The parameters a, b, c and d are the * four bytes going into the last three stages. For 192-bit keys, c = d * are the index preprocessed through q0, and a = b are the index * preprocessed through q1; j is the index of the first key byte to use. * CALC_K192 is identical to CALC_K but for using the CALC_K192_2 macro * instead of CALC_K_2. * CALC_K256_2 expands CALC_K192_2 to handle 256-bit keys, by doing an * additional lookup-and-XOR stage. The parameters a and b are the index * preprocessed through q0 and q1 respectively; j is the index of the first * key byte to use. CALC_K256 is identical to CALC_K but for using the * CALC_K256_2 macro instead of CALC_K_2. */ #define CALC_K_2(a, b, c, d, j) \ mds[0][q0[a ^ key[(j) + 8]] ^ key[j]] \ ^ mds[1][q0[b ^ key[(j) + 9]] ^ key[(j) + 1]] \ ^ mds[2][q1[c ^ key[(j) + 10]] ^ key[(j) + 2]] \ ^ mds[3][q1[d ^ key[(j) + 11]] ^ key[(j) + 3]] #define CALC_K(a, j, k, l, m, n) \ x = CALC_K_2 (k, l, k, l, 0); \ y = CALC_K_2 (m, n, m, n, 4); \ y = rol32(y, 8); \ x += y; y += x; ctx->a[j] = x; \ ctx->a[(j) + 1] = rol32(y, 9) #define CALC_K192_2(a, b, c, d, j) \ CALC_K_2 (q0[a ^ key[(j) + 16]], \ q1[b ^ key[(j) + 17]], \ q0[c ^ key[(j) + 18]], \ q1[d ^ key[(j) + 19]], j) #define CALC_K192(a, j, k, l, m, n) \ x = CALC_K192_2 (l, l, k, k, 0); \ y = CALC_K192_2 (n, n, m, m, 4); \ y = rol32(y, 8); \ x += y; y += x; ctx->a[j] = x; \ ctx->a[(j) + 1] = rol32(y, 9) #define CALC_K256_2(a, b, j) \ CALC_K192_2 (q1[b ^ key[(j) + 24]], \ q1[a ^ key[(j) + 25]], \ q0[a ^ key[(j) + 26]], \ q0[b ^ key[(j) + 27]], j) #define CALC_K256(a, j, k, l, m, n) \ x = CALC_K256_2 (k, l, 0); \ y = CALC_K256_2 (m, n, 4); \ y = rol32(y, 8); \ x += y; y += x; ctx->a[j] = x; \ ctx->a[(j) + 1] = rol32(y, 9) /* Perform the key setup. */ int __twofish_setkey(struct twofish_ctx *ctx, const u8 *key, unsigned int key_len) { int i, j, k; /* Temporaries for CALC_K. */ u32 x, y; /* The S vector used to key the S-boxes, split up into individual bytes. * 128-bit keys use only sa through sh; 256-bit use all of them. */ u8 sa = 0, sb = 0, sc = 0, sd = 0, se = 0, sf = 0, sg = 0, sh = 0; u8 si = 0, sj = 0, sk = 0, sl = 0, sm = 0, sn = 0, so = 0, sp = 0; /* Temporary for CALC_S. */ u8 tmp; /* Check key length. */ if (key_len % 8) return -EINVAL; /* unsupported key length */ /* Compute the first two words of the S vector. The magic numbers are * the entries of the RS matrix, preprocessed through poly_to_exp. The * numbers in the comments are the original (polynomial form) matrix * entries. */ CALC_S (sa, sb, sc, sd, 0, 0x00, 0x2D, 0x01, 0x2D); /* 01 A4 02 A4 */ CALC_S (sa, sb, sc, sd, 1, 0x2D, 0xA4, 0x44, 0x8A); /* A4 56 A1 55 */ CALC_S (sa, sb, sc, sd, 2, 0x8A, 0xD5, 0xBF, 0xD1); /* 55 82 FC 87 */ CALC_S (sa, sb, sc, sd, 3, 0xD1, 0x7F, 0x3D, 0x99); /* 87 F3 C1 5A */ CALC_S (sa, sb, sc, sd, 4, 0x99, 0x46, 0x66, 0x96); /* 5A 1E 47 58 */ CALC_S (sa, sb, sc, sd, 5, 0x96, 0x3C, 0x5B, 0xED); /* 58 C6 AE DB */ CALC_S (sa, sb, sc, sd, 6, 0xED, 0x37, 0x4F, 0xE0); /* DB 68 3D 9E */ CALC_S (sa, sb, sc, sd, 7, 0xE0, 0xD0, 0x8C, 0x17); /* 9E E5 19 03 */ CALC_S (se, sf, sg, sh, 8, 0x00, 0x2D, 0x01, 0x2D); /* 01 A4 02 A4 */ CALC_S (se, sf, sg, sh, 9, 0x2D, 0xA4, 0x44, 0x8A); /* A4 56 A1 55 */ CALC_S (se, sf, sg, sh, 10, 0x8A, 0xD5, 0xBF, 0xD1); /* 55 82 FC 87 */ CALC_S (se, sf, sg, sh, 11, 0xD1, 0x7F, 0x3D, 0x99); /* 87 F3 C1 5A */ CALC_S (se, sf, sg, sh, 12, 0x99, 0x46, 0x66, 0x96); /* 5A 1E 47 58 */ CALC_S (se, sf, sg, sh, 13, 0x96, 0x3C, 0x5B, 0xED); /* 58 C6 AE DB */ CALC_S (se, sf, sg, sh, 14, 0xED, 0x37, 0x4F, 0xE0); /* DB 68 3D 9E */ CALC_S (se, sf, sg, sh, 15, 0xE0, 0xD0, 0x8C, 0x17); /* 9E E5 19 03 */ if (key_len == 24 || key_len == 32) { /* 192- or 256-bit key */ /* Calculate the third word of the S vector */ CALC_S (si, sj, sk, sl, 16, 0x00, 0x2D, 0x01, 0x2D); /* 01 A4 02 A4 */ CALC_S (si, sj, sk, sl, 17, 0x2D, 0xA4, 0x44, 0x8A); /* A4 56 A1 55 */ CALC_S (si, sj, sk, sl, 18, 0x8A, 0xD5, 0xBF, 0xD1); /* 55 82 FC 87 */ CALC_S (si, sj, sk, sl, 19, 0xD1, 0x7F, 0x3D, 0x99); /* 87 F3 C1 5A */ CALC_S (si, sj, sk, sl, 20, 0x99, 0x46, 0x66, 0x96); /* 5A 1E 47 58 */ CALC_S (si, sj, sk, sl, 21, 0x96, 0x3C, 0x5B, 0xED); /* 58 C6 AE DB */ CALC_S (si, sj, sk, sl, 22, 0xED, 0x37, 0x4F, 0xE0); /* DB 68 3D 9E */ CALC_S (si, sj, sk, sl, 23, 0xE0, 0xD0, 0x8C, 0x17); /* 9E E5 19 03 */ } if (key_len == 32) { /* 256-bit key */ /* Calculate the fourth word of the S vector */ CALC_S (sm, sn, so, sp, 24, 0x00, 0x2D, 0x01, 0x2D); /* 01 A4 02 A4 */ CALC_S (sm, sn, so, sp, 25, 0x2D, 0xA4, 0x44, 0x8A); /* A4 56 A1 55 */ CALC_S (sm, sn, so, sp, 26, 0x8A, 0xD5, 0xBF, 0xD1); /* 55 82 FC 87 */ CALC_S (sm, sn, so, sp, 27, 0xD1, 0x7F, 0x3D, 0x99); /* 87 F3 C1 5A */ CALC_S (sm, sn, so, sp, 28, 0x99, 0x46, 0x66, 0x96); /* 5A 1E 47 58 */ CALC_S (sm, sn, so, sp, 29, 0x96, 0x3C, 0x5B, 0xED); /* 58 C6 AE DB */ CALC_S (sm, sn, so, sp, 30, 0xED, 0x37, 0x4F, 0xE0); /* DB 68 3D 9E */ CALC_S (sm, sn, so, sp, 31, 0xE0, 0xD0, 0x8C, 0x17); /* 9E E5 19 03 */ /* Compute the S-boxes. */ for ( i = j = 0, k = 1; i < 256; i++, j += 2, k += 2 ) { CALC_SB256_2( i, calc_sb_tbl[j], calc_sb_tbl[k] ); } /* CALC_K256/CALC_K192/CALC_K loops were unrolled. * Unrolling produced x2.5 more code (+18k on i386), * and speeded up key setup by 7%: * unrolled: twofish_setkey/sec: 41128 * loop: twofish_setkey/sec: 38148 * CALC_K256: ~100 insns each * CALC_K192: ~90 insns * CALC_K: ~70 insns */ /* Calculate whitening and round subkeys */ for ( i = 0; i < 8; i += 2 ) { CALC_K256 (w, i, q0[i], q1[i], q0[i+1], q1[i+1]); } for ( i = 0; i < 32; i += 2 ) { CALC_K256 (k, i, q0[i+8], q1[i+8], q0[i+9], q1[i+9]); } } else if (key_len == 24) { /* 192-bit key */ /* Compute the S-boxes. */ for ( i = j = 0, k = 1; i < 256; i++, j += 2, k += 2 ) { CALC_SB192_2( i, calc_sb_tbl[j], calc_sb_tbl[k] ); } /* Calculate whitening and round subkeys */ for ( i = 0; i < 8; i += 2 ) { CALC_K192 (w, i, q0[i], q1[i], q0[i+1], q1[i+1]); } for ( i = 0; i < 32; i += 2 ) { CALC_K192 (k, i, q0[i+8], q1[i+8], q0[i+9], q1[i+9]); } } else { /* 128-bit key */ /* Compute the S-boxes. */ for ( i = j = 0, k = 1; i < 256; i++, j += 2, k += 2 ) { CALC_SB_2( i, calc_sb_tbl[j], calc_sb_tbl[k] ); } /* Calculate whitening and round subkeys */ for ( i = 0; i < 8; i += 2 ) { CALC_K (w, i, q0[i], q1[i], q0[i+1], q1[i+1]); } for ( i = 0; i < 32; i += 2 ) { CALC_K (k, i, q0[i+8], q1[i+8], q0[i+9], q1[i+9]); } } return 0; } EXPORT_SYMBOL_GPL(__twofish_setkey); int twofish_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int key_len) { return __twofish_setkey(crypto_tfm_ctx(tfm), key, key_len); } EXPORT_SYMBOL_GPL(twofish_setkey); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Twofish cipher common functions"); |
| 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_blackhole.c Black hole queue * * Authors: Thomas Graf <tgraf@suug.ch> * * Note: Quantum tunneling is not supported. */ #include <linux/init.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { qdisc_drop(skb, sch, to_free); return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } static struct sk_buff *blackhole_dequeue(struct Qdisc *sch) { return NULL; } static struct Qdisc_ops blackhole_qdisc_ops __read_mostly = { .id = "blackhole", .priv_size = 0, .enqueue = blackhole_enqueue, .dequeue = blackhole_dequeue, .peek = blackhole_dequeue, .owner = THIS_MODULE, }; static int __init blackhole_init(void) { return register_qdisc(&blackhole_qdisc_ops); } device_initcall(blackhole_init) |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* xfrm_hash.c: Common hash table code. * * Copyright (C) 2006 David S. Miller (davem@davemloft.net) */ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/memblock.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/xfrm.h> #include "xfrm_hash.h" struct hlist_head *xfrm_hash_alloc(unsigned int sz) { struct hlist_head *n; if (sz <= PAGE_SIZE) n = kzalloc(sz, GFP_KERNEL); else if (hashdist) n = vzalloc(sz); else n = (struct hlist_head *) __get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); return n; } void xfrm_hash_free(struct hlist_head *n, unsigned int sz) { if (sz <= PAGE_SIZE) kfree(n); else if (hashdist) vfree(n); else free_pages((unsigned long)n, get_order(sz)); } |
| 237 238 238 164 160 6 162 5 164 162 1 164 14 150 62 32 60 50 50 6 45 10 11 8 4 8 226 262 262 248 7 10 2 147 168 251 263 14 250 163 166 155 155 262 197 162 43 43 2 23 23 23 23 30 30 29 42 43 42 42 5 16 14 31 12 9 1 12 265 15 259 18 264 261 18 4 50 8 44 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001-2003 International Business Machines Corp. * Copyright (c) 2001 Intel Corp. * Copyright (c) 2001 La Monte H.P. Yarroll * * This file is part of the SCTP kernel implementation * * This module provides the abstraction for an SCTP transport representing * a remote transport address. For local transport addresses, we just use * union sctp_addr. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Xingang Guo <xingang.guo@intel.com> * Hui Huang <hui.huang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/slab.h> #include <linux/types.h> #include <linux/random.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> /* 1st Level Abstractions. */ /* Initialize a new transport from provided memory. */ static struct sctp_transport *sctp_transport_init(struct net *net, struct sctp_transport *peer, const union sctp_addr *addr, gfp_t gfp) { /* Copy in the address. */ peer->af_specific = sctp_get_af_specific(addr->sa.sa_family); memcpy(&peer->ipaddr, addr, peer->af_specific->sockaddr_len); memset(&peer->saddr, 0, sizeof(union sctp_addr)); peer->sack_generation = 0; /* From 6.3.1 RTO Calculation: * * C1) Until an RTT measurement has been made for a packet sent to the * given destination transport address, set RTO to the protocol * parameter 'RTO.Initial'. */ peer->rto = msecs_to_jiffies(net->sctp.rto_initial); peer->last_time_heard = 0; peer->last_time_ecne_reduced = jiffies; peer->param_flags = SPP_HB_DISABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; /* Initialize the default path max_retrans. */ peer->pathmaxrxt = net->sctp.max_retrans_path; peer->pf_retrans = net->sctp.pf_retrans; INIT_LIST_HEAD(&peer->transmitted); INIT_LIST_HEAD(&peer->send_ready); INIT_LIST_HEAD(&peer->transports); timer_setup(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event, 0); timer_setup(&peer->hb_timer, sctp_generate_heartbeat_event, 0); timer_setup(&peer->reconf_timer, sctp_generate_reconf_event, 0); timer_setup(&peer->probe_timer, sctp_generate_probe_event, 0); timer_setup(&peer->proto_unreach_timer, sctp_generate_proto_unreach_event, 0); /* Initialize the 64-bit random nonce sent with heartbeat. */ get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce)); refcount_set(&peer->refcnt, 1); return peer; } /* Allocate and initialize a new transport. */ struct sctp_transport *sctp_transport_new(struct net *net, const union sctp_addr *addr, gfp_t gfp) { struct sctp_transport *transport; transport = kzalloc(sizeof(*transport), gfp); if (!transport) goto fail; if (!sctp_transport_init(net, transport, addr, gfp)) goto fail_init; SCTP_DBG_OBJCNT_INC(transport); return transport; fail_init: kfree(transport); fail: return NULL; } /* This transport is no longer needed. Free up if possible, or * delay until it last reference count. */ void sctp_transport_free(struct sctp_transport *transport) { /* Try to delete the heartbeat timer. */ if (del_timer(&transport->hb_timer)) sctp_transport_put(transport); /* Delete the T3_rtx timer if it's active. * There is no point in not doing this now and letting * structure hang around in memory since we know * the transport is going away. */ if (del_timer(&transport->T3_rtx_timer)) sctp_transport_put(transport); if (del_timer(&transport->reconf_timer)) sctp_transport_put(transport); if (del_timer(&transport->probe_timer)) sctp_transport_put(transport); /* Delete the ICMP proto unreachable timer if it's active. */ if (del_timer(&transport->proto_unreach_timer)) sctp_transport_put(transport); sctp_transport_put(transport); } static void sctp_transport_destroy_rcu(struct rcu_head *head) { struct sctp_transport *transport; transport = container_of(head, struct sctp_transport, rcu); dst_release(transport->dst); kfree(transport); SCTP_DBG_OBJCNT_DEC(transport); } /* Destroy the transport data structure. * Assumes there are no more users of this structure. */ static void sctp_transport_destroy(struct sctp_transport *transport) { if (unlikely(refcount_read(&transport->refcnt))) { WARN(1, "Attempt to destroy undead transport %p!\n", transport); return; } sctp_packet_free(&transport->packet); if (transport->asoc) sctp_association_put(transport->asoc); call_rcu(&transport->rcu, sctp_transport_destroy_rcu); } /* Start T3_rtx timer if it is not already running and update the heartbeat * timer. This routine is called every time a DATA chunk is sent. */ void sctp_transport_reset_t3_rtx(struct sctp_transport *transport) { /* RFC 2960 6.3.2 Retransmission Timer Rules * * R1) Every time a DATA chunk is sent to any address(including a * retransmission), if the T3-rtx timer of that address is not running * start it running so that it will expire after the RTO of that * address. */ if (!timer_pending(&transport->T3_rtx_timer)) if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) sctp_transport_hold(transport); } void sctp_transport_reset_hb_timer(struct sctp_transport *transport) { unsigned long expires; /* When a data chunk is sent, reset the heartbeat interval. */ expires = jiffies + sctp_transport_timeout(transport); if (!mod_timer(&transport->hb_timer, expires + get_random_u32_below(transport->rto))) sctp_transport_hold(transport); } void sctp_transport_reset_reconf_timer(struct sctp_transport *transport) { if (!timer_pending(&transport->reconf_timer)) if (!mod_timer(&transport->reconf_timer, jiffies + transport->rto)) sctp_transport_hold(transport); } void sctp_transport_reset_probe_timer(struct sctp_transport *transport) { if (!mod_timer(&transport->probe_timer, jiffies + transport->probe_interval)) sctp_transport_hold(transport); } void sctp_transport_reset_raise_timer(struct sctp_transport *transport) { if (!mod_timer(&transport->probe_timer, jiffies + transport->probe_interval * 30)) sctp_transport_hold(transport); } /* This transport has been assigned to an association. * Initialize fields from the association or from the sock itself. * Register the reference count in the association. */ void sctp_transport_set_owner(struct sctp_transport *transport, struct sctp_association *asoc) { transport->asoc = asoc; sctp_association_hold(asoc); } /* Initialize the pmtu of a transport. */ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) { /* If we don't have a fresh route, look one up */ if (!transport->dst || transport->dst->obsolete) { sctp_transport_dst_release(transport); transport->af_specific->get_dst(transport, &transport->saddr, &transport->fl, sk); } if (transport->param_flags & SPP_PMTUD_DISABLE) { struct sctp_association *asoc = transport->asoc; if (!transport->pathmtu && asoc && asoc->pathmtu) transport->pathmtu = asoc->pathmtu; if (transport->pathmtu) return; } if (transport->dst) transport->pathmtu = sctp_dst_mtu(transport->dst); else transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; sctp_transport_pl_update(transport); } void sctp_transport_pl_send(struct sctp_transport *t) { if (t->pl.probe_count < SCTP_MAX_PROBES) goto out; t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */ t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ t->pl.pmtu = SCTP_BASE_PLPMTU; t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); } } else if (t->pl.state == SCTP_PL_SEARCH) { if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */ t->pl.state = SCTP_PL_BASE; /* Search -> Base */ t->pl.probe_size = SCTP_BASE_PLPMTU; t->pl.probe_high = 0; t->pl.pmtu = SCTP_BASE_PLPMTU; t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); } else { /* Normal probe failure. */ t->pl.probe_high = t->pl.probe_size; t->pl.probe_size = t->pl.pmtu; } } else if (t->pl.state == SCTP_PL_COMPLETE) { if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */ t->pl.state = SCTP_PL_BASE; /* Search Complete -> Base */ t->pl.probe_size = SCTP_BASE_PLPMTU; t->pl.pmtu = SCTP_BASE_PLPMTU; t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); } } out: pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); t->pl.probe_count++; } bool sctp_transport_pl_recv(struct sctp_transport *t) { pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); t->pl.pmtu = t->pl.probe_size; t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { t->pl.state = SCTP_PL_SEARCH; /* Base -> Search */ t->pl.probe_size += SCTP_PL_BIG_STEP; } else if (t->pl.state == SCTP_PL_ERROR) { t->pl.state = SCTP_PL_SEARCH; /* Error -> Search */ t->pl.pmtu = t->pl.probe_size; t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); t->pl.probe_size += SCTP_PL_BIG_STEP; } else if (t->pl.state == SCTP_PL_SEARCH) { if (!t->pl.probe_high) { if (t->pl.probe_size < SCTP_MAX_PLPMTU) { t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, SCTP_MAX_PLPMTU); return false; } t->pl.probe_high = SCTP_MAX_PLPMTU; } t->pl.probe_size += SCTP_PL_MIN_STEP; if (t->pl.probe_size >= t->pl.probe_high) { t->pl.probe_high = 0; t->pl.state = SCTP_PL_COMPLETE; /* Search -> Search Complete */ t->pl.probe_size = t->pl.pmtu; t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); sctp_transport_reset_raise_timer(t); } } else if (t->pl.state == SCTP_PL_COMPLETE) { /* Raise probe_size again after 30 * interval in Search Complete */ t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_MIN_STEP, SCTP_MAX_PLPMTU); } return t->pl.state == SCTP_PL_COMPLETE; } static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu) { pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, ptb: %d\n", __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, pmtu); if (pmtu < SCTP_MIN_PLPMTU || pmtu >= t->pl.probe_size) return false; if (t->pl.state == SCTP_PL_BASE) { if (pmtu >= SCTP_MIN_PLPMTU && pmtu < SCTP_BASE_PLPMTU) { t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ t->pl.pmtu = SCTP_BASE_PLPMTU; t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); return true; } } else if (t->pl.state == SCTP_PL_SEARCH) { if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) { t->pl.state = SCTP_PL_BASE; /* Search -> Base */ t->pl.probe_size = SCTP_BASE_PLPMTU; t->pl.probe_count = 0; t->pl.probe_high = 0; t->pl.pmtu = SCTP_BASE_PLPMTU; t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); return true; } else if (pmtu > t->pl.pmtu && pmtu < t->pl.probe_size) { t->pl.probe_size = pmtu; t->pl.probe_count = 0; } } else if (t->pl.state == SCTP_PL_COMPLETE) { if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) { t->pl.state = SCTP_PL_BASE; /* Complete -> Base */ t->pl.probe_size = SCTP_BASE_PLPMTU; t->pl.probe_count = 0; t->pl.probe_high = 0; t->pl.pmtu = SCTP_BASE_PLPMTU; t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_transport_reset_probe_timer(t); return true; } } return false; } bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) { struct sock *sk = t->asoc->base.sk; struct dst_entry *dst; bool change = true; if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) { pr_warn_ratelimited("%s: Reported pmtu %d too low, using default minimum of %d\n", __func__, pmtu, SCTP_DEFAULT_MINSEGMENT); /* Use default minimum segment instead */ pmtu = SCTP_DEFAULT_MINSEGMENT; } pmtu = SCTP_TRUNC4(pmtu); if (sctp_transport_pl_enabled(t)) return sctp_transport_pl_toobig(t, pmtu - sctp_transport_pl_hlen(t)); dst = sctp_transport_dst_check(t); if (dst) { struct sctp_pf *pf = sctp_get_pf_specific(dst->ops->family); union sctp_addr addr; pf->af->from_sk(&addr, sk); pf->to_sk_daddr(&t->ipaddr, sk); dst->ops->update_pmtu(dst, sk, NULL, pmtu, true); pf->to_sk_daddr(&addr, sk); dst = sctp_transport_dst_check(t); } if (!dst) { t->af_specific->get_dst(t, &t->saddr, &t->fl, sk); dst = t->dst; } if (dst) { /* Re-fetch, as under layers may have a higher minimum size */ pmtu = sctp_dst_mtu(dst); change = t->pathmtu != pmtu; } t->pathmtu = pmtu; return change; } /* Caches the dst entry and source address for a transport's destination * address. */ void sctp_transport_route(struct sctp_transport *transport, union sctp_addr *saddr, struct sctp_sock *opt) { struct sctp_association *asoc = transport->asoc; struct sctp_af *af = transport->af_specific; sctp_transport_dst_release(transport); af->get_dst(transport, saddr, &transport->fl, sctp_opt2sk(opt)); if (saddr) memcpy(&transport->saddr, saddr, sizeof(union sctp_addr)); else af->get_saddr(opt, transport, &transport->fl); sctp_transport_pmtu(transport, sctp_opt2sk(opt)); /* Initialize sk->sk_rcv_saddr, if the transport is the * association's active path for getsockname(). */ if (transport->dst && asoc && (!asoc->peer.primary_path || transport == asoc->peer.active_path)) opt->pf->to_sk_saddr(&transport->saddr, asoc->base.sk); } /* Hold a reference to a transport. */ int sctp_transport_hold(struct sctp_transport *transport) { return refcount_inc_not_zero(&transport->refcnt); } /* Release a reference to a transport and clean up * if there are no more references. */ void sctp_transport_put(struct sctp_transport *transport) { if (refcount_dec_and_test(&transport->refcnt)) sctp_transport_destroy(transport); } /* Update transport's RTO based on the newly calculated RTT. */ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) { if (unlikely(!tp->rto_pending)) /* We should not be doing any RTO updates unless rto_pending is set. */ pr_debug("%s: rto_pending not set on transport %p!\n", __func__, tp); if (tp->rttvar || tp->srtt) { struct net *net = tp->asoc->base.net; /* 6.3.1 C3) When a new RTT measurement R' is made, set * RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'| * SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R' */ /* Note: The above algorithm has been rewritten to * express rto_beta and rto_alpha as inverse powers * of two. * For example, assuming the default value of RTO.Alpha of * 1/8, rto_alpha would be expressed as 3. */ tp->rttvar = tp->rttvar - (tp->rttvar >> net->sctp.rto_beta) + (((__u32)abs((__s64)tp->srtt - (__s64)rtt)) >> net->sctp.rto_beta); tp->srtt = tp->srtt - (tp->srtt >> net->sctp.rto_alpha) + (rtt >> net->sctp.rto_alpha); } else { /* 6.3.1 C2) When the first RTT measurement R is made, set * SRTT <- R, RTTVAR <- R/2. */ tp->srtt = rtt; tp->rttvar = rtt >> 1; } /* 6.3.1 G1) Whenever RTTVAR is computed, if RTTVAR = 0, then * adjust RTTVAR <- G, where G is the CLOCK GRANULARITY. */ if (tp->rttvar == 0) tp->rttvar = SCTP_CLOCK_GRANULARITY; /* 6.3.1 C3) After the computation, update RTO <- SRTT + 4 * RTTVAR. */ tp->rto = tp->srtt + (tp->rttvar << 2); /* 6.3.1 C6) Whenever RTO is computed, if it is less than RTO.Min * seconds then it is rounded up to RTO.Min seconds. */ if (tp->rto < tp->asoc->rto_min) tp->rto = tp->asoc->rto_min; /* 6.3.1 C7) A maximum value may be placed on RTO provided it is * at least RTO.max seconds. */ if (tp->rto > tp->asoc->rto_max) tp->rto = tp->asoc->rto_max; sctp_max_rto(tp->asoc, tp); tp->rtt = rtt; /* Reset rto_pending so that a new RTT measurement is started when a * new data chunk is sent. */ tp->rto_pending = 0; pr_debug("%s: transport:%p, rtt:%d, srtt:%d rttvar:%d, rto:%ld\n", __func__, tp, rtt, tp->srtt, tp->rttvar, tp->rto); } /* This routine updates the transport's cwnd and partial_bytes_acked * parameters based on the bytes acked in the received SACK. */ void sctp_transport_raise_cwnd(struct sctp_transport *transport, __u32 sack_ctsn, __u32 bytes_acked) { struct sctp_association *asoc = transport->asoc; __u32 cwnd, ssthresh, flight_size, pba, pmtu; cwnd = transport->cwnd; flight_size = transport->flight_size; /* See if we need to exit Fast Recovery first */ if (asoc->fast_recovery && TSN_lte(asoc->fast_recovery_exit, sack_ctsn)) asoc->fast_recovery = 0; ssthresh = transport->ssthresh; pba = transport->partial_bytes_acked; pmtu = transport->asoc->pathmtu; if (cwnd <= ssthresh) { /* RFC 4960 7.2.1 * o When cwnd is less than or equal to ssthresh, an SCTP * endpoint MUST use the slow-start algorithm to increase * cwnd only if the current congestion window is being fully * utilized, an incoming SACK advances the Cumulative TSN * Ack Point, and the data sender is not in Fast Recovery. * Only when these three conditions are met can the cwnd be * increased; otherwise, the cwnd MUST not be increased. * If these conditions are met, then cwnd MUST be increased * by, at most, the lesser of 1) the total size of the * previously outstanding DATA chunk(s) acknowledged, and * 2) the destination's path MTU. This upper bound protects * against the ACK-Splitting attack outlined in [SAVAGE99]. */ if (asoc->fast_recovery) return; /* The appropriate cwnd increase algorithm is performed * if, and only if the congestion window is being fully * utilized. Note that RFC4960 Errata 3.22 removed the * other condition on ctsn moving. */ if (flight_size < cwnd) return; if (bytes_acked > pmtu) cwnd += pmtu; else cwnd += bytes_acked; pr_debug("%s: slow start: transport:%p, bytes_acked:%d, " "cwnd:%d, ssthresh:%d, flight_size:%d, pba:%d\n", __func__, transport, bytes_acked, cwnd, ssthresh, flight_size, pba); } else { /* RFC 2960 7.2.2 Whenever cwnd is greater than ssthresh, * upon each SACK arrival, increase partial_bytes_acked * by the total number of bytes of all new chunks * acknowledged in that SACK including chunks * acknowledged by the new Cumulative TSN Ack and by Gap * Ack Blocks. (updated by RFC4960 Errata 3.22) * * When partial_bytes_acked is greater than cwnd and * before the arrival of the SACK the sender had less * bytes of data outstanding than cwnd (i.e., before * arrival of the SACK, flightsize was less than cwnd), * reset partial_bytes_acked to cwnd. (RFC 4960 Errata * 3.26) * * When partial_bytes_acked is equal to or greater than * cwnd and before the arrival of the SACK the sender * had cwnd or more bytes of data outstanding (i.e., * before arrival of the SACK, flightsize was greater * than or equal to cwnd), partial_bytes_acked is reset * to (partial_bytes_acked - cwnd). Next, cwnd is * increased by MTU. (RFC 4960 Errata 3.12) */ pba += bytes_acked; if (pba > cwnd && flight_size < cwnd) pba = cwnd; if (pba >= cwnd && flight_size >= cwnd) { pba = pba - cwnd; cwnd += pmtu; } pr_debug("%s: congestion avoidance: transport:%p, " "bytes_acked:%d, cwnd:%d, ssthresh:%d, " "flight_size:%d, pba:%d\n", __func__, transport, bytes_acked, cwnd, ssthresh, flight_size, pba); } transport->cwnd = cwnd; transport->partial_bytes_acked = pba; } /* This routine is used to lower the transport's cwnd when congestion is * detected. */ void sctp_transport_lower_cwnd(struct sctp_transport *transport, enum sctp_lower_cwnd reason) { struct sctp_association *asoc = transport->asoc; switch (reason) { case SCTP_LOWER_CWND_T3_RTX: /* RFC 2960 Section 7.2.3, sctpimpguide * When the T3-rtx timer expires on an address, SCTP should * perform slow start by: * ssthresh = max(cwnd/2, 4*MTU) * cwnd = 1*MTU * partial_bytes_acked = 0 */ transport->ssthresh = max(transport->cwnd/2, 4*asoc->pathmtu); transport->cwnd = asoc->pathmtu; /* T3-rtx also clears fast recovery */ asoc->fast_recovery = 0; break; case SCTP_LOWER_CWND_FAST_RTX: /* RFC 2960 7.2.4 Adjust the ssthresh and cwnd of the * destination address(es) to which the missing DATA chunks * were last sent, according to the formula described in * Section 7.2.3. * * RFC 2960 7.2.3, sctpimpguide Upon detection of packet * losses from SACK (see Section 7.2.4), An endpoint * should do the following: * ssthresh = max(cwnd/2, 4*MTU) * cwnd = ssthresh * partial_bytes_acked = 0 */ if (asoc->fast_recovery) return; /* Mark Fast recovery */ asoc->fast_recovery = 1; asoc->fast_recovery_exit = asoc->next_tsn - 1; transport->ssthresh = max(transport->cwnd/2, 4*asoc->pathmtu); transport->cwnd = transport->ssthresh; break; case SCTP_LOWER_CWND_ECNE: /* RFC 2481 Section 6.1.2. * If the sender receives an ECN-Echo ACK packet * then the sender knows that congestion was encountered in the * network on the path from the sender to the receiver. The * indication of congestion should be treated just as a * congestion loss in non-ECN Capable TCP. That is, the TCP * source halves the congestion window "cwnd" and reduces the * slow start threshold "ssthresh". * A critical condition is that TCP does not react to * congestion indications more than once every window of * data (or more loosely more than once every round-trip time). */ if (time_after(jiffies, transport->last_time_ecne_reduced + transport->rtt)) { transport->ssthresh = max(transport->cwnd/2, 4*asoc->pathmtu); transport->cwnd = transport->ssthresh; transport->last_time_ecne_reduced = jiffies; } break; case SCTP_LOWER_CWND_INACTIVE: /* RFC 2960 Section 7.2.1, sctpimpguide * When the endpoint does not transmit data on a given * transport address, the cwnd of the transport address * should be adjusted to max(cwnd/2, 4*MTU) per RTO. * NOTE: Although the draft recommends that this check needs * to be done every RTO interval, we do it every hearbeat * interval. */ transport->cwnd = max(transport->cwnd/2, 4*asoc->pathmtu); /* RFC 4960 Errata 3.27.2: also adjust sshthresh */ transport->ssthresh = transport->cwnd; break; } transport->partial_bytes_acked = 0; pr_debug("%s: transport:%p, reason:%d, cwnd:%d, ssthresh:%d\n", __func__, transport, reason, transport->cwnd, transport->ssthresh); } /* Apply Max.Burst limit to the congestion window: * sctpimpguide-05 2.14.2 * D) When the time comes for the sender to * transmit new DATA chunks, the protocol parameter Max.Burst MUST * first be applied to limit how many new DATA chunks may be sent. * The limit is applied by adjusting cwnd as follows: * if ((flightsize+ Max.Burst * MTU) < cwnd) * cwnd = flightsize + Max.Burst * MTU */ void sctp_transport_burst_limited(struct sctp_transport *t) { struct sctp_association *asoc = t->asoc; u32 old_cwnd = t->cwnd; u32 max_burst_bytes; if (t->burst_limited || asoc->max_burst == 0) return; max_burst_bytes = t->flight_size + (asoc->max_burst * asoc->pathmtu); if (max_burst_bytes < old_cwnd) { t->cwnd = max_burst_bytes; t->burst_limited = old_cwnd; } } /* Restore the old cwnd congestion window, after the burst had it's * desired effect. */ void sctp_transport_burst_reset(struct sctp_transport *t) { if (t->burst_limited) { t->cwnd = t->burst_limited; t->burst_limited = 0; } } /* What is the next timeout value for this transport? */ unsigned long sctp_transport_timeout(struct sctp_transport *trans) { /* RTO + timer slack +/- 50% of RTO */ unsigned long timeout = trans->rto >> 1; if (trans->state != SCTP_UNCONFIRMED && trans->state != SCTP_PF) timeout += trans->hbinterval; return max_t(unsigned long, timeout, HZ / 5); } /* Reset transport variables to their initial values */ void sctp_transport_reset(struct sctp_transport *t) { struct sctp_association *asoc = t->asoc; /* RFC 2960 (bis), Section 5.2.4 * All the congestion control parameters (e.g., cwnd, ssthresh) * related to this peer MUST be reset to their initial values * (see Section 6.2.1) */ t->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); t->burst_limited = 0; t->ssthresh = asoc->peer.i.a_rwnd; t->rto = asoc->rto_initial; sctp_max_rto(asoc, t); t->rtt = 0; t->srtt = 0; t->rttvar = 0; /* Reset these additional variables so that we have a clean slate. */ t->partial_bytes_acked = 0; t->flight_size = 0; t->error_count = 0; t->rto_pending = 0; t->hb_sent = 0; /* Initialize the state information for SFR-CACC */ t->cacc.changeover_active = 0; t->cacc.cycling_changeover = 0; t->cacc.next_tsn_at_change = 0; t->cacc.cacc_saw_newack = 0; } /* Schedule retransmission on the given transport */ void sctp_transport_immediate_rtx(struct sctp_transport *t) { /* Stop pending T3_rtx_timer */ if (del_timer(&t->T3_rtx_timer)) sctp_transport_put(t); sctp_retransmit(&t->asoc->outqueue, t, SCTP_RTXR_T3_RTX); if (!timer_pending(&t->T3_rtx_timer)) { if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto)) sctp_transport_hold(t); } } /* Drop dst */ void sctp_transport_dst_release(struct sctp_transport *t) { dst_release(t->dst); t->dst = NULL; t->dst_pending_confirm = 0; } /* Schedule neighbour confirm */ void sctp_transport_dst_confirm(struct sctp_transport *t) { t->dst_pending_confirm = 1; } |
| 3 3 3 3 3 3 3 3 3 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/super.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include <linux/module.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/time.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/parser.h> #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/vfs.h> #include <linux/random.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/quotaops.h> #include <linux/seq_file.h> #include <linux/ctype.h> #include <linux/log2.h> #include <linux/crc16.h> #include <linux/dax.h> #include <linux/uaccess.h> #include <linux/iversion.h> #include <linux/unicode.h> #include <linux/part_stat.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/fsnotify.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include "ext4.h" #include "ext4_extents.h" /* Needed for trace points definition */ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "mballoc.h" #include "fsmap.h" #define CREATE_TRACE_POINTS #include <trace/events/ext4.h> static struct ext4_lazy_init *ext4_li_info; static DEFINE_MUTEX(ext4_li_mtx); static struct ratelimit_state ext4_mount_msg_ratelimit; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); static void ext4_update_super(struct super_block *sb); static int ext4_commit_super(struct super_block *sb); static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static inline int ext2_feature_set_ok(struct super_block *sb); static inline int ext3_feature_set_ok(struct super_block *sb); static void ext4_destroy_lazyinit_thread(void); static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); static struct inode *ext4_get_journal_inode(struct super_block *sb, unsigned int journal_inum); static int ext4_validate_options(struct fs_context *fc); static int ext4_check_opt_consistency(struct fs_context *fc, struct super_block *sb); static void ext4_apply_options(struct fs_context *fc, struct super_block *sb); static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param); static int ext4_get_tree(struct fs_context *fc); static int ext4_reconfigure(struct fs_context *fc); static void ext4_fc_free(struct fs_context *fc); static int ext4_init_fs_context(struct fs_context *fc); static void ext4_kill_sb(struct super_block *sb); static const struct fs_parameter_spec ext4_param_specs[]; /* * Lock ordering * * page fault path: * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start * -> page lock -> i_data_sem (rw) * * buffered write path: * sb_start_write -> i_mutex -> mmap_lock * sb_start_write -> i_mutex -> transaction start -> page lock -> * i_data_sem (rw) * * truncate: * sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) -> * page lock * sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start -> * i_data_sem (rw) * * direct IO: * sb_start_write -> i_mutex -> mmap_lock * sb_start_write -> i_mutex -> transaction start -> i_data_sem (rw) * * writepages: * transaction start -> page lock(s) -> i_data_sem (rw) */ static const struct fs_context_operations ext4_context_ops = { .parse_param = ext4_parse_param, .get_tree = ext4_get_tree, .reconfigure = ext4_reconfigure, .free = ext4_fc_free, }; #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static struct file_system_type ext2_fs_type = { .owner = THIS_MODULE, .name = "ext2", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext2"); MODULE_ALIAS("ext2"); #define IS_EXT2_SB(sb) ((sb)->s_type == &ext2_fs_type) #else #define IS_EXT2_SB(sb) (0) #endif static struct file_system_type ext3_fs_type = { .owner = THIS_MODULE, .name = "ext3", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext3"); MODULE_ALIAS("ext3"); #define IS_EXT3_SB(sb) ((sb)->s_type == &ext3_fs_type) static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io) { /* * buffer's verified bit is no longer valid after reading from * disk again due to write out error, clear it to make sure we * recheck the buffer contents. */ clear_buffer_verified(bh); bh->b_end_io = end_io ? end_io : end_buffer_read_sync; get_bh(bh); submit_bh(REQ_OP_READ | op_flags, bh); } void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io) { BUG_ON(!buffer_locked(bh)); if (ext4_buffer_uptodate(bh)) { unlock_buffer(bh); return; } __ext4_read_bh(bh, op_flags, end_io); } int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io) { BUG_ON(!buffer_locked(bh)); if (ext4_buffer_uptodate(bh)) { unlock_buffer(bh); return 0; } __ext4_read_bh(bh, op_flags, end_io); wait_on_buffer(bh); if (buffer_uptodate(bh)) return 0; return -EIO; } int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { lock_buffer(bh); if (!wait) { ext4_read_bh_nowait(bh, op_flags, NULL); return 0; } return ext4_read_bh(bh, op_flags, NULL); } /* * This works like __bread_gfp() except it uses ERR_PTR for error * returns. Currently with sb_bread it's impossible to distinguish * between ENOMEM and EIO situations (since both result in a NULL * return. */ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb, sector_t block, blk_opf_t op_flags, gfp_t gfp) { struct buffer_head *bh; int ret; bh = sb_getblk_gfp(sb, block, gfp); if (bh == NULL) return ERR_PTR(-ENOMEM); if (ext4_buffer_uptodate(bh)) return bh; ret = ext4_read_bh_lock(bh, REQ_META | op_flags, true); if (ret) { put_bh(bh); return ERR_PTR(ret); } return bh; } struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, blk_opf_t op_flags) { gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS) | __GFP_MOVABLE; return __ext4_sb_bread_gfp(sb, block, op_flags, gfp); } struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block) { gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS); return __ext4_sb_bread_gfp(sb, block, 0, gfp); } void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) { struct buffer_head *bh = bdev_getblk(sb->s_bdev, block, sb->s_blocksize, GFP_NOWAIT | __GFP_NOWARN); if (likely(bh)) { if (trylock_buffer(bh)) ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL); brelse(bh); } } static int ext4_verify_csum_type(struct super_block *sb, struct ext4_super_block *es) { if (!ext4_has_feature_metadata_csum(sb)) return 1; return es->s_checksum_type == EXT4_CRC32C_CHKSUM; } __le32 ext4_superblock_csum(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); int offset = offsetof(struct ext4_super_block, s_checksum); __u32 csum; csum = ext4_chksum(sbi, ~0, (char *)es, offset); return cpu_to_le32(csum); } static int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es) { if (!ext4_has_metadata_csum(sb)) return 1; return es->s_checksum == ext4_superblock_csum(sb, es); } void ext4_superblock_csum_set(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (!ext4_has_metadata_csum(sb)) return; es->s_checksum = ext4_superblock_csum(sb, es); } ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_block_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_inode_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_table(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_inode_table_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); } __u32 ext4_free_group_clusters(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_free_blocks_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0); } __u32 ext4_free_inodes_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_free_inodes_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0); } __u32 ext4_used_dirs_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_used_dirs_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0); } __u32 ext4_itable_unused_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_itable_unused_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0); } void ext4_block_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32); } void ext4_inode_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32); } void ext4_inode_table_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_inode_table_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_table_hi = cpu_to_le32(blk >> 32); } void ext4_free_group_clusters_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16); } void ext4_free_inodes_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16); } void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16); } void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_itable_unused_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_itable_unused_hi = cpu_to_le16(count >> 16); } static void __ext4_update_tstamp(__le32 *lo, __u8 *hi, time64_t now) { now = clamp_val(now, 0, (1ull << 40) - 1); *lo = cpu_to_le32(lower_32_bits(now)); *hi = upper_32_bits(now); } static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) { return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo); } #define ext4_update_tstamp(es, tstamp) \ __ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi, \ ktime_get_real_seconds()) #define ext4_get_tstamp(es, tstamp) \ __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) #define EXT4_SB_REFRESH_INTERVAL_SEC (3600) /* seconds (1 hour) */ #define EXT4_SB_REFRESH_INTERVAL_KB (16384) /* kilobytes (16MB) */ /* * The ext4_maybe_update_superblock() function checks and updates the * superblock if needed. * * This function is designed to update the on-disk superblock only under * certain conditions to prevent excessive disk writes and unnecessary * waking of the disk from sleep. The superblock will be updated if: * 1. More than an hour has passed since the last superblock update, and * 2. More than 16MB have been written since the last superblock update. * * @sb: The superblock */ static void ext4_maybe_update_superblock(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; journal_t *journal = sbi->s_journal; time64_t now; __u64 last_update; __u64 lifetime_write_kbytes; __u64 diff_size; if (sb_rdonly(sb) || !(sb->s_flags & SB_ACTIVE) || !journal || (journal->j_flags & JBD2_UNMOUNT)) return; now = ktime_get_real_seconds(); last_update = ext4_get_tstamp(es, s_wtime); if (likely(now - last_update < EXT4_SB_REFRESH_INTERVAL_SEC)) return; lifetime_write_kbytes = sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1); /* Get the number of kilobytes not written to disk to account * for statistics and compare with a multiple of 16 MB. This * is used to determine when the next superblock commit should * occur (i.e. not more often than once per 16MB if there was * less written in an hour). */ diff_size = lifetime_write_kbytes - le64_to_cpu(es->s_kbytes_written); if (diff_size > EXT4_SB_REFRESH_INTERVAL_KB) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); int error = is_journal_aborted(journal); struct ext4_journal_cb_entry *jce; BUG_ON(txn->t_state == T_FINISHED); ext4_process_freed_data(sb, txn->t_tid); ext4_maybe_update_superblock(sb); spin_lock(&sbi->s_md_lock); while (!list_empty(&txn->t_private_list)) { jce = list_entry(txn->t_private_list.next, struct ext4_journal_cb_entry, jce_list); list_del_init(&jce->jce_list); spin_unlock(&sbi->s_md_lock); jce->jce_func(sb, jce, error); spin_lock(&sbi->s_md_lock); } spin_unlock(&sbi->s_md_lock); } /* * This writepage callback for write_cache_pages() * takes care of a few cases after page cleaning. * * write_cache_pages() already checks for dirty pages * and calls clear_page_dirty_for_io(), which we want, * to write protect the pages. * * However, we may have to redirty a page (see below.) */ static int ext4_journalled_writepage_callback(struct folio *folio, struct writeback_control *wbc, void *data) { transaction_t *transaction = (transaction_t *) data; struct buffer_head *bh, *head; struct journal_head *jh; bh = head = folio_buffers(folio); do { /* * We have to redirty a page in these cases: * 1) If buffer is dirty, it means the page was dirty because it * contains a buffer that needs checkpointing. So the dirty bit * needs to be preserved so that checkpointing writes the buffer * properly. * 2) If buffer is not part of the committing transaction * (we may have just accidentally come across this buffer because * inode range tracking is not exact) or if the currently running * transaction already contains this buffer as well, dirty bit * needs to be preserved so that the buffer gets writeprotected * properly on running transaction's commit. */ jh = bh2jh(bh); if (buffer_dirty(bh) || (jh && (jh->b_transaction != transaction || jh->b_next_transaction))) { folio_redirty_for_writepage(wbc, folio); goto out; } } while ((bh = bh->b_this_page) != head); out: return AOP_WRITEPAGE_ACTIVATE; } static int ext4_journalled_submit_inode_data_buffers(struct jbd2_inode *jinode) { struct address_space *mapping = jinode->i_vfs_inode->i_mapping; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .range_start = jinode->i_dirty_start, .range_end = jinode->i_dirty_end, }; return write_cache_pages(mapping, &wbc, ext4_journalled_writepage_callback, jinode->i_transaction); } static int ext4_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) { int ret; if (ext4_should_journal_data(jinode->i_vfs_inode)) ret = ext4_journalled_submit_inode_data_buffers(jinode); else ret = ext4_normal_submit_inode_data_buffers(jinode); return ret; } static int ext4_journal_finish_inode_data_buffers(struct jbd2_inode *jinode) { int ret = 0; if (!ext4_should_journal_data(jinode->i_vfs_inode)) ret = jbd2_journal_finish_inode_data_buffers(jinode); return ret; } static bool system_going_down(void) { return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || system_state == SYSTEM_RESTART; } struct ext4_err_translation { int code; int errno; }; #define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err } static struct ext4_err_translation err_translation[] = { EXT4_ERR_TRANSLATE(EIO), EXT4_ERR_TRANSLATE(ENOMEM), EXT4_ERR_TRANSLATE(EFSBADCRC), EXT4_ERR_TRANSLATE(EFSCORRUPTED), EXT4_ERR_TRANSLATE(ENOSPC), EXT4_ERR_TRANSLATE(ENOKEY), EXT4_ERR_TRANSLATE(EROFS), EXT4_ERR_TRANSLATE(EFBIG), EXT4_ERR_TRANSLATE(EEXIST), EXT4_ERR_TRANSLATE(ERANGE), EXT4_ERR_TRANSLATE(EOVERFLOW), EXT4_ERR_TRANSLATE(EBUSY), EXT4_ERR_TRANSLATE(ENOTDIR), EXT4_ERR_TRANSLATE(ENOTEMPTY), EXT4_ERR_TRANSLATE(ESHUTDOWN), EXT4_ERR_TRANSLATE(EFAULT), }; static int ext4_errno_to_code(int errno) { int i; for (i = 0; i < ARRAY_SIZE(err_translation); i++) if (err_translation[i].errno == errno) return err_translation[i].code; return EXT4_ERR_UNKNOWN; } static void save_error_info(struct super_block *sb, int error, __u32 ino, __u64 block, const char *func, unsigned int line) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* We default to EFSCORRUPTED error... */ if (error == 0) error = EFSCORRUPTED; spin_lock(&sbi->s_error_lock); sbi->s_add_error_count++; sbi->s_last_error_code = error; sbi->s_last_error_line = line; sbi->s_last_error_ino = ino; sbi->s_last_error_block = block; sbi->s_last_error_func = func; sbi->s_last_error_time = ktime_get_real_seconds(); if (!sbi->s_first_error_time) { sbi->s_first_error_code = error; sbi->s_first_error_line = line; sbi->s_first_error_ino = ino; sbi->s_first_error_block = block; sbi->s_first_error_func = func; sbi->s_first_error_time = sbi->s_last_error_time; } spin_unlock(&sbi->s_error_lock); } /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * * On ext2, we can store the error state of the filesystem in the * superblock. That is not possible on ext4, because we may have other * write ordering constraints on the superblock which prevent us from * writing it out straight away; and given that the journal is about to * be aborted, we can't rely on the current, or future, transactions to * write out the superblock safely. * * We'll just use the jbd2_journal_abort() error code to record an error in * the journal instead. On recovery, the journal will complain about * that error until we've noted it down and cleared it. * * If force_ro is set, we unconditionally force the filesystem into an * ABORT|READONLY state, unless the error response on the fs has been set to * panic in which case we take the easy way out and panic immediately. This is * used to deal with unrecoverable failures such as journal IO errors or ENOMEM * at a critical moment in log management. */ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, __u32 ino, __u64 block, const char *func, unsigned int line) { journal_t *journal = EXT4_SB(sb)->s_journal; bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); if (!continue_fs && !sb_rdonly(sb)) { set_bit(EXT4_FLAGS_SHUTDOWN, &EXT4_SB(sb)->s_ext4_flags); if (journal) jbd2_journal_abort(journal, -EIO); } if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, error, ino, block, func, line); /* * In case the fs should keep running, we need to writeout * superblock through the journal. Due to lock ordering * constraints, it may not be safe to do it right here so we * defer superblock flushing to a workqueue. */ if (continue_fs && journal) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); else ext4_commit_super(sb); } /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already * disabled. */ if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) { panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); } if (sb_rdonly(sb) || continue_fs) return; ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* * Make sure updated value of ->s_mount_flags will be visible before * ->s_flags update */ smp_wmb(); sb->s_flags |= SB_RDONLY; } static void update_super_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, s_sb_upd_work); journal_t *journal = sbi->s_journal; handle_t *handle; /* * If the journal is still running, we have to write out superblock * through the journal to avoid collisions of other journalled sb * updates. * * We use directly jbd2 functions here to avoid recursing back into * ext4 error handling code during handling of previous errors. */ if (!sb_rdonly(sbi->s_sb) && journal) { struct buffer_head *sbh = sbi->s_sbh; bool call_notify_err = false; handle = jbd2_journal_start(journal, 1); if (IS_ERR(handle)) goto write_directly; if (jbd2_journal_get_write_access(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } if (sbi->s_add_error_count > 0) call_notify_err = true; ext4_update_super(sbi->s_sb); if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } if (jbd2_journal_dirty_metadata(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } jbd2_journal_stop(handle); if (call_notify_err) ext4_notify_error_sysfs(sbi); return; } write_directly: /* * Write through journal failed. Write sb directly to get error info * out and hope for the best. */ ext4_commit_super(sbi->s_sb); ext4_notify_error_sysfs(sbi); } #define ext4_error_ratelimit(sb) \ ___ratelimit(&(EXT4_SB(sb)->s_err_ratelimit_state), \ "EXT4-fs error") void __ext4_error(struct super_block *sb, const char *function, unsigned int line, bool force_ro, int error, __u64 block, const char *fmt, ...) { struct va_format vaf; va_list args; if (unlikely(ext4_forced_shutdown(sb))) return; trace_ext4_error(sb, function, line); if (ext4_error_ratelimit(sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n", sb->s_id, function, line, current->comm, &vaf); va_end(args); } fsnotify_sb_error(sb, NULL, error ? error : EFSCORRUPTED); ext4_handle_error(sb, force_ro, error, 0, block, function, line); } void __ext4_error_inode(struct inode *inode, const char *function, unsigned int line, ext4_fsblk_t block, int error, const char *fmt, ...) { va_list args; struct va_format vaf; if (unlikely(ext4_forced_shutdown(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); if (ext4_error_ratelimit(inode->i_sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (block) printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: " "inode #%lu: block %llu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, block, current->comm, &vaf); else printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: " "inode #%lu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, &vaf); va_end(args); } fsnotify_sb_error(inode->i_sb, inode, error ? error : EFSCORRUPTED); ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block, function, line); } void __ext4_error_file(struct file *file, const char *function, unsigned int line, ext4_fsblk_t block, const char *fmt, ...) { va_list args; struct va_format vaf; struct inode *inode = file_inode(file); char pathname[80], *path; if (unlikely(ext4_forced_shutdown(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); if (ext4_error_ratelimit(inode->i_sb)) { path = file_path(file, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (block) printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: " "block %llu: comm %s: path %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, block, current->comm, path, &vaf); else printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: " "comm %s: path %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, path, &vaf); va_end(args); } fsnotify_sb_error(inode->i_sb, inode, EFSCORRUPTED); ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block, function, line); } const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]) { char *errstr = NULL; switch (errno) { case -EFSCORRUPTED: errstr = "Corrupt filesystem"; break; case -EFSBADCRC: errstr = "Filesystem failed CRC"; break; case -EIO: errstr = "IO failure"; break; case -ENOMEM: errstr = "Out of memory"; break; case -EROFS: if (!sb || (EXT4_SB(sb)->s_journal && EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT)) errstr = "Journal has aborted"; else errstr = "Readonly filesystem"; break; default: /* If the caller passed in an extra buffer for unknown * errors, textualise them now. Else we just return * NULL. */ if (nbuf) { /* Check for truncated error codes... */ if (snprintf(nbuf, 16, "error %d", -errno) >= 0) errstr = nbuf; } break; } return errstr; } /* __ext4_std_error decodes expected errors from journaling functions * automatically and invokes the appropriate error response. */ void __ext4_std_error(struct super_block *sb, const char *function, unsigned int line, int errno) { char nbuf[16]; const char *errstr; if (unlikely(ext4_forced_shutdown(sb))) return; /* Special case: if the error is EROFS, and we're not already * inside a transaction, then there's really no point in logging * an error. */ if (errno == -EROFS && journal_current_handle() == NULL && sb_rdonly(sb)) return; if (ext4_error_ratelimit(sb)) { errstr = ext4_decode_error(sb, errno, nbuf); printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n", sb->s_id, function, line, errstr); } fsnotify_sb_error(sb, NULL, errno ? errno : EFSCORRUPTED); ext4_handle_error(sb, false, -errno, 0, 0, function, line); } void __ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...) { struct va_format vaf; va_list args; if (sb) { atomic_inc(&EXT4_SB(sb)->s_msg_count); if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs")) return; } va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (sb) printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf); else printk("%sEXT4-fs: %pV\n", prefix, &vaf); va_end(args); } static int ext4_warning_ratelimit(struct super_block *sb) { atomic_inc(&EXT4_SB(sb)->s_warning_count); return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), "EXT4-fs warning"); } void __ext4_warning(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; if (!ext4_warning_ratelimit(sb)) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: %pV\n", sb->s_id, function, line, &vaf); va_end(args); } void __ext4_warning_inode(const struct inode *inode, const char *function, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; if (!ext4_warning_ratelimit(inode->i_sb)) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: " "inode #%lu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, &vaf); va_end(args); } void __ext4_grp_locked_error(const char *function, unsigned int line, struct super_block *sb, ext4_group_t grp, unsigned long ino, ext4_fsblk_t block, const char *fmt, ...) __releases(bitlock) __acquires(bitlock) { struct va_format vaf; va_list args; if (unlikely(ext4_forced_shutdown(sb))) return; trace_ext4_error(sb, function, line); if (ext4_error_ratelimit(sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ", sb->s_id, function, line, grp); if (ino) printk(KERN_CONT "inode %lu: ", ino); if (block) printk(KERN_CONT "block %llu:", (unsigned long long) block); printk(KERN_CONT "%pV\n", &vaf); va_end(args); } if (test_opt(sb, ERRORS_CONT)) { if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, EFSCORRUPTED, ino, block, function, line); schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } return; } ext4_unlock_group(sb, grp); ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line); /* * We only get here in the ERRORS_RO case; relocking the group * may be dangerous, but nothing bad will happen since the * filesystem will have already been marked read/only and the * journal has been aborted. We return 1 as a hint to callers * who might what to use the return value from * ext4_grp_locked_error() to distinguish between the * ERRORS_CONT and ERRORS_RO case, and perhaps return more * aggressively from the ext4 function in question, with a * more appropriate error code. */ ext4_lock_group(sb, grp); return; } void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t group, unsigned int flags) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; if (!grp || !gdp) return; if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); if (!ret) percpu_counter_sub(&sbi->s_freeclusters_counter, grp->bb_free); } if (flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); if (!ret && gdp) { int count; count = ext4_free_inodes_count(sb, gdp); percpu_counter_sub(&sbi->s_freeinodes_counter, count); } } } void ext4_update_dynamic_rev(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV) return; ext4_warning(sb, "updating to rev %d because of new feature flag, " "running e2fsck is recommended", EXT4_DYNAMIC_REV); es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO); es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE); es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV); /* leave es->s_feature_*compat flags alone */ /* es->s_uuid will be set by e2fsck if empty */ /* * The rest of the superblock fields should be zero, and if not it * means they are likely already in use, so leave them alone. We * can leave it up to e2fsck to clean up any inconsistencies there. */ } static inline struct inode *orphan_list_entry(struct list_head *l) { return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode; } static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi) { struct list_head *l; ext4_msg(sb, KERN_ERR, "sb orphan head is %d", le32_to_cpu(sbi->s_es->s_last_orphan)); printk(KERN_ERR "sb_info orphan list:\n"); list_for_each(l, &sbi->s_orphan) { struct inode *inode = orphan_list_entry(l); printk(KERN_ERR " " "inode %s:%lu at %p: mode %o, nlink %d, next %d\n", inode->i_sb->s_id, inode->i_ino, inode, inode->i_mode, inode->i_nlink, NEXT_ORPHAN(inode)); } } #ifdef CONFIG_QUOTA static int ext4_quota_off(struct super_block *sb, int type); static inline void ext4_quotas_off(struct super_block *sb, int type) { BUG_ON(type > EXT4_MAXQUOTAS); /* Use our quota_off function to clear inode flags etc. */ for (type--; type >= 0; type--) ext4_quota_off(sb, type); } /* * This is a helper function which is used in the mount/remount * codepaths (which holds s_umount) to fetch the quota file name. */ static inline char *get_qf_name(struct super_block *sb, struct ext4_sb_info *sbi, int type) { return rcu_dereference_protected(sbi->s_qf_names[type], lockdep_is_held(&sb->s_umount)); } #else static inline void ext4_quotas_off(struct super_block *sb, int type) { } #endif static int ext4_percpu_param_init(struct ext4_sb_info *sbi) { ext4_fsblk_t block; int err; block = ext4_count_free_clusters(sbi->s_sb); ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); err = percpu_counter_init(&sbi->s_freeclusters_counter, block, GFP_KERNEL); if (!err) { unsigned long freei = ext4_count_free_inodes(sbi->s_sb); sbi->s_es->s_free_inodes_count = cpu_to_le32(freei); err = percpu_counter_init(&sbi->s_freeinodes_counter, freei, GFP_KERNEL); } if (!err) err = percpu_counter_init(&sbi->s_dirs_counter, ext4_count_dirs(sbi->s_sb), GFP_KERNEL); if (!err) err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0, GFP_KERNEL); if (!err) err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0, GFP_KERNEL); if (!err) err = percpu_init_rwsem(&sbi->s_writepages_rwsem); if (err) ext4_msg(sbi->s_sb, KERN_ERR, "insufficient memory"); return err; } static void ext4_percpu_param_destroy(struct ext4_sb_info *sbi) { percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit); percpu_free_rwsem(&sbi->s_writepages_rwsem); } static void ext4_group_desc_free(struct ext4_sb_info *sbi) { struct buffer_head **group_desc; int i; rcu_read_lock(); group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < sbi->s_gdb_count; i++) brelse(group_desc[i]); kvfree(group_desc); rcu_read_unlock(); } static void ext4_flex_groups_free(struct ext4_sb_info *sbi) { struct flex_groups **flex_groups; int i; rcu_read_lock(); flex_groups = rcu_dereference(sbi->s_flex_groups); if (flex_groups) { for (i = 0; i < sbi->s_flex_groups_allocated; i++) kvfree(flex_groups[i]); kvfree(flex_groups); } rcu_read_unlock(); } static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int aborted = 0; int err; /* * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL * Unregister sysfs before flush sbi->s_sb_upd_work. * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If * read metadata verify failed then will queue error work. * update_super_work will call start_this_handle may trigger * BUG_ON. */ ext4_unregister_sysfs(sb); if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs unmount")) ext4_msg(sb, KERN_INFO, "unmounting filesystem %pU.", &sb->s_uuid); ext4_unregister_li_request(sb); ext4_quotas_off(sb, EXT4_MAXQUOTAS); flush_work(&sbi->s_sb_upd_work); destroy_workqueue(sbi->rsv_conversion_wq); ext4_release_orphan_info(sb); if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; if ((err < 0) && !aborted) { ext4_abort(sb, -err, "Couldn't clean up the journal"); } } ext4_es_unregister_shrinker(sbi); timer_shutdown_sync(&sbi->s_err_report); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); if (!sb_rdonly(sb) && !aborted) { ext4_clear_feature_journal_needs_recovery(sb); ext4_clear_feature_orphan_present(sb); es->s_state = cpu_to_le16(sbi->s_mount_state); } if (!sb_rdonly(sb)) ext4_commit_super(sb); ext4_group_desc_free(sbi); ext4_flex_groups_free(sbi); ext4_percpu_param_destroy(sbi); #ifdef CONFIG_QUOTA for (int i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); #endif /* Debugging code just in case the in-memory inode orphan list * isn't empty. The on-disk one can be non-empty if we've * detected an error and taken the fs readonly, but the * in-memory list had better be clean by this point. */ if (!list_empty(&sbi->s_orphan)) dump_orphan_list(sb, sbi); ASSERT(list_empty(&sbi->s_orphan)); sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); if (sbi->s_journal_bdev_file) { /* * Invalidate the journal device's buffers. We don't want them * floating about in memory - the physical journal device may * hotswapped, and it breaks the `ro-after' testing code. */ sync_blockdev(file_bdev(sbi->s_journal_bdev_file)); invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); } ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); sbi->s_ea_inode_cache = NULL; ext4_xattr_destroy_cache(sbi->s_ea_block_cache); sbi->s_ea_block_cache = NULL; ext4_stop_mmpd(sbi); brelse(sbi->s_sbh); sb->s_fs_info = NULL; /* * Now that we are completely done shutting down the * superblock, we need to actually destroy the kobject. */ kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev, NULL); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); } static struct kmem_cache *ext4_inode_cachep; /* * Called inside transaction, so use GFP_NOFS */ static struct inode *ext4_alloc_inode(struct super_block *sb) { struct ext4_inode_info *ei; ei = alloc_inode_sb(sb, ext4_inode_cachep, GFP_NOFS); if (!ei) return NULL; inode_set_iversion(&ei->vfs_inode, 1); ei->i_flags = 0; spin_lock_init(&ei->i_raw_lock); ei->i_prealloc_node = RB_ROOT; atomic_set(&ei->i_prealloc_active, 0); rwlock_init(&ei->i_prealloc_lock); ext4_es_init_tree(&ei->i_es_tree); rwlock_init(&ei->i_es_lock); INIT_LIST_HEAD(&ei->i_es_list); ei->i_es_all_nr = 0; ei->i_es_shk_nr = 0; ei->i_es_shrink_lblk = 0; ei->i_reserved_data_blocks = 0; spin_lock_init(&(ei->i_block_reservation_lock)); ext4_init_pending_tree(&ei->i_pending_tree); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); #endif ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_rsv_conversion_list); spin_lock_init(&ei->i_completed_io_lock); ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_unwritten, 0); INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); ext4_fc_init_inode(&ei->vfs_inode); mutex_init(&ei->i_fc_lock); return &ei->vfs_inode; } static int ext4_drop_inode(struct inode *inode) { int drop = generic_drop_inode(inode); if (!drop) drop = fscrypt_drop_inode(inode); trace_ext4_drop_inode(inode, drop); return drop; } static void ext4_free_in_core_inode(struct inode *inode) { fscrypt_free_inode(inode); if (!list_empty(&(EXT4_I(inode)->i_fc_list))) { pr_warn("%s: inode %ld still in fc list", __func__, inode->i_ino); } kmem_cache_free(ext4_inode_cachep, EXT4_I(inode)); } static void ext4_destroy_inode(struct inode *inode) { if (!list_empty(&(EXT4_I(inode)->i_orphan))) { ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): orphan list check failed!", inode->i_ino, EXT4_I(inode)); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4, EXT4_I(inode), sizeof(struct ext4_inode_info), true); dump_stack(); } if (EXT4_I(inode)->i_reserved_data_blocks) ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!", inode->i_ino, EXT4_I(inode), EXT4_I(inode)->i_reserved_data_blocks); } static void ext4_shutdown(struct super_block *sb) { ext4_force_shutdown(sb, EXT4_GOING_FLAGS_NOLOGFLUSH); } static void init_once(void *foo) { struct ext4_inode_info *ei = foo; INIT_LIST_HEAD(&ei->i_orphan); init_rwsem(&ei->xattr_sem); init_rwsem(&ei->i_data_sem); inode_init_once(&ei->vfs_inode); ext4_fc_init_inode(&ei->vfs_inode); } static int __init init_inodecache(void) { ext4_inode_cachep = kmem_cache_create_usercopy("ext4_inode_cache", sizeof(struct ext4_inode_info), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, offsetof(struct ext4_inode_info, i_data), sizeof_field(struct ext4_inode_info, i_data), init_once); if (ext4_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(ext4_inode_cachep); } void ext4_clear_inode(struct inode *inode) { ext4_fc_del(inode); invalidate_inode_buffers(inode); clear_inode(inode); ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode); jbd2_free_inode(EXT4_I(inode)->jinode); EXT4_I(inode)->jinode = NULL; } fscrypt_put_encryption_info(inode); fsverity_cleanup_inode(inode); } static struct inode *ext4_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation) { struct inode *inode; /* * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ inode = ext4_iget(sb, ino, EXT4_IGET_HANDLE); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { iput(inode); return ERR_PTR(-ESTALE); } return inode; } static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_dentry(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_parent(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static int ext4_nfs_commit_metadata(struct inode *inode) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL }; trace_ext4_nfs_commit_metadata(inode); return ext4_write_inode(inode, &wbc); } #ifdef CONFIG_QUOTA static const char * const quotatypes[] = INITQFNAMES; #define QTYPE2NAME(t) (quotatypes[t]) static int ext4_write_dquot(struct dquot *dquot); static int ext4_acquire_dquot(struct dquot *dquot); static int ext4_release_dquot(struct dquot *dquot); static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, const struct path *path); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags); static struct dquot __rcu **ext4_get_dquots(struct inode *inode) { return EXT4_I(inode)->i_dquot; } static const struct dquot_operations ext4_quota_operations = { .get_reserved_space = ext4_get_reserved_space, .write_dquot = ext4_write_dquot, .acquire_dquot = ext4_acquire_dquot, .release_dquot = ext4_release_dquot, .mark_dirty = ext4_mark_dquot_dirty, .write_info = ext4_write_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .get_projid = ext4_get_projid, .get_inode_usage = ext4_get_inode_usage, .get_next_id = dquot_get_next_id, }; static const struct quotactl_ops ext4_qctl_operations = { .quota_on = ext4_quota_on, .quota_off = ext4_quota_off, .quota_sync = dquot_quota_sync, .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk, .get_nextdqblk = dquot_get_next_dqblk, }; #endif static const struct super_operations ext4_sops = { .alloc_inode = ext4_alloc_inode, .free_inode = ext4_free_in_core_inode, .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, .put_super = ext4_put_super, .sync_fs = ext4_sync_fs, .freeze_fs = ext4_freeze, .unfreeze_fs = ext4_unfreeze, .statfs = ext4_statfs, .show_options = ext4_show_options, .shutdown = ext4_shutdown, #ifdef CONFIG_QUOTA .quota_read = ext4_quota_read, .quota_write = ext4_quota_write, .get_dquots = ext4_get_dquots, #endif }; static const struct export_operations ext4_export_ops = { .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = ext4_fh_to_dentry, .fh_to_parent = ext4_fh_to_parent, .get_parent = ext4_get_parent, .commit_metadata = ext4_nfs_commit_metadata, }; enum { Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, Opt_resgid, Opt_resuid, Opt_sb, Opt_nouid32, Opt_debug, Opt_removed, Opt_user_xattr, Opt_acl, Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev, Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption, Opt_inlinecrypt, Opt_usrjquota, Opt_grpjquota, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error, Opt_nowarn_on_error, Opt_mblk_io_submit, Opt_debug_want_extra_isize, Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan, Opt_errors, Opt_data, Opt_data_err, Opt_jqfmt, Opt_dax_type, #ifdef CONFIG_EXT4_DEBUG Opt_fc_debug_max_replay, Opt_fc_debug_force #endif }; static const struct constant_table ext4_param_errors[] = { {"continue", EXT4_MOUNT_ERRORS_CONT}, {"panic", EXT4_MOUNT_ERRORS_PANIC}, {"remount-ro", EXT4_MOUNT_ERRORS_RO}, {} }; static const struct constant_table ext4_param_data[] = { {"journal", EXT4_MOUNT_JOURNAL_DATA}, {"ordered", EXT4_MOUNT_ORDERED_DATA}, {"writeback", EXT4_MOUNT_WRITEBACK_DATA}, {} }; static const struct constant_table ext4_param_data_err[] = { {"abort", Opt_data_err_abort}, {"ignore", Opt_data_err_ignore}, {} }; static const struct constant_table ext4_param_jqfmt[] = { {"vfsold", QFMT_VFS_OLD}, {"vfsv0", QFMT_VFS_V0}, {"vfsv1", QFMT_VFS_V1}, {} }; static const struct constant_table ext4_param_dax[] = { {"always", Opt_dax_always}, {"inode", Opt_dax_inode}, {"never", Opt_dax_never}, {} }; /* * Mount option specification * We don't use fsparam_flag_no because of the way we set the * options and the way we show them in _ext4_show_options(). To * keep the changes to a minimum, let's keep the negative options * separate for now. */ static const struct fs_parameter_spec ext4_param_specs[] = { fsparam_flag ("bsddf", Opt_bsd_df), fsparam_flag ("minixdf", Opt_minix_df), fsparam_flag ("grpid", Opt_grpid), fsparam_flag ("bsdgroups", Opt_grpid), fsparam_flag ("nogrpid", Opt_nogrpid), fsparam_flag ("sysvgroups", Opt_nogrpid), fsparam_u32 ("resgid", Opt_resgid), fsparam_u32 ("resuid", Opt_resuid), fsparam_u32 ("sb", Opt_sb), fsparam_enum ("errors", Opt_errors, ext4_param_errors), fsparam_flag ("nouid32", Opt_nouid32), fsparam_flag ("debug", Opt_debug), fsparam_flag ("oldalloc", Opt_removed), fsparam_flag ("orlov", Opt_removed), fsparam_flag ("user_xattr", Opt_user_xattr), fsparam_flag ("acl", Opt_acl), fsparam_flag ("norecovery", Opt_noload), fsparam_flag ("noload", Opt_noload), fsparam_flag ("bh", Opt_removed), fsparam_flag ("nobh", Opt_removed), fsparam_u32 ("commit", Opt_commit), fsparam_u32 ("min_batch_time", Opt_min_batch_time), fsparam_u32 ("max_batch_time", Opt_max_batch_time), fsparam_u32 ("journal_dev", Opt_journal_dev), fsparam_bdev ("journal_path", Opt_journal_path), fsparam_flag ("journal_checksum", Opt_journal_checksum), fsparam_flag ("nojournal_checksum", Opt_nojournal_checksum), fsparam_flag ("journal_async_commit",Opt_journal_async_commit), fsparam_flag ("abort", Opt_abort), fsparam_enum ("data", Opt_data, ext4_param_data), fsparam_enum ("data_err", Opt_data_err, ext4_param_data_err), fsparam_string_empty ("usrjquota", Opt_usrjquota), fsparam_string_empty ("grpjquota", Opt_grpjquota), fsparam_enum ("jqfmt", Opt_jqfmt, ext4_param_jqfmt), fsparam_flag ("grpquota", Opt_grpquota), fsparam_flag ("quota", Opt_quota), fsparam_flag ("noquota", Opt_noquota), fsparam_flag ("usrquota", Opt_usrquota), fsparam_flag ("prjquota", Opt_prjquota), fsparam_flag ("barrier", Opt_barrier), fsparam_u32 ("barrier", Opt_barrier), fsparam_flag ("nobarrier", Opt_nobarrier), fsparam_flag ("i_version", Opt_removed), fsparam_flag ("dax", Opt_dax), fsparam_enum ("dax", Opt_dax_type, ext4_param_dax), fsparam_u32 ("stripe", Opt_stripe), fsparam_flag ("delalloc", Opt_delalloc), fsparam_flag ("nodelalloc", Opt_nodelalloc), fsparam_flag ("warn_on_error", Opt_warn_on_error), fsparam_flag ("nowarn_on_error", Opt_nowarn_on_error), fsparam_u32 ("debug_want_extra_isize", Opt_debug_want_extra_isize), fsparam_flag ("mblk_io_submit", Opt_removed), fsparam_flag ("nomblk_io_submit", Opt_removed), fsparam_flag ("block_validity", Opt_block_validity), fsparam_flag ("noblock_validity", Opt_noblock_validity), fsparam_u32 ("inode_readahead_blks", Opt_inode_readahead_blks), fsparam_u32 ("journal_ioprio", Opt_journal_ioprio), fsparam_u32 ("auto_da_alloc", Opt_auto_da_alloc), fsparam_flag ("auto_da_alloc", Opt_auto_da_alloc), fsparam_flag ("noauto_da_alloc", Opt_noauto_da_alloc), fsparam_flag ("dioread_nolock", Opt_dioread_nolock), fsparam_flag ("nodioread_nolock", Opt_dioread_lock), fsparam_flag ("dioread_lock", Opt_dioread_lock), fsparam_flag ("discard", Opt_discard), fsparam_flag ("nodiscard", Opt_nodiscard), fsparam_u32 ("init_itable", Opt_init_itable), fsparam_flag ("init_itable", Opt_init_itable), fsparam_flag ("noinit_itable", Opt_noinit_itable), #ifdef CONFIG_EXT4_DEBUG fsparam_flag ("fc_debug_force", Opt_fc_debug_force), fsparam_u32 ("fc_debug_max_replay", Opt_fc_debug_max_replay), #endif fsparam_u32 ("max_dir_size_kb", Opt_max_dir_size_kb), fsparam_flag ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_string ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_flag ("inlinecrypt", Opt_inlinecrypt), fsparam_flag ("nombcache", Opt_nombcache), fsparam_flag ("no_mbcache", Opt_nombcache), /* for backward compatibility */ fsparam_flag ("prefetch_block_bitmaps", Opt_removed), fsparam_flag ("no_prefetch_block_bitmaps", Opt_no_prefetch_block_bitmaps), fsparam_s32 ("mb_optimize_scan", Opt_mb_optimize_scan), fsparam_string ("check", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("nocheck", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("reservation", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("noreservation", Opt_removed), /* mount option from ext2/3 */ fsparam_u32 ("journal", Opt_removed), /* mount option from ext2/3 */ {} }; #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) #define MOPT_SET 0x0001 #define MOPT_CLEAR 0x0002 #define MOPT_NOSUPPORT 0x0004 #define MOPT_EXPLICIT 0x0008 #ifdef CONFIG_QUOTA #define MOPT_Q 0 #define MOPT_QFMT 0x0010 #else #define MOPT_Q MOPT_NOSUPPORT #define MOPT_QFMT MOPT_NOSUPPORT #endif #define MOPT_NO_EXT2 0x0020 #define MOPT_NO_EXT3 0x0040 #define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3) #define MOPT_SKIP 0x0080 #define MOPT_2 0x0100 static const struct mount_opts { int token; int mount_opt; int flags; } ext4_mount_opts[] = { {Opt_minix_df, EXT4_MOUNT_MINIX_DF, MOPT_SET}, {Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR}, {Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET}, {Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR}, {Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET}, {Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR}, {Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_EXT4_ONLY | MOPT_SET}, {Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_discard, EXT4_MOUNT_DISCARD, MOPT_SET}, {Opt_nodiscard, EXT4_MOUNT_DISCARD, MOPT_CLEAR}, {Opt_delalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_nodelalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET}, {Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR}, {Opt_commit, 0, MOPT_NO_EXT2}, {Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT | EXT4_MOUNT_JOURNAL_CHECKSUM), MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET}, {Opt_data_err, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_NO_EXT2}, {Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET}, {Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR}, {Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET}, {Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR}, {Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR}, {Opt_dax_type, 0, MOPT_EXT4_ONLY}, {Opt_journal_dev, 0, MOPT_NO_EXT2}, {Opt_journal_path, 0, MOPT_NO_EXT2}, {Opt_journal_ioprio, 0, MOPT_NO_EXT2}, {Opt_data, 0, MOPT_NO_EXT2}, {Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET}, #ifdef CONFIG_EXT4_FS_POSIX_ACL {Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET}, #else {Opt_acl, 0, MOPT_NOSUPPORT}, #endif {Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET}, {Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET}, {Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA, MOPT_SET | MOPT_Q}, {Opt_prjquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_PRJQUOTA, MOPT_SET | MOPT_Q}, {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA), MOPT_CLEAR | MOPT_Q}, {Opt_usrjquota, 0, MOPT_Q}, {Opt_grpjquota, 0, MOPT_Q}, {Opt_jqfmt, 0, MOPT_QFMT}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS, MOPT_SET}, #ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, #endif {Opt_abort, EXT4_MOUNT2_ABORT, MOPT_SET | MOPT_2}, {Opt_err, 0, 0} }; #if IS_ENABLED(CONFIG_UNICODE) static const struct ext4_sb_encodings { __u16 magic; char *name; unsigned int version; } ext4_sb_encoding_map[] = { {EXT4_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)}, }; static const struct ext4_sb_encodings * ext4_sb_read_encoding(const struct ext4_super_block *es) { __u16 magic = le16_to_cpu(es->s_encoding); int i; for (i = 0; i < ARRAY_SIZE(ext4_sb_encoding_map); i++) if (magic == ext4_sb_encoding_map[i].magic) return &ext4_sb_encoding_map[i]; return NULL; } #endif #define EXT4_SPEC_JQUOTA (1 << 0) #define EXT4_SPEC_JQFMT (1 << 1) #define EXT4_SPEC_DATAJ (1 << 2) #define EXT4_SPEC_SB_BLOCK (1 << 3) #define EXT4_SPEC_JOURNAL_DEV (1 << 4) #define EXT4_SPEC_JOURNAL_IOPRIO (1 << 5) #define EXT4_SPEC_s_want_extra_isize (1 << 7) #define EXT4_SPEC_s_max_batch_time (1 << 8) #define EXT4_SPEC_s_min_batch_time (1 << 9) #define EXT4_SPEC_s_inode_readahead_blks (1 << 10) #define EXT4_SPEC_s_li_wait_mult (1 << 11) #define EXT4_SPEC_s_max_dir_size_kb (1 << 12) #define EXT4_SPEC_s_stripe (1 << 13) #define EXT4_SPEC_s_resuid (1 << 14) #define EXT4_SPEC_s_resgid (1 << 15) #define EXT4_SPEC_s_commit_interval (1 << 16) #define EXT4_SPEC_s_fc_debug_max_replay (1 << 17) #define EXT4_SPEC_s_sb_block (1 << 18) #define EXT4_SPEC_mb_optimize_scan (1 << 19) struct ext4_fs_context { char *s_qf_names[EXT4_MAXQUOTAS]; struct fscrypt_dummy_policy dummy_enc_policy; int s_jquota_fmt; /* Format of quota to use */ #ifdef CONFIG_EXT4_DEBUG int s_fc_debug_max_replay; #endif unsigned short qname_spec; unsigned long vals_s_flags; /* Bits to set in s_flags */ unsigned long mask_s_flags; /* Bits changed in s_flags */ unsigned long journal_devnum; unsigned long s_commit_interval; unsigned long s_stripe; unsigned int s_inode_readahead_blks; unsigned int s_want_extra_isize; unsigned int s_li_wait_mult; unsigned int s_max_dir_size_kb; unsigned int journal_ioprio; unsigned int vals_s_mount_opt; unsigned int mask_s_mount_opt; unsigned int vals_s_mount_opt2; unsigned int mask_s_mount_opt2; unsigned int opt_flags; /* MOPT flags */ unsigned int spec; u32 s_max_batch_time; u32 s_min_batch_time; kuid_t s_resuid; kgid_t s_resgid; ext4_fsblk_t s_sb_block; }; static void ext4_fc_free(struct fs_context *fc) { struct ext4_fs_context *ctx = fc->fs_private; int i; if (!ctx) return; for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(ctx->s_qf_names[i]); fscrypt_free_dummy_policy(&ctx->dummy_enc_policy); kfree(ctx); } int ext4_init_fs_context(struct fs_context *fc) { struct ext4_fs_context *ctx; ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; fc->fs_private = ctx; fc->ops = &ext4_context_ops; return 0; } #ifdef CONFIG_QUOTA /* * Note the name of the specified quota file. */ static int note_qf_name(struct fs_context *fc, int qtype, struct fs_parameter *param) { struct ext4_fs_context *ctx = fc->fs_private; char *qname; if (param->size < 1) { ext4_msg(NULL, KERN_ERR, "Missing quota name"); return -EINVAL; } if (strchr(param->string, '/')) { ext4_msg(NULL, KERN_ERR, "quotafile must be on filesystem root"); return -EINVAL; } if (ctx->s_qf_names[qtype]) { if (strcmp(ctx->s_qf_names[qtype], param->string) != 0) { ext4_msg(NULL, KERN_ERR, "%s quota file already specified", QTYPE2NAME(qtype)); return -EINVAL; } return 0; } qname = kmemdup_nul(param->string, param->size, GFP_KERNEL); if (!qname) { ext4_msg(NULL, KERN_ERR, "Not enough memory for storing quotafile name"); return -ENOMEM; } ctx->s_qf_names[qtype] = qname; ctx->qname_spec |= 1 << qtype; ctx->spec |= EXT4_SPEC_JQUOTA; return 0; } /* * Clear the name of the specified quota file. */ static int unnote_qf_name(struct fs_context *fc, int qtype) { struct ext4_fs_context *ctx = fc->fs_private; kfree(ctx->s_qf_names[qtype]); ctx->s_qf_names[qtype] = NULL; ctx->qname_spec |= 1 << qtype; ctx->spec |= EXT4_SPEC_JQUOTA; return 0; } #endif static int ext4_parse_test_dummy_encryption(const struct fs_parameter *param, struct ext4_fs_context *ctx) { int err; if (!IS_ENABLED(CONFIG_FS_ENCRYPTION)) { ext4_msg(NULL, KERN_WARNING, "test_dummy_encryption option not supported"); return -EINVAL; } err = fscrypt_parse_test_dummy_encryption(param, &ctx->dummy_enc_policy); if (err == -EINVAL) { ext4_msg(NULL, KERN_WARNING, "Value of option \"%s\" is unrecognized", param->key); } else if (err == -EEXIST) { ext4_msg(NULL, KERN_WARNING, "Conflicting test_dummy_encryption options"); return -EINVAL; } return err; } #define EXT4_SET_CTX(name) \ static inline void ctx_set_##name(struct ext4_fs_context *ctx, \ unsigned long flag) \ { \ ctx->mask_s_##name |= flag; \ ctx->vals_s_##name |= flag; \ } #define EXT4_CLEAR_CTX(name) \ static inline void ctx_clear_##name(struct ext4_fs_context *ctx, \ unsigned long flag) \ { \ ctx->mask_s_##name |= flag; \ ctx->vals_s_##name &= ~flag; \ } #define EXT4_TEST_CTX(name) \ static inline unsigned long \ ctx_test_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ return (ctx->vals_s_##name & flag); \ } EXT4_SET_CTX(flags); /* set only */ EXT4_SET_CTX(mount_opt); EXT4_CLEAR_CTX(mount_opt); EXT4_TEST_CTX(mount_opt); EXT4_SET_CTX(mount_opt2); EXT4_CLEAR_CTX(mount_opt2); EXT4_TEST_CTX(mount_opt2); static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct ext4_fs_context *ctx = fc->fs_private; struct fs_parse_result result; const struct mount_opts *m; int is_remount; kuid_t uid; kgid_t gid; int token; token = fs_parse(fc, ext4_param_specs, param, &result); if (token < 0) return token; is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; for (m = ext4_mount_opts; m->token != Opt_err; m++) if (token == m->token) break; ctx->opt_flags |= m->flags; if (m->flags & MOPT_EXPLICIT) { if (m->mount_opt & EXT4_MOUNT_DELALLOC) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_EXPLICIT_DELALLOC); } else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM); } else return -EINVAL; } if (m->flags & MOPT_NOSUPPORT) { ext4_msg(NULL, KERN_ERR, "%s option not supported", param->key); return 0; } switch (token) { #ifdef CONFIG_QUOTA case Opt_usrjquota: if (!*param->string) return unnote_qf_name(fc, USRQUOTA); else return note_qf_name(fc, USRQUOTA, param); case Opt_grpjquota: if (!*param->string) return unnote_qf_name(fc, GRPQUOTA); else return note_qf_name(fc, GRPQUOTA, param); #endif case Opt_sb: if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { ext4_msg(NULL, KERN_WARNING, "Ignoring %s option on remount", param->key); } else { ctx->s_sb_block = result.uint_32; ctx->spec |= EXT4_SPEC_s_sb_block; } return 0; case Opt_removed: ext4_msg(NULL, KERN_WARNING, "Ignoring removed %s option", param->key); return 0; case Opt_inlinecrypt: #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT ctx_set_flags(ctx, SB_INLINECRYPT); #else ext4_msg(NULL, KERN_ERR, "inline encryption not supported"); #endif return 0; case Opt_errors: ctx_clear_mount_opt(ctx, EXT4_MOUNT_ERRORS_MASK); ctx_set_mount_opt(ctx, result.uint_32); return 0; #ifdef CONFIG_QUOTA case Opt_jqfmt: ctx->s_jquota_fmt = result.uint_32; ctx->spec |= EXT4_SPEC_JQFMT; return 0; #endif case Opt_data: ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS); ctx_set_mount_opt(ctx, result.uint_32); ctx->spec |= EXT4_SPEC_DATAJ; return 0; case Opt_commit: if (result.uint_32 == 0) result.uint_32 = JBD2_DEFAULT_MAX_COMMIT_AGE; else if (result.uint_32 > INT_MAX / HZ) { ext4_msg(NULL, KERN_ERR, "Invalid commit interval %d, " "must be smaller than %d", result.uint_32, INT_MAX / HZ); return -EINVAL; } ctx->s_commit_interval = HZ * result.uint_32; ctx->spec |= EXT4_SPEC_s_commit_interval; return 0; case Opt_debug_want_extra_isize: if ((result.uint_32 & 1) || (result.uint_32 < 4)) { ext4_msg(NULL, KERN_ERR, "Invalid want_extra_isize %d", result.uint_32); return -EINVAL; } ctx->s_want_extra_isize = result.uint_32; ctx->spec |= EXT4_SPEC_s_want_extra_isize; return 0; case Opt_max_batch_time: ctx->s_max_batch_time = result.uint_32; ctx->spec |= EXT4_SPEC_s_max_batch_time; return 0; case Opt_min_batch_time: ctx->s_min_batch_time = result.uint_32; ctx->spec |= EXT4_SPEC_s_min_batch_time; return 0; case Opt_inode_readahead_blks: if (result.uint_32 && (result.uint_32 > (1 << 30) || !is_power_of_2(result.uint_32))) { ext4_msg(NULL, KERN_ERR, "EXT4-fs: inode_readahead_blks must be " "0 or a power of 2 smaller than 2^31"); return -EINVAL; } ctx->s_inode_readahead_blks = result.uint_32; ctx->spec |= EXT4_SPEC_s_inode_readahead_blks; return 0; case Opt_init_itable: ctx_set_mount_opt(ctx, EXT4_MOUNT_INIT_INODE_TABLE); ctx->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; if (param->type == fs_value_is_string) ctx->s_li_wait_mult = result.uint_32; ctx->spec |= EXT4_SPEC_s_li_wait_mult; return 0; case Opt_max_dir_size_kb: ctx->s_max_dir_size_kb = result.uint_32; ctx->spec |= EXT4_SPEC_s_max_dir_size_kb; return 0; #ifdef CONFIG_EXT4_DEBUG case Opt_fc_debug_max_replay: ctx->s_fc_debug_max_replay = result.uint_32; ctx->spec |= EXT4_SPEC_s_fc_debug_max_replay; return 0; #endif case Opt_stripe: ctx->s_stripe = result.uint_32; ctx->spec |= EXT4_SPEC_s_stripe; return 0; case Opt_resuid: uid = make_kuid(current_user_ns(), result.uint_32); if (!uid_valid(uid)) { ext4_msg(NULL, KERN_ERR, "Invalid uid value %d", result.uint_32); return -EINVAL; } ctx->s_resuid = uid; ctx->spec |= EXT4_SPEC_s_resuid; return 0; case Opt_resgid: gid = make_kgid(current_user_ns(), result.uint_32); if (!gid_valid(gid)) { ext4_msg(NULL, KERN_ERR, "Invalid gid value %d", result.uint_32); return -EINVAL; } ctx->s_resgid = gid; ctx->spec |= EXT4_SPEC_s_resgid; return 0; case Opt_journal_dev: if (is_remount) { ext4_msg(NULL, KERN_ERR, "Cannot specify journal on remount"); return -EINVAL; } ctx->journal_devnum = result.uint_32; ctx->spec |= EXT4_SPEC_JOURNAL_DEV; return 0; case Opt_journal_path: { struct inode *journal_inode; struct path path; int error; if (is_remount) { ext4_msg(NULL, KERN_ERR, "Cannot specify journal on remount"); return -EINVAL; } error = fs_lookup_param(fc, param, 1, LOOKUP_FOLLOW, &path); if (error) { ext4_msg(NULL, KERN_ERR, "error: could not find " "journal device path"); return -EINVAL; } journal_inode = d_inode(path.dentry); ctx->journal_devnum = new_encode_dev(journal_inode->i_rdev); ctx->spec |= EXT4_SPEC_JOURNAL_DEV; path_put(&path); return 0; } case Opt_journal_ioprio: if (result.uint_32 > 7) { ext4_msg(NULL, KERN_ERR, "Invalid journal IO priority" " (must be 0-7)"); return -EINVAL; } ctx->journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, result.uint_32); ctx->spec |= EXT4_SPEC_JOURNAL_IOPRIO; return 0; case Opt_test_dummy_encryption: return ext4_parse_test_dummy_encryption(param, ctx); case Opt_dax: case Opt_dax_type: #ifdef CONFIG_FS_DAX { int type = (token == Opt_dax) ? Opt_dax : result.uint_32; switch (type) { case Opt_dax: case Opt_dax_always: ctx_set_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); break; case Opt_dax_never: ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); break; case Opt_dax_inode: ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); /* Strictly for printing options */ ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE); break; } return 0; } #else ext4_msg(NULL, KERN_INFO, "dax option not supported"); return -EINVAL; #endif case Opt_data_err: if (result.uint_32 == Opt_data_err_abort) ctx_set_mount_opt(ctx, m->mount_opt); else if (result.uint_32 == Opt_data_err_ignore) ctx_clear_mount_opt(ctx, m->mount_opt); return 0; case Opt_mb_optimize_scan: if (result.int_32 == 1) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN); ctx->spec |= EXT4_SPEC_mb_optimize_scan; } else if (result.int_32 == 0) { ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN); ctx->spec |= EXT4_SPEC_mb_optimize_scan; } else { ext4_msg(NULL, KERN_WARNING, "mb_optimize_scan should be set to 0 or 1."); return -EINVAL; } return 0; } /* * At this point we should only be getting options requiring MOPT_SET, * or MOPT_CLEAR. Anything else is a bug */ if (m->token == Opt_err) { ext4_msg(NULL, KERN_WARNING, "buggy handling of option %s", param->key); WARN_ON(1); return -EINVAL; } else { unsigned int set = 0; if ((param->type == fs_value_is_flag) || result.uint_32 > 0) set = 1; if (m->flags & MOPT_CLEAR) set = !set; else if (unlikely(!(m->flags & MOPT_SET))) { ext4_msg(NULL, KERN_WARNING, "buggy handling of option %s", param->key); WARN_ON(1); return -EINVAL; } if (m->flags & MOPT_2) { if (set != 0) ctx_set_mount_opt2(ctx, m->mount_opt); else ctx_clear_mount_opt2(ctx, m->mount_opt); } else { if (set != 0) ctx_set_mount_opt(ctx, m->mount_opt); else ctx_clear_mount_opt(ctx, m->mount_opt); } } return 0; } static int parse_options(struct fs_context *fc, char *options) { struct fs_parameter param; int ret; char *key; if (!options) return 0; while ((key = strsep(&options, ",")) != NULL) { if (*key) { size_t v_len = 0; char *value = strchr(key, '='); param.type = fs_value_is_flag; param.string = NULL; if (value) { if (value == key) continue; *value++ = 0; v_len = strlen(value); param.string = kmemdup_nul(value, v_len, GFP_KERNEL); if (!param.string) return -ENOMEM; param.type = fs_value_is_string; } param.key = key; param.size = v_len; ret = ext4_parse_param(fc, ¶m); kfree(param.string); if (ret < 0) return ret; } } ret = ext4_validate_options(fc); if (ret < 0) return ret; return 0; } static int parse_apply_sb_mount_options(struct super_block *sb, struct ext4_fs_context *m_ctx) { struct ext4_sb_info *sbi = EXT4_SB(sb); char *s_mount_opts = NULL; struct ext4_fs_context *s_ctx = NULL; struct fs_context *fc = NULL; int ret = -ENOMEM; if (!sbi->s_es->s_mount_opts[0]) return 0; s_mount_opts = kstrndup(sbi->s_es->s_mount_opts, sizeof(sbi->s_es->s_mount_opts), GFP_KERNEL); if (!s_mount_opts) return ret; fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL); if (!fc) goto out_free; s_ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL); if (!s_ctx) goto out_free; fc->fs_private = s_ctx; fc->s_fs_info = sbi; ret = parse_options(fc, s_mount_opts); if (ret < 0) goto parse_failed; ret = ext4_check_opt_consistency(fc, sb); if (ret < 0) { parse_failed: ext4_msg(sb, KERN_WARNING, "failed to parse options in superblock: %s", s_mount_opts); ret = 0; goto out_free; } if (s_ctx->spec & EXT4_SPEC_JOURNAL_DEV) m_ctx->journal_devnum = s_ctx->journal_devnum; if (s_ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO) m_ctx->journal_ioprio = s_ctx->journal_ioprio; ext4_apply_options(fc, sb); ret = 0; out_free: if (fc) { ext4_fc_free(fc); kfree(fc); } kfree(s_mount_opts); return ret; } static void ext4_apply_quota_options(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_QUOTA bool quota_feature = ext4_has_feature_quota(sb); struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = EXT4_SB(sb); char *qname; int i; if (quota_feature) return; if (ctx->spec & EXT4_SPEC_JQUOTA) { for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (!(ctx->qname_spec & (1 << i))) continue; qname = ctx->s_qf_names[i]; /* May be NULL */ if (qname) set_opt(sb, QUOTA); ctx->s_qf_names[i] = NULL; qname = rcu_replace_pointer(sbi->s_qf_names[i], qname, lockdep_is_held(&sb->s_umount)); if (qname) kfree_rcu_mightsleep(qname); } } if (ctx->spec & EXT4_SPEC_JQFMT) sbi->s_jquota_fmt = ctx->s_jquota_fmt; #endif } /* * Check quota settings consistency. */ static int ext4_check_quota_consistency(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_QUOTA struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = EXT4_SB(sb); bool quota_feature = ext4_has_feature_quota(sb); bool quota_loaded = sb_any_quota_loaded(sb); bool usr_qf_name, grp_qf_name, usrquota, grpquota; int quota_flags, i; /* * We do the test below only for project quotas. 'usrquota' and * 'grpquota' mount options are allowed even without quota feature * to support legacy quotas in quota files. */ if (ctx_test_mount_opt(ctx, EXT4_MOUNT_PRJQUOTA) && !ext4_has_feature_project(sb)) { ext4_msg(NULL, KERN_ERR, "Project quota feature not enabled. " "Cannot enable project quota enforcement."); return -EINVAL; } quota_flags = EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA; if (quota_loaded && ctx->mask_s_mount_opt & quota_flags && !ctx_test_mount_opt(ctx, quota_flags)) goto err_quota_change; if (ctx->spec & EXT4_SPEC_JQUOTA) { for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (!(ctx->qname_spec & (1 << i))) continue; if (quota_loaded && !!sbi->s_qf_names[i] != !!ctx->s_qf_names[i]) goto err_jquota_change; if (sbi->s_qf_names[i] && ctx->s_qf_names[i] && strcmp(get_qf_name(sb, sbi, i), ctx->s_qf_names[i]) != 0) goto err_jquota_specified; } if (quota_feature) { ext4_msg(NULL, KERN_INFO, "Journaled quota options ignored when " "QUOTA feature is enabled"); return 0; } } if (ctx->spec & EXT4_SPEC_JQFMT) { if (sbi->s_jquota_fmt != ctx->s_jquota_fmt && quota_loaded) goto err_jquota_change; if (quota_feature) { ext4_msg(NULL, KERN_INFO, "Quota format mount options " "ignored when QUOTA feature is enabled"); return 0; } } /* Make sure we don't mix old and new quota format */ usr_qf_name = (get_qf_name(sb, sbi, USRQUOTA) || ctx->s_qf_names[USRQUOTA]); grp_qf_name = (get_qf_name(sb, sbi, GRPQUOTA) || ctx->s_qf_names[GRPQUOTA]); usrquota = (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) || test_opt(sb, USRQUOTA)); grpquota = (ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA) || test_opt(sb, GRPQUOTA)); if (usr_qf_name) { ctx_clear_mount_opt(ctx, EXT4_MOUNT_USRQUOTA); usrquota = false; } if (grp_qf_name) { ctx_clear_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA); grpquota = false; } if (usr_qf_name || grp_qf_name) { if (usrquota || grpquota) { ext4_msg(NULL, KERN_ERR, "old and new quota " "format mixing"); return -EINVAL; } if (!(ctx->spec & EXT4_SPEC_JQFMT || sbi->s_jquota_fmt)) { ext4_msg(NULL, KERN_ERR, "journaled quota format " "not specified"); return -EINVAL; } } return 0; err_quota_change: ext4_msg(NULL, KERN_ERR, "Cannot change quota options when quota turned on"); return -EINVAL; err_jquota_change: ext4_msg(NULL, KERN_ERR, "Cannot change journaled quota " "options when quota turned on"); return -EINVAL; err_jquota_specified: ext4_msg(NULL, KERN_ERR, "%s quota file already specified", QTYPE2NAME(i)); return -EINVAL; #else return 0; #endif } static int ext4_check_test_dummy_encryption(const struct fs_context *fc, struct super_block *sb) { const struct ext4_fs_context *ctx = fc->fs_private; const struct ext4_sb_info *sbi = EXT4_SB(sb); if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy)) return 0; if (!ext4_has_feature_encrypt(sb)) { ext4_msg(NULL, KERN_WARNING, "test_dummy_encryption requires encrypt feature"); return -EINVAL; } /* * This mount option is just for testing, and it's not worthwhile to * implement the extra complexity (e.g. RCU protection) that would be * needed to allow it to be set or changed during remount. We do allow * it to be specified during remount, but only if there is no change. */ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { if (fscrypt_dummy_policies_equal(&sbi->s_dummy_enc_policy, &ctx->dummy_enc_policy)) return 0; ext4_msg(NULL, KERN_WARNING, "Can't set or change test_dummy_encryption on remount"); return -EINVAL; } /* Also make sure s_mount_opts didn't contain a conflicting value. */ if (fscrypt_is_dummy_policy_set(&sbi->s_dummy_enc_policy)) { if (fscrypt_dummy_policies_equal(&sbi->s_dummy_enc_policy, &ctx->dummy_enc_policy)) return 0; ext4_msg(NULL, KERN_WARNING, "Conflicting test_dummy_encryption options"); return -EINVAL; } return 0; } static void ext4_apply_test_dummy_encryption(struct ext4_fs_context *ctx, struct super_block *sb) { if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy) || /* if already set, it was already verified to be the same */ fscrypt_is_dummy_policy_set(&EXT4_SB(sb)->s_dummy_enc_policy)) return; EXT4_SB(sb)->s_dummy_enc_policy = ctx->dummy_enc_policy; memset(&ctx->dummy_enc_policy, 0, sizeof(ctx->dummy_enc_policy)); ext4_msg(sb, KERN_WARNING, "Test dummy encryption mode enabled"); } static int ext4_check_opt_consistency(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = fc->s_fs_info; int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; int err; if ((ctx->opt_flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) { ext4_msg(NULL, KERN_ERR, "Mount option(s) incompatible with ext2"); return -EINVAL; } if ((ctx->opt_flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) { ext4_msg(NULL, KERN_ERR, "Mount option(s) incompatible with ext3"); return -EINVAL; } if (ctx->s_want_extra_isize > (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE)) { ext4_msg(NULL, KERN_ERR, "Invalid want_extra_isize %d", ctx->s_want_extra_isize); return -EINVAL; } err = ext4_check_test_dummy_encryption(fc, sb); if (err) return err; if ((ctx->spec & EXT4_SPEC_DATAJ) && is_remount) { if (!sbi->s_journal) { ext4_msg(NULL, KERN_WARNING, "Remounting file system with no journal " "so ignoring journalled data option"); ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS); } else if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS) != test_opt(sb, DATA_FLAGS)) { ext4_msg(NULL, KERN_ERR, "Cannot change data mode " "on remount"); return -EINVAL; } } if (is_remount) { if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) { ext4_msg(NULL, KERN_ERR, "can't mount with " "both data=journal and dax"); return -EINVAL; } if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) { fail_dax_change_remount: ext4_msg(NULL, KERN_ERR, "can't change " "dax mount option while remounting"); return -EINVAL; } else if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER) && (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS))) { goto fail_dax_change_remount; } else if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE) && ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE))) { goto fail_dax_change_remount; } } return ext4_check_quota_consistency(fc, sb); } static void ext4_apply_options(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = fc->s_fs_info; sbi->s_mount_opt &= ~ctx->mask_s_mount_opt; sbi->s_mount_opt |= ctx->vals_s_mount_opt; sbi->s_mount_opt2 &= ~ctx->mask_s_mount_opt2; sbi->s_mount_opt2 |= ctx->vals_s_mount_opt2; sb->s_flags &= ~ctx->mask_s_flags; sb->s_flags |= ctx->vals_s_flags; #define APPLY(X) ({ if (ctx->spec & EXT4_SPEC_##X) sbi->X = ctx->X; }) APPLY(s_commit_interval); APPLY(s_stripe); APPLY(s_max_batch_time); APPLY(s_min_batch_time); APPLY(s_want_extra_isize); APPLY(s_inode_readahead_blks); APPLY(s_max_dir_size_kb); APPLY(s_li_wait_mult); APPLY(s_resgid); APPLY(s_resuid); #ifdef CONFIG_EXT4_DEBUG APPLY(s_fc_debug_max_replay); #endif ext4_apply_quota_options(fc, sb); ext4_apply_test_dummy_encryption(ctx, sb); } static int ext4_validate_options(struct fs_context *fc) { #ifdef CONFIG_QUOTA struct ext4_fs_context *ctx = fc->fs_private; char *usr_qf_name, *grp_qf_name; usr_qf_name = ctx->s_qf_names[USRQUOTA]; grp_qf_name = ctx->s_qf_names[GRPQUOTA]; if (usr_qf_name || grp_qf_name) { if (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) && usr_qf_name) ctx_clear_mount_opt(ctx, EXT4_MOUNT_USRQUOTA); if (ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA) && grp_qf_name) ctx_clear_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA); if (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) || ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA)) { ext4_msg(NULL, KERN_ERR, "old and new quota " "format mixing"); return -EINVAL; } } #endif return 1; } static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb) { #if defined(CONFIG_QUOTA) struct ext4_sb_info *sbi = EXT4_SB(sb); char *usr_qf_name, *grp_qf_name; if (sbi->s_jquota_fmt) { char *fmtname = ""; switch (sbi->s_jquota_fmt) { case QFMT_VFS_OLD: fmtname = "vfsold"; break; case QFMT_VFS_V0: fmtname = "vfsv0"; break; case QFMT_VFS_V1: fmtname = "vfsv1"; break; } seq_printf(seq, ",jqfmt=%s", fmtname); } rcu_read_lock(); usr_qf_name = rcu_dereference(sbi->s_qf_names[USRQUOTA]); grp_qf_name = rcu_dereference(sbi->s_qf_names[GRPQUOTA]); if (usr_qf_name) seq_show_option(seq, "usrjquota", usr_qf_name); if (grp_qf_name) seq_show_option(seq, "grpjquota", grp_qf_name); rcu_read_unlock(); #endif } static const char *token2str(int token) { const struct fs_parameter_spec *spec; for (spec = ext4_param_specs; spec->name != NULL; spec++) if (spec->opt == token && !spec->type) break; return spec->name; } /* * Show an option if * - it's set to a non-default value OR * - if the per-sb default is different from the global default */ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, int nodefs) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int def_errors; const struct mount_opts *m; char sep = nodefs ? '\n' : ','; #define SEQ_OPTS_PUTS(str) seq_printf(seq, "%c" str, sep) #define SEQ_OPTS_PRINT(str, arg) seq_printf(seq, "%c" str, sep, arg) if (sbi->s_sb_block != 1) SEQ_OPTS_PRINT("sb=%llu", sbi->s_sb_block); for (m = ext4_mount_opts; m->token != Opt_err; m++) { int want_set = m->flags & MOPT_SET; int opt_2 = m->flags & MOPT_2; unsigned int mount_opt, def_mount_opt; if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) || m->flags & MOPT_SKIP) continue; if (opt_2) { mount_opt = sbi->s_mount_opt2; def_mount_opt = sbi->s_def_mount_opt2; } else { mount_opt = sbi->s_mount_opt; def_mount_opt = sbi->s_def_mount_opt; } /* skip if same as the default */ if (!nodefs && !(m->mount_opt & (mount_opt ^ def_mount_opt))) continue; /* select Opt_noFoo vs Opt_Foo */ if ((want_set && (mount_opt & m->mount_opt) != m->mount_opt) || (!want_set && (mount_opt & m->mount_opt))) continue; SEQ_OPTS_PRINT("%s", token2str(m->token)); } if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) SEQ_OPTS_PRINT("resuid=%u", from_kuid_munged(&init_user_ns, sbi->s_resuid)); if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) SEQ_OPTS_PRINT("resgid=%u", from_kgid_munged(&init_user_ns, sbi->s_resgid)); def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors); if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO) SEQ_OPTS_PUTS("errors=remount-ro"); if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE) SEQ_OPTS_PUTS("errors=continue"); if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC) SEQ_OPTS_PUTS("errors=panic"); if (nodefs || sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) SEQ_OPTS_PRINT("commit=%lu", sbi->s_commit_interval / HZ); if (nodefs || sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time); if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (nodefs || EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) SEQ_OPTS_PUTS("data=journal"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) SEQ_OPTS_PUTS("data=ordered"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) SEQ_OPTS_PUTS("data=writeback"); } if (nodefs || sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS) SEQ_OPTS_PRINT("inode_readahead_blks=%u", sbi->s_inode_readahead_blks); if (test_opt(sb, INIT_INODE_TABLE) && (nodefs || (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT))) SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult); if (nodefs || sbi->s_max_dir_size_kb) SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb); if (test_opt(sb, DATA_ERR_ABORT)) SEQ_OPTS_PUTS("data_err=abort"); fscrypt_show_test_dummy_encryption(seq, sep, sb); if (sb->s_flags & SB_INLINECRYPT) SEQ_OPTS_PUTS("inlinecrypt"); if (test_opt(sb, DAX_ALWAYS)) { if (IS_EXT2_SB(sb)) SEQ_OPTS_PUTS("dax"); else SEQ_OPTS_PUTS("dax=always"); } else if (test_opt2(sb, DAX_NEVER)) { SEQ_OPTS_PUTS("dax=never"); } else if (test_opt2(sb, DAX_INODE)) { SEQ_OPTS_PUTS("dax=inode"); } if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD && !test_opt2(sb, MB_OPTIMIZE_SCAN)) { SEQ_OPTS_PUTS("mb_optimize_scan=0"); } else if (sbi->s_groups_count < MB_DEFAULT_LINEAR_SCAN_THRESHOLD && test_opt2(sb, MB_OPTIMIZE_SCAN)) { SEQ_OPTS_PUTS("mb_optimize_scan=1"); } ext4_show_quota_options(seq, sb); return 0; } static int ext4_show_options(struct seq_file *seq, struct dentry *root) { return _ext4_show_options(seq, root->d_sb, 0); } int ext4_seq_options_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; int rc; seq_puts(seq, sb_rdonly(sb) ? "ro" : "rw"); rc = _ext4_show_options(seq, sb, 1); seq_puts(seq, "\n"); return rc; } static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int read_only) { struct ext4_sb_info *sbi = EXT4_SB(sb); int err = 0; if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { ext4_msg(sb, KERN_ERR, "revision level too high, " "forcing read-only mode"); err = -EROFS; goto done; } if (read_only) goto done; if (!(sbi->s_mount_state & EXT4_VALID_FS)) ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, " "running e2fsck is recommended"); else if (sbi->s_mount_state & EXT4_ERROR_FS) ext4_msg(sb, KERN_WARNING, "warning: mounting fs with errors, " "running e2fsck is recommended"); else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 && le16_to_cpu(es->s_mnt_count) >= (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) ext4_msg(sb, KERN_WARNING, "warning: maximal mount count reached, " "running e2fsck is recommended"); else if (le32_to_cpu(es->s_checkinterval) && (ext4_get_tstamp(es, s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= ktime_get_real_seconds())) ext4_msg(sb, KERN_WARNING, "warning: checktime reached, " "running e2fsck is recommended"); if (!sbi->s_journal) es->s_state &= cpu_to_le16(~EXT4_VALID_FS); if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); ext4_update_tstamp(es, s_mtime); if (sbi->s_journal) { ext4_set_feature_journal_needs_recovery(sb); if (ext4_has_feature_orphan_file(sb)) ext4_set_feature_orphan_present(sb); } err = ext4_commit_super(sb); done: if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " "bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n", sb->s_blocksize, sbi->s_groups_count, EXT4_BLOCKS_PER_GROUP(sb), EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt, sbi->s_mount_opt2); return err; } int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct flex_groups **old_groups, **new_groups; int size, i, j; if (!sbi->s_log_groups_per_flex) return 0; size = ext4_flex_group(sbi, ngroup - 1) + 1; if (size <= sbi->s_flex_groups_allocated) return 0; new_groups = kvzalloc(roundup_pow_of_two(size * sizeof(*sbi->s_flex_groups)), GFP_KERNEL); if (!new_groups) { ext4_msg(sb, KERN_ERR, "not enough memory for %d flex group pointers", size); return -ENOMEM; } for (i = sbi->s_flex_groups_allocated; i < size; i++) { new_groups[i] = kvzalloc(roundup_pow_of_two( sizeof(struct flex_groups)), GFP_KERNEL); if (!new_groups[i]) { for (j = sbi->s_flex_groups_allocated; j < i; j++) kvfree(new_groups[j]); kvfree(new_groups); ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", size); return -ENOMEM; } } rcu_read_lock(); old_groups = rcu_dereference(sbi->s_flex_groups); if (old_groups) memcpy(new_groups, old_groups, (sbi->s_flex_groups_allocated * sizeof(struct flex_groups *))); rcu_read_unlock(); rcu_assign_pointer(sbi->s_flex_groups, new_groups); sbi->s_flex_groups_allocated = size; if (old_groups) ext4_kvfree_array_rcu(old_groups); return 0; } static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; struct flex_groups *fg; ext4_group_t flex_group; int i, err; sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) { sbi->s_log_groups_per_flex = 0; return 1; } err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count); if (err) goto failed; for (i = 0; i < sbi->s_groups_count; i++) { gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes); atomic64_add(ext4_free_group_clusters(sb, gdp), &fg->free_clusters); atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs); } return 1; failed: return 0; } static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { int offset = offsetof(struct ext4_group_desc, bg_checksum); __u16 crc = 0; __le32 le_group = cpu_to_le32(block_group); struct ext4_sb_info *sbi = EXT4_SB(sb); if (ext4_has_metadata_csum(sbi->s_sb)) { /* Use new metadata_csum algorithm */ __u32 csum32; __u16 dummy_csum = 0; csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group, sizeof(le_group)); csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset); csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum, sizeof(dummy_csum)); offset += sizeof(dummy_csum); if (offset < sbi->s_desc_size) csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset, sbi->s_desc_size - offset); crc = csum32 & 0xFFFF; goto out; } /* old crc16 code */ if (!ext4_has_feature_gdt_csum(sb)) return 0; crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group)); crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, sbi->s_desc_size - offset); out: return cpu_to_le16(crc); } int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (ext4_has_group_desc_csum(sb) && (gdp->bg_checksum != ext4_group_desc_csum(sb, block_group, gdp))) return 0; return 1; } void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (!ext4_has_group_desc_csum(sb)) return; gdp->bg_checksum = ext4_group_desc_csum(sb, block_group, gdp); } /* Called at mount-time, super-block is locked */ static int ext4_check_descriptors(struct super_block *sb, ext4_fsblk_t sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext4_fsblk_t last_block; ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0); ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; int flexbg_flag = 0; ext4_group_t i, grp = sbi->s_groups_count; if (ext4_has_feature_flex_bg(sb)) flexbg_flag = 1; ext4_debug("Checking group descriptors"); for (i = 0; i < sbi->s_groups_count; i++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); if (i == sbi->s_groups_count - 1 || flexbg_flag) last_block = ext4_blocks_count(sbi->s_es) - 1; else last_block = first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); if ((grp == sbi->s_groups_count) && !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) grp = i; block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (block_bitmap >= sb_block + 1 && block_bitmap <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " "(block %llu)!", i, block_bitmap); return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); if (inode_bitmap == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (inode_bitmap >= sb_block + 1 && inode_bitmap <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (inode_bitmap < first_block || inode_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " "(block %llu)!", i, inode_bitmap); return 0; } inode_table = ext4_inode_table(sb, gdp); if (inode_table == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (inode_table >= sb_block + 1 && inode_table <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u not in group " "(block %llu)!", i, inode_table); return 0; } ext4_lock_group(sb, i); if (!ext4_group_desc_csum_verify(sb, i, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Checksum for group %u failed (%u!=%u)", i, le16_to_cpu(ext4_group_desc_csum(sb, i, gdp)), le16_to_cpu(gdp->bg_checksum)); if (!sb_rdonly(sb)) { ext4_unlock_group(sb, i); return 0; } } ext4_unlock_group(sb, i); if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); } if (NULL != first_not_zeroed) *first_not_zeroed = grp; return 1; } /* * Maximal extent format file size. * Resulting logical blkno at s_maxbytes must fit in our on-disk * extent format containers, within a sector_t, and within i_blocks * in the vfs. ext4 inode has 48 bits of i_block in fsblock units, * so that won't be a limiting factor. * * However there is other limiting factor. We do store extents in the form * of starting block and length, hence the resulting length of the extent * covering maximum file size must fit into on-disk format containers as * well. Given that length is always by 1 unit bigger than max unit (because * we count 0 as well) we have to lower the s_maxbytes by one fs block. * * Note, this does *not* consider any metadata overhead for vfs i_blocks. */ static loff_t ext4_max_size(int blkbits, int has_huge_files) { loff_t res; loff_t upper_limit = MAX_LFS_FILESIZE; BUILD_BUG_ON(sizeof(blkcnt_t) < sizeof(u64)); if (!has_huge_files) { upper_limit = (1LL << 32) - 1; /* total blocks in file system block size */ upper_limit >>= (blkbits - 9); upper_limit <<= blkbits; } /* * 32-bit extent-start container, ee_block. We lower the maxbytes * by one fs block, so ee_len can cover the extent of maximum file * size */ res = (1LL << 32) - 1; res <<= blkbits; /* Sanity check against vm- & vfs- imposed limits */ if (res > upper_limit) res = upper_limit; return res; } /* * Maximal bitmap file size. There is a direct, and {,double-,triple-}indirect * block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks. * We need to be 1 filesystem block less than the 2^48 sector limit. */ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) { loff_t upper_limit, res = EXT4_NDIR_BLOCKS; int meta_blocks; unsigned int ppb = 1 << (bits - 2); /* * This is calculated to be the largest file size for a dense, block * mapped file such that the file's total number of 512-byte sectors, * including data and all indirect blocks, does not exceed (2^48 - 1). * * __u32 i_blocks_lo and _u16 i_blocks_high represent the total * number of 512-byte sectors of the file. */ if (!has_huge_files) { /* * !has_huge_files or implies that the inode i_block field * represents total file blocks in 2^32 512-byte sectors == * size of vfs inode i_blocks * 8 */ upper_limit = (1LL << 32) - 1; /* total blocks in file system block size */ upper_limit >>= (bits - 9); } else { /* * We use 48 bit ext4_inode i_blocks * With EXT4_HUGE_FILE_FL set the i_blocks * represent total number of blocks in * file system block size */ upper_limit = (1LL << 48) - 1; } /* Compute how many blocks we can address by block tree */ res += ppb; res += ppb * ppb; res += ((loff_t)ppb) * ppb * ppb; /* Compute how many metadata blocks are needed */ meta_blocks = 1; meta_blocks += 1 + ppb; meta_blocks += 1 + ppb + ppb * ppb; /* Does block tree limit file size? */ if (res + meta_blocks <= upper_limit) goto check_lfs; res = upper_limit; /* How many metadata blocks are needed for addressing upper_limit? */ upper_limit -= EXT4_NDIR_BLOCKS; /* indirect blocks */ meta_blocks = 1; upper_limit -= ppb; /* double indirect blocks */ if (upper_limit < ppb * ppb) { meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb); res -= meta_blocks; goto check_lfs; } meta_blocks += 1 + ppb; upper_limit -= ppb * ppb; /* tripple indirect blocks for the rest */ meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb) + DIV_ROUND_UP_ULL(upper_limit, ppb*ppb); res -= meta_blocks; check_lfs: res <<= bits; if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; return res; } static ext4_fsblk_t descriptor_loc(struct super_block *sb, ext4_fsblk_t logical_sb_block, int nr) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t bg, first_meta_bg; int has_super = 0; first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg); if (!ext4_has_feature_meta_bg(sb) || nr < first_meta_bg) return logical_sb_block + nr + 1; bg = sbi->s_desc_per_block * nr; if (ext4_bg_has_super(sb, bg)) has_super = 1; /* * If we have a meta_bg fs with 1k blocks, group 0's GDT is at * block 2, not 1. If s_first_data_block == 0 (bigalloc is enabled * on modern mke2fs or blksize > 1k on older mke2fs) then we must * compensate. */ if (sb->s_blocksize == 1024 && nr == 0 && le32_to_cpu(sbi->s_es->s_first_data_block) == 0) has_super++; return (has_super + ext4_group_first_block_no(sb, bg)); } /** * ext4_get_stripe_size: Get the stripe size. * @sbi: In memory super block info * * If we have specified it via mount option, then * use the mount option value. If the value specified at mount time is * greater than the blocks per group use the super block value. * If the super block value is greater than blocks per group return 0. * Allocator needs it be less than blocks per group. * */ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi) { unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride); unsigned long stripe_width = le32_to_cpu(sbi->s_es->s_raid_stripe_width); int ret; if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group) ret = sbi->s_stripe; else if (stripe_width && stripe_width <= sbi->s_blocks_per_group) ret = stripe_width; else if (stride && stride <= sbi->s_blocks_per_group) ret = stride; else ret = 0; /* * If the stripe width is 1, this makes no sense and * we set it to 0 to turn off stripe handling code. */ if (ret <= 1) ret = 0; return ret; } /* * Check whether this filesystem can be mounted based on * the features present and the RDONLY/RDWR mount requested. * Returns 1 if this filesystem can be mounted as requested, * 0 if it cannot be. */ int ext4_feature_set_ok(struct super_block *sb, int readonly) { if (ext4_has_unknown_ext4_incompat_features(sb)) { ext4_msg(sb, KERN_ERR, "Couldn't mount because of " "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) & ~EXT4_FEATURE_INCOMPAT_SUPP)); return 0; } #if !IS_ENABLED(CONFIG_UNICODE) if (ext4_has_feature_casefold(sb)) { ext4_msg(sb, KERN_ERR, "Filesystem with casefold feature cannot be " "mounted without CONFIG_UNICODE"); return 0; } #endif if (readonly) return 1; if (ext4_has_feature_readonly(sb)) { ext4_msg(sb, KERN_INFO, "filesystem is read-only"); sb->s_flags |= SB_RDONLY; return 1; } /* Check that feature set is OK for a read-write mount */ if (ext4_has_unknown_ext4_ro_compat_features(sb)) { ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of " "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) & ~EXT4_FEATURE_RO_COMPAT_SUPP)); return 0; } if (ext4_has_feature_bigalloc(sb) && !ext4_has_feature_extents(sb)) { ext4_msg(sb, KERN_ERR, "Can't support bigalloc feature without " "extents feature\n"); return 0; } #if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2) if (!readonly && (ext4_has_feature_quota(sb) || ext4_has_feature_project(sb))) { ext4_msg(sb, KERN_ERR, "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2"); return 0; } #endif /* CONFIG_QUOTA */ return 1; } /* * This function is called once a day if we have errors logged * on the file system */ static void print_daily_error_info(struct timer_list *t) { struct ext4_sb_info *sbi = from_timer(sbi, t, s_err_report); struct super_block *sb = sbi->s_sb; struct ext4_super_block *es = sbi->s_es; if (es->s_error_count) /* fsck newer than v1.41.13 is needed to clean this condition. */ ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u", le32_to_cpu(es->s_error_count)); if (es->s_first_error_time) { printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %llu: %.*s:%d", sb->s_id, ext4_get_tstamp(es, s_first_error_time), (int) sizeof(es->s_first_error_func), es->s_first_error_func, le32_to_cpu(es->s_first_error_line)); if (es->s_first_error_ino) printk(KERN_CONT ": inode %u", le32_to_cpu(es->s_first_error_ino)); if (es->s_first_error_block) printk(KERN_CONT ": block %llu", (unsigned long long) le64_to_cpu(es->s_first_error_block)); printk(KERN_CONT "\n"); } if (es->s_last_error_time) { printk(KERN_NOTICE "EXT4-fs (%s): last error at time %llu: %.*s:%d", sb->s_id, ext4_get_tstamp(es, s_last_error_time), (int) sizeof(es->s_last_error_func), es->s_last_error_func, le32_to_cpu(es->s_last_error_line)); if (es->s_last_error_ino) printk(KERN_CONT ": inode %u", le32_to_cpu(es->s_last_error_ino)); if (es->s_last_error_block) printk(KERN_CONT ": block %llu", (unsigned long long) le64_to_cpu(es->s_last_error_block)); printk(KERN_CONT "\n"); } mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */ } /* Find next suitable group and run ext4_init_inode_table */ static int ext4_run_li_request(struct ext4_li_request *elr) { struct ext4_group_desc *gdp = NULL; struct super_block *sb = elr->lr_super; ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; ext4_group_t group = elr->lr_next_group; unsigned int prefetch_ios = 0; int ret = 0; int nr = EXT4_SB(sb)->s_mb_prefetch; u64 start_time; if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) { elr->lr_next_group = ext4_mb_prefetch(sb, group, nr, &prefetch_ios); ext4_mb_prefetch_fini(sb, elr->lr_next_group, nr); trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group, nr); if (group >= elr->lr_next_group) { ret = 1; if (elr->lr_first_not_zeroed != ngroups && !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) { elr->lr_next_group = elr->lr_first_not_zeroed; elr->lr_mode = EXT4_LI_MODE_ITABLE; ret = 0; } } return ret; } for (; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) { ret = 1; break; } if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; } if (group >= ngroups) ret = 1; if (!ret) { start_time = ktime_get_real_ns(); ret = ext4_init_inode_table(sb, group, elr->lr_timeout ? 0 : 1); trace_ext4_lazy_itable_init(sb, group); if (elr->lr_timeout == 0) { elr->lr_timeout = nsecs_to_jiffies((ktime_get_real_ns() - start_time) * EXT4_SB(elr->lr_super)->s_li_wait_mult); } elr->lr_next_sched = jiffies + elr->lr_timeout; elr->lr_next_group = group + 1; } return ret; } /* * Remove lr_request from the list_request and free the * request structure. Should be called with li_list_mtx held */ static void ext4_remove_li_request(struct ext4_li_request *elr) { if (!elr) return; list_del(&elr->lr_request); EXT4_SB(elr->lr_super)->s_li_request = NULL; kfree(elr); } static void ext4_unregister_li_request(struct super_block *sb) { mutex_lock(&ext4_li_mtx); if (!ext4_li_info) { mutex_unlock(&ext4_li_mtx); return; } mutex_lock(&ext4_li_info->li_list_mtx); ext4_remove_li_request(EXT4_SB(sb)->s_li_request); mutex_unlock(&ext4_li_info->li_list_mtx); mutex_unlock(&ext4_li_mtx); } static struct task_struct *ext4_lazyinit_task; /* * This is the function where ext4lazyinit thread lives. It walks * through the request list searching for next scheduled filesystem. * When such a fs is found, run the lazy initialization request * (ext4_rn_li_request) and keep track of the time spend in this * function. Based on that time we compute next schedule time of * the request. When walking through the list is complete, compute * next waking time and put itself into sleep. */ static int ext4_lazyinit_thread(void *arg) { struct ext4_lazy_init *eli = arg; struct list_head *pos, *n; struct ext4_li_request *elr; unsigned long next_wakeup, cur; BUG_ON(NULL == eli); set_freezable(); cont_thread: while (true) { next_wakeup = MAX_JIFFY_OFFSET; mutex_lock(&eli->li_list_mtx); if (list_empty(&eli->li_request_list)) { mutex_unlock(&eli->li_list_mtx); goto exit_thread; } list_for_each_safe(pos, n, &eli->li_request_list) { int err = 0; int progress = 0; elr = list_entry(pos, struct ext4_li_request, lr_request); if (time_before(jiffies, elr->lr_next_sched)) { if (time_before(elr->lr_next_sched, next_wakeup)) next_wakeup = elr->lr_next_sched; continue; } if (down_read_trylock(&elr->lr_super->s_umount)) { if (sb_start_write_trylock(elr->lr_super)) { progress = 1; /* * We hold sb->s_umount, sb can not * be removed from the list, it is * now safe to drop li_list_mtx */ mutex_unlock(&eli->li_list_mtx); err = ext4_run_li_request(elr); sb_end_write(elr->lr_super); mutex_lock(&eli->li_list_mtx); n = pos->next; } up_read((&elr->lr_super->s_umount)); } /* error, remove the lazy_init job */ if (err) { ext4_remove_li_request(elr); continue; } if (!progress) { elr->lr_next_sched = jiffies + get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ); } if (time_before(elr->lr_next_sched, next_wakeup)) next_wakeup = elr->lr_next_sched; } mutex_unlock(&eli->li_list_mtx); try_to_freeze(); cur = jiffies; if ((time_after_eq(cur, next_wakeup)) || (MAX_JIFFY_OFFSET == next_wakeup)) { cond_resched(); continue; } schedule_timeout_interruptible(next_wakeup - cur); if (kthread_should_stop()) { ext4_clear_request_list(); goto exit_thread; } } exit_thread: /* * It looks like the request list is empty, but we need * to check it under the li_list_mtx lock, to prevent any * additions into it, and of course we should lock ext4_li_mtx * to atomically free the list and ext4_li_info, because at * this point another ext4 filesystem could be registering * new one. */ mutex_lock(&ext4_li_mtx); mutex_lock(&eli->li_list_mtx); if (!list_empty(&eli->li_request_list)) { mutex_unlock(&eli->li_list_mtx); mutex_unlock(&ext4_li_mtx); goto cont_thread; } mutex_unlock(&eli->li_list_mtx); kfree(ext4_li_info); ext4_li_info = NULL; mutex_unlock(&ext4_li_mtx); return 0; } static void ext4_clear_request_list(void) { struct list_head *pos, *n; struct ext4_li_request *elr; mutex_lock(&ext4_li_info->li_list_mtx); list_for_each_safe(pos, n, &ext4_li_info->li_request_list) { elr = list_entry(pos, struct ext4_li_request, lr_request); ext4_remove_li_request(elr); } mutex_unlock(&ext4_li_info->li_list_mtx); } static int ext4_run_lazyinit_thread(void) { ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit"); if (IS_ERR(ext4_lazyinit_task)) { int err = PTR_ERR(ext4_lazyinit_task); ext4_clear_request_list(); kfree(ext4_li_info); ext4_li_info = NULL; printk(KERN_CRIT "EXT4-fs: error %d creating inode table " "initialization thread\n", err); return err; } ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING; return 0; } /* * Check whether it make sense to run itable init. thread or not. * If there is at least one uninitialized inode table, return * corresponding group number, else the loop goes through all * groups and return total number of groups. */ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) { ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count; struct ext4_group_desc *gdp = NULL; if (!ext4_has_group_desc_csum(sb)) return ngroups; for (group = 0; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) continue; if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; } return group; } static int ext4_li_info_new(void) { struct ext4_lazy_init *eli = NULL; eli = kzalloc(sizeof(*eli), GFP_KERNEL); if (!eli) return -ENOMEM; INIT_LIST_HEAD(&eli->li_request_list); mutex_init(&eli->li_list_mtx); eli->li_state |= EXT4_LAZYINIT_QUIT; ext4_li_info = eli; return 0; } static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, ext4_group_t start) { struct ext4_li_request *elr; elr = kzalloc(sizeof(*elr), GFP_KERNEL); if (!elr) return NULL; elr->lr_super = sb; elr->lr_first_not_zeroed = start; if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) { elr->lr_mode = EXT4_LI_MODE_ITABLE; elr->lr_next_group = start; } else { elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP; } /* * Randomize first schedule time of the request to * spread the inode table initialization requests * better. */ elr->lr_next_sched = jiffies + get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ); return elr; } int ext4_register_li_request(struct super_block *sb, ext4_group_t first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_li_request *elr = NULL; ext4_group_t ngroups = sbi->s_groups_count; int ret = 0; mutex_lock(&ext4_li_mtx); if (sbi->s_li_request != NULL) { /* * Reset timeout so it can be computed again, because * s_li_wait_mult might have changed. */ sbi->s_li_request->lr_timeout = 0; goto out; } if (sb_rdonly(sb) || (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS) && (first_not_zeroed == ngroups || !test_opt(sb, INIT_INODE_TABLE)))) goto out; elr = ext4_li_request_new(sb, first_not_zeroed); if (!elr) { ret = -ENOMEM; goto out; } if (NULL == ext4_li_info) { ret = ext4_li_info_new(); if (ret) goto out; } mutex_lock(&ext4_li_info->li_list_mtx); list_add(&elr->lr_request, &ext4_li_info->li_request_list); mutex_unlock(&ext4_li_info->li_list_mtx); sbi->s_li_request = elr; /* * set elr to NULL here since it has been inserted to * the request_list and the removal and free of it is * handled by ext4_clear_request_list from now on. */ elr = NULL; if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) { ret = ext4_run_lazyinit_thread(); if (ret) goto out; } out: mutex_unlock(&ext4_li_mtx); if (ret) kfree(elr); return ret; } /* * We do not need to lock anything since this is called on * module unload. */ static void ext4_destroy_lazyinit_thread(void) { /* * If thread exited earlier * there's nothing to be done. */ if (!ext4_li_info || !ext4_lazyinit_task) return; kthread_stop(ext4_lazyinit_task); } static int set_journal_csum_feature_set(struct super_block *sb) { int ret = 1; int compat, incompat; struct ext4_sb_info *sbi = EXT4_SB(sb); if (ext4_has_metadata_csum(sb)) { /* journal checksum v3 */ compat = 0; incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3; } else { /* journal checksum v1 */ compat = JBD2_FEATURE_COMPAT_CHECKSUM; incompat = 0; } jbd2_journal_clear_features(sbi->s_journal, JBD2_FEATURE_COMPAT_CHECKSUM, 0, JBD2_FEATURE_INCOMPAT_CSUM_V3 | JBD2_FEATURE_INCOMPAT_CSUM_V2); if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ret = jbd2_journal_set_features(sbi->s_journal, compat, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | incompat); } else if (test_opt(sb, JOURNAL_CHECKSUM)) { ret = jbd2_journal_set_features(sbi->s_journal, compat, 0, incompat); jbd2_journal_clear_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); } else { jbd2_journal_clear_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); } return ret; } /* * Note: calculating the overhead so we can be compatible with * historical BSD practice is quite difficult in the face of * clusters/bigalloc. This is because multiple metadata blocks from * different block group can end up in the same allocation cluster. * Calculating the exact overhead in the face of clustered allocation * requires either O(all block bitmaps) in memory or O(number of block * groups**2) in time. We will still calculate the superblock for * older file systems --- and if we come across with a bigalloc file * system with zero in s_overhead_clusters the estimate will be close to * correct especially for very large cluster sizes --- but for newer * file systems, it's better to calculate this figure once at mkfs * time, and store it in the superblock. If the superblock value is * present (even for non-bigalloc file systems), we will use it. */ static int count_overhead(struct super_block *sb, ext4_group_t grp, char *buf) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp; ext4_fsblk_t first_block, last_block, b; ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; int has_super = ext4_bg_has_super(sb, grp); if (!ext4_has_feature_bigalloc(sb)) return (has_super + ext4_bg_num_gdb(sb, grp) + (has_super ? le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0) + sbi->s_itb_per_group + 2); first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + (grp * EXT4_BLOCKS_PER_GROUP(sb)); last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1; for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); b = ext4_block_bitmap(sb, gdp); if (b >= first_block && b <= last_block) { ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); count++; } b = ext4_inode_bitmap(sb, gdp); if (b >= first_block && b <= last_block) { ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); count++; } b = ext4_inode_table(sb, gdp); if (b >= first_block && b + sbi->s_itb_per_group <= last_block) for (j = 0; j < sbi->s_itb_per_group; j++, b++) { int c = EXT4_B2C(sbi, b - first_block); ext4_set_bit(c, buf); count++; } if (i != grp) continue; s = 0; if (ext4_bg_has_super(sb, grp)) { ext4_set_bit(s++, buf); count++; } j = ext4_bg_num_gdb(sb, grp); if (s + j > EXT4_BLOCKS_PER_GROUP(sb)) { ext4_error(sb, "Invalid number of block group " "descriptor blocks: %d", j); j = EXT4_BLOCKS_PER_GROUP(sb) - s; } count += j; for (; j > 0; j--) ext4_set_bit(EXT4_B2C(sbi, s++), buf); } if (!count) return 0; return EXT4_CLUSTERS_PER_GROUP(sb) - ext4_count_free(buf, EXT4_CLUSTERS_PER_GROUP(sb) / 8); } /* * Compute the overhead and stash it in sbi->s_overhead */ int ext4_calculate_overhead(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct inode *j_inode; unsigned int j_blocks, j_inum = le32_to_cpu(es->s_journal_inum); ext4_group_t i, ngroups = ext4_get_groups_count(sb); ext4_fsblk_t overhead = 0; char *buf = (char *) get_zeroed_page(GFP_NOFS); if (!buf) return -ENOMEM; /* * Compute the overhead (FS structures). This is constant * for a given filesystem unless the number of block groups * changes so we cache the previous value until it does. */ /* * All of the blocks before first_data_block are overhead */ overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block)); /* * Add the overhead found in each block group */ for (i = 0; i < ngroups; i++) { int blks; blks = count_overhead(sb, i, buf); overhead += blks; if (blks) memset(buf, 0, PAGE_SIZE); cond_resched(); } /* * Add the internal journal blocks whether the journal has been * loaded or not */ if (sbi->s_journal && !sbi->s_journal_bdev_file) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); if (!IS_ERR(j_inode)) { j_blocks = j_inode->i_size >> sb->s_blocksize_bits; overhead += EXT4_NUM_B2C(sbi, j_blocks); iput(j_inode); } else { ext4_msg(sb, KERN_ERR, "can't get journal size"); } } sbi->s_overhead = overhead; smp_wmb(); free_page((unsigned long) buf); return 0; } static void ext4_set_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; struct ext4_sb_info *sbi = EXT4_SB(sb); /* * There's no need to reserve anything when we aren't using extents. * The space estimates are exact, there are no unwritten extents, * hole punching doesn't need new metadata... This is needed especially * to keep ext2/3 backward compatibility. */ if (!ext4_has_feature_extents(sb)) return; /* * By default we reserve 2% or 4096 clusters, whichever is smaller. * This should cover the situations where we can not afford to run * out of space like for example punch hole, or converting * unwritten extents in delalloc path. In most cases such * allocation would require 1, or 2 blocks, higher numbers are * very rare. */ resv_clusters = (ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits); do_div(resv_clusters, 50); resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096); atomic64_set(&sbi->s_resv_clusters, resv_clusters); } static const char *ext4_quota_mode(struct super_block *sb) { #ifdef CONFIG_QUOTA if (!ext4_quota_capable(sb)) return "none"; if (EXT4_SB(sb)->s_journal && ext4_is_quota_journalled(sb)) return "journalled"; else return "writeback"; #else return "disabled"; #endif } static void ext4_setup_csum_trigger(struct super_block *sb, enum ext4_journal_trigger_type type, void (*trigger)( struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size)) { struct ext4_sb_info *sbi = EXT4_SB(sb); sbi->s_journal_triggers[type].sb = sb; sbi->s_journal_triggers[type].tr_triggers.t_frozen = trigger; } static void ext4_free_sbi(struct ext4_sb_info *sbi) { if (!sbi) return; kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); } static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb) { struct ext4_sb_info *sbi; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return NULL; sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off, NULL, NULL); sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); if (!sbi->s_blockgroup_lock) goto err_out; sb->s_fs_info = sbi; sbi->s_sb = sb; return sbi; err_out: fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); return NULL; } static void ext4_set_def_opts(struct super_block *sb, struct ext4_super_block *es) { unsigned long def_mount_opts; /* Set defaults before we parse the mount options */ def_mount_opts = le32_to_cpu(es->s_default_mount_opts); set_opt(sb, INIT_INODE_TABLE); if (def_mount_opts & EXT4_DEFM_DEBUG) set_opt(sb, DEBUG); if (def_mount_opts & EXT4_DEFM_BSDGROUPS) set_opt(sb, GRPID); if (def_mount_opts & EXT4_DEFM_UID16) set_opt(sb, NO_UID32); /* xattr user namespace & acls are now defaulted on */ set_opt(sb, XATTR_USER); #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif if (ext4_has_feature_fast_commit(sb)) set_opt2(sb, JOURNAL_FAST_COMMIT); /* don't forget to enable journal_csum when metadata_csum is enabled. */ if (ext4_has_metadata_csum(sb)) set_opt(sb, JOURNAL_CHECKSUM); if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) set_opt(sb, JOURNAL_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED) set_opt(sb, ORDERED_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK) set_opt(sb, WRITEBACK_DATA); if (le16_to_cpu(es->s_errors) == EXT4_ERRORS_PANIC) set_opt(sb, ERRORS_PANIC); else if (le16_to_cpu(es->s_errors) == EXT4_ERRORS_CONTINUE) set_opt(sb, ERRORS_CONT); else set_opt(sb, ERRORS_RO); /* block_validity enabled by default; disable with noblock_validity */ set_opt(sb, BLOCK_VALIDITY); if (def_mount_opts & EXT4_DEFM_DISCARD) set_opt(sb, DISCARD); if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0) set_opt(sb, BARRIER); /* * enable delayed allocation by default * Use -o nodelalloc to turn it off */ if (!IS_EXT3_SB(sb) && !IS_EXT2_SB(sb) && ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0)) set_opt(sb, DELALLOC); if (sb->s_blocksize <= PAGE_SIZE) set_opt(sb, DIOREAD_NOLOCK); } static int ext4_handle_clustersize(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int clustersize; /* Handle clustersize */ clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size); if (ext4_has_feature_bigalloc(sb)) { if (clustersize < sb->s_blocksize) { ext4_msg(sb, KERN_ERR, "cluster size (%d) smaller than " "block size (%lu)", clustersize, sb->s_blocksize); return -EINVAL; } sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - le32_to_cpu(es->s_log_block_size); } else { if (clustersize != sb->s_blocksize) { ext4_msg(sb, KERN_ERR, "fragment/cluster size (%d) != " "block size (%lu)", clustersize, sb->s_blocksize); return -EINVAL; } if (sbi->s_blocks_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "#blocks per group too big: %lu", sbi->s_blocks_per_group); return -EINVAL; } sbi->s_cluster_bits = 0; } sbi->s_clusters_per_group = le32_to_cpu(es->s_clusters_per_group); if (sbi->s_clusters_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "#clusters per group too big: %lu", sbi->s_clusters_per_group); return -EINVAL; } if (sbi->s_blocks_per_group != (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) { ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and clusters per group (%lu) inconsistent", sbi->s_blocks_per_group, sbi->s_clusters_per_group); return -EINVAL; } sbi->s_cluster_ratio = clustersize / sb->s_blocksize; /* Do we have standard group size of clustersize * 8 blocks ? */ if (sbi->s_blocks_per_group == clustersize << 3) set_opt2(sb, STD_GROUP_SIZE); return 0; } static void ext4_fast_commit_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* Initialize fast commit stuff */ atomic_set(&sbi->s_fc_subtid, 0); INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_STAGING]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]); sbi->s_fc_bytes = 0; ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); sbi->s_fc_ineligible_tid = 0; spin_lock_init(&sbi->s_fc_lock); memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); sbi->s_fc_replay_state.fc_regions = NULL; sbi->s_fc_replay_state.fc_regions_size = 0; sbi->s_fc_replay_state.fc_regions_used = 0; sbi->s_fc_replay_state.fc_regions_valid = 0; sbi->s_fc_replay_state.fc_modified_inodes = NULL; sbi->s_fc_replay_state.fc_modified_inodes_size = 0; sbi->s_fc_replay_state.fc_modified_inodes_used = 0; } static int ext4_inode_info_init(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; } else { sbi->s_inode_size = le16_to_cpu(es->s_inode_size); sbi->s_first_ino = le32_to_cpu(es->s_first_ino); if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) { ext4_msg(sb, KERN_ERR, "invalid first ino: %u", sbi->s_first_ino); return -EINVAL; } if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || (!is_power_of_2(sbi->s_inode_size)) || (sbi->s_inode_size > sb->s_blocksize)) { ext4_msg(sb, KERN_ERR, "unsupported inode size: %d", sbi->s_inode_size); ext4_msg(sb, KERN_ERR, "blocksize: %lu", sb->s_blocksize); return -EINVAL; } /* * i_atime_extra is the last extra field available for * [acm]times in struct ext4_inode. Checking for that * field should suffice to ensure we have extra space * for all three. */ if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) + sizeof(((struct ext4_inode *)0)->i_atime_extra)) { sb->s_time_gran = 1; sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX; } else { sb->s_time_gran = NSEC_PER_SEC; sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX; } sb->s_time_min = EXT4_TIMESTAMP_MIN; } if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { sbi->s_want_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; if (ext4_has_feature_extra_isize(sb)) { unsigned v, max = (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE); v = le16_to_cpu(es->s_want_extra_isize); if (v > max) { ext4_msg(sb, KERN_ERR, "bad s_want_extra_isize: %d", v); return -EINVAL; } if (sbi->s_want_extra_isize < v) sbi->s_want_extra_isize = v; v = le16_to_cpu(es->s_min_extra_isize); if (v > max) { ext4_msg(sb, KERN_ERR, "bad s_min_extra_isize: %d", v); return -EINVAL; } if (sbi->s_want_extra_isize < v) sbi->s_want_extra_isize = v; } } return 0; } #if IS_ENABLED(CONFIG_UNICODE) static int ext4_encoding_init(struct super_block *sb, struct ext4_super_block *es) { const struct ext4_sb_encodings *encoding_info; struct unicode_map *encoding; __u16 encoding_flags = le16_to_cpu(es->s_encoding_flags); if (!ext4_has_feature_casefold(sb) || sb->s_encoding) return 0; encoding_info = ext4_sb_read_encoding(es); if (!encoding_info) { ext4_msg(sb, KERN_ERR, "Encoding requested by superblock is unknown"); return -EINVAL; } encoding = utf8_load(encoding_info->version); if (IS_ERR(encoding)) { ext4_msg(sb, KERN_ERR, "can't mount with superblock charset: %s-%u.%u.%u " "not supported by the kernel. flags: 0x%x.", encoding_info->name, unicode_major(encoding_info->version), unicode_minor(encoding_info->version), unicode_rev(encoding_info->version), encoding_flags); return -EINVAL; } ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: " "%s-%u.%u.%u with flags 0x%hx", encoding_info->name, unicode_major(encoding_info->version), unicode_minor(encoding_info->version), unicode_rev(encoding_info->version), encoding_flags); sb->s_encoding = encoding; sb->s_encoding_flags = encoding_flags; return 0; } #else static inline int ext4_encoding_init(struct super_block *sb, struct ext4_super_block *es) { return 0; } #endif static int ext4_init_metadata_csum(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* Warn if metadata_csum and gdt_csum are both set. */ if (ext4_has_feature_metadata_csum(sb) && ext4_has_feature_gdt_csum(sb)) ext4_warning(sb, "metadata_csum and uninit_bg are " "redundant flags; please run fsck."); /* Check for a known checksum algorithm */ if (!ext4_verify_csum_type(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " "unknown checksum algorithm."); return -EINVAL; } ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE, ext4_orphan_file_block_trigger); /* Load the checksum driver */ sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(sbi->s_chksum_driver)) { int ret = PTR_ERR(sbi->s_chksum_driver); ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver."); sbi->s_chksum_driver = NULL; return ret; } /* Check superblock checksum */ if (!ext4_superblock_csum_verify(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " "invalid superblock checksum. Run e2fsck?"); return -EFSBADCRC; } /* Precompute checksum seed for all metadata */ if (ext4_has_feature_csum_seed(sb)) sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed); else if (ext4_has_metadata_csum(sb) || ext4_has_feature_ea_inode(sb)) sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, sizeof(es->s_uuid)); return 0; } static int ext4_check_feature_compatibility(struct super_block *sb, struct ext4_super_block *es, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV && (ext4_has_compat_features(sb) || ext4_has_ro_compat_features(sb) || ext4_has_incompat_features(sb))) ext4_msg(sb, KERN_WARNING, "feature flags set on rev 0 fs, " "running e2fsck is recommended"); if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) { set_opt2(sb, HURD_COMPAT); if (ext4_has_feature_64bit(sb)) { ext4_msg(sb, KERN_ERR, "The Hurd can't support 64-bit file systems"); return -EINVAL; } /* * ea_inode feature uses l_i_version field which is not * available in HURD_COMPAT mode. */ if (ext4_has_feature_ea_inode(sb)) { ext4_msg(sb, KERN_ERR, "ea_inode feature is not supported for Hurd"); return -EINVAL; } } if (IS_EXT2_SB(sb)) { if (ext2_feature_set_ok(sb)) ext4_msg(sb, KERN_INFO, "mounting ext2 file system " "using the ext4 subsystem"); else { /* * If we're probing be silent, if this looks like * it's actually an ext[34] filesystem. */ if (silent && ext4_feature_set_ok(sb, sb_rdonly(sb))) return -EINVAL; ext4_msg(sb, KERN_ERR, "couldn't mount as ext2 due " "to feature incompatibilities"); return -EINVAL; } } if (IS_EXT3_SB(sb)) { if (ext3_feature_set_ok(sb)) ext4_msg(sb, KERN_INFO, "mounting ext3 file system " "using the ext4 subsystem"); else { /* * If we're probing be silent, if this looks like * it's actually an ext4 filesystem. */ if (silent && ext4_feature_set_ok(sb, sb_rdonly(sb))) return -EINVAL; ext4_msg(sb, KERN_ERR, "couldn't mount as ext3 due " "to feature incompatibilities"); return -EINVAL; } } /* * Check feature flags regardless of the revision level, since we * previously didn't change the revision level when setting the flags, * so there is a chance incompat flags are set on a rev 0 filesystem. */ if (!ext4_feature_set_ok(sb, (sb_rdonly(sb)))) return -EINVAL; if (sbi->s_daxdev) { if (sb->s_blocksize == PAGE_SIZE) set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); else ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n"); } if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) { if (ext4_has_feature_inline_data(sb)) { ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem" " that may contain inline data"); return -EINVAL; } if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) { ext4_msg(sb, KERN_ERR, "DAX unsupported by block device."); return -EINVAL; } } if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) { ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d", es->s_encryption_level); return -EINVAL; } return 0; } static int ext4_check_geometry(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); __u64 blocks_count; int err; if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (sb->s_blocksize / 4)) { ext4_msg(sb, KERN_ERR, "Number of reserved GDT blocks insanely large: %d", le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks)); return -EINVAL; } /* * Test whether we have more sectors than will fit in sector_t, * and whether the max offset is addressable by the page cache. */ err = generic_check_addressable(sb->s_blocksize_bits, ext4_blocks_count(es)); if (err) { ext4_msg(sb, KERN_ERR, "filesystem" " too large to mount safely on this system"); return err; } /* check blocks count against device size */ blocks_count = sb_bdev_nr_blocks(sb); if (blocks_count && ext4_blocks_count(es) > blocks_count) { ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu " "exceeds size of device (%llu blocks)", ext4_blocks_count(es), blocks_count); return -EINVAL; } /* * It makes no sense for the first data block to be beyond the end * of the filesystem. */ if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { ext4_msg(sb, KERN_WARNING, "bad geometry: first data " "block %u is beyond end of filesystem (%llu)", le32_to_cpu(es->s_first_data_block), ext4_blocks_count(es)); return -EINVAL; } if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) && (sbi->s_cluster_ratio == 1)) { ext4_msg(sb, KERN_WARNING, "bad geometry: first data " "block is 0 with a 1k block and cluster size"); return -EINVAL; } blocks_count = (ext4_blocks_count(es) - le32_to_cpu(es->s_first_data_block) + EXT4_BLOCKS_PER_GROUP(sb) - 1); do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) { ext4_msg(sb, KERN_WARNING, "groups count too large: %llu " "(block count %llu, first data block %u, " "blocks per group %lu)", blocks_count, ext4_blocks_count(es), le32_to_cpu(es->s_first_data_block), EXT4_BLOCKS_PER_GROUP(sb)); return -EINVAL; } sbi->s_groups_count = blocks_count; sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != le32_to_cpu(es->s_inodes_count)) { ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", le32_to_cpu(es->s_inodes_count), ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); return -EINVAL; } return 0; } static int ext4_group_desc_init(struct super_block *sb, struct ext4_super_block *es, ext4_fsblk_t logical_sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned int db_count; ext4_fsblk_t block; int i; db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); if (ext4_has_feature_meta_bg(sb)) { if (le32_to_cpu(es->s_first_meta_bg) > db_count) { ext4_msg(sb, KERN_WARNING, "first meta block group too large: %u " "(group descriptor block count %u)", le32_to_cpu(es->s_first_meta_bg), db_count); return -EINVAL; } } rcu_assign_pointer(sbi->s_group_desc, kvmalloc_array(db_count, sizeof(struct buffer_head *), GFP_KERNEL)); if (sbi->s_group_desc == NULL) { ext4_msg(sb, KERN_ERR, "not enough memory"); return -ENOMEM; } bgl_lock_init(sbi->s_blockgroup_lock); /* Pre-read the descriptors into the buffer cache */ for (i = 0; i < db_count; i++) { block = descriptor_loc(sb, logical_sb_block, i); ext4_sb_breadahead_unmovable(sb, block); } for (i = 0; i < db_count; i++) { struct buffer_head *bh; block = descriptor_loc(sb, logical_sb_block, i); bh = ext4_sb_bread_unmovable(sb, block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "can't read group descriptor %d", i); sbi->s_gdb_count = i; return PTR_ERR(bh); } rcu_read_lock(); rcu_dereference(sbi->s_group_desc)[i] = bh; rcu_read_unlock(); } sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); return -EFSCORRUPTED; } return 0; } static int ext4_load_and_init_journal(struct super_block *sb, struct ext4_super_block *es, struct ext4_fs_context *ctx) { struct ext4_sb_info *sbi = EXT4_SB(sb); int err; err = ext4_load_journal(sb, es, ctx->journal_devnum); if (err) return err; if (ext4_has_feature_64bit(sb) && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_64BIT)) { ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature"); goto out; } if (!set_journal_csum_feature_set(sb)) { ext4_msg(sb, KERN_ERR, "Failed to set journal checksum " "feature set"); goto out; } if (test_opt2(sb, JOURNAL_FAST_COMMIT) && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) { ext4_msg(sb, KERN_ERR, "Failed to set fast commit journal feature"); goto out; } /* We have now updated the journal if required, so we can * validate the data journaling mode. */ switch (test_opt(sb, DATA_FLAGS)) { case 0: /* No mode set, assume a default based on the journal * capabilities: ORDERED_DATA if the journal can * cope, else JOURNAL_DATA */ if (jbd2_journal_check_available_features (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { set_opt(sb, ORDERED_DATA); sbi->s_def_mount_opt |= EXT4_MOUNT_ORDERED_DATA; } else { set_opt(sb, JOURNAL_DATA); sbi->s_def_mount_opt |= EXT4_MOUNT_JOURNAL_DATA; } break; case EXT4_MOUNT_ORDERED_DATA: case EXT4_MOUNT_WRITEBACK_DATA: if (!jbd2_journal_check_available_features (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { ext4_msg(sb, KERN_ERR, "Journal does not support " "requested data journaling mode"); goto out; } break; default: break; } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA && test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit in data=ordered mode"); goto out; } set_task_ioprio(sbi->s_journal->j_task, ctx->journal_ioprio); sbi->s_journal->j_submit_inode_data_buffers = ext4_journal_submit_inode_data_buffers; sbi->s_journal->j_finish_inode_data_buffers = ext4_journal_finish_inode_data_buffers; return 0; out: /* flush s_sb_upd_work before destroying the journal. */ flush_work(&sbi->s_sb_upd_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; return -EINVAL; } static int ext4_check_journal_data_mode(struct super_block *sb) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with " "data=journal disables delayed allocation, " "dioread_nolock, O_DIRECT and fast_commit support!\n"); /* can't mount with both data=journal and dioread_nolock. */ clear_opt(sb, DIOREAD_NOLOCK); clear_opt2(sb, JOURNAL_FAST_COMMIT); if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); return -EINVAL; } if (test_opt(sb, DAX_ALWAYS)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and dax"); return -EINVAL; } if (ext4_has_feature_encrypt(sb)) { ext4_msg(sb, KERN_WARNING, "encrypted files will use data=ordered " "instead of data journaling mode"); } if (test_opt(sb, DELALLOC)) clear_opt(sb, DELALLOC); } else { sb->s_iflags |= SB_I_CGROUPWB; } return 0; } static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es; ext4_fsblk_t logical_sb_block; unsigned long offset = 0; struct buffer_head *bh; int ret = -EINVAL; int blocksize; blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); if (!blocksize) { ext4_msg(sb, KERN_ERR, "unable to set blocksize"); return -EINVAL; } /* * The ext4 superblock will not be buffer aligned for other than 1kB * block sizes. We need to calculate the offset from buffer start. */ if (blocksize != EXT4_MIN_BLOCK_SIZE) { logical_sb_block = sbi->s_sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); } else { logical_sb_block = sbi->s_sb_block; } bh = ext4_sb_bread_unmovable(sb, logical_sb_block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "unable to read superblock"); return PTR_ERR(bh); } /* * Note: s_es must be initialized as soon as possible because * some ext4 macro-instructions depend on its value */ es = (struct ext4_super_block *) (bh->b_data + offset); sbi->s_es = es; sb->s_magic = le16_to_cpu(es->s_magic); if (sb->s_magic != EXT4_SUPER_MAGIC) { if (!silent) ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); goto out; } if (le32_to_cpu(es->s_log_block_size) > (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, "Invalid log block size: %u", le32_to_cpu(es->s_log_block_size)); goto out; } if (le32_to_cpu(es->s_log_cluster_size) > (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, "Invalid log cluster size: %u", le32_to_cpu(es->s_log_cluster_size)); goto out; } blocksize = EXT4_MIN_BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); /* * If the default block size is not the same as the real block size, * we need to reload it. */ if (sb->s_blocksize == blocksize) { *lsb = logical_sb_block; sbi->s_sbh = bh; return 0; } /* * bh must be released before kill_bdev(), otherwise * it won't be freed and its page also. kill_bdev() * is called by sb_set_blocksize(). */ brelse(bh); /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { ext4_msg(sb, KERN_ERR, "bad block size %d", blocksize); bh = NULL; goto out; } logical_sb_block = sbi->s_sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); bh = ext4_sb_bread_unmovable(sb, logical_sb_block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "Can't read superblock on 2nd try"); ret = PTR_ERR(bh); bh = NULL; goto out; } es = (struct ext4_super_block *)(bh->b_data + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { ext4_msg(sb, KERN_ERR, "Magic mismatch, very weird!"); goto out; } *lsb = logical_sb_block; sbi->s_sbh = bh; return 0; out: brelse(bh); return ret; } static void ext4_hash_info_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; unsigned int i; for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; if (ext4_has_feature_dir_index(sb)) { i = le32_to_cpu(es->s_flags); if (i & EXT2_FLAGS_UNSIGNED_HASH) sbi->s_hash_unsigned = 3; else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { #ifdef __CHAR_UNSIGNED__ if (!sb_rdonly(sb)) es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); sbi->s_hash_unsigned = 3; #else if (!sb_rdonly(sb)) es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); #endif } } } static int ext4_block_group_meta_init(struct super_block *sb, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int has_huge_files; has_huge_files = ext4_has_feature_huge_file(sb); sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits, has_huge_files); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files); sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (ext4_has_feature_64bit(sb)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || sbi->s_desc_size > EXT4_MAX_DESC_SIZE || !is_power_of_2(sbi->s_desc_size)) { ext4_msg(sb, KERN_ERR, "unsupported descriptor size %lu", sbi->s_desc_size); return -EINVAL; } } else sbi->s_desc_size = EXT4_MIN_DESC_SIZE; sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); sbi->s_inodes_per_block = sb->s_blocksize / EXT4_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0 || sbi->s_blocks_per_group == 0) { if (!silent) ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); return -EINVAL; } if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || sbi->s_inodes_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n", sbi->s_inodes_per_group); return -EINVAL; } sbi->s_itb_per_group = sbi->s_inodes_per_group / sbi->s_inodes_per_block; sbi->s_desc_per_block = sb->s_blocksize / EXT4_DESC_SIZE(sb); sbi->s_mount_state = le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY; sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); return 0; } static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) { struct ext4_super_block *es = NULL; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t logical_sb_block; struct inode *root; int needs_recovery; int err; ext4_group_t first_not_zeroed; struct ext4_fs_context *ctx = fc->fs_private; int silent = fc->sb_flags & SB_SILENT; /* Set defaults for the variables that will be set during parsing */ if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sectors_written_start = part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); err = ext4_load_super(sb, &logical_sb_block, silent); if (err) goto out_fail; es = sbi->s_es; sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written); err = ext4_init_metadata_csum(sb, es); if (err) goto failed_mount; ext4_set_def_opts(sb, es); sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; /* * set default s_li_wait_mult for lazyinit, for the case there is * no mount option specified. */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; err = ext4_inode_info_init(sb, es); if (err) goto failed_mount; err = parse_apply_sb_mount_options(sb, ctx); if (err < 0) goto failed_mount; sbi->s_def_mount_opt = sbi->s_mount_opt; sbi->s_def_mount_opt2 = sbi->s_mount_opt2; err = ext4_check_opt_consistency(fc, sb); if (err < 0) goto failed_mount; ext4_apply_options(fc, sb); err = ext4_encoding_init(sb, es); if (err) goto failed_mount; err = ext4_check_journal_data_mode(sb); if (err) goto failed_mount; sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); /* i_version is always enabled now */ sb->s_flags |= SB_I_VERSION; err = ext4_check_feature_compatibility(sb, es, silent); if (err) goto failed_mount; err = ext4_block_group_meta_init(sb, silent); if (err) goto failed_mount; ext4_hash_info_init(sb); err = ext4_handle_clustersize(sb); if (err) goto failed_mount; err = ext4_check_geometry(sb, es); if (err) goto failed_mount; timer_setup(&sbi->s_err_report, print_daily_error_info, 0); spin_lock_init(&sbi->s_error_lock); INIT_WORK(&sbi->s_sb_upd_work, update_super_work); err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed); if (err) goto failed_mount3; err = ext4_es_register_shrinker(sbi); if (err) goto failed_mount3; sbi->s_stripe = ext4_get_stripe_size(sbi); /* * It's hard to get stripe aligned blocks if stripe is not aligned with * cluster, just disable stripe and alert user to simpfy code and avoid * stripe aligned allocation which will rarely successes. */ if (sbi->s_stripe > 0 && sbi->s_cluster_ratio > 1 && sbi->s_stripe % sbi->s_cluster_ratio != 0) { ext4_msg(sb, KERN_WARNING, "stripe (%lu) is not aligned with cluster size (%u), " "stripe is disabled", sbi->s_stripe, sbi->s_cluster_ratio); sbi->s_stripe = 0; } sbi->s_extent_max_zeroout_kb = 32; /* * set up enough so that it can read an inode */ sb->s_op = &ext4_sops; sb->s_export_op = &ext4_export_ops; sb->s_xattr = ext4_xattr_handlers; #ifdef CONFIG_FS_ENCRYPTION sb->s_cop = &ext4_cryptops; #endif #ifdef CONFIG_FS_VERITY sb->s_vop = &ext4_verityops; #endif #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; if (ext4_has_feature_quota(sb)) sb->s_qcop = &dquot_quotactl_sysfile_ops; else sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif super_set_uuid(sb, es->s_uuid, sizeof(es->s_uuid)); super_set_sysfs_name_bdev(sb); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); ext4_fast_commit_init(sb); sb->s_root = NULL; needs_recovery = (es->s_last_orphan != 0 || ext4_has_feature_orphan_present(sb) || ext4_has_feature_journal_needs_recovery(sb)); if (ext4_has_feature_mmp(sb) && !sb_rdonly(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); if (err) goto failed_mount3a; } err = -EINVAL; /* * The first inode we look at is the journal inode. Don't try * root first: it may be modified in the journal! */ if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) { err = ext4_load_and_init_journal(sb, es, ctx); if (err) goto failed_mount3a; } else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) && ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); goto failed_mount3a; } else { /* Nojournal mode, all journal mount options are illegal */ if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit, fs mounted w/o journal"); goto failed_mount3a; } if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_checksum, fs mounted w/o journal"); goto failed_mount3a; } if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { ext4_msg(sb, KERN_ERR, "can't mount with " "commit=%lu, fs mounted w/o journal", sbi->s_commit_interval / HZ); goto failed_mount3a; } if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { ext4_msg(sb, KERN_ERR, "can't mount with " "data=, fs mounted w/o journal"); goto failed_mount3a; } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); clear_opt(sb, DATA_FLAGS); clear_opt2(sb, JOURNAL_FAST_COMMIT); sbi->s_journal = NULL; needs_recovery = 0; } if (!test_opt(sb, NO_MBCACHE)) { sbi->s_ea_block_cache = ext4_xattr_create_cache(); if (!sbi->s_ea_block_cache) { ext4_msg(sb, KERN_ERR, "Failed to create ea_block_cache"); err = -EINVAL; goto failed_mount_wq; } if (ext4_has_feature_ea_inode(sb)) { sbi->s_ea_inode_cache = ext4_xattr_create_cache(); if (!sbi->s_ea_inode_cache) { ext4_msg(sb, KERN_ERR, "Failed to create ea_inode_cache"); err = -EINVAL; goto failed_mount_wq; } } } /* * Get the # of file system overhead blocks from the * superblock if present. */ sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); /* ignore the precalculated value if it is ridiculous */ if (sbi->s_overhead > ext4_blocks_count(es)) sbi->s_overhead = 0; /* * If the bigalloc feature is not enabled recalculating the * overhead doesn't take long, so we might as well just redo * it to make sure we are using the correct value. */ if (!ext4_has_feature_bigalloc(sb)) sbi->s_overhead = 0; if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq; } /* * The maximum number of concurrent works can be high and * concurrency isn't really necessary. Limit it to 1. */ EXT4_SB(sb)->rsv_conversion_wq = alloc_workqueue("ext4-rsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!EXT4_SB(sb)->rsv_conversion_wq) { printk(KERN_ERR "EXT4-fs: failed to create workqueue\n"); err = -ENOMEM; goto failed_mount4; } /* * The jbd2_journal_load will have done any necessary log recovery, * so we can safely mount the rest of the filesystem now. */ root = ext4_iget(sb, EXT4_ROOT_INO, EXT4_IGET_SPECIAL); if (IS_ERR(root)) { ext4_msg(sb, KERN_ERR, "get root inode failed"); err = PTR_ERR(root); root = NULL; goto failed_mount4; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck"); iput(root); err = -EFSCORRUPTED; goto failed_mount4; } generic_set_sb_d_ops(sb); sb->s_root = d_make_root(root); if (!sb->s_root) { ext4_msg(sb, KERN_ERR, "get root dentry failed"); err = -ENOMEM; goto failed_mount4; } err = ext4_setup_super(sb, es, sb_rdonly(sb)); if (err == -EROFS) { sb->s_flags |= SB_RDONLY; } else if (err) goto failed_mount4a; ext4_set_resv_clusters(sb); if (test_opt(sb, BLOCK_VALIDITY)) { err = ext4_setup_system_zone(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize system " "zone (%d)", err); goto failed_mount4a; } } ext4_fc_replay_cleanup(sb); ext4_ext_init(sb); /* * Enable optimize_scan if number of groups is > threshold. This can be * turned off by passing "mb_optimize_scan=0". This can also be * turned on forcefully by passing "mb_optimize_scan=1". */ if (!(ctx->spec & EXT4_SPEC_mb_optimize_scan)) { if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD) set_opt2(sb, MB_OPTIMIZE_SCAN); else clear_opt2(sb, MB_OPTIMIZE_SCAN); } err = ext4_mb_init(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)", err); goto failed_mount5; } /* * We can only set up the journal commit callback once * mballoc is initialized */ if (sbi->s_journal) sbi->s_journal->j_commit_callback = ext4_journal_commit_callback; err = ext4_percpu_param_init(sbi); if (err) goto failed_mount6; if (ext4_has_feature_flex_bg(sb)) if (!ext4_fill_flex_info(sb)) { ext4_msg(sb, KERN_ERR, "unable to initialize " "flex_bg meta info!"); err = -ENOMEM; goto failed_mount6; } err = ext4_register_li_request(sb, first_not_zeroed); if (err) goto failed_mount6; err = ext4_init_orphan_info(sb); if (err) goto failed_mount7; #ifdef CONFIG_QUOTA /* Enable quota usage during mount. */ if (ext4_has_feature_quota(sb) && !sb_rdonly(sb)) { err = ext4_enable_quotas(sb); if (err) goto failed_mount8; } #endif /* CONFIG_QUOTA */ /* * Save the original bdev mapping's wb_err value which could be * used to detect the metadata async write error. */ spin_lock_init(&sbi->s_bdev_wb_lock); errseq_check_and_advance(&sb->s_bdev->bd_mapping->wb_err, &sbi->s_bdev_wb_err); EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; /* * Update the checksum after updating free space/inode counters and * ext4_orphan_cleanup. Otherwise the superblock can have an incorrect * checksum in the buffer cache until it is written out and * e2fsprogs programs trying to open a file system immediately * after it is mounted can fail. */ ext4_superblock_csum_set(sb); if (needs_recovery) { ext4_msg(sb, KERN_INFO, "recovery complete"); err = ext4_mark_recovery_complete(sb, es); if (err) goto failed_mount9; } if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev)) ext4_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but the device does not support discard"); if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ /* Enable message ratelimiting. Default is 10 messages per 5 secs. */ ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10); atomic_set(&sbi->s_warning_count, 0); atomic_set(&sbi->s_msg_count, 0); /* Register sysfs after all initializations are complete. */ err = ext4_register_sysfs(sb); if (err) goto failed_mount9; return 0; failed_mount9: ext4_quotas_off(sb, EXT4_MAXQUOTAS); failed_mount8: __maybe_unused ext4_release_orphan_info(sb); failed_mount7: ext4_unregister_li_request(sb); failed_mount6: ext4_mb_release(sb); ext4_flex_groups_free(sbi); ext4_percpu_param_destroy(sbi); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); failed_mount4a: dput(sb->s_root); sb->s_root = NULL; failed_mount4: ext4_msg(sb, KERN_ERR, "mount failed"); if (EXT4_SB(sb)->rsv_conversion_wq) destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq); failed_mount_wq: ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); sbi->s_ea_inode_cache = NULL; ext4_xattr_destroy_cache(sbi->s_ea_block_cache); sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { /* flush s_sb_upd_work before journal destroy. */ flush_work(&sbi->s_sb_upd_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: /* flush s_sb_upd_work before sbi destroy */ flush_work(&sbi->s_sb_upd_work); del_timer_sync(&sbi->s_err_report); ext4_stop_mmpd(sbi); ext4_group_desc_free(sbi); failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif #ifdef CONFIG_QUOTA for (unsigned int i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); brelse(sbi->s_sbh); if (sbi->s_journal_bdev_file) { invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); bdev_fput(sbi->s_journal_bdev_file); } out_fail: invalidate_bdev(sb->s_bdev); sb->s_fs_info = NULL; return err; } static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi; const char *descr; int ret; sbi = ext4_alloc_sbi(sb); if (!sbi) return -ENOMEM; fc->s_fs_info = sbi; /* Cleanup superblock name */ strreplace(sb->s_id, '/', '!'); sbi->s_sb_block = 1; /* Default super block location */ if (ctx->spec & EXT4_SPEC_s_sb_block) sbi->s_sb_block = ctx->s_sb_block; ret = __ext4_fill_super(fc, sb); if (ret < 0) goto free_sbi; if (sbi->s_journal) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) descr = " journalled data mode"; else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) descr = " ordered data mode"; else descr = " writeback data mode"; } else descr = "out journal"; if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount")) ext4_msg(sb, KERN_INFO, "mounted filesystem %pU %s with%s. " "Quota mode: %s.", &sb->s_uuid, sb_rdonly(sb) ? "ro" : "r/w", descr, ext4_quota_mode(sb)); /* Update the s_overhead_clusters if necessary */ ext4_update_overhead(sb, false); return 0; free_sbi: ext4_free_sbi(sbi); fc->s_fs_info = NULL; return ret; } static int ext4_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, ext4_fill_super); } /* * Setup any per-fs journal parameters now. We'll do this both on * initial mount, once the journal has been initialised but before we've * done any recovery; and again on any subsequent remount. */ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal) { struct ext4_sb_info *sbi = EXT4_SB(sb); journal->j_commit_interval = sbi->s_commit_interval; journal->j_min_batch_time = sbi->s_min_batch_time; journal->j_max_batch_time = sbi->s_max_batch_time; ext4_fc_init(sb, journal); write_lock(&journal->j_state_lock); if (test_opt(sb, BARRIER)) journal->j_flags |= JBD2_BARRIER; else journal->j_flags &= ~JBD2_BARRIER; if (test_opt(sb, DATA_ERR_ABORT)) journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR; else journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR; /* * Always enable journal cycle record option, letting the journal * records log transactions continuously between each mount. */ journal->j_flags |= JBD2_CYCLE_RECORD; write_unlock(&journal->j_state_lock); } static struct inode *ext4_get_journal_inode(struct super_block *sb, unsigned int journal_inum) { struct inode *journal_inode; /* * Test for the existence of a valid inode on disk. Bad things * happen if we iget() an unused inode, as the subsequent iput() * will try to delete it. */ journal_inode = ext4_iget(sb, journal_inum, EXT4_IGET_SPECIAL); if (IS_ERR(journal_inode)) { ext4_msg(sb, KERN_ERR, "no journal found"); return ERR_CAST(journal_inode); } if (!journal_inode->i_nlink) { make_bad_inode(journal_inode); iput(journal_inode); ext4_msg(sb, KERN_ERR, "journal inode is deleted"); return ERR_PTR(-EFSCORRUPTED); } if (!S_ISREG(journal_inode->i_mode) || IS_ENCRYPTED(journal_inode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); return ERR_PTR(-EFSCORRUPTED); } ext4_debug("Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); return journal_inode; } static int ext4_journal_bmap(journal_t *journal, sector_t *block) { struct ext4_map_blocks map; int ret; if (journal->j_inode == NULL) return 0; map.m_lblk = *block; map.m_len = 1; ret = ext4_map_blocks(NULL, journal->j_inode, &map, 0); if (ret <= 0) { ext4_msg(journal->j_inode->i_sb, KERN_CRIT, "journal bmap failed: block %llu ret %d\n", *block, ret); jbd2_journal_abort(journal, ret ? ret : -EIO); return ret; } *block = map.m_pblk; return 0; } static journal_t *ext4_open_inode_journal(struct super_block *sb, unsigned int journal_inum) { struct inode *journal_inode; journal_t *journal; journal_inode = ext4_get_journal_inode(sb, journal_inum); if (IS_ERR(journal_inode)) return ERR_CAST(journal_inode); journal = jbd2_journal_init_inode(journal_inode); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "Could not load journal inode"); iput(journal_inode); return ERR_CAST(journal); } journal->j_private = sb; journal->j_bmap = ext4_journal_bmap; ext4_init_journal_params(sb, journal); return journal; } static struct file *ext4_get_journal_blkdev(struct super_block *sb, dev_t j_dev, ext4_fsblk_t *j_start, ext4_fsblk_t *j_len) { struct buffer_head *bh; struct block_device *bdev; struct file *bdev_file; int hblock, blocksize; ext4_fsblk_t sb_block; unsigned long offset; struct ext4_super_block *es; int errno; bdev_file = bdev_file_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES, sb, &fs_holder_ops); if (IS_ERR(bdev_file)) { ext4_msg(sb, KERN_ERR, "failed to open journal device unknown-block(%u,%u) %ld", MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_file)); return bdev_file; } bdev = file_bdev(bdev_file); blocksize = sb->s_blocksize; hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { ext4_msg(sb, KERN_ERR, "blocksize too small for journal device"); errno = -EINVAL; goto out_bdev; } sb_block = EXT4_MIN_BLOCK_SIZE / blocksize; offset = EXT4_MIN_BLOCK_SIZE % blocksize; set_blocksize(bdev_file, blocksize); bh = __bread(bdev, sb_block, blocksize); if (!bh) { ext4_msg(sb, KERN_ERR, "couldn't read superblock of " "external journal"); errno = -EINVAL; goto out_bdev; } es = (struct ext4_super_block *) (bh->b_data + offset); if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) { ext4_msg(sb, KERN_ERR, "external journal has bad superblock"); errno = -EFSCORRUPTED; goto out_bh; } if ((le32_to_cpu(es->s_feature_ro_compat) & EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && es->s_checksum != ext4_superblock_csum(sb, es)) { ext4_msg(sb, KERN_ERR, "external journal has corrupt superblock"); errno = -EFSCORRUPTED; goto out_bh; } if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) { ext4_msg(sb, KERN_ERR, "journal UUID does not match"); errno = -EFSCORRUPTED; goto out_bh; } *j_start = sb_block + 1; *j_len = ext4_blocks_count(es); brelse(bh); return bdev_file; out_bh: brelse(bh); out_bdev: bdev_fput(bdev_file); return ERR_PTR(errno); } static journal_t *ext4_open_dev_journal(struct super_block *sb, dev_t j_dev) { journal_t *journal; ext4_fsblk_t j_start; ext4_fsblk_t j_len; struct file *bdev_file; int errno = 0; bdev_file = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); if (IS_ERR(bdev_file)) return ERR_CAST(bdev_file); journal = jbd2_journal_init_dev(file_bdev(bdev_file), sb->s_bdev, j_start, j_len, sb->s_blocksize); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "failed to create device journal"); errno = PTR_ERR(journal); goto out_bdev; } if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) { ext4_msg(sb, KERN_ERR, "External journal has more than one " "user (unsupported) - %d", be32_to_cpu(journal->j_superblock->s_nr_users)); errno = -EINVAL; goto out_journal; } journal->j_private = sb; EXT4_SB(sb)->s_journal_bdev_file = bdev_file; ext4_init_journal_params(sb, journal); return journal; out_journal: jbd2_journal_destroy(journal); out_bdev: bdev_fput(bdev_file); return ERR_PTR(errno); } static int ext4_load_journal(struct super_block *sb, struct ext4_super_block *es, unsigned long journal_devnum) { journal_t *journal; unsigned int journal_inum = le32_to_cpu(es->s_journal_inum); dev_t journal_dev; int err = 0; int really_read_only; int journal_dev_ro; if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) return -EFSCORRUPTED; if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { ext4_msg(sb, KERN_INFO, "external journal device major/minor " "numbers have changed"); journal_dev = new_decode_dev(journal_devnum); } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); if (journal_inum && journal_dev) { ext4_msg(sb, KERN_ERR, "filesystem has both journal inode and journal device!"); return -EINVAL; } if (journal_inum) { journal = ext4_open_inode_journal(sb, journal_inum); if (IS_ERR(journal)) return PTR_ERR(journal); } else { journal = ext4_open_dev_journal(sb, journal_dev); if (IS_ERR(journal)) return PTR_ERR(journal); } journal_dev_ro = bdev_read_only(journal->j_dev); really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro; if (journal_dev_ro && !sb_rdonly(sb)) { ext4_msg(sb, KERN_ERR, "journal device read-only, try mounting with '-o ro'"); err = -EROFS; goto err_out; } /* * Are we loading a blank journal or performing recovery after a * crash? For recovery, we need to check in advance whether we * can get read-write access to the device. */ if (ext4_has_feature_journal_needs_recovery(sb)) { if (sb_rdonly(sb)) { ext4_msg(sb, KERN_INFO, "INFO: recovery " "required on readonly filesystem"); if (really_read_only) { ext4_msg(sb, KERN_ERR, "write access " "unavailable, cannot proceed " "(try mounting with noload)"); err = -EROFS; goto err_out; } ext4_msg(sb, KERN_INFO, "write access will " "be enabled during recovery"); } } if (!(journal->j_flags & JBD2_BARRIER)) ext4_msg(sb, KERN_INFO, "barriers disabled"); if (!ext4_has_feature_journal_needs_recovery(sb)) err = jbd2_journal_wipe(journal, !really_read_only); if (!err) { char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL); __le16 orig_state; bool changed = false; if (save) memcpy(save, ((char *) es) + EXT4_S_ERR_START, EXT4_S_ERR_LEN); err = jbd2_journal_load(journal); if (save && memcmp(((char *) es) + EXT4_S_ERR_START, save, EXT4_S_ERR_LEN)) { memcpy(((char *) es) + EXT4_S_ERR_START, save, EXT4_S_ERR_LEN); changed = true; } kfree(save); orig_state = es->s_state; es->s_state |= cpu_to_le16(EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS); if (orig_state != es->s_state) changed = true; /* Write out restored error information to the superblock */ if (changed && !really_read_only) { int err2; err2 = ext4_commit_super(sb); err = err ? : err2; } } if (err) { ext4_msg(sb, KERN_ERR, "error loading journal"); goto err_out; } EXT4_SB(sb)->s_journal = journal; err = ext4_clear_journal_err(sb, es); if (err) { EXT4_SB(sb)->s_journal = NULL; jbd2_journal_destroy(journal); return err; } if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { es->s_journal_dev = cpu_to_le32(journal_devnum); ext4_commit_super(sb); } if (!really_read_only && journal_inum && journal_inum != le32_to_cpu(es->s_journal_inum)) { es->s_journal_inum = cpu_to_le32(journal_inum); ext4_commit_super(sb); } return 0; err_out: jbd2_journal_destroy(journal); return err; } /* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */ static void ext4_update_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct buffer_head *sbh = sbi->s_sbh; lock_buffer(sbh); /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock * write time when we are mounting the root file system * read/only but we need to replay the journal; at that point, * for people who are east of GMT and who make their clock * tick in localtime for Windows bug-for-bug compatibility, * the clock is set in the future, and this will cause e2fsck * to complain and force a full file system check. */ if (!sb_rdonly(sb)) ext4_update_tstamp(es, s_wtime); es->s_kbytes_written = cpu_to_le64(sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1)); if (percpu_counter_initialized(&sbi->s_freeclusters_counter)) ext4_free_blocks_count_set(es, EXT4_C2B(sbi, percpu_counter_sum_positive( &sbi->s_freeclusters_counter))); if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( &sbi->s_freeinodes_counter)); /* Copy error information to the on-disk superblock */ spin_lock(&sbi->s_error_lock); if (sbi->s_add_error_count > 0) { es->s_state |= cpu_to_le16(EXT4_ERROR_FS); if (!es->s_first_error_time && !es->s_first_error_time_hi) { __ext4_update_tstamp(&es->s_first_error_time, &es->s_first_error_time_hi, sbi->s_first_error_time); strtomem_pad(es->s_first_error_func, sbi->s_first_error_func, 0); es->s_first_error_line = cpu_to_le32(sbi->s_first_error_line); es->s_first_error_ino = cpu_to_le32(sbi->s_first_error_ino); es->s_first_error_block = cpu_to_le64(sbi->s_first_error_block); es->s_first_error_errcode = ext4_errno_to_code(sbi->s_first_error_code); } __ext4_update_tstamp(&es->s_last_error_time, &es->s_last_error_time_hi, sbi->s_last_error_time); strtomem_pad(es->s_last_error_func, sbi->s_last_error_func, 0); es->s_last_error_line = cpu_to_le32(sbi->s_last_error_line); es->s_last_error_ino = cpu_to_le32(sbi->s_last_error_ino); es->s_last_error_block = cpu_to_le64(sbi->s_last_error_block); es->s_last_error_errcode = ext4_errno_to_code(sbi->s_last_error_code); /* * Start the daily error reporting function if it hasn't been * started already */ if (!es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); le32_add_cpu(&es->s_error_count, sbi->s_add_error_count); sbi->s_add_error_count = 0; } spin_unlock(&sbi->s_error_lock); ext4_superblock_csum_set(sb); unlock_buffer(sbh); } static int ext4_commit_super(struct super_block *sb) { struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; if (!sbh) return -EINVAL; ext4_update_super(sb); lock_buffer(sbh); /* Buffer got discarded which means block device got invalidated */ if (!buffer_mapped(sbh)) { unlock_buffer(sbh); return -EIO; } if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the * superblock failed. This could happen because the * USB device was yanked out. Or it could happen to * be a transient write error and maybe the block will * be remapped. Nothing we can do but to retry the * write and hope for the best. */ ext4_msg(sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } get_bh(sbh); /* Clear potential dirty bit if it was journalled update */ clear_buffer_dirty(sbh); sbh->b_end_io = end_buffer_write_sync; submit_bh(REQ_OP_WRITE | REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0), sbh); wait_on_buffer(sbh); if (buffer_write_io_error(sbh)) { ext4_msg(sb, KERN_ERR, "I/O error while writing " "superblock"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); return -EIO; } return 0; } /* * Have we just finished recovery? If so, and if we are mounting (or * remounting) the filesystem readonly, then we will end up with a * consistent fs on disk. Record that fact. */ static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es) { int err; journal_t *journal = EXT4_SB(sb)->s_journal; if (!ext4_has_feature_journal(sb)) { if (journal != NULL) { ext4_error(sb, "Journal got removed while the fs was " "mounted!"); return -EFSCORRUPTED; } return 0; } jbd2_journal_lock_updates(journal); err = jbd2_journal_flush(journal, 0); if (err < 0) goto out; if (sb_rdonly(sb) && (ext4_has_feature_journal_needs_recovery(sb) || ext4_has_feature_orphan_present(sb))) { if (!ext4_orphan_file_empty(sb)) { ext4_error(sb, "Orphan file not empty on read-only fs."); err = -EFSCORRUPTED; goto out; } ext4_clear_feature_journal_needs_recovery(sb); ext4_clear_feature_orphan_present(sb); ext4_commit_super(sb); } out: jbd2_journal_unlock_updates(journal); return err; } /* * If we are mounting (or read-write remounting) a filesystem whose journal * has recorded an error from a previous lifetime, move that error to the * main filesystem now. */ static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es) { journal_t *journal; int j_errno; const char *errstr; if (!ext4_has_feature_journal(sb)) { ext4_error(sb, "Journal got removed while the fs was mounted!"); return -EFSCORRUPTED; } journal = EXT4_SB(sb)->s_journal; /* * Now check for any error status which may have been recorded in the * journal by a prior ext4_error() or ext4_abort() */ j_errno = jbd2_journal_errno(journal); if (j_errno) { char nbuf[16]; errstr = ext4_decode_error(sb, j_errno, nbuf); ext4_warning(sb, "Filesystem error recorded " "from previous mount: %s", errstr); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); j_errno = ext4_commit_super(sb); if (j_errno) return j_errno; ext4_warning(sb, "Marked fs in need of filesystem check."); jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); } return 0; } /* * Force the running and committing transactions to commit, * and wait on the commit. */ int ext4_force_commit(struct super_block *sb) { return ext4_journal_force_commit(EXT4_SB(sb)->s_journal); } static int ext4_sync_fs(struct super_block *sb, int wait) { int ret = 0; tid_t target; bool needs_barrier = false; struct ext4_sb_info *sbi = EXT4_SB(sb); if (unlikely(ext4_forced_shutdown(sb))) return 0; trace_ext4_sync_fs(sb, wait); flush_workqueue(sbi->rsv_conversion_wq); /* * Writeback quota in non-journalled quota case - journalled quota has * no dirty dquots */ dquot_writeback_dquots(sb, -1); /* * Data writeback is possible w/o journal transaction, so barrier must * being sent at the end of the function. But we can skip it if * transaction_commit will do it for us. */ if (sbi->s_journal) { target = jbd2_get_latest_transaction(sbi->s_journal); if (wait && sbi->s_journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(sbi->s_journal, target)) needs_barrier = true; if (jbd2_journal_start_commit(sbi->s_journal, &target)) { if (wait) ret = jbd2_log_wait_commit(sbi->s_journal, target); } } else if (wait && test_opt(sb, BARRIER)) needs_barrier = true; if (needs_barrier) { int err; err = blkdev_issue_flush(sb->s_bdev); if (!ret) ret = err; } return ret; } /* * LVM calls this function before a (read-only) snapshot is created. This * gives us a chance to flush the journal completely and mark the fs clean. * * Note that only this function cannot bring a filesystem to be in a clean * state independently. It relies on upper layer to stop all data & metadata * modifications. */ static int ext4_freeze(struct super_block *sb) { int error = 0; journal_t *journal = EXT4_SB(sb)->s_journal; if (journal) { /* Now we set up the journal barrier. */ jbd2_journal_lock_updates(journal); /* * Don't clear the needs_recovery flag if we failed to * flush the journal. */ error = jbd2_journal_flush(journal, 0); if (error < 0) goto out; /* Journal blocked and flushed, clear needs_recovery flag. */ ext4_clear_feature_journal_needs_recovery(sb); if (ext4_orphan_file_empty(sb)) ext4_clear_feature_orphan_present(sb); } error = ext4_commit_super(sb); out: if (journal) /* we rely on upper layer to stop further updates */ jbd2_journal_unlock_updates(journal); return error; } /* * Called by LVM after the snapshot is done. We need to reset the RECOVER * flag here, even though the filesystem is not technically dirty yet. */ static int ext4_unfreeze(struct super_block *sb) { if (ext4_forced_shutdown(sb)) return 0; if (EXT4_SB(sb)->s_journal) { /* Reset the needs_recovery flag before the fs is unlocked. */ ext4_set_feature_journal_needs_recovery(sb); if (ext4_has_feature_orphan_file(sb)) ext4_set_feature_orphan_present(sb); } ext4_commit_super(sb); return 0; } /* * Structure to save mount options for ext4_remount's benefit */ struct ext4_mount_options { unsigned long s_mount_opt; unsigned long s_mount_opt2; kuid_t s_resuid; kgid_t s_resgid; unsigned long s_commit_interval; u32 s_min_batch_time, s_max_batch_time; #ifdef CONFIG_QUOTA int s_jquota_fmt; char *s_qf_names[EXT4_MAXQUOTAS]; #endif }; static int __ext4_remount(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_super_block *es; struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long old_sb_flags; struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; int alloc_ctx; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; char *to_free[EXT4_MAXQUOTAS]; #endif /* Store the original options */ old_sb_flags = sb->s_flags; old_opts.s_mount_opt = sbi->s_mount_opt; old_opts.s_mount_opt2 = sbi->s_mount_opt2; old_opts.s_resuid = sbi->s_resuid; old_opts.s_resgid = sbi->s_resgid; old_opts.s_commit_interval = sbi->s_commit_interval; old_opts.s_min_batch_time = sbi->s_min_batch_time; old_opts.s_max_batch_time = sbi->s_max_batch_time; #ifdef CONFIG_QUOTA old_opts.s_jquota_fmt = sbi->s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) if (sbi->s_qf_names[i]) { char *qf_name = get_qf_name(sb, sbi, i); old_opts.s_qf_names[i] = kstrdup(qf_name, GFP_KERNEL); if (!old_opts.s_qf_names[i]) { for (j = 0; j < i; j++) kfree(old_opts.s_qf_names[j]); return -ENOMEM; } } else old_opts.s_qf_names[i] = NULL; #endif if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) { if (sbi->s_journal && sbi->s_journal->j_task->io_context) ctx->journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; else ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; } /* * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause * two calls to ext4_should_dioread_nolock() to return inconsistent * values, triggering WARN_ON in ext4_add_complete_io(). we grab * here s_writepages_rwsem to avoid race between writepages ops and * remount. */ alloc_ctx = ext4_writepages_down_write(sb); ext4_apply_options(fc, sb); ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " "during remount not supported; ignoring"); sbi->s_mount_opt ^= EXT4_MOUNT_JOURNAL_CHECKSUM; } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); err = -EINVAL; goto restore_opts; } if (test_opt(sb, DIOREAD_NOLOCK)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and dioread_nolock"); err = -EINVAL; goto restore_opts; } } else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) { if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit in data=ordered mode"); err = -EINVAL; goto restore_opts; } } if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_NO_MBCACHE) { ext4_msg(sb, KERN_ERR, "can't enable nombcache during remount"); err = -EINVAL; goto restore_opts; } if (test_opt2(sb, ABORT)) ext4_abort(sb, ESHUTDOWN, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); es = sbi->s_es; if (sbi->s_journal) { ext4_init_journal_params(sb, sbi->s_journal); set_task_ioprio(sbi->s_journal->j_task, ctx->journal_ioprio); } /* Flush outstanding errors before changing fs state */ flush_work(&sbi->s_sb_upd_work); if ((bool)(fc->sb_flags & SB_RDONLY) != sb_rdonly(sb)) { if (ext4_forced_shutdown(sb)) { err = -EROFS; goto restore_opts; } if (fc->sb_flags & SB_RDONLY) { err = sync_filesystem(sb); if (err < 0) goto restore_opts; err = dquot_suspend(sb, -1); if (err < 0) goto restore_opts; /* * First of all, the unconditional stuff we have to do * to disable replay of the journal when we next remount */ sb->s_flags |= SB_RDONLY; /* * OK, test if we are remounting a valid rw partition * readonly, and if so set the rdonly flag and then * mark the partition as valid again. */ if (!(es->s_state & cpu_to_le16(EXT4_VALID_FS)) && (sbi->s_mount_state & EXT4_VALID_FS)) es->s_state = cpu_to_le16(sbi->s_mount_state); if (sbi->s_journal) { /* * We let remount-ro finish even if marking fs * as clean failed... */ ext4_mark_recovery_complete(sb, es); } } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || !ext4_feature_set_ok(sb, 0)) { err = -EROFS; goto restore_opts; } /* * Make sure the group descriptor checksums * are sane. If they aren't, refuse to remount r/w. */ for (g = 0; g < sbi->s_groups_count; g++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, g, NULL); if (!ext4_group_desc_csum_verify(sb, g, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_remount: Checksum for group %u failed (%u!=%u)", g, le16_to_cpu(ext4_group_desc_csum(sb, g, gdp)), le16_to_cpu(gdp->bg_checksum)); err = -EFSBADCRC; goto restore_opts; } } /* * If we have an unprocessed orphan list hanging * around from a previously readonly bdev mount, * require a full umount/remount for now. */ if (es->s_last_orphan || !ext4_orphan_file_empty(sb)) { ext4_msg(sb, KERN_WARNING, "Couldn't " "remount RDWR because of unprocessed " "orphan inode list. Please " "umount/remount instead"); err = -EINVAL; goto restore_opts; } /* * Mounting a RDONLY partition read-write, so reread * and store the current valid flag. (It may have * been changed by e2fsck since we originally mounted * the partition.) */ if (sbi->s_journal) { err = ext4_clear_journal_err(sb, es); if (err) goto restore_opts; } sbi->s_mount_state = (le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY); err = ext4_setup_super(sb, es, 0); if (err) goto restore_opts; sb->s_flags &= ~SB_RDONLY; if (ext4_has_feature_mmp(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); if (err) goto restore_opts; } #ifdef CONFIG_QUOTA enable_quota = 1; #endif } } /* * Handle creation of system zone data early because it can fail. * Releasing of existing data is done when we are sure remount will * succeed. */ if (test_opt(sb, BLOCK_VALIDITY) && !sbi->s_system_blks) { err = ext4_setup_system_zone(sb); if (err) goto restore_opts; } if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { err = ext4_commit_super(sb); if (err) goto restore_opts; } #ifdef CONFIG_QUOTA if (enable_quota) { if (sb_any_quota_suspended(sb)) dquot_resume(sb, -1); else if (ext4_has_feature_quota(sb)) { err = ext4_enable_quotas(sb); if (err) goto restore_opts; } } /* Release old quota file names */ for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(old_opts.s_qf_names[i]); #endif if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); /* * Reinitialize lazy itable initialization thread based on * current settings */ if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) ext4_unregister_li_request(sb); else { ext4_group_t first_not_zeroed; first_not_zeroed = ext4_has_uninit_itable(sb); ext4_register_li_request(sb, first_not_zeroed); } if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); return 0; restore_opts: /* * If there was a failing r/w to ro transition, we may need to * re-enable quota */ if (sb_rdonly(sb) && !(old_sb_flags & SB_RDONLY) && sb_any_quota_suspended(sb)) dquot_resume(sb, -1); alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; sbi->s_resuid = old_opts.s_resuid; sbi->s_resgid = old_opts.s_resgid; sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; ext4_writepages_up_write(sb, alloc_ctx); if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { to_free[i] = get_qf_name(sb, sbi, i); rcu_assign_pointer(sbi->s_qf_names[i], old_opts.s_qf_names[i]); } synchronize_rcu(); for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(to_free[i]); #endif if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); return err; } static int ext4_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; int ret; fc->s_fs_info = EXT4_SB(sb); ret = ext4_check_opt_consistency(fc, sb); if (ret < 0) return ret; ret = __ext4_remount(fc, sb); if (ret < 0) return ret; ext4_msg(sb, KERN_INFO, "re-mounted %pU %s. Quota mode: %s.", &sb->s_uuid, sb_rdonly(sb) ? "ro" : "r/w", ext4_quota_mode(sb)); return 0; } #ifdef CONFIG_QUOTA static int ext4_statfs_project(struct super_block *sb, kprojid_t projid, struct kstatfs *buf) { struct kqid qid; struct dquot *dquot; u64 limit; u64 curblock; qid = make_kqid_projid(projid); dquot = dqget(sb, qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); spin_lock(&dquot->dq_dqb_lock); limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit, dquot->dq_dqb.dqb_bhardlimit); limit >>= sb->s_blocksize_bits; if (limit && buf->f_blocks > limit) { curblock = (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; buf->f_blocks = limit; buf->f_bfree = buf->f_bavail = (buf->f_blocks > curblock) ? (buf->f_blocks - curblock) : 0; } limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit, dquot->dq_dqb.dqb_ihardlimit); if (limit && buf->f_files > limit) { buf->f_files = limit; buf->f_ffree = (buf->f_files > dquot->dq_dqb.dqb_curinodes) ? (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0; } spin_unlock(&dquot->dq_dqb_lock); dqput(dquot); return 0; } #endif static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; ext4_fsblk_t overhead = 0, resv_blocks; s64 bfree; resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters)); if (!test_opt(sb, MINIX_DF)) overhead = sbi->s_overhead; buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, overhead); bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) - percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0)); buf->f_bavail = buf->f_bfree - (ext4_r_blocks_count(es) + resv_blocks); if (buf->f_bfree < (ext4_r_blocks_count(es) + resv_blocks)) buf->f_bavail = 0; buf->f_files = le32_to_cpu(es->s_inodes_count); buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter); buf->f_namelen = EXT4_NAME_LEN; buf->f_fsid = uuid_to_fsid(es->s_uuid); #ifdef CONFIG_QUOTA if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) && sb_has_quota_limits_enabled(sb, PRJQUOTA)) ext4_statfs_project(sb, EXT4_I(dentry->d_inode)->i_projid, buf); #endif return 0; } #ifdef CONFIG_QUOTA /* * Helper functions so that transaction is started before we acquire dqio_sem * to keep correct lock ordering of transaction > dqio_sem */ static inline struct inode *dquot_to_inode(struct dquot *dquot) { return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type]; } static int ext4_write_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; struct inode *inode; inode = dquot_to_inode(dquot); handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to commit dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static int ext4_acquire_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to acquire dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static int ext4_release_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA, EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); return PTR_ERR(handle); } ret = dquot_release(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to release dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static int ext4_mark_dquot_dirty(struct dquot *dquot) { struct super_block *sb = dquot->dq_sb; if (ext4_is_quota_journalled(sb)) { dquot_mark_dquot_dirty(dquot); return ext4_write_dquot(dquot); } else { return dquot_mark_dquot_dirty(dquot); } } static int ext4_write_info(struct super_block *sb, int type) { int ret, err; handle_t *handle; /* Data block + inode block */ handle = ext4_journal_start_sb(sb, EXT4_HT_QUOTA, 2); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit_info(sb, type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static void lockdep_set_quota_inode(struct inode *inode, int subclass) { struct ext4_inode_info *ei = EXT4_I(inode); /* The first argument of lockdep_set_subclass has to be * *exactly* the same as the argument to init_rwsem() --- in * this case, in init_once() --- or lockdep gets unhappy * because the name of the lock is set using the * stringification of the argument to init_rwsem(). */ (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ lockdep_set_subclass(&ei->i_data_sem, subclass); } /* * Standard function to be called on quota_on */ static int ext4_quota_on(struct super_block *sb, int type, int format_id, const struct path *path) { int err; if (!test_opt(sb, QUOTA)) return -EINVAL; /* Quotafile not on the same filesystem? */ if (path->dentry->d_sb != sb) return -EXDEV; /* Quota already enabled for this file? */ if (IS_NOQUOTA(d_inode(path->dentry))) return -EBUSY; /* Journaling quota? */ if (EXT4_SB(sb)->s_qf_names[type]) { /* Quotafile not in fs root? */ if (path->dentry->d_parent != sb->s_root) ext4_msg(sb, KERN_WARNING, "Quota file not on filesystem root. " "Journaled quota will not work"); sb_dqopt(sb)->flags |= DQUOT_NOLIST_DIRTY; } else { /* * Clear the flag just in case mount options changed since * last time. */ sb_dqopt(sb)->flags &= ~DQUOT_NOLIST_DIRTY; } lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA); err = dquot_quota_on(sb, type, format_id, path); if (!err) { struct inode *inode = d_inode(path->dentry); handle_t *handle; /* * Set inode flags to prevent userspace from messing with quota * files. If this fails, we return success anyway since quotas * are already enabled and this is not a hard failure. */ inode_lock(inode); handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1); if (IS_ERR(handle)) goto unlock_inode; EXT4_I(inode)->i_flags |= EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL; inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, S_NOATIME | S_IMMUTABLE); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); unlock_inode: inode_unlock(inode); if (err) dquot_quota_off(sb, type); } if (err) lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_NORMAL); return err; } static inline bool ext4_check_quota_inum(int type, unsigned long qf_inum) { switch (type) { case USRQUOTA: return qf_inum == EXT4_USR_QUOTA_INO; case GRPQUOTA: return qf_inum == EXT4_GRP_QUOTA_INO; case PRJQUOTA: return qf_inum >= EXT4_GOOD_OLD_FIRST_INO; default: BUG(); } } static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags) { int err; struct inode *qf_inode; unsigned long qf_inums[EXT4_MAXQUOTAS] = { le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum) }; BUG_ON(!ext4_has_feature_quota(sb)); if (!qf_inums[type]) return -EPERM; if (!ext4_check_quota_inum(type, qf_inums[type])) { ext4_error(sb, "Bad quota inum: %lu, type: %d", qf_inums[type], type); return -EUCLEAN; } qf_inode = ext4_iget(sb, qf_inums[type], EXT4_IGET_SPECIAL); if (IS_ERR(qf_inode)) { ext4_error(sb, "Bad quota inode: %lu, type: %d", qf_inums[type], type); return PTR_ERR(qf_inode); } /* Don't account quota for quota files to avoid recursion */ qf_inode->i_flags |= S_NOQUOTA; lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA); err = dquot_load_quota_inode(qf_inode, type, format_id, flags); if (err) lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL); iput(qf_inode); return err; } /* Enable usage tracking for all quota types. */ int ext4_enable_quotas(struct super_block *sb) { int type, err = 0; unsigned long qf_inums[EXT4_MAXQUOTAS] = { le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum) }; bool quota_mopt[EXT4_MAXQUOTAS] = { test_opt(sb, USRQUOTA), test_opt(sb, GRPQUOTA), test_opt(sb, PRJQUOTA), }; sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY; for (type = 0; type < EXT4_MAXQUOTAS; type++) { if (qf_inums[type]) { err = ext4_quota_enable(sb, type, QFMT_VFS_V1, DQUOT_USAGE_ENABLED | (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0)); if (err) { ext4_warning(sb, "Failed to enable quota tracking " "(type=%d, err=%d, ino=%lu). " "Please run e2fsck to fix.", type, err, qf_inums[type]); ext4_quotas_off(sb, type); return err; } } } return 0; } static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; handle_t *handle; int err; /* Force all delayed allocation blocks to be allocated. * Caller already holds s_umount sem */ if (test_opt(sb, DELALLOC)) sync_filesystem(sb); if (!inode || !igrab(inode)) goto out; err = dquot_quota_off(sb, type); if (err || ext4_has_feature_quota(sb)) goto out_put; /* * When the filesystem was remounted read-only first, we cannot cleanup * inode flags here. Bad luck but people should be using QUOTA feature * these days anyway. */ if (sb_rdonly(sb)) goto out_put; inode_lock(inode); /* * Update modification times of quota files when userspace can * start looking at them. If we fail, we return success anyway since * this is not a hard failure and quotas are already disabled. */ handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto out_unlock; } EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL); inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); out_unlock: inode_unlock(inode); out_put: lockdep_set_quota_inode(inode, I_DATA_SEM_NORMAL); iput(inode); return err; out: return dquot_quota_off(sb, type); } /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) * we don't have to be afraid of races */ static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); int offset = off & (sb->s_blocksize - 1); int tocopy; size_t toread; struct buffer_head *bh; loff_t i_size = i_size_read(inode); if (off > i_size) return 0; if (off+len > i_size) len = i_size-off; toread = len; while (toread > 0) { tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread); bh = ext4_bread(NULL, inode, blk, 0); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) /* A hole? */ memset(data, 0, tocopy); else memcpy(data, bh->b_data+offset, tocopy); brelse(bh); offset = 0; toread -= tocopy; data += tocopy; blk++; } return len; } /* Write to quotafile (we know the transaction is already started and has * enough credits) */ static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); int err = 0, err2 = 0, offset = off & (sb->s_blocksize - 1); int retries = 0; struct buffer_head *bh; handle_t *handle = journal_current_handle(); if (!handle) { ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" " cancelled because transaction is not started", (unsigned long long)off, (unsigned long long)len); return -EIO; } /* * Since we account only one data block in transaction credits, * then it is impossible to cross a block boundary. */ if (sb->s_blocksize - offset < len) { ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" " cancelled because not block aligned", (unsigned long long)off, (unsigned long long)len); return -EIO; } do { bh = ext4_bread(handle, inode, blk, EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL); } while (PTR_ERR(bh) == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) goto out; BUFFER_TRACE(bh, "get write access"); err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); if (err) { brelse(bh); return err; } lock_buffer(bh); memcpy(bh->b_data+offset, data, len); flush_dcache_page(bh->b_page); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, NULL, bh); brelse(bh); out: if (inode->i_size < off + len) { i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; err2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(err2 && !err)) err = err2; } return err ? err : len; } #endif #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static inline void register_as_ext2(void) { int err = register_filesystem(&ext2_fs_type); if (err) printk(KERN_WARNING "EXT4-fs: Unable to register as ext2 (%d)\n", err); } static inline void unregister_as_ext2(void) { unregister_filesystem(&ext2_fs_type); } static inline int ext2_feature_set_ok(struct super_block *sb) { if (ext4_has_unknown_ext2_incompat_features(sb)) return 0; if (sb_rdonly(sb)) return 1; if (ext4_has_unknown_ext2_ro_compat_features(sb)) return 0; return 1; } #else static inline void register_as_ext2(void) { } static inline void unregister_as_ext2(void) { } static inline int ext2_feature_set_ok(struct super_block *sb) { return 0; } #endif static inline void register_as_ext3(void) { int err = register_filesystem(&ext3_fs_type); if (err) printk(KERN_WARNING "EXT4-fs: Unable to register as ext3 (%d)\n", err); } static inline void unregister_as_ext3(void) { unregister_filesystem(&ext3_fs_type); } static inline int ext3_feature_set_ok(struct super_block *sb) { if (ext4_has_unknown_ext3_incompat_features(sb)) return 0; if (!ext4_has_feature_journal(sb)) return 0; if (sb_rdonly(sb)) return 1; if (ext4_has_unknown_ext3_ro_compat_features(sb)) return 0; return 1; } static void ext4_kill_sb(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct file *bdev_file = sbi ? sbi->s_journal_bdev_file : NULL; kill_block_super(sb); if (bdev_file) bdev_fput(bdev_file); } static struct file_system_type ext4_fs_type = { .owner = THIS_MODULE, .name = "ext4", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("ext4"); /* Shared across all ext4 file systems */ wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; static int __init ext4_init_fs(void) { int i, err; ratelimit_state_init(&ext4_mount_msg_ratelimit, 30 * HZ, 64); ext4_li_info = NULL; /* Build-time check for flags consistency */ ext4_check_flag_values(); for (i = 0; i < EXT4_WQ_HASH_SZ; i++) init_waitqueue_head(&ext4__ioend_wq[i]); err = ext4_init_es(); if (err) return err; err = ext4_init_pending(); if (err) goto out7; err = ext4_init_post_read_processing(); if (err) goto out6; err = ext4_init_pageio(); if (err) goto out5; err = ext4_init_system_zone(); if (err) goto out4; err = ext4_init_sysfs(); if (err) goto out3; err = ext4_init_mballoc(); if (err) goto out2; err = init_inodecache(); if (err) goto out1; err = ext4_fc_init_dentry_cache(); if (err) goto out05; register_as_ext3(); register_as_ext2(); err = register_filesystem(&ext4_fs_type); if (err) goto out; return 0; out: unregister_as_ext2(); unregister_as_ext3(); ext4_fc_destroy_dentry_cache(); out05: destroy_inodecache(); out1: ext4_exit_mballoc(); out2: ext4_exit_sysfs(); out3: ext4_exit_system_zone(); out4: ext4_exit_pageio(); out5: ext4_exit_post_read_processing(); out6: ext4_exit_pending(); out7: ext4_exit_es(); return err; } static void __exit ext4_exit_fs(void) { ext4_destroy_lazyinit_thread(); unregister_as_ext2(); unregister_as_ext3(); unregister_filesystem(&ext4_fs_type); ext4_fc_destroy_dentry_cache(); destroy_inodecache(); ext4_exit_mballoc(); ext4_exit_sysfs(); ext4_exit_system_zone(); ext4_exit_pageio(); ext4_exit_post_read_processing(); ext4_exit_es(); ext4_exit_pending(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); MODULE_DESCRIPTION("Fourth Extended Filesystem"); MODULE_LICENSE("GPL"); MODULE_SOFTDEP("pre: crc32c"); module_init(ext4_init_fs) module_exit(ext4_exit_fs) |
| 46 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 | // SPDX-License-Identifier: GPL-2.0-or-later /* Sysfs attributes of bond slaves * * Copyright (c) 2014 Scott Feldman <sfeldma@cumulusnetworks.com> */ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <net/bonding.h> struct slave_attribute { struct attribute attr; ssize_t (*show)(struct slave *, char *); }; #define SLAVE_ATTR_RO(_name) \ const struct slave_attribute slave_attr_##_name = __ATTR_RO(_name) static ssize_t state_show(struct slave *slave, char *buf) { switch (bond_slave_state(slave)) { case BOND_STATE_ACTIVE: return sysfs_emit(buf, "active\n"); case BOND_STATE_BACKUP: return sysfs_emit(buf, "backup\n"); default: return sysfs_emit(buf, "UNKNOWN\n"); } } static SLAVE_ATTR_RO(state); static ssize_t mii_status_show(struct slave *slave, char *buf) { return sysfs_emit(buf, "%s\n", bond_slave_link_status(slave->link)); } static SLAVE_ATTR_RO(mii_status); static ssize_t link_failure_count_show(struct slave *slave, char *buf) { return sysfs_emit(buf, "%d\n", slave->link_failure_count); } static SLAVE_ATTR_RO(link_failure_count); static ssize_t perm_hwaddr_show(struct slave *slave, char *buf) { return sysfs_emit(buf, "%*phC\n", slave->dev->addr_len, slave->perm_hwaddr); } static SLAVE_ATTR_RO(perm_hwaddr); static ssize_t queue_id_show(struct slave *slave, char *buf) { return sysfs_emit(buf, "%d\n", READ_ONCE(slave->queue_id)); } static SLAVE_ATTR_RO(queue_id); static ssize_t ad_aggregator_id_show(struct slave *slave, char *buf) { const struct aggregator *agg; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { agg = SLAVE_AD_INFO(slave)->port.aggregator; if (agg) return sysfs_emit(buf, "%d\n", agg->aggregator_identifier); } return sysfs_emit(buf, "N/A\n"); } static SLAVE_ATTR_RO(ad_aggregator_id); static ssize_t ad_actor_oper_port_state_show(struct slave *slave, char *buf) { const struct port *ad_port; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; if (ad_port->aggregator) return sysfs_emit(buf, "%u\n", ad_port->actor_oper_port_state); } return sysfs_emit(buf, "N/A\n"); } static SLAVE_ATTR_RO(ad_actor_oper_port_state); static ssize_t ad_partner_oper_port_state_show(struct slave *slave, char *buf) { const struct port *ad_port; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; if (ad_port->aggregator) return sysfs_emit(buf, "%u\n", ad_port->partner_oper.port_state); } return sysfs_emit(buf, "N/A\n"); } static SLAVE_ATTR_RO(ad_partner_oper_port_state); static const struct attribute *slave_attrs[] = { &slave_attr_state.attr, &slave_attr_mii_status.attr, &slave_attr_link_failure_count.attr, &slave_attr_perm_hwaddr.attr, &slave_attr_queue_id.attr, &slave_attr_ad_aggregator_id.attr, &slave_attr_ad_actor_oper_port_state.attr, &slave_attr_ad_partner_oper_port_state.attr, NULL }; #define to_slave_attr(_at) container_of(_at, struct slave_attribute, attr) static ssize_t slave_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct slave_attribute *slave_attr = to_slave_attr(attr); struct slave *slave = to_slave(kobj); return slave_attr->show(slave, buf); } const struct sysfs_ops slave_sysfs_ops = { .show = slave_show, }; int bond_sysfs_slave_add(struct slave *slave) { return sysfs_create_files(&slave->kobj, slave_attrs); } void bond_sysfs_slave_del(struct slave *slave) { sysfs_remove_files(&slave->kobj, slave_attrs); } |
| 18 11 2 7 2 1 5 86 79 8 7 6 87 84 2 8 2 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SR-IPv6 implementation * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/slab.h> #include <linux/rhashtable.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/seg6.h> #include <net/genetlink.h> #include <linux/seg6.h> #include <linux/seg6_genl.h> #include <net/seg6_hmac.h> bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced) { unsigned int tlv_offset; int max_last_entry; int trailing; if (srh->type != IPV6_SRCRT_TYPE_4) return false; if (((srh->hdrlen + 1) << 3) != len) return false; if (!reduced && srh->segments_left > srh->first_segment) { return false; } else { max_last_entry = (srh->hdrlen / 2) - 1; if (srh->first_segment > max_last_entry) return false; if (srh->segments_left > srh->first_segment + 1) return false; } tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4); trailing = len - tlv_offset; if (trailing < 0) return false; while (trailing) { struct sr6_tlv *tlv; unsigned int tlv_len; if (trailing < sizeof(*tlv)) return false; tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset); tlv_len = sizeof(*tlv) + tlv->len; trailing -= tlv_len; if (trailing < 0) return false; tlv_offset += tlv_len; } return true; } struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags) { struct ipv6_sr_hdr *srh; int len, srhoff = 0; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, &flags) < 0) return NULL; if (!pskb_may_pull(skb, srhoff + sizeof(*srh))) return NULL; srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); len = (srh->hdrlen + 1) << 3; if (!pskb_may_pull(skb, srhoff + len)) return NULL; /* note that pskb_may_pull may change pointers in header; * for this reason it is necessary to reload them when needed. */ srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); if (!seg6_validate_srh(srh, len, true)) return NULL; return srh; } /* Determine if an ICMP invoking packet contains a segment routing * header. If it does, extract the offset to the true destination * address, which is in the first segment address. */ void seg6_icmp_srh(struct sk_buff *skb, struct inet6_skb_parm *opt) { __u16 network_header = skb->network_header; struct ipv6_sr_hdr *srh; /* Update network header to point to the invoking packet * inside the ICMP packet, so we can use the seg6_get_srh() * helper. */ skb_reset_network_header(skb); srh = seg6_get_srh(skb, 0); if (!srh) goto out; if (srh->type != IPV6_SRCRT_TYPE_4) goto out; opt->flags |= IP6SKB_SEG6; opt->srhoff = (unsigned char *)srh - skb->data; out: /* Restore the network header back to the ICMP packet */ skb->network_header = network_header; } static struct genl_family seg6_genl_family; static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = { [SEG6_ATTR_DST] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr) }, [SEG6_ATTR_DSTLEN] = { .type = NLA_S32, }, [SEG6_ATTR_HMACKEYID] = { .type = NLA_U32, }, [SEG6_ATTR_SECRET] = { .type = NLA_BINARY, }, [SEG6_ATTR_SECRETLEN] = { .type = NLA_U8, }, [SEG6_ATTR_ALGID] = { .type = NLA_U8, }, [SEG6_ATTR_HMACINFO] = { .type = NLA_NESTED, }, }; #ifdef CONFIG_IPV6_SEG6_HMAC static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct seg6_pernet_data *sdata; struct seg6_hmac_info *hinfo; u32 hmackeyid; char *secret; int err = 0; u8 algid; u8 slen; sdata = seg6_pernet(net); if (!info->attrs[SEG6_ATTR_HMACKEYID] || !info->attrs[SEG6_ATTR_SECRETLEN] || !info->attrs[SEG6_ATTR_ALGID]) return -EINVAL; hmackeyid = nla_get_u32(info->attrs[SEG6_ATTR_HMACKEYID]); slen = nla_get_u8(info->attrs[SEG6_ATTR_SECRETLEN]); algid = nla_get_u8(info->attrs[SEG6_ATTR_ALGID]); if (hmackeyid == 0) return -EINVAL; if (slen > SEG6_HMAC_SECRET_LEN) return -EINVAL; mutex_lock(&sdata->lock); hinfo = seg6_hmac_info_lookup(net, hmackeyid); if (!slen) { err = seg6_hmac_info_del(net, hmackeyid); goto out_unlock; } if (!info->attrs[SEG6_ATTR_SECRET]) { err = -EINVAL; goto out_unlock; } if (slen > nla_len(info->attrs[SEG6_ATTR_SECRET])) { err = -EINVAL; goto out_unlock; } if (hinfo) { err = seg6_hmac_info_del(net, hmackeyid); if (err) goto out_unlock; } secret = (char *)nla_data(info->attrs[SEG6_ATTR_SECRET]); hinfo = kzalloc(sizeof(*hinfo), GFP_KERNEL); if (!hinfo) { err = -ENOMEM; goto out_unlock; } memcpy(hinfo->secret, secret, slen); hinfo->slen = slen; hinfo->alg_id = algid; hinfo->hmackeyid = hmackeyid; err = seg6_hmac_info_add(net, hmackeyid, hinfo); if (err) kfree(hinfo); out_unlock: mutex_unlock(&sdata->lock); return err; } #else static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) { return -ENOTSUPP; } #endif static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct in6_addr *val, *t_old, *t_new; struct seg6_pernet_data *sdata; sdata = seg6_pernet(net); if (!info->attrs[SEG6_ATTR_DST]) return -EINVAL; val = nla_data(info->attrs[SEG6_ATTR_DST]); t_new = kmemdup(val, sizeof(*val), GFP_KERNEL); if (!t_new) return -ENOMEM; mutex_lock(&sdata->lock); t_old = sdata->tun_src; rcu_assign_pointer(sdata->tun_src, t_new); mutex_unlock(&sdata->lock); synchronize_net(); kfree(t_old); return 0; } static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct in6_addr *tun_src; struct sk_buff *msg; void *hdr; msg = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &seg6_genl_family, 0, SEG6_CMD_GET_TUNSRC); if (!hdr) goto free_msg; rcu_read_lock(); tun_src = rcu_dereference(seg6_pernet(net)->tun_src); if (nla_put(msg, SEG6_ATTR_DST, sizeof(struct in6_addr), tun_src)) goto nla_put_failure; rcu_read_unlock(); genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); nla_put_failure: rcu_read_unlock(); free_msg: nlmsg_free(msg); return -ENOMEM; } #ifdef CONFIG_IPV6_SEG6_HMAC static int __seg6_hmac_fill_info(struct seg6_hmac_info *hinfo, struct sk_buff *msg) { if (nla_put_u32(msg, SEG6_ATTR_HMACKEYID, hinfo->hmackeyid) || nla_put_u8(msg, SEG6_ATTR_SECRETLEN, hinfo->slen) || nla_put(msg, SEG6_ATTR_SECRET, hinfo->slen, hinfo->secret) || nla_put_u8(msg, SEG6_ATTR_ALGID, hinfo->alg_id)) return -1; return 0; } static int __seg6_genl_dumphmac_element(struct seg6_hmac_info *hinfo, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &seg6_genl_family, flags, cmd); if (!hdr) return -ENOMEM; if (__seg6_hmac_fill_info(hinfo, skb) < 0) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int seg6_genl_dumphmac_start(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct seg6_pernet_data *sdata; struct rhashtable_iter *iter; sdata = seg6_pernet(net); iter = (struct rhashtable_iter *)cb->args[0]; if (!iter) { iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return -ENOMEM; cb->args[0] = (long)iter; } rhashtable_walk_enter(&sdata->hmac_infos, iter); return 0; } static int seg6_genl_dumphmac_done(struct netlink_callback *cb) { struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; rhashtable_walk_exit(iter); kfree(iter); return 0; } static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) { struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; struct seg6_hmac_info *hinfo; int ret; rhashtable_walk_start(iter); for (;;) { hinfo = rhashtable_walk_next(iter); if (IS_ERR(hinfo)) { if (PTR_ERR(hinfo) == -EAGAIN) continue; ret = PTR_ERR(hinfo); goto done; } else if (!hinfo) { break; } ret = __seg6_genl_dumphmac_element(hinfo, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, SEG6_CMD_DUMPHMAC); if (ret) goto done; } ret = skb->len; done: rhashtable_walk_stop(iter); return ret; } #else static int seg6_genl_dumphmac_start(struct netlink_callback *cb) { return 0; } static int seg6_genl_dumphmac_done(struct netlink_callback *cb) { return 0; } static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) { return -ENOTSUPP; } #endif static int __net_init seg6_net_init(struct net *net) { struct seg6_pernet_data *sdata; sdata = kzalloc(sizeof(*sdata), GFP_KERNEL); if (!sdata) return -ENOMEM; mutex_init(&sdata->lock); sdata->tun_src = kzalloc(sizeof(*sdata->tun_src), GFP_KERNEL); if (!sdata->tun_src) { kfree(sdata); return -ENOMEM; } net->ipv6.seg6_data = sdata; if (seg6_hmac_net_init(net)) { kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); return -ENOMEM; } return 0; } static void __net_exit seg6_net_exit(struct net *net) { struct seg6_pernet_data *sdata = seg6_pernet(net); seg6_hmac_net_exit(net); kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); } static struct pernet_operations ip6_segments_ops = { .init = seg6_net_init, .exit = seg6_net_exit, }; static const struct genl_ops seg6_genl_ops[] = { { .cmd = SEG6_CMD_SETHMAC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_sethmac, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_DUMPHMAC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .start = seg6_genl_dumphmac_start, .dumpit = seg6_genl_dumphmac, .done = seg6_genl_dumphmac_done, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_SET_TUNSRC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_set_tunsrc, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_GET_TUNSRC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_get_tunsrc, .flags = GENL_ADMIN_PERM, }, }; static struct genl_family seg6_genl_family __ro_after_init = { .hdrsize = 0, .name = SEG6_GENL_NAME, .version = SEG6_GENL_VERSION, .maxattr = SEG6_ATTR_MAX, .policy = seg6_genl_policy, .netnsok = true, .parallel_ops = true, .ops = seg6_genl_ops, .n_ops = ARRAY_SIZE(seg6_genl_ops), .resv_start_op = SEG6_CMD_GET_TUNSRC + 1, .module = THIS_MODULE, }; int __init seg6_init(void) { int err; err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; err = genl_register_family(&seg6_genl_family); if (err) goto out_unregister_pernet; err = seg6_iptunnel_init(); if (err) goto out_unregister_genl; err = seg6_local_init(); if (err) goto out_unregister_iptun; err = seg6_hmac_init(); if (err) goto out_unregister_seg6; pr_info("Segment Routing with IPv6\n"); out: return err; out_unregister_seg6: seg6_local_exit(); out_unregister_iptun: seg6_iptunnel_exit(); out_unregister_genl: genl_unregister_family(&seg6_genl_family); out_unregister_pernet: unregister_pernet_subsys(&ip6_segments_ops); goto out; } void seg6_exit(void) { seg6_hmac_exit(); seg6_local_exit(); seg6_iptunnel_exit(); genl_unregister_family(&seg6_genl_family); unregister_pernet_subsys(&ip6_segments_ops); } |
| 199 199 199 207 158 207 208 200 200 2 17 2 8 176 20 37 100 1 6616 5097 32 32 113 143 120 32 38 47 1370 18792 362 639 1738 1453 40 1786 20 20 1996 931 632 1 1413 1428 1428 1426 145 18 12 132 12 132 24 2766 38 68 178 2232 7 2 1149 42 124 170 111 113 14 5167 5168 14 334 111 4155 114 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_H #define _LINUX_MM_H #include <linux/errno.h> #include <linux/mmdebug.h> #include <linux/gfp.h> #include <linux/pgalloc_tag.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/percpu-refcount.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> #include <linux/resource.h> #include <linux/page_ext.h> #include <linux/err.h> #include <linux/page-flags.h> #include <linux/page_ref.h> #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> #include <linux/pgtable.h> #include <linux/kasan.h> #include <linux/memremap.h> #include <linux/slab.h> struct mempolicy; struct anon_vma; struct anon_vma_chain; struct user_struct; struct pt_regs; struct folio_batch; extern int sysctl_page_lock_unfairness; void mm_core_init(void); void init_mm_internals(void); #ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; static inline void set_max_mapnr(unsigned long limit) { max_mapnr = limit; } #else static inline void set_max_mapnr(unsigned long limit) { } #endif extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { return (unsigned long)atomic_long_read(&_totalram_pages); } static inline void totalram_pages_inc(void) { atomic_long_inc(&_totalram_pages); } static inline void totalram_pages_dec(void) { atomic_long_dec(&_totalram_pages); } static inline void totalram_pages_add(long count) { atomic_long_add(count, &_totalram_pages); } extern void * high_memory; extern int page_cluster; extern const int page_cluster_max; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else #define sysctl_legacy_va_layout 0 #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; extern int mmap_rnd_bits_max __ro_after_init; extern int mmap_rnd_bits __read_mostly; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS extern const int mmap_rnd_compat_bits_min; extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif #include <asm/page.h> #include <asm/processor.h> #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif #ifndef page_to_virt #define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x))) #endif #ifndef lm_alias #define lm_alias(x) __va(__pa_symbol(x)) #endif /* * To prevent common memory management code establishing * a zero page mapping on a read fault. * This macro should be defined within <asm/pgtable.h>. * s390 does this to prevent multiplexing of hardware bits * related to the physical page in case of virtualization. */ #ifndef mm_forbids_zeropage #define mm_forbids_zeropage(X) (0) #endif /* * On some architectures it is expensive to call memset() for small sizes. * If an architecture decides to implement their own version of * mm_zero_struct_page they should wrap the defines below in a #ifndef and * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 /* This function must be updated when the size of struct page grows above 96 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statements if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) static inline void __mm_zero_struct_page(struct page *page) { unsigned long *_pp = (void *)page; /* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */ BUILD_BUG_ON(sizeof(struct page) & 7); BUILD_BUG_ON(sizeof(struct page) < 56); BUILD_BUG_ON(sizeof(struct page) > 96); switch (sizeof(struct page)) { case 96: _pp[11] = 0; fallthrough; case 88: _pp[10] = 0; fallthrough; case 80: _pp[9] = 0; fallthrough; case 72: _pp[8] = 0; fallthrough; case 64: _pp[7] = 0; fallthrough; case 56: _pp[6] = 0; _pp[5] = 0; _pp[4] = 0; _pp[3] = 0; _pp[2] = 0; _pp[1] = 0; _pp[0] = 0; } } #else #define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page))) #endif /* * Default maximum number of active map areas, this limits the number of vmas * per mm struct. Users can overwrite this number by sysctl but there is a * problem. * * When a program's coredump is generated as ELF format, a section is created * per a vma. In ELF, the number of sections is represented in unsigned short. * This means the number of sections should be smaller than 65535 at coredump. * Because the kernel adds some informative sections to a image of program at * generating coredump, we need some margin. The number of extra sections is * 1-3 now and depends on arch. We use "5" as safe margin, here. * * ELF extended numbering allows more than 65535 sections, so 16-bit bound is * not a hard limit any more. Although some userspace tools can be surprised by * that. */ #define MAPCOUNT_ELF_CORE_MARGIN (5) #define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, loff_t *); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) #define folio_page_idx(folio, p) (page_to_pfn(p) - folio_pfn(folio)) #else #define nth_page(page,n) ((page) + (n)) #define folio_page_idx(folio, p) ((p) - &(folio)->page) #endif /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* to align the pointer to the (prev) page boundary */ #define PAGE_ALIGN_DOWN(addr) ALIGN_DOWN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) static inline struct folio *lru_to_folio(struct list_head *head) { return list_entry((head)->prev, struct folio, lru); } void setup_initial_init_mm(void *start_code, void *end_code, void *end_data, void *brk); /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way * we have a virtual fs - giving a cleaner interface to the * mm details, and allowing different kinds of memory mappings * (from shared memory to executable loading to arbitrary * mmap() functions). */ struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); /* Use only if VMA has no other users */ void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif /* * vm_flags in vm_area_struct, see mm_types.h. * When changing, update also include/trace/events/mmflags.h */ #define VM_NONE 0x00000000 #define VM_READ 0x00000001 /* currently active flags */ #define VM_WRITE 0x00000002 #define VM_EXEC 0x00000004 #define VM_SHARED 0x00000008 /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ #define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */ #define VM_MAYWRITE 0x00000020 #define VM_MAYEXEC 0x00000040 #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #ifdef CONFIG_MMU #define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ #else /* CONFIG_MMU */ #define VM_MAYOVERLAY 0x00000200 /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */ #define VM_UFFD_MISSING 0 #endif /* CONFIG_MMU */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ /* Used by sys_madvise() */ #define VM_SEQ_READ 0x00008000 /* App will access data sequentially */ #define VM_RAND_READ 0x00010000 /* App will not benefit from clustered reads */ #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_SYNC 0x00800000 /* Synchronous page faults */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #ifdef CONFIG_MEM_SOFT_DIRTY # define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */ #else # define VM_SOFTDIRTY 0 #endif #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ #ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS #define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) #define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS # define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 # define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ # define VM_PKEY_BIT1 VM_HIGH_ARCH_1 /* on x86 and 5-bit value on ppc64 */ # define VM_PKEY_BIT2 VM_HIGH_ARCH_2 # define VM_PKEY_BIT3 VM_HIGH_ARCH_3 #ifdef CONFIG_PPC # define VM_PKEY_BIT4 VM_HIGH_ARCH_4 #else # define VM_PKEY_BIT4 0 #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ #ifdef CONFIG_X86_USER_SHADOW_STACK /* * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of * support core mm. * * These VMAs will get a single end guard page. This helps userspace protect * itself from attacks. A single page is enough for current shadow stack archs * (x86). See the comments near alloc_shstk() in arch/x86/kernel/shstk.c * for more details on the guard size. */ # define VM_SHADOW_STACK VM_HIGH_ARCH_5 #else # define VM_SHADOW_STACK VM_NONE #endif #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ #elif defined(CONFIG_PPC) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI #elif defined(CONFIG_ARM64) # define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */ # define VM_ARCH_CLEAR VM_ARM64_BTI #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif #if defined(CONFIG_ARM64_MTE) # define VM_MTE VM_HIGH_ARCH_0 /* Use Tagged memory for access control */ # define VM_MTE_ALLOWED VM_HIGH_ARCH_1 /* Tagged memory permitted */ #else # define VM_MTE VM_NONE # define VM_MTE_ALLOWED VM_NONE #endif #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR # define VM_UFFD_MINOR_BIT 38 # define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ # define VM_UFFD_MINOR VM_NONE #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ /* * This flag is used to connect VFIO to arch specific KVM code. It * indicates that the memory under this VMA is safe for use with any * non-cachable memory type inside KVM. Some VFIO devices, on some * platforms, are thought to be unsafe and can cause machine crashes * if KVM does not lock down the memory type. */ #ifdef CONFIG_64BIT #define VM_ALLOW_ANY_UNCACHED_BIT 39 #define VM_ALLOW_ANY_UNCACHED BIT(VM_ALLOW_ANY_UNCACHED_BIT) #else #define VM_ALLOW_ANY_UNCACHED VM_NONE #endif #ifdef CONFIG_64BIT /* VM is sealed, in vm_flags */ #define VM_SEALED _BITUL(63) #endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) #define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) /* Common data flag combinations */ #define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \ VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */ #define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC #endif #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif #define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK) #ifdef CONFIG_STACK_GROWSUP #define VM_STACK VM_GROWSUP #define VM_STACK_EARLY VM_GROWSDOWN #else #define VM_STACK VM_GROWSDOWN #define VM_STACK_EARLY 0 #endif #define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) /* VMA basic access permission flags */ #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) /* * Special vmas that are non-mergable, non-mlock()able. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) /* This mask prevents VMA from being scanned with khugepaged */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE /* This mask represents all the VMA flag bits used by mlock */ #define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR # define VM_ARCH_CLEAR VM_NONE #endif #define VM_FLAGS_CLEAR (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR) /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. */ #define FAULT_FLAG_DEFAULT (FAULT_FLAG_ALLOW_RETRY | \ FAULT_FLAG_KILLABLE | \ FAULT_FLAG_INTERRUPTIBLE) /** * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * @flags: Fault flags. * * This is mostly used for places where we want to try to avoid taking * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the * mmap_lock in the first round to avoid potential starvation of other * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. */ static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { return (flags & FAULT_FLAG_ALLOW_RETRY) && (!(flags & FAULT_FLAG_TRIED)); } #define FAULT_FLAG_TRACE \ { FAULT_FLAG_WRITE, "WRITE" }, \ { FAULT_FLAG_MKWRITE, "MKWRITE" }, \ { FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \ { FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \ { FAULT_FLAG_KILLABLE, "KILLABLE" }, \ { FAULT_FLAG_TRIED, "TRIED" }, \ { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ { FAULT_FLAG_VMA_LOCK, "VMA_LOCK" } /* * vm_fault is filled by the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * * MM layer fills up gfp_mask for page allocations but fault handler might * alter it if its implementation requires a different allocation context. * * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { const struct { struct vm_area_struct *vma; /* Target VMA */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address - masked */ unsigned long real_address; /* Faulting virtual address - unmasked */ }; enum fault_flag flags; /* FAULT_FLAG_xxx flags * XXX: should really be 'const' */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ pud_t *pud; /* Pointer to pud entry matching * the 'address' */ union { pte_t orig_pte; /* Value of PTE at the time of fault */ pmd_t orig_pmd; /* Value of PMD at the time of fault, * used by PMD fault only. */ }; struct page *cow_page; /* Page handler may use for COW fault */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by * VM_FAULT_ERROR). */ /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page * table hasn't been allocated. */ spinlock_t *ptl; /* Page table lock. * Protects pte page table if 'pte' * is not NULL, otherwise pmd. */ pgtable_t prealloc_pte; /* Pre-allocated pte page table. * vm_ops->map_pages() sets up a page * table from atomic context. * do_fault_around() pre-allocates * page table to avoid allocation from * atomic context. */ }; /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); /** * @close: Called when the VMA is being removed from the MM. * Context: User context. May sleep. Caller holds mmap_lock. */ void (*close)(struct vm_area_struct * area); /* Called any time before splitting to check if it's allowed */ int (*may_split)(struct vm_area_struct *area, unsigned long addr); int (*mremap)(struct vm_area_struct *area); /* * Called by mprotect() to make driver-specific permission * checks before mprotect() is finalised. The VMA must not * be modified. Returns 0 if mprotect() can proceed. */ int (*mprotect)(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long newflags); vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order); vm_fault_t (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ vm_fault_t (*page_mkwrite)(struct vm_fault *vmf); /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs. See also generic_access_phys() for a generic * implementation useful for any iomem mapping. */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); /* Called by the /proc/PID/maps code to ask the vma whether it * has a special name. Returning non-NULL will also cause this * vma to be dumped unconditionally. */ const char *(*name)(struct vm_area_struct *vma); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy * to hold the policy upon return. Caller should pass NULL @new to * remove a policy and fall back to surrounding context--i.e. do not * install a MPOL_DEFAULT policy, nor the task or system default * mempolicy. */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); /* * get_policy() op must add reference [mpol_get()] to any policy at * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); #endif /* * Called by vm_normal_page() for special PTEs to find the * page for @addr. This is useful if the default behavior * (using pte_page()) would not find the correct page. */ struct page *(*find_special_page)(struct vm_area_struct *vma, unsigned long addr); }; #ifdef CONFIG_NUMA_BALANCING static inline void vma_numab_state_init(struct vm_area_struct *vma) { vma->numab_state = NULL; } static inline void vma_numab_state_free(struct vm_area_struct *vma) { kfree(vma->numab_state); } #else static inline void vma_numab_state_init(struct vm_area_struct *vma) {} static inline void vma_numab_state_free(struct vm_area_struct *vma) {} #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_PER_VMA_LOCK /* * Try to read-lock a vma. The function is allowed to occasionally yield false * locked result to avoid performance overhead, in which case we fall back to * using mmap_lock. The function should never yield false unlocked result. */ static inline bool vma_start_read(struct vm_area_struct *vma) { /* * Check before locking. A race might cause false locked result. * We can use READ_ONCE() for the mm_lock_seq here, and don't need * ACQUIRE semantics, because this is just a lockless check whose result * we don't rely on for anything - the mm_lock_seq read against which we * need ordering is below. */ if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq)) return false; if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) return false; /* * Overflow might produce false locked result. * False unlocked result is impossible because we modify and check * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq * modification invalidates all existing locks. * * We must use ACQUIRE semantics for the mm_lock_seq so that if we are * racing with vma_end_write_all(), we only start reading from the VMA * after it has been unlocked. * This pairs with RELEASE semantics in vma_end_write_all(). */ if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) { up_read(&vma->vm_lock->lock); return false; } return true; } static inline void vma_end_read(struct vm_area_struct *vma) { rcu_read_lock(); /* keeps vma alive till the end of up_read */ up_read(&vma->vm_lock->lock); rcu_read_unlock(); } /* WARNING! Can only be used if mmap_lock is expected to be write-locked */ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) { mmap_assert_write_locked(vma->vm_mm); /* * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ *mm_lock_seq = vma->vm_mm->mm_lock_seq; return (vma->vm_lock_seq == *mm_lock_seq); } /* * Begin writing to a VMA. * Exclude concurrent readers under the per-VMA lock until the currently * write-locked mmap_lock is dropped or downgraded. */ static inline void vma_start_write(struct vm_area_struct *vma) { int mm_lock_seq; if (__is_vma_write_locked(vma, &mm_lock_seq)) return; down_write(&vma->vm_lock->lock); /* * We should use WRITE_ONCE() here because we can have concurrent reads * from the early lockless pessimistic check in vma_start_read(). * We don't really care about the correctness of that early check, but * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy. */ WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); up_write(&vma->vm_lock->lock); } static inline void vma_assert_write_locked(struct vm_area_struct *vma) { int mm_lock_seq; VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } static inline void vma_assert_locked(struct vm_area_struct *vma) { if (!rwsem_is_locked(&vma->vm_lock->lock)) vma_assert_write_locked(vma); } static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) { /* When detaching vma should be write-locked */ if (detached) vma_assert_write_locked(vma); vma->detached = detached; } static inline void release_fault_lock(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) vma_end_read(vmf->vma); else mmap_read_unlock(vmf->vma->vm_mm); } static inline void assert_fault_locked(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) vma_assert_locked(vmf->vma); else mmap_assert_locked(vmf->vma->vm_mm); } struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address); #else /* CONFIG_PER_VMA_LOCK */ static inline bool vma_start_read(struct vm_area_struct *vma) { return false; } static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} static inline void vma_assert_write_locked(struct vm_area_struct *vma) { mmap_assert_write_locked(vma->vm_mm); } static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) {} static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) { return NULL; } static inline void vma_assert_locked(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); } static inline void release_fault_lock(struct vm_fault *vmf) { mmap_read_unlock(vmf->vma->vm_mm); } static inline void assert_fault_locked(struct vm_fault *vmf) { mmap_assert_locked(vmf->vma->vm_mm); } #endif /* CONFIG_PER_VMA_LOCK */ extern const struct vm_operations_struct vma_dummy_vm_ops; /* * WARNING: vma_init does not initialize vma->vm_lock. * Use vm_area_alloc()/vm_area_free() if vma needs locking. */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); vma_mark_detached(vma, false); vma_numab_state_init(vma); } /* Use when VMA is not part of the VMA tree and needs no locking */ static inline void vm_flags_init(struct vm_area_struct *vma, vm_flags_t flags) { ACCESS_PRIVATE(vma, __vm_flags) = flags; } /* * Use when VMA is part of the VMA tree and modifications need coordination * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and * it should be locked explicitly beforehand. */ static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { vma_assert_write_locked(vma); vm_flags_init(vma, flags); } static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { vma_assert_write_locked(vma); WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); } static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) |= flags; } static inline void vm_flags_clear(struct vm_area_struct *vma, vm_flags_t flags) { vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; } /* * Use only if VMA is not part of the VMA tree or has no other users and * therefore needs no locking. */ static inline void __vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { vm_flags_init(vma, (vma->vm_flags | set) & ~clear); } /* * Use only when the order of set/clear operations is unimportant, otherwise * use vm_flags_{set|clear} explicitly. */ static inline void vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { vma_start_write(vma); __vm_flags_mod(vma, set, clear); } static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; } static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; } /* * Indicate if the VMA is a heap for the given task; for * /proc/PID/maps that is the heap of the main task. */ static inline bool vma_is_initial_heap(const struct vm_area_struct *vma) { return vma->vm_start < vma->vm_mm->brk && vma->vm_end > vma->vm_mm->start_brk; } /* * Indicate if the VMA is a stack for the given task; for * /proc/PID/maps that is the stack of the main task. */ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) { /* * We make no effort to guess what a given thread considers to be * its "stack". It's not even well-defined for programs written * languages like Go. */ return vma->vm_start <= vma->vm_mm->start_stack && vma->vm_end >= vma->vm_mm->start_stack; } static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); if (!maybe_stack) return false; if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == VM_STACK_INCOMPLETE_SETUP) return true; return false; } static inline bool vma_is_foreign(struct vm_area_struct *vma) { if (!current->mm) return true; if (current->mm != vma->vm_mm) return true; return false; } static inline bool vma_is_accessible(struct vm_area_struct *vma) { return vma->vm_flags & VM_ACCESS_FLAGS; } static inline bool is_shared_maywrite(vm_flags_t vm_flags) { return (vm_flags & (VM_SHARED | VM_MAYWRITE)) == (VM_SHARED | VM_MAYWRITE); } static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) { return is_shared_maywrite(vma->vm_flags); } static inline struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) { return mas_find(&vmi->mas, max - 1); } static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) { /* * Uses mas_find() to get the first VMA when the iterator starts. * Calling mas_next() could skip the first entry. */ return mas_find(&vmi->mas, ULONG_MAX); } static inline struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi) { return mas_next_range(&vmi->mas, ULONG_MAX); } static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) { return mas_prev(&vmi->mas, 0); } static inline struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi) { return mas_prev_range(&vmi->mas, 0); } static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) { return vmi->mas.index; } static inline unsigned long vma_iter_end(struct vma_iterator *vmi) { return vmi->mas.last + 1; } static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi, unsigned long count) { return mas_expected_entries(&vmi->mas, count); } static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, unsigned long start, unsigned long end, gfp_t gfp) { __mas_set_range(&vmi->mas, start, end - 1); mas_store_gfp(&vmi->mas, NULL, gfp); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; return 0; } /* Free any unused preallocations */ static inline void vma_iter_free(struct vma_iterator *vmi) { mas_destroy(&vmi->mas); } static inline int vma_iter_bulk_store(struct vma_iterator *vmi, struct vm_area_struct *vma) { vmi->mas.index = vma->vm_start; vmi->mas.last = vma->vm_end - 1; mas_store(&vmi->mas, vma); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; return 0; } static inline void vma_iter_invalidate(struct vma_iterator *vmi) { mas_pause(&vmi->mas); } static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) { mas_set(&vmi->mas, addr); } #define for_each_vma(__vmi, __vma) \ while (((__vma) = vma_next(&(__vmi))) != NULL) /* The MM code likes to work with exclusive end addresses */ #define for_each_vma_range(__vmi, __vma, __end) \ while (((__vma) = vma_find(&(__vmi), (__end))) != NULL) #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow * paths in userfault. */ bool vma_is_shmem(struct vm_area_struct *vma); bool vma_is_anon_shmem(struct vm_area_struct *vma); #else static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; } #endif int vma_is_stack_for_current(struct vm_area_struct *vma); /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } struct mmu_gather; struct inode; /* * compound_order() can be called without holding a reference, which means * that niceties like page_folio() don't work. These callers should be * prepared to handle wild return values. For example, PG_head may be * set before the order is initialised, or this may be a tail page. * See compaction.c for some good examples. */ static inline unsigned int compound_order(struct page *page) { struct folio *folio = (struct folio *)page; if (!test_bit(PG_head, &folio->flags)) return 0; return folio->_flags_1 & 0xff; } /** * folio_order - The allocation order of a folio. * @folio: The folio. * * A folio is composed of 2^order pages. See get_order() for the definition * of order. * * Return: The order of the folio. */ static inline unsigned int folio_order(struct folio *folio) { if (!folio_test_large(folio)) return 0; return folio->_flags_1 & 0xff; } #include <linux/huge_mm.h> /* * Methods to modify the page usage count. * * What counts for a page usage: * - cache mapping (page->mapping) * - private data (page->private) * - page mapped in a task's page tables, each mapping * is counted separately * * Also, many kernel routines increase the page count before a critical * routine so they can be sure the page doesn't go away from under them. */ /* * Drop a ref, return true if the refcount fell to zero (the page has no users) */ static inline int put_page_testzero(struct page *page) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); return page_ref_dec_and_test(page); } static inline int folio_put_testzero(struct folio *folio) { return put_page_testzero(&folio->page); } /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. * This can be called when MMU is off so it must not access * any of the virtual mappings. */ static inline bool get_page_unless_zero(struct page *page) { return page_ref_add_unless(page, 1, 0); } static inline struct folio *folio_get_nontail_page(struct page *page) { if (unlikely(!get_page_unless_zero(page))) return NULL; return (struct folio *)page; } extern int page_is_ram(unsigned long pfn); enum { REGION_INTERSECTS, REGION_DISJOINT, REGION_MIXED, }; int region_intersects(resource_size_t offset, size_t size, unsigned long flags, unsigned long desc); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); unsigned long vmalloc_to_pfn(const void *addr); /* * Determine if an address is within the vmalloc range * * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ #ifdef CONFIG_MMU extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); #else static inline bool is_vmalloc_addr(const void *x) { return false; } static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } #endif /* * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for * debugging purposes - it does not include PTE-mapped sub-pages; look * at folio_mapcount() or page_mapcount() instead. */ static inline int folio_entire_mapcount(const struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); return atomic_read(&folio->_entire_mapcount) + 1; } /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). */ static inline void page_mapcount_reset(struct page *page) { atomic_set(&(page)->_mapcount, -1); } /** * page_mapcount() - Number of times this precise page is mapped. * @page: The page. * * The number of times this page is mapped. If this page is part of * a large folio, it includes the number of times this page is mapped * as part of that folio. * * Will report 0 for pages which cannot be mapped into userspace, eg * slab, page tables and similar. */ static inline int page_mapcount(struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; /* Handle page_has_type() pages */ if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) mapcount = 0; if (unlikely(PageCompound(page))) mapcount += folio_entire_mapcount(page_folio(page)); return mapcount; } static inline int folio_large_mapcount(const struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_large(folio), folio); return atomic_read(&folio->_large_mapcount) + 1; } /** * folio_mapcount() - Number of mappings of this folio. * @folio: The folio. * * The folio mapcount corresponds to the number of present user page table * entries that reference any part of a folio. Each such present user page * table entry must be paired with exactly on folio reference. * * For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts * exactly once. * * For hugetlb folios, each abstracted "hugetlb" user page table entry that * references the entire folio counts exactly once, even when such special * page table entries are comprised of multiple ordinary page table entries. * * Will report 0 for pages which cannot be mapped into userspace, such as * slab, page tables and similar. * * Return: The number of times this folio is mapped. */ static inline int folio_mapcount(const struct folio *folio) { int mapcount; if (likely(!folio_test_large(folio))) { mapcount = atomic_read(&folio->_mapcount) + 1; /* Handle page_has_type() pages */ if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) mapcount = 0; return mapcount; } return folio_large_mapcount(folio); } /** * folio_mapped - Is this folio mapped into userspace? * @folio: The folio. * * Return: True if any page in this folio is referenced by user page tables. */ static inline bool folio_mapped(const struct folio *folio) { return folio_mapcount(folio) >= 1; } /* * Return true if this page is mapped into pagetables. * For compound page it returns true if any sub-page of compound page is mapped, * even if this particular sub-page is not itself mapped by any PTE or PMD. */ static inline bool page_mapped(const struct page *page) { return folio_mapped(page_folio(page)); } static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); return compound_head(page); } static inline struct folio *virt_to_folio(const void *x) { struct page *page = virt_to_page(x); return page_folio(page); } void __folio_put(struct folio *folio); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); void folio_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { return PAGE_SIZE << compound_order(page); } /* Returns the number of bits needed for the number of bytes in a page */ static inline unsigned int page_shift(struct page *page) { return PAGE_SHIFT + compound_order(page); } /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. */ static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return compound_order(page); } /** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. * * Return: Number of bytes in this page. */ static inline unsigned long thp_size(struct page *page) { return PAGE_SIZE << thp_order(page); } #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pte = pte_mkwrite(pte, vma); return pte; } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr); vm_fault_t finish_fault(struct vm_fault *vmf); #endif /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of * zeroes, and text pages of executables and shared libraries have * only one copy in memory, at most, normally. * * For the non-reserved pages, page_count(page) denotes a reference count. * page_count() == 0 means the page is free. page->lru is then used for * freelist management in the buddy allocator. * page_count() > 0 means the page has been allocated. * * Pages are allocated by the slab allocator in order to provide memory * to kmalloc and kmem_cache_alloc. In this case, the management of the * page, and the fields in 'struct page' are the responsibility of mm/slab.c * unless a particular usage is carefully commented. (the responsibility of * freeing the kmalloc memory is the caller's, of course). * * A page may be used by anyone else who does a __get_free_page(). * In this case, page_count still tracks the references, and should only * be used through the normal accessor functions. The top bits of page->flags * and page->virtual store page management information, but all other fields * are unused and could be used privately, carefully. The management of this * page is the responsibility of the one who allocated it, and those who have * subsequently been given references to it. * * The other pages (we may call them "pagecache pages") are completely * managed by the Linux memory manager: I/O, buffers, swapping etc. * The following discussion applies only to them. * * A pagecache page contains an opaque `private' member, which belongs to the * page's address_space. Usually, this is the address of a circular list of * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * * A page may belong to an inode's memory mapping. In this case, page->mapping * is the pointer to the inode, and page->index is the file offset of the page, * in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that * case PG_swapcache is set, and page->private is an offset into the swapcache. * * In either case (swapcache or inode backed), the pagecache itself holds one * reference to the page. Setting PG_private should also increment the * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is * rooted at mapping->i_pages, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * * All pagecache pages may be subject to I/O: * - inode pages may need to be read from disk, * - inode pages which have been modified and are MAP_SHARED may need * to be written back to the inode on disk, * - anonymous pages (including MAP_PRIVATE file mappings) which have been * modified may need to be swapped out to swap space and (later) to be read * back into memory. */ #if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) DECLARE_STATIC_KEY_FALSE(devmap_managed_key); bool __put_devmap_managed_folio_refs(struct folio *folio, int refs); static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { if (!static_branch_unlikely(&devmap_managed_key)) return false; if (!folio_is_zone_device(folio)) return false; return __put_devmap_managed_folio_refs(folio, refs); } #else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { return false; } #endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) /** * folio_get - Increment the reference count on a folio. * @folio: The folio. * * Context: May be called in any context, as long as you know that * you have a refcount on the folio. If you do not already have one, * folio_try_get() may be the right interface for you to use. */ static inline void folio_get(struct folio *folio) { VM_BUG_ON_FOLIO(folio_ref_zero_or_close_to_overflow(folio), folio); folio_ref_inc(folio); } static inline void get_page(struct page *page) { folio_get(page_folio(page)); } static inline __must_check bool try_get_page(struct page *page) { page = compound_head(page); if (WARN_ON_ONCE(page_ref_count(page) <= 0)) return false; page_ref_inc(page); return true; } /** * folio_put - Decrement the reference count on a folio. * @folio: The folio. * * If the folio's reference count reaches zero, the memory will be * released back to the page allocator and may be used by another * allocation immediately. Do not access the memory or the struct folio * after calling folio_put() unless you can be sure that it wasn't the * last reference. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folio_put(struct folio *folio) { if (folio_put_testzero(folio)) __folio_put(folio); } /** * folio_put_refs - Reduce the reference count on a folio. * @folio: The folio. * @refs: The amount to subtract from the folio's reference count. * * If the folio's reference count reaches zero, the memory will be * released back to the page allocator and may be used by another * allocation immediately. Do not access the memory or the struct folio * after calling folio_put_refs() unless you can be sure that these weren't * the last references. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folio_put_refs(struct folio *folio, int refs) { if (folio_ref_sub_and_test(folio, refs)) __folio_put(folio); } void folios_put_refs(struct folio_batch *folios, unsigned int *refs); /* * union release_pages_arg - an array of pages or folios * * release_pages() releases a simple array of multiple pages, and * accepts various different forms of said page array: either * a regular old boring array of pages, an array of folios, or * an array of encoded page pointers. * * The transparent union syntax for this kind of "any of these * argument types" is all kinds of ugly, so look away. */ typedef union { struct page **pages; struct folio **folios; struct encoded_page **encoded_pages; } release_pages_arg __attribute__ ((__transparent_union__)); void release_pages(release_pages_arg, int nr); /** * folios_put - Decrement the reference count on an array of folios. * @folios: The folios. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need to * reinitialise it. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folios_put(struct folio_batch *folios) { folios_put_refs(folios, NULL); } static inline void put_page(struct page *page) { struct folio *folio = page_folio(page); /* * For some devmap managed pages we need to catch refcount transition * from 2 to 1: */ if (put_devmap_managed_folio_refs(folio, 1)) return; folio_put(folio); } /* * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload * the page's refcount so that two separate items are tracked: the original page * reference count, and also a new count of how many pin_user_pages() calls were * made against the page. ("gup-pinned" is another term for the latter). * * With this scheme, pin_user_pages() becomes special: such pages are marked as * distinct from normal pages. As such, the unpin_user_page() call (and its * variants) must be used in order to release gup-pinned pages. * * Choice of value: * * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference * counts with respect to pin_user_pages() and unpin_user_page() becomes * simpler, due to the fact that adding an even power of two to the page * refcount has the effect of using only the upper N bits, for the code that * counts up using the bias value. This means that the lower bits are left for * the exclusive use of the original code that increments and decrements by one * (or at least, by much smaller values than the bias value). * * Of course, once the lower bits overflow into the upper bits (and this is * OK, because subtraction recovers the original values), then visual inspection * no longer suffices to directly view the separate counts. However, for normal * applications that don't have huge page reference counts, this won't be an * issue. * * Locking: the lockless algorithm described in folio_try_get_rcu() * provides safe operation for get_user_pages(), page_mkclean() and * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) void unpin_user_page(struct page *page); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } #ifndef CONFIG_MMU static inline bool is_nommu_shared_mapping(vm_flags_t flags) { /* * NOMMU shared mappings are ordinary MAP_SHARED mappings and selected * R/O MAP_PRIVATE file mappings that are an effective R/O overlay of * a file mapping. R/O MAP_PRIVATE mappings might still modify * underlying memory if ptrace is active, so this is only possible if * ptrace does not apply. Note that there is no mprotect() to upgrade * write permissions later. */ return flags & (VM_MAYSHARE | VM_MAYOVERLAY); } #endif #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif /* * The identification function is mainly used by the buddy allocator for * determining if two pages could be buddies. We are not really identifying * the zone since we could be using the section number id if we do not have * node id available in page flags. * We only guarantee that it will return the same value for two combinable * pages in a zone. */ static inline int page_zone_id(struct page *page) { return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } #ifdef NODE_NOT_IN_PAGE_FLAGS int page_to_nid(const struct page *page); #else static inline int page_to_nid(const struct page *page) { return (PF_POISONED_CHECK(page)->flags >> NODES_PGSHIFT) & NODES_MASK; } #endif static inline int folio_nid(const struct folio *folio) { return page_to_nid(&folio->page); } #ifdef CONFIG_NUMA_BALANCING /* page access time bits needs to hold at least 4 seconds */ #define PAGE_ACCESS_TIME_MIN_BITS 12 #if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS #define PAGE_ACCESS_TIME_BUCKETS \ (PAGE_ACCESS_TIME_MIN_BITS - LAST_CPUPID_SHIFT) #else #define PAGE_ACCESS_TIME_BUCKETS 0 #endif #define PAGE_ACCESS_TIME_MASK \ (LAST_CPUPID_MASK << PAGE_ACCESS_TIME_BUCKETS) static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); } static inline int cpupid_to_pid(int cpupid) { return cpupid & LAST__PID_MASK; } static inline int cpupid_to_cpu(int cpupid) { return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK; } static inline int cpupid_to_nid(int cpupid) { return cpu_to_node(cpupid_to_cpu(cpupid)); } static inline bool cpupid_pid_unset(int cpupid) { return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK); } static inline bool cpupid_cpu_unset(int cpupid) { return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK); } static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) { return (task_pid & LAST__PID_MASK) == cpupid_to_pid(cpupid); } #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int folio_last_cpupid(struct folio *folio) { return folio->_last_cpupid; } static inline void page_cpupid_reset_last(struct page *page) { page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else static inline int folio_last_cpupid(struct folio *folio) { return (folio->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } int folio_xchg_last_cpupid(struct folio *folio, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ static inline int folio_xchg_access_time(struct folio *folio, int time) { int last_time; last_time = folio_xchg_last_cpupid(folio, time >> PAGE_ACCESS_TIME_BUCKETS); return last_time << PAGE_ACCESS_TIME_BUCKETS; } static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { unsigned int pid_bit; pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG)); if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->pids_active[1])) { __set_bit(pid_bit, &vma->numab_state->pids_active[1]); } } #else /* !CONFIG_NUMA_BALANCING */ static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { return folio_nid(folio); /* XXX */ } static inline int folio_xchg_access_time(struct folio *folio, int time) { return 0; } static inline int folio_last_cpupid(struct folio *folio) { return folio_nid(folio); /* XXX */ } static inline int cpupid_to_nid(int cpupid) { return -1; } static inline int cpupid_to_pid(int cpupid) { return -1; } static inline int cpupid_to_cpu(int cpupid) { return -1; } static inline int cpu_pid_to_cpupid(int nid, int pid) { return -1; } static inline bool cpupid_pid_unset(int cpupid) { return true; } static inline void page_cpupid_reset_last(struct page *page) { } static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { } #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) /* * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid * setting tags for all pages to native kernel tag value 0xff, as the default * value 0x00 maps to 0xff. */ static inline u8 page_kasan_tag(const struct page *page) { u8 tag = KASAN_TAG_KERNEL; if (kasan_enabled()) { tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; tag ^= 0xff; } return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { unsigned long old_flags, flags; if (!kasan_enabled()) return; tag ^= 0xff; old_flags = READ_ONCE(page->flags); do { flags = old_flags; flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) { if (kasan_enabled()) page_kasan_tag_set(page, KASAN_TAG_KERNEL); } #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline u8 page_kasan_tag(const struct page *page) { return 0xff; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { } static inline void page_kasan_tag_reset(struct page *page) { } #endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline struct zone *page_zone(const struct page *page) { return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } static inline pg_data_t *page_pgdat(const struct page *page) { return NODE_DATA(page_to_nid(page)); } static inline struct zone *folio_zone(const struct folio *folio) { return page_zone(&folio->page); } static inline pg_data_t *folio_pgdat(const struct folio *folio) { return page_pgdat(&folio->page); } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } static inline unsigned long page_to_section(const struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } #endif /** * folio_pfn - Return the Page Frame Number of a folio. * @folio: The folio. * * A folio may contain multiple pages. The pages have consecutive * Page Frame Numbers. * * Return: The Page Frame Number of the first page in the folio. */ static inline unsigned long folio_pfn(struct folio *folio) { return page_to_pfn(&folio->page); } static inline struct folio *pfn_folio(unsigned long pfn) { return page_folio(pfn_to_page(pfn)); } /** * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. * @folio: The folio. * * This function checks if a folio has been pinned via a call to * a function in the pin_user_pages() family. * * For small folios, the return value is partially fuzzy: false is not fuzzy, * because it means "definitely not pinned for DMA", but true means "probably * pinned for DMA, but possibly a false positive due to having at least * GUP_PIN_COUNTING_BIAS worth of normal folio references". * * False positives are OK, because: a) it's unlikely for a folio to * get that many refcounts, and b) all the callers of this routine are * expected to be able to deal gracefully with a false positive. * * For large folios, the result will be exactly correct. That's because * we have more tracking data available: the _pincount field is used * instead of the GUP_PIN_COUNTING_BIAS scheme. * * For more information, please see Documentation/core-api/pin_user_pages.rst. * * Return: True, if it is likely that the page has been "dma-pinned". * False, if the page is definitely not dma-pinned. */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { if (folio_test_large(folio)) return atomic_read(&folio->_pincount) > 0; /* * folio_ref_count() is signed. If that refcount overflows, then * folio_ref_count() returns a negative value, and callers will avoid * further incrementing the refcount. * * Here, for that overflow case, use the sign bit to count a little * bit higher via unsigned math, and thus still get an accurate result. */ return ((unsigned int)folio_ref_count(folio)) >= GUP_PIN_COUNTING_BIAS; } static inline bool page_maybe_dma_pinned(struct page *page) { return folio_maybe_dma_pinned(page_folio(page)); } /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for an anon page on the src mm. * * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma, struct folio *folio) { VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; return folio_maybe_dma_pinned(folio); } /** * is_zero_page - Query if a page is a zero page * @page: The page to query * * This returns true if @page is one of the permanent zero pages. */ static inline bool is_zero_page(const struct page *page) { return is_zero_pfn(page_to_pfn(page)); } /** * is_zero_folio - Query if a folio is a zero page * @folio: The folio to query * * This returns true if @folio is one of the permanent zero pages. */ static inline bool is_zero_folio(const struct folio *folio) { return is_zero_page(&folio->page); } /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin folios */ #ifdef CONFIG_MIGRATION static inline bool folio_is_longterm_pinnable(struct folio *folio) { #ifdef CONFIG_CMA int mt = folio_migratetype(folio); if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif /* The zero page can be "pinned" but gets special handling. */ if (is_zero_folio(folio)) return true; /* Coherent device memory must always allow eviction. */ if (folio_is_device_coherent(folio)) return false; /* Otherwise, non-movable zone folios can be pinned. */ return !folio_is_zone_movable(folio); } #else static inline bool folio_is_longterm_pinnable(struct folio *folio) { return true; } #endif static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { page->flags &= ~(NODES_MASK << NODES_PGSHIFT); page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); set_page_node(page, node); #ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } /** * folio_nr_pages - The number of pages in the folio. * @folio: The folio. * * Return: A positive power of two. */ static inline long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; #ifdef CONFIG_64BIT return folio->_folio_nr_pages; #else return 1L << (folio->_flags_1 & 0xff); #endif } /* Only hugetlbfs can allocate folios larger than MAX_ORDER */ #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE #define MAX_FOLIO_NR_PAGES (1UL << PUD_ORDER) #else #define MAX_FOLIO_NR_PAGES MAX_ORDER_NR_PAGES #endif /* * compound_nr() returns the number of pages in this potentially compound * page. compound_nr() can be called on a tail page, and is defined to * return 1 in that case. */ static inline unsigned long compound_nr(struct page *page) { struct folio *folio = (struct folio *)page; if (!test_bit(PG_head, &folio->flags)) return 1; #ifdef CONFIG_64BIT return folio->_folio_nr_pages; #else return 1L << (folio->_flags_1 & 0xff); #endif } /** * thp_nr_pages - The number of regular pages in this huge page. * @page: The head page of a huge page. */ static inline int thp_nr_pages(struct page *page) { return folio_nr_pages((struct folio *)page); } /** * folio_next - Move to the next physical folio. * @folio: The folio we're currently operating on. * * If you have physically contiguous memory which may span more than * one folio (eg a &struct bio_vec), use this function to move from one * folio to the next. Do not use it if the memory is only virtually * contiguous as the folios are almost certainly not adjacent to each * other. This is the folio equivalent to writing ``page++``. * * Context: We assume that the folios are refcounted and/or locked at a * higher level and do not adjust the reference counts. * Return: The next struct folio. */ static inline struct folio *folio_next(struct folio *folio) { return (struct folio *)folio_page(folio, folio_nr_pages(folio)); } /** * folio_shift - The size of the memory described by this folio. * @folio: The folio. * * A folio represents a number of bytes which is a power-of-two in size. * This function tells you which power-of-two the folio is. See also * folio_size() and folio_order(). * * Context: The caller should have a reference on the folio to prevent * it from being split. It is not necessary for the folio to be locked. * Return: The base-2 logarithm of the size of this folio. */ static inline unsigned int folio_shift(struct folio *folio) { return PAGE_SHIFT + folio_order(folio); } /** * folio_size - The number of bytes in a folio. * @folio: The folio. * * Context: The caller should have a reference on the folio to prevent * it from being split. It is not necessary for the folio to be locked. * Return: The number of bytes in this folio. */ static inline size_t folio_size(struct folio *folio) { return PAGE_SIZE << folio_order(folio); } /** * folio_likely_mapped_shared - Estimate if the folio is mapped into the page * tables of more than one MM * @folio: The folio. * * This function checks if the folio is currently mapped into more than one * MM ("mapped shared"), or if the folio is only mapped into a single MM * ("mapped exclusively"). * * As precise information is not easily available for all folios, this function * estimates the number of MMs ("sharers") that are currently mapping a folio * using the number of times the first page of the folio is currently mapped * into page tables. * * For small anonymous folios (except KSM folios) and anonymous hugetlb folios, * the return value will be exactly correct, because they can only be mapped * at most once into an MM, and they cannot be partially mapped. * * For other folios, the result can be fuzzy: * #. For partially-mappable large folios (THP), the return value can wrongly * indicate "mapped exclusively" (false negative) when the folio is * only partially mapped into at least one MM. * #. For pagecache folios (including hugetlb), the return value can wrongly * indicate "mapped shared" (false positive) when two VMAs in the same MM * cover the same file range. * #. For (small) KSM folios, the return value can wrongly indicate "mapped * shared" (false positive), when the folio is mapped multiple times into * the same MM. * * Further, this function only considers current page table mappings that * are tracked using the folio mapcount(s). * * This function does not consider: * #. If the folio might get mapped in the (near) future (e.g., swapcache, * pagecache, temporary unmapping for migration). * #. If the folio is mapped differently (VM_PFNMAP). * #. If hugetlb page table sharing applies. Callers might want to check * hugetlb_pmd_shared(). * * Return: Whether the folio is estimated to be mapped into more than one MM. */ static inline bool folio_likely_mapped_shared(struct folio *folio) { int mapcount = folio_mapcount(folio); /* Only partially-mappable folios require more care. */ if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio))) return mapcount > 1; /* A single mapping implies "mapped exclusively". */ if (mapcount <= 1) return false; /* If any page is mapped more than once we treat it "mapped shared". */ if (folio_entire_mapcount(folio) || mapcount > folio_nr_pages(folio)) return true; /* Let's guess based on the first subpage. */ return atomic_read(&folio->_mapcount) > 0; } #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { return 0; } #endif #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE static inline int arch_make_folio_accessible(struct folio *folio) { int ret; long i, nr = folio_nr_pages(folio); for (i = 0; i < nr; i++) { ret = arch_make_page_accessible(folio_page(folio, i)); if (ret) break; } return ret; } #endif /* * Some inline functions in vmstat.h depend on page_zone() */ #include <linux/vmstat.h> #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif #if defined(WANT_PAGE_VIRTUAL) static inline void *page_address(const struct page *page) { return page->virtual; } static inline void set_page_address(struct page *page, void *address) { page->virtual = address; } #define page_address_init() do { } while(0) #endif #if defined(HASHED_PAGE_VIRTUAL) void *page_address(const struct page *page); void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif static __always_inline void *lowmem_page_address(const struct page *page) { return page_to_virt(page); } #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) #define page_address_init() do { } while(0) #endif static inline void *folio_address(const struct folio *folio) { return page_address(&folio->page); } extern pgoff_t __page_file_index(struct page *page); /* * Return the pagecache index of the passed page. Regular pagecache pages * use ->index whereas swapcache pages use swp_offset(->private) */ static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_index(page); return page->index; } /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool page_is_pfmemalloc(const struct page *page) { /* * lru.next has bit 1 set if the page is allocated from the * pfmemalloc reserves. Callers may simply overwrite it if * they do not need to preserve that information. */ return (uintptr_t)page->lru.next & BIT(1); } /* * Return true only if the folio has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool folio_is_pfmemalloc(const struct folio *folio) { /* * lru.next has bit 1 set if the page is allocated from the * pfmemalloc reserves. Callers may simply overwrite it if * they do not need to preserve that information. */ return (uintptr_t)folio->lru.next & BIT(1); } /* * Only to be called by the page allocator on a freshly allocated * page. */ static inline void set_page_pfmemalloc(struct page *page) { page->lru.next = (void *)BIT(1); } static inline void clear_page_pfmemalloc(struct page *page) { page->lru.next = NULL; } /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. */ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) #define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) #define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool even_cows; /* Zap COWed private pages too? */ zap_flags_t zap_flags; /* Extra flags for zapping */ }; /* * Whether to drop the pte markers, for example, the uffd-wp information for * file-backed memory. This should only be specified when we will completely * drop the page in the mm, either by truncation or unmapping of the vma. By * default, the flag is not set. */ #define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) /* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ #define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) #ifdef CONFIG_SCHED_MM_CID void sched_mm_cid_before_execve(struct task_struct *t); void sched_mm_cid_after_execve(struct task_struct *t); void sched_mm_cid_fork(struct task_struct *t); void sched_mm_cid_exit_signals(struct task_struct *t); static inline int task_mm_cid(struct task_struct *t) { return t->mm_cid; } #else static inline void sched_mm_cid_before_execve(struct task_struct *t) { } static inline void sched_mm_cid_after_execve(struct task_struct *t) { } static inline void sched_mm_cid_fork(struct task_struct *t) { } static inline void sched_mm_cid_exit_signals(struct task_struct *t) { } static inline int task_mm_cid(struct task_struct *t) { /* * Use the processor id as a fall-back when the mm cid feature is * disabled. This provides functional per-cpu data structure accesses * in user-space, althrough it won't provide the memory usage benefits. */ return raw_smp_processor_id(); } #endif #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else static inline bool can_do_mlock(void) { return false; } #endif extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details); static inline void zap_vma_pages(struct vm_area_struct *vma) { zap_page_range_single(vma, vma->vm_start, vma->vm_end - vma->vm_start, NULL); } void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long start, unsigned long end, unsigned long tree_end, bool mm_wr_locked); struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); int follow_pte(struct vm_area_struct *vma, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int generic_error_remove_folio(struct address_space *mapping, struct folio *folio); struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm, unsigned long address, struct pt_regs *regs); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs); extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* should never happen if there's no MMU */ BUG(); return VM_FAULT_SIGBUS; } static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); return -EFAULT; } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { } #endif static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) { unmap_mapping_range(mapping, holebegin, holelen, 0); } static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); /* * Retrieves a single page alongside its VMA. Does not support FOLL_NOWAIT. */ static inline struct page *get_user_page_vma_remote(struct mm_struct *mm, unsigned long addr, int gup_flags, struct vm_area_struct **vmap) { struct page *page; struct vm_area_struct *vma; int got; if (WARN_ON_ONCE(unlikely(gup_flags & FOLL_NOWAIT))) return ERR_PTR(-EINVAL); got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL); if (got < 0) return ERR_PTR(got); vma = vma_lookup(mm, addr); if (WARN_ON_ONCE(!vma)) { put_page(page); return ERR_PTR(-EINVAL); } *vmap = vma; return page; } long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages); long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); void folio_add_pin(struct folio *folio); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); struct kvec; struct page *get_dump_page(unsigned long addr); bool folio_mark_dirty(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, bool need_rmap_locks, bool for_stack); /* * Flags used by change_protection(). For now we make it a bitmap so * that we can pass in multiple flags just like parameters. However * for now all the callers are only use one of the flags at the same * time. */ /* * Whether we should manually check if we can map individual PTEs writable, * because something (e.g., COW, uffd-wp) blocks that from happening for all * PTEs automatically in a writable mapping. */ #define MM_CP_TRY_CHANGE_WRITABLE (1UL << 0) /* Whether this protection change is for NUMA hints */ #define MM_CP_PROT_NUMA (1UL << 1) /* Whether this change is for write protecting */ #define MM_CP_UFFD_WP (1UL << 2) /* do wp */ #define MM_CP_UFFD_WP_RESOLVE (1UL << 3) /* Resolve wp */ #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) bool vma_needs_dirty_tracking(struct vm_area_struct *vma); bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) { /* * We want to check manually if we can change individual PTEs writable * if we can't do that automatically for all PTEs in a mapping. For * private mappings, that's always the case when we have write * permissions as we properly have to handle COW. */ if (vma->vm_flags & VM_SHARED) return vma_wants_writenotify(vma, vma->vm_page_prot); return !!(vma->vm_flags & VM_WRITE); } bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, pte_t pte); extern long change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long cp_flags); extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); /* * doesn't attempt to fault and will return short. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); static inline bool get_user_page_fast_only(unsigned long addr, unsigned int gup_flags, struct page **pagep) { return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1; } /* * per-process(per-mm_struct) statistics. */ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) { return percpu_counter_read_positive(&mm->rss_stat[member]); } void mm_trace_rss_stat(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { percpu_counter_add(&mm->rss_stat[member], value); mm_trace_rss_stat(mm, member); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { percpu_counter_inc(&mm->rss_stat[member]); mm_trace_rss_stat(mm, member); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { percpu_counter_dec(&mm->rss_stat[member]); mm_trace_rss_stat(mm, member); } /* Optimized variant when folio is already known not to be anon */ static inline int mm_counter_file(struct folio *folio) { if (folio_test_swapbacked(folio)) return MM_SHMEMPAGES; return MM_FILEPAGES; } static inline int mm_counter(struct folio *folio) { if (folio_test_anon(folio)) return MM_ANONPAGES; return mm_counter_file(folio); } static inline unsigned long get_mm_rss(struct mm_struct *mm) { return get_mm_counter(mm, MM_FILEPAGES) + get_mm_counter(mm, MM_ANONPAGES) + get_mm_counter(mm, MM_SHMEMPAGES); } static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) { return max(mm->hiwater_rss, get_mm_rss(mm)); } static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) { return max(mm->hiwater_vm, mm->total_vm); } static inline void update_hiwater_rss(struct mm_struct *mm) { unsigned long _rss = get_mm_rss(mm); if ((mm)->hiwater_rss < _rss) (mm)->hiwater_rss = _rss; } static inline void update_hiwater_vm(struct mm_struct *mm) { if (mm->hiwater_vm < mm->total_vm) mm->hiwater_vm = mm->total_vm; } static inline void reset_mm_hiwater_rss(struct mm_struct *mm) { mm->hiwater_rss = get_mm_rss(mm); } static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, struct mm_struct *mm) { unsigned long hiwater_rss = get_mm_hiwater_rss(mm); if (*maxrss < hiwater_rss) *maxrss = hiwater_rss; } #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_mkspecial(pte_t pte) { return pte; } #endif #ifndef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t pte) { return 0; } #endif extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pte_t *ptep; __cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl)); return ptep; } #ifdef __PAGETABLE_P4D_FOLDED static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return 0; } #else int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); #endif #if defined(__PAGETABLE_PUD_FOLDED) || !defined(CONFIG_MMU) static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return 0; } static inline void mm_inc_nr_puds(struct mm_struct *mm) {} static inline void mm_dec_nr_puds(struct mm_struct *mm) {} #else int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return 0; } static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif #ifdef CONFIG_MMU static inline void mm_pgtables_bytes_init(struct mm_struct *mm) { atomic_long_set(&mm->pgtables_bytes, 0); } static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return atomic_long_read(&mm->pgtables_bytes); } static inline void mm_inc_nr_ptes(struct mm_struct *mm) { atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_ptes(struct mm_struct *mm) { atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } #else static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {} static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return 0; } static inline void mm_inc_nr_ptes(struct mm_struct *mm) {} static inline void mm_dec_nr_ptes(struct mm_struct *mm) {} #endif int __pte_alloc(struct mm_struct *mm, pmd_t *pmd); int __pte_alloc_kernel(pmd_t *pmd); #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? NULL : p4d_offset(pgd, address); } static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } #endif /* CONFIG_MMU */ static inline struct ptdesc *virt_to_ptdesc(const void *x) { return page_ptdesc(virt_to_page(x)); } static inline void *ptdesc_to_virt(const struct ptdesc *pt) { return page_to_virt(ptdesc_page(pt)); } static inline void *ptdesc_address(const struct ptdesc *pt) { return folio_address(ptdesc_folio(pt)); } static inline bool pagetable_is_reserved(struct ptdesc *pt) { return folio_test_reserved(ptdesc_folio(pt)); } /** * pagetable_alloc - Allocate pagetables * @gfp: GFP flags * @order: desired pagetable order * * pagetable_alloc allocates memory for page tables as well as a page table * descriptor to describe that memory. * * Return: The ptdesc describing the allocated page tables. */ static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int order) { struct page *page = alloc_pages_noprof(gfp | __GFP_COMP, order); return page_ptdesc(page); } #define pagetable_alloc(...) alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__)) /** * pagetable_free - Free pagetables * @pt: The page table descriptor * * pagetable_free frees the memory of all page tables described by a page * table descriptor and the memory for the descriptor itself. */ static inline void pagetable_free(struct ptdesc *pt) { struct page *page = ptdesc_page(pt); __free_pages(page, compound_order(page)); } #if USE_SPLIT_PTE_PTLOCKS #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); bool ptlock_alloc(struct ptdesc *ptdesc); void ptlock_free(struct ptdesc *ptdesc); static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { return ptdesc->ptl; } #else /* ALLOC_SPLIT_PTLOCKS */ static inline void ptlock_cache_init(void) { } static inline bool ptlock_alloc(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) { } static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { return &ptdesc->ptl; } #endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } static inline bool ptlock_init(struct ptdesc *ptdesc) { /* * prep_new_page() initialize page->private (and therefore page->ptl) * with 0. Make sure nobody took it in use in between. * * It can happen if arch try to use slab for page table allocation: * slab code uses page->slab_cache, which share storage with page->ptl. */ VM_BUG_ON_PAGE(*(unsigned long *)&ptdesc->ptl, ptdesc_page(ptdesc)); if (!ptlock_alloc(ptdesc)) return false; spin_lock_init(ptlock_ptr(ptdesc)); return true; } #else /* !USE_SPLIT_PTE_PTLOCKS */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); if (!ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); ptlock_free(ptdesc); __folio_clear_pgtable(folio); lruvec_stat_sub_folio(folio, NR_PAGETABLE); } pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr) { return __pte_offset_map(pmd, addr, NULL); } pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp); static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp) { pte_t *pte; __cond_lock(*ptlp, pte = __pte_offset_map_lock(mm, pmd, addr, ptlp)); return pte; } pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp); #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ pte_unmap(pte); \ } while (0) #define pte_alloc(mm, pmd) (unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd)) #define pte_alloc_map(mm, pmd, address) \ (pte_alloc(mm, pmd) ? NULL : pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ (pte_alloc(mm, pmd) ? \ NULL : pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) #if USE_SPLIT_PMD_PTLOCKS static inline struct page *pmd_pgtable_page(pmd_t *pmd) { unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1); return virt_to_page((void *)((unsigned long) pmd & mask)); } static inline struct ptdesc *pmd_ptdesc(pmd_t *pmd) { return page_ptdesc(pmd_pgtable_page(pmd)); } static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_ptdesc(pmd)); } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE ptdesc->pmd_huge_pte = NULL; #endif return ptlock_init(ptdesc); } static inline void pmd_ptlock_free(struct ptdesc *ptdesc) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE VM_BUG_ON_PAGE(ptdesc->pmd_huge_pte, ptdesc_page(ptdesc)); #endif ptlock_free(ptdesc); } #define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte) #else static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void pmd_ptlock_free(struct ptdesc *ptdesc) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) #endif static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); return ptl; } static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); if (!pmd_ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } static inline void pagetable_pmd_dtor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); pmd_ptlock_free(ptdesc); __folio_clear_pgtable(folio); lruvec_stat_sub_folio(folio, NR_PAGETABLE); } /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be * considered ready to switch to split PUD locks yet; there may be places * which need to be converted from page_table_lock. */ static inline spinlock_t *pud_lockptr(struct mm_struct *mm, pud_t *pud) { return &mm->page_table_lock; } static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) { spinlock_t *ptl = pud_lockptr(mm, pud); spin_lock(ptl); return ptl; } static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); __folio_set_pgtable(folio); lruvec_stat_add_folio(folio, NR_PAGETABLE); } static inline void pagetable_pud_dtor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); __folio_clear_pgtable(folio); lruvec_stat_sub_folio(folio, NR_PAGETABLE); } extern void __init pagecache_init(void); extern void free_initmem(void); /* * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK) * into the buddy system. The freed pages will be poisoned with pattern * "poison" if it's within range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); extern void adjust_managed_page_count(struct page *page, long count); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid); /* Free the reserved page into the buddy system, so it gets managed. */ static inline void free_reserved_page(struct page *page) { if (mem_alloc_profiling_enabled()) { union codetag_ref *ref = get_page_tag_ref(page); if (ref) { set_codetag_empty(ref); put_page_tag_ref(ref); } } ClearPageReserved(page); init_page_count(page); __free_page(page); adjust_managed_page_count(page, 1); } #define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) { SetPageReserved(page); adjust_managed_page_count(page, -1); } static inline void free_reserved_ptdesc(struct ptdesc *pt) { free_reserved_page(ptdesc_page(pt)); } /* * Default method to free all the __init memory into the buddy system. * The freed pages will be poisoned with pattern "poison" if it's within * range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ static inline unsigned long free_initmem_default(int poison) { extern char __init_begin[], __init_end[]; return free_reserved_area(&__init_begin, &__init_end, poison, "unused kernel image (initmem)"); } static inline unsigned long get_num_physpages(void) { int nid; unsigned long phys_pages = 0; for_each_online_node(nid) phys_pages += node_present_pages(nid); return phys_pages; } /* * Using memblock node mappings, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in an * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid, MEMBLOCK_NONE) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); #ifndef CONFIG_NUMA static inline int early_pfn_to_nid(unsigned long pfn) { return 0; } #else /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif extern void mem_init(void); extern void __init mmap_init(void); extern void __show_mem(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); static inline void show_mem(void) { __show_mem(0, NULL, MAX_NR_ZONES - 1); } extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); extern __printf(3, 4) void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, struct rb_root_cached *root); void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, struct rb_root_cached *root); struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, unsigned long start, unsigned long last); #define vma_interval_tree_foreach(vma, root, start, last) \ for (vma = vma_interval_tree_iter_first(root, start, last); \ vma; vma = vma_interval_tree_iter_next(vma, start, last)) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root); struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct anon_vma_chain *anon_vma_interval_tree_iter_next( struct anon_vma_chain *node, unsigned long start, unsigned long last); #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node); #endif #define anon_vma_interval_tree_foreach(avc, root, start, last) \ for (avc = anon_vma_interval_tree_iter_first(root, start, last); \ avc; avc = anon_vma_interval_tree_iter_next(avc, start, last)) /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *next); extern int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); struct vm_area_struct *vma_modify(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long vm_flags, struct mempolicy *policy, struct vm_userfaultfd_ctx uffd_ctx, struct anon_vma_name *anon_name); /* We are about to modify the VMA's flags. */ static inline struct vm_area_struct *vma_modify_flags(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags) { return vma_modify(vmi, prev, vma, start, end, new_flags, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); } /* We are about to modify the VMA's flags and/or anon_name. */ static inline struct vm_area_struct *vma_modify_flags_name(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, struct anon_vma_name *new_name) { return vma_modify(vmi, prev, vma, start, end, new_flags, vma_policy(vma), vma->vm_userfaultfd_ctx, new_name); } /* We are about to modify the VMA's memory policy. */ static inline struct vm_area_struct *vma_modify_policy(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct mempolicy *new_pol) { return vma_modify(vmi, prev, vma, start, end, vma->vm_flags, new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma)); } /* We are about to modify the VMA's flags and/or uffd context. */ static inline struct vm_area_struct *vma_modify_flags_uffd(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, struct vm_userfaultfd_ctx new_ctx) { return vma_modify(vmi, prev, vma, start, end, new_flags, vma_policy(vma), new_ctx, anon_vma_name(vma)); } static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, unsigned long end_data, unsigned long start_data) { if (rlim < RLIM_INFINITY) { if (((new - start) + (end_data - start_data)) > rlim) return -ENOSPC; } return 0; } extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); extern int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); extern struct file *get_task_exe_file(struct task_struct *task); extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); extern bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm); extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, const struct vm_special_mapping *spec); /* This is an obsolete alternative to _install_special_mapping. */ extern int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, struct page **pages); unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); unsigned long __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); static inline unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return __get_unmapped_area(file, addr, len, pgoff, flags, 0); } extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU extern int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf, bool unlock); extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) { /* Ignore errors */ (void) __mm_populate(addr, len, 1); } #else static inline void mm_populate(unsigned long addr, unsigned long len) {} #endif /* This takes the mm semaphore itself */ extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); extern unsigned long __must_check vm_mmap(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); struct vm_unmapped_area_info { #define VM_UNMAPPED_AREA_TOPDOWN 1 unsigned long flags; unsigned long length; unsigned long low_limit; unsigned long high_limit; unsigned long align_mask; unsigned long align_offset; unsigned long start_gap; }; extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ extern void truncate_inode_pages(struct address_space *, loff_t); extern void truncate_inode_pages_range(struct address_space *, loff_t lstart, loff_t lend); extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ int expand_stack_locked(struct vm_area_struct *vma, unsigned long address); struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr); /* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ int expand_downwards(struct vm_area_struct *vma, unsigned long address); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); /* * Look up the first VMA which intersects the interval [start_addr, end_addr) * NULL if none. Assume start_addr < end_addr. */ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr); /** * vma_lookup() - Find a VMA at a specific address * @mm: The process address space. * @addr: The user address. * * Return: The vm_area_struct at the given address, %NULL otherwise. */ static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) { return mtree_load(&mm->mm_mt, addr); } static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) { if (vma->vm_flags & VM_GROWSDOWN) return stack_guard_gap; /* See reasoning around the VM_SHADOW_STACK definition */ if (vma->vm_flags & VM_SHADOW_STACK) return PAGE_SIZE; return 0; } static inline unsigned long vm_start_gap(struct vm_area_struct *vma) { unsigned long gap = stack_guard_start_gap(vma); unsigned long vm_start = vma->vm_start; vm_start -= gap; if (vm_start > vma->vm_start) vm_start = 0; return vm_start; } static inline unsigned long vm_end_gap(struct vm_area_struct *vma) { unsigned long vm_end = vma->vm_end; if (vma->vm_flags & VM_GROWSUP) { vm_end += stack_guard_gap; if (vm_end < vma->vm_end) vm_end = -PAGE_SIZE; } return vm_end; } static inline unsigned long vma_pages(struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) { struct vm_area_struct *vma = vma_lookup(mm, vm_start); if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end)) vma = NULL; return vma; } static inline bool range_in_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { return (vma && vma->vm_start <= start && end <= vma->vm_end); } #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); #else static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) { return __pgprot(0); } static inline void vma_set_page_prot(struct vm_area_struct *vma) { vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); } #endif void vma_set_file(struct vm_area_struct *vma, struct file *file); #ifdef CONFIG_NUMA_BALANCING unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long start, unsigned long end); #endif struct vm_area_struct *find_extend_vma_locked(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num); int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num); int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { int err = vm_insert_page(vma, addr, page); if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } #ifndef io_remap_pfn_range static inline int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot)); } #endif static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) return VM_FAULT_OOM; else if (err == -EHWPOISON) return VM_FAULT_HWPOISON; return VM_FAULT_SIGBUS; } /* * Convert errno to return value for ->page_mkwrite() calls. * * This should eventually be merged with vmf_error() above, but will need a * careful audit of all vmf_error() callers. */ static inline vm_fault_t vmf_fs_error(int err) { if (err == 0) return VM_FAULT_LOCKED; if (err == -EFAULT || err == -EAGAIN) return VM_FAULT_NOPAGE; if (err == -ENOMEM) return VM_FAULT_OOM; /* -ENOSPC, -EDQUOT, -EIO ... */ return VM_FAULT_SIGBUS; } struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags); static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) return -ENOMEM; if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT; if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; return 0; } /* * Indicates whether GUP can follow a PROT_NONE mapped page, or whether * a (NUMA hinting) fault is required. */ static inline bool gup_can_follow_protnone(struct vm_area_struct *vma, unsigned int flags) { /* * If callers don't want to honor NUMA hinting faults, no need to * determine if we would actually have to trigger a NUMA hinting fault. */ if (!(flags & FOLL_HONOR_NUMA_FAULT)) return true; /* * NUMA hinting faults don't apply in inaccessible (PROT_NONE) VMAs. * * Requiring a fault here even for inaccessible VMAs would mean that * FOLL_FORCE cannot make any progress, because handle_mm_fault() * refuses to process NUMA hinting faults in inaccessible VMAs. */ return !vma_is_accessible(vma); } typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); extern bool _page_poisoning_enabled_early; DECLARE_STATIC_KEY_FALSE(_page_poisoning_enabled); static inline bool page_poisoning_enabled(void) { return _page_poisoning_enabled_early; } /* * For use in fast paths after init_mem_debugging() has run, or when a * false negative result is not harmful when called too early. */ static inline bool page_poisoning_enabled_static(void) { return static_branch_unlikely(&_page_poisoning_enabled); } static inline void kernel_poison_pages(struct page *page, int numpages) { if (page_poisoning_enabled_static()) __kernel_poison_pages(page, numpages); } static inline void kernel_unpoison_pages(struct page *page, int numpages) { if (page_poisoning_enabled_static()) __kernel_unpoison_pages(page, numpages); } #else static inline bool page_poisoning_enabled(void) { return false; } static inline bool page_poisoning_enabled_static(void) { return false; } static inline void __kernel_poison_pages(struct page *page, int nunmpages) { } static inline void kernel_poison_pages(struct page *page, int numpages) { } static inline void kernel_unpoison_pages(struct page *page, int numpages) { } #endif DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc); static inline bool want_init_on_alloc(gfp_t flags) { if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, &init_on_alloc)) return true; return flags & __GFP_ZERO; } DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); static inline bool want_init_on_free(void) { return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, &init_on_free); } extern bool _debug_pagealloc_enabled_early; DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) { return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled_early; } /* * For use in fast paths after mem_debugging_and_hardening_init() has run, * or when a false negative result is not harmful when called too early. */ static inline bool debug_pagealloc_enabled_static(void) { if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) return false; return static_branch_unlikely(&_debug_pagealloc_enabled); } /* * To support DEBUG_PAGEALLOC architecture must ensure that * __kernel_map_pages() never fails */ extern void __kernel_map_pages(struct page *page, int numpages, int enable); #ifdef CONFIG_DEBUG_PAGEALLOC static inline void debug_pagealloc_map_pages(struct page *page, int numpages) { if (debug_pagealloc_enabled_static()) __kernel_map_pages(page, numpages, 1); } static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) { if (debug_pagealloc_enabled_static()) __kernel_map_pages(page, numpages, 0); } extern unsigned int _debug_guardpage_minorder; DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static inline unsigned int debug_guardpage_minorder(void) { return _debug_guardpage_minorder; } static inline bool debug_guardpage_enabled(void) { return static_branch_unlikely(&_debug_guardpage_enabled); } static inline bool page_is_guard(struct page *page) { if (!debug_guardpage_enabled()) return false; return PageGuard(page); } bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order) { if (!debug_guardpage_enabled()) return false; return __set_page_guard(zone, page, order); } void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order) { if (!debug_guardpage_enabled()) return; __clear_page_guard(zone, page, order); } #else /* CONFIG_DEBUG_PAGEALLOC */ static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {} static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {} static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } static inline bool page_is_guard(struct page *page) { return false; } static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order) {} #endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); extern int in_gate_area_no_mm(unsigned long addr); extern int in_gate_area(struct mm_struct *mm, unsigned long addr); #else static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { return NULL; } static inline int in_gate_area_no_mm(unsigned long addr) { return 0; } static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) { return 0; } #endif /* __HAVE_ARCH_GATE_AREA */ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); #ifdef CONFIG_SYSCTL extern int sysctl_drop_caches; int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); #endif void drop_slab(void); #ifndef CONFIG_MMU #define randomize_va_space 0 #else extern int randomize_va_space; #endif const char * arch_vma_name(struct vm_area_struct *vma); #ifdef CONFIG_MMU void print_vma_addr(char *prefix, unsigned long rip); #else static inline void print_vma_addr(char *prefix, unsigned long rip) { } #endif void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); void pmd_init(void *addr); void pud_init(void *addr); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, struct vmem_altmap *altmap, struct page *reuse); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); void vmemmap_set_pmd(pmd_t *pmd, void *p, int node, unsigned long addr, unsigned long next); int vmemmap_check_pmd(pmd_t *pmd, int node, unsigned long addr, unsigned long next); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate_hugepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { /* number of pfns from base where pfn_to_page() is valid */ if (altmap) return altmap->reserve + altmap->free; return 0; } static inline void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) { altmap->alloc -= nr_pfns; } #else 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) { } #endif #define VMEMMAP_RESERVE_NR 2 #ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { unsigned long nr_pages; unsigned long nr_vmemmap_pages; if (!pgmap || !is_power_of_2(sizeof(struct page))) return false; nr_pages = pgmap_vmemmap_nr(pgmap); nr_vmemmap_pages = ((nr_pages * sizeof(struct page)) >> PAGE_SHIFT); /* * For vmemmap optimization with DAX we need minimum 2 vmemmap * pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst */ return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR); } /* * If we don't have an architecture override, use the generic rule */ #ifndef vmemmap_can_optimize #define vmemmap_can_optimize __vmemmap_can_optimize #endif #else static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { return false; } #endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, MF_UNPOISON = 1 << 4, MF_SW_SIMULATED = 1 << 5, MF_NO_RETRY = 1 << 6, MF_MEM_PRE_REMOVE = 1 << 7, }; int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags); extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE /* * Sysfs entries for memory failure handling statistics. */ extern const struct attribute_group memory_failure_attr_group; extern void memory_failure_queue(unsigned long pfn, int flags); extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void num_poisoned_pages_inc(unsigned long pfn); void num_poisoned_pages_sub(unsigned long pfn, long i); struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { } static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { return 0; } static inline void num_poisoned_pages_inc(unsigned long pfn) { } static inline void num_poisoned_pages_sub(unsigned long pfn, long i) { } #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_KSM) void add_to_kill_ksm(struct task_struct *tsk, struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long ksm_addr); #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); #else static inline void memblk_nr_poison_inc(unsigned long pfn) { } static inline void memblk_nr_poison_sub(unsigned long pfn, long i) { } #endif #ifndef arch_memory_failure static inline int arch_memory_failure(unsigned long pfn, int flags) { return -ENXIO; } #endif #ifndef arch_is_platform_page static inline bool arch_is_platform_page(u64 paddr) { return false; } #endif /* * Error handlers for various types of pages. */ enum mf_result { MF_IGNORED, /* Error: cannot be handled */ MF_FAILED, /* Error: handling failed */ MF_DELAYED, /* Will be handled later */ MF_RECOVERED, /* Successfully recovered */ }; enum mf_action_page_type { MF_MSG_KERNEL, MF_MSG_KERNEL_HIGH_ORDER, MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, MF_MSG_HUGE, MF_MSG_FREE_HUGE, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, MF_MSG_DIRTY_MLOCKED_LRU, MF_MSG_CLEAN_MLOCKED_LRU, MF_MSG_DIRTY_UNEVICTABLE_LRU, MF_MSG_CLEAN_UNEVICTABLE_LRU, MF_MSG_DIRTY_LRU, MF_MSG_CLEAN_LRU, MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_UNKNOWN, }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); int copy_user_large_folio(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma); long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault); /** * vma_is_special_huge - Are transhuge page-table entries considered special? * @vma: Pointer to the struct vm_area_struct to consider * * Whether transhuge page-table entries are considered "special" following * the definition in vm_normal_page(). * * Return: true if transhuge page-table entries should be considered special, * false otherwise. */ static inline bool vma_is_special_huge(const struct vm_area_struct *vma) { return vma_is_dax(vma) || (vma->vm_file && (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if MAX_NUMNODES > 1 void __init setup_nr_node_ids(void); #else static inline void setup_nr_node_ids(void) {} #endif extern int memcmp_pages(struct page *page1, struct page *page2); static inline int pages_identical(struct page *page1, struct page *page2) { return !memcmp_pages(page1, page2); } #ifdef CONFIG_MAPPING_DIRTY_HELPERS unsigned long clean_record_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, pgoff_t bitmap_pgoff, unsigned long *bitmap, pgoff_t *start, pgoff_t *end); unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif extern int sysctl_nr_trim_pages; #ifdef CONFIG_PRINTK void mem_dump_obj(void *object); #else static inline void mem_dump_obj(void *object) {} #endif /** * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and * handle them. * @seals: the seals to check * @vma: the vma to operate on * * Check whether F_SEAL_WRITE or F_SEAL_FUTURE_WRITE are set; if so, do proper * check/handling on the vma flags. Return 0 if check pass, or <0 for errors. */ static inline int seal_check_write(int seals, struct vm_area_struct *vma) { if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { /* * New PROT_WRITE and MAP_SHARED mmaps are not allowed when * write seals are active. */ if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) return -EPERM; /* * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as * MAP_SHARED and read-only, take care to not allow mprotect to * revert protections on such mappings. Do this only for shared * mappings. For private mappings, don't need to mask * VM_MAYWRITE as we still want them to be COW-writable. */ if (vma->vm_flags & VM_SHARED) vm_flags_clear(vma, VM_MAYWRITE); } return 0; } #ifdef CONFIG_ANON_VMA_NAME int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name); #else static inline int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name) { return 0; } #endif #ifdef CONFIG_UNACCEPTED_MEMORY bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end); void accept_memory(phys_addr_t start, phys_addr_t end); #else static inline bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end) { return false; } static inline void accept_memory(phys_addr_t start, phys_addr_t end) { } #endif static inline bool pfn_is_unaccepted_memory(unsigned long pfn) { phys_addr_t paddr = pfn << PAGE_SHIFT; return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); } void vma_pgtable_walk_begin(struct vm_area_struct *vma); void vma_pgtable_walk_end(struct vm_area_struct *vma); #endif /* _LINUX_MM_H */ |
| 184 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ /** * DOC: Readahead Overview * * Readahead is used to read content into the page cache before it is * explicitly requested by the application. Readahead only ever * attempts to read folios that are not yet in the page cache. If a * folio is present but not up-to-date, readahead will not try to read * it. In that case a simple ->read_folio() will be requested. * * Readahead is triggered when an application read request (whether a * system call or a page fault) finds that the requested folio is not in * the page cache, or that it is in the page cache and has the * readahead flag set. This flag indicates that the folio was read * as part of a previous readahead request and now that it has been * accessed, it is time for the next readahead. * * Each readahead request is partly synchronous read, and partly async * readahead. This is reflected in the struct file_ra_state which * contains ->size being the total number of pages, and ->async_size * which is the number of pages in the async section. The readahead * flag will be set on the first folio in this async section to trigger * a subsequent readahead. Once a series of sequential reads has been * established, there should be no need for a synchronous component and * all readahead request will be fully asynchronous. * * When either of the triggers causes a readahead, three numbers need * to be determined: the start of the region to read, the size of the * region, and the size of the async tail. * * The start of the region is simply the first page address at or after * the accessed address, which is not currently populated in the page * cache. This is found with a simple search in the page cache. * * The size of the async tail is determined by subtracting the size that * was explicitly requested from the determined request size, unless * this would be less than zero - then zero is used. NOTE THIS * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. * * The size of the region is normally determined from the size of the * previous readahead which loaded the preceding pages. This may be * discovered from the struct file_ra_state for simple sequential reads, * or from examining the state of the page cache when multiple * sequential reads are interleaved. Specifically: where the readahead * was triggered by the readahead flag, the size of the previous * readahead is assumed to be the number of pages from the triggering * page to the start of the new readahead. In these cases, the size of * the previous readahead is scaled, often doubled, for the new * readahead, though see get_next_ra_size() for details. * * If the size of the previous read cannot be determined, the number of * preceding pages in the page cache is used to estimate the size of * a previous read. This estimate could easily be misled by random * reads being coincidentally adjacent, so it is ignored unless it is * larger than the current request, and it is not scaled up, unless it * is at the start of file. * * In general readahead is accelerated at the start of the file, as * reads from there are often sequential. There are other minor * adjustments to the readahead size in various special cases and these * are best discovered by reading the code. * * The above calculation, based on the previous readahead size, * determines the size of the readahead, to which any requested read * size may be added. * * Readahead requests are sent to the filesystem using the ->readahead() * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all * folios, but may fail to read any or all folios without causing an I/O * error. The page cache reading code will issue a ->read_folio() request * for any folio which ->readahead() did not read, and only an error * from this will be final. * * ->readahead() will generally call readahead_folio() repeatedly to get * each folio from those prepared for readahead. It may fail to read a * folio by: * * * not calling readahead_folio() sufficiently many times, effectively * ignoring some folios, as might be appropriate if the path to * storage is congested. * * * failing to actually submit a read request for a given folio, * possibly due to insufficient resources, or * * * getting an error during subsequent processing of a request. * * In the last two cases, the folio should be unlocked by the filesystem * to indicate that the read attempt has failed. In the first case the * folio will be unlocked by the VFS. * * Those folios not in the final ``async_size`` of the request should be * considered to be important and ->readahead() should not fail them due * to congestion or temporary resource unavailability, but should wait * for necessary resources (e.g. memory or indexing information) to * become available. Folios in the final ``async_size`` may be * considered less urgent and failure to read them is more acceptable. * In this case it is best to use filemap_remove_folio() to remove the * folios from the page cache as is automatically done for folios that * were not fetched with readahead_folio(). This will allow a * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using * ->read_folio() which may be less efficient. */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagemap.h> #include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) return; if (unlikely(rac->_workingset)) psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); /* * Clean up the remaining folios. The sizes in ->ra * may be used to size the next readahead, so make sure * they accurately reflect what happened. */ while ((folio = readahead_folio(rac)) != NULL) { unsigned long nr = folio_nr_pages(folio); folio_get(folio); rac->ra->size -= nr; if (rac->ra->async_size >= nr) { rac->ra->async_size -= nr; filemap_remove_folio(folio); } folio_unlock(folio); folio_put(folio); } } else { while ((folio = readahead_folio(rac)) != NULL) aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); if (unlikely(rac->_workingset)) psi_memstall_leave(&rac->_pflags); rac->_workingset = false; BUG_ON(readahead_count(rac)); } /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. * @nr_to_read: The number of pages to read. * @lookahead_size: Where to start the next readahead. * * This function is for filesystems to call when they want to start * readahead beyond a file's stated i_size. This is almost certainly * not the function you want to call. Use page_cache_async_readahead() * or page_cache_sync_readahead() instead. * * Context: File is referenced by caller. Mutexes may be held by caller. * May sleep, but will not reenter filesystem to reclaim memory. */ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long i; /* * Partway through the readahead operation, we will have added * locked pages to the page cache, but will not yet have submitted * them for I/O. Adding another page may need to allocate memory, * which can trigger memory reclaim. Telling the VM we're in * the middle of a filesystem operation will cause it to not * touch file-backed pages, preventing a deadlock. Most (all?) * filesystems already specify __GFP_NOFS in their mapping's * gfp_mask, but let's be explicit here. */ unsigned int nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); /* * Preallocate as many pages as we will need. */ for (i = 0; i < nr_to_read; i++) { struct folio *folio = xa_load(&mapping->i_pages, index + i); int ret; if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the * next batch. This page may be the one we would * have intended to mark as Readahead, but we don't * have a stable reference to this page, and it's * not worth getting one just for that. */ read_pages(ractl); ractl->_index++; i = ractl->_index + ractl->_nr_pages - index - 1; continue; } folio = filemap_alloc_folio(gfp_mask, 0); if (!folio) break; ret = filemap_add_folio(mapping, folio, index + i, gfp_mask); if (ret < 0) { folio_put(folio); if (ret == -ENOMEM) break; read_pages(ractl); ractl->_index++; i = ractl->_index + ractl->_nr_pages - index - 1; continue; } if (i == nr_to_read - lookahead_size) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages++; } /* * Now start the IO. We ignore I/O errors - if the folio is not * uptodate then the caller will launch read_folio again, and * will then handle the error. */ read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); /* * do_page_cache_ra() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ static void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct inode *inode = ractl->mapping->host; unsigned long index = readahead_index(ractl); loff_t isize = i_size_read(inode); pgoff_t end_index; /* The last page we want to read */ if (isize == 0) return; end_index = (isize - 1) >> PAGE_SHIFT; if (index > end_index) return; /* Don't read past the page containing the last byte of the file */ if (nr_to_read > end_index - index) nr_to_read = end_index - index + 1; page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages, index; if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ index = readahead_index(ractl); max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min_t(unsigned long, nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; ractl->_index = index; do_page_cache_ra(ractl, this_chunk, 0); index += this_chunk; nr_to_read -= this_chunk; } } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readhead. */ /* * Count contiguously cached pages from @index-1 to @index-@max, * this count is a conservative estimation of * - length of the sequential read sequence, or * - thrashing threshold in memory tight systems */ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t index, unsigned long max) { pgoff_t head; rcu_read_lock(); head = page_cache_prev_miss(mapping, index - 1, max); rcu_read_unlock(); return index - 1 - head; } /* * page cache context based readahead */ static int try_context_readahead(struct address_space *mapping, struct file_ra_state *ra, pgoff_t index, unsigned long req_size, unsigned long max) { pgoff_t size; size = count_history_pages(mapping, index, max); /* * not enough history pages: * it could be a random read */ if (size <= req_size) return 0; /* * starts from beginning of file: * it is a strong indication of long-run stream (or whole-file-read) */ if (size >= index) size *= 2; ra->start = index; ra->size = min(size + req_size, max); ra->async_size = 1; return 1; } static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; struct folio *folio = filemap_alloc_folio(gfp, order); if (!folio) return -ENOMEM; mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) { folio_put(folio); return err; } ractl->_nr_pages += 1UL << order; ractl->_workingset |= folio_test_workingset(folio); return 0; } void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra, unsigned int new_order) { struct address_space *mapping = ractl->mapping; pgoff_t index = readahead_index(ractl); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); if (!mapping_large_folio_support(mapping) || ra->size < 4) goto fallback; limit = min(limit, index + ra->size - 1); if (new_order < MAX_PAGECACHE_ORDER) { new_order += 2; new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); } /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); while (index <= limit) { unsigned int order = new_order; /* Align with smaller pages if needed */ if (index & ((1UL << order) - 1)) order = __ffs(index); /* Don't allocate pages past EOF */ while (index + (1UL << order) - 1 > limit) order--; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) break; index += 1UL << order; } if (index > limit) { ra->size += index - limit - 1; ra->async_size += index - limit - 1; } read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have * left some gaps. Let the regular readahead code take care of this * situation. */ if (!err) return; fallback: do_page_cache_ra(ractl, ra->size, ra->async_size); } /* * A minimal readahead algorithm for trivial sequential/random reads. */ static void ondemand_readahead(struct readahead_control *ractl, struct folio *folio, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); struct file_ra_state *ra = ractl->ra; unsigned long max_pages = ra->ra_pages; unsigned long add_pages; pgoff_t index = readahead_index(ractl); pgoff_t expected, prev_index; unsigned int order = folio ? folio_order(folio) : 0; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); /* * start of file */ if (!index) goto initial_readahead; /* * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ expected = round_down(ra->start + ra->size - ra->async_size, 1UL << order); if (index == expected || index == (ra->start + ra->size)) { ra->start += ra->size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; goto readit; } /* * Hit a marked folio without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ if (folio) { pgoff_t start; rcu_read_lock(); start = page_cache_next_miss(ractl->mapping, index + 1, max_pages); rcu_read_unlock(); if (!start || start - index > max_pages) return; ra->start = start; ra->size = start - index; /* old async_size */ ra->size += req_size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; goto readit; } /* * oversize read */ if (req_size > max_pages) goto initial_readahead; /* * sequential cache miss * trivial case: (index - prev_index) == 1 * unaligned reads: (index - prev_index) == 0 */ prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; if (index - prev_index <= 1UL) goto initial_readahead; /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ if (try_context_readahead(ractl->mapping, ra, index, req_size, max_pages)) goto readit; /* * standalone, small random read * Read as is, and do not pollute the readahead state. */ do_page_cache_ra(ractl, req_size, 0); return; initial_readahead: ra->start = index; ra->size = get_init_ra_size(req_size, max_pages); ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size; readit: /* * Will this read hit the readahead marker made by itself? * If so, trigger the readahead marker hit now, and merge * the resulted next readahead window into the current one. * Take care of maximum IO pages as above. */ if (index == ra->start && ra->size == ra->async_size) { add_pages = get_next_ra_size(ra, max_pages); if (ra->size + add_pages <= max_pages) { ra->async_size = add_pages; ra->size += add_pages; } else { ra->size = max_pages; ra->async_size = max_pages >> 1; } } ractl->_index = ra->start; page_cache_ra_order(ractl, ra, order); } void page_cache_sync_ra(struct readahead_control *ractl, unsigned long req_count) { bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ractl->ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; do_forced_ra = true; } /* be dumb */ if (do_forced_ra) { force_page_cache_ra(ractl, req_count); return; } ondemand_readahead(ractl, NULL, req_count); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct folio *folio, unsigned long req_count) { /* no readahead */ if (!ractl->ra->ra_pages) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (folio_test_writeback(folio)) return; folio_clear_readahead(folio); if (blk_cgroup_congested()) return; ondemand_readahead(ractl, folio, req_count); } EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { ssize_t ret; struct fd f; ret = -EBADF; f = fdget(fd); if (!f.file || !(f.file->f_mode & FMODE_READ)) goto out; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ ret = -EINVAL; if (!f.file->f_mapping || !f.file->f_mapping->a_ops || (!S_ISREG(file_inode(f.file)->i_mode) && !S_ISBLK(file_inode(f.file)->i_mode))) goto out; ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); out: fdput(f); return ret; } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD) COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count) { return ksys_readahead(fd, compat_arg_u64_glue(offset), count); } #endif /** * readahead_expand - Expand a readahead request * @ractl: The request to be expanded * @new_start: The revised start * @new_len: The revised size of the request * * Attempt to expand a readahead request outwards from the current size to the * specified size by inserting locked pages before and after the current window * to increase the size to the new window. This may involve the insertion of * THPs, in which case the window may get expanded even beyond what was * requested. * * The algorithm will stop if it encounters a conflicting page already in the * pagecache and leave a smaller expansion than requested. * * The caller must check for this by examining the revised @ractl object for a * different expansion than was requested. */ void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; pgoff_t new_index, new_nr_pages; gfp_t gfp_mask = readahead_gfp_mask(mapping); new_index = new_start / PAGE_SIZE; /* Expand the leading edge downwards */ while (ractl->_index > new_index) { unsigned long index = ractl->_index - 1; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = filemap_alloc_folio(gfp_mask, 0); if (!folio) return; if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages++; ractl->_index = folio->index; } new_len += new_start - readahead_pos(ractl); new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); /* Expand the trailing edge upwards */ while (ractl->_nr_pages < new_nr_pages) { unsigned long index = ractl->_index + ractl->_nr_pages; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = filemap_alloc_folio(gfp_mask, 0); if (!folio) return; if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages++; if (ra) { ra->size++; ra->async_size++; } } } EXPORT_SYMBOL(readahead_expand); |
| 311 146 24 298 131 5 11 5 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001 Intel Corp. * Copyright (c) 2001 Nokia, Inc. * * This file is part of the SCTP kernel implementation * * These are the state tables for the SCTP state machine. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Hui Huang <hui.huang@nokia.com> * Daisy Chang <daisyc@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> * Sridhar Samudrala <sri@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/skbuff.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> static const struct sctp_sm_table_entry primitive_event_table[SCTP_NUM_PRIMITIVE_TYPES][SCTP_STATE_NUM_STATES]; static const struct sctp_sm_table_entry other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES]; static const struct sctp_sm_table_entry timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES]; static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( struct net *net, enum sctp_cid cid, enum sctp_state state); static const struct sctp_sm_table_entry bug = { .fn = sctp_sf_bug, .name = "sctp_sf_bug" }; #define DO_LOOKUP(_max, _type, _table) \ ({ \ const struct sctp_sm_table_entry *rtn; \ \ if ((event_subtype._type > (_max))) { \ pr_warn("table %p possible attack: event %d exceeds max %d\n", \ _table, event_subtype._type, _max); \ rtn = &bug; \ } else \ rtn = &_table[event_subtype._type][(int)state]; \ \ rtn; \ }) const struct sctp_sm_table_entry *sctp_sm_lookup_event( struct net *net, enum sctp_event_type event_type, enum sctp_state state, union sctp_subtype event_subtype) { switch (event_type) { case SCTP_EVENT_T_CHUNK: return sctp_chunk_event_lookup(net, event_subtype.chunk, state); case SCTP_EVENT_T_TIMEOUT: return DO_LOOKUP(SCTP_EVENT_TIMEOUT_MAX, timeout, timeout_event_table); case SCTP_EVENT_T_OTHER: return DO_LOOKUP(SCTP_EVENT_OTHER_MAX, other, other_event_table); case SCTP_EVENT_T_PRIMITIVE: return DO_LOOKUP(SCTP_EVENT_PRIMITIVE_MAX, primitive, primitive_event_table); default: /* Yikes! We got an illegal event type. */ return &bug; } } #define TYPE_SCTP_FUNC(func) {.fn = func, .name = #func} #define TYPE_SCTP_DATA { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_data_6_2), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_data_6_2), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_data_fast_4_4), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_DATA */ #define TYPE_SCTP_INIT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1B_init), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_1_siminit), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_1_siminit), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_reshutack), \ } /* TYPE_SCTP_INIT */ #define TYPE_SCTP_INIT_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_3_initack), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1C_ack), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_INIT_ACK */ #define TYPE_SCTP_SACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_SACK */ #define TYPE_SCTP_HEARTBEAT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ /* This should not happen, but we are nice. */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ } /* TYPE_SCTP_HEARTBEAT */ #define TYPE_SCTP_HEARTBEAT_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_HEARTBEAT_ACK */ #define TYPE_SCTP_ABORT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_pdiscard), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_abort), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_abort), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_abort), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_pending_abort), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_sent_abort), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_abort), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_ack_sent_abort), \ } /* TYPE_SCTP_ABORT */ #define TYPE_SCTP_SHUTDOWN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown_ack), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shut_ctsn), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_SHUTDOWN */ #define TYPE_SCTP_SHUTDOWN_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_8_5_1_E_sa), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_8_5_1_E_sa), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_final), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_final), \ } /* TYPE_SCTP_SHUTDOWN_ACK */ #define TYPE_SCTP_ERROR { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_err), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_operr_notify), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_operr_notify), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_operr_notify), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ERROR */ #define TYPE_SCTP_COOKIE_ECHO { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1D_ce), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ } /* TYPE_SCTP_COOKIE_ECHO */ #define TYPE_SCTP_COOKIE_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1E_ca), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_COOKIE_ACK */ #define TYPE_SCTP_ECN_ECNE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ECN_ECNE */ #define TYPE_SCTP_ECN_CWR { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecn_cwr), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecn_cwr), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecn_cwr), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ECN_CWR */ #define TYPE_SCTP_SHUTDOWN_COMPLETE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_4_C), \ } /* TYPE_SCTP_SHUTDOWN_COMPLETE */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. * * For base protocol (RFC 2960). */ static const struct sctp_sm_table_entry chunk_event_table[SCTP_NUM_BASE_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_DATA, TYPE_SCTP_INIT, TYPE_SCTP_INIT_ACK, TYPE_SCTP_SACK, TYPE_SCTP_HEARTBEAT, TYPE_SCTP_HEARTBEAT_ACK, TYPE_SCTP_ABORT, TYPE_SCTP_SHUTDOWN, TYPE_SCTP_SHUTDOWN_ACK, TYPE_SCTP_ERROR, TYPE_SCTP_COOKIE_ECHO, TYPE_SCTP_COOKIE_ACK, TYPE_SCTP_ECN_ECNE, TYPE_SCTP_ECN_CWR, TYPE_SCTP_SHUTDOWN_COMPLETE, }; /* state_fn_t chunk_event_table[][] */ #define TYPE_SCTP_ASCONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ASCONF */ #define TYPE_SCTP_ASCONF_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ASCONF_ACK */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry addip_chunk_event_table[SCTP_NUM_ADDIP_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_ASCONF, TYPE_SCTP_ASCONF_ACK, }; /*state_fn_t addip_chunk_event_table[][] */ #define TYPE_SCTP_FWD_TSN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_fwd_tsn), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_fwd_tsn), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_fwd_tsn_fast), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_FWD_TSN */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry prsctp_chunk_event_table[SCTP_NUM_PRSCTP_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_FWD_TSN, }; /*state_fn_t prsctp_chunk_event_table[][] */ #define TYPE_SCTP_RECONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_reconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_reconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_RECONF */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry reconf_chunk_event_table[SCTP_NUM_RECONF_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_RECONF, }; /*state_fn_t reconf_chunk_event_table[][] */ #define TYPE_SCTP_AUTH { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ } /* TYPE_SCTP_AUTH */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_AUTH, }; /*state_fn_t auth_chunk_event_table[][] */ static const struct sctp_sm_table_entry pad_chunk_event_table[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_COOKIE_WAIT */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_COOKIE_ECHOED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_ESTABLISHED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_PENDING */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_SENT */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_RECEIVED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_ACK_SENT */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), }; /* chunk pad */ static const struct sctp_sm_table_entry chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ TYPE_SCTP_FUNC(sctp_sf_ootb), /* SCTP_STATE_COOKIE_WAIT */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_COOKIE_ECHOED */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_ESTABLISHED */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_PENDING */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_SENT */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_RECEIVED */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_ACK_SENT */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), }; /* chunk unknown */ #define TYPE_SCTP_PRIMITIVE_ASSOCIATE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asoc), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ } /* TYPE_SCTP_PRIMITIVE_ASSOCIATE */ #define TYPE_SCTP_PRIMITIVE_SHUTDOWN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_prm_shutdown), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_prm_shutdown),\ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_prm_shutdown), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ } /* TYPE_SCTP_PRIMITIVE_SHUTDOWN */ #define TYPE_SCTP_PRIMITIVE_ABORT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_prm_abort), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_prm_abort), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_prm_abort), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_pending_prm_abort), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_sent_prm_abort), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_prm_abort), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_ack_sent_prm_abort), \ } /* TYPE_SCTP_PRIMITIVE_ABORT */ #define TYPE_SCTP_PRIMITIVE_SEND { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_send), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_send), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_send), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ } /* TYPE_SCTP_PRIMITIVE_SEND */ #define TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ } /* TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT */ #define TYPE_SCTP_PRIMITIVE_ASCONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ } /* TYPE_SCTP_PRIMITIVE_ASCONF */ #define TYPE_SCTP_PRIMITIVE_RECONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ } /* TYPE_SCTP_PRIMITIVE_RECONF */ /* The primary index for this table is the primitive type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry primitive_event_table[SCTP_NUM_PRIMITIVE_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_PRIMITIVE_ASSOCIATE, TYPE_SCTP_PRIMITIVE_SHUTDOWN, TYPE_SCTP_PRIMITIVE_ABORT, TYPE_SCTP_PRIMITIVE_SEND, TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT, TYPE_SCTP_PRIMITIVE_ASCONF, TYPE_SCTP_PRIMITIVE_RECONF, }; #define TYPE_SCTP_OTHER_NO_PENDING_TSN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_no_pending_tsn), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_start_shutdown), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown_ack), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ } #define TYPE_SCTP_OTHER_ICMP_PROTO_UNREACH { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_icmp_abort), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ } static const struct sctp_sm_table_entry other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_OTHER_NO_PENDING_TSN, TYPE_SCTP_OTHER_ICMP_PROTO_UNREACH, }; #define TYPE_SCTP_EVENT_TIMEOUT_NONE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T1_COOKIE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_t1_cookie_timer_expire), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T1_INIT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_t1_init_timer_expire), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T2_SHUTDOWN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t2_timer_expire), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t2_timer_expire), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T3_RTX { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T4_RTO { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_t4_timer_expire), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_sendbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_sendbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_sendbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_SACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_2_sack), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_2_sack), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_2_sack), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_autoclose_timer_expire), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_RECONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_send_reconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_PROBE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_send_probe), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } static const struct sctp_sm_table_entry timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_EVENT_TIMEOUT_NONE, TYPE_SCTP_EVENT_TIMEOUT_T1_COOKIE, TYPE_SCTP_EVENT_TIMEOUT_T1_INIT, TYPE_SCTP_EVENT_TIMEOUT_T2_SHUTDOWN, TYPE_SCTP_EVENT_TIMEOUT_T3_RTX, TYPE_SCTP_EVENT_TIMEOUT_T4_RTO, TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD, TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT, TYPE_SCTP_EVENT_TIMEOUT_RECONF, TYPE_SCTP_EVENT_TIMEOUT_PROBE, TYPE_SCTP_EVENT_TIMEOUT_SACK, TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE, }; static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( struct net *net, enum sctp_cid cid, enum sctp_state state) { if (state > SCTP_STATE_MAX) return &bug; if (cid == SCTP_CID_I_DATA) cid = SCTP_CID_DATA; if (cid <= SCTP_CID_BASE_MAX) return &chunk_event_table[cid][state]; switch ((u16)cid) { case SCTP_CID_FWD_TSN: case SCTP_CID_I_FWD_TSN: return &prsctp_chunk_event_table[0][state]; case SCTP_CID_ASCONF: return &addip_chunk_event_table[0][state]; case SCTP_CID_ASCONF_ACK: return &addip_chunk_event_table[1][state]; case SCTP_CID_RECONF: return &reconf_chunk_event_table[0][state]; case SCTP_CID_AUTH: return &auth_chunk_event_table[0][state]; case SCTP_CID_PAD: return &pad_chunk_event_table[state]; } return &chunk_event_table_unknown[state]; } |
| 14 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2007, 2008, 2009 Siemens AG * * Written by: * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> */ #ifndef __NET_CFG802154_H #define __NET_CFG802154_H #include <linux/ieee802154.h> #include <linux/netdevice.h> #include <linux/spinlock.h> #include <linux/bug.h> #include <net/nl802154.h> struct wpan_phy; struct wpan_phy_cca; struct cfg802154_scan_request; struct cfg802154_beacon_request; struct ieee802154_addr; #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL struct ieee802154_llsec_device_key; struct ieee802154_llsec_seclevel; struct ieee802154_llsec_params; struct ieee802154_llsec_device; struct ieee802154_llsec_table; struct ieee802154_llsec_key_id; struct ieee802154_llsec_key; #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ struct cfg802154_ops { struct net_device * (*add_virtual_intf_deprecated)(struct wpan_phy *wpan_phy, const char *name, unsigned char name_assign_type, int type); void (*del_virtual_intf_deprecated)(struct wpan_phy *wpan_phy, struct net_device *dev); int (*suspend)(struct wpan_phy *wpan_phy); int (*resume)(struct wpan_phy *wpan_phy); int (*add_virtual_intf)(struct wpan_phy *wpan_phy, const char *name, unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr); int (*del_virtual_intf)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev); int (*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel); int (*set_cca_mode)(struct wpan_phy *wpan_phy, const struct wpan_phy_cca *cca); int (*set_cca_ed_level)(struct wpan_phy *wpan_phy, s32 ed_level); int (*set_tx_power)(struct wpan_phy *wpan_phy, s32 power); int (*set_pan_id)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 pan_id); int (*set_short_addr)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 short_addr); int (*set_backoff_exponent)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, u8 min_be, u8 max_be); int (*set_max_csma_backoffs)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, u8 max_csma_backoffs); int (*set_max_frame_retries)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, s8 max_frame_retries); int (*set_lbt_mode)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, bool mode); int (*set_ackreq_default)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, bool ackreq); int (*trigger_scan)(struct wpan_phy *wpan_phy, struct cfg802154_scan_request *request); int (*abort_scan)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev); int (*send_beacons)(struct wpan_phy *wpan_phy, struct cfg802154_beacon_request *request); int (*stop_beacons)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev); int (*associate)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, struct ieee802154_addr *coord); int (*disassociate)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, struct ieee802154_addr *target); #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL void (*get_llsec_table)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, struct ieee802154_llsec_table **table); void (*lock_llsec_table)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev); void (*unlock_llsec_table)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev); /* TODO remove locking/get table callbacks, this is part of the * nl802154 interface and should be accessible from ieee802154 layer. */ int (*get_llsec_params)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, struct ieee802154_llsec_params *params); int (*set_llsec_params)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_params *params, int changed); int (*add_llsec_key)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_key_id *id, const struct ieee802154_llsec_key *key); int (*del_llsec_key)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_key_id *id); int (*add_seclevel)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_seclevel *sl); int (*del_seclevel)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_seclevel *sl); int (*add_device)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_device *dev); int (*del_device)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le64 extended_addr); int (*add_devkey)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le64 extended_addr, const struct ieee802154_llsec_device_key *key); int (*del_devkey)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le64 extended_addr, const struct ieee802154_llsec_device_key *key); #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ }; static inline bool wpan_phy_supported_bool(bool b, enum nl802154_supported_bool_states st) { switch (st) { case NL802154_SUPPORTED_BOOL_TRUE: return b; case NL802154_SUPPORTED_BOOL_FALSE: return !b; case NL802154_SUPPORTED_BOOL_BOTH: return true; default: WARN_ON(1); } return false; } struct wpan_phy_supported { u32 channels[IEEE802154_MAX_PAGE + 1], cca_modes, cca_opts, iftypes; enum nl802154_supported_bool_states lbt; u8 min_minbe, max_minbe, min_maxbe, max_maxbe, min_csma_backoffs, max_csma_backoffs; s8 min_frame_retries, max_frame_retries; size_t tx_powers_size, cca_ed_levels_size; const s32 *tx_powers, *cca_ed_levels; }; struct wpan_phy_cca { enum nl802154_cca_modes mode; enum nl802154_cca_opts opt; }; static inline bool wpan_phy_cca_cmp(const struct wpan_phy_cca *a, const struct wpan_phy_cca *b) { if (a->mode != b->mode) return false; if (a->mode == NL802154_CCA_ENERGY_CARRIER) return a->opt == b->opt; return true; } /** * enum wpan_phy_flags - WPAN PHY state flags * @WPAN_PHY_FLAG_TXPOWER: Indicates that transceiver will support * transmit power setting. * @WPAN_PHY_FLAG_CCA_ED_LEVEL: Indicates that transceiver will support cca ed * level setting. * @WPAN_PHY_FLAG_CCA_MODE: Indicates that transceiver will support cca mode * setting. * @WPAN_PHY_FLAG_STATE_QUEUE_STOPPED: Indicates that the transmit queue was * temporarily stopped. * @WPAN_PHY_FLAG_DATAGRAMS_ONLY: Indicates that transceiver is only able to * send/receive datagrams. */ enum wpan_phy_flags { WPAN_PHY_FLAG_TXPOWER = BIT(1), WPAN_PHY_FLAG_CCA_ED_LEVEL = BIT(2), WPAN_PHY_FLAG_CCA_MODE = BIT(3), WPAN_PHY_FLAG_STATE_QUEUE_STOPPED = BIT(4), WPAN_PHY_FLAG_DATAGRAMS_ONLY = BIT(5), }; struct wpan_phy { /* If multiple wpan_phys are registered and you're handed e.g. * a regular netdev with assigned ieee802154_ptr, you won't * know whether it points to a wpan_phy your driver has registered * or not. Assign this to something global to your driver to * help determine whether you own this wpan_phy or not. */ const void *privid; unsigned long flags; /* * This is a PIB according to 802.15.4-2011. * We do not provide timing-related variables, as they * aren't used outside of driver */ u8 current_channel; u8 current_page; struct wpan_phy_supported supported; /* current transmit_power in mBm */ s32 transmit_power; struct wpan_phy_cca cca; __le64 perm_extended_addr; /* current cca ed threshold in mBm */ s32 cca_ed_level; /* PHY depended MAC PIB values */ /* 802.15.4 acronym: Tdsym in nsec */ u32 symbol_duration; /* lifs and sifs periods timing */ u16 lifs_period; u16 sifs_period; struct device dev; /* the network namespace this phy lives in currently */ possible_net_t _net; /* Transmission monitoring and control */ spinlock_t queue_lock; atomic_t ongoing_txs; atomic_t hold_txs; wait_queue_head_t sync_txq; /* Current filtering level on reception. * Only allowed to be changed if phy is not operational. */ enum ieee802154_filtering_level filtering; char priv[] __aligned(NETDEV_ALIGN); }; static inline struct net *wpan_phy_net(struct wpan_phy *wpan_phy) { return read_pnet(&wpan_phy->_net); } static inline void wpan_phy_net_set(struct wpan_phy *wpan_phy, struct net *net) { write_pnet(&wpan_phy->_net, net); } static inline bool ieee802154_chan_is_valid(struct wpan_phy *phy, u8 page, u8 channel) { if (page > IEEE802154_MAX_PAGE || channel > IEEE802154_MAX_CHANNEL || !(phy->supported.channels[page] & BIT(channel))) return false; return true; } /** * struct ieee802154_addr - IEEE802.15.4 device address * @mode: Address mode from frame header. Can be one of: * - @IEEE802154_ADDR_NONE * - @IEEE802154_ADDR_SHORT * - @IEEE802154_ADDR_LONG * @pan_id: The PAN ID this address belongs to * @short_addr: address if @mode is @IEEE802154_ADDR_SHORT * @extended_addr: address if @mode is @IEEE802154_ADDR_LONG */ struct ieee802154_addr { u8 mode; __le16 pan_id; union { __le16 short_addr; __le64 extended_addr; }; }; /** * struct ieee802154_coord_desc - Coordinator descriptor * @addr: PAN ID and coordinator address * @page: page this coordinator is using * @channel: channel this coordinator is using * @superframe_spec: SuperFrame specification as received * @link_quality: link quality indicator at which the beacon was received * @gts_permit: the coordinator accepts GTS requests */ struct ieee802154_coord_desc { struct ieee802154_addr addr; u8 page; u8 channel; u16 superframe_spec; u8 link_quality; bool gts_permit; }; /** * struct ieee802154_pan_device - PAN device information * @pan_id: the PAN ID of this device * @mode: the preferred mode to reach the device * @short_addr: the short address of this device * @extended_addr: the extended address of this device * @node: the list node */ struct ieee802154_pan_device { __le16 pan_id; u8 mode; __le16 short_addr; __le64 extended_addr; struct list_head node; }; /** * struct cfg802154_scan_request - Scan request * * @type: type of scan to be performed * @page: page on which to perform the scan * @channels: channels in te %page to be scanned * @duration: time spent on each channel, calculated with: * aBaseSuperframeDuration * (2 ^ duration + 1) * @wpan_dev: the wpan device on which to perform the scan * @wpan_phy: the wpan phy on which to perform the scan */ struct cfg802154_scan_request { enum nl802154_scan_types type; u8 page; u32 channels; u8 duration; struct wpan_dev *wpan_dev; struct wpan_phy *wpan_phy; }; /** * struct cfg802154_beacon_request - Beacon request descriptor * * @interval: interval n between sendings, in multiple order of the super frame * duration: aBaseSuperframeDuration * (2^n) unless the interval * order is greater or equal to 15, in this case beacons won't be * passively sent out at a fixed rate but instead inform the device * that it should answer beacon requests as part of active scan * procedures * @wpan_dev: the concerned wpan device * @wpan_phy: the wpan phy this was for */ struct cfg802154_beacon_request { u8 interval; struct wpan_dev *wpan_dev; struct wpan_phy *wpan_phy; }; /** * struct cfg802154_mac_pkt - MAC packet descriptor (beacon/command) * @node: MAC packets to process list member * @skb: the received sk_buff * @sdata: the interface on which @skb was received * @page: page configuration when @skb was received * @channel: channel configuration when @skb was received */ struct cfg802154_mac_pkt { struct list_head node; struct sk_buff *skb; struct ieee802154_sub_if_data *sdata; u8 page; u8 channel; }; struct ieee802154_llsec_key_id { u8 mode; u8 id; union { struct ieee802154_addr device_addr; __le32 short_source; __le64 extended_source; }; }; #define IEEE802154_LLSEC_KEY_SIZE 16 struct ieee802154_llsec_key { u8 frame_types; u32 cmd_frame_ids; /* TODO replace with NL802154_KEY_SIZE */ u8 key[IEEE802154_LLSEC_KEY_SIZE]; }; struct ieee802154_llsec_key_entry { struct list_head list; struct rcu_head rcu; struct ieee802154_llsec_key_id id; struct ieee802154_llsec_key *key; }; struct ieee802154_llsec_params { bool enabled; __be32 frame_counter; u8 out_level; struct ieee802154_llsec_key_id out_key; __le64 default_key_source; __le16 pan_id; __le64 hwaddr; __le64 coord_hwaddr; __le16 coord_shortaddr; }; struct ieee802154_llsec_table { struct list_head keys; struct list_head devices; struct list_head security_levels; }; struct ieee802154_llsec_seclevel { struct list_head list; u8 frame_type; u8 cmd_frame_id; bool device_override; u32 sec_levels; }; struct ieee802154_llsec_device { struct list_head list; __le16 pan_id; __le16 short_addr; __le64 hwaddr; u32 frame_counter; bool seclevel_exempt; u8 key_mode; struct list_head keys; }; struct ieee802154_llsec_device_key { struct list_head list; struct ieee802154_llsec_key_id key_id; u32 frame_counter; }; struct wpan_dev_header_ops { /* TODO create callback currently assumes ieee802154_mac_cb inside * skb->cb. This should be changed to give these information as * parameter. */ int (*create)(struct sk_buff *skb, struct net_device *dev, const struct ieee802154_addr *daddr, const struct ieee802154_addr *saddr, unsigned int len); }; struct wpan_dev { struct wpan_phy *wpan_phy; int iftype; /* the remainder of this struct should be private to cfg802154 */ struct list_head list; struct net_device *netdev; const struct wpan_dev_header_ops *header_ops; /* lowpan interface, set when the wpan_dev belongs to one lowpan_dev */ struct net_device *lowpan_dev; u32 identifier; /* MAC PIB */ __le16 pan_id; __le16 short_addr; __le64 extended_addr; /* MAC BSN field */ atomic_t bsn; /* MAC DSN field */ atomic_t dsn; u8 min_be; u8 max_be; u8 csma_retries; s8 frame_retries; bool lbt; /* fallback for acknowledgment bit setting */ bool ackreq; /* Associations */ struct mutex association_lock; struct ieee802154_pan_device *parent; struct list_head children; unsigned int max_associations; unsigned int nchildren; }; #define to_phy(_dev) container_of(_dev, struct wpan_phy, dev) #if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN) static inline int wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, const struct ieee802154_addr *daddr, const struct ieee802154_addr *saddr, unsigned int len) { struct wpan_dev *wpan_dev = dev->ieee802154_ptr; return wpan_dev->header_ops->create(skb, dev, daddr, saddr, len); } #endif struct wpan_phy * wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size); static inline void wpan_phy_set_dev(struct wpan_phy *phy, struct device *dev) { phy->dev.parent = dev; } int wpan_phy_register(struct wpan_phy *phy); void wpan_phy_unregister(struct wpan_phy *phy); void wpan_phy_free(struct wpan_phy *phy); /* Same semantics as for class_for_each_device */ int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data), void *data); static inline void *wpan_phy_priv(struct wpan_phy *phy) { BUG_ON(!phy); return &phy->priv; } struct wpan_phy *wpan_phy_find(const char *str); static inline void wpan_phy_put(struct wpan_phy *phy) { put_device(&phy->dev); } static inline const char *wpan_phy_name(struct wpan_phy *phy) { return dev_name(&phy->dev); } void ieee802154_configure_durations(struct wpan_phy *phy, unsigned int page, unsigned int channel); /** * cfg802154_device_is_associated - Checks whether we are associated to any device * @wpan_dev: the wpan device * @return: true if we are associated */ bool cfg802154_device_is_associated(struct wpan_dev *wpan_dev); /** * cfg802154_device_is_parent - Checks if a device is our coordinator * @wpan_dev: the wpan device * @target: the expected parent * @return: true if @target is our coordinator */ bool cfg802154_device_is_parent(struct wpan_dev *wpan_dev, struct ieee802154_addr *target); /** * cfg802154_device_is_child - Checks whether a device is associated to us * @wpan_dev: the wpan device * @target: the expected child * @return: the PAN device */ struct ieee802154_pan_device * cfg802154_device_is_child(struct wpan_dev *wpan_dev, struct ieee802154_addr *target); /** * cfg802154_set_max_associations - Limit the number of future associations * @wpan_dev: the wpan device * @max: the maximum number of devices we accept to associate * @return: the old maximum value */ unsigned int cfg802154_set_max_associations(struct wpan_dev *wpan_dev, unsigned int max); /** * cfg802154_get_free_short_addr - Get a free address among the known devices * @wpan_dev: the wpan device * @return: a random short address expectedly unused on our PAN */ __le16 cfg802154_get_free_short_addr(struct wpan_dev *wpan_dev); #endif /* __NET_CFG802154_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Rewritten and vastly simplified by Rusty Russell for in-kernel * module loader: * Copyright 2002 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation */ #ifndef _LINUX_KALLSYMS_H #define _LINUX_KALLSYMS_H #include <linux/errno.h> #include <linux/buildid.h> #include <linux/kernel.h> #include <linux/stddef.h> #include <linux/mm.h> #include <linux/module.h> #include <asm/sections.h> #define KSYM_NAME_LEN 512 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s %s]") + \ (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + \ (BUILD_ID_SIZE_MAX * 2) + 1) struct cred; struct module; static inline int is_kernel_text(unsigned long addr) { if (__is_kernel_text(addr)) return 1; return in_gate_area_no_mm(addr); } static inline int is_kernel(unsigned long addr) { if (__is_kernel(addr)) return 1; return in_gate_area_no_mm(addr); } static inline int is_ksym_addr(unsigned long addr) { if (IS_ENABLED(CONFIG_KALLSYMS_ALL)) return is_kernel(addr); return is_kernel_text(addr) || is_kernel_inittext(addr); } static inline void *dereference_symbol_descriptor(void *ptr) { #ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS struct module *mod; ptr = dereference_kernel_function_descriptor(ptr); if (is_ksym_addr((unsigned long)ptr)) return ptr; preempt_disable(); mod = __module_address((unsigned long)ptr); preempt_enable(); if (mod) ptr = dereference_module_function_descriptor(mod, ptr); #endif return ptr; } /* How and when do we show kallsyms values? */ extern bool kallsyms_show_value(const struct cred *cred); #ifdef CONFIG_KALLSYMS unsigned long kallsyms_sym_address(int idx); int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), void *data); int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), const char *name, void *data); /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); extern int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset); /* Lookup an address. modname is set to NULL if it's in the kernel. */ const char *kallsyms_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, char *namebuf); /* Look up a kernel symbol and return it in a text buffer. */ extern int sprint_symbol(char *buffer, unsigned long address); extern int sprint_symbol_build_id(char *buffer, unsigned long address); extern int sprint_symbol_no_offset(char *buffer, unsigned long address); extern int sprint_backtrace(char *buffer, unsigned long address); extern int sprint_backtrace_build_id(char *buffer, unsigned long address); int lookup_symbol_name(unsigned long addr, char *symname); #else /* !CONFIG_KALLSYMS */ static inline unsigned long kallsyms_lookup_name(const char *name) { return 0; } static inline int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) { return 0; } static inline const char *kallsyms_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, char *namebuf) { return NULL; } static inline int sprint_symbol(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int sprint_symbol_build_id(char *buffer, unsigned long address) { *buffer = '\0'; return 0; } static inline int sprint_symbol_no_offset(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int sprint_backtrace(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int sprint_backtrace_build_id(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int lookup_symbol_name(unsigned long addr, char *symname) { return -ERANGE; } static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), void *data) { return -EOPNOTSUPP; } static inline int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), const char *name, void *data) { return -EOPNOTSUPP; } #endif /*CONFIG_KALLSYMS*/ static inline void print_ip_sym(const char *loglvl, unsigned long ip) { printk("%s[<%px>] %pS\n", loglvl, (void *) ip, (void *) ip); } #endif /*_LINUX_KALLSYMS_H*/ |
| 3107 3104 3105 3106 3101 3103 3101 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 | // SPDX-License-Identifier: GPL-2.0 /* * SHA1 routine optimized to do word accesses rather than byte accesses, * and to avoid unnecessary copies into the context array. * * This was based on the git SHA1 implementation. */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/module.h> #include <linux/bitops.h> #include <linux/string.h> #include <crypto/sha1.h> #include <asm/unaligned.h> /* * If you have 32 registers or more, the compiler can (and should) * try to change the array[] accesses into registers. However, on * machines with less than ~25 registers, that won't really work, * and at least gcc will make an unholy mess of it. * * So to avoid that mess which just slows things down, we force * the stores to memory to actually happen (we might be better off * with a 'W(t)=(val);asm("":"+m" (W(t))' there instead, as * suggested by Artur Skawina - that will also make gcc unable to * try to do the silly "optimize away loads" part because it won't * see what the value will be). * * Ben Herrenschmidt reports that on PPC, the C version comes close * to the optimized asm with this (ie on PPC you don't want that * 'volatile', since there are lots of registers). * * On ARM we get the best code generation by forcing a full memory barrier * between each SHA_ROUND, otherwise gcc happily get wild with spilling and * the stack frame size simply explode and performance goes down the drain. */ #ifdef CONFIG_X86 #define setW(x, val) (*(volatile __u32 *)&W(x) = (val)) #elif defined(CONFIG_ARM) #define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0) #else #define setW(x, val) (W(x) = (val)) #endif /* This "rolls" over the 512-bit array */ #define W(x) (array[(x)&15]) /* * Where do we get the source from? The first 16 iterations get it from * the input data, the next mix it from the 512-bit array. */ #define SHA_SRC(t) get_unaligned_be32((__u32 *)data + t) #define SHA_MIX(t) rol32(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1) #define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \ __u32 TEMP = input(t); setW(t, TEMP); \ E += TEMP + rol32(A,5) + (fn) + (constant); \ B = ror32(B, 2); \ TEMP = E; E = D; D = C; C = B; B = A; A = TEMP; } while (0) #define T_0_15(t, A, B, C, D, E) SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E ) #define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E ) #define T_20_39(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1, A, B, C, D, E ) #define T_40_59(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc, A, B, C, D, E ) #define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0xca62c1d6, A, B, C, D, E ) /** * sha1_transform - single block SHA1 transform (deprecated) * * @digest: 160 bit digest to update * @data: 512 bits of data to hash * @array: 16 words of workspace (see note) * * This function executes SHA-1's internal compression function. It updates the * 160-bit internal state (@digest) with a single 512-bit data block (@data). * * Don't use this function. SHA-1 is no longer considered secure. And even if * you do have to use SHA-1, this isn't the correct way to hash something with * SHA-1 as this doesn't handle padding and finalization. * * Note: If the hash is security sensitive, the caller should be sure * to clear the workspace. This is left to the caller to avoid * unnecessary clears between chained hashing operations. */ void sha1_transform(__u32 *digest, const char *data, __u32 *array) { __u32 A, B, C, D, E; unsigned int i = 0; A = digest[0]; B = digest[1]; C = digest[2]; D = digest[3]; E = digest[4]; /* Round 1 - iterations 0-16 take their input from 'data' */ for (; i < 16; ++i) T_0_15(i, A, B, C, D, E); /* Round 1 - tail. Input from 512-bit mixing array */ for (; i < 20; ++i) T_16_19(i, A, B, C, D, E); /* Round 2 */ for (; i < 40; ++i) T_20_39(i, A, B, C, D, E); /* Round 3 */ for (; i < 60; ++i) T_40_59(i, A, B, C, D, E); /* Round 4 */ for (; i < 80; ++i) T_60_79(i, A, B, C, D, E); digest[0] += A; digest[1] += B; digest[2] += C; digest[3] += D; digest[4] += E; } EXPORT_SYMBOL(sha1_transform); /** * sha1_init - initialize the vectors for a SHA1 digest * @buf: vector to initialize */ void sha1_init(__u32 *buf) { buf[0] = 0x67452301; buf[1] = 0xefcdab89; buf[2] = 0x98badcfe; buf[3] = 0x10325476; buf[4] = 0xc3d2e1f0; } EXPORT_SYMBOL(sha1_init); MODULE_LICENSE("GPL"); |
| 13 1 1 3 8 8 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_choke.c CHOKE scheduler * * Copyright (c) 2011 Stephen Hemminger <shemminger@vyatta.com> * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com> */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/inet_ecn.h> #include <net/red.h> #include <net/flow_dissector.h> /* CHOKe stateless AQM for fair bandwidth allocation ================================================= CHOKe (CHOose and Keep for responsive flows, CHOose and Kill for unresponsive flows) is a variant of RED that penalizes misbehaving flows but maintains no flow state. The difference from RED is an additional step during the enqueuing process. If average queue size is over the low threshold (qmin), a packet is chosen at random from the queue. If both the new and chosen packet are from the same flow, both are dropped. Unlike RED, CHOKe is not really a "classful" qdisc because it needs to access packets in queue randomly. It has a minimal class interface to allow overriding the builtin flow classifier with filters. Source: R. Pan, B. Prabhakar, and K. Psounis, "CHOKe, A Stateless Active Queue Management Scheme for Approximating Fair Bandwidth Allocation", IEEE INFOCOM, 2000. A. Tang, J. Wang, S. Low, "Understanding CHOKe: Throughput and Spatial Characteristics", IEEE/ACM Transactions on Networking, 2004 */ /* Upper bound on size of sk_buff table (packets) */ #define CHOKE_MAX_QUEUE (128*1024 - 1) struct choke_sched_data { /* Parameters */ u32 limit; unsigned char flags; struct red_parms parms; /* Variables */ struct red_vars vars; struct { u32 prob_drop; /* Early probability drops */ u32 prob_mark; /* Early probability marks */ u32 forced_drop; /* Forced drops, qavg > max_thresh */ u32 forced_mark; /* Forced marks, qavg > max_thresh */ u32 pdrop; /* Drops due to queue limits */ u32 matched; /* Drops to flow match */ } stats; unsigned int head; unsigned int tail; unsigned int tab_mask; /* size - 1 */ struct sk_buff **tab; }; /* number of elements in queue including holes */ static unsigned int choke_len(const struct choke_sched_data *q) { return (q->tail - q->head) & q->tab_mask; } /* Is ECN parameter configured */ static int use_ecn(const struct choke_sched_data *q) { return q->flags & TC_RED_ECN; } /* Should packets over max just be dropped (versus marked) */ static int use_harddrop(const struct choke_sched_data *q) { return q->flags & TC_RED_HARDDROP; } /* Move head pointer forward to skip over holes */ static void choke_zap_head_holes(struct choke_sched_data *q) { do { q->head = (q->head + 1) & q->tab_mask; if (q->head == q->tail) break; } while (q->tab[q->head] == NULL); } /* Move tail pointer backwards to reuse holes */ static void choke_zap_tail_holes(struct choke_sched_data *q) { do { q->tail = (q->tail - 1) & q->tab_mask; if (q->head == q->tail) break; } while (q->tab[q->tail] == NULL); } /* Drop packet from queue array by creating a "hole" */ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx, struct sk_buff **to_free) { struct choke_sched_data *q = qdisc_priv(sch); struct sk_buff *skb = q->tab[idx]; q->tab[idx] = NULL; if (idx == q->head) choke_zap_head_holes(q); if (idx == q->tail) choke_zap_tail_holes(q); qdisc_qstats_backlog_dec(sch, skb); qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_drop(skb, sch, to_free); --sch->q.qlen; } struct choke_skb_cb { u8 keys_valid; struct flow_keys_digest keys; }; static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb) { qdisc_cb_private_validate(skb, sizeof(struct choke_skb_cb)); return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data; } /* * Compare flow of two packets * Returns true only if source and destination address and port match. * false for special cases */ static bool choke_match_flow(struct sk_buff *skb1, struct sk_buff *skb2) { struct flow_keys temp; if (skb1->protocol != skb2->protocol) return false; if (!choke_skb_cb(skb1)->keys_valid) { choke_skb_cb(skb1)->keys_valid = 1; skb_flow_dissect_flow_keys(skb1, &temp, 0); make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp); } if (!choke_skb_cb(skb2)->keys_valid) { choke_skb_cb(skb2)->keys_valid = 1; skb_flow_dissect_flow_keys(skb2, &temp, 0); make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp); } return !memcmp(&choke_skb_cb(skb1)->keys, &choke_skb_cb(skb2)->keys, sizeof(choke_skb_cb(skb1)->keys)); } /* * Select a packet at random from queue * HACK: since queue can have holes from previous deletion; retry several * times to find a random skb but then just give up and return the head * Will return NULL if queue is empty (q->head == q->tail) */ static struct sk_buff *choke_peek_random(const struct choke_sched_data *q, unsigned int *pidx) { struct sk_buff *skb; int retrys = 3; do { *pidx = (q->head + get_random_u32_below(choke_len(q))) & q->tab_mask; skb = q->tab[*pidx]; if (skb) return skb; } while (--retrys > 0); return q->tab[*pidx = q->head]; } /* * Compare new packet with random packet in queue * returns true if matched and sets *pidx */ static bool choke_match_random(const struct choke_sched_data *q, struct sk_buff *nskb, unsigned int *pidx) { struct sk_buff *oskb; if (q->head == q->tail) return false; oskb = choke_peek_random(q, pidx); return choke_match_flow(oskb, nskb); } static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct choke_sched_data *q = qdisc_priv(sch); const struct red_parms *p = &q->parms; choke_skb_cb(skb)->keys_valid = 0; /* Compute average queue usage (see RED) */ q->vars.qavg = red_calc_qavg(p, &q->vars, sch->q.qlen); if (red_is_idling(&q->vars)) red_end_of_idle_period(&q->vars); /* Is queue small? */ if (q->vars.qavg <= p->qth_min) q->vars.qcount = -1; else { unsigned int idx; /* Draw a packet at random from queue and compare flow */ if (choke_match_random(q, skb, &idx)) { q->stats.matched++; choke_drop_by_idx(sch, idx, to_free); goto congestion_drop; } /* Queue is large, always mark/drop */ if (q->vars.qavg > p->qth_max) { q->vars.qcount = -1; qdisc_qstats_overlimit(sch); if (use_harddrop(q) || !use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.forced_drop++; goto congestion_drop; } q->stats.forced_mark++; } else if (++q->vars.qcount) { if (red_mark_probability(p, &q->vars, q->vars.qavg)) { q->vars.qcount = 0; q->vars.qR = red_random(p); qdisc_qstats_overlimit(sch); if (!use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.prob_drop++; goto congestion_drop; } q->stats.prob_mark++; } } else q->vars.qR = red_random(p); } /* Admit new packet */ if (sch->q.qlen < q->limit) { q->tab[q->tail] = skb; q->tail = (q->tail + 1) & q->tab_mask; ++sch->q.qlen; qdisc_qstats_backlog_inc(sch, skb); return NET_XMIT_SUCCESS; } q->stats.pdrop++; return qdisc_drop(skb, sch, to_free); congestion_drop: qdisc_drop(skb, sch, to_free); return NET_XMIT_CN; } static struct sk_buff *choke_dequeue(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; if (q->head == q->tail) { if (!red_is_idling(&q->vars)) red_start_of_idle_period(&q->vars); return NULL; } skb = q->tab[q->head]; q->tab[q->head] = NULL; choke_zap_head_holes(q); --sch->q.qlen; qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); return skb; } static void choke_reset(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); while (q->head != q->tail) { struct sk_buff *skb = q->tab[q->head]; q->head = (q->head + 1) & q->tab_mask; if (!skb) continue; rtnl_qdisc_drop(skb, sch); } if (q->tab) memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; red_restart(&q->vars); } static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = { [TCA_CHOKE_PARMS] = { .len = sizeof(struct tc_red_qopt) }, [TCA_CHOKE_STAB] = { .len = RED_STAB_SIZE }, [TCA_CHOKE_MAX_P] = { .type = NLA_U32 }, }; static void choke_free(void *addr) { kvfree(addr); } static int choke_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct choke_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CHOKE_MAX + 1]; const struct tc_red_qopt *ctl; int err; struct sk_buff **old = NULL; unsigned int mask; u32 max_P; u8 *stab; if (opt == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_CHOKE_MAX, opt, choke_policy, NULL); if (err < 0) return err; if (tb[TCA_CHOKE_PARMS] == NULL || tb[TCA_CHOKE_STAB] == NULL) return -EINVAL; max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0; ctl = nla_data(tb[TCA_CHOKE_PARMS]); stab = nla_data(tb[TCA_CHOKE_STAB]); if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) return -EINVAL; if (ctl->limit > CHOKE_MAX_QUEUE) return -EINVAL; mask = roundup_pow_of_two(ctl->limit + 1) - 1; if (mask != q->tab_mask) { struct sk_buff **ntab; ntab = kvcalloc(mask + 1, sizeof(struct sk_buff *), GFP_KERNEL); if (!ntab) return -ENOMEM; sch_tree_lock(sch); old = q->tab; if (old) { unsigned int oqlen = sch->q.qlen, tail = 0; unsigned dropped = 0; while (q->head != q->tail) { struct sk_buff *skb = q->tab[q->head]; q->head = (q->head + 1) & q->tab_mask; if (!skb) continue; if (tail < mask) { ntab[tail++] = skb; continue; } dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); --sch->q.qlen; rtnl_qdisc_drop(skb, sch); } qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped); q->head = 0; q->tail = tail; } q->tab_mask = mask; q->tab = ntab; } else sch_tree_lock(sch); WRITE_ONCE(q->flags, ctl->flags); WRITE_ONCE(q->limit, ctl->limit); red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, stab, max_P); red_set_vars(&q->vars); if (q->head == q->tail) red_end_of_idle_period(&q->vars); sch_tree_unlock(sch); choke_free(old); return 0; } static int choke_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { return choke_change(sch, opt, extack); } static int choke_dump(struct Qdisc *sch, struct sk_buff *skb) { struct choke_sched_data *q = qdisc_priv(sch); u8 Wlog = READ_ONCE(q->parms.Wlog); struct nlattr *opts = NULL; struct tc_red_qopt opt = { .limit = READ_ONCE(q->limit), .flags = READ_ONCE(q->flags), .qth_min = READ_ONCE(q->parms.qth_min) >> Wlog, .qth_max = READ_ONCE(q->parms.qth_max) >> Wlog, .Wlog = Wlog, .Plog = READ_ONCE(q->parms.Plog), .Scell_log = READ_ONCE(q->parms.Scell_log), }; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt) || nla_put_u32(skb, TCA_CHOKE_MAX_P, READ_ONCE(q->parms.max_P))) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: nla_nest_cancel(skb, opts); return -EMSGSIZE; } static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct choke_sched_data *q = qdisc_priv(sch); struct tc_choke_xstats st = { .early = q->stats.prob_drop + q->stats.forced_drop, .marked = q->stats.prob_mark + q->stats.forced_mark, .pdrop = q->stats.pdrop, .matched = q->stats.matched, }; return gnet_stats_copy_app(d, &st, sizeof(st)); } static void choke_destroy(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); choke_free(q->tab); } static struct sk_buff *choke_peek_head(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); return (q->head != q->tail) ? q->tab[q->head] : NULL; } static struct Qdisc_ops choke_qdisc_ops __read_mostly = { .id = "choke", .priv_size = sizeof(struct choke_sched_data), .enqueue = choke_enqueue, .dequeue = choke_dequeue, .peek = choke_peek_head, .init = choke_init, .destroy = choke_destroy, .reset = choke_reset, .change = choke_change, .dump = choke_dump, .dump_stats = choke_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("choke"); static int __init choke_module_init(void) { return register_qdisc(&choke_qdisc_ops); } static void __exit choke_module_exit(void) { unregister_qdisc(&choke_qdisc_ops); } module_init(choke_module_init) module_exit(choke_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Choose and keep responsive flows scheduler"); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ebtable_nat * * Authors: * Bart De Schuymer <bdschuym@pandora.be> * * April, 2002 * */ #include <linux/netfilter_bridge/ebtables.h> #include <uapi/linux/netfilter_bridge.h> #include <linux/module.h> #define NAT_VALID_HOOKS ((1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_OUT) | \ (1 << NF_BR_POST_ROUTING)) static struct ebt_entries initial_chains[] = { { .name = "PREROUTING", .policy = EBT_ACCEPT, }, { .name = "OUTPUT", .policy = EBT_ACCEPT, }, { .name = "POSTROUTING", .policy = EBT_ACCEPT, } }; static struct ebt_replace_kernel initial_table = { .name = "nat", .valid_hooks = NAT_VALID_HOOKS, .entries_size = 3 * sizeof(struct ebt_entries), .hook_entry = { [NF_BR_PRE_ROUTING] = &initial_chains[0], [NF_BR_LOCAL_OUT] = &initial_chains[1], [NF_BR_POST_ROUTING] = &initial_chains[2], }, .entries = (char *)initial_chains, }; static const struct ebt_table frame_nat = { .name = "nat", .table = &initial_table, .valid_hooks = NAT_VALID_HOOKS, .me = THIS_MODULE, }; static const struct nf_hook_ops ebt_ops_nat[] = { { .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_NAT_DST_OTHER, }, { .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, .priority = NF_BR_PRI_NAT_SRC, }, { .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_NAT_DST_BRIDGED, }, }; static int frame_nat_table_init(struct net *net) { return ebt_register_table(net, &frame_nat, ebt_ops_nat); } static void __net_exit frame_nat_net_pre_exit(struct net *net) { ebt_unregister_table_pre_exit(net, "nat"); } static void __net_exit frame_nat_net_exit(struct net *net) { ebt_unregister_table(net, "nat"); } static struct pernet_operations frame_nat_net_ops = { .exit = frame_nat_net_exit, .pre_exit = frame_nat_net_pre_exit, }; static int __init ebtable_nat_init(void) { int ret = ebt_register_template(&frame_nat, frame_nat_table_init); if (ret) return ret; ret = register_pernet_subsys(&frame_nat_net_ops); if (ret) { ebt_unregister_template(&frame_nat); return ret; } return ret; } static void __exit ebtable_nat_fini(void) { unregister_pernet_subsys(&frame_nat_net_ops); ebt_unregister_template(&frame_nat); } module_init(ebtable_nat_init); module_exit(ebtable_nat_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ebtables legacy stateless nat table"); |
| 11 11 11 11 11 11 11 11 7 3 11 12 490 489 489 490 1447 1448 1096 5 214 5 17 15 71 24 47 44 1 1 4 202 202 202 202 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/tracepoint-defs.h> struct folio_batch; /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_NOLOCKDEP) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) /* * Different from WARN_ON_ONCE(), no warning will be issued * when we specify __GFP_NOWARN. */ #define WARN_ON_ONCE_GFP(cond, gfp) ({ \ static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ __warned = true; \ WARN_ON(1); \ } \ unlikely(__ret_warn_once); \ }) void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ #define ENTIRELY_MAPPED 0x800000 #define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. * * Don't use this function outside of debugging code. */ static inline int folio_nr_pages_mapped(const struct folio *folio) { return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } /* * Retrieve the first entry of a folio based on a provided entry within the * folio. We cannot rely on folio->swap as there is no guarantee that it has * been initialized. Used for calling arch_swap_restore() */ static inline swp_entry_t folio_swap(swp_entry_t entry, const struct folio *folio) { swp_entry_t swap = { .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), }; return swap; } static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ typedef int __bitwise fpb_t; /* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */ #define FPB_IGNORE_DIRTY ((__force fpb_t)BIT(0)) /* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */ #define FPB_IGNORE_SOFT_DIRTY ((__force fpb_t)BIT(1)) static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) { if (flags & FPB_IGNORE_DIRTY) pte = pte_mkclean(pte); if (likely(flags & FPB_IGNORE_SOFT_DIRTY)) pte = pte_clear_soft_dirty(pte); return pte_wrprotect(pte_mkold(pte)); } /** * folio_pte_batch - detect a PTE batch for a large folio * @folio: The large folio to detect a PTE batch for. * @addr: The user virtual address the first page is mapped at. * @start_ptep: Page table pointer for the first entry. * @pte: Page table entry for the first page. * @max_nr: The maximum number of table entries to consider. * @flags: Flags to modify the PTE batch semantics. * @any_writable: Optional pointer to indicate whether any entry except the * first one is writable. * @any_young: Optional pointer to indicate whether any entry except the * first one is young. * @any_dirty: Optional pointer to indicate whether any entry except the * first one is dirty. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio. * * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, * the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and * soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY). * * start_ptep must map any page of the folio. max_nr must be at least one and * must be limited by the caller so scanning cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, bool *any_writable, bool *any_young, bool *any_dirty) { unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; bool writable, young, dirty; int nr; if (any_writable) *any_writable = false; if (any_young) *any_young = false; if (any_dirty) *any_dirty = false; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); nr = pte_batch_hint(start_ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = start_ptep + nr; while (ptep < end_ptep) { pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); if (any_young) young = !!pte_young(pte); if (any_dirty) dirty = !!pte_dirty(pte); pte = __pte_batch_clear_ignored(pte, flags); if (!pte_same(pte, expected_pte)) break; /* * Stop immediately once we reached the end of the folio. In * corner cases the next PFN might fall into a different * folio. */ if (pte_pfn(pte) >= folio_end_pfn) break; if (any_writable) *any_writable |= writable; if (any_young) *any_young |= young; if (any_dirty) *any_dirty |= dirty; nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, nr); ptep += nr; } return min(ptep - start_ptep, max_nr); } /** * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * * Increments the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_next_swp_offset(pte_t pte) { swp_entry_t entry = pte_to_swp_entry(pte); pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), (swp_offset(entry) + 1))); if (pte_swp_soft_dirty(pte)) new = pte_swp_mksoft_dirty(new); if (pte_swp_exclusive(pte)) new = pte_swp_mkexclusive(new); if (pte_swp_uffd_wp(pte)) new = pte_swp_mkuffd_wp(new); return new; } /** * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries * @start_ptep: Page table pointer for the first entry. * @max_nr: The maximum number of table entries to consider. * @pte: Page table entry for the first entry. * * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs * containing swap entries all with consecutive offsets and targeting the same * swap type, all with matching swp pte bits. * * max_nr must be at least one and must be limited by the caller so scanning * cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) { pte_t expected_pte = pte_next_swp_offset(pte); const pte_t *end_ptep = start_ptep + max_nr; pte_t *ptep = start_ptep + 1; VM_WARN_ON(max_nr < 1); VM_WARN_ON(!is_swap_pte(pte)); VM_WARN_ON(non_swap_entry(pte_to_swp_entry(pte))); while (ptep < end_ptep) { pte = ptep_get(ptep); if (!pte_same(pte, expected_pte)) break; expected_pte = pte_next_swp_offset(expected_pte); ptep++; } return ptep - start_ptep; } #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) { pg_data_t *pgdat = folio_pgdat(folio); int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); if (nr_throttled) __acct_reclaim_writeback(pgdat, folio, nr_throttled); } static inline void wake_throttle_isolated(pg_data_t *pgdat) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; if (waitqueue_active(wqh)) wake_up(wqh); } vm_fault_t vmf_anon_prepare(struct vm_fault *vmf); vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); void deactivate_file_folio(struct folio *folio); void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling, bool mm_wr_locked); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); struct zap_details; void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *, unsigned int order); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index); force_page_cache_ra(&ractl, nr_to_read); } unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); /** * folio_evictable - Test whether a folio is evictable. * @folio: The folio to test. * * Test whether @folio is evictable -- i.e., should be placed on * active/inactive lists vs unevictable list. * * Reasons folio might not be evictable: * 1. folio's mapping marked unevictable * 2. One of the pages in the folio is part of an mlocked VMA */ static inline bool folio_evictable(struct folio *folio) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(folio_mapping(folio)) && !folio_test_mlocked(folio); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } /* * Return true if a folio needs ->release_folio() calling upon it. */ static inline bool folio_needs_release(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); return folio_has_private(folio) || (mapping && mapping_release_always(mapping)); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ bool isolate_lru_page(struct page *page); bool folio_isolate_lru(struct folio *folio); void putback_lru_page(struct page *page); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); /* * in mm/rmap.c: */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ #define K(x) ((x) << (PAGE_SHIFT-10)) extern char * const zone_names[MAX_NR_ZONES]; /* perform sanity checks on struct pages being allocated or freed */ DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); extern int min_free_kbytes; void setup_per_zone_wmarks(void); void calculate_min_free_kbytes(void); int __meminit init_per_zone_wmark_min(void); void page_alloc_sysctl_init(void); /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) /* * This function checks whether a page is free && is the buddy * we can coalesce a page and its buddy if * (a) the buddy is not in a hole (check before calling!) && * (b) the buddy is in the buddy system && * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * * For recording whether a page is in the buddy system, we set PageBuddy. * Setting, clearing, and testing PageBuddy is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline bool page_is_buddy(struct page *page, struct page *buddy, unsigned int order) { if (!page_is_guard(buddy) && !PageBuddy(buddy)) return false; if (buddy_order(buddy) != order) return false; /* * zone check is done late to avoid uselessly calculating * zone/node ids for pages that could never merge. */ if (page_zone_id(page) != page_zone_id(buddy)) return false; VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return true; } /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } /* * Find the buddy of @page and validate it. * @page: The input page * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the * function is used in the performance-critical __free_one_page(). * @order: The order of the page * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to * page_to_pfn(). * * The found buddy can be a non PageBuddy, out of @page's zone, or its order is * not the same as @page. The validation is necessary before use it. * * Return: the found buddy page or NULL if not found. */ static inline struct page *find_buddy_page_pfn(struct page *page, unsigned long pfn, unsigned int order, unsigned long *buddy_pfn) { unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order); struct page *buddy; buddy = page + (__buddy_pfn - pfn); if (buddy_pfn) *buddy_pfn = __buddy_pfn; if (page_is_buddy(page, buddy, order)) return buddy; return NULL; } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } void set_zone_contiguous(struct zone *zone); static inline void clear_zone_contiguous(struct zone *zone) { zone->contiguous = false; } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); /* * This will have no effect, other than possibly generating a warning, if the * caller passes in a non-large folio. */ static inline void folio_set_order(struct folio *folio, unsigned int order) { if (WARN_ON_ONCE(!order || !folio_test_large(folio))) return; folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; #ifdef CONFIG_64BIT folio->_folio_nr_pages = 1U << order; #endif } void folio_undo_large_rmappable(struct folio *folio); static inline struct folio *page_rmappable_folio(struct page *page) { struct folio *folio = (struct folio *)page; if (folio && folio_test_large(folio)) folio_set_large_rmappable(folio); return folio; } static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; folio_set_order(folio, order); atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_entire_mapcount, -1); atomic_set(&folio->_nr_pages_mapped, 0); atomic_set(&folio->_pincount, 0); if (order > 1) INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) { struct page *p = head + tail_idx; p->mapping = TAIL_MAPPING; set_compound_head(p, head); set_page_private(p, 0); } extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; void free_unref_page(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); extern void zone_pcp_init(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int); #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ /* * Acts as an in/out parameter to page isolation for migration. * isolate_migratepages uses it as a search base. * isolate_migratepages_block will update the value to the next pfn * after the last isolated one. */ unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock contention */ bool finish_pageblock; /* Scan the remainder of a pageblock. Used * when there are potentially transient * isolation or migration failures to * ensure forward progress. */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long start, unsigned long end, int migratetype); /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); #endif /* CONFIG_COMPACTION || CONFIG_CMA */ int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } /* * These three helpers classifies VMAs for virtual memory accounting. */ /* * Executable code area - executable, not writable, not stack */ static inline bool is_exec_mapping(vm_flags_t flags) { return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; } /* * Stack area (including shadow stacks) * * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: * do_mmap() forbids all other combinations. */ static inline bool is_stack_mapping(vm_flags_t flags) { return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK); } /* * Data area - private, writable, not stack */ static inline bool is_data_mapping(vm_flags_t flags) { return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; } /* mm/util.c */ struct anon_vma *folio_anon_vma(struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); /* * NOTE: This function can't tell whether the folio is "fully mapped" in the * range. * "fully mapped" means all the pages of folio is associated with the page * table of range while this function just check whether the folio range is * within the range [start, end). Function caller needs to do page table * check if it cares about the page table association. * * Typical usage (like mlock or madvise) is: * Caller knows at least 1 page of folio is associated with page table of VMA * and the range [start, end) is intersect with the VMA range. Caller wants * to know whether the folio is fully associated with the range. It calls * this function to check whether the folio is in the range first. Then checks * the page table to know whether the folio is fully mapped to the range. */ static inline bool folio_within_range(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end) { pgoff_t pgoff, addr; unsigned long vma_pglen = vma_pages(vma); VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); if (start > end) return false; if (start < vma->vm_start) start = vma->vm_start; if (end > vma->vm_end) end = vma->vm_end; pgoff = folio_pgoff(folio); /* if folio start address is not in vma range */ if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) return false; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); return !(addr < start || end - addr < folio_size(folio)); } static inline bool folio_within_vma(struct folio *folio, struct vm_area_struct *vma) { return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); } /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, * under page table lock for the pte/pmd being added or removed. * * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at * the end of folio_remove_rmap_*(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. * 1) VM_IO check prevents migration from double-counting during mlock. * 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED * is never left set on a VM_SPECIAL vma, there is an interval while * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * munlock if the function is called. Ideally, we should only * do munlock if any page of folio is unmapped from VMA and * cause folio not fully mapped to VMA. * * But it's not easy to confirm that's the situation. So we * always munlock the folio and page reclaim will correct it * if it's wrong. */ if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } void mlock_new_folio(struct folio *folio); bool need_mlock_drain(int cpu); void mlock_drain_local(void); void mlock_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /** * vma_address - Find the virtual address a page range is mapped at * @vma: The vma which maps this object. * @pgoff: The page offset within its object. * @nr_pages: The number of pages to consider. * * If any page in this range is mapped by this VMA, return the first address * where any of these pages appear. Otherwise, return -EFAULT. */ static inline unsigned long vma_address(struct vm_area_struct *vma, pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. */ static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw) { struct vm_area_struct *vma = pvmw->vma; pgoff_t pgoff; unsigned long address; /* Common case, plus ->pgoff is invalid for KSM */ if (pvmw->nr_pages == 1) return pvmw->address + PAGE_SIZE; pgoff = pvmw->pgoff + pvmw->nr_pages; address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); release_fault_lock(vmf); } return fpin; } #else /* !CONFIG_MMU */ static inline void unmap_mapping_folio(struct folio *folio) { } static inline void mlock_new_folio(struct folio *folio) { } static inline bool need_mlock_drain(int cpu) { return false; } static inline void mlock_drain_local(void) { } static inline void mlock_drain_remote(int cpu) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } #endif /* !CONFIG_MMU */ /* Memory initialisation debug and verification */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT DECLARE_STATIC_KEY_TRUE(deferred_pages); bool __init deferred_grow_zone(struct zone *zone, unsigned int order); #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); extern int find_next_best_node(int node, nodemask_t *used_node_mask); #else static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } static inline int find_next_best_node(int node, nodemask_t *used_node_mask) { return NUMA_NO_NODE; } #endif /* * mm/memory-failure.c */ void shake_folio(struct folio *folio); extern int hwpoison_filter(struct page *p); extern u32 hwpoison_filter_dev_major; extern u32 hwpoison_filter_dev_minor; extern u64 hwpoison_filter_flags_mask; extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); unsigned long reclaim_pages(struct list_head *folio_list); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access * to 25% of the min watermark or * 62.5% if __GFP_HIGH is set. */ #define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50% * of the min watermark. */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */ #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ /* Flags that allow allocations below the min watermark. */ #define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM) enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags pagetype_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; static inline bool is_migrate_highatomic(enum migratetype migratetype) { return migratetype == MIGRATE_HIGHATOMIC; } void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; enum migrate_reason reason; }; /* * mm/filemap.c */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size); /* * mm/vmalloc.c */ #ifdef CONFIG_MMU void __init vmalloc_init(void); int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); #else static inline void vmalloc_init(void) { } static inline int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { return -EINVAL; } #endif int __must_check __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); int numa_migrate_prep(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int page_nid, int *flags); void free_zone_device_folio(struct folio *folio); int migrate_device_coherent_page(struct page *page); /* * mm/gup.c */ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags); int __must_check try_grab_page(struct page *page, unsigned int flags); /* * mm/huge_memory.c */ void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write); void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); /* * mm/mmap.c */ struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long delta); enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, /* a retry, previous pass started an IO */ FOLL_TRIED = 1 << 17, /* we are working on non-current tsk/mm */ FOLL_REMOTE = 1 << 18, /* pages must be released via unpin_user_page */ FOLL_PIN = 1 << 19, /* gup_fast: prevent fall-back to slow gup */ FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the * GUP pin will remain consistent with the pages mapped into the page tables * of the MM. * * Temporary unmapping of PageAnonExclusive() pages or clearing of * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq * * GUP-fast and KSM or temporary unmapping (swap, migration): see * folio_try_share_anon_rmap_*() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a * PTE-mapped THP. * * If the vma is NULL, we're coming from the GUP-fast path and might have * to fallback to the slow path just to lookup the vma. */ static inline bool gup_must_unshare(struct vm_area_struct *vma, unsigned int flags, struct page *page) { /* * FOLL_WRITE is implicitly handled correctly as the page table entry * has to be writable -- and if it references (part of) an anonymous * folio, that part is required to be marked exclusive. */ if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) return false; /* * Note: PageAnon(page) is stable until the page is actually getting * freed. */ if (!PageAnon(page)) { /* * We only care about R/O long-term pining: R/O short-term * pinning does not have the semantics to observe successive * changes through the process page tables. */ if (!(flags & FOLL_LONGTERM)) return false; /* We really need the vma ... */ if (!vma) return true; /* * ... because we only care about writable private ("COW") * mappings where we have to break COW early. */ return is_cow_mapping(vma->vm_flags); } /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_rmb(); /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. */ return !PageAnonExclusive(page); } extern bool mirrored_kernelcore; extern bool memblock_has_mirror(void); static __always_inline void vma_set_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; } static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) { /* * NOTE: we must check this before VM_SOFTDIRTY on soft-dirty * enablements, because when without soft-dirty being compiled in, * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) * will be constantly true. */ if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) return false; /* * Soft-dirty is kind of special: its tracking is enabled when the * vma flags not set. */ return !(vma->vm_flags & VM_SOFTDIRTY); } static inline void vma_iter_config(struct vma_iterator *vmi, unsigned long index, unsigned long last) { __mas_set_range(&vmi->mas, index, last - 1); } static inline void vma_iter_reset(struct vma_iterator *vmi) { mas_reset(&vmi->mas); } static inline struct vm_area_struct *vma_iter_prev_range_limit(struct vma_iterator *vmi, unsigned long min) { return mas_prev_range(&vmi->mas, min); } static inline struct vm_area_struct *vma_iter_next_range_limit(struct vma_iterator *vmi, unsigned long max) { return mas_next_range(&vmi->mas, max); } static inline int vma_iter_area_lowest(struct vma_iterator *vmi, unsigned long min, unsigned long max, unsigned long size) { return mas_empty_area(&vmi->mas, min, max - 1, size); } static inline int vma_iter_area_highest(struct vma_iterator *vmi, unsigned long min, unsigned long max, unsigned long size) { return mas_empty_area_rev(&vmi->mas, min, max - 1, size); } /* * VMA Iterator functions shared between nommu and mmap */ static inline int vma_iter_prealloc(struct vma_iterator *vmi, struct vm_area_struct *vma) { return mas_preallocate(&vmi->mas, vma, GFP_KERNEL); } static inline void vma_iter_clear(struct vma_iterator *vmi) { mas_store_prealloc(&vmi->mas, NULL); } static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi) { return mas_walk(&vmi->mas); } /* Store a VMA with preallocated memory */ static inline void vma_iter_store(struct vma_iterator *vmi, struct vm_area_struct *vma) { #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && vmi->mas.index > vma->vm_start)) { pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n", vmi->mas.index, vma->vm_start, vma->vm_start, vma->vm_end, vmi->mas.index, vmi->mas.last); } if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && vmi->mas.last < vma->vm_start)) { pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n", vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end, vmi->mas.index, vmi->mas.last); } #endif if (vmi->mas.status != ma_start && ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) vma_iter_invalidate(vmi); __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); mas_store_prealloc(&vmi->mas, vma); } static inline int vma_iter_store_gfp(struct vma_iterator *vmi, struct vm_area_struct *vma, gfp_t gfp) { if (vmi->mas.status != ma_start && ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) vma_iter_invalidate(vmi); __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); mas_store_gfp(&vmi->mas, vma, gfp); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; return 0; } /* * VMA lock generalization */ struct vma_prepare { struct vm_area_struct *vma; struct vm_area_struct *adj_next; struct file *file; struct address_space *mapping; struct anon_vma *anon_vma; struct vm_area_struct *insert; struct vm_area_struct *remove; struct vm_area_struct *remove2; }; void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid); /* shrinker related functions */ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); #ifdef CONFIG_64BIT static inline int can_do_mseal(unsigned long flags) { if (flags) return -EINVAL; return 0; } bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end); bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end, int behavior); #else static inline int can_do_mseal(unsigned long flags) { return -EPERM; } static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end) { return true; } static inline bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end, int behavior) { return true; } #endif #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) { shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); return shrinker->name ? 0 : -ENOMEM; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { kfree_const(shrinker->name); shrinker->name = NULL; } extern int shrinker_debugfs_add(struct shrinker *shrinker); extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id); extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id); #else /* CONFIG_SHRINKER_DEBUG */ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, const char *fmt, va_list ap) { return 0; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { } static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id) { *debugfs_id = -1; return NULL; } static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) { } #endif /* CONFIG_SHRINKER_DEBUG */ /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; #endif /* __MM_INTERNAL_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to generic timeout handling of requests. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/blkdev.h> #include <linux/fault-inject.h> #include "blk.h" #include "blk-mq.h" #ifdef CONFIG_FAIL_IO_TIMEOUT static DECLARE_FAULT_ATTR(fail_io_timeout); static int __init setup_fail_io_timeout(char *str) { return setup_fault_attr(&fail_io_timeout, str); } __setup("fail_io_timeout=", setup_fail_io_timeout); bool __blk_should_fake_timeout(struct request_queue *q) { return should_fail(&fail_io_timeout, 1); } EXPORT_SYMBOL_GPL(__blk_should_fake_timeout); static int __init fail_io_timeout_debugfs(void) { struct dentry *dir = fault_create_debugfs_attr("fail_io_timeout", NULL, &fail_io_timeout); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_io_timeout_debugfs); ssize_t part_timeout_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); int set = test_bit(QUEUE_FLAG_FAIL_IO, &disk->queue->queue_flags); return sprintf(buf, "%d\n", set != 0); } ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct gendisk *disk = dev_to_disk(dev); int val; if (count) { struct request_queue *q = disk->queue; char *p = (char *) buf; val = simple_strtoul(p, &p, 10); if (val) blk_queue_flag_set(QUEUE_FLAG_FAIL_IO, q); else blk_queue_flag_clear(QUEUE_FLAG_FAIL_IO, q); } return count; } #endif /* CONFIG_FAIL_IO_TIMEOUT */ /** * blk_abort_request - Request recovery for the specified command * @req: pointer to the request of interest * * This function requests that the block layer start recovery for the * request by deleting the timer and calling the q's timeout function. * LLDDs who implement their own error recovery MAY ignore the timeout * event if they generated blk_abort_request. */ void blk_abort_request(struct request *req) { /* * All we need to ensure is that timeout scan takes place * immediately and that scan sees the new timeout value. * No need for fancy synchronizations. */ WRITE_ONCE(req->deadline, jiffies); kblockd_schedule_work(&req->q->timeout_work); } EXPORT_SYMBOL_GPL(blk_abort_request); static unsigned long blk_timeout_mask __read_mostly; static int __init blk_timeout_init(void) { blk_timeout_mask = roundup_pow_of_two(HZ) - 1; return 0; } late_initcall(blk_timeout_init); /* * Just a rough estimate, we don't care about specific values for timeouts. */ static inline unsigned long blk_round_jiffies(unsigned long j) { return (j + blk_timeout_mask) + 1; } unsigned long blk_rq_timeout(unsigned long timeout) { unsigned long maxt; maxt = blk_round_jiffies(jiffies + BLK_MAX_TIMEOUT); if (time_after(timeout, maxt)) timeout = maxt; return timeout; } /** * blk_add_timer - Start timeout timer for a single request * @req: request that is about to start running. * * Notes: * Each request has its own timer, and as it is added to the queue, we * set up the timer. When the request completes, we cancel the timer. */ void blk_add_timer(struct request *req) { struct request_queue *q = req->q; unsigned long expiry; /* * Some LLDs, like scsi, peek at the timeout to prevent a * command from being retried forever. */ if (!req->timeout) req->timeout = q->rq_timeout; req->rq_flags &= ~RQF_TIMED_OUT; expiry = jiffies + req->timeout; WRITE_ONCE(req->deadline, expiry); /* * If the timer isn't already pending or this timeout is earlier * than an existing one, modify the timer. Round up to next nearest * second. */ expiry = blk_rq_timeout(blk_round_jiffies(expiry)); if (!timer_pending(&q->timeout) || time_before(expiry, q->timeout.expires)) { unsigned long diff = q->timeout.expires - expiry; /* * Due to added timer slack to group timers, the timer * will often be a little in front of what we asked for. * So apply some tolerance here too, otherwise we keep * modifying the timer because expires for value X * will be X + something. */ if (!timer_pending(&q->timeout) || (diff >= HZ / 2)) mod_timer(&q->timeout, expiry); } } |
| 1 6 5 1 4 1 2 1 1 1 1 1 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 | // SPDX-License-Identifier: GPL-2.0-only /* * Module for modifying the secmark field of the skb, for use by * security subsystems. * * Based on the nfmark match by: * (C) 1999-2001 Marc Boucher <marc@mbsi.ca> * * (C) 2006,2008 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/security.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_SECMARK.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Morris <jmorris@redhat.com>"); MODULE_DESCRIPTION("Xtables: packet security mark modification"); MODULE_ALIAS("ipt_SECMARK"); MODULE_ALIAS("ip6t_SECMARK"); static u8 mode; static unsigned int secmark_tg(struct sk_buff *skb, const struct xt_secmark_target_info_v1 *info) { u32 secmark = 0; switch (mode) { case SECMARK_MODE_SEL: secmark = info->secid; break; default: BUG(); } skb->secmark = secmark; return XT_CONTINUE; } static int checkentry_lsm(struct xt_secmark_target_info_v1 *info) { int err; info->secctx[SECMARK_SECCTX_MAX - 1] = '\0'; info->secid = 0; err = security_secctx_to_secid(info->secctx, strlen(info->secctx), &info->secid); if (err) { if (err == -EINVAL) pr_info_ratelimited("invalid security context \'%s\'\n", info->secctx); return err; } if (!info->secid) { pr_info_ratelimited("unable to map security context \'%s\'\n", info->secctx); return -ENOENT; } err = security_secmark_relabel_packet(info->secid); if (err) { pr_info_ratelimited("unable to obtain relabeling permission\n"); return err; } security_secmark_refcount_inc(); return 0; } static int secmark_tg_check(const char *table, struct xt_secmark_target_info_v1 *info) { int err; if (strcmp(table, "mangle") != 0 && strcmp(table, "security") != 0) { pr_info_ratelimited("only valid in \'mangle\' or \'security\' table, not \'%s\'\n", table); return -EINVAL; } if (mode && mode != info->mode) { pr_info_ratelimited("mode already set to %hu cannot mix with rules for mode %hu\n", mode, info->mode); return -EINVAL; } switch (info->mode) { case SECMARK_MODE_SEL: break; default: pr_info_ratelimited("invalid mode: %hu\n", info->mode); return -EINVAL; } err = checkentry_lsm(info); if (err) return err; if (!mode) mode = info->mode; return 0; } static void secmark_tg_destroy(const struct xt_tgdtor_param *par) { switch (mode) { case SECMARK_MODE_SEL: security_secmark_refcount_dec(); } } static int secmark_tg_check_v0(const struct xt_tgchk_param *par) { struct xt_secmark_target_info *info = par->targinfo; struct xt_secmark_target_info_v1 newinfo = { .mode = info->mode, }; int ret; memcpy(newinfo.secctx, info->secctx, SECMARK_SECCTX_MAX); ret = secmark_tg_check(par->table, &newinfo); info->secid = newinfo.secid; return ret; } static unsigned int secmark_tg_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_secmark_target_info *info = par->targinfo; struct xt_secmark_target_info_v1 newinfo = { .secid = info->secid, }; return secmark_tg(skb, &newinfo); } static int secmark_tg_check_v1(const struct xt_tgchk_param *par) { return secmark_tg_check(par->table, par->targinfo); } static unsigned int secmark_tg_v1(struct sk_buff *skb, const struct xt_action_param *par) { return secmark_tg(skb, par->targinfo); } static struct xt_target secmark_tg_reg[] __read_mostly = { { .name = "SECMARK", .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = secmark_tg_check_v0, .destroy = secmark_tg_destroy, .target = secmark_tg_v0, .targetsize = sizeof(struct xt_secmark_target_info), .me = THIS_MODULE, }, { .name = "SECMARK", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = secmark_tg_check_v1, .destroy = secmark_tg_destroy, .target = secmark_tg_v1, .targetsize = sizeof(struct xt_secmark_target_info_v1), .usersize = offsetof(struct xt_secmark_target_info_v1, secid), .me = THIS_MODULE, }, }; static int __init secmark_tg_init(void) { return xt_register_targets(secmark_tg_reg, ARRAY_SIZE(secmark_tg_reg)); } static void __exit secmark_tg_exit(void) { xt_unregister_targets(secmark_tg_reg, ARRAY_SIZE(secmark_tg_reg)); } module_init(secmark_tg_init); module_exit(secmark_tg_exit); |
| 7 272 11626 12242 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PID_H #define _LINUX_PID_H #include <linux/pid_types.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/sched.h> #include <linux/wait.h> /* * What is struct pid? * * A struct pid is the kernel's internal notion of a process identifier. * It refers to individual tasks, process groups, and sessions. While * there are processes attached to it the struct pid lives in a hash * table, so it and then the processes that it refers to can be found * quickly from the numeric pid value. The attached processes may be * quickly accessed by following pointers from struct pid. * * Storing pid_t values in the kernel and referring to them later has a * problem. The process originally with that pid may have exited and the * pid allocator wrapped, and another process could have come along * and been assigned that pid. * * Referring to user space processes by holding a reference to struct * task_struct has a problem. When the user space process exits * the now useless task_struct is still kept. A task_struct plus a * stack consumes around 10K of low kernel memory. More precisely * this is THREAD_SIZE + sizeof(struct task_struct). By comparison * a struct pid is about 64 bytes. * * Holding a reference to struct pid solves both of these problems. * It is small so holding a reference does not consume a lot of * resources, and since a new struct pid is allocated when the numeric pid * value is reused (when pids wrap around) we don't mistakenly refer to new * processes. */ /* * struct upid is used to get the id of the struct pid, as it is * seen in particular namespace. Later the struct pid is found with * find_pid_ns() using the int nr and struct pid_namespace *ns. */ #define RESERVED_PIDS 300 struct upid { int nr; struct pid_namespace *ns; }; struct pid { refcount_t count; unsigned int level; spinlock_t lock; struct dentry *stashed; u64 ino; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; /* wait queue for pidfd notifications */ wait_queue_head_t wait_pidfd; struct rcu_head rcu; struct upid numbers[]; }; extern struct pid init_struct_pid; struct file; struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); void do_notify_pidfd(struct task_struct *task); static inline struct pid *get_pid(struct pid *pid) { if (pid) refcount_inc(&pid->count); return pid; } extern void put_pid(struct pid *pid); extern struct task_struct *pid_task(struct pid *pid, enum pid_type); static inline bool pid_has_task(struct pid *pid, enum pid_type type) { return !hlist_empty(&pid->tasks[type]); } extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type); extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); /* * these helpers must be called with the tasklist_lock write-held. */ extern void attach_pid(struct task_struct *task, enum pid_type); extern void detach_pid(struct task_struct *task, enum pid_type); extern void change_pid(struct task_struct *task, enum pid_type, struct pid *pid); extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); extern int pid_max; extern int pid_max_min, pid_max_max; /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. * * find_pid_ns() finds the pid in the namespace specified * find_vpid() finds the pid by its virtual id, i.e. in the current namespace * * see also find_task_by_vpid() set in include/linux/sched.h */ extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns); extern struct pid *find_vpid(int nr); /* * Lookup a PID in the hash table, and return with it's count elevated. */ extern struct pid *find_get_pid(int nr); extern struct pid *find_ge_pid(int nr, struct pid_namespace *); extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size); extern void free_pid(struct pid *pid); extern void disable_pid_allocation(struct pid_namespace *ns); /* * ns_of_pid() returns the pid namespace in which the specified pid was * allocated. * * NOTE: * ns_of_pid() is expected to be called for a process (task) that has * an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid * is expected to be non-NULL. If @pid is NULL, caller should handle * the resulting NULL pid-ns. */ static inline struct pid_namespace *ns_of_pid(struct pid *pid) { struct pid_namespace *ns = NULL; if (pid) ns = pid->numbers[pid->level].ns; return ns; } /* * is_child_reaper returns true if the pid is the init process * of the current namespace. As this one could be checked before * pid_ns->child_reaper is assigned in copy_process, we check * with the pid number. */ static inline bool is_child_reaper(struct pid *pid) { return pid->numbers[pid->level].nr == 1; } /* * the helpers to get the pid's id seen from different namespaces * * pid_nr() : global id, i.e. the id seen from the init namespace; * pid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * pid_nr_ns() : id seen from the ns specified. * * see also task_xid_nr() etc in include/linux/sched.h */ static inline pid_t pid_nr(struct pid *pid) { pid_t nr = 0; if (pid) nr = pid->numbers[0].nr; return nr; } pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns); pid_t pid_vnr(struct pid *pid); #define do_each_pid_task(pid, type, task) \ do { \ if ((pid) != NULL) \ hlist_for_each_entry_rcu((task), \ &(pid)->tasks[type], pid_links[type]) { /* * Both old and new leaders may be attached to * the same pid in the middle of de_thread(). */ #define while_each_pid_task(pid, type, task) \ if (type == PIDTYPE_PID) \ break; \ } \ } while (0) #define do_each_pid_thread(pid, type, task) \ do_each_pid_task(pid, type, task) { \ struct task_struct *tg___ = task; \ for_each_thread(tg___, task) { #define while_each_pid_thread(pid, type, task) \ } \ task = tg___; \ } while_each_pid_task(pid, type, task) static inline struct pid *task_pid(struct task_struct *task) { return task->thread_pid; } /* * the helpers to get the task's different pids as they are seen * from various namespaces * * task_xid_nr() : global id, i.e. the id seen from the init namespace; * task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * task_xid_nr_ns() : id seen from the ns specified; * * see also pid_nr() etc in include/linux/pid.h */ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); static inline pid_t task_pid_nr(struct task_struct *tsk) { return tsk->pid; } static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); } static inline pid_t task_pid_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); } static inline pid_t task_tgid_nr(struct task_struct *tsk) { return tsk->tgid; } /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. * * Test if a process is not yet dead (at most zombie state) * If pid_alive fails, then pointers within the task structure * can be stale and must not be dereferenced. * * Return: 1 if the process is alive. 0 otherwise. */ static inline int pid_alive(const struct task_struct *p) { return p->thread_pid != NULL; } static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); } static inline pid_t task_pgrp_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); } static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); } static inline pid_t task_session_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); } static inline pid_t task_tgid_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); } static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) { pid_t pid = 0; rcu_read_lock(); if (pid_alive(tsk)) pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); rcu_read_unlock(); return pid; } static inline pid_t task_ppid_nr(const struct task_struct *tsk) { return task_ppid_nr_ns(tsk, &init_pid_ns); } /* Obsolete, do not use: */ static inline pid_t task_pgrp_nr(struct task_struct *tsk) { return task_pgrp_nr_ns(tsk, &init_pid_ns); } /** * is_global_init - check if a task structure is init. Since init * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. * * Return: 1 if the task structure is init. 0 otherwise. */ static inline int is_global_init(struct task_struct *tsk) { return task_tgid_nr(tsk) == 1; } #endif /* _LINUX_PID_H */ |
| 12 180 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 | /* 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. * * Checksumming functions for IP, TCP, UDP and so on * * Authors: Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Borrows very liberally from tcp.c and ip.c, see those * files for more names. */ #ifndef _CHECKSUM_H #define _CHECKSUM_H #include <linux/errno.h> #include <asm/types.h> #include <asm/byteorder.h> #include <asm/checksum.h> #if !defined(_HAVE_ARCH_COPY_AND_CSUM_FROM_USER) || !defined(HAVE_CSUM_COPY_USER) #include <linux/uaccess.h> #endif #ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER static __always_inline __wsum csum_and_copy_from_user (const void __user *src, void *dst, int len) { if (copy_from_user(dst, src, len)) return 0; return csum_partial(dst, len, ~0U); } #endif #ifndef HAVE_CSUM_COPY_USER static __always_inline __wsum csum_and_copy_to_user (const void *src, void __user *dst, int len) { __wsum sum = csum_partial(src, len, ~0U); if (copy_to_user(dst, src, len) == 0) return sum; return 0; } #endif #ifndef _HAVE_ARCH_CSUM_AND_COPY static __always_inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len) { memcpy(dst, src, len); return csum_partial(dst, len, 0); } #endif #ifndef HAVE_ARCH_CSUM_ADD static __always_inline __wsum csum_add(__wsum csum, __wsum addend) { u32 res = (__force u32)csum; res += (__force u32)addend; return (__force __wsum)(res + (res < (__force u32)addend)); } #endif static __always_inline __wsum csum_sub(__wsum csum, __wsum addend) { return csum_add(csum, ~addend); } static __always_inline __sum16 csum16_add(__sum16 csum, __be16 addend) { u16 res = (__force u16)csum; res += (__force u16)addend; return (__force __sum16)(res + (res < (__force u16)addend)); } static __always_inline __sum16 csum16_sub(__sum16 csum, __be16 addend) { return csum16_add(csum, ~addend); } #ifndef HAVE_ARCH_CSUM_SHIFT static __always_inline __wsum csum_shift(__wsum sum, int offset) { /* rotate sum to align it with a 16b boundary */ if (offset & 1) return (__force __wsum)ror32((__force u32)sum, 8); return sum; } #endif static __always_inline __wsum csum_block_add(__wsum csum, __wsum csum2, int offset) { return csum_add(csum, csum_shift(csum2, offset)); } static __always_inline __wsum csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len) { return csum_block_add(csum, csum2, offset); } static __always_inline __wsum csum_block_sub(__wsum csum, __wsum csum2, int offset) { return csum_block_add(csum, ~csum2, offset); } static __always_inline __wsum csum_unfold(__sum16 n) { return (__force __wsum)n; } static __always_inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum) { return csum_partial(buff, len, sum); } #define CSUM_MANGLED_0 ((__force __sum16)0xffff) static __always_inline void csum_replace_by_diff(__sum16 *sum, __wsum diff) { *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); } static __always_inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) { __wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from); *sum = csum_fold(csum_add(tmp, (__force __wsum)to)); } /* Implements RFC 1624 (Incremental Internet Checksum) * 3. Discussion states : * HC' = ~(~HC + ~m + m') * m : old value of a 16bit field * m' : new value of a 16bit field */ static __always_inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new) { *sum = ~csum16_add(csum16_sub(~(*sum), old), new); } static inline void csum_replace(__wsum *csum, __wsum old, __wsum new) { *csum = csum_add(csum_sub(*csum, old), new); } struct sk_buff; void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr); void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr); void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, __wsum diff, bool pseudohdr); static __always_inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb, __be16 from, __be16 to, bool pseudohdr) { inet_proto_csum_replace4(sum, skb, (__force __be32)from, (__force __be32)to, pseudohdr); } static __always_inline __wsum remcsum_adjust(void *ptr, __wsum csum, int start, int offset) { __sum16 *psum = (__sum16 *)(ptr + offset); __wsum delta; /* Subtract out checksum up to start */ csum = csum_sub(csum, csum_partial(ptr, start, 0)); /* Set derived checksum in packet */ delta = csum_sub((__force __wsum)csum_fold(csum), (__force __wsum)*psum); *psum = csum_fold(csum); return delta; } static __always_inline void remcsum_unadjust(__sum16 *psum, __wsum delta) { *psum = csum_fold(csum_sub(delta, (__force __wsum)*psum)); } static __always_inline __wsum wsum_negate(__wsum val) { return (__force __wsum)-((__force u32)val); } #endif |
| 7 4 7 6 2 5 5 6 2 2 2 8 8 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * CMAC: Cipher Block Mode for Authentication * * Copyright © 2013 Jussi Kivilinna <jussi.kivilinna@iki.fi> * * Based on work by: * Copyright © 2013 Tom St Denis <tstdenis@elliptictech.com> * Based on crypto/xcbc.c: * Copyright © 2006 USAGI/WIDE Project, * Author: Kazunori Miyazawa <miyazawa@linux-ipv6.org> */ #include <crypto/internal/cipher.h> #include <crypto/internal/hash.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> /* * +------------------------ * | <parent tfm> * +------------------------ * | cmac_tfm_ctx * +------------------------ * | consts (block size * 2) * +------------------------ */ struct cmac_tfm_ctx { struct crypto_cipher *child; __be64 consts[]; }; /* * +------------------------ * | <shash desc> * +------------------------ * | cmac_desc_ctx * +------------------------ * | odds (block size) * +------------------------ * | prev (block size) * +------------------------ */ struct cmac_desc_ctx { unsigned int len; u8 odds[]; }; static int crypto_cmac_digest_setkey(struct crypto_shash *parent, const u8 *inkey, unsigned int keylen) { struct cmac_tfm_ctx *ctx = crypto_shash_ctx(parent); unsigned int bs = crypto_shash_blocksize(parent); __be64 *consts = ctx->consts; u64 _const[2]; int i, err = 0; u8 msb_mask, gfmask; err = crypto_cipher_setkey(ctx->child, inkey, keylen); if (err) return err; /* encrypt the zero block */ memset(consts, 0, bs); crypto_cipher_encrypt_one(ctx->child, (u8 *)consts, (u8 *)consts); switch (bs) { case 16: gfmask = 0x87; _const[0] = be64_to_cpu(consts[1]); _const[1] = be64_to_cpu(consts[0]); /* gf(2^128) multiply zero-ciphertext with u and u^2 */ for (i = 0; i < 4; i += 2) { msb_mask = ((s64)_const[1] >> 63) & gfmask; _const[1] = (_const[1] << 1) | (_const[0] >> 63); _const[0] = (_const[0] << 1) ^ msb_mask; consts[i + 0] = cpu_to_be64(_const[1]); consts[i + 1] = cpu_to_be64(_const[0]); } break; case 8: gfmask = 0x1B; _const[0] = be64_to_cpu(consts[0]); /* gf(2^64) multiply zero-ciphertext with u and u^2 */ for (i = 0; i < 2; i++) { msb_mask = ((s64)_const[0] >> 63) & gfmask; _const[0] = (_const[0] << 1) ^ msb_mask; consts[i] = cpu_to_be64(_const[0]); } break; } return 0; } static int crypto_cmac_digest_init(struct shash_desc *pdesc) { struct cmac_desc_ctx *ctx = shash_desc_ctx(pdesc); int bs = crypto_shash_blocksize(pdesc->tfm); u8 *prev = &ctx->odds[bs]; ctx->len = 0; memset(prev, 0, bs); return 0; } static int crypto_cmac_digest_update(struct shash_desc *pdesc, const u8 *p, unsigned int len) { struct crypto_shash *parent = pdesc->tfm; struct cmac_tfm_ctx *tctx = crypto_shash_ctx(parent); struct cmac_desc_ctx *ctx = shash_desc_ctx(pdesc); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_blocksize(parent); u8 *odds = ctx->odds; u8 *prev = odds + bs; /* checking the data can fill the block */ if ((ctx->len + len) <= bs) { memcpy(odds + ctx->len, p, len); ctx->len += len; return 0; } /* filling odds with new data and encrypting it */ memcpy(odds + ctx->len, p, bs - ctx->len); len -= bs - ctx->len; p += bs - ctx->len; crypto_xor(prev, odds, bs); crypto_cipher_encrypt_one(tfm, prev, prev); /* clearing the length */ ctx->len = 0; /* encrypting the rest of data */ while (len > bs) { crypto_xor(prev, p, bs); crypto_cipher_encrypt_one(tfm, prev, prev); p += bs; len -= bs; } /* keeping the surplus of blocksize */ if (len) { memcpy(odds, p, len); ctx->len = len; } return 0; } static int crypto_cmac_digest_final(struct shash_desc *pdesc, u8 *out) { struct crypto_shash *parent = pdesc->tfm; struct cmac_tfm_ctx *tctx = crypto_shash_ctx(parent); struct cmac_desc_ctx *ctx = shash_desc_ctx(pdesc); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_blocksize(parent); u8 *odds = ctx->odds; u8 *prev = odds + bs; unsigned int offset = 0; if (ctx->len != bs) { unsigned int rlen; u8 *p = odds + ctx->len; *p = 0x80; p++; rlen = bs - ctx->len - 1; if (rlen) memset(p, 0, rlen); offset += bs; } crypto_xor(prev, odds, bs); crypto_xor(prev, (const u8 *)tctx->consts + offset, bs); crypto_cipher_encrypt_one(tfm, out, prev); return 0; } static int cmac_init_tfm(struct crypto_shash *tfm) { struct shash_instance *inst = shash_alg_instance(tfm); struct cmac_tfm_ctx *ctx = crypto_shash_ctx(tfm); struct crypto_cipher_spawn *spawn; struct crypto_cipher *cipher; spawn = shash_instance_ctx(inst); cipher = crypto_spawn_cipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->child = cipher; return 0; } static int cmac_clone_tfm(struct crypto_shash *tfm, struct crypto_shash *otfm) { struct cmac_tfm_ctx *octx = crypto_shash_ctx(otfm); struct cmac_tfm_ctx *ctx = crypto_shash_ctx(tfm); struct crypto_cipher *cipher; cipher = crypto_clone_cipher(octx->child); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->child = cipher; return 0; } static void cmac_exit_tfm(struct crypto_shash *tfm) { struct cmac_tfm_ctx *ctx = crypto_shash_ctx(tfm); crypto_free_cipher(ctx->child); } static int cmac_create(struct crypto_template *tmpl, struct rtattr **tb) { struct shash_instance *inst; struct crypto_cipher_spawn *spawn; struct crypto_alg *alg; u32 mask; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SHASH, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = shash_instance_ctx(inst); err = crypto_grab_cipher(spawn, shash_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; alg = crypto_spawn_cipher_alg(spawn); switch (alg->cra_blocksize) { case 16: case 8: break; default: err = -EINVAL; goto err_free_inst; } err = crypto_inst_setname(shash_crypto_instance(inst), tmpl->name, alg); if (err) goto err_free_inst; inst->alg.base.cra_priority = alg->cra_priority; inst->alg.base.cra_blocksize = alg->cra_blocksize; inst->alg.base.cra_ctxsize = sizeof(struct cmac_tfm_ctx) + alg->cra_blocksize * 2; inst->alg.digestsize = alg->cra_blocksize; inst->alg.descsize = sizeof(struct cmac_desc_ctx) + alg->cra_blocksize * 2; inst->alg.init = crypto_cmac_digest_init; inst->alg.update = crypto_cmac_digest_update; inst->alg.final = crypto_cmac_digest_final; inst->alg.setkey = crypto_cmac_digest_setkey; inst->alg.init_tfm = cmac_init_tfm; inst->alg.clone_tfm = cmac_clone_tfm; inst->alg.exit_tfm = cmac_exit_tfm; inst->free = shash_free_singlespawn_instance; err = shash_register_instance(tmpl, inst); if (err) { err_free_inst: shash_free_singlespawn_instance(inst); } return err; } static struct crypto_template crypto_cmac_tmpl = { .name = "cmac", .create = cmac_create, .module = THIS_MODULE, }; static int __init crypto_cmac_module_init(void) { return crypto_register_template(&crypto_cmac_tmpl); } static void __exit crypto_cmac_module_exit(void) { crypto_unregister_template(&crypto_cmac_tmpl); } subsys_initcall(crypto_cmac_module_init); module_exit(crypto_cmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CMAC keyed hash algorithm"); MODULE_ALIAS_CRYPTO("cmac"); MODULE_IMPORT_NS(CRYPTO_INTERNAL); |
| 3834 3597 480 4116 3597 3834 3705 132 133 133 4116 5575 223 4319 74 4 253 481 187 187 4392 68 4420 3703 3701 3705 3419 3600 3697 3706 3711 3704 3698 3706 3711 3705 481 12 12 11 496 482 12 136 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* memcontrol.h - Memory Controller * * Copyright IBM Corporation, 2007 * Author Balbir Singh <balbir@linux.vnet.ibm.com> * * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov <xemul@openvz.org> */ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H #include <linux/cgroup.h> #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> #include <linux/shrinker.h> struct mem_cgroup; struct obj_cgroup; struct page; struct mm_struct; struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, MEMCG_VMALLOC, MEMCG_KMEM, MEMCG_ZSWAP_B, MEMCG_ZSWAPPED, MEMCG_NR_STAT, }; enum memcg_memory_event { MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, MEMCG_OOM_GROUP_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, }; struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; unsigned int generation; }; #ifdef CONFIG_MEMCG #define MEM_CGROUP_ID_SHIFT 16 struct mem_cgroup_id { int id; refcount_t ref; }; /* * Per memcg event counter is incremented at every pagein/pageout. With THP, * it will be incremented by the number of pages. This counter is used * to trigger some periodic events. This is straightforward and better * than using jiffies etc. to handle periodic memcg event. */ enum mem_cgroup_events_target { MEM_CGROUP_TARGET_THRESH, MEM_CGROUP_TARGET_SOFTLIMIT, MEM_CGROUP_NTARGETS, }; struct memcg_vmstats_percpu; struct memcg_vmstats; struct lruvec_stats_percpu; struct lruvec_stats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ unsigned int generation; }; /* * per-node information in memory controller. */ struct mem_cgroup_per_node { struct lruvec lruvec; struct lruvec_stats_percpu __percpu *lruvec_stats_percpu; struct lruvec_stats *lruvec_stats; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; struct shrinker_info __rcu *shrinker_info; struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; }; /* For threshold */ struct mem_cgroup_threshold_ary { /* An array index points to threshold just below or equal to usage. */ int current_threshold; /* Size of entries[] */ unsigned int size; /* Array of thresholds */ struct mem_cgroup_threshold entries[] __counted_by(size); }; struct mem_cgroup_thresholds { /* Primary thresholds array */ struct mem_cgroup_threshold_ary *primary; /* * Spare threshold array. * This is needed to make mem_cgroup_unregister_event() "never fail". * It must be able to store at least primary->size - 1 entries. */ struct mem_cgroup_threshold_ary *spare; }; /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss * one in a given round, we're likely to catch it later if it keeps * foreign-dirtying, so a fairly low count should be enough. * * See mem_cgroup_track_foreign_dirty_slowpath() for details. */ #define MEMCG_CGWB_FRN_CNT 4 struct memcg_cgwb_frn { u64 bdi_id; /* bdi->id of the foreign inode */ int memcg_id; /* memcg->css.id of foreign inode */ u64 at; /* jiffies_64 at the time of dirtying */ struct wb_completion done; /* tracks in-flight foreign writebacks */ }; /* * Bucket for arbitrarily byte-sized objects charged to a memory * cgroup. The bucket can be reparented in one piece when the cgroup * is destroyed, without having to round up the individual references * of all live memory objects in the wild. */ struct obj_cgroup { struct percpu_ref refcnt; struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; }; /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, * to help the administrator determine what knobs to tune. */ struct mem_cgroup { struct cgroup_subsys_state css; /* Private memcg ID. Used to ID objects that outlive the cgroup */ struct mem_cgroup_id id; /* Accounted resources */ struct page_counter memory; /* Both v1 & v2 */ union { struct page_counter swap; /* v2 only */ struct page_counter memsw; /* v1 only */ }; /* Legacy consumer-oriented counters */ struct page_counter kmem; /* v1 only */ struct page_counter tcpmem; /* v1 only */ /* Range enforcement for interrupt charges */ struct work_struct high_work; #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) unsigned long zswap_max; /* * Prevent pages from this memcg from being written back from zswap to * swap, and from being swapped out on zswap store failures. */ bool zswap_writeback; #endif unsigned long soft_limit; /* vmpressure notifications */ struct vmpressure vmpressure; /* * Should the OOM killer kill all belonging tasks, had it kill one? */ bool oom_group; /* protected by memcg_oom_lock */ bool oom_lock; int under_oom; int swappiness; /* OOM-Killer disable */ int oom_kill_disable; /* memory.events and memory.events.local */ struct cgroup_file events_file; struct cgroup_file events_local_file; /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; /* protect arrays of thresholds */ struct mutex thresholds_lock; /* thresholds for memory usage. RCU-protected */ struct mem_cgroup_thresholds thresholds; /* thresholds for mem+swap usage. RCU-protected */ struct mem_cgroup_thresholds memsw_thresholds; /* For oom notifier event fd */ struct list_head oom_notify; /* * Should we move charges of a task when a task is moved into this * mem_cgroup ? And what type of charges should we move ? */ unsigned long move_charge_at_immigrate; /* taken only while moving_account > 0 */ spinlock_t move_lock; unsigned long move_lock_flags; CACHELINE_PADDING(_pad1_); /* memory.stat */ struct memcg_vmstats *vmstats; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; /* * Hint of reclaim pressure for socket memroy management. Note * that this indicator should NOT be used in legacy cgroup mode * where socket memory is accounted/charged separately. */ unsigned long socket_pressure; /* Legacy tcp memory accounting */ bool tcpmem_active; int tcpmem_pressure; #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; /* * memcg->objcg is wiped out as a part of the objcg repaprenting * process. memcg->orig_objcg preserves a pointer (and a reference) * to the original objcg until the end of live of memcg. */ struct obj_cgroup __rcu *objcg; struct obj_cgroup *orig_objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; #endif CACHELINE_PADDING(_pad2_); /* * set > 0 if pages under this cgroup are moving to other cgroup. */ atomic_t moving_account; struct task_struct *move_lock_task; struct memcg_vmstats_percpu __percpu *vmstats_percpu; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif #ifdef CONFIG_LRU_GEN_WALKS_MMU /* per-memcg mm_struct list */ struct lru_gen_mm_list mm_list; #endif struct mem_cgroup_per_node *nodeinfo[]; }; /* * size of first charge trial. * TODO: maybe necessary to use big numbers in big irons or dynamic based of the * workload. */ #define MEMCG_CHARGE_BATCH 64U extern struct mem_cgroup *root_mem_cgroup; enum page_memcg_data_flags { /* page->memcg_data is a pointer to an slabobj_ext vector */ MEMCG_DATA_OBJEXTS = (1UL << 0), /* page has been accounted as a non-slab kernel page */ MEMCG_DATA_KMEM = (1UL << 1), /* the next bit after the last actual flag */ __NR_MEMCG_DATA_FLAGS = (1UL << 2), }; #define __FIRST_OBJEXT_FLAG __NR_MEMCG_DATA_FLAGS #else /* CONFIG_MEMCG */ #define __FIRST_OBJEXT_FLAG (1UL << 0) #endif /* CONFIG_MEMCG */ enum objext_flags { /* slabobj_ext vector failed to allocate */ OBJEXTS_ALLOC_FAIL = __FIRST_OBJEXT_FLAG, /* the next bit after the last actual flag */ __NR_OBJEXTS_FLAGS = (__FIRST_OBJEXT_FLAG << 1), }; #define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1) #ifdef CONFIG_MEMCG static inline bool folio_memcg_kmem(struct folio *folio); /* * After the initialization objcg->memcg is always pointing at * a valid memcg, but can be atomically swapped to the parent memcg. * * The caller must ensure that the returned memcg won't be released: * e.g. acquire the rcu_read_lock or css_set_lock. */ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) { return READ_ONCE(objcg->memcg); } /* * __folio_memcg - Get the memory cgroup associated with a non-kmem folio * @folio: Pointer to the folio. * * Returns a pointer to the memory cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function * against some type of folios, e.g. slab folios or ex-slab folios or * kmem folios. */ static inline struct mem_cgroup *__folio_memcg(struct folio *folio) { unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio); return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* * __folio_objcg - get the object cgroup associated with a kmem folio. * @folio: Pointer to the folio. * * Returns a pointer to the object cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a * proper object cgroup pointer. It's not safe to call this function * against some type of folios, e.g. slab folios or ex-slab folios or * LRU folios. */ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) { unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio); return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* * folio_memcg - Get the memory cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the memory cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function * against some type of folios, e.g. slab folios or ex-slab folios. * * For a non-kmem folio any of the following ensures folio and memcg binding * stability: * * - the folio lock * - LRU isolation * - folio_memcg_lock() * - exclusive reference * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. */ static inline struct mem_cgroup *folio_memcg(struct folio *folio) { if (folio_memcg_kmem(folio)) return obj_cgroup_memcg(__folio_objcg(folio)); return __folio_memcg(folio); } static inline struct mem_cgroup *page_memcg(struct page *page) { return folio_memcg(page_folio(page)); } /** * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. * @folio: Pointer to the folio. * * This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function * against some type of folios, e.g. slab folios or ex-slab folios. * * Return: A pointer to the memory cgroup associated with the folio, * or NULL. */ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) { unsigned long memcg_data = READ_ONCE(folio->memcg_data); VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); WARN_ON_ONCE(!rcu_read_lock_held()); if (memcg_data & MEMCG_DATA_KMEM) { struct obj_cgroup *objcg; objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); return obj_cgroup_memcg(objcg); } return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* * folio_memcg_check - Get the memory cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the memory cgroup associated with the folio, * or NULL. This function unlike folio_memcg() can take any folio * as an argument. It has to be used in cases when it's not known if a folio * has an associated memory cgroup pointer or an object cgroups vector or * an object cgroup. * * For a non-kmem folio any of the following ensures folio and memcg binding * stability: * * - the folio lock * - LRU isolation * - lock_folio_memcg() * - exclusive reference * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. */ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) { /* * Because folio->memcg_data might be changed asynchronously * for slabs, READ_ONCE() should be used here. */ unsigned long memcg_data = READ_ONCE(folio->memcg_data); if (memcg_data & MEMCG_DATA_OBJEXTS) return NULL; if (memcg_data & MEMCG_DATA_KMEM) { struct obj_cgroup *objcg; objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); return obj_cgroup_memcg(objcg); } return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } static inline struct mem_cgroup *page_memcg_check(struct page *page) { if (PageTail(page)) return NULL; return folio_memcg_check((struct folio *)page); } static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) { struct mem_cgroup *memcg; rcu_read_lock(); retry: memcg = obj_cgroup_memcg(objcg); if (unlikely(!css_tryget(&memcg->css))) goto retry; rcu_read_unlock(); return memcg; } #ifdef CONFIG_MEMCG_KMEM /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. * @folio: Pointer to the folio. * * Checks if the folio has MemcgKmem flag set. The caller must ensure * that the folio has an associated memory cgroup. It's not safe to call * this function against some types of folios, e.g. slab folios. */ static inline bool folio_memcg_kmem(struct folio *folio) { VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJEXTS, folio); return folio->memcg_data & MEMCG_DATA_KMEM; } #else static inline bool folio_memcg_kmem(struct folio *folio) { return false; } #endif static inline bool PageMemcgKmem(struct page *page) { return folio_memcg_kmem(page_folio(page)); } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); } static inline bool mem_cgroup_disabled(void) { return !cgroup_subsys_enabled(memory_cgrp_subsys); } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; if (mem_cgroup_disabled()) return; /* * There is no reclaim protection applied to a targeted reclaim. * We are special casing this specific case here because * mem_cgroup_calculate_protection is not robust enough to keep * the protection invariant for calculated effective values for * parallel reclaimers with different reclaim target. This is * especially a problem for tail memcgs (as they have pages on LRU) * which would want to have effective values 0 for targeted reclaim * but a different value for external reclaim. * * Example * Let's have global and A's reclaim in parallel: * | * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) * |\ * | C (low = 1G, usage = 2.5G) * B (low = 1G, usage = 0.5G) * * For the global reclaim * A.elow = A.low * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow * C.elow = min(C.usage, C.low) * * With the effective values resetting we have A reclaim * A.elow = 0 * B.elow = B.low * C.elow = C.low * * If the global reclaim races with A's reclaim then * B.elow = C.elow = 0 because children_low_usage > A.elow) * is possible and reclaiming B would be violating the protection. * */ if (root == memcg) return; *min = READ_ONCE(memcg->memory.emin); *low = READ_ONCE(memcg->memory.elow); } void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg); static inline bool mem_cgroup_unprotected(struct mem_cgroup *target, struct mem_cgroup *memcg) { /* * The root memcg doesn't account charges, and doesn't support * protection. The target memcg's protection is ignored, see * mem_cgroup_calculate_protection() and mem_cgroup_protection() */ return mem_cgroup_disabled() || mem_cgroup_is_root(memcg) || memcg == target; } static inline bool mem_cgroup_below_low(struct mem_cgroup *target, struct mem_cgroup *memcg) { if (mem_cgroup_unprotected(target, memcg)) return false; return READ_ONCE(memcg->memory.elow) >= page_counter_read(&memcg->memory); } static inline bool mem_cgroup_below_min(struct mem_cgroup *target, struct mem_cgroup *memcg) { if (mem_cgroup_unprotected(target, memcg)) return false; return READ_ONCE(memcg->memory.emin) >= page_counter_read(&memcg->memory); } void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg); int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); /** * mem_cgroup_charge - Charge a newly allocated folio to a cgroup. * @folio: Folio to charge. * @mm: mm context of the allocating task. * @gfp: Reclaim mode. * * Try to charge @folio to the memcg that @mm belongs to, reclaiming * pages according to @gfp if necessary. If @mm is NULL, try to * charge to the active memcg. * * Do not use this for folios allocated for swapin. * * Return: 0 on success. Otherwise, an error code is returned. */ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_charge(folio, mm, gfp); } int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp, long nr_pages); int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); void __mem_cgroup_uncharge(struct folio *folio); /** * mem_cgroup_uncharge - Uncharge a folio. * @folio: Folio to uncharge. * * Uncharge a folio previously charged with mem_cgroup_charge(). */ static inline void mem_cgroup_uncharge(struct folio *folio) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge(folio); } void __mem_cgroup_uncharge_folios(struct folio_batch *folios); static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_folios(folios); } void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_replace_folio(struct folio *old, struct folio *new); void mem_cgroup_migrate(struct folio *old, struct folio *new); /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec * @pgdat: pglist_data * * Returns the lru list vector holding pages for a given @memcg & * @pgdat combination. This can be the node lruvec, if the memory * controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { lruvec = &pgdat->__lruvec; goto out; } if (!memcg) memcg = root_mem_cgroup; mz = memcg->nodeinfo[pgdat->node_id]; lruvec = &mz->lruvec; out: /* * Since a node can be onlined after the mem_cgroup was created, * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ if (unlikely(lruvec->pgdat != pgdat)) lruvec->pgdat = pgdat; return lruvec; } /** * folio_lruvec - return lruvec for isolating/putting an LRU folio * @folio: Pointer to the folio. * * This function relies on folio->mem_cgroup being stable. */ static inline struct lruvec *folio_lruvec(struct folio *folio) { struct mem_cgroup *memcg = folio_memcg(folio); VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio); return mem_cgroup_lruvec(memcg, folio_pgdat(folio)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); struct mem_cgroup *get_mem_cgroup_from_current(void); struct lruvec *folio_lruvec_lock(struct folio *folio); struct lruvec *folio_lruvec_lock_irq(struct folio *folio); struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flags); #ifdef CONFIG_DEBUG_VM void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio); #else static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { } #endif static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg) { return percpu_ref_tryget(&objcg->refcnt); } static inline void obj_cgroup_get(struct obj_cgroup *objcg) { percpu_ref_get(&objcg->refcnt); } static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, unsigned long nr) { percpu_ref_get_many(&objcg->refcnt, nr); } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { if (objcg) percpu_ref_put(&objcg->refcnt); } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) { return !memcg || css_tryget(&memcg->css); } static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg) { return !memcg || css_tryget_online(&memcg->css); } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) css_put(&memcg->css); } #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*)(struct task_struct *, void *), void *arg); static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return 0; return memcg->id.id; } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); #ifdef CONFIG_SHRINKER_DEBUG static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) { return memcg ? cgroup_ino(memcg->css.cgroup) : 0; } struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino); #endif static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { struct mem_cgroup_per_node *mz; if (mem_cgroup_disabled()) return NULL; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->memcg; } /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find * * Returns the parent memcg, or NULL if this is the root. */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return mem_cgroup_from_css(memcg->css.parent); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { if (root == memcg) return true; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; bool match = false; rcu_read_lock(); task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (task_memcg) match = mem_cgroup_is_descendant(task_memcg, memcg); rcu_read_unlock(); return match; } struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return true; return !!(memcg->css.flags & CSS_ONLINE); } void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages); static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } void mem_cgroup_handle_over_high(gfp_t gfp_mask); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); unsigned long mem_cgroup_size(struct mem_cgroup *memcg); void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); static inline void mem_cgroup_enter_user_fault(void) { WARN_ON(current->in_user_fault); current->in_user_fault = 1; } static inline void mem_cgroup_exit_user_fault(void) { WARN_ON(!current->in_user_fault); current->in_user_fault = 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { return p->memcg_in_oom; } bool mem_cgroup_oom_synchronize(bool wait); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); void folio_memcg_lock(struct folio *folio); void folio_memcg_unlock(struct folio *folio); void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int val); /* try to stablize folio_memcg() for all the pages in a memcg */ static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) { rcu_read_lock(); if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) return true; rcu_read_unlock(); return false; } static inline void mem_cgroup_unlock_pages(void) { rcu_read_unlock(); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_memcg_state(memcg, idx, val); local_irq_restore(flags); } static inline void mod_memcg_page_state(struct page *page, enum memcg_stat_item idx, int val) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = page_memcg(page); if (memcg) mod_memcg_state(memcg, idx, val); rcu_read_unlock(); } unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx); unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx); void mem_cgroup_flush_stats(struct mem_cgroup *memcg); void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg); void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_kmem_state(p, idx, val); local_irq_restore(flags); } void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { unsigned long flags; local_irq_save(flags); __count_memcg_events(memcg, idx, count); local_irq_restore(flags); } static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { struct mem_cgroup *memcg = folio_memcg(folio); if (memcg) count_memcg_events(memcg, idx, nr); } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) count_memcg_events(memcg, idx, 1); rcu_read_unlock(); } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || event == MEMCG_SWAP_FAIL; atomic_long_inc(&memcg->memory_events_local[event]); if (!swap_event) cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); if (swap_event) cgroup_file_notify(&memcg->swap_events_file); else cgroup_file_notify(&memcg->events_file); if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) memcg_memory_event(memcg, event); rcu_read_unlock(); } void split_page_memcg(struct page *head, int old_order, int new_order); unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 static inline struct mem_cgroup *folio_memcg(struct folio *folio) { return NULL; } static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; } static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) { WARN_ON_ONCE(!rcu_read_lock_held()); return NULL; } static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) { return NULL; } static inline struct mem_cgroup *page_memcg_check(struct page *page) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) { return NULL; } static inline bool folio_memcg_kmem(struct folio *folio) { return false; } static inline bool PageMemcgKmem(struct page *page) { return false; } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_disabled(void) { return true; } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; } static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg) { } static inline bool mem_cgroup_unprotected(struct mem_cgroup *target, struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_below_low(struct mem_cgroup *target, struct mem_cgroup *memcg) { return false; } static inline bool mem_cgroup_below_min(struct mem_cgroup *target, struct mem_cgroup *memcg) { return false; } static inline void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg) { } static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { return 0; } static inline int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp, long nr_pages) { return 0; } static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { return 0; } static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry) { } static inline void mem_cgroup_uncharge(struct folio *folio) { } static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { } static inline void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { } static inline void mem_cgroup_replace_folio(struct folio *old, struct folio *new) { } static inline void mem_cgroup_migrate(struct folio *old, struct folio *new) { } static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); return &pgdat->__lruvec; } static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { } static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return NULL; } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { return true; } static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_current(void) { return NULL; } static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) { return NULL; } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg) { return true; } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } static inline struct lruvec *folio_lruvec_lock(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); spin_lock(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); spin_lock_irq(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flagsp) { struct pglist_data *pgdat = folio_pgdat(folio); spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp); return &pgdat->__lruvec; } static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { return NULL; } static inline void mem_cgroup_iter_break(struct mem_cgroup *root, struct mem_cgroup *prev) { } static inline void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*fn)(struct task_struct *, void *), void *arg) { } static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { WARN_ON_ONCE(id); /* XXX: This should always return root_mem_cgroup */ return NULL; } #ifdef CONFIG_SHRINKER_DEBUG static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino) { return NULL; } #endif static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { return NULL; } static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { return true; } static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { return 0; } static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { return 0; } static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg) { return 0; } static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { } static inline void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } static inline void folio_memcg_lock(struct folio *folio) { } static inline void folio_memcg_unlock(struct folio *folio) { } static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) { /* to match folio_memcg_rcu() */ rcu_read_lock(); return true; } static inline void mem_cgroup_unlock_pages(void) { rcu_read_unlock(); } static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } static inline void mem_cgroup_enter_user_fault(void) { } static inline void mem_cgroup_exit_user_fault(void) { } static inline bool task_in_memcg_oom(struct task_struct *p) { return false; } static inline bool mem_cgroup_oom_synchronize(bool wait) { return false; } static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { return NULL; } static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } static inline void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int nr) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, enum memcg_stat_item idx, int val) { } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline void mem_cgroup_flush_stats(struct mem_cgroup *memcg) { } static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) { } static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); mod_node_page_state(page_pgdat(page), idx, val); } static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } static inline void split_page_memcg(struct page *head, int old_order, int new_order) { } static inline unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { return 0; } #endif /* CONFIG_MEMCG */ /* * Extended information for slab objects stored as an array in page->memcg_data * if MEMCG_DATA_OBJEXTS is set. */ struct slabobj_ext { #ifdef CONFIG_MEMCG_KMEM struct obj_cgroup *objcg; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref ref; #endif } __aligned(8); static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx) { __mod_lruvec_kmem_state(p, idx, 1); } static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx) { __mod_lruvec_kmem_state(p, idx, -1); } static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; memcg = lruvec_memcg(lruvec); if (!memcg) return NULL; memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); } static inline void unlock_page_lruvec(struct lruvec *lruvec) { spin_unlock(&lruvec->lru_lock); } static inline void unlock_page_lruvec_irq(struct lruvec *lruvec) { spin_unlock_irq(&lruvec->lru_lock); } static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, unsigned long flags) { spin_unlock_irqrestore(&lruvec->lru_lock, flags); } /* Test requires a stable page->memcg binding, see page_memcg() */ static inline bool folio_matches_lruvec(struct folio *folio, struct lruvec *lruvec) { return lruvec_pgdat(lruvec) == folio_pgdat(folio) && lruvec_memcg(lruvec) == folio_memcg(folio); } /* Don't lock again iff page's lruvec locked */ static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio, struct lruvec *locked_lruvec) { if (locked_lruvec) { if (folio_matches_lruvec(folio, locked_lruvec)) return locked_lruvec; unlock_page_lruvec_irq(locked_lruvec); } return folio_lruvec_lock_irq(folio); } /* Don't lock again iff folio's lruvec locked */ static inline void folio_lruvec_relock_irqsave(struct folio *folio, struct lruvec **lruvecp, unsigned long *flags) { if (*lruvecp) { if (folio_matches_lruvec(folio, *lruvecp)) return; unlock_page_lruvec_irqrestore(*lruvecp, *flags); } *lruvecp = folio_lruvec_lock_irqsave(folio, flags); } #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb); static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; memcg = folio_memcg(folio); if (unlikely(memcg && &memcg->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(folio, wb); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); #else /* CONFIG_CGROUP_WRITEBACK */ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) { return NULL; } static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback) { } static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { } static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) { } #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages, gfp_t gfp_mask); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return !!memcg->tcpmem_pressure; do { if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; } int alloc_shrinker_info(struct mem_cgroup *memcg); void free_shrinker_info(struct mem_cgroup *memcg); void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); void reparent_shrinker_deferred(struct mem_cgroup *memcg); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; static inline void mem_cgroup_sk_free(struct sock *sk) { }; static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { return false; } static inline void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { } #endif #ifdef CONFIG_MEMCG_KMEM bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); /* * The returned objcg pointer is safe to use without additional * protection within a scope. The scope is defined either by * the current task (similar to the "current" global variable) * or by set_active_memcg() pair. * Please, use obj_cgroup_get() to get a reference if the pointer * needs to be used outside of the local scope. */ struct obj_cgroup *current_obj_cgroup(void); struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio); static inline struct obj_cgroup *get_obj_cgroup_from_current(void) { struct obj_cgroup *objcg = current_obj_cgroup(); if (objcg) obj_cgroup_get(objcg); return objcg; } int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_bpf_enabled_key; static inline bool memcg_bpf_enabled(void) { return static_branch_likely(&memcg_bpf_enabled_key); } extern struct static_key_false memcg_kmem_online_key; static inline bool memcg_kmem_online(void) { return static_branch_likely(&memcg_kmem_online_key); } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { if (memcg_kmem_online()) return __memcg_kmem_charge_page(page, gfp, order); return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { if (memcg_kmem_online()) __memcg_kmem_uncharge_page(page, order); } /* * A helper for accessing memcg's kmem_id, used for getting * corresponding LRU lists. */ static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } struct mem_cgroup *mem_cgroup_from_obj(void *p); struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); static inline void count_objcg_event(struct obj_cgroup *objcg, enum vm_event_item idx) { struct mem_cgroup *memcg; if (!memcg_kmem_online()) return; rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); count_memcg_events(memcg, idx, 1); rcu_read_unlock(); } #else static inline bool mem_cgroup_kmem_disabled(void) { return true; } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { } static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } static inline struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio) { return NULL; } static inline bool memcg_bpf_enabled(void) { return false; } static inline bool memcg_kmem_online(void) { return false; } static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return -1; } static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { return NULL; } static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) { return NULL; } static inline void count_objcg_event(struct obj_cgroup *objcg, enum vm_event_item idx) { } #endif /* CONFIG_MEMCG_KMEM */ #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg); #else static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) { return true; } static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size) { } static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size) { } static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) { /* if zswap is disabled, do not block pages going to the swapping device */ return true; } #endif #endif /* _LINUX_MEMCONTROL_H */ |
| 11 100 99 92 11 11 7 7 2 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004 IBM Corporation * * Author: Serge Hallyn <serue@us.ibm.com> */ #include <linux/export.h> #include <linux/uts.h> #include <linux/utsname.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/sched/task.h> static struct kmem_cache *uts_ns_cache __ro_after_init; static struct ucounts *inc_uts_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_UTS_NAMESPACES); } static void dec_uts_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_UTS_NAMESPACES); } static struct uts_namespace *create_uts_ns(void) { struct uts_namespace *uts_ns; uts_ns = kmem_cache_alloc(uts_ns_cache, GFP_KERNEL); if (uts_ns) refcount_set(&uts_ns->ns.count, 1); return uts_ns; } /* * Clone a new ns copying an original utsname, setting refcount to 1 * @old_ns: namespace to clone * Return ERR_PTR(-ENOMEM) on error (failure to allocate), new ns otherwise */ static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns, struct uts_namespace *old_ns) { struct uts_namespace *ns; struct ucounts *ucounts; int err; err = -ENOSPC; ucounts = inc_uts_namespaces(user_ns); if (!ucounts) goto fail; err = -ENOMEM; ns = create_uts_ns(); if (!ns) goto fail_dec; err = ns_alloc_inum(&ns->ns); if (err) goto fail_free; ns->ucounts = ucounts; ns->ns.ops = &utsns_operations; down_read(&uts_sem); memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); ns->user_ns = get_user_ns(user_ns); up_read(&uts_sem); return ns; fail_free: kmem_cache_free(uts_ns_cache, ns); fail_dec: dec_uts_namespaces(ucounts); fail: return ERR_PTR(err); } /* * Copy task tsk's utsname namespace, or clone it if flags * specifies CLONE_NEWUTS. In latter case, changes to the * utsname of this process won't be seen by parent, and vice * versa. */ struct uts_namespace *copy_utsname(unsigned long flags, struct user_namespace *user_ns, struct uts_namespace *old_ns) { struct uts_namespace *new_ns; BUG_ON(!old_ns); get_uts_ns(old_ns); if (!(flags & CLONE_NEWUTS)) return old_ns; new_ns = clone_uts_ns(user_ns, old_ns); put_uts_ns(old_ns); return new_ns; } void free_uts_ns(struct uts_namespace *ns) { dec_uts_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); kmem_cache_free(uts_ns_cache, ns); } static inline struct uts_namespace *to_uts_ns(struct ns_common *ns) { return container_of(ns, struct uts_namespace, ns); } static struct ns_common *utsns_get(struct task_struct *task) { struct uts_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->uts_ns; get_uts_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static void utsns_put(struct ns_common *ns) { put_uts_ns(to_uts_ns(ns)); } static int utsns_install(struct nsset *nsset, struct ns_common *new) { struct nsproxy *nsproxy = nsset->nsproxy; struct uts_namespace *ns = to_uts_ns(new); if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; get_uts_ns(ns); put_uts_ns(nsproxy->uts_ns); nsproxy->uts_ns = ns; return 0; } static struct user_namespace *utsns_owner(struct ns_common *ns) { return to_uts_ns(ns)->user_ns; } const struct proc_ns_operations utsns_operations = { .name = "uts", .type = CLONE_NEWUTS, .get = utsns_get, .put = utsns_put, .install = utsns_install, .owner = utsns_owner, }; void __init uts_ns_init(void) { uts_ns_cache = kmem_cache_create_usercopy( "uts_namespace", sizeof(struct uts_namespace), 0, SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct uts_namespace, name), sizeof_field(struct uts_namespace, name), NULL); } |
| 2 3 3 1 7 7 17 17 17 17 3 3 3 7 11 7 3 4 4 4 1 7 7 3 12 2 10 10 1 3 4 9 1 8 6 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 | // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2010-2011 EIA Electronics, // Kurt Van Dijck <kurt.van.dijck@eia.be> // Copyright (c) 2017-2019 Pengutronix, // Marc Kleine-Budde <kernel@pengutronix.de> // Copyright (c) 2017-2019 Pengutronix, // Oleksij Rempel <kernel@pengutronix.de> /* bus for j1939 remote devices * Since rtnetlink, no real bus is used. */ #include <net/sock.h> #include "j1939-priv.h" static void __j1939_ecu_release(struct kref *kref) { struct j1939_ecu *ecu = container_of(kref, struct j1939_ecu, kref); struct j1939_priv *priv = ecu->priv; list_del(&ecu->list); kfree(ecu); j1939_priv_put(priv); } void j1939_ecu_put(struct j1939_ecu *ecu) { kref_put(&ecu->kref, __j1939_ecu_release); } static void j1939_ecu_get(struct j1939_ecu *ecu) { kref_get(&ecu->kref); } static bool j1939_ecu_is_mapped_locked(struct j1939_ecu *ecu) { struct j1939_priv *priv = ecu->priv; lockdep_assert_held(&priv->lock); return j1939_ecu_find_by_addr_locked(priv, ecu->addr) == ecu; } /* ECU device interface */ /* map ECU to a bus address space */ static void j1939_ecu_map_locked(struct j1939_ecu *ecu) { struct j1939_priv *priv = ecu->priv; struct j1939_addr_ent *ent; lockdep_assert_held(&priv->lock); if (!j1939_address_is_unicast(ecu->addr)) return; ent = &priv->ents[ecu->addr]; if (ent->ecu) { netdev_warn(priv->ndev, "Trying to map already mapped ECU, addr: 0x%02x, name: 0x%016llx. Skip it.\n", ecu->addr, ecu->name); return; } j1939_ecu_get(ecu); ent->ecu = ecu; ent->nusers += ecu->nusers; } /* unmap ECU from a bus address space */ void j1939_ecu_unmap_locked(struct j1939_ecu *ecu) { struct j1939_priv *priv = ecu->priv; struct j1939_addr_ent *ent; lockdep_assert_held(&priv->lock); if (!j1939_address_is_unicast(ecu->addr)) return; if (!j1939_ecu_is_mapped_locked(ecu)) return; ent = &priv->ents[ecu->addr]; ent->ecu = NULL; ent->nusers -= ecu->nusers; j1939_ecu_put(ecu); } void j1939_ecu_unmap(struct j1939_ecu *ecu) { write_lock_bh(&ecu->priv->lock); j1939_ecu_unmap_locked(ecu); write_unlock_bh(&ecu->priv->lock); } void j1939_ecu_unmap_all(struct j1939_priv *priv) { int i; write_lock_bh(&priv->lock); for (i = 0; i < ARRAY_SIZE(priv->ents); i++) if (priv->ents[i].ecu) j1939_ecu_unmap_locked(priv->ents[i].ecu); write_unlock_bh(&priv->lock); } void j1939_ecu_timer_start(struct j1939_ecu *ecu) { /* The ECU is held here and released in the * j1939_ecu_timer_handler() or j1939_ecu_timer_cancel(). */ j1939_ecu_get(ecu); /* Schedule timer in 250 msec to commit address change. */ hrtimer_start(&ecu->ac_timer, ms_to_ktime(250), HRTIMER_MODE_REL_SOFT); } void j1939_ecu_timer_cancel(struct j1939_ecu *ecu) { if (hrtimer_cancel(&ecu->ac_timer)) j1939_ecu_put(ecu); } static enum hrtimer_restart j1939_ecu_timer_handler(struct hrtimer *hrtimer) { struct j1939_ecu *ecu = container_of(hrtimer, struct j1939_ecu, ac_timer); struct j1939_priv *priv = ecu->priv; write_lock_bh(&priv->lock); /* TODO: can we test if ecu->addr is unicast before starting * the timer? */ j1939_ecu_map_locked(ecu); /* The corresponding j1939_ecu_get() is in * j1939_ecu_timer_start(). */ j1939_ecu_put(ecu); write_unlock_bh(&priv->lock); return HRTIMER_NORESTART; } struct j1939_ecu *j1939_ecu_create_locked(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); ecu = kzalloc(sizeof(*ecu), gfp_any()); if (!ecu) return ERR_PTR(-ENOMEM); kref_init(&ecu->kref); ecu->addr = J1939_IDLE_ADDR; ecu->name = name; hrtimer_init(&ecu->ac_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); ecu->ac_timer.function = j1939_ecu_timer_handler; INIT_LIST_HEAD(&ecu->list); j1939_priv_get(priv); ecu->priv = priv; list_add_tail(&ecu->list, &priv->ecus); return ecu; } struct j1939_ecu *j1939_ecu_find_by_addr_locked(struct j1939_priv *priv, u8 addr) { lockdep_assert_held(&priv->lock); return priv->ents[addr].ecu; } struct j1939_ecu *j1939_ecu_get_by_addr_locked(struct j1939_priv *priv, u8 addr) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); if (!j1939_address_is_unicast(addr)) return NULL; ecu = j1939_ecu_find_by_addr_locked(priv, addr); if (ecu) j1939_ecu_get(ecu); return ecu; } struct j1939_ecu *j1939_ecu_get_by_addr(struct j1939_priv *priv, u8 addr) { struct j1939_ecu *ecu; read_lock_bh(&priv->lock); ecu = j1939_ecu_get_by_addr_locked(priv, addr); read_unlock_bh(&priv->lock); return ecu; } /* get pointer to ecu without increasing ref counter */ static struct j1939_ecu *j1939_ecu_find_by_name_locked(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); list_for_each_entry(ecu, &priv->ecus, list) { if (ecu->name == name) return ecu; } return NULL; } struct j1939_ecu *j1939_ecu_get_by_name_locked(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); if (!name) return NULL; ecu = j1939_ecu_find_by_name_locked(priv, name); if (ecu) j1939_ecu_get(ecu); return ecu; } struct j1939_ecu *j1939_ecu_get_by_name(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; read_lock_bh(&priv->lock); ecu = j1939_ecu_get_by_name_locked(priv, name); read_unlock_bh(&priv->lock); return ecu; } u8 j1939_name_to_addr(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; int addr = J1939_IDLE_ADDR; if (!name) return J1939_NO_ADDR; read_lock_bh(&priv->lock); ecu = j1939_ecu_find_by_name_locked(priv, name); if (ecu && j1939_ecu_is_mapped_locked(ecu)) /* ecu's SA is registered */ addr = ecu->addr; read_unlock_bh(&priv->lock); return addr; } /* TX addr/name accounting * Transport protocol needs to know if a SA is local or not * These functions originate from userspace manipulating sockets, * so locking is straigforward */ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa) { struct j1939_ecu *ecu; int err = 0; write_lock_bh(&priv->lock); if (j1939_address_is_unicast(sa)) priv->ents[sa].nusers++; if (!name) goto done; ecu = j1939_ecu_get_by_name_locked(priv, name); if (!ecu) ecu = j1939_ecu_create_locked(priv, name); err = PTR_ERR_OR_ZERO(ecu); if (err) goto done; ecu->nusers++; /* TODO: do we care if ecu->addr != sa? */ if (j1939_ecu_is_mapped_locked(ecu)) /* ecu's sa is active already */ priv->ents[ecu->addr].nusers++; done: write_unlock_bh(&priv->lock); return err; } void j1939_local_ecu_put(struct j1939_priv *priv, name_t name, u8 sa) { struct j1939_ecu *ecu; write_lock_bh(&priv->lock); if (j1939_address_is_unicast(sa)) priv->ents[sa].nusers--; if (!name) goto done; ecu = j1939_ecu_find_by_name_locked(priv, name); if (WARN_ON_ONCE(!ecu)) goto done; ecu->nusers--; /* TODO: do we care if ecu->addr != sa? */ if (j1939_ecu_is_mapped_locked(ecu)) /* ecu's sa is active already */ priv->ents[ecu->addr].nusers--; j1939_ecu_put(ecu); done: write_unlock_bh(&priv->lock); } |
| 14505 4 114 701 701 15 281 15724 862 14509 701 281 15 15696 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* I/O iterator iteration building functions. * * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_IOV_ITER_H #define _LINUX_IOV_ITER_H #include <linux/uio.h> #include <linux/bvec.h> typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len, void *priv, void *priv2); typedef size_t (*iov_ustep_f)(void __user *iter_base, size_t progress, size_t len, void *priv, void *priv2); /* * Handle ITER_UBUF. */ static __always_inline size_t iterate_ubuf(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { void __user *base = iter->ubuf; size_t progress = 0, remain; remain = step(base + iter->iov_offset, 0, len, priv, priv2); progress = len - remain; iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_IOVEC. */ static __always_inline size_t iterate_iovec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { const struct iovec *p = iter->__iov; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->__iov; iter->__iov = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_KVEC. */ static __always_inline size_t iterate_kvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct kvec *p = iter->kvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->kvec; iter->kvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_BVEC. */ static __always_inline size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct bio_vec *p = iter->bvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t offset = p->bv_offset + skip, part; void *kaddr = kmap_local_page(p->bv_page + offset / PAGE_SIZE); part = min3(len, (size_t)(p->bv_len - skip), (size_t)(PAGE_SIZE - offset % PAGE_SIZE)); remain = step(kaddr + offset % PAGE_SIZE, progress, part, priv, priv2); kunmap_local(kaddr); consumed = part - remain; len -= consumed; progress += consumed; skip += consumed; if (skip >= p->bv_len) { skip = 0; p++; } if (remain) break; } while (len); iter->nr_segs -= p - iter->bvec; iter->bvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_XARRAY. */ static __always_inline size_t iterate_xarray(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { struct folio *folio; size_t progress = 0; loff_t start = iter->xarray_start + iter->iov_offset; pgoff_t index = start / PAGE_SIZE; XA_STATE(xas, iter->xarray, index); rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) { size_t remain, consumed, offset, part, flen; if (xas_retry(&xas, folio)) continue; if (WARN_ON(xa_is_value(folio))) break; if (WARN_ON(folio_test_hugetlb(folio))) break; offset = offset_in_folio(folio, start + progress); flen = min(folio_size(folio) - offset, len); while (flen) { void *base = kmap_local_folio(folio, offset); part = min_t(size_t, flen, PAGE_SIZE - offset_in_page(offset)); remain = step(base, progress, part, priv, priv2); kunmap_local(base); consumed = part - remain; progress += consumed; len -= consumed; if (remain || len == 0) goto out; flen -= consumed; offset += consumed; } } out: rcu_read_unlock(); iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_DISCARD. */ static __always_inline size_t iterate_discard(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { size_t progress = len; iter->count -= progress; return progress; } /** * iterate_and_advance2 - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @priv2: More data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * Iterate over the next part of an iterator, up to the specified length. The * buffer is presented in segments, which for kernel iteration are broken up by * physical pages and mapped, with the mapped address being presented. * * Two step functions, @step and @ustep, must be provided, one for handling * mapped kernel addresses and the other is given user addresses which have the * potential to fault since no pinning is performed. * * The step functions are passed the address and length of the segment, @priv, * @priv2 and the amount of data so far iterated over (which can, for example, * be added to @priv to point to the right part of a second buffer). The step * functions should return the amount of the segment they didn't process (ie. 0 * indicates complete processsing). * * This function returns the amount of data processed (ie. 0 means nothing was * processed and the value of @len means processes to completion). */ static __always_inline size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f ustep, iov_step_f step) { if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len)) return 0; if (likely(iter_is_ubuf(iter))) return iterate_ubuf(iter, len, priv, priv2, ustep); if (likely(iter_is_iovec(iter))) return iterate_iovec(iter, len, priv, priv2, ustep); if (iov_iter_is_bvec(iter)) return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); } /** * iterate_and_advance - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * As iterate_and_advance2(), but priv2 is always NULL. */ static __always_inline size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv, iov_ustep_f ustep, iov_step_f step) { return iterate_and_advance2(iter, len, priv, NULL, ustep, step); } #endif /* _LINUX_IOV_ITER_H */ |
| 9 9 108 32 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.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; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth kernel library. */ #define pr_fmt(fmt) "Bluetooth: " fmt #include <linux/export.h> #include <net/bluetooth/bluetooth.h> /** * baswap() - Swaps the order of a bd address * @dst: Pointer to a bdaddr_t struct that will store the swapped * bd address. * @src: Pointer to the bdaddr_t struct to be swapped. * * This function reverses the byte order of a Bluetooth device * address. */ void baswap(bdaddr_t *dst, const bdaddr_t *src) { const unsigned char *s = (const unsigned char *)src; unsigned char *d = (unsigned char *)dst; unsigned int i; for (i = 0; i < 6; i++) d[i] = s[5 - i]; } EXPORT_SYMBOL(baswap); /** * bt_to_errno() - Bluetooth error codes to standard errno * @code: Bluetooth error code to be converted * * This function takes a Bluetooth error code as input and convets * it to an equivalent Unix/standard errno value. * * Return: * * If the bt error code is known, an equivalent Unix errno value * is returned. * If the given bt error code is not known, ENOSYS is returned. */ int bt_to_errno(__u16 code) { switch (code) { case 0: return 0; case 0x01: return EBADRQC; case 0x02: return ENOTCONN; case 0x03: return EIO; case 0x04: case 0x3c: return EHOSTDOWN; case 0x05: return EACCES; case 0x06: return EBADE; case 0x07: return ENOMEM; case 0x08: return ETIMEDOUT; case 0x09: return EMLINK; case 0x0a: return EMLINK; case 0x0b: return EALREADY; case 0x0c: return EBUSY; case 0x0d: case 0x0e: case 0x0f: return ECONNREFUSED; case 0x10: return ETIMEDOUT; case 0x11: case 0x27: case 0x29: case 0x20: return EOPNOTSUPP; case 0x12: return EINVAL; case 0x13: case 0x14: case 0x15: return ECONNRESET; case 0x16: return ECONNABORTED; case 0x17: return ELOOP; case 0x18: return EACCES; case 0x1a: return EPROTONOSUPPORT; case 0x1b: return ECONNREFUSED; case 0x19: case 0x1e: case 0x23: case 0x24: case 0x25: return EPROTO; default: return ENOSYS; } } EXPORT_SYMBOL(bt_to_errno); /** * bt_status() - Standard errno value to Bluetooth error code * @err: Unix/standard errno value to be converted * * This function converts a standard/Unix errno value to an * equivalent Bluetooth error code. * * Return: Bluetooth error code. * * If the given errno is not found, 0x1f is returned by default * which indicates an unspecified error. * For err >= 0, no conversion is performed, and the same value * is immediately returned. */ __u8 bt_status(int err) { if (err >= 0) return err; switch (err) { case -EBADRQC: return 0x01; case -ENOTCONN: return 0x02; case -EIO: return 0x03; case -EHOSTDOWN: return 0x04; case -EACCES: return 0x05; case -EBADE: return 0x06; case -ENOMEM: return 0x07; case -ETIMEDOUT: return 0x08; case -EMLINK: return 0x09; case -EALREADY: return 0x0b; case -EBUSY: return 0x0c; case -ECONNREFUSED: return 0x0d; case -EOPNOTSUPP: return 0x11; case -EINVAL: return 0x12; case -ECONNRESET: return 0x13; case -ECONNABORTED: return 0x16; case -ELOOP: return 0x17; case -EPROTONOSUPPORT: return 0x1a; case -EPROTO: return 0x19; default: return 0x1f; } } EXPORT_SYMBOL(bt_status); /** * bt_info() - Log Bluetooth information message * @format: Message's format string */ void bt_info(const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; pr_info("%pV", &vaf); va_end(args); } EXPORT_SYMBOL(bt_info); /** * bt_warn() - Log Bluetooth warning message * @format: Message's format string */ void bt_warn(const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; pr_warn("%pV", &vaf); va_end(args); } EXPORT_SYMBOL(bt_warn); /** * bt_err() - Log Bluetooth error message * @format: Message's format string */ void bt_err(const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; pr_err("%pV", &vaf); va_end(args); } EXPORT_SYMBOL(bt_err); #ifdef CONFIG_BT_FEATURE_DEBUG static bool debug_enable; void bt_dbg_set(bool enable) { debug_enable = enable; } bool bt_dbg_get(void) { return debug_enable; } /** * bt_dbg() - Log Bluetooth debugging message * @format: Message's format string */ void bt_dbg(const char *format, ...) { struct va_format vaf; va_list args; if (likely(!debug_enable)) return; va_start(args, format); vaf.fmt = format; vaf.va = &args; printk(KERN_DEBUG pr_fmt("%pV"), &vaf); va_end(args); } EXPORT_SYMBOL(bt_dbg); #endif /** * bt_warn_ratelimited() - Log rate-limited Bluetooth warning message * @format: Message's format string * * This functions works like bt_warn, but it uses rate limiting * to prevent the message from being logged too often. */ void bt_warn_ratelimited(const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; pr_warn_ratelimited("%pV", &vaf); va_end(args); } EXPORT_SYMBOL(bt_warn_ratelimited); /** * bt_err_ratelimited() - Log rate-limited Bluetooth error message * @format: Message's format string * * This functions works like bt_err, but it uses rate limiting * to prevent the message from being logged too often. */ void bt_err_ratelimited(const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; pr_err_ratelimited("%pV", &vaf); va_end(args); } EXPORT_SYMBOL(bt_err_ratelimited); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * XDR standard data types and function declarations * * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de> * * Based on: * RFC 4506 "XDR: External Data Representation Standard", May 2006 */ #ifndef _SUNRPC_XDR_H_ #define _SUNRPC_XDR_H_ #include <linux/uio.h> #include <asm/byteorder.h> #include <asm/unaligned.h> #include <linux/scatterlist.h> struct bio_vec; struct rpc_rqst; /* * Size of an XDR encoding unit in bytes, i.e. 32 bits, * as defined in Section 3 of RFC 4506. All encoded * XDR data items are aligned on a boundary of 32 bits. */ #define XDR_UNIT sizeof(__be32) /* * Buffer adjustment */ #define XDR_QUADLEN(l) (((l) + 3) >> 2) /* * Generic opaque `network object.' */ #define XDR_MAX_NETOBJ 1024 struct xdr_netobj { unsigned int len; u8 * data; }; /* * Basic structure for transmission/reception of a client XDR message. * Features a header (for a linear buffer containing RPC headers * and the data payload for short messages), and then an array of * pages. * The tail iovec allows you to append data after the page array. Its * main interest is for appending padding to the pages in order to * satisfy the int_32-alignment requirements in RFC1832. * * For the future, we might want to string several of these together * in a list if anybody wants to make use of NFSv4 COMPOUND * operations and/or has a need for scatter/gather involving pages. */ struct xdr_buf { struct kvec head[1], /* RPC header + non-page data */ tail[1]; /* Appended after page data */ struct bio_vec *bvec; struct page ** pages; /* Array of pages */ unsigned int page_base, /* Start of page data */ page_len, /* Length of page data */ flags; /* Flags for data disposition */ #define XDRBUF_READ 0x01 /* target of file read */ #define XDRBUF_WRITE 0x02 /* source of file write */ #define XDRBUF_SPARSE_PAGES 0x04 /* Page array is sparse */ unsigned int buflen, /* Total length of storage buffer */ len; /* Length of XDR encoded message */ }; static inline void xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) { buf->head[0].iov_base = start; buf->head[0].iov_len = len; buf->tail[0].iov_len = 0; buf->pages = NULL; buf->page_len = 0; buf->flags = 0; buf->len = 0; buf->buflen = len; } /* * pre-xdr'ed macros. */ #define xdr_zero cpu_to_be32(0) #define xdr_one cpu_to_be32(1) #define xdr_two cpu_to_be32(2) #define rpc_auth_null cpu_to_be32(RPC_AUTH_NULL) #define rpc_auth_unix cpu_to_be32(RPC_AUTH_UNIX) #define rpc_auth_short cpu_to_be32(RPC_AUTH_SHORT) #define rpc_auth_gss cpu_to_be32(RPC_AUTH_GSS) #define rpc_auth_tls cpu_to_be32(RPC_AUTH_TLS) #define rpc_call cpu_to_be32(RPC_CALL) #define rpc_reply cpu_to_be32(RPC_REPLY) #define rpc_msg_accepted cpu_to_be32(RPC_MSG_ACCEPTED) #define rpc_success cpu_to_be32(RPC_SUCCESS) #define rpc_prog_unavail cpu_to_be32(RPC_PROG_UNAVAIL) #define rpc_prog_mismatch cpu_to_be32(RPC_PROG_MISMATCH) #define rpc_proc_unavail cpu_to_be32(RPC_PROC_UNAVAIL) #define rpc_garbage_args cpu_to_be32(RPC_GARBAGE_ARGS) #define rpc_system_err cpu_to_be32(RPC_SYSTEM_ERR) #define rpc_drop_reply cpu_to_be32(RPC_DROP_REPLY) #define rpc_mismatch cpu_to_be32(RPC_MISMATCH) #define rpc_auth_error cpu_to_be32(RPC_AUTH_ERROR) #define rpc_auth_ok cpu_to_be32(RPC_AUTH_OK) #define rpc_autherr_badcred cpu_to_be32(RPC_AUTH_BADCRED) #define rpc_autherr_rejectedcred cpu_to_be32(RPC_AUTH_REJECTEDCRED) #define rpc_autherr_badverf cpu_to_be32(RPC_AUTH_BADVERF) #define rpc_autherr_rejectedverf cpu_to_be32(RPC_AUTH_REJECTEDVERF) #define rpc_autherr_tooweak cpu_to_be32(RPC_AUTH_TOOWEAK) #define rpcsec_gsserr_credproblem cpu_to_be32(RPCSEC_GSS_CREDPROBLEM) #define rpcsec_gsserr_ctxproblem cpu_to_be32(RPCSEC_GSS_CTXPROBLEM) /* * Miscellaneous XDR helper functions */ __be32 *xdr_encode_opaque_fixed(__be32 *p, const void *ptr, unsigned int len); __be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int len); __be32 *xdr_encode_string(__be32 *p, const char *s); __be32 *xdr_decode_string_inplace(__be32 *p, char **sp, unsigned int *lenp, unsigned int maxlen); __be32 *xdr_encode_netobj(__be32 *p, const struct xdr_netobj *); __be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *); void xdr_inline_pages(struct xdr_buf *, unsigned int, struct page **, unsigned int, unsigned int); void xdr_terminate_string(const struct xdr_buf *, const u32); size_t xdr_buf_pagecount(const struct xdr_buf *buf); int xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp); void xdr_free_bvec(struct xdr_buf *buf); unsigned int xdr_buf_to_bvec(struct bio_vec *bvec, unsigned int bvec_size, const struct xdr_buf *xdr); static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int len) { return xdr_encode_opaque(p, s, len); } /* * Decode 64bit quantities (NFSv3 support) */ static inline __be32 * xdr_encode_hyper(__be32 *p, __u64 val) { put_unaligned_be64(val, p); return p + 2; } static inline __be32 * xdr_decode_hyper(__be32 *p, __u64 *valp) { *valp = get_unaligned_be64(p); return p + 2; } static inline __be32 * xdr_decode_opaque_fixed(__be32 *p, void *ptr, unsigned int len) { memcpy(ptr, p, len); return p + XDR_QUADLEN(len); } static inline void xdr_netobj_dup(struct xdr_netobj *dst, struct xdr_netobj *src, gfp_t gfp_mask) { dst->data = kmemdup(src->data, src->len, gfp_mask); dst->len = src->len; } /* * Adjust kvec to reflect end of xdr'ed data (RPC client XDR) */ static inline int xdr_adjust_iovec(struct kvec *iov, __be32 *p) { return iov->iov_len = ((u8 *) p - (u8 *) iov->iov_base); } /* * XDR buffer helper functions */ extern void xdr_buf_from_iov(const struct kvec *, struct xdr_buf *); extern int xdr_buf_subsegment(const struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int); extern void xdr_buf_trim(struct xdr_buf *, unsigned int); extern int read_bytes_from_xdr_buf(const struct xdr_buf *, unsigned int, void *, unsigned int); extern int write_bytes_to_xdr_buf(const struct xdr_buf *, unsigned int, void *, unsigned int); extern int xdr_encode_word(const struct xdr_buf *, unsigned int, u32); extern int xdr_decode_word(const struct xdr_buf *, unsigned int, u32 *); struct xdr_array2_desc; typedef int (*xdr_xcode_elem_t)(struct xdr_array2_desc *desc, void *elem); struct xdr_array2_desc { unsigned int elem_size; unsigned int array_len; unsigned int array_maxlen; xdr_xcode_elem_t xcode; }; extern int xdr_decode_array2(const struct xdr_buf *buf, unsigned int base, struct xdr_array2_desc *desc); extern int xdr_encode_array2(const struct xdr_buf *buf, unsigned int base, struct xdr_array2_desc *desc); extern void _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len); /* * Provide some simple tools for XDR buffer overflow-checking etc. */ struct xdr_stream { __be32 *p; /* start of available buffer */ struct xdr_buf *buf; /* XDR buffer to read/write */ __be32 *end; /* end of available buffer space */ struct kvec *iov; /* pointer to the current kvec */ struct kvec scratch; /* Scratch buffer */ struct page **page_ptr; /* pointer to the current page */ void *page_kaddr; /* kmapped address of the current page */ unsigned int nwords; /* Remaining decode buffer length */ struct rpc_rqst *rqst; /* For debugging */ }; /* * These are the xdr_stream style generic XDR encode and decode functions. */ typedef void (*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, const void *obj); typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, void *obj); extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst); extern void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, struct page **pages, struct rpc_rqst *rqst); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); extern int xdr_reserve_space_vec(struct xdr_stream *xdr, size_t nbytes); extern void __xdr_commit_encode(struct xdr_stream *xdr); extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len); extern void xdr_truncate_decode(struct xdr_stream *xdr, size_t len); extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int base, unsigned int len); extern unsigned int xdr_stream_pos(const struct xdr_stream *xdr); extern unsigned int xdr_page_pos(const struct xdr_stream *xdr); extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst); extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, struct page **pages, unsigned int len); extern void xdr_finish_decode(struct xdr_stream *xdr); extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); extern int xdr_process_buf(const struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data); extern void xdr_set_pagelen(struct xdr_stream *, unsigned int len); extern bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf, unsigned int len); extern unsigned int xdr_stream_move_subsegment(struct xdr_stream *xdr, unsigned int offset, unsigned int target, unsigned int length); extern unsigned int xdr_stream_zero(struct xdr_stream *xdr, unsigned int offset, unsigned int length); /** * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data. * @xdr: pointer to xdr_stream struct * @buf: pointer to an empty buffer * @buflen: size of 'buf' * * The scratch buffer is used when decoding from an array of pages. * If an xdr_inline_decode() call spans across page boundaries, then * we copy the data into the scratch buffer in order to allow linear * access. */ static inline void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen) { xdr->scratch.iov_base = buf; xdr->scratch.iov_len = buflen; } /** * xdr_set_scratch_page - Attach a scratch buffer for decoding data * @xdr: pointer to xdr_stream struct * @page: an anonymous page * * See xdr_set_scratch_buffer(). */ static inline void xdr_set_scratch_page(struct xdr_stream *xdr, struct page *page) { xdr_set_scratch_buffer(xdr, page_address(page), PAGE_SIZE); } /** * xdr_reset_scratch_buffer - Clear scratch buffer information * @xdr: pointer to xdr_stream struct * * See xdr_set_scratch_buffer(). */ static inline void xdr_reset_scratch_buffer(struct xdr_stream *xdr) { xdr_set_scratch_buffer(xdr, NULL, 0); } /** * xdr_commit_encode - Ensure all data is written to xdr->buf * @xdr: pointer to xdr_stream * * Handle encoding across page boundaries by giving the caller a * temporary location to write to, then later copying the data into * place. __xdr_commit_encode() does that copying. */ static inline void xdr_commit_encode(struct xdr_stream *xdr) { if (unlikely(xdr->scratch.iov_len)) __xdr_commit_encode(xdr); } /** * xdr_stream_remaining - Return the number of bytes remaining in the stream * @xdr: pointer to struct xdr_stream * * Return value: * Number of bytes remaining in @xdr before xdr->end */ static inline size_t xdr_stream_remaining(const struct xdr_stream *xdr) { return xdr->nwords << 2; } ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr, size_t size); ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr, size_t maxlen, gfp_t gfp_flags); ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, size_t size); ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, size_t maxlen, gfp_t gfp_flags); ssize_t xdr_stream_decode_opaque_auth(struct xdr_stream *xdr, u32 *flavor, void **body, unsigned int *body_len); ssize_t xdr_stream_encode_opaque_auth(struct xdr_stream *xdr, u32 flavor, void *body, unsigned int body_len); /** * xdr_align_size - Calculate padded size of an object * @n: Size of an object being XDR encoded (in bytes) * * Return value: * Size (in bytes) of the object including xdr padding */ static inline size_t xdr_align_size(size_t n) { const size_t mask = XDR_UNIT - 1; return (n + mask) & ~mask; } /** * xdr_pad_size - Calculate size of an object's pad * @n: Size of an object being XDR encoded (in bytes) * * This implementation avoids the need for conditional * branches or modulo division. * * Return value: * Size (in bytes) of the needed XDR pad */ static inline size_t xdr_pad_size(size_t n) { return xdr_align_size(n) - n; } /** * xdr_stream_encode_item_present - Encode a "present" list item * @xdr: pointer to xdr_stream * * Return values: * On success, returns length in bytes of XDR buffer consumed * %-EMSGSIZE on XDR buffer overflow */ static inline ssize_t xdr_stream_encode_item_present(struct xdr_stream *xdr) { const size_t len = XDR_UNIT; __be32 *p = xdr_reserve_space(xdr, len); if (unlikely(!p)) return -EMSGSIZE; *p = xdr_one; return len; } /** * xdr_stream_encode_item_absent - Encode a "not present" list item * @xdr: pointer to xdr_stream * * Return values: * On success, returns length in bytes of XDR buffer consumed * %-EMSGSIZE on XDR buffer overflow */ static inline int xdr_stream_encode_item_absent(struct xdr_stream *xdr) { const size_t len = XDR_UNIT; __be32 *p = xdr_reserve_space(xdr, len); if (unlikely(!p)) return -EMSGSIZE; *p = xdr_zero; return len; } /** * xdr_encode_bool - Encode a boolean item * @p: address in a buffer into which to encode * @n: boolean value to encode * * Return value: * Address of item following the encoded boolean */ static inline __be32 *xdr_encode_bool(__be32 *p, u32 n) { *p++ = n ? xdr_one : xdr_zero; return p; } /** * xdr_stream_encode_bool - Encode a boolean item * @xdr: pointer to xdr_stream * @n: boolean value to encode * * Return values: * On success, returns length in bytes of XDR buffer consumed * %-EMSGSIZE on XDR buffer overflow */ static inline int xdr_stream_encode_bool(struct xdr_stream *xdr, __u32 n) { const size_t len = XDR_UNIT; __be32 *p = xdr_reserve_space(xdr, len); if (unlikely(!p)) return -EMSGSIZE; xdr_encode_bool(p, n); return len; } /** * xdr_stream_encode_u32 - Encode a 32-bit integer * @xdr: pointer to xdr_stream * @n: integer to encode * * Return values: * On success, returns length in bytes of XDR buffer consumed * %-EMSGSIZE on XDR buffer overflow */ static inline ssize_t xdr_stream_encode_u32(struct xdr_stream *xdr, __u32 n) { const size_t len = sizeof(n); __be32 *p = xdr_reserve_space(xdr, len); if (unlikely(!p)) return -EMSGSIZE; *p = cpu_to_be32(n); return len; } /** * xdr_stream_encode_be32 - Encode a big-endian 32-bit integer * @xdr: pointer to xdr_stream * @n: integer to encode * * Return values: * On success, returns length in bytes of XDR buffer consumed * %-EMSGSIZE on XDR buffer overflow */ static inline ssize_t xdr_stream_encode_be32(struct xdr_stream *xdr, __be32 n) { const size_t len = sizeof(n); __be32 *p = xdr_reserve_space(xdr, len); if (unlikely(!p)) return -EMSGSIZE; *p = n; return len; } /** * xdr_stream_encode_u64 - Encode a 64-bit integer * @xdr: pointer to xdr_stream * @n: 64-bit integer to encode * * Return values: * On success, returns length in bytes of XDR buffer consumed * %-EMSGSIZE on XDR buffer overflow */ static inline ssize_t xdr_stream_encode_u64(struct xdr_stream *xdr, __u64 n) { const size_t len = sizeof(n); __be32 *p = xdr_reserve_space(xdr, len); if (unlikely(!p)) return -EMSGSIZE; xdr_encode_hyper(p, n); return len; } /** * xdr_stream_encode_opaque_inline - Encode opaque xdr data * @xdr: pointer to xdr_stream * @ptr: pointer to void pointer * @len: size of object * * Return values: * On success, returns length in bytes of XDR buffer consumed * %-EMSGSIZE on XDR buffer overflow */ static inline ssize_t xdr_stream_encode_opaque_inline(struct xdr_stream *xdr, void **ptr, size_t len) { size_t count = sizeof(__u32) + xdr_align_size(len); __be32 *p = xdr_reserve_space(xdr, count); if (unlikely(!p)) { *ptr = NULL; return -EMSGSIZE; } xdr_encode_opaque(p, NULL, len); *ptr = ++p; return count; } /** * xdr_stream_encode_opaque_fixed - Encode fixed length opaque xdr data * @xdr: pointer to xdr_stream * @ptr: pointer to opaque data object * @len: size of object pointed to by @ptr * * Return values: * On success, returns length in bytes of XDR buffer consumed * %-EMSGSIZE on XDR buffer overflow */ static inline ssize_t xdr_stream_encode_opaque_fixed(struct xdr_stream *xdr, const void *ptr, size_t len) { __be32 *p = xdr_reserve_space(xdr, len); if (unlikely(!p)) return -EMSGSIZE; xdr_encode_opaque_fixed(p, ptr, len); return xdr_align_size(len); } /** * xdr_stream_encode_opaque - Encode variable length opaque xdr data * @xdr: pointer to xdr_stream * @ptr: pointer to opaque data object * @len: size of object pointed to by @ptr * * Return values: * On success, returns length in bytes of XDR buffer consumed * %-EMSGSIZE on XDR buffer overflow */ static inline ssize_t xdr_stream_encode_opaque(struct xdr_stream *xdr, const void *ptr, size_t len) { size_t count = sizeof(__u32) + xdr_align_size(len); __be32 *p = xdr_reserve_space(xdr, count); if (unlikely(!p)) return -EMSGSIZE; xdr_encode_opaque(p, ptr, len); return count; } /** * xdr_stream_encode_uint32_array - Encode variable length array of integers * @xdr: pointer to xdr_stream * @array: array of integers * @array_size: number of elements in @array * * Return values: * On success, returns length in bytes of XDR buffer consumed * %-EMSGSIZE on XDR buffer overflow */ static inline ssize_t xdr_stream_encode_uint32_array(struct xdr_stream *xdr, const __u32 *array, size_t array_size) { ssize_t ret = (array_size+1) * sizeof(__u32); __be32 *p = xdr_reserve_space(xdr, ret); if (unlikely(!p)) return -EMSGSIZE; *p++ = cpu_to_be32(array_size); for (; array_size > 0; p++, array++, array_size--) *p = cpu_to_be32p(array); return ret; } /** * xdr_item_is_absent - symbolically handle XDR discriminators * @p: pointer to undecoded discriminator * * Return values: * %true if the following XDR item is absent * %false if the following XDR item is present */ static inline bool xdr_item_is_absent(const __be32 *p) { return *p == xdr_zero; } /** * xdr_item_is_present - symbolically handle XDR discriminators * @p: pointer to undecoded discriminator * * Return values: * %true if the following XDR item is present * %false if the following XDR item is absent */ static inline bool xdr_item_is_present(const __be32 *p) { return *p != xdr_zero; } /** * xdr_stream_decode_bool - Decode a boolean * @xdr: pointer to xdr_stream * @ptr: pointer to a u32 in which to store the result * * Return values: * %0 on success * %-EBADMSG on XDR buffer overflow */ static inline ssize_t xdr_stream_decode_bool(struct xdr_stream *xdr, __u32 *ptr) { const size_t count = sizeof(*ptr); __be32 *p = xdr_inline_decode(xdr, count); if (unlikely(!p)) return -EBADMSG; *ptr = (*p != xdr_zero); return 0; } /** * xdr_stream_decode_u32 - Decode a 32-bit integer * @xdr: pointer to xdr_stream * @ptr: location to store integer * * Return values: * %0 on success * %-EBADMSG on XDR buffer overflow */ static inline ssize_t xdr_stream_decode_u32(struct xdr_stream *xdr, __u32 *ptr) { const size_t count = sizeof(*ptr); __be32 *p = xdr_inline_decode(xdr, count); if (unlikely(!p)) return -EBADMSG; *ptr = be32_to_cpup(p); return 0; } /** * xdr_stream_decode_u64 - Decode a 64-bit integer * @xdr: pointer to xdr_stream * @ptr: location to store 64-bit integer * * Return values: * %0 on success * %-EBADMSG on XDR buffer overflow */ static inline ssize_t xdr_stream_decode_u64(struct xdr_stream *xdr, __u64 *ptr) { const size_t count = sizeof(*ptr); __be32 *p = xdr_inline_decode(xdr, count); if (unlikely(!p)) return -EBADMSG; xdr_decode_hyper(p, ptr); return 0; } /** * xdr_stream_decode_opaque_fixed - Decode fixed length opaque xdr data * @xdr: pointer to xdr_stream * @ptr: location to store data * @len: size of buffer pointed to by @ptr * * Return values: * On success, returns size of object stored in @ptr * %-EBADMSG on XDR buffer overflow */ static inline ssize_t xdr_stream_decode_opaque_fixed(struct xdr_stream *xdr, void *ptr, size_t len) { __be32 *p = xdr_inline_decode(xdr, len); if (unlikely(!p)) return -EBADMSG; xdr_decode_opaque_fixed(p, ptr, len); return len; } /** * xdr_stream_decode_opaque_inline - Decode variable length opaque xdr data * @xdr: pointer to xdr_stream * @ptr: location to store pointer to opaque data * @maxlen: maximum acceptable object size * * Note: the pointer stored in @ptr cannot be assumed valid after the XDR * buffer has been destroyed, or even after calling xdr_inline_decode() * on @xdr. It is therefore expected that the object it points to should * be processed immediately. * * Return values: * On success, returns size of object stored in *@ptr * %-EBADMSG on XDR buffer overflow * %-EMSGSIZE if the size of the object would exceed @maxlen */ static inline ssize_t xdr_stream_decode_opaque_inline(struct xdr_stream *xdr, void **ptr, size_t maxlen) { __be32 *p; __u32 len; *ptr = NULL; if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return -EBADMSG; if (len != 0) { p = xdr_inline_decode(xdr, len); if (unlikely(!p)) return -EBADMSG; if (unlikely(len > maxlen)) return -EMSGSIZE; *ptr = p; } return len; } /** * xdr_stream_decode_uint32_array - Decode variable length array of integers * @xdr: pointer to xdr_stream * @array: location to store the integer array or NULL * @array_size: number of elements to store * * Return values: * On success, returns number of elements stored in @array * %-EBADMSG on XDR buffer overflow * %-EMSGSIZE if the size of the array exceeds @array_size */ static inline ssize_t xdr_stream_decode_uint32_array(struct xdr_stream *xdr, __u32 *array, size_t array_size) { __be32 *p; __u32 len; ssize_t retval; if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return -EBADMSG; if (U32_MAX >= SIZE_MAX / sizeof(*p) && len > SIZE_MAX / sizeof(*p)) return -EBADMSG; p = xdr_inline_decode(xdr, len * sizeof(*p)); if (unlikely(!p)) return -EBADMSG; if (array == NULL) return len; if (len <= array_size) { if (len < array_size) memset(array+len, 0, (array_size-len)*sizeof(*array)); array_size = len; retval = len; } else retval = -EMSGSIZE; for (; array_size > 0; p++, array++, array_size--) *array = be32_to_cpup(p); return retval; } #endif /* _SUNRPC_XDR_H_ */ |
| 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #ifndef _CORE_PRIV_H #define _CORE_PRIV_H #include <linux/list.h> #include <linux/spinlock.h> #include <linux/cgroup_rdma.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <rdma/ib_verbs.h> #include <rdma/opa_addr.h> #include <rdma/ib_mad.h> #include <rdma/restrack.h> #include "mad_priv.h" #include "restrack.h" /* Total number of ports combined across all struct ib_devices's */ #define RDMA_MAX_PORTS 8192 struct pkey_index_qp_list { struct list_head pkey_index_list; u16 pkey_index; /* Lock to hold while iterating the qp_list. */ spinlock_t qp_list_lock; struct list_head qp_list; }; /** * struct rdma_dev_net - rdma net namespace metadata for a net * @nl_sock: Pointer to netlink socket * @net: Pointer to owner net namespace * @id: xarray id to identify the net namespace. */ struct rdma_dev_net { struct sock *nl_sock; possible_net_t net; u32 id; }; extern const struct attribute_group ib_dev_attr_group; extern bool ib_devices_shared_netns; extern unsigned int rdma_dev_net_id; static inline struct rdma_dev_net *rdma_net_to_dev_net(struct net *net) { return net_generic(net, rdma_dev_net_id); } int ib_device_rename(struct ib_device *ibdev, const char *name); int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim); typedef void (*roce_netdev_callback)(struct ib_device *device, u32 port, struct net_device *idev, void *cookie); typedef bool (*roce_netdev_filter)(struct ib_device *device, u32 port, struct net_device *idev, void *cookie); struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, u32 port); void ib_enum_roce_netdev(struct ib_device *ib_dev, roce_netdev_filter filter, void *filter_cookie, roce_netdev_callback cb, void *cookie); void ib_enum_all_roce_netdevs(roce_netdev_filter filter, void *filter_cookie, roce_netdev_callback cb, void *cookie); typedef int (*nldev_callback)(struct ib_device *device, struct sk_buff *skb, struct netlink_callback *cb, unsigned int idx); int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb, struct netlink_callback *cb); struct ib_client_nl_info { struct sk_buff *nl_msg; struct device *cdev; u32 port; u64 abi; }; int ib_get_client_nl_info(struct ib_device *ibdev, const char *client_name, struct ib_client_nl_info *res); enum ib_cache_gid_default_mode { IB_CACHE_GID_DEFAULT_MODE_SET, IB_CACHE_GID_DEFAULT_MODE_DELETE }; int ib_cache_gid_parse_type_str(const char *buf); const char *ib_cache_gid_type_str(enum ib_gid_type gid_type); void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u32 port, struct net_device *ndev, unsigned long gid_type_mask, enum ib_cache_gid_default_mode mode); int ib_cache_gid_add(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr); int ib_cache_gid_del(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr); int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev); int roce_gid_mgmt_init(void); void roce_gid_mgmt_cleanup(void); unsigned long roce_gid_type_mask_support(struct ib_device *ib_dev, u32 port); int ib_cache_setup_one(struct ib_device *device); void ib_cache_cleanup_one(struct ib_device *device); void ib_cache_release_one(struct ib_device *device); void ib_dispatch_event_clients(struct ib_event *event); #ifdef CONFIG_CGROUP_RDMA void ib_device_register_rdmacg(struct ib_device *device); void ib_device_unregister_rdmacg(struct ib_device *device); int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index); void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index); #else static inline void ib_device_register_rdmacg(struct ib_device *device) { } static inline void ib_device_unregister_rdmacg(struct ib_device *device) { } static inline int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index) { return 0; } static inline void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index) { } #endif static inline bool rdma_is_upper_dev_rcu(struct net_device *dev, struct net_device *upper) { return netdev_has_upper_dev_all_rcu(dev, upper); } int addr_init(void); void addr_cleanup(void); int ib_mad_init(void); void ib_mad_cleanup(void); int ib_sa_init(void); void ib_sa_cleanup(void); void rdma_nl_init(void); void rdma_nl_exit(void); int ib_nl_handle_resolve_resp(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); int ib_nl_handle_set_timeout(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); int ib_nl_handle_ip_res_resp(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); void ib_get_cached_subnet_prefix(struct ib_device *device, u32 port_num, u64 *sn_pfx); #ifdef CONFIG_SECURITY_INFINIBAND void ib_security_release_port_pkey_list(struct ib_device *device); void ib_security_cache_change(struct ib_device *device, u32 port_num, u64 subnet_prefix); int ib_security_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata); int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev); void ib_destroy_qp_security_begin(struct ib_qp_security *sec); void ib_destroy_qp_security_abort(struct ib_qp_security *sec); void ib_destroy_qp_security_end(struct ib_qp_security *sec); int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev); void ib_close_shared_qp_security(struct ib_qp_security *sec); int ib_mad_agent_security_setup(struct ib_mad_agent *agent, enum ib_qp_type qp_type); void ib_mad_agent_security_cleanup(struct ib_mad_agent *agent); int ib_mad_enforce_security(struct ib_mad_agent_private *map, u16 pkey_index); void ib_mad_agent_security_change(void); #else static inline void ib_security_release_port_pkey_list(struct ib_device *device) { } static inline void ib_security_cache_change(struct ib_device *device, u32 port_num, u64 subnet_prefix) { } static inline int ib_security_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata) { return qp->device->ops.modify_qp(qp->real_qp, qp_attr, qp_attr_mask, udata); } static inline int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev) { return 0; } static inline void ib_destroy_qp_security_begin(struct ib_qp_security *sec) { } static inline void ib_destroy_qp_security_abort(struct ib_qp_security *sec) { } static inline void ib_destroy_qp_security_end(struct ib_qp_security *sec) { } static inline int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev) { return 0; } static inline void ib_close_shared_qp_security(struct ib_qp_security *sec) { } static inline int ib_mad_agent_security_setup(struct ib_mad_agent *agent, enum ib_qp_type qp_type) { return 0; } static inline void ib_mad_agent_security_cleanup(struct ib_mad_agent *agent) { } static inline int ib_mad_enforce_security(struct ib_mad_agent_private *map, u16 pkey_index) { return 0; } static inline void ib_mad_agent_security_change(void) { } #endif struct ib_device *ib_device_get_by_index(const struct net *net, u32 index); /* RDMA device netlink */ void nldev_init(void); void nldev_exit(void); struct ib_qp *ib_create_qp_user(struct ib_device *dev, struct ib_pd *pd, struct ib_qp_init_attr *attr, struct ib_udata *udata, struct ib_uqp_object *uobj, const char *caller); void ib_qp_usecnt_inc(struct ib_qp *qp); void ib_qp_usecnt_dec(struct ib_qp *qp); struct rdma_dev_addr; int rdma_resolve_ip_route(struct sockaddr *src_addr, const struct sockaddr *dst_addr, struct rdma_dev_addr *addr); int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid, const union ib_gid *dgid, u8 *dmac, const struct ib_gid_attr *sgid_attr, int *hoplimit); void rdma_copy_src_l2_addr(struct rdma_dev_addr *dev_addr, const struct net_device *dev); struct sa_path_rec; int roce_resolve_route_from_path(struct sa_path_rec *rec, const struct ib_gid_attr *attr); struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr); void ib_free_port_attrs(struct ib_core_device *coredev); int ib_setup_port_attrs(struct ib_core_device *coredev); struct rdma_hw_stats *ib_get_hw_stats_port(struct ib_device *ibdev, u32 port_num); void ib_device_release_hw_stats(struct hw_stats_device_data *data); int ib_setup_device_attrs(struct ib_device *ibdev); int rdma_compatdev_set(u8 enable); int ib_port_register_client_groups(struct ib_device *ibdev, u32 port_num, const struct attribute_group **groups); void ib_port_unregister_client_groups(struct ib_device *ibdev, u32 port_num, const struct attribute_group **groups); int ib_device_set_netns_put(struct sk_buff *skb, struct ib_device *dev, u32 ns_fd); int rdma_nl_net_init(struct rdma_dev_net *rnet); void rdma_nl_net_exit(struct rdma_dev_net *rnet); struct rdma_umap_priv { struct vm_area_struct *vma; struct list_head list; struct rdma_user_mmap_entry *entry; }; void rdma_umap_priv_init(struct rdma_umap_priv *priv, struct vm_area_struct *vma, struct rdma_user_mmap_entry *entry); void ib_cq_pool_cleanup(struct ib_device *dev); bool rdma_nl_get_privileged_qkey(void); #endif /* _CORE_PRIV_H */ |
| 4 4 16 22 20 4 1 3 5 5 1 3 3 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 | /* * algif_rng: User-space interface for random number generators * * This file provides the user-space API for random number generators. * * Copyright (C) 2014, Stephan Mueller <smueller@chronox.de> * * 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, and the entire permission notice in its entirety, * including the disclaimer of warranties. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. The name of the author may not be used to endorse or promote * products derived from this software without specific prior * written permission. * * ALTERNATIVELY, this product may be distributed under the terms of * the GNU General Public License, in which case the provisions of the GPL2 * are required INSTEAD OF the above restrictions. (This clause is * necessary due to a potential bad interaction between the GPL and * the restrictions contained in a BSD-style copyright.) * * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF * WHICH ARE HEREBY DISCLAIMED. IN NO EVENT SHALL THE AUTHOR 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 NOT ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. */ #include <linux/capability.h> #include <linux/module.h> #include <crypto/rng.h> #include <linux/random.h> #include <crypto/if_alg.h> #include <linux/net.h> #include <net/sock.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Stephan Mueller <smueller@chronox.de>"); MODULE_DESCRIPTION("User-space interface for random number generators"); struct rng_ctx { #define MAXSIZE 128 unsigned int len; struct crypto_rng *drng; u8 *addtl; size_t addtl_len; }; struct rng_parent_ctx { struct crypto_rng *drng; u8 *entropy; }; static void rng_reset_addtl(struct rng_ctx *ctx) { kfree_sensitive(ctx->addtl); ctx->addtl = NULL; ctx->addtl_len = 0; } static int _rng_recvmsg(struct crypto_rng *drng, struct msghdr *msg, size_t len, u8 *addtl, size_t addtl_len) { int err = 0; int genlen = 0; u8 result[MAXSIZE]; if (len == 0) return 0; if (len > MAXSIZE) len = MAXSIZE; /* * although not strictly needed, this is a precaution against coding * errors */ memset(result, 0, len); /* * The enforcement of a proper seeding of an RNG is done within an * RNG implementation. Some RNGs (DRBG, krng) do not need specific * seeding as they automatically seed. The X9.31 DRNG will return * an error if it was not seeded properly. */ genlen = crypto_rng_generate(drng, addtl, addtl_len, result, len); if (genlen < 0) return genlen; err = memcpy_to_msg(msg, result, len); memzero_explicit(result, len); return err ? err : len; } static int rng_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct rng_ctx *ctx = ask->private; return _rng_recvmsg(ctx->drng, msg, len, NULL, 0); } static int rng_test_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct rng_ctx *ctx = ask->private; int ret; lock_sock(sock->sk); ret = _rng_recvmsg(ctx->drng, msg, len, ctx->addtl, ctx->addtl_len); rng_reset_addtl(ctx); release_sock(sock->sk); return ret; } static int rng_test_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { int err; struct alg_sock *ask = alg_sk(sock->sk); struct rng_ctx *ctx = ask->private; lock_sock(sock->sk); if (len > MAXSIZE) { err = -EMSGSIZE; goto unlock; } rng_reset_addtl(ctx); ctx->addtl = kmalloc(len, GFP_KERNEL); if (!ctx->addtl) { err = -ENOMEM; goto unlock; } err = memcpy_from_msg(ctx->addtl, msg, len); if (err) { rng_reset_addtl(ctx); goto unlock; } ctx->addtl_len = len; unlock: release_sock(sock->sk); return err ? err : len; } static struct proto_ops algif_rng_ops = { .family = PF_ALG, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, .bind = sock_no_bind, .accept = sock_no_accept, .sendmsg = sock_no_sendmsg, .release = af_alg_release, .recvmsg = rng_recvmsg, }; static struct proto_ops __maybe_unused algif_rng_test_ops = { .family = PF_ALG, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, .bind = sock_no_bind, .accept = sock_no_accept, .release = af_alg_release, .recvmsg = rng_test_recvmsg, .sendmsg = rng_test_sendmsg, }; static void *rng_bind(const char *name, u32 type, u32 mask) { struct rng_parent_ctx *pctx; struct crypto_rng *rng; pctx = kzalloc(sizeof(*pctx), GFP_KERNEL); if (!pctx) return ERR_PTR(-ENOMEM); rng = crypto_alloc_rng(name, type, mask); if (IS_ERR(rng)) { kfree(pctx); return ERR_CAST(rng); } pctx->drng = rng; return pctx; } static void rng_release(void *private) { struct rng_parent_ctx *pctx = private; if (unlikely(!pctx)) return; crypto_free_rng(pctx->drng); kfree_sensitive(pctx->entropy); kfree_sensitive(pctx); } static void rng_sock_destruct(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct rng_ctx *ctx = ask->private; rng_reset_addtl(ctx); sock_kfree_s(sk, ctx, ctx->len); af_alg_release_parent(sk); } static int rng_accept_parent(void *private, struct sock *sk) { struct rng_ctx *ctx; struct rng_parent_ctx *pctx = private; struct alg_sock *ask = alg_sk(sk); unsigned int len = sizeof(*ctx); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->len = len; ctx->addtl = NULL; ctx->addtl_len = 0; /* * No seeding done at that point -- if multiple accepts are * done on one RNG instance, each resulting FD points to the same * state of the RNG. */ ctx->drng = pctx->drng; ask->private = ctx; sk->sk_destruct = rng_sock_destruct; /* * Non NULL pctx->entropy means that CAVP test has been initiated on * this socket, replace proto_ops algif_rng_ops with algif_rng_test_ops. */ if (IS_ENABLED(CONFIG_CRYPTO_USER_API_RNG_CAVP) && pctx->entropy) sk->sk_socket->ops = &algif_rng_test_ops; return 0; } static int rng_setkey(void *private, const u8 *seed, unsigned int seedlen) { struct rng_parent_ctx *pctx = private; /* * Check whether seedlen is of sufficient size is done in RNG * implementations. */ return crypto_rng_reset(pctx->drng, seed, seedlen); } static int __maybe_unused rng_setentropy(void *private, sockptr_t entropy, unsigned int len) { struct rng_parent_ctx *pctx = private; u8 *kentropy = NULL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (pctx->entropy) return -EINVAL; if (len > MAXSIZE) return -EMSGSIZE; if (len) { kentropy = memdup_sockptr(entropy, len); if (IS_ERR(kentropy)) return PTR_ERR(kentropy); } crypto_rng_alg(pctx->drng)->set_ent(pctx->drng, kentropy, len); /* * Since rng doesn't perform any memory management for the entropy * buffer, save kentropy pointer to pctx now to free it after use. */ pctx->entropy = kentropy; return 0; } static const struct af_alg_type algif_type_rng = { .bind = rng_bind, .release = rng_release, .accept = rng_accept_parent, .setkey = rng_setkey, #ifdef CONFIG_CRYPTO_USER_API_RNG_CAVP .setentropy = rng_setentropy, #endif .ops = &algif_rng_ops, .name = "rng", .owner = THIS_MODULE }; static int __init rng_init(void) { return af_alg_register_type(&algif_type_rng); } static void __exit rng_exit(void) { int err = af_alg_unregister_type(&algif_type_rng); BUG_ON(err); } module_init(rng_init); module_exit(rng_exit); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * bio-integrity.c - bio data integrity extensions * * Copyright (C) 2007, 2008, 2009 Oracle Corporation * Written by: Martin K. Petersen <martin.petersen@oracle.com> */ #include <linux/blk-integrity.h> #include <linux/mempool.h> #include <linux/export.h> #include <linux/bio.h> #include <linux/workqueue.h> #include <linux/slab.h> #include "blk.h" static struct kmem_cache *bip_slab; static struct workqueue_struct *kintegrityd_wq; void blk_flush_integrity(void) { flush_workqueue(kintegrityd_wq); } static void __bio_integrity_free(struct bio_set *bs, struct bio_integrity_payload *bip) { if (bs && mempool_initialized(&bs->bio_integrity_pool)) { if (bip->bip_vec) bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_max_vcnt); mempool_free(bip, &bs->bio_integrity_pool); } else { kfree(bip); } } /** * bio_integrity_alloc - Allocate integrity payload and attach it to bio * @bio: bio to attach integrity metadata to * @gfp_mask: Memory allocation mask * @nr_vecs: Number of integrity metadata scatter-gather elements * * Description: This function prepares a bio for attaching integrity * metadata. nr_vecs specifies the maximum number of pages containing * integrity metadata that can be attached. */ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp_mask, unsigned int nr_vecs) { struct bio_integrity_payload *bip; struct bio_set *bs = bio->bi_pool; unsigned inline_vecs; if (WARN_ON_ONCE(bio_has_crypt_ctx(bio))) return ERR_PTR(-EOPNOTSUPP); if (!bs || !mempool_initialized(&bs->bio_integrity_pool)) { bip = kmalloc(struct_size(bip, bip_inline_vecs, nr_vecs), gfp_mask); inline_vecs = nr_vecs; } else { bip = mempool_alloc(&bs->bio_integrity_pool, gfp_mask); inline_vecs = BIO_INLINE_VECS; } if (unlikely(!bip)) return ERR_PTR(-ENOMEM); memset(bip, 0, sizeof(*bip)); /* always report as many vecs as asked explicitly, not inline vecs */ bip->bip_max_vcnt = nr_vecs; if (nr_vecs > inline_vecs) { bip->bip_vec = bvec_alloc(&bs->bvec_integrity_pool, &bip->bip_max_vcnt, gfp_mask); if (!bip->bip_vec) goto err; } else { bip->bip_vec = bip->bip_inline_vecs; } bip->bip_bio = bio; bio->bi_integrity = bip; bio->bi_opf |= REQ_INTEGRITY; return bip; err: __bio_integrity_free(bs, bip); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(bio_integrity_alloc); static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs, bool dirty) { int i; for (i = 0; i < nr_vecs; i++) { if (dirty && !PageCompound(bv[i].bv_page)) set_page_dirty_lock(bv[i].bv_page); unpin_user_page(bv[i].bv_page); } } static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip) { unsigned short nr_vecs = bip->bip_max_vcnt - 1; struct bio_vec *copy = &bip->bip_vec[1]; size_t bytes = bip->bip_iter.bi_size; struct iov_iter iter; int ret; iov_iter_bvec(&iter, ITER_DEST, copy, nr_vecs, bytes); ret = copy_to_iter(bvec_virt(bip->bip_vec), bytes, &iter); WARN_ON_ONCE(ret != bytes); bio_integrity_unpin_bvec(copy, nr_vecs, true); } static void bio_integrity_unmap_user(struct bio_integrity_payload *bip) { bool dirty = bio_data_dir(bip->bip_bio) == READ; if (bip->bip_flags & BIP_COPY_USER) { if (dirty) bio_integrity_uncopy_user(bip); kfree(bvec_virt(bip->bip_vec)); return; } bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt, dirty); } /** * bio_integrity_free - Free bio integrity payload * @bio: bio containing bip to be freed * * Description: Used to free the integrity portion of a bio. Usually * called from bio_free(). */ void bio_integrity_free(struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_set *bs = bio->bi_pool; if (bip->bip_flags & BIP_INTEGRITY_USER) return; if (bip->bip_flags & BIP_BLOCK_INTEGRITY) kfree(bvec_virt(bip->bip_vec)); __bio_integrity_free(bs, bip); bio->bi_integrity = NULL; bio->bi_opf &= ~REQ_INTEGRITY; } /** * bio_integrity_unmap_free_user - Unmap and free bio user integrity payload * @bio: bio containing bip to be unmapped and freed * * Description: Used to unmap and free the user mapped integrity portion of a * bio. Submitter attaching the user integrity buffer is responsible for * unmapping and freeing it during completion. */ void bio_integrity_unmap_free_user(struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_set *bs = bio->bi_pool; if (WARN_ON_ONCE(!(bip->bip_flags & BIP_INTEGRITY_USER))) return; bio_integrity_unmap_user(bip); __bio_integrity_free(bs, bip); bio->bi_integrity = NULL; bio->bi_opf &= ~REQ_INTEGRITY; } EXPORT_SYMBOL(bio_integrity_unmap_free_user); /** * bio_integrity_add_page - Attach integrity metadata * @bio: bio to update * @page: page containing integrity metadata * @len: number of bytes of integrity metadata in page * @offset: start offset within page * * Description: Attach a page containing integrity metadata to bio. */ int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct bio_integrity_payload *bip = bio_integrity(bio); if (((bip->bip_iter.bi_size + len) >> SECTOR_SHIFT) > queue_max_hw_sectors(q)) return 0; if (bip->bip_vcnt > 0) { struct bio_vec *bv = &bip->bip_vec[bip->bip_vcnt - 1]; bool same_page = false; if (bvec_try_merge_hw_page(q, bv, page, len, offset, &same_page)) { bip->bip_iter.bi_size += len; return len; } if (bip->bip_vcnt >= min(bip->bip_max_vcnt, queue_max_integrity_segments(q))) return 0; /* * If the queue doesn't support SG gaps and adding this segment * would create a gap, disallow it. */ if (bvec_gap_to_prev(&q->limits, bv, offset)) return 0; } bvec_set_page(&bip->bip_vec[bip->bip_vcnt], page, len, offset); bip->bip_vcnt++; bip->bip_iter.bi_size += len; return len; } EXPORT_SYMBOL(bio_integrity_add_page); static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec, int nr_vecs, unsigned int len, unsigned int direction, u32 seed) { bool write = direction == ITER_SOURCE; struct bio_integrity_payload *bip; struct iov_iter iter; void *buf; int ret; buf = kmalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; if (write) { iov_iter_bvec(&iter, direction, bvec, nr_vecs, len); if (!copy_from_iter_full(buf, len, &iter)) { ret = -EFAULT; goto free_buf; } bip = bio_integrity_alloc(bio, GFP_KERNEL, 1); } else { memset(buf, 0, len); /* * We need to preserve the original bvec and the number of vecs * in it for completion handling */ bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs + 1); } if (IS_ERR(bip)) { ret = PTR_ERR(bip); goto free_buf; } if (write) bio_integrity_unpin_bvec(bvec, nr_vecs, false); else memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec)); ret = bio_integrity_add_page(bio, virt_to_page(buf), len, offset_in_page(buf)); if (ret != len) { ret = -ENOMEM; goto free_bip; } bip->bip_flags |= BIP_INTEGRITY_USER | BIP_COPY_USER; bip->bip_iter.bi_sector = seed; return 0; free_bip: bio_integrity_free(bio); free_buf: kfree(buf); return ret; } static int bio_integrity_init_user(struct bio *bio, struct bio_vec *bvec, int nr_vecs, unsigned int len, u32 seed) { struct bio_integrity_payload *bip; bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs); if (IS_ERR(bip)) return PTR_ERR(bip); memcpy(bip->bip_vec, bvec, nr_vecs * sizeof(*bvec)); bip->bip_flags |= BIP_INTEGRITY_USER; bip->bip_iter.bi_sector = seed; bip->bip_iter.bi_size = len; return 0; } static unsigned int bvec_from_pages(struct bio_vec *bvec, struct page **pages, int nr_vecs, ssize_t bytes, ssize_t offset) { unsigned int nr_bvecs = 0; int i, j; for (i = 0; i < nr_vecs; i = j) { size_t size = min_t(size_t, bytes, PAGE_SIZE - offset); struct folio *folio = page_folio(pages[i]); bytes -= size; for (j = i + 1; j < nr_vecs; j++) { size_t next = min_t(size_t, PAGE_SIZE, bytes); if (page_folio(pages[j]) != folio || pages[j] != pages[j - 1] + 1) break; unpin_user_page(pages[j]); size += next; bytes -= next; } bvec_set_page(&bvec[nr_bvecs], pages[i], size, offset); offset = 0; nr_bvecs++; } return nr_bvecs; } int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes, u32 seed) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); unsigned int align = q->dma_pad_mask | queue_dma_alignment(q); struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages; struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec; unsigned int direction, nr_bvecs; struct iov_iter iter; int ret, nr_vecs; size_t offset; bool copy; if (bio_integrity(bio)) return -EINVAL; if (bytes >> SECTOR_SHIFT > queue_max_hw_sectors(q)) return -E2BIG; if (bio_data_dir(bio) == READ) direction = ITER_DEST; else direction = ITER_SOURCE; iov_iter_ubuf(&iter, direction, ubuf, bytes); nr_vecs = iov_iter_npages(&iter, BIO_MAX_VECS + 1); if (nr_vecs > BIO_MAX_VECS) return -E2BIG; if (nr_vecs > UIO_FASTIOV) { bvec = kcalloc(nr_vecs, sizeof(*bvec), GFP_KERNEL); if (!bvec) return -ENOMEM; pages = NULL; } copy = !iov_iter_is_aligned(&iter, align, align); ret = iov_iter_extract_pages(&iter, &pages, bytes, nr_vecs, 0, &offset); if (unlikely(ret < 0)) goto free_bvec; nr_bvecs = bvec_from_pages(bvec, pages, nr_vecs, bytes, offset); if (pages != stack_pages) kvfree(pages); if (nr_bvecs > queue_max_integrity_segments(q)) copy = true; if (copy) ret = bio_integrity_copy_user(bio, bvec, nr_bvecs, bytes, direction, seed); else ret = bio_integrity_init_user(bio, bvec, nr_bvecs, bytes, seed); if (ret) goto release_pages; if (bvec != stack_vec) kfree(bvec); return 0; release_pages: bio_integrity_unpin_bvec(bvec, nr_bvecs, false); free_bvec: if (bvec != stack_vec) kfree(bvec); return ret; } EXPORT_SYMBOL_GPL(bio_integrity_map_user); /** * bio_integrity_process - Process integrity metadata for a bio * @bio: bio to generate/verify integrity metadata for * @proc_iter: iterator to process * @proc_fn: Pointer to the relevant processing function */ static blk_status_t bio_integrity_process(struct bio *bio, struct bvec_iter *proc_iter, integrity_processing_fn *proc_fn) { struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); struct blk_integrity_iter iter; struct bvec_iter bviter; struct bio_vec bv; struct bio_integrity_payload *bip = bio_integrity(bio); blk_status_t ret = BLK_STS_OK; iter.disk_name = bio->bi_bdev->bd_disk->disk_name; iter.interval = 1 << bi->interval_exp; iter.tuple_size = bi->tuple_size; iter.seed = proc_iter->bi_sector; iter.prot_buf = bvec_virt(bip->bip_vec); iter.pi_offset = bi->pi_offset; __bio_for_each_segment(bv, bio, bviter, *proc_iter) { void *kaddr = bvec_kmap_local(&bv); iter.data_buf = kaddr; iter.data_size = bv.bv_len; ret = proc_fn(&iter); kunmap_local(kaddr); if (ret) break; } return ret; } /** * bio_integrity_prep - Prepare bio for integrity I/O * @bio: bio to prepare * * Description: Checks if the bio already has an integrity payload attached. * If it does, the payload has been generated by another kernel subsystem, * and we just pass it through. Otherwise allocates integrity payload. * The bio must have data direction, target device and start sector set priot * to calling. In the WRITE case, integrity metadata will be generated using * the block device's integrity function. In the READ case, the buffer * will be prepared for DMA and a suitable end_io handler set up. */ bool bio_integrity_prep(struct bio *bio) { struct bio_integrity_payload *bip; struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); void *buf; unsigned long start, end; unsigned int len, nr_pages; unsigned int bytes, offset, i; if (!bi) return true; if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE) return true; if (!bio_sectors(bio)) return true; /* Already protected? */ if (bio_integrity(bio)) return true; if (bio_data_dir(bio) == READ) { if (!bi->profile->verify_fn || !(bi->flags & BLK_INTEGRITY_VERIFY)) return true; } else { if (!bi->profile->generate_fn || !(bi->flags & BLK_INTEGRITY_GENERATE)) return true; } /* Allocate kernel buffer for protection data */ len = bio_integrity_bytes(bi, bio_sectors(bio)); buf = kmalloc(len, GFP_NOIO); if (unlikely(buf == NULL)) { printk(KERN_ERR "could not allocate integrity buffer\n"); goto err_end_io; } end = (((unsigned long) buf) + len + PAGE_SIZE - 1) >> PAGE_SHIFT; start = ((unsigned long) buf) >> PAGE_SHIFT; nr_pages = end - start; /* Allocate bio integrity payload and integrity vectors */ bip = bio_integrity_alloc(bio, GFP_NOIO, nr_pages); if (IS_ERR(bip)) { printk(KERN_ERR "could not allocate data integrity bioset\n"); kfree(buf); goto err_end_io; } bip->bip_flags |= BIP_BLOCK_INTEGRITY; bip_set_seed(bip, bio->bi_iter.bi_sector); if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM) bip->bip_flags |= BIP_IP_CHECKSUM; /* Map it */ offset = offset_in_page(buf); for (i = 0; i < nr_pages && len > 0; i++) { bytes = PAGE_SIZE - offset; if (bytes > len) bytes = len; if (bio_integrity_add_page(bio, virt_to_page(buf), bytes, offset) < bytes) { printk(KERN_ERR "could not attach integrity payload\n"); goto err_end_io; } buf += bytes; len -= bytes; offset = 0; } /* Auto-generate integrity metadata if this is a write */ if (bio_data_dir(bio) == WRITE) { bio_integrity_process(bio, &bio->bi_iter, bi->profile->generate_fn); } else { bip->bio_iter = bio->bi_iter; } return true; err_end_io: bio->bi_status = BLK_STS_RESOURCE; bio_endio(bio); return false; } EXPORT_SYMBOL(bio_integrity_prep); /** * bio_integrity_verify_fn - Integrity I/O completion worker * @work: Work struct stored in bio to be verified * * Description: This workqueue function is called to complete a READ * request. The function verifies the transferred integrity metadata * and then calls the original bio end_io function. */ static void bio_integrity_verify_fn(struct work_struct *work) { struct bio_integrity_payload *bip = container_of(work, struct bio_integrity_payload, bip_work); struct bio *bio = bip->bip_bio; struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); /* * At the moment verify is called bio's iterator was advanced * during split and completion, we need to rewind iterator to * it's original position. */ bio->bi_status = bio_integrity_process(bio, &bip->bio_iter, bi->profile->verify_fn); bio_integrity_free(bio); bio_endio(bio); } /** * __bio_integrity_endio - Integrity I/O completion function * @bio: Protected bio * * Description: Completion for integrity I/O * * Normally I/O completion is done in interrupt context. However, * verifying I/O integrity is a time-consuming task which must be run * in process context. This function postpones completion * accordingly. */ bool __bio_integrity_endio(struct bio *bio) { struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); struct bio_integrity_payload *bip = bio_integrity(bio); if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->profile->verify_fn) { INIT_WORK(&bip->bip_work, bio_integrity_verify_fn); queue_work(kintegrityd_wq, &bip->bip_work); return false; } bio_integrity_free(bio); return true; } /** * bio_integrity_advance - Advance integrity vector * @bio: bio whose integrity vector to update * @bytes_done: number of data bytes that have been completed * * Description: This function calculates how many integrity bytes the * number of completed data bytes correspond to and advances the * integrity vector accordingly. */ void bio_integrity_advance(struct bio *bio, unsigned int bytes_done) { struct bio_integrity_payload *bip = bio_integrity(bio); struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9); bip->bip_iter.bi_sector += bio_integrity_intervals(bi, bytes_done >> 9); bvec_iter_advance(bip->bip_vec, &bip->bip_iter, bytes); } /** * bio_integrity_trim - Trim integrity vector * @bio: bio whose integrity vector to update * * Description: Used to trim the integrity vector in a cloned bio. */ void bio_integrity_trim(struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); bip->bip_iter.bi_size = bio_integrity_bytes(bi, bio_sectors(bio)); } EXPORT_SYMBOL(bio_integrity_trim); /** * bio_integrity_clone - Callback for cloning bios with integrity metadata * @bio: New bio * @bio_src: Original bio * @gfp_mask: Memory allocation mask * * Description: Called to allocate a bip when cloning a bio */ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) { struct bio_integrity_payload *bip_src = bio_integrity(bio_src); struct bio_integrity_payload *bip; BUG_ON(bip_src == NULL); bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt); if (IS_ERR(bip)) return PTR_ERR(bip); memcpy(bip->bip_vec, bip_src->bip_vec, bip_src->bip_vcnt * sizeof(struct bio_vec)); bip->bip_vcnt = bip_src->bip_vcnt; bip->bip_iter = bip_src->bip_iter; bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY; return 0; } int bioset_integrity_create(struct bio_set *bs, int pool_size) { if (mempool_initialized(&bs->bio_integrity_pool)) return 0; if (mempool_init_slab_pool(&bs->bio_integrity_pool, pool_size, bip_slab)) return -1; if (biovec_init_pool(&bs->bvec_integrity_pool, pool_size)) { mempool_exit(&bs->bio_integrity_pool); return -1; } return 0; } EXPORT_SYMBOL(bioset_integrity_create); void bioset_integrity_free(struct bio_set *bs) { mempool_exit(&bs->bio_integrity_pool); mempool_exit(&bs->bvec_integrity_pool); } void __init bio_integrity_init(void) { /* * kintegrityd won't block much but may burn a lot of CPU cycles. * Make it highpri CPU intensive wq with max concurrency of 1. */ kintegrityd_wq = alloc_workqueue("kintegrityd", WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1); if (!kintegrityd_wq) panic("Failed to create kintegrityd\n"); bip_slab = kmem_cache_create("bio_integrity_payload", sizeof(struct bio_integrity_payload) + sizeof(struct bio_vec) * BIO_INLINE_VECS, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); } |
| 739 739 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_H #define _ASM_X86_PAGE_H #include <linux/types.h> #ifdef __KERNEL__ #include <asm/page_types.h> #ifdef CONFIG_X86_64 #include <asm/page_64.h> #else #include <asm/page_32.h> #endif /* CONFIG_X86_64 */ #ifndef __ASSEMBLY__ struct page; #include <linux/range.h> extern struct range pfn_mapped[]; extern int nr_pfn_mapped; static inline void clear_user_page(void *page, unsigned long vaddr, struct page *pg) { clear_page(page); } static inline void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage) { copy_page(to, from); } #define vma_alloc_zeroed_movable_folio(vma, vaddr) \ vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false) #ifndef __pa #define __pa(x) __phys_addr((unsigned long)(x)) #endif #define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) /* __pa_symbol should be used for C visible symbols. This seems to be the official gcc blessed way to do such arithmetic. */ /* * We need __phys_reloc_hide() here because gcc may assume that there is no * overflow during __pa() calculation and can optimize it unexpectedly. * Newer versions of gcc provide -fno-strict-overflow switch to handle this * case properly. Once all supported versions of gcc understand it, we can * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated) */ #define __pa_symbol(x) \ __phys_addr_symbol(__phys_reloc_hide((unsigned long)(x))) #ifndef __va #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) #endif #define __boot_va(x) __va(x) #define __boot_pa(x) __pa(x) /* * virt_to_page(kaddr) returns a valid pointer if and only if * virt_addr_valid(kaddr) returns true. */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) extern bool __virt_addr_valid(unsigned long kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) static __always_inline void *pfn_to_kaddr(unsigned long pfn) { return __va(pfn << PAGE_SHIFT); } static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits) { return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); } static __always_inline u64 __is_canonical_address(u64 vaddr, u8 vaddr_bits) { return __canonical_address(vaddr, vaddr_bits) == vaddr; } #endif /* __ASSEMBLY__ */ #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #endif /* __KERNEL__ */ #endif /* _ASM_X86_PAGE_H */ |
| 5 7 9 9 9 55 55 9 55 55 55 24 19 9 9 248 248 52 52 52 52 11 52 52 52 1 52 1 1 26 11 26 26 26 83 58 24 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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 <trace/events/power.h> #include "power.h" #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. */ void device_wakeup_disable(struct device *dev) { struct wakeup_source *ws; if (!dev || !dev->power.can_wakeup) return; ws = device_wakeup_detach(dev); wakeup_source_unregister(ws); } 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) { if (enable) return device_wakeup_enable(dev); device_wakeup_disable(dev); return 0; } 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_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; 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(); } 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) pm_system_wakeup(); } unsigned int pm_wakeup_irq(void) { return wakeup_irq[0]; } /** * 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); |
| 7 1 1 1 2 2 1 1 2 2 2 1 1 1 1 1 9 9 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * CLC (connection layer control) handshake over initial TCP socket to * prepare for RDMA traffic * * Copyright IBM Corp. 2016, 2018 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #include <linux/in.h> #include <linux/inetdevice.h> #include <linux/if_ether.h> #include <linux/sched/signal.h> #include <linux/utsname.h> #include <linux/ctype.h> #include <net/addrconf.h> #include <net/sock.h> #include <net/tcp.h> #include "smc.h" #include "smc_core.h" #include "smc_clc.h" #include "smc_ib.h" #include "smc_ism.h" #include "smc_netlink.h" #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48 #define SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 78 #define SMCR_CLC_ACCEPT_CONFIRM_LEN_V2 108 #define SMC_CLC_RECV_BUF_LEN 100 /* eye catcher "SMCR" EBCDIC for CLC messages */ static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'}; /* eye catcher "SMCD" EBCDIC for CLC messages */ static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'}; static u8 smc_hostname[SMC_MAX_HOSTNAME_LEN]; struct smc_clc_eid_table { rwlock_t lock; struct list_head list; u8 ueid_cnt; u8 seid_enabled; }; static struct smc_clc_eid_table smc_clc_eid_table; struct smc_clc_eid_entry { struct list_head list; u8 eid[SMC_MAX_EID_LEN]; }; /* The size of a user EID is 32 characters. * Valid characters should be (single-byte character set) A-Z, 0-9, '.' and '-'. * Blanks should only be used to pad to the expected size. * First character must be alphanumeric. */ static bool smc_clc_ueid_valid(char *ueid) { char *end = ueid + SMC_MAX_EID_LEN; while (--end >= ueid && isspace(*end)) ; if (end < ueid) return false; if (!isalnum(*ueid) || islower(*ueid)) return false; while (ueid <= end) { if ((!isalnum(*ueid) || islower(*ueid)) && *ueid != '.' && *ueid != '-') return false; ueid++; } return true; } static int smc_clc_ueid_add(char *ueid) { struct smc_clc_eid_entry *new_ueid, *tmp_ueid; int rc; if (!smc_clc_ueid_valid(ueid)) return -EINVAL; /* add a new ueid entry to the ueid table if there isn't one */ new_ueid = kzalloc(sizeof(*new_ueid), GFP_KERNEL); if (!new_ueid) return -ENOMEM; memcpy(new_ueid->eid, ueid, SMC_MAX_EID_LEN); write_lock(&smc_clc_eid_table.lock); if (smc_clc_eid_table.ueid_cnt >= SMC_MAX_UEID) { rc = -ERANGE; goto err_out; } list_for_each_entry(tmp_ueid, &smc_clc_eid_table.list, list) { if (!memcmp(tmp_ueid->eid, ueid, SMC_MAX_EID_LEN)) { rc = -EEXIST; goto err_out; } } list_add_tail(&new_ueid->list, &smc_clc_eid_table.list); smc_clc_eid_table.ueid_cnt++; write_unlock(&smc_clc_eid_table.lock); return 0; err_out: write_unlock(&smc_clc_eid_table.lock); kfree(new_ueid); return rc; } int smc_clc_ueid_count(void) { int count; read_lock(&smc_clc_eid_table.lock); count = smc_clc_eid_table.ueid_cnt; read_unlock(&smc_clc_eid_table.lock); return count; } int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info) { struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY]; char *ueid; if (!nla_ueid || nla_len(nla_ueid) != SMC_MAX_EID_LEN + 1) return -EINVAL; ueid = (char *)nla_data(nla_ueid); return smc_clc_ueid_add(ueid); } /* remove one or all ueid entries from the table */ static int smc_clc_ueid_remove(char *ueid) { struct smc_clc_eid_entry *lst_ueid, *tmp_ueid; int rc = -ENOENT; /* remove table entry */ write_lock(&smc_clc_eid_table.lock); list_for_each_entry_safe(lst_ueid, tmp_ueid, &smc_clc_eid_table.list, list) { if (!ueid || !memcmp(lst_ueid->eid, ueid, SMC_MAX_EID_LEN)) { list_del(&lst_ueid->list); smc_clc_eid_table.ueid_cnt--; kfree(lst_ueid); rc = 0; } } #if IS_ENABLED(CONFIG_S390) if (!rc && !smc_clc_eid_table.ueid_cnt) { smc_clc_eid_table.seid_enabled = 1; rc = -EAGAIN; /* indicate success and enabling of seid */ } #endif write_unlock(&smc_clc_eid_table.lock); return rc; } int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info) { struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY]; char *ueid; if (!nla_ueid || nla_len(nla_ueid) != SMC_MAX_EID_LEN + 1) return -EINVAL; ueid = (char *)nla_data(nla_ueid); return smc_clc_ueid_remove(ueid); } int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info) { smc_clc_ueid_remove(NULL); return 0; } static int smc_nl_ueid_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, u32 flags, char *ueid) { char ueid_str[SMC_MAX_EID_LEN + 1]; void *hdr; hdr = genlmsg_put(skb, portid, seq, &smc_gen_nl_family, flags, SMC_NETLINK_DUMP_UEID); if (!hdr) return -ENOMEM; memcpy(ueid_str, ueid, SMC_MAX_EID_LEN); ueid_str[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_EID_TABLE_ENTRY, ueid_str)) { genlmsg_cancel(skb, hdr); return -EMSGSIZE; } genlmsg_end(skb, hdr); return 0; } static int _smc_nl_ueid_dump(struct sk_buff *skb, u32 portid, u32 seq, int start_idx) { struct smc_clc_eid_entry *lst_ueid; int idx = 0; read_lock(&smc_clc_eid_table.lock); list_for_each_entry(lst_ueid, &smc_clc_eid_table.list, list) { if (idx++ < start_idx) continue; if (smc_nl_ueid_dumpinfo(skb, portid, seq, NLM_F_MULTI, lst_ueid->eid)) { --idx; break; } } read_unlock(&smc_clc_eid_table.lock); return idx; } int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); int idx; idx = _smc_nl_ueid_dump(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb_ctx->pos[0]); cb_ctx->pos[0] = idx; return skb->len; } int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); char seid_str[SMC_MAX_EID_LEN + 1]; u8 seid_enabled; void *hdr; u8 *seid; if (cb_ctx->pos[0]) return skb->len; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_DUMP_SEID); if (!hdr) return -ENOMEM; if (!smc_ism_is_v2_capable()) goto end; smc_ism_get_system_eid(&seid); memcpy(seid_str, seid, SMC_MAX_EID_LEN); seid_str[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SEID_ENTRY, seid_str)) goto err; read_lock(&smc_clc_eid_table.lock); seid_enabled = smc_clc_eid_table.seid_enabled; read_unlock(&smc_clc_eid_table.lock); if (nla_put_u8(skb, SMC_NLA_SEID_ENABLED, seid_enabled)) goto err; end: genlmsg_end(skb, hdr); cb_ctx->pos[0]++; return skb->len; err: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info) { #if IS_ENABLED(CONFIG_S390) write_lock(&smc_clc_eid_table.lock); smc_clc_eid_table.seid_enabled = 1; write_unlock(&smc_clc_eid_table.lock); return 0; #else return -EOPNOTSUPP; #endif } int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info) { int rc = 0; #if IS_ENABLED(CONFIG_S390) write_lock(&smc_clc_eid_table.lock); if (!smc_clc_eid_table.ueid_cnt) rc = -ENOENT; else smc_clc_eid_table.seid_enabled = 0; write_unlock(&smc_clc_eid_table.lock); #else rc = -EOPNOTSUPP; #endif return rc; } static bool _smc_clc_match_ueid(u8 *peer_ueid) { struct smc_clc_eid_entry *tmp_ueid; list_for_each_entry(tmp_ueid, &smc_clc_eid_table.list, list) { if (!memcmp(tmp_ueid->eid, peer_ueid, SMC_MAX_EID_LEN)) return true; } return false; } bool smc_clc_match_eid(u8 *negotiated_eid, struct smc_clc_v2_extension *smc_v2_ext, u8 *peer_eid, u8 *local_eid) { bool match = false; int i; negotiated_eid[0] = 0; read_lock(&smc_clc_eid_table.lock); if (peer_eid && local_eid && smc_clc_eid_table.seid_enabled && smc_v2_ext->hdr.flag.seid && !memcmp(peer_eid, local_eid, SMC_MAX_EID_LEN)) { memcpy(negotiated_eid, peer_eid, SMC_MAX_EID_LEN); match = true; goto out; } for (i = 0; i < smc_v2_ext->hdr.eid_cnt; i++) { if (_smc_clc_match_ueid(smc_v2_ext->user_eids[i])) { memcpy(negotiated_eid, smc_v2_ext->user_eids[i], SMC_MAX_EID_LEN); match = true; goto out; } } out: read_unlock(&smc_clc_eid_table.lock); return match; } /* check arriving CLC proposal */ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) { struct smc_clc_msg_proposal_prefix *pclc_prfx; struct smc_clc_smcd_v2_extension *smcd_v2_ext; struct smc_clc_msg_hdr *hdr = &pclc->hdr; struct smc_clc_v2_extension *v2_ext; v2_ext = smc_get_clc_v2_ext(pclc); pclc_prfx = smc_clc_proposal_get_prefix(pclc); if (hdr->version == SMC_V1) { if (hdr->typev1 == SMC_TYPE_N) return false; if (ntohs(hdr->length) != sizeof(*pclc) + ntohs(pclc->iparea_offset) + sizeof(*pclc_prfx) + pclc_prfx->ipv6_prefixes_cnt * sizeof(struct smc_clc_ipv6_prefix) + sizeof(struct smc_clc_msg_trail)) return false; } else { if (ntohs(hdr->length) != sizeof(*pclc) + sizeof(struct smc_clc_msg_smcd) + (hdr->typev1 != SMC_TYPE_N ? sizeof(*pclc_prfx) + pclc_prfx->ipv6_prefixes_cnt * sizeof(struct smc_clc_ipv6_prefix) : 0) + (hdr->typev2 != SMC_TYPE_N ? sizeof(*v2_ext) + v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN : 0) + (smcd_indicated(hdr->typev2) ? sizeof(*smcd_v2_ext) + v2_ext->hdr.ism_gid_cnt * sizeof(struct smc_clc_smcd_gid_chid) : 0) + sizeof(struct smc_clc_msg_trail)) return false; } return true; } /* check arriving CLC accept or confirm */ static bool smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm *clc) { struct smc_clc_msg_hdr *hdr = &clc->hdr; if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D) return false; if (hdr->version == SMC_V1) { if ((hdr->typev1 == SMC_TYPE_R && ntohs(hdr->length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) || (hdr->typev1 == SMC_TYPE_D && ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN)) return false; } else { if (hdr->typev1 == SMC_TYPE_D && ntohs(hdr->length) < SMCD_CLC_ACCEPT_CONFIRM_LEN_V2) return false; if (hdr->typev1 == SMC_TYPE_R && ntohs(hdr->length) < SMCR_CLC_ACCEPT_CONFIRM_LEN_V2) return false; } return true; } /* check arriving CLC decline */ static bool smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc) { struct smc_clc_msg_hdr *hdr = &dclc->hdr; if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D) return false; if (hdr->version == SMC_V1) { if (ntohs(hdr->length) != sizeof(struct smc_clc_msg_decline)) return false; } else { if (ntohs(hdr->length) != sizeof(struct smc_clc_msg_decline_v2)) return false; } return true; } static int smc_clc_fill_fce_v2x(struct smc_clc_first_contact_ext_v2x *fce_v2x, struct smc_init_info *ini) { int ret = sizeof(*fce_v2x); memset(fce_v2x, 0, sizeof(*fce_v2x)); fce_v2x->fce_v2_base.os_type = SMC_CLC_OS_LINUX; fce_v2x->fce_v2_base.release = ini->release_nr; memcpy(fce_v2x->fce_v2_base.hostname, smc_hostname, sizeof(smc_hostname)); if (ini->is_smcd && ini->release_nr < SMC_RELEASE_1) { ret = sizeof(struct smc_clc_first_contact_ext); goto out; } if (ini->release_nr >= SMC_RELEASE_1) { if (!ini->is_smcd) { fce_v2x->max_conns = ini->max_conns; fce_v2x->max_links = ini->max_links; } fce_v2x->feature_mask = htons(ini->feature_mask); } out: return ret; } /* check if received message has a correct header length and contains valid * heading and trailing eyecatchers */ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl) { struct smc_clc_msg_accept_confirm *clc; struct smc_clc_msg_proposal *pclc; struct smc_clc_msg_decline *dclc; struct smc_clc_msg_trail *trl; if (memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) && memcmp(clcm->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER))) return false; switch (clcm->type) { case SMC_CLC_PROPOSAL: pclc = (struct smc_clc_msg_proposal *)clcm; if (!smc_clc_msg_prop_valid(pclc)) return false; trl = (struct smc_clc_msg_trail *) ((u8 *)pclc + ntohs(pclc->hdr.length) - sizeof(*trl)); break; case SMC_CLC_ACCEPT: case SMC_CLC_CONFIRM: clc = (struct smc_clc_msg_accept_confirm *)clcm; if (!smc_clc_msg_acc_conf_valid(clc)) return false; trl = (struct smc_clc_msg_trail *) ((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl)); break; case SMC_CLC_DECLINE: dclc = (struct smc_clc_msg_decline *)clcm; if (!smc_clc_msg_decl_valid(dclc)) return false; check_trl = false; break; default: return false; } if (check_trl && memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) && memcmp(trl->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER))) return false; return true; } /* find ipv4 addr on device and get the prefix len, fill CLC proposal msg */ static int smc_clc_prfx_set4_rcu(struct dst_entry *dst, __be32 ipv4, struct smc_clc_msg_proposal_prefix *prop) { struct in_device *in_dev = __in_dev_get_rcu(dst->dev); const struct in_ifaddr *ifa; if (!in_dev) return -ENODEV; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (!inet_ifa_match(ipv4, ifa)) continue; prop->prefix_len = inet_mask_len(ifa->ifa_mask); prop->outgoing_subnet = ifa->ifa_address & ifa->ifa_mask; /* prop->ipv6_prefixes_cnt = 0; already done by memset before */ return 0; } return -ENOENT; } /* fill CLC proposal msg with ipv6 prefixes from device */ static int smc_clc_prfx_set6_rcu(struct dst_entry *dst, struct smc_clc_msg_proposal_prefix *prop, struct smc_clc_ipv6_prefix *ipv6_prfx) { #if IS_ENABLED(CONFIG_IPV6) struct inet6_dev *in6_dev = __in6_dev_get(dst->dev); struct inet6_ifaddr *ifa; int cnt = 0; if (!in6_dev) return -ENODEV; /* use a maximum of 8 IPv6 prefixes from device */ list_for_each_entry(ifa, &in6_dev->addr_list, if_list) { if (ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL) continue; ipv6_addr_prefix(&ipv6_prfx[cnt].prefix, &ifa->addr, ifa->prefix_len); ipv6_prfx[cnt].prefix_len = ifa->prefix_len; cnt++; if (cnt == SMC_CLC_MAX_V6_PREFIX) break; } prop->ipv6_prefixes_cnt = cnt; if (cnt) return 0; #endif return -ENOENT; } /* retrieve and set prefixes in CLC proposal msg */ static int smc_clc_prfx_set(struct socket *clcsock, struct smc_clc_msg_proposal_prefix *prop, struct smc_clc_ipv6_prefix *ipv6_prfx) { struct dst_entry *dst = sk_dst_get(clcsock->sk); struct sockaddr_storage addrs; struct sockaddr_in6 *addr6; struct sockaddr_in *addr; int rc = -ENOENT; if (!dst) { rc = -ENOTCONN; goto out; } if (!dst->dev) { rc = -ENODEV; goto out_rel; } /* get address to which the internal TCP socket is bound */ if (kernel_getsockname(clcsock, (struct sockaddr *)&addrs) < 0) goto out_rel; /* analyze IP specific data of net_device belonging to TCP socket */ addr6 = (struct sockaddr_in6 *)&addrs; rcu_read_lock(); if (addrs.ss_family == PF_INET) { /* IPv4 */ addr = (struct sockaddr_in *)&addrs; rc = smc_clc_prfx_set4_rcu(dst, addr->sin_addr.s_addr, prop); } else if (ipv6_addr_v4mapped(&addr6->sin6_addr)) { /* mapped IPv4 address - peer is IPv4 only */ rc = smc_clc_prfx_set4_rcu(dst, addr6->sin6_addr.s6_addr32[3], prop); } else { /* IPv6 */ rc = smc_clc_prfx_set6_rcu(dst, prop, ipv6_prfx); } rcu_read_unlock(); out_rel: dst_release(dst); out: return rc; } /* match ipv4 addrs of dev against addr in CLC proposal */ static int smc_clc_prfx_match4_rcu(struct net_device *dev, struct smc_clc_msg_proposal_prefix *prop) { struct in_device *in_dev = __in_dev_get_rcu(dev); const struct in_ifaddr *ifa; if (!in_dev) return -ENODEV; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (prop->prefix_len == inet_mask_len(ifa->ifa_mask) && inet_ifa_match(prop->outgoing_subnet, ifa)) return 0; } return -ENOENT; } /* match ipv6 addrs of dev against addrs in CLC proposal */ static int smc_clc_prfx_match6_rcu(struct net_device *dev, struct smc_clc_msg_proposal_prefix *prop) { #if IS_ENABLED(CONFIG_IPV6) struct inet6_dev *in6_dev = __in6_dev_get(dev); struct smc_clc_ipv6_prefix *ipv6_prfx; struct inet6_ifaddr *ifa; int i, max; if (!in6_dev) return -ENODEV; /* ipv6 prefix list starts behind smc_clc_msg_proposal_prefix */ ipv6_prfx = (struct smc_clc_ipv6_prefix *)((u8 *)prop + sizeof(*prop)); max = min_t(u8, prop->ipv6_prefixes_cnt, SMC_CLC_MAX_V6_PREFIX); list_for_each_entry(ifa, &in6_dev->addr_list, if_list) { if (ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL) continue; for (i = 0; i < max; i++) { if (ifa->prefix_len == ipv6_prfx[i].prefix_len && ipv6_prefix_equal(&ifa->addr, &ipv6_prfx[i].prefix, ifa->prefix_len)) return 0; } } #endif return -ENOENT; } /* check if proposed prefixes match one of our device prefixes */ int smc_clc_prfx_match(struct socket *clcsock, struct smc_clc_msg_proposal_prefix *prop) { struct dst_entry *dst = sk_dst_get(clcsock->sk); int rc; if (!dst) { rc = -ENOTCONN; goto out; } if (!dst->dev) { rc = -ENODEV; goto out_rel; } rcu_read_lock(); if (!prop->ipv6_prefixes_cnt) rc = smc_clc_prfx_match4_rcu(dst->dev, prop); else rc = smc_clc_prfx_match6_rcu(dst->dev, prop); rcu_read_unlock(); out_rel: dst_release(dst); out: return rc; } /* Wait for data on the tcp-socket, analyze received data * Returns: * 0 if success and it was not a decline that we received. * SMC_CLC_DECL_REPLY if decline received for fallback w/o another decl send. * clcsock error, -EINTR, -ECONNRESET, -EPROTO otherwise. */ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, u8 expected_type, unsigned long timeout) { long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo; struct sock *clc_sk = smc->clcsock->sk; struct smc_clc_msg_hdr *clcm = buf; struct msghdr msg = {NULL, 0}; int reason_code = 0; struct kvec vec = {buf, buflen}; int len, datlen, recvlen; bool check_trl = true; int krflags; /* peek the first few bytes to determine length of data to receive * so we don't consume any subsequent CLC message or payload data * in the TCP byte stream */ /* * Caller must make sure that buflen is no less than * sizeof(struct smc_clc_msg_hdr) */ krflags = MSG_PEEK | MSG_WAITALL; clc_sk->sk_rcvtimeo = timeout; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &vec, 1, sizeof(struct smc_clc_msg_hdr)); len = sock_recvmsg(smc->clcsock, &msg, krflags); if (signal_pending(current)) { reason_code = -EINTR; clc_sk->sk_err = EINTR; smc->sk.sk_err = EINTR; goto out; } if (clc_sk->sk_err) { reason_code = -clc_sk->sk_err; if (clc_sk->sk_err == EAGAIN && expected_type == SMC_CLC_DECLINE) clc_sk->sk_err = 0; /* reset for fallback usage */ else smc->sk.sk_err = clc_sk->sk_err; goto out; } if (!len) { /* peer has performed orderly shutdown */ smc->sk.sk_err = ECONNRESET; reason_code = -ECONNRESET; goto out; } if (len < 0) { if (len != -EAGAIN || expected_type != SMC_CLC_DECLINE) smc->sk.sk_err = -len; reason_code = len; goto out; } datlen = ntohs(clcm->length); if ((len < sizeof(struct smc_clc_msg_hdr)) || (clcm->version < SMC_V1) || ((clcm->type != SMC_CLC_DECLINE) && (clcm->type != expected_type))) { smc->sk.sk_err = EPROTO; reason_code = -EPROTO; goto out; } /* receive the complete CLC message */ memset(&msg, 0, sizeof(struct msghdr)); if (datlen > buflen) { check_trl = false; recvlen = buflen; } else { recvlen = datlen; } iov_iter_kvec(&msg.msg_iter, ITER_DEST, &vec, 1, recvlen); krflags = MSG_WAITALL; len = sock_recvmsg(smc->clcsock, &msg, krflags); if (len < recvlen || !smc_clc_msg_hdr_valid(clcm, check_trl)) { smc->sk.sk_err = EPROTO; reason_code = -EPROTO; goto out; } datlen -= len; while (datlen) { u8 tmp[SMC_CLC_RECV_BUF_LEN]; vec.iov_base = &tmp; vec.iov_len = SMC_CLC_RECV_BUF_LEN; /* receive remaining proposal message */ recvlen = datlen > SMC_CLC_RECV_BUF_LEN ? SMC_CLC_RECV_BUF_LEN : datlen; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &vec, 1, recvlen); len = sock_recvmsg(smc->clcsock, &msg, krflags); datlen -= len; } if (clcm->type == SMC_CLC_DECLINE) { struct smc_clc_msg_decline *dclc; dclc = (struct smc_clc_msg_decline *)clcm; reason_code = SMC_CLC_DECL_PEERDECL; smc->peer_diagnosis = ntohl(dclc->peer_diagnosis); if (((struct smc_clc_msg_decline *)buf)->hdr.typev2 & SMC_FIRST_CONTACT_MASK) { smc->conn.lgr->sync_err = 1; smc_lgr_terminate_sched(smc->conn.lgr); } } out: clc_sk->sk_rcvtimeo = rcvtimeo; return reason_code; } /* send CLC DECLINE message across internal TCP socket */ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version) { struct smc_clc_msg_decline *dclc_v1; struct smc_clc_msg_decline_v2 dclc; struct msghdr msg; int len, send_len; struct kvec vec; dclc_v1 = (struct smc_clc_msg_decline *)&dclc; memset(&dclc, 0, sizeof(dclc)); memcpy(dclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); dclc.hdr.type = SMC_CLC_DECLINE; dclc.hdr.version = version; dclc.os_type = version == SMC_V1 ? 0 : SMC_CLC_OS_LINUX; dclc.hdr.typev2 = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? SMC_FIRST_CONTACT_MASK : 0; if ((!smc_conn_lgr_valid(&smc->conn) || !smc->conn.lgr->is_smcd) && smc_ib_is_valid_local_systemid()) memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid)); dclc.peer_diagnosis = htonl(peer_diag_info); if (version == SMC_V1) { memcpy(dclc_v1->trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); send_len = sizeof(*dclc_v1); } else { memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); send_len = sizeof(dclc); } dclc.hdr.length = htons(send_len); memset(&msg, 0, sizeof(msg)); vec.iov_base = &dclc; vec.iov_len = send_len; len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, send_len); if (len < 0 || len < send_len) len = -EPROTO; return len > 0 ? 0 : len; } /* send CLC PROPOSAL message across internal TCP socket */ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) { struct smc_clc_smcd_v2_extension *smcd_v2_ext; struct smc_clc_msg_proposal_prefix *pclc_prfx; struct smc_clc_msg_proposal *pclc_base; struct smc_clc_smcd_gid_chid *gidchids; struct smc_clc_msg_proposal_area *pclc; struct smc_clc_ipv6_prefix *ipv6_prfx; struct net *net = sock_net(&smc->sk); struct smc_clc_v2_extension *v2_ext; struct smc_clc_msg_smcd *pclc_smcd; struct smc_clc_msg_trail *trl; struct smcd_dev *smcd; int len, i, plen, rc; int reason_code = 0; struct kvec vec[8]; struct msghdr msg; pclc = kzalloc(sizeof(*pclc), GFP_KERNEL); if (!pclc) return -ENOMEM; pclc_base = &pclc->pclc_base; pclc_smcd = &pclc->pclc_smcd; pclc_prfx = &pclc->pclc_prfx; ipv6_prfx = pclc->pclc_prfx_ipv6; v2_ext = container_of(&pclc->pclc_v2_ext, struct smc_clc_v2_extension, fixed); smcd_v2_ext = container_of(&pclc->pclc_smcd_v2_ext, struct smc_clc_smcd_v2_extension, fixed); gidchids = pclc->pclc_gidchids; trl = &pclc->pclc_trl; pclc_base->hdr.version = SMC_V2; pclc_base->hdr.typev1 = ini->smc_type_v1; pclc_base->hdr.typev2 = ini->smc_type_v2; plen = sizeof(*pclc_base) + sizeof(*pclc_smcd) + sizeof(*trl); /* retrieve ip prefixes for CLC proposal msg */ if (ini->smc_type_v1 != SMC_TYPE_N) { rc = smc_clc_prfx_set(smc->clcsock, pclc_prfx, ipv6_prfx); if (rc) { if (ini->smc_type_v2 == SMC_TYPE_N) { kfree(pclc); return SMC_CLC_DECL_CNFERR; } pclc_base->hdr.typev1 = SMC_TYPE_N; } else { pclc_base->iparea_offset = htons(sizeof(*pclc_smcd)); plen += sizeof(*pclc_prfx) + pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0]); } } /* build SMC Proposal CLC message */ memcpy(pclc_base->hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); pclc_base->hdr.type = SMC_CLC_PROPOSAL; if (smcr_indicated(ini->smc_type_v1)) { /* add SMC-R specifics */ memcpy(pclc_base->lcl.id_for_peer, local_systemid, sizeof(local_systemid)); memcpy(pclc_base->lcl.gid, ini->ib_gid, SMC_GID_SIZE); memcpy(pclc_base->lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1], ETH_ALEN); } if (smcd_indicated(ini->smc_type_v1)) { struct smcd_gid smcd_gid; /* add SMC-D specifics */ if (ini->ism_dev[0]) { smcd = ini->ism_dev[0]; smcd->ops->get_local_gid(smcd, &smcd_gid); pclc_smcd->ism.gid = htonll(smcd_gid.gid); pclc_smcd->ism.chid = htons(smc_ism_get_chid(ini->ism_dev[0])); } } if (ini->smc_type_v2 == SMC_TYPE_N) { pclc_smcd->v2_ext_offset = 0; } else { struct smc_clc_eid_entry *ueident; u16 v2_ext_offset; v2_ext->hdr.flag.release = SMC_RELEASE; v2_ext_offset = sizeof(*pclc_smcd) - offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); if (ini->smc_type_v1 != SMC_TYPE_N) v2_ext_offset += sizeof(*pclc_prfx) + pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0]); pclc_smcd->v2_ext_offset = htons(v2_ext_offset); plen += sizeof(*v2_ext); v2_ext->feature_mask = htons(SMC_FEATURE_MASK); read_lock(&smc_clc_eid_table.lock); v2_ext->hdr.eid_cnt = smc_clc_eid_table.ueid_cnt; plen += smc_clc_eid_table.ueid_cnt * SMC_MAX_EID_LEN; i = 0; list_for_each_entry(ueident, &smc_clc_eid_table.list, list) { memcpy(v2_ext->user_eids[i++], ueident->eid, sizeof(ueident->eid)); } read_unlock(&smc_clc_eid_table.lock); } if (smcd_indicated(ini->smc_type_v2)) { struct smcd_gid smcd_gid; u8 *eid = NULL; int entry = 0; v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled; v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) - offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset) + v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN); smc_ism_get_system_eid(&eid); if (eid && v2_ext->hdr.flag.seid) memcpy(smcd_v2_ext->system_eid, eid, SMC_MAX_EID_LEN); plen += sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { for (i = 1; i <= ini->ism_offered_cnt; i++) { smcd = ini->ism_dev[i]; smcd->ops->get_local_gid(smcd, &smcd_gid); gidchids[entry].chid = htons(smc_ism_get_chid(ini->ism_dev[i])); gidchids[entry].gid = htonll(smcd_gid.gid); if (smc_ism_is_emulated(smcd)) { /* an Emulated-ISM device takes two * entries. CHID of the second entry * repeats that of the first entry. */ gidchids[entry + 1].chid = gidchids[entry].chid; gidchids[entry + 1].gid = htonll(smcd_gid.gid_ext); entry++; } entry++; } plen += entry * sizeof(struct smc_clc_smcd_gid_chid); } v2_ext->hdr.ism_gid_cnt = entry; } if (smcr_indicated(ini->smc_type_v2)) { memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE); v2_ext->max_conns = net->smc.sysctl_max_conns_per_lgr; v2_ext->max_links = net->smc.sysctl_max_links_per_lgr; } pclc_base->hdr.length = htons(plen); memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); /* send SMC Proposal CLC message */ memset(&msg, 0, sizeof(msg)); i = 0; vec[i].iov_base = pclc_base; vec[i++].iov_len = sizeof(*pclc_base); vec[i].iov_base = pclc_smcd; vec[i++].iov_len = sizeof(*pclc_smcd); if (ini->smc_type_v1 != SMC_TYPE_N) { vec[i].iov_base = pclc_prfx; vec[i++].iov_len = sizeof(*pclc_prfx); if (pclc_prfx->ipv6_prefixes_cnt > 0) { vec[i].iov_base = ipv6_prfx; vec[i++].iov_len = pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0]); } } if (ini->smc_type_v2 != SMC_TYPE_N) { vec[i].iov_base = v2_ext; vec[i++].iov_len = sizeof(*v2_ext) + (v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN); if (smcd_indicated(ini->smc_type_v2)) { vec[i].iov_base = smcd_v2_ext; vec[i++].iov_len = sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { vec[i].iov_base = gidchids; vec[i++].iov_len = v2_ext->hdr.ism_gid_cnt * sizeof(struct smc_clc_smcd_gid_chid); } } } vec[i].iov_base = trl; vec[i++].iov_len = sizeof(*trl); /* due to the few bytes needed for clc-handshake this cannot block */ len = kernel_sendmsg(smc->clcsock, &msg, vec, i, plen); if (len < 0) { smc->sk.sk_err = smc->clcsock->sk->sk_err; reason_code = -smc->sk.sk_err; } else if (len < ntohs(pclc_base->hdr.length)) { reason_code = -ENETUNREACH; smc->sk.sk_err = -reason_code; } kfree(pclc); return reason_code; } static void smcd_clc_prep_confirm_accept(struct smc_connection *conn, struct smc_clc_msg_accept_confirm *clc, int first_contact, u8 version, u8 *eid, struct smc_init_info *ini, int *fce_len, struct smc_clc_first_contact_ext_v2x *fce_v2x, struct smc_clc_msg_trail *trl) { struct smcd_dev *smcd = conn->lgr->smcd; struct smcd_gid smcd_gid; u16 chid; int len; /* SMC-D specific settings */ memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)); smcd->ops->get_local_gid(smcd, &smcd_gid); clc->hdr.typev1 = SMC_TYPE_D; clc->d0.gid = htonll(smcd_gid.gid); clc->d0.token = htonll(conn->rmb_desc->token); clc->d0.dmbe_size = conn->rmbe_size_comp; clc->d0.dmbe_idx = 0; memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); if (version == SMC_V1) { clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); } else { chid = smc_ism_get_chid(smcd); clc->d1.chid = htons(chid); if (eid && eid[0]) memcpy(clc->d1.eid, eid, SMC_MAX_EID_LEN); if (__smc_ism_is_emulated(chid)) clc->d1.gid_ext = htonll(smcd_gid.gid_ext); len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; if (first_contact) { *fce_len = smc_clc_fill_fce_v2x(fce_v2x, ini); len += *fce_len; } clc->hdr.length = htons(len); } memcpy(trl->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)); } static void smcr_clc_prep_confirm_accept(struct smc_connection *conn, struct smc_clc_msg_accept_confirm *clc, int first_contact, u8 version, u8 *eid, struct smc_init_info *ini, int *fce_len, struct smc_clc_first_contact_ext_v2x *fce_v2x, struct smc_clc_fce_gid_ext *gle, struct smc_clc_msg_trail *trl) { struct smc_link *link = conn->lnk; int len; /* SMC-R specific settings */ memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); clc->hdr.typev1 = SMC_TYPE_R; memcpy(clc->r0.lcl.id_for_peer, local_systemid, sizeof(local_systemid)); memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE); memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN); hton24(clc->r0.qpn, link->roce_qp->qp_num); clc->r0.rmb_rkey = htonl(conn->rmb_desc->mr[link->link_idx]->rkey); clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */ clc->r0.rmbe_alert_token = htonl(conn->alert_token_local); switch (clc->hdr.type) { case SMC_CLC_ACCEPT: clc->r0.qp_mtu = link->path_mtu; break; case SMC_CLC_CONFIRM: clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); break; } clc->r0.rmbe_size = conn->rmbe_size_comp; clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ? cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) : cpu_to_be64((u64)sg_dma_address (conn->rmb_desc->sgt[link->link_idx].sgl)); hton24(clc->r0.psn, link->psn_initial); if (version == SMC_V1) { clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); } else { if (eid && eid[0]) memcpy(clc->r1.eid, eid, SMC_MAX_EID_LEN); len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2; if (first_contact) { *fce_len = smc_clc_fill_fce_v2x(fce_v2x, ini); len += *fce_len; fce_v2x->fce_v2_base.v2_direct = !link->lgr->uses_gateway; if (clc->hdr.type == SMC_CLC_CONFIRM) { memset(gle, 0, sizeof(*gle)); gle->gid_cnt = ini->smcrv2.gidlist.len; len += sizeof(*gle); len += gle->gid_cnt * sizeof(gle->gid[0]); } } clc->hdr.length = htons(len); } memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); } /* build and send CLC CONFIRM / ACCEPT message */ static int smc_clc_send_confirm_accept(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc, int first_contact, u8 version, u8 *eid, struct smc_init_info *ini) { struct smc_clc_first_contact_ext_v2x fce_v2x; struct smc_connection *conn = &smc->conn; struct smc_clc_fce_gid_ext gle; struct smc_clc_msg_trail trl; int i, fce_len; struct kvec vec[5]; struct msghdr msg; /* send SMC Confirm CLC msg */ clc->hdr.version = version; /* SMC version */ if (first_contact) clc->hdr.typev2 |= SMC_FIRST_CONTACT_MASK; if (conn->lgr->is_smcd) smcd_clc_prep_confirm_accept(conn, clc, first_contact, version, eid, ini, &fce_len, &fce_v2x, &trl); else smcr_clc_prep_confirm_accept(conn, clc, first_contact, version, eid, ini, &fce_len, &fce_v2x, &gle, &trl); memset(&msg, 0, sizeof(msg)); i = 0; vec[i].iov_base = clc; if (version > SMC_V1) vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ? SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 : SMCR_CLC_ACCEPT_CONFIRM_LEN_V2) - sizeof(trl); else vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ? SMCD_CLC_ACCEPT_CONFIRM_LEN : SMCR_CLC_ACCEPT_CONFIRM_LEN) - sizeof(trl); if (version > SMC_V1 && first_contact) { vec[i].iov_base = &fce_v2x; vec[i++].iov_len = fce_len; if (!conn->lgr->is_smcd) { if (clc->hdr.type == SMC_CLC_CONFIRM) { vec[i].iov_base = &gle; vec[i++].iov_len = sizeof(gle); vec[i].iov_base = &ini->smcrv2.gidlist.list; vec[i++].iov_len = gle.gid_cnt * sizeof(gle.gid[0]); } } } vec[i].iov_base = &trl; vec[i++].iov_len = sizeof(trl); return kernel_sendmsg(smc->clcsock, &msg, vec, 1, ntohs(clc->hdr.length)); } /* send CLC CONFIRM message across internal TCP socket */ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, u8 version, u8 *eid, struct smc_init_info *ini) { struct smc_clc_msg_accept_confirm cclc; int reason_code = 0; int len; /* send SMC Confirm CLC msg */ memset(&cclc, 0, sizeof(cclc)); cclc.hdr.type = SMC_CLC_CONFIRM; len = smc_clc_send_confirm_accept(smc, &cclc, clnt_first_contact, version, eid, ini); if (len < ntohs(cclc.hdr.length)) { if (len >= 0) { reason_code = -ENETUNREACH; smc->sk.sk_err = -reason_code; } else { smc->sk.sk_err = smc->clcsock->sk->sk_err; reason_code = -smc->sk.sk_err; } } return reason_code; } /* send CLC ACCEPT message across internal TCP socket */ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, u8 version, u8 *negotiated_eid, struct smc_init_info *ini) { struct smc_clc_msg_accept_confirm aclc; int len; memset(&aclc, 0, sizeof(aclc)); aclc.hdr.type = SMC_CLC_ACCEPT; len = smc_clc_send_confirm_accept(new_smc, &aclc, srv_first_contact, version, negotiated_eid, ini); if (len < ntohs(aclc.hdr.length)) len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err; return len > 0 ? 0 : len; } int smc_clc_srv_v2x_features_validate(struct smc_sock *smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { struct smc_clc_v2_extension *pclc_v2_ext; struct net *net = sock_net(&smc->sk); ini->max_conns = SMC_CONN_PER_LGR_MAX; ini->max_links = SMC_LINKS_ADD_LNK_MAX; ini->feature_mask = SMC_FEATURE_MASK; if ((!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) || ini->release_nr < SMC_RELEASE_1) return 0; pclc_v2_ext = smc_get_clc_v2_ext(pclc); if (!pclc_v2_ext) return SMC_CLC_DECL_NOV2EXT; if (ini->smcr_version & SMC_V2) { ini->max_conns = min_t(u8, pclc_v2_ext->max_conns, net->smc.sysctl_max_conns_per_lgr); if (ini->max_conns < SMC_CONN_PER_LGR_MIN) return SMC_CLC_DECL_MAXCONNERR; ini->max_links = min_t(u8, pclc_v2_ext->max_links, net->smc.sysctl_max_links_per_lgr); if (ini->max_links < SMC_LINKS_ADD_LNK_MIN) return SMC_CLC_DECL_MAXLINKERR; } return 0; } int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce, struct smc_init_info *ini) { struct smc_clc_first_contact_ext_v2x *fce_v2x = (struct smc_clc_first_contact_ext_v2x *)fce; if (ini->release_nr < SMC_RELEASE_1) return 0; if (!ini->is_smcd) { if (fce_v2x->max_conns < SMC_CONN_PER_LGR_MIN) return SMC_CLC_DECL_MAXCONNERR; ini->max_conns = fce_v2x->max_conns; if (fce_v2x->max_links > SMC_LINKS_ADD_LNK_MAX || fce_v2x->max_links < SMC_LINKS_ADD_LNK_MIN) return SMC_CLC_DECL_MAXLINKERR; ini->max_links = fce_v2x->max_links; } /* common supplemental features of server and client */ ini->feature_mask = ntohs(fce_v2x->feature_mask) & SMC_FEATURE_MASK; return 0; } int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc, struct smc_init_info *ini) { struct smc_clc_first_contact_ext *fce = smc_get_clc_first_contact_ext(cclc, ini->is_smcd); struct smc_clc_first_contact_ext_v2x *fce_v2x = (struct smc_clc_first_contact_ext_v2x *)fce; if (cclc->hdr.version == SMC_V1 || !(cclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) return 0; if (ini->release_nr != fce->release) return SMC_CLC_DECL_RELEASEERR; if (fce->release < SMC_RELEASE_1) return 0; if (!ini->is_smcd) { if (fce_v2x->max_conns != ini->max_conns) return SMC_CLC_DECL_MAXCONNERR; if (fce_v2x->max_links != ini->max_links) return SMC_CLC_DECL_MAXLINKERR; } /* common supplemental features returned by client */ ini->feature_mask = ntohs(fce_v2x->feature_mask); return 0; } void smc_clc_get_hostname(u8 **host) { *host = &smc_hostname[0]; } void __init smc_clc_init(void) { struct new_utsname *u; memset(smc_hostname, _S, sizeof(smc_hostname)); /* ASCII blanks */ u = utsname(); memcpy(smc_hostname, u->nodename, min_t(size_t, strlen(u->nodename), sizeof(smc_hostname))); INIT_LIST_HEAD(&smc_clc_eid_table.list); rwlock_init(&smc_clc_eid_table.lock); smc_clc_eid_table.ueid_cnt = 0; #if IS_ENABLED(CONFIG_S390) smc_clc_eid_table.seid_enabled = 1; #else smc_clc_eid_table.seid_enabled = 0; #endif } void smc_clc_exit(void) { smc_clc_ueid_remove(NULL); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Handshake request lifetime events * * Author: Chuck Lever <chuck.lever@oracle.com> * * Copyright (c) 2023, Oracle and/or its affiliates. */ #include <linux/types.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/inet.h> #include <linux/fdtable.h> #include <linux/rhashtable.h> #include <net/sock.h> #include <net/genetlink.h> #include <net/netns/generic.h> #include <kunit/visibility.h> #include <uapi/linux/handshake.h> #include "handshake.h" #include <trace/events/handshake.h> /* * We need both a handshake_req -> sock mapping, and a sock -> * handshake_req mapping. Both are one-to-one. * * To avoid adding another pointer field to struct sock, net/handshake * maintains a hash table, indexed by the memory address of @sock, to * find the struct handshake_req outstanding for that socket. The * reverse direction uses a simple pointer field in the handshake_req * struct. */ static struct rhashtable handshake_rhashtbl ____cacheline_aligned_in_smp; static const struct rhashtable_params handshake_rhash_params = { .key_len = sizeof_field(struct handshake_req, hr_sk), .key_offset = offsetof(struct handshake_req, hr_sk), .head_offset = offsetof(struct handshake_req, hr_rhash), .automatic_shrinking = true, }; int handshake_req_hash_init(void) { return rhashtable_init(&handshake_rhashtbl, &handshake_rhash_params); } void handshake_req_hash_destroy(void) { rhashtable_destroy(&handshake_rhashtbl); } struct handshake_req *handshake_req_hash_lookup(struct sock *sk) { return rhashtable_lookup_fast(&handshake_rhashtbl, &sk, handshake_rhash_params); } EXPORT_SYMBOL_IF_KUNIT(handshake_req_hash_lookup); static bool handshake_req_hash_add(struct handshake_req *req) { int ret; ret = rhashtable_lookup_insert_fast(&handshake_rhashtbl, &req->hr_rhash, handshake_rhash_params); return ret == 0; } static void handshake_req_destroy(struct handshake_req *req) { if (req->hr_proto->hp_destroy) req->hr_proto->hp_destroy(req); rhashtable_remove_fast(&handshake_rhashtbl, &req->hr_rhash, handshake_rhash_params); kfree(req); } static void handshake_sk_destruct(struct sock *sk) { void (*sk_destruct)(struct sock *sk); struct handshake_req *req; req = handshake_req_hash_lookup(sk); if (!req) return; trace_handshake_destruct(sock_net(sk), req, sk); sk_destruct = req->hr_odestruct; handshake_req_destroy(req); if (sk_destruct) sk_destruct(sk); } /** * handshake_req_alloc - Allocate a handshake request * @proto: security protocol * @flags: memory allocation flags * * Returns an initialized handshake_req or NULL. */ struct handshake_req *handshake_req_alloc(const struct handshake_proto *proto, gfp_t flags) { struct handshake_req *req; if (!proto) return NULL; if (proto->hp_handler_class <= HANDSHAKE_HANDLER_CLASS_NONE) return NULL; if (proto->hp_handler_class >= HANDSHAKE_HANDLER_CLASS_MAX) return NULL; if (!proto->hp_accept || !proto->hp_done) return NULL; req = kzalloc(struct_size(req, hr_priv, proto->hp_privsize), flags); if (!req) return NULL; INIT_LIST_HEAD(&req->hr_list); req->hr_proto = proto; return req; } EXPORT_SYMBOL(handshake_req_alloc); /** * handshake_req_private - Get per-handshake private data * @req: handshake arguments * */ void *handshake_req_private(struct handshake_req *req) { return (void *)&req->hr_priv; } EXPORT_SYMBOL(handshake_req_private); static bool __add_pending_locked(struct handshake_net *hn, struct handshake_req *req) { if (WARN_ON_ONCE(!list_empty(&req->hr_list))) return false; hn->hn_pending++; list_add_tail(&req->hr_list, &hn->hn_requests); return true; } static void __remove_pending_locked(struct handshake_net *hn, struct handshake_req *req) { hn->hn_pending--; list_del_init(&req->hr_list); } /* * Returns %true if the request was found on @net's pending list, * otherwise %false. * * If @req was on a pending list, it has not yet been accepted. */ static bool remove_pending(struct handshake_net *hn, struct handshake_req *req) { bool ret = false; spin_lock(&hn->hn_lock); if (!list_empty(&req->hr_list)) { __remove_pending_locked(hn, req); ret = true; } spin_unlock(&hn->hn_lock); return ret; } struct handshake_req *handshake_req_next(struct handshake_net *hn, int class) { struct handshake_req *req, *pos; req = NULL; spin_lock(&hn->hn_lock); list_for_each_entry(pos, &hn->hn_requests, hr_list) { if (pos->hr_proto->hp_handler_class != class) continue; __remove_pending_locked(hn, pos); req = pos; break; } spin_unlock(&hn->hn_lock); return req; } EXPORT_SYMBOL_IF_KUNIT(handshake_req_next); /** * handshake_req_submit - Submit a handshake request * @sock: open socket on which to perform the handshake * @req: handshake arguments * @flags: memory allocation flags * * Return values: * %0: Request queued * %-EINVAL: Invalid argument * %-EBUSY: A handshake is already under way for this socket * %-ESRCH: No handshake agent is available * %-EAGAIN: Too many pending handshake requests * %-ENOMEM: Failed to allocate memory * %-EMSGSIZE: Failed to construct notification message * %-EOPNOTSUPP: Handshake module not initialized * * A zero return value from handshake_req_submit() means that * exactly one subsequent completion callback is guaranteed. * * A negative return value from handshake_req_submit() means that * no completion callback will be done and that @req has been * destroyed. */ int handshake_req_submit(struct socket *sock, struct handshake_req *req, gfp_t flags) { struct handshake_net *hn; struct net *net; int ret; if (!sock || !req || !sock->file) { kfree(req); return -EINVAL; } req->hr_sk = sock->sk; if (!req->hr_sk) { kfree(req); return -EINVAL; } req->hr_odestruct = req->hr_sk->sk_destruct; req->hr_sk->sk_destruct = handshake_sk_destruct; ret = -EOPNOTSUPP; net = sock_net(req->hr_sk); hn = handshake_pernet(net); if (!hn) goto out_err; ret = -EAGAIN; if (READ_ONCE(hn->hn_pending) >= hn->hn_pending_max) goto out_err; spin_lock(&hn->hn_lock); ret = -EOPNOTSUPP; if (test_bit(HANDSHAKE_F_NET_DRAINING, &hn->hn_flags)) goto out_unlock; ret = -EBUSY; if (!handshake_req_hash_add(req)) goto out_unlock; if (!__add_pending_locked(hn, req)) goto out_unlock; spin_unlock(&hn->hn_lock); ret = handshake_genl_notify(net, req->hr_proto, flags); if (ret) { trace_handshake_notify_err(net, req, req->hr_sk, ret); if (remove_pending(hn, req)) goto out_err; } /* Prevent socket release while a handshake request is pending */ sock_hold(req->hr_sk); trace_handshake_submit(net, req, req->hr_sk); return 0; out_unlock: spin_unlock(&hn->hn_lock); out_err: trace_handshake_submit_err(net, req, req->hr_sk, ret); handshake_req_destroy(req); return ret; } EXPORT_SYMBOL(handshake_req_submit); void handshake_complete(struct handshake_req *req, unsigned int status, struct genl_info *info) { struct sock *sk = req->hr_sk; struct net *net = sock_net(sk); if (!test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { trace_handshake_complete(net, req, sk, status); req->hr_proto->hp_done(req, status, info); /* Handshake request is no longer pending */ sock_put(sk); } } EXPORT_SYMBOL_IF_KUNIT(handshake_complete); /** * handshake_req_cancel - Cancel an in-progress handshake * @sk: socket on which there is an ongoing handshake * * Request cancellation races with request completion. To determine * who won, callers examine the return value from this function. * * Return values: * %true - Uncompleted handshake request was canceled * %false - Handshake request already completed or not found */ bool handshake_req_cancel(struct sock *sk) { struct handshake_req *req; struct handshake_net *hn; struct net *net; net = sock_net(sk); req = handshake_req_hash_lookup(sk); if (!req) { trace_handshake_cancel_none(net, req, sk); return false; } hn = handshake_pernet(net); if (hn && remove_pending(hn, req)) { /* Request hadn't been accepted */ goto out_true; } if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { /* Request already completed */ trace_handshake_cancel_busy(net, req, sk); return false; } out_true: trace_handshake_cancel(net, req, sk); /* Handshake request is no longer pending */ sock_put(sk); return true; } EXPORT_SYMBOL(handshake_req_cancel); |
| 29 104 8 11 4 24 60 10 12 100 80 19 45 32 15 709 760 5 56 70 46 17 3 33 1 31 2 18 1 7 42 23 67 67 67 67 67 67 43 27 10 17 69 69 68 69 69 67 2 7 59 59 57 1 56 3 59 59 23 57 1 1 1 59 1 1 1 133 125 9 41 93 141 142 142 59 58 39 78 95 58 39 36 48 69 46 47 114 82 60 38 133 134 11 10 23 3 6 1 2 13 2 7 2 6 8 8 8 8 121 247 3 5 21 21 21 21 21 8 14 14 8 5 5 72 28 28 100 100 5 5 5 5 5 5 4 24 24 24 88 88 88 88 88 88 88 63 63 63 5 60 6 6 46 46 6 6 6 6 46 46 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 | // 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. * * Support for INET connection oriented protocols. * * Authors: See the TCP sources */ #include <linux/module.h> #include <linux/jhash.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet_timewait_sock.h> #include <net/ip.h> #include <net/route.h> #include <net/tcp_states.h> #include <net/xfrm.h> #include <net/tcp.h> #include <net/sock_reuseport.h> #include <net/addrconf.h> #if IS_ENABLED(CONFIG_IPV6) /* match_sk*_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses * if IPv6 only, and any IPv4 addresses * if not IPv6 only * match_sk*_wildcard == false: addresses must be exactly the same, i.e. * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, * and 0.0.0.0 equals to 0.0.0.0 only */ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, const struct in6_addr *sk2_rcv_saddr6, __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, bool sk1_ipv6only, bool sk2_ipv6only, bool match_sk1_wildcard, bool match_sk2_wildcard) { int addr_type = ipv6_addr_type(sk1_rcv_saddr6); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; /* if both are mapped, treat as IPv4 */ if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) return true; return (match_sk1_wildcard && !sk1_rcv_saddr) || (match_sk2_wildcard && !sk2_rcv_saddr); } return false; } if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) return true; if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) return true; if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard && !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) return true; if (sk2_rcv_saddr6 && ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6)) return true; return false; } #endif /* match_sk*_wildcard == true: 0.0.0.0 equals to any IPv4 addresses * match_sk*_wildcard == false: addresses must be exactly the same, i.e. * 0.0.0.0 only equals to 0.0.0.0 */ static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, bool sk2_ipv6only, bool match_sk1_wildcard, bool match_sk2_wildcard) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) return true; return (match_sk1_wildcard && !sk1_rcv_saddr) || (match_sk2_wildcard && !sk2_rcv_saddr); } return false; } bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, bool match_wildcard) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) return ipv6_rcv_saddr_equal(&sk->sk_v6_rcv_saddr, inet6_rcv_saddr(sk2), sk->sk_rcv_saddr, sk2->sk_rcv_saddr, ipv6_only_sock(sk), ipv6_only_sock(sk2), match_wildcard, match_wildcard); #endif return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr, ipv6_only_sock(sk2), match_wildcard, match_wildcard); } EXPORT_SYMBOL(inet_rcv_saddr_equal); bool inet_rcv_saddr_any(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) return ipv6_addr_any(&sk->sk_v6_rcv_saddr); #endif return !sk->sk_rcv_saddr; } /** * inet_sk_get_local_port_range - fetch ephemeral ports range * @sk: socket * @low: pointer to low port * @high: pointer to high port * * Fetch netns port range (/proc/sys/net/ipv4/ip_local_port_range) * Range can be overridden if socket got IP_LOCAL_PORT_RANGE option. * Returns true if IP_LOCAL_PORT_RANGE was set on this socket. */ bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high) { int lo, hi, sk_lo, sk_hi; bool local_range = false; u32 sk_range; inet_get_local_port_range(sock_net(sk), &lo, &hi); sk_range = READ_ONCE(inet_sk(sk)->local_port_range); if (unlikely(sk_range)) { sk_lo = sk_range & 0xffff; sk_hi = sk_range >> 16; if (lo <= sk_lo && sk_lo <= hi) lo = sk_lo; if (lo <= sk_hi && sk_hi <= hi) hi = sk_hi; local_range = true; } *low = lo; *high = hi; return local_range; } EXPORT_SYMBOL(inet_sk_get_local_port_range); static bool inet_use_bhash2_on_bind(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) { int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); if (addr_type == IPV6_ADDR_ANY) return false; if (addr_type != IPV6_ADDR_MAPPED) return true; } #endif return sk->sk_rcv_saddr != htonl(INADDR_ANY); } static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { int bound_dev_if2; if (sk == sk2) return false; bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if); if (!sk->sk_bound_dev_if || !bound_dev_if2 || sk->sk_bound_dev_if == bound_dev_if2) { if (sk->sk_reuse && sk2->sk_reuse && sk2->sk_state != TCP_LISTEN) { if (!relax || (!reuseport_ok && sk->sk_reuseport && sk2->sk_reuseport && reuseport_cb_ok && (sk2->sk_state == TCP_TIME_WAIT || uid_eq(sk_uid, sock_i_uid(sk2))))) return true; } else if (!reuseport_ok || !sk->sk_reuseport || !sk2->sk_reuseport || !reuseport_cb_ok || (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(sk_uid, sock_i_uid(sk2)))) { return true; } } return false; } static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { if (ipv6_only_sock(sk2)) { if (sk->sk_family == AF_INET) return false; #if IS_ENABLED(CONFIG_IPV6) if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) return false; #endif } return inet_bind_conflict(sk, sk2, sk_uid, relax, reuseport_cb_ok, reuseport_ok); } static bool inet_bhash2_conflict(const struct sock *sk, const struct inet_bind2_bucket *tb2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { struct sock *sk2; sk_for_each_bound(sk2, &tb2->owners) { if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax, reuseport_cb_ok, reuseport_ok)) return true; } return false; } #define sk_for_each_bound_bhash(__sk, __tb2, __tb) \ hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node) \ sk_for_each_bound(sk2, &(__tb2)->owners) /* This should be called only when the tb and tb2 hashbuckets' locks are held */ static int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, const struct inet_bind2_bucket *tb2, /* may be null */ bool relax, bool reuseport_ok) { kuid_t uid = sock_i_uid((struct sock *)sk); struct sock_reuseport *reuseport_cb; bool reuseport_cb_ok; struct sock *sk2; rcu_read_lock(); reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); /* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */ reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks); rcu_read_unlock(); /* Conflicts with an existing IPV6_ADDR_ANY (if ipv6) or INADDR_ANY (if * ipv4) should have been checked already. We need to do these two * checks separately because their spinlocks have to be acquired/released * independently of each other, to prevent possible deadlocks */ if (inet_use_bhash2_on_bind(sk)) return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok); /* Unlike other sk lookup places we do not check * for sk_net here, since _all_ the socks listed * in tb->owners and tb2->owners list belong * to the same net - the one this bucket belongs to. */ sk_for_each_bound_bhash(sk2, tb2, tb) { if (!inet_bind_conflict(sk, sk2, uid, relax, reuseport_cb_ok, reuseport_ok)) continue; if (inet_rcv_saddr_equal(sk, sk2, true)) return true; } return false; } /* Determine if there is a bind conflict with an existing IPV6_ADDR_ANY (if ipv6) or * INADDR_ANY (if ipv4) socket. * * Caller must hold bhash hashbucket lock with local bh disabled, to protect * against concurrent binds on the port for addr any */ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l3mdev, bool relax, bool reuseport_ok) { kuid_t uid = sock_i_uid((struct sock *)sk); const struct net *net = sock_net(sk); struct sock_reuseport *reuseport_cb; struct inet_bind_hashbucket *head2; struct inet_bind2_bucket *tb2; bool conflict = false; bool reuseport_cb_ok; rcu_read_lock(); reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); /* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */ reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks); rcu_read_unlock(); head2 = inet_bhash2_addr_any_hashbucket(sk, net, port); spin_lock(&head2->lock); inet_bind_bucket_for_each(tb2, &head2->chain) { if (!inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) continue; if (!inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok)) continue; conflict = true; break; } spin_unlock(&head2->lock); return conflict; } /* * Find an open port number for the socket. Returns with the * inet_bind_hashbucket locks held if successful. */ static struct inet_bind_hashbucket * inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret, struct inet_bind2_bucket **tb2_ret, struct inet_bind_hashbucket **head2_ret, int *port_ret) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); int i, low, high, attempt_half, port, l3mdev; struct inet_bind_hashbucket *head, *head2; struct net *net = sock_net(sk); struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; u32 remaining, offset; bool relax = false; l3mdev = inet_sk_bound_l3mdev(sk); ports_exhausted: attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0; other_half_scan: inet_sk_get_local_port_range(sk, &low, &high); high++; /* [32768, 60999] -> [32768, 61000[ */ if (high - low < 4) attempt_half = 0; if (attempt_half) { int half = low + (((high - low) >> 2) << 1); if (attempt_half == 1) high = half; else low = half; } remaining = high - low; if (likely(remaining > 1)) remaining &= ~1U; offset = get_random_u32_below(remaining); /* __inet_hash_connect() favors ports having @low parity * We do the opposite to not pollute connect() users. */ offset |= 1U; other_parity_scan: port = low + offset; for (i = 0; i < remaining; i += 2, port += 2) { if (unlikely(port >= high)) port -= remaining; if (inet_is_local_reserved_port(net, port)) continue; head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); if (inet_use_bhash2_on_bind(sk)) { if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, relax, false)) goto next_port; } head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); inet_bind_bucket_for_each(tb, &head->chain) if (inet_bind_bucket_match(tb, net, port, l3mdev)) { if (!inet_csk_bind_conflict(sk, tb, tb2, relax, false)) goto success; spin_unlock(&head2->lock); goto next_port; } tb = NULL; goto success; next_port: spin_unlock_bh(&head->lock); cond_resched(); } offset--; if (!(offset & 1)) goto other_parity_scan; if (attempt_half == 1) { /* OK we now try the upper half of the range */ attempt_half = 2; goto other_half_scan; } if (READ_ONCE(net->ipv4.sysctl_ip_autobind_reuse) && !relax) { /* We still have a chance to connect to different destinations */ relax = true; goto ports_exhausted; } return NULL; success: *port_ret = port; *tb_ret = tb; *tb2_ret = tb2; *head2_ret = head2; return head; } static inline int sk_reuseport_match(struct inet_bind_bucket *tb, struct sock *sk) { kuid_t uid = sock_i_uid(sk); if (tb->fastreuseport <= 0) return 0; if (!sk->sk_reuseport) return 0; if (rcu_access_pointer(sk->sk_reuseport_cb)) return 0; if (!uid_eq(tb->fastuid, uid)) return 0; /* We only need to check the rcv_saddr if this tb was once marked * without fastreuseport and then was reset, as we can only know that * the fast_*rcv_saddr doesn't have any conflicts with the socks on the * owners list. */ if (tb->fastreuseport == FASTREUSEPORT_ANY) return 1; #if IS_ENABLED(CONFIG_IPV6) if (tb->fast_sk_family == AF_INET6) return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr, inet6_rcv_saddr(sk), tb->fast_rcv_saddr, sk->sk_rcv_saddr, tb->fast_ipv6_only, ipv6_only_sock(sk), true, false); #endif return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr, ipv6_only_sock(sk), true, false); } void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, struct sock *sk) { kuid_t uid = sock_i_uid(sk); bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; if (hlist_empty(&tb->bhash2)) { tb->fastreuse = reuse; if (sk->sk_reuseport) { tb->fastreuseport = FASTREUSEPORT_ANY; tb->fastuid = uid; tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); tb->fast_sk_family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; #endif } else { tb->fastreuseport = 0; } } else { if (!reuse) tb->fastreuse = 0; if (sk->sk_reuseport) { /* We didn't match or we don't have fastreuseport set on * the tb, but we have sk_reuseport set on this socket * and we know that there are no bind conflicts with * this socket in this tb, so reset our tb's reuseport * settings so that any subsequent sockets that match * our current socket will be put on the fast path. * * If we reset we need to set FASTREUSEPORT_STRICT so we * do extra checking for all subsequent sk_reuseport * socks. */ if (!sk_reuseport_match(tb, sk)) { tb->fastreuseport = FASTREUSEPORT_STRICT; tb->fastuid = uid; tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); tb->fast_sk_family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; #endif } } else { tb->fastreuseport = 0; } } } /* Obtain a reference to a local port for the given sock, * if snum is zero it means select any available local port. * We try to allocate an odd port (and leave even ports for connect()) */ int inet_csk_get_port(struct sock *sk, unsigned short snum) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; bool found_port = false, check_bind_conflict = true; bool bhash_created = false, bhash2_created = false; int ret = -EADDRINUSE, port = snum, l3mdev; struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2 = NULL; struct inet_bind_bucket *tb = NULL; bool head2_lock_acquired = false; struct net *net = sock_net(sk); l3mdev = inet_sk_bound_l3mdev(sk); if (!port) { head = inet_csk_find_open_port(sk, &tb, &tb2, &head2, &port); if (!head) return ret; head2_lock_acquired = true; if (tb && tb2) goto success; found_port = true; } else { head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); inet_bind_bucket_for_each(tb, &head->chain) if (inet_bind_bucket_match(tb, net, port, l3mdev)) break; } if (!tb) { tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, net, head, port, l3mdev); if (!tb) goto fail_unlock; bhash_created = true; } if (!found_port) { if (!hlist_empty(&tb->bhash2)) { if (sk->sk_reuse == SK_FORCE_REUSE || (tb->fastreuse > 0 && reuse) || sk_reuseport_match(tb, sk)) check_bind_conflict = false; } if (check_bind_conflict && inet_use_bhash2_on_bind(sk)) { if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, true, true)) goto fail_unlock; } head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); spin_lock(&head2->lock); head2_lock_acquired = true; tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); } if (!tb2) { tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net, head2, tb, sk); if (!tb2) goto fail_unlock; bhash2_created = true; } if (!found_port && check_bind_conflict) { if (inet_csk_bind_conflict(sk, tb, tb2, true, true)) goto fail_unlock; } success: inet_csk_update_fastreuse(tb, sk); if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, tb2, port); WARN_ON(inet_csk(sk)->icsk_bind_hash != tb); WARN_ON(inet_csk(sk)->icsk_bind2_hash != tb2); ret = 0; fail_unlock: if (ret) { if (bhash2_created) inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, tb2); if (bhash_created) inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); } if (head2_lock_acquired) spin_unlock(&head2->lock); spin_unlock_bh(&head->lock); return ret; } EXPORT_SYMBOL_GPL(inet_csk_get_port); /* * Wait for an incoming connection, avoid race conditions. This must be called * with the socket locked. */ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) { struct inet_connection_sock *icsk = inet_csk(sk); DEFINE_WAIT(wait); int err; /* * True wake-one mechanism for incoming connections: only * one process gets woken up, not the 'whole herd'. * Since we do not 'race & poll' for established sockets * anymore, the common case will execute the loop only once. * * Subtle issue: "add_wait_queue_exclusive()" will be added * after any current non-exclusive waiters, and we know that * it will always _stay_ after any new non-exclusive waiters * because all non-exclusive waiters are added at the * beginning of the wait-queue. As such, it's ok to "drop" * our exclusiveness temporarily when we get woken up without * having to remove and re-insert us on the wait queue. */ for (;;) { prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); release_sock(sk); if (reqsk_queue_empty(&icsk->icsk_accept_queue)) timeo = schedule_timeout(timeo); sched_annotate_sleep(); lock_sock(sk); err = 0; if (!reqsk_queue_empty(&icsk->icsk_accept_queue)) break; err = -EINVAL; if (sk->sk_state != TCP_LISTEN) break; err = sock_intr_errno(timeo); if (signal_pending(current)) break; err = -EAGAIN; if (!timeo) break; } finish_wait(sk_sleep(sk), &wait); return err; } /* * This will accept the next outstanding connection. */ struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct request_sock *req; struct sock *newsk; int error; lock_sock(sk); /* We need to make sure that this socket is listening, * and that it has something pending. */ error = -EINVAL; if (sk->sk_state != TCP_LISTEN) goto out_err; /* Find already established connection */ if (reqsk_queue_empty(queue)) { long timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); /* If this is a non blocking socket don't sleep */ error = -EAGAIN; if (!timeo) goto out_err; error = inet_csk_wait_for_connect(sk, timeo); if (error) goto out_err; } req = reqsk_queue_remove(queue, sk); arg->is_empty = reqsk_queue_empty(queue); newsk = req->sk; if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { spin_lock_bh(&queue->fastopenq.lock); if (tcp_rsk(req)->tfo_listener) { /* We are still waiting for the final ACK from 3WHS * so can't free req now. Instead, we set req->sk to * NULL to signify that the child socket is taken * so reqsk_fastopen_remove() will free the req * when 3WHS finishes (or is aborted). */ req->sk = NULL; req = NULL; } spin_unlock_bh(&queue->fastopenq.lock); } out: release_sock(sk); if (newsk && mem_cgroup_sockets_enabled) { int amt = 0; /* atomically get the memory usage, set and charge the * newsk->sk_memcg. */ lock_sock(newsk); mem_cgroup_sk_alloc(newsk); if (newsk->sk_memcg) { /* The socket has not been accepted yet, no need * to look at newsk->sk_wmem_queued. */ amt = sk_mem_pages(newsk->sk_forward_alloc + atomic_read(&newsk->sk_rmem_alloc)); } if (amt) mem_cgroup_charge_skmem(newsk->sk_memcg, amt, GFP_KERNEL | __GFP_NOFAIL); release_sock(newsk); } if (req) reqsk_put(req); if (newsk) inet_init_csk_locks(newsk); return newsk; out_err: newsk = NULL; req = NULL; arg->err = error; goto out; } EXPORT_SYMBOL(inet_csk_accept); /* * Using different timers for retransmit, delayed acks and probes * We may wish use just one timer maintaining a list of expire jiffies * to optimize. */ void inet_csk_init_xmit_timers(struct sock *sk, void (*retransmit_handler)(struct timer_list *t), void (*delack_handler)(struct timer_list *t), void (*keepalive_handler)(struct timer_list *t)) { struct inet_connection_sock *icsk = inet_csk(sk); timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0); timer_setup(&icsk->icsk_delack_timer, delack_handler, 0); timer_setup(&sk->sk_timer, keepalive_handler, 0); icsk->icsk_pending = icsk->icsk_ack.pending = 0; } EXPORT_SYMBOL(inet_csk_init_xmit_timers); void inet_csk_clear_xmit_timers(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_pending = icsk->icsk_ack.pending = 0; sk_stop_timer(sk, &icsk->icsk_retransmit_timer); sk_stop_timer(sk, &icsk->icsk_delack_timer); sk_stop_timer(sk, &sk->sk_timer); } EXPORT_SYMBOL(inet_csk_clear_xmit_timers); void inet_csk_clear_xmit_timers_sync(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); /* ongoing timer handlers need to acquire socket lock. */ sock_not_owned_by_me(sk); icsk->icsk_pending = icsk->icsk_ack.pending = 0; sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); sk_stop_timer_sync(sk, &sk->sk_timer); } void inet_csk_delete_keepalive_timer(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); } EXPORT_SYMBOL(inet_csk_delete_keepalive_timer); void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len) { sk_reset_timer(sk, &sk->sk_timer, jiffies + len); } EXPORT_SYMBOL(inet_csk_reset_keepalive_timer); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req) { const struct inet_request_sock *ireq = inet_rsk(req); struct net *net = read_pnet(&ireq->ireq_net); struct ip_options_rcu *opt; struct rtable *rt; rcu_read_lock(); opt = rcu_dereference(ireq->ireq_opt); flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, ireq->ir_rmt_port, htons(ireq->ir_num), sk->sk_uid); security_req_classify_flow(req, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; rcu_read_unlock(); return &rt->dst; route_err: ip_rt_put(rt); no_route: rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } EXPORT_SYMBOL_GPL(inet_csk_route_req); struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req) { const struct inet_request_sock *ireq = inet_rsk(req); struct net *net = read_pnet(&ireq->ireq_net); struct inet_sock *newinet = inet_sk(newsk); struct ip_options_rcu *opt; struct flowi4 *fl4; struct rtable *rt; opt = rcu_dereference(ireq->ireq_opt); fl4 = &newinet->cork.fl.u.ip4; flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, ireq->ir_rmt_port, htons(ireq->ir_num), sk->sk_uid); security_req_classify_flow(req, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; return &rt->dst; route_err: ip_rt_put(rt); no_route: __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } EXPORT_SYMBOL_GPL(inet_csk_route_child_sock); /* Decide when to expire the request and when to resend SYN-ACK */ static void syn_ack_recalc(struct request_sock *req, const int max_syn_ack_retries, const u8 rskq_defer_accept, int *expire, int *resend) { if (!rskq_defer_accept) { *expire = req->num_timeout >= max_syn_ack_retries; *resend = 1; return; } *expire = req->num_timeout >= max_syn_ack_retries && (!inet_rsk(req)->acked || req->num_timeout >= rskq_defer_accept); /* Do not resend while waiting for data after ACK, * start to resend on end of deferring period to give * last chance for data or ACK to create established socket. */ *resend = !inet_rsk(req)->acked || req->num_timeout >= rskq_defer_accept - 1; } int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) { int err = req->rsk_ops->rtx_syn_ack(parent, req); if (!err) req->num_retrans++; return err; } EXPORT_SYMBOL(inet_rtx_syn_ack); static struct request_sock * reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener) { struct request_sock *req; req = kmem_cache_alloc_noprof(ops->slab, GFP_ATOMIC | __GFP_NOWARN); if (!req) return NULL; req->rsk_listener = NULL; if (attach_listener) { if (unlikely(!refcount_inc_not_zero(&sk_listener->sk_refcnt))) { kmem_cache_free(ops->slab, req); return NULL; } req->rsk_listener = sk_listener; } req->rsk_ops = ops; req_to_sk(req)->sk_prot = sk_listener->sk_prot; sk_node_init(&req_to_sk(req)->sk_node); sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; req->syncookie = 0; req->timeout = 0; req->num_timeout = 0; req->num_retrans = 0; req->sk = NULL; refcount_set(&req->rsk_refcnt, 0); return req; } #define reqsk_alloc(...) alloc_hooks(reqsk_alloc_noprof(__VA_ARGS__)) struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener) { struct request_sock *req = reqsk_alloc(ops, sk_listener, attach_listener); if (req) { struct inet_request_sock *ireq = inet_rsk(req); ireq->ireq_opt = NULL; #if IS_ENABLED(CONFIG_IPV6) ireq->pktopts = NULL; #endif atomic64_set(&ireq->ir_cookie, 0); ireq->ireq_state = TCP_NEW_SYN_RECV; write_pnet(&ireq->ireq_net, sock_net(sk_listener)); ireq->ireq_family = sk_listener->sk_family; req->timeout = TCP_TIMEOUT_INIT; } return req; } EXPORT_SYMBOL(inet_reqsk_alloc); static struct request_sock *inet_reqsk_clone(struct request_sock *req, struct sock *sk) { struct sock *req_sk, *nreq_sk; struct request_sock *nreq; nreq = kmem_cache_alloc(req->rsk_ops->slab, GFP_ATOMIC | __GFP_NOWARN); if (!nreq) { __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); /* paired with refcount_inc_not_zero() in reuseport_migrate_sock() */ sock_put(sk); return NULL; } req_sk = req_to_sk(req); nreq_sk = req_to_sk(nreq); memcpy(nreq_sk, req_sk, offsetof(struct sock, sk_dontcopy_begin)); unsafe_memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end), /* alloc is larger than struct, see above */); sk_node_init(&nreq_sk->sk_node); nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping; #endif nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu; nreq->rsk_listener = sk; /* We need not acquire fastopenq->lock * because the child socket is locked in inet_csk_listen_stop(). */ if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq); return nreq; } static void reqsk_queue_migrated(struct request_sock_queue *queue, const struct request_sock *req) { if (req->num_timeout == 0) atomic_inc(&queue->young); atomic_inc(&queue->qlen); } static void reqsk_migrate_reset(struct request_sock *req) { req->saved_syn = NULL; #if IS_ENABLED(CONFIG_IPV6) inet_rsk(req)->ipv6_opt = NULL; inet_rsk(req)->pktopts = NULL; #else inet_rsk(req)->ireq_opt = NULL; #endif } /* return true if req was found in the ehash table */ static bool reqsk_queue_unlink(struct request_sock *req) { struct sock *sk = req_to_sk(req); bool found = false; if (sk_hashed(sk)) { struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash); spin_lock(lock); found = __sk_nulls_del_node_init_rcu(sk); spin_unlock(lock); } if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer)) reqsk_put(req); return found; } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) { bool unlinked = reqsk_queue_unlink(req); if (unlinked) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); reqsk_put(req); } return unlinked; } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req) { inet_csk_reqsk_queue_drop(sk, req); reqsk_put(req); } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); static void reqsk_timer_handler(struct timer_list *t) { struct request_sock *req = from_timer(req, t, rsk_timer); struct request_sock *nreq = NULL, *oreq = req; struct sock *sk_listener = req->rsk_listener; struct inet_connection_sock *icsk; struct request_sock_queue *queue; struct net *net; int max_syn_ack_retries, qlen, expire = 0, resend = 0; if (inet_sk_state_load(sk_listener) != TCP_LISTEN) { struct sock *nsk; nsk = reuseport_migrate_sock(sk_listener, req_to_sk(req), NULL); if (!nsk) goto drop; nreq = inet_reqsk_clone(req, nsk); if (!nreq) goto drop; /* The new timer for the cloned req can decrease the 2 * by calling inet_csk_reqsk_queue_drop_and_put(), so * hold another count to prevent use-after-free and * call reqsk_put() just before return. */ refcount_set(&nreq->rsk_refcnt, 2 + 1); timer_setup(&nreq->rsk_timer, reqsk_timer_handler, TIMER_PINNED); reqsk_queue_migrated(&inet_csk(nsk)->icsk_accept_queue, req); req = nreq; sk_listener = nsk; } icsk = inet_csk(sk_listener); net = sock_net(sk_listener); max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means * one of the following things: synack was lost, ack was lost, * rtt is high or nobody planned to ack (i.e. synflood). * When server is a bit loaded, queue is populated with old * open requests, reducing effective size of queue. * When server is well loaded, queue size reduces to zero * after several minutes of work. It is not synflood, * it is normal operation. The solution is pruning * too old entries overriding normal timeout, when * situation becomes dangerous. * * Essentially, we reserve half of room for young * embrions; and abort old ones without pity, if old * ones are about to clog our table. */ queue = &icsk->icsk_accept_queue; qlen = reqsk_queue_len(queue); if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) { int young = reqsk_queue_len_young(queue) << 1; while (max_syn_ack_retries > 2) { if (qlen < young) break; max_syn_ack_retries--; young <<= 1; } } syn_ack_recalc(req, max_syn_ack_retries, READ_ONCE(queue->rskq_defer_accept), &expire, &resend); req->rsk_ops->syn_ack_timeout(req); if (!expire && (!resend || !inet_rtx_syn_ack(sk_listener, req) || inet_rsk(req)->acked)) { if (req->num_timeout++ == 0) atomic_dec(&queue->young); mod_timer(&req->rsk_timer, jiffies + reqsk_timeout(req, TCP_RTO_MAX)); if (!nreq) return; if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { /* delete timer */ inet_csk_reqsk_queue_drop(sk_listener, nreq); goto no_ownership; } __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQSUCCESS); reqsk_migrate_reset(oreq); reqsk_queue_removed(&inet_csk(oreq->rsk_listener)->icsk_accept_queue, oreq); reqsk_put(oreq); reqsk_put(nreq); return; } /* Even if we can clone the req, we may need not retransmit any more * SYN+ACKs (nreq->num_timeout > max_syn_ack_retries, etc), or another * CPU may win the "own_req" race so that inet_ehash_insert() fails. */ if (nreq) { __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQFAILURE); no_ownership: reqsk_migrate_reset(nreq); reqsk_queue_removed(queue, nreq); __reqsk_free(nreq); } drop: inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq); } static bool reqsk_queue_hash_req(struct request_sock *req, unsigned long timeout) { bool found_dup_sk = false; if (!inet_ehash_insert(req_to_sk(req), NULL, &found_dup_sk)) return false; /* The timer needs to be setup after a successful insertion. */ timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ smp_wmb(); refcount_set(&req->rsk_refcnt, 2 + 1); return true; } bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout) { if (!reqsk_queue_hash_req(req, timeout)) return false; inet_csk_reqsk_queue_added(sk); return true; } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk, const gfp_t priority) { struct inet_connection_sock *icsk = inet_csk(newsk); if (!icsk->icsk_ulp_ops) return; icsk->icsk_ulp_ops->clone(req, newsk, priority); } /** * inet_csk_clone_lock - clone an inet socket, and lock its clone * @sk: the socket to clone * @req: request_sock * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) */ struct sock *inet_csk_clone_lock(const struct sock *sk, const struct request_sock *req, const gfp_t priority) { struct sock *newsk = sk_clone_lock(sk, priority); if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port; inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num; inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); /* listeners have SOCK_RCU_FREE, not the children */ sock_reset_flag(newsk, SOCK_RCU_FREE); inet_sk(newsk)->mc_list = NULL; newsk->sk_mark = inet_rsk(req)->ir_mark; atomic64_set(&newsk->sk_cookie, atomic64_read(&inet_rsk(req)->ir_cookie)); newicsk->icsk_retransmits = 0; newicsk->icsk_backoff = 0; newicsk->icsk_probes_out = 0; newicsk->icsk_probes_tstamp = 0; /* Deinitialize accept_queue to trap illegal accesses. */ memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue)); inet_clone_ulp(req, newsk, priority); security_inet_csk_clone(newsk, req); } return newsk; } EXPORT_SYMBOL_GPL(inet_csk_clone_lock); /* * At this point, there should be no process reference to this * socket, and thus no user references at all. Therefore we * can assume the socket waitqueue is inactive and nobody will * try to jump onto it. */ void inet_csk_destroy_sock(struct sock *sk) { WARN_ON(sk->sk_state != TCP_CLOSE); WARN_ON(!sock_flag(sk, SOCK_DEAD)); /* It cannot be in hash table! */ WARN_ON(!sk_unhashed(sk)); /* If it has not 0 inet_sk(sk)->inet_num, it must be bound */ WARN_ON(inet_sk(sk)->inet_num && !inet_csk(sk)->icsk_bind_hash); sk->sk_prot->destroy(sk); sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); this_cpu_dec(*sk->sk_prot->orphan_count); sock_put(sk); } EXPORT_SYMBOL(inet_csk_destroy_sock); /* This function allows to force a closure of a socket after the call to * tcp/dccp_create_openreq_child(). */ void inet_csk_prepare_forced_close(struct sock *sk) __releases(&sk->sk_lock.slock) { /* sk_clone_lock locked the socket and set refcnt to 2 */ bh_unlock_sock(sk); sock_put(sk); inet_csk_prepare_for_destroy_sock(sk); inet_sk(sk)->inet_num = 0; } EXPORT_SYMBOL(inet_csk_prepare_forced_close); static int inet_ulp_can_listen(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone) return -EINVAL; return 0; } int inet_csk_listen_start(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); int err; err = inet_ulp_can_listen(sk); if (unlikely(err)) return err; reqsk_queue_alloc(&icsk->icsk_accept_queue); sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only * after validation is complete. */ inet_sk_state_store(sk, TCP_LISTEN); err = sk->sk_prot->get_port(sk, inet->inet_num); if (!err) { inet->inet_sport = htons(inet->inet_num); sk_dst_reset(sk); err = sk->sk_prot->hash(sk); if (likely(!err)) return 0; } inet_sk_set_state(sk, TCP_CLOSE); return err; } EXPORT_SYMBOL_GPL(inet_csk_listen_start); static void inet_child_forget(struct sock *sk, struct request_sock *req, struct sock *child) { sk->sk_prot->disconnect(child, O_NONBLOCK); sock_orphan(child); this_cpu_inc(*sk->sk_prot->orphan_count); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if * an inbound pkt destined for child is * blocked by sock lock in tcp_v4_rcv(). * Also to satisfy an assertion in * tcp_v4_destroy_sock(). */ RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL); } inet_csk_destroy_sock(child); } struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; spin_lock(&queue->rskq_lock); if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_child_forget(sk, req, child); child = NULL; } else { req->sk = child; req->dl_next = NULL; if (queue->rskq_accept_head == NULL) WRITE_ONCE(queue->rskq_accept_head, req); else queue->rskq_accept_tail->dl_next = req; queue->rskq_accept_tail = req; sk_acceptq_added(sk); } spin_unlock(&queue->rskq_lock); return child; } EXPORT_SYMBOL(inet_csk_reqsk_queue_add); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req) { if (own_req) { inet_csk_reqsk_queue_drop(req->rsk_listener, req); reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); if (sk != req->rsk_listener) { /* another listening sk has been selected, * migrate the req to it. */ struct request_sock *nreq; /* hold a refcnt for the nreq->rsk_listener * which is assigned in inet_reqsk_clone() */ sock_hold(sk); nreq = inet_reqsk_clone(req, sk); if (!nreq) { inet_child_forget(sk, req, child); goto child_put; } refcount_set(&nreq->rsk_refcnt, 1); if (inet_csk_reqsk_queue_add(sk, nreq, child)) { __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQSUCCESS); reqsk_migrate_reset(req); reqsk_put(req); return child; } __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); reqsk_migrate_reset(nreq); __reqsk_free(nreq); } else if (inet_csk_reqsk_queue_add(sk, req, child)) { return child; } } /* Too bad, another child took ownership of the request, undo. */ child_put: bh_unlock_sock(child); sock_put(child); return NULL; } EXPORT_SYMBOL(inet_csk_complete_hashdance); /* * This routine closes sockets which have been at least partially * opened, but not yet accepted. */ void inet_csk_listen_stop(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct request_sock *next, *req; /* Following specs, it would be better either to send FIN * (and enter FIN-WAIT-1, it is normal close) * or to send active reset (abort). * Certainly, it is pretty dangerous while synflood, but it is * bad justification for our negligence 8) * To be honest, we are not able to make either * of the variants now. --ANK */ while ((req = reqsk_queue_remove(queue, sk)) != NULL) { struct sock *child = req->sk, *nsk; struct request_sock *nreq; local_bh_disable(); bh_lock_sock(child); WARN_ON(sock_owned_by_user(child)); sock_hold(child); nsk = reuseport_migrate_sock(sk, child, NULL); if (nsk) { nreq = inet_reqsk_clone(req, nsk); if (nreq) { refcount_set(&nreq->rsk_refcnt, 1); if (inet_csk_reqsk_queue_add(nsk, nreq, child)) { __NET_INC_STATS(sock_net(nsk), LINUX_MIB_TCPMIGRATEREQSUCCESS); reqsk_migrate_reset(req); } else { __NET_INC_STATS(sock_net(nsk), LINUX_MIB_TCPMIGRATEREQFAILURE); reqsk_migrate_reset(nreq); __reqsk_free(nreq); } /* inet_csk_reqsk_queue_add() has already * called inet_child_forget() on failure case. */ goto skip_child_forget; } } inet_child_forget(sk, req, child); skip_child_forget: reqsk_put(req); bh_unlock_sock(child); local_bh_enable(); sock_put(child); cond_resched(); } if (queue->fastopenq.rskq_rst_head) { /* Free all the reqs queued in rskq_rst_head. */ spin_lock_bh(&queue->fastopenq.lock); req = queue->fastopenq.rskq_rst_head; queue->fastopenq.rskq_rst_head = NULL; spin_unlock_bh(&queue->fastopenq.lock); while (req != NULL) { next = req->dl_next; reqsk_put(req); req = next; } } WARN_ON_ONCE(sk->sk_ack_backlog); } EXPORT_SYMBOL_GPL(inet_csk_listen_stop); void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; const struct inet_sock *inet = inet_sk(sk); sin->sin_family = AF_INET; sin->sin_addr.s_addr = inet->inet_daddr; sin->sin_port = inet->inet_dport; } EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr); static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; struct flowi4 *fl4; struct rtable *rt; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; fl4 = &fl->u.ip4; rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) rt = NULL; if (rt) sk_setup_caps(sk, &rt->dst); rcu_read_unlock(); return &rt->dst; } struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) { struct dst_entry *dst = __sk_dst_check(sk, 0); struct inet_sock *inet = inet_sk(sk); if (!dst) { dst = inet_csk_rebuild_route(sk, &inet->cork.fl); if (!dst) goto out; } dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = __sk_dst_check(sk, 0); if (!dst) dst = inet_csk_rebuild_route(sk, &inet->cork.fl); out: return dst; } EXPORT_SYMBOL_GPL(inet_csk_update_pmtu); |
| 741 739 741 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 | // SPDX-License-Identifier: GPL-2.0 OR MIT /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include <crypto/internal/blake2s.h> #include <linux/types.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/sizes.h> #include <asm/cpufeature.h> #include <asm/fpu/api.h> #include <asm/processor.h> #include <asm/simd.h> asmlinkage void blake2s_compress_ssse3(struct blake2s_state *state, const u8 *block, const size_t nblocks, const u32 inc); asmlinkage void blake2s_compress_avx512(struct blake2s_state *state, const u8 *block, const size_t nblocks, const u32 inc); static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3); static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512); void blake2s_compress(struct blake2s_state *state, const u8 *block, size_t nblocks, const u32 inc) { /* SIMD disables preemption, so relax after processing each page. */ BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8); if (!static_branch_likely(&blake2s_use_ssse3) || !may_use_simd()) { blake2s_compress_generic(state, block, nblocks, inc); return; } do { const size_t blocks = min_t(size_t, nblocks, SZ_4K / BLAKE2S_BLOCK_SIZE); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&blake2s_use_avx512)) blake2s_compress_avx512(state, block, blocks, inc); else blake2s_compress_ssse3(state, block, blocks, inc); kernel_fpu_end(); nblocks -= blocks; block += blocks * BLAKE2S_BLOCK_SIZE; } while (nblocks); } EXPORT_SYMBOL(blake2s_compress); static int __init blake2s_mod_init(void) { if (boot_cpu_has(X86_FEATURE_SSSE3)) static_branch_enable(&blake2s_use_ssse3); if (IS_ENABLED(CONFIG_AS_AVX512) && boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX512F) && boot_cpu_has(X86_FEATURE_AVX512VL) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL)) static_branch_enable(&blake2s_use_avx512); return 0; } subsys_initcall(blake2s_mod_init); |
| 3 3 45 24 23 355 141 243 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_proto.c: transport protocol load balancing support for IPVS * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Julian Anastasov <ja@ssi.bg> * * Changes: */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/gfp.h> #include <linux/in.h> #include <linux/ip.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/udp.h> #include <linux/stat.h> #include <linux/proc_fs.h> #include <net/ip_vs.h> /* * IPVS protocols can only be registered/unregistered when the ipvs * module is loaded/unloaded, so no lock is needed in accessing the * ipvs protocol table. */ #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */ #define IP_VS_PROTO_HASH(proto) ((proto) & (IP_VS_PROTO_TAB_SIZE-1)) static struct ip_vs_protocol *ip_vs_proto_table[IP_VS_PROTO_TAB_SIZE]; /* States for conn templates: NONE or words separated with ",", max 15 chars */ static const char *ip_vs_ctpl_state_name_table[IP_VS_CTPL_S_LAST] = { [IP_VS_CTPL_S_NONE] = "NONE", [IP_VS_CTPL_S_ASSURED] = "ASSURED", }; /* * register an ipvs protocol */ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) { unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); pp->next = ip_vs_proto_table[hash]; ip_vs_proto_table[hash] = pp; if (pp->init != NULL) pp->init(pp); return 0; } /* * register an ipvs protocols netns related data */ static int register_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_protocol *pp) { unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); struct ip_vs_proto_data *pd = kzalloc(sizeof(struct ip_vs_proto_data), GFP_KERNEL); if (!pd) return -ENOMEM; pd->pp = pp; /* For speed issues */ pd->next = ipvs->proto_data_table[hash]; ipvs->proto_data_table[hash] = pd; atomic_set(&pd->appcnt, 0); /* Init app counter */ if (pp->init_netns != NULL) { int ret = pp->init_netns(ipvs, pd); if (ret) { /* unlink an free proto data */ ipvs->proto_data_table[hash] = pd->next; kfree(pd); return ret; } } return 0; } /* * unregister an ipvs protocol */ static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp) { struct ip_vs_protocol **pp_p; unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); pp_p = &ip_vs_proto_table[hash]; for (; *pp_p; pp_p = &(*pp_p)->next) { if (*pp_p == pp) { *pp_p = pp->next; if (pp->exit != NULL) pp->exit(pp); return 0; } } return -ESRCH; } /* * unregister an ipvs protocols netns data */ static int unregister_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { struct ip_vs_proto_data **pd_p; unsigned int hash = IP_VS_PROTO_HASH(pd->pp->protocol); pd_p = &ipvs->proto_data_table[hash]; for (; *pd_p; pd_p = &(*pd_p)->next) { if (*pd_p == pd) { *pd_p = pd->next; if (pd->pp->exit_netns != NULL) pd->pp->exit_netns(ipvs, pd); kfree(pd); return 0; } } return -ESRCH; } /* * get ip_vs_protocol object by its proto. */ struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto) { struct ip_vs_protocol *pp; unsigned int hash = IP_VS_PROTO_HASH(proto); for (pp = ip_vs_proto_table[hash]; pp; pp = pp->next) { if (pp->protocol == proto) return pp; } return NULL; } EXPORT_SYMBOL(ip_vs_proto_get); /* * get ip_vs_protocol object data by netns and proto */ struct ip_vs_proto_data * ip_vs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) { struct ip_vs_proto_data *pd; unsigned int hash = IP_VS_PROTO_HASH(proto); for (pd = ipvs->proto_data_table[hash]; pd; pd = pd->next) { if (pd->pp->protocol == proto) return pd; } return NULL; } EXPORT_SYMBOL(ip_vs_proto_data_get); /* * Propagate event for state change to all protocols */ void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags) { struct ip_vs_proto_data *pd; int i; for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { for (pd = ipvs->proto_data_table[i]; pd; pd = pd->next) { if (pd->pp->timeout_change) pd->pp->timeout_change(pd, flags); } } } int * ip_vs_create_timeout_table(int *table, int size) { return kmemdup(table, size, GFP_KERNEL); } const char *ip_vs_state_name(const struct ip_vs_conn *cp) { unsigned int state = cp->state; struct ip_vs_protocol *pp; if (cp->flags & IP_VS_CONN_F_TEMPLATE) { if (state >= IP_VS_CTPL_S_LAST) return "ERR!"; return ip_vs_ctpl_state_name_table[state] ? : "?"; } pp = ip_vs_proto_get(cp->protocol); if (pp == NULL || pp->state_name == NULL) return (cp->protocol == IPPROTO_IP) ? "NONE" : "ERR!"; return pp->state_name(state); } static void ip_vs_tcpudp_debug_packet_v4(struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg) { char buf[128]; struct iphdr _iph, *ih; ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) sprintf(buf, "TRUNCATED"); else if (ih->frag_off & htons(IP_OFFSET)) sprintf(buf, "%pI4->%pI4 frag", &ih->saddr, &ih->daddr); else { __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, offset + ih->ihl*4, sizeof(_ports), _ports); if (pptr == NULL) sprintf(buf, "TRUNCATED %pI4->%pI4", &ih->saddr, &ih->daddr); else sprintf(buf, "%pI4:%u->%pI4:%u", &ih->saddr, ntohs(pptr[0]), &ih->daddr, ntohs(pptr[1])); } pr_debug("%s: %s %s\n", msg, pp->name, buf); } #ifdef CONFIG_IP_VS_IPV6 static void ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg) { char buf[192]; struct ipv6hdr _iph, *ih; ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) sprintf(buf, "TRUNCATED"); else if (ih->nexthdr == IPPROTO_FRAGMENT) sprintf(buf, "%pI6c->%pI6c frag", &ih->saddr, &ih->daddr); else { __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, offset + sizeof(struct ipv6hdr), sizeof(_ports), _ports); if (pptr == NULL) sprintf(buf, "TRUNCATED %pI6c->%pI6c", &ih->saddr, &ih->daddr); else sprintf(buf, "%pI6c:%u->%pI6c:%u", &ih->saddr, ntohs(pptr[0]), &ih->daddr, ntohs(pptr[1])); } pr_debug("%s: %s %s\n", msg, pp->name, buf); } #endif void ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_tcpudp_debug_packet_v6(pp, skb, offset, msg); else #endif ip_vs_tcpudp_debug_packet_v4(pp, skb, offset, msg); } /* * per network name-space init */ int __net_init ip_vs_protocol_net_init(struct netns_ipvs *ipvs) { int i, ret; static struct ip_vs_protocol *protos[] = { #ifdef CONFIG_IP_VS_PROTO_TCP &ip_vs_protocol_tcp, #endif #ifdef CONFIG_IP_VS_PROTO_UDP &ip_vs_protocol_udp, #endif #ifdef CONFIG_IP_VS_PROTO_SCTP &ip_vs_protocol_sctp, #endif #ifdef CONFIG_IP_VS_PROTO_AH &ip_vs_protocol_ah, #endif #ifdef CONFIG_IP_VS_PROTO_ESP &ip_vs_protocol_esp, #endif }; for (i = 0; i < ARRAY_SIZE(protos); i++) { ret = register_ip_vs_proto_netns(ipvs, protos[i]); if (ret < 0) goto cleanup; } return 0; cleanup: ip_vs_protocol_net_cleanup(ipvs); return ret; } void __net_exit ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs) { struct ip_vs_proto_data *pd; int i; /* unregister all the ipvs proto data for this netns */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pd = ipvs->proto_data_table[i]) != NULL) unregister_ip_vs_proto_netns(ipvs, pd); } } int __init ip_vs_protocol_init(void) { char protocols[64]; #define REGISTER_PROTOCOL(p) \ do { \ register_ip_vs_protocol(p); \ strcat(protocols, ", "); \ strcat(protocols, (p)->name); \ } while (0) protocols[0] = '\0'; protocols[2] = '\0'; #ifdef CONFIG_IP_VS_PROTO_TCP REGISTER_PROTOCOL(&ip_vs_protocol_tcp); #endif #ifdef CONFIG_IP_VS_PROTO_UDP REGISTER_PROTOCOL(&ip_vs_protocol_udp); #endif #ifdef CONFIG_IP_VS_PROTO_SCTP REGISTER_PROTOCOL(&ip_vs_protocol_sctp); #endif #ifdef CONFIG_IP_VS_PROTO_AH REGISTER_PROTOCOL(&ip_vs_protocol_ah); #endif #ifdef CONFIG_IP_VS_PROTO_ESP REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); return 0; } void ip_vs_protocol_cleanup(void) { struct ip_vs_protocol *pp; int i; /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) unregister_ip_vs_protocol(pp); } } |
| 14 3 1 1 3 2 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2016 Pablo Neira Ayuso <pablo@netfilter.org> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> struct nft_range_expr { struct nft_data data_from; struct nft_data data_to; u8 sreg; u8 len; enum nft_range_ops op:8; }; void nft_range_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_range_expr *priv = nft_expr_priv(expr); int d1, d2; d1 = memcmp(®s->data[priv->sreg], &priv->data_from, priv->len); d2 = memcmp(®s->data[priv->sreg], &priv->data_to, priv->len); switch (priv->op) { case NFT_RANGE_EQ: if (d1 < 0 || d2 > 0) regs->verdict.code = NFT_BREAK; break; case NFT_RANGE_NEQ: if (d1 >= 0 && d2 <= 0) regs->verdict.code = NFT_BREAK; break; } } static const struct nla_policy nft_range_policy[NFTA_RANGE_MAX + 1] = { [NFTA_RANGE_SREG] = { .type = NLA_U32 }, [NFTA_RANGE_OP] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_RANGE_FROM_DATA] = { .type = NLA_NESTED }, [NFTA_RANGE_TO_DATA] = { .type = NLA_NESTED }, }; static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_range_expr *priv = nft_expr_priv(expr); struct nft_data_desc desc_from = { .type = NFT_DATA_VALUE, .size = sizeof(priv->data_from), }; struct nft_data_desc desc_to = { .type = NFT_DATA_VALUE, .size = sizeof(priv->data_to), }; int err; u32 op; if (!tb[NFTA_RANGE_SREG] || !tb[NFTA_RANGE_OP] || !tb[NFTA_RANGE_FROM_DATA] || !tb[NFTA_RANGE_TO_DATA]) return -EINVAL; err = nft_data_init(NULL, &priv->data_from, &desc_from, tb[NFTA_RANGE_FROM_DATA]); if (err < 0) return err; err = nft_data_init(NULL, &priv->data_to, &desc_to, tb[NFTA_RANGE_TO_DATA]); if (err < 0) goto err1; if (desc_from.len != desc_to.len) { err = -EINVAL; goto err2; } err = nft_parse_register_load(tb[NFTA_RANGE_SREG], &priv->sreg, desc_from.len); if (err < 0) goto err2; err = nft_parse_u32_check(tb[NFTA_RANGE_OP], U8_MAX, &op); if (err < 0) goto err2; switch (op) { case NFT_RANGE_EQ: case NFT_RANGE_NEQ: break; default: err = -EINVAL; goto err2; } priv->op = op; priv->len = desc_from.len; return 0; err2: nft_data_release(&priv->data_to, desc_to.type); err1: nft_data_release(&priv->data_from, desc_from.type); return err; } static int nft_range_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_range_expr *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_RANGE_SREG, priv->sreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_RANGE_OP, htonl(priv->op))) goto nla_put_failure; if (nft_data_dump(skb, NFTA_RANGE_FROM_DATA, &priv->data_from, NFT_DATA_VALUE, priv->len) < 0 || nft_data_dump(skb, NFTA_RANGE_TO_DATA, &priv->data_to, NFT_DATA_VALUE, priv->len) < 0) goto nla_put_failure; return 0; nla_put_failure: return -1; } static const struct nft_expr_ops nft_range_ops = { .type = &nft_range_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_range_expr)), .eval = nft_range_eval, .init = nft_range_init, .dump = nft_range_dump, .reduce = NFT_REDUCE_READONLY, }; struct nft_expr_type nft_range_type __read_mostly = { .name = "range", .ops = &nft_range_ops, .policy = nft_range_policy, .maxattr = NFTA_RANGE_MAX, .owner = THIS_MODULE, }; |
| 15 15 4 1 8 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 | // SPDX-License-Identifier: GPL-2.0-only /* iptables module for using new netfilter netlink queue * * (C) 2005 by Harald Welte <laforge@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/netfilter_arp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_NFQUEUE.h> #include <net/netfilter/nf_queue.h> MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: packet forwarding to netlink"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_NFQUEUE"); MODULE_ALIAS("ip6t_NFQUEUE"); MODULE_ALIAS("arpt_NFQUEUE"); static u32 jhash_initval __read_mostly; static unsigned int nfqueue_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info *tinfo = par->targinfo; return NF_QUEUE_NR(tinfo->queuenum); } static unsigned int nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v1 *info = par->targinfo; u32 queue = info->queuenum; if (info->queues_total > 1) { queue = nfqueue_hash(skb, queue, info->queues_total, xt_family(par), jhash_initval); } return NF_QUEUE_NR(queue); } static unsigned int nfqueue_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v2 *info = par->targinfo; unsigned int ret = nfqueue_tg_v1(skb, par); if (info->bypass) ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; return ret; } static int nfqueue_tg_check(const struct xt_tgchk_param *par) { const struct xt_NFQ_info_v3 *info = par->targinfo; u32 maxid; init_hashrandom(&jhash_initval); if (info->queues_total == 0) { pr_info_ratelimited("number of total queues is 0\n"); return -EINVAL; } maxid = info->queues_total - 1 + info->queuenum; if (maxid > 0xffff) { pr_info_ratelimited("number of queues (%u) out of range (got %u)\n", info->queues_total, maxid); return -ERANGE; } if (par->target->revision == 2 && info->flags > 1) return -EINVAL; if (par->target->revision == 3 && info->flags & ~NFQ_FLAG_MASK) return -EINVAL; return 0; } static unsigned int nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v3 *info = par->targinfo; u32 queue = info->queuenum; int ret; if (info->queues_total > 1) { if (info->flags & NFQ_FLAG_CPU_FANOUT) { int cpu = smp_processor_id(); queue = info->queuenum + cpu % info->queues_total; } else { queue = nfqueue_hash(skb, queue, info->queues_total, xt_family(par), jhash_initval); } } ret = NF_QUEUE_NR(queue); if (info->flags & NFQ_FLAG_BYPASS) ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; return ret; } static struct xt_target nfqueue_tg_reg[] __read_mostly = { { .name = "NFQUEUE", .family = NFPROTO_UNSPEC, .target = nfqueue_tg, .targetsize = sizeof(struct xt_NFQ_info), .me = THIS_MODULE, }, { .name = "NFQUEUE", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v1, .targetsize = sizeof(struct xt_NFQ_info_v1), .me = THIS_MODULE, }, { .name = "NFQUEUE", .revision = 2, .family = NFPROTO_UNSPEC, .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v2, .targetsize = sizeof(struct xt_NFQ_info_v2), .me = THIS_MODULE, }, { .name = "NFQUEUE", .revision = 3, .family = NFPROTO_UNSPEC, .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v3, .targetsize = sizeof(struct xt_NFQ_info_v3), .me = THIS_MODULE, }, }; static int __init nfqueue_tg_init(void) { return xt_register_targets(nfqueue_tg_reg, ARRAY_SIZE(nfqueue_tg_reg)); } static void __exit nfqueue_tg_exit(void) { xt_unregister_targets(nfqueue_tg_reg, ARRAY_SIZE(nfqueue_tg_reg)); } module_init(nfqueue_tg_init); module_exit(nfqueue_tg_exit); |
| 298 19 10 297 1602 176 676 1356 1184 27 5148 1029 2181 1123 4880 43 4883 765 254 4575 46 5073 5074 5075 4771 979 4458 1590 1454 1452 1162 1165 1519 31 287 187 175 9 1423 9 211 1485 181 33 16 17 17 17 1 16 2 17 2 593 96 29 73 73 506 192 1429 108 212 899 1073 90 90 28 19 90 4 90 66 60 90 1584 1429 1431 1433 1151 1430 1310 1584 261 122 139 938 1066 1066 851 1541 1379 595 1826 705 72 1756 1760 529 1540 1521 27 1581 636 1755 1759 1377 19 19 595 610 9 609 1545 175 181 176 704 635 673 594 337 298 1479 22 448 1358 1184 1 441 10 46 587 727 47 1684 10 197 1687 1039 1122 1077 155 233 93 212 187 1640 1641 1442 473 1418 1059 30 1420 1420 1420 1089 1089 1420 1086 1114 1029 86 112 82 33 86 86 22 81 16 16 15 2734 2732 2738 850 635 630 631 630 851 851 850 849 7 7 7 64 11 46 10 64 1105 1105 1106 1097 1097 1095 1096 4 1 180 182 182 176 11 171 3 4 1 1 703 704 182 538 104 703 440 412 20 46 49 7 42 43 20 20 48 43 20 389 389 391 98 296 391 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation * Copyright (c) 2017-2018 Microsoft Corporation * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox <willy@infradead.org> */ #include <linux/bitmap.h> #include <linux/export.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Coding conventions in this file: * * @xa is used to refer to the entire xarray. * @xas is the 'xarray operation state'. It may be either a pointer to * an xa_state, or an xa_state stored on the stack. This is an unfortunate * ambiguity. * @index is the index of the entry being operated on * @mark is an xa_mark_t; a small number indicating one of the mark bits. * @node refers to an xa_node; usually the primary one being operated on by * this function. * @offset is the index into the slots array inside an xa_node. * @parent refers to the @xa_node closer to the head than @node. * @entry refers to something stored in a slot in the xarray */ static inline unsigned int xa_lock_type(const struct xarray *xa) { return (__force unsigned int)xa->xa_flags & 3; } static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_lock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_lock_bh(xas); else xas_lock(xas); } static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_unlock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_unlock_bh(xas); else xas_unlock(xas); } static inline bool xa_track_free(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_TRACK_FREE; } static inline bool xa_zero_busy(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_ZERO_BUSY; } static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) xa->xa_flags |= XA_FLAGS_MARK(mark); } static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark) { if (xa->xa_flags & XA_FLAGS_MARK(mark)) xa->xa_flags &= ~(XA_FLAGS_MARK(mark)); } static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark) { return node->marks[(__force unsigned)mark]; } static inline bool node_get_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return test_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_set_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_set_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_clear_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_clear_bit(offset, node_marks(node, mark)); } static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) { return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); } static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) { bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE); } #define mark_inc(mark) do { \ mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \ } while (0) /* * xas_squash_marks() - Merge all marks to the first entry * @xas: Array operation state. * * Set a mark on the first entry if any entry has it set. Clear marks on * all sibling entries. */ static void xas_squash_marks(const struct xa_state *xas) { unsigned int mark = 0; unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; if (!xas->xa_sibs) return; do { unsigned long *marks = xas->xa_node->marks[mark]; if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit) continue; __set_bit(xas->xa_offset, marks); bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); } while (mark++ != (__force unsigned)XA_MARK_MAX); } /* extracts the offset within this node from the index */ static unsigned int get_offset(unsigned long index, struct xa_node *node) { return (index >> node->shift) & XA_CHUNK_MASK; } static void xas_set_offset(struct xa_state *xas) { xas->xa_offset = get_offset(xas->xa_index, xas->xa_node); } /* move the index either forwards (find) or backwards (sibling slot) */ static void xas_move_index(struct xa_state *xas, unsigned long offset) { unsigned int shift = xas->xa_node->shift; xas->xa_index &= ~XA_CHUNK_MASK << shift; xas->xa_index += offset << shift; } static void xas_next_offset(struct xa_state *xas) { xas->xa_offset++; xas_move_index(xas, xas->xa_offset); } static void *set_bounds(struct xa_state *xas) { xas->xa_node = XAS_BOUNDS; return NULL; } /* * Starts a walk. If the @xas is already valid, we assume that it's on * the right path and just return where we've got to. If we're in an * error state, return NULL. If the index is outside the current scope * of the xarray, return NULL without changing @xas->xa_node. Otherwise * set @xas->xa_node to NULL and return the current head of the array. */ static void *xas_start(struct xa_state *xas) { void *entry; if (xas_valid(xas)) return xas_reload(xas); if (xas_error(xas)) return NULL; entry = xa_head(xas->xa); if (!xa_is_node(entry)) { if (xas->xa_index) return set_bounds(xas); } else { if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK) return set_bounds(xas); } xas->xa_node = NULL; return entry; } static __always_inline void *xas_descend(struct xa_state *xas, struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); xas->xa_node = node; while (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) entry = XA_RETRY_ENTRY; } xas->xa_offset = offset; return entry; } /** * xas_load() - Load an entry from the XArray (advanced). * @xas: XArray operation state. * * Usually walks the @xas to the appropriate state to load the entry * stored at xa_index. However, it will do nothing and return %NULL if * @xas is in an error state. xas_load() will never expand the tree. * * If the xa_state is set up to operate on a multi-index entry, xas_load() * may return %NULL or an internal entry, even if there are entries * present within the range specified by @xas. * * Context: Any context. The caller should hold the xa_lock or the RCU lock. * Return: Usually an entry in the XArray, but see description for exceptions. */ void *xas_load(struct xa_state *xas) { void *entry = xas_start(xas); while (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); if (xas->xa_shift > node->shift) break; entry = xas_descend(xas, node); if (node->shift == 0) break; } return entry; } EXPORT_SYMBOL_GPL(xas_load); #define XA_RCU_FREE ((struct xarray *)1) static void xa_node_free(struct xa_node *node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->array = XA_RCU_FREE; call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * xas_destroy() - Free any resources allocated during the XArray operation. * @xas: XArray operation state. * * Most users will not need to call this function; it is called for you * by xas_nomem(). */ void xas_destroy(struct xa_state *xas) { struct xa_node *next, *node = xas->xa_alloc; while (node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); next = rcu_dereference_raw(node->parent); radix_tree_node_rcu_free(&node->rcu_head); xas->xa_alloc = node = next; } } /** * xas_nomem() - Allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * If we need to add new nodes to the XArray, we try to allocate memory * with GFP_NOWAIT while holding the lock, which will usually succeed. * If it fails, @xas is flagged as needing memory to continue. The caller * should drop the lock and call xas_nomem(). If xas_nomem() succeeds, * the caller should retry the operation. * * Forward progress is guaranteed as one node is allocated here and * stored in the xa_state where it will be found by xas_alloc(). More * nodes will likely be found in the slab allocator, but we do not tie * them up here. * * Return: true if memory was needed, and was successfully allocated. */ bool xas_nomem(struct xa_state *xas, gfp_t gfp) { if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } EXPORT_SYMBOL_GPL(xas_nomem); /* * __xas_nomem() - Drop locks and allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * Internal variant of xas_nomem(). * * Return: true if memory was needed, and was successfully allocated. */ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) __must_hold(xas->xa->xa_lock) { unsigned int lock_type = xa_lock_type(xas->xa); if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; if (gfpflags_allow_blocking(gfp)) { xas_unlock_type(xas, lock_type); xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); xas_lock_type(xas, lock_type); } else { xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); } if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } static void xas_update(struct xa_state *xas, struct xa_node *node) { if (xas->xa_update) xas->xa_update(node); else XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); } static void *xas_alloc(struct xa_state *xas, unsigned int shift) { struct xa_node *parent = xas->xa_node; struct xa_node *node = xas->xa_alloc; if (xas_invalid(xas)) return NULL; if (node) { xas->xa_alloc = NULL; } else { gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN; if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!node) { xas_set_err(xas, -ENOMEM); return NULL; } } if (parent) { node->offset = xas->xa_offset; parent->count++; XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE); xas_update(xas, parent); } XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->shift = shift; node->count = 0; node->nr_values = 0; RCU_INIT_POINTER(node->parent, xas->xa_node); node->array = xas->xa; return node; } #ifdef CONFIG_XARRAY_MULTI /* Returns the number of indices covered by a given xa_state */ static unsigned long xas_size(const struct xa_state *xas) { return (xas->xa_sibs + 1UL) << xas->xa_shift; } #endif /* * Use this to calculate the maximum index that will need to be created * in order to add the entry described by @xas. Because we cannot store a * multi-index entry at index 0, the calculation is a little more complex * than you might expect. */ static unsigned long xas_max(struct xa_state *xas) { unsigned long max = xas->xa_index; #ifdef CONFIG_XARRAY_MULTI if (xas->xa_shift || xas->xa_sibs) { unsigned long mask = xas_size(xas) - 1; max |= mask; if (mask == max) max++; } #endif return max; } /* The maximum index that can be contained in the array without expanding it */ static unsigned long max_index(void *entry) { if (!xa_is_node(entry)) return 0; return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; } static void xas_shrink(struct xa_state *xas) { struct xarray *xa = xas->xa; struct xa_node *node = xas->xa_node; for (;;) { void *entry; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count != 1) break; entry = xa_entry_locked(xa, node, 0); if (!entry) break; if (!xa_is_node(entry) && node->shift) break; if (xa_is_zero(entry) && xa_zero_busy(xa)) entry = NULL; xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK)) xa_mark_clear(xa, XA_FREE_MARK); node->count = 0; node->nr_values = 0; if (!xa_is_node(entry)) RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY); xas_update(xas, node); xa_node_free(node); if (!xa_is_node(entry)) break; node = xa_to_node(entry); node->parent = NULL; } } /* * xas_delete_node() - Attempt to delete an xa_node * @xas: Array operation state. * * Attempts to delete the @xas->xa_node. This will fail if xa->node has * a non-zero reference count. */ static void xas_delete_node(struct xa_state *xas) { struct xa_node *node = xas->xa_node; for (;;) { struct xa_node *parent; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count) break; parent = xa_parent_locked(xas->xa, node); xas->xa_node = parent; xas->xa_offset = node->offset; xa_node_free(node); if (!parent) { xas->xa->xa_head = NULL; xas->xa_node = XAS_BOUNDS; return; } parent->slots[xas->xa_offset] = NULL; parent->count--; XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE); node = parent; xas_update(xas, node); } if (!node->parent) xas_shrink(xas); } /** * xas_free_nodes() - Free this node and all nodes that it references * @xas: Array operation state. * @top: Node to free * * This node has been removed from the tree. We must now free it and all * of its subnodes. There may be RCU walkers with references into the tree, * so we must replace all entries with retry markers. */ static void xas_free_nodes(struct xa_state *xas, struct xa_node *top) { unsigned int offset = 0; struct xa_node *node = top; for (;;) { void *entry = xa_entry_locked(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) { node = xa_to_node(entry); offset = 0; continue; } if (entry) RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY); offset++; while (offset == XA_CHUNK_SIZE) { struct xa_node *parent; parent = xa_parent_locked(xas->xa, node); offset = node->offset + 1; node->count = 0; node->nr_values = 0; xas_update(xas, node); xa_node_free(node); if (node == top) return; node = parent; } } } /* * xas_expand adds nodes to the head of the tree until it has reached * sufficient height to be able to contain @xas->xa_index */ static int xas_expand(struct xa_state *xas, void *head) { struct xarray *xa = xas->xa; struct xa_node *node = NULL; unsigned int shift = 0; unsigned long max = xas_max(xas); if (!head) { if (max == 0) return 0; while ((max >> shift) >= XA_CHUNK_SIZE) shift += XA_CHUNK_SHIFT; return shift + XA_CHUNK_SHIFT; } else if (xa_is_node(head)) { node = xa_to_node(head); shift = node->shift + XA_CHUNK_SHIFT; } xas->xa_node = NULL; while (max > max_index(head)) { xa_mark_t mark = 0; XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); node = xas_alloc(xas, shift); if (!node) return -ENOMEM; node->count = 1; if (xa_is_value(head)) node->nr_values = 1; RCU_INIT_POINTER(node->slots[0], head); /* Propagate the aggregated mark info to the new child */ for (;;) { if (xa_track_free(xa) && mark == XA_FREE_MARK) { node_mark_all(node, XA_FREE_MARK); if (!xa_marked(xa, XA_FREE_MARK)) { node_clear_mark(node, 0, XA_FREE_MARK); xa_mark_set(xa, XA_FREE_MARK); } } else if (xa_marked(xa, mark)) { node_set_mark(node, 0, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } /* * Now that the new node is fully initialised, we can add * it to the tree */ if (xa_is_node(head)) { xa_to_node(head)->offset = 0; rcu_assign_pointer(xa_to_node(head)->parent, node); } head = xa_mk_node(node); rcu_assign_pointer(xa->xa_head, head); xas_update(xas, node); shift += XA_CHUNK_SHIFT; } xas->xa_node = node; return shift; } /* * xas_create() - Create a slot to store an entry in. * @xas: XArray operation state. * @allow_root: %true if we can store the entry in the root directly * * Most users will not need to call this function directly, as it is called * by xas_store(). It is useful for doing conditional store operations * (see the xa_cmpxchg() implementation for an example). * * Return: If the slot already existed, returns the contents of this slot. * If the slot was newly created, returns %NULL. If it failed to create the * slot, returns %NULL and indicates the error in @xas. */ static void *xas_create(struct xa_state *xas, bool allow_root) { struct xarray *xa = xas->xa; void *entry; void __rcu **slot; struct xa_node *node = xas->xa_node; int shift; unsigned int order = xas->xa_shift; if (xas_top(node)) { entry = xa_head_locked(xa); xas->xa_node = NULL; if (!entry && xa_zero_busy(xa)) entry = XA_ZERO_ENTRY; shift = xas_expand(xas, entry); if (shift < 0) return NULL; if (!shift && !allow_root) shift = XA_CHUNK_SHIFT; entry = xa_head_locked(xa); slot = &xa->xa_head; } else if (xas_error(xas)) { return NULL; } else if (node) { unsigned int offset = xas->xa_offset; shift = node->shift; entry = xa_entry_locked(xa, node, offset); slot = &node->slots[offset]; } else { shift = 0; entry = xa_head_locked(xa); slot = &xa->xa_head; } while (shift > order) { shift -= XA_CHUNK_SHIFT; if (!entry) { node = xas_alloc(xas, shift); if (!node) break; if (xa_track_free(xa)) node_mark_all(node, XA_FREE_MARK); rcu_assign_pointer(*slot, xa_mk_node(node)); } else if (xa_is_node(entry)) { node = xa_to_node(entry); } else { break; } entry = xas_descend(xas, node); slot = &node->slots[xas->xa_offset]; } return entry; } /** * xas_create_range() - Ensure that stores to this range will succeed * @xas: XArray operation state. * * Creates all of the slots in the range covered by @xas. Sets @xas to * create single-index entries and positions it at the beginning of the * range. This is for the benefit of users which have not yet been * converted to use multi-index entries. */ void xas_create_range(struct xa_state *xas) { unsigned long index = xas->xa_index; unsigned char shift = xas->xa_shift; unsigned char sibs = xas->xa_sibs; xas->xa_index |= ((sibs + 1UL) << shift) - 1; if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift) xas->xa_offset |= sibs; xas->xa_shift = 0; xas->xa_sibs = 0; for (;;) { xas_create(xas, true); if (xas_error(xas)) goto restore; if (xas->xa_index <= (index | XA_CHUNK_MASK)) goto success; xas->xa_index -= XA_CHUNK_SIZE; for (;;) { struct xa_node *node = xas->xa_node; if (node->shift >= shift) break; xas->xa_node = xa_parent_locked(xas->xa, node); xas->xa_offset = node->offset - 1; if (node->offset != 0) break; } } restore: xas->xa_shift = shift; xas->xa_sibs = sibs; xas->xa_index = index; return; success: xas->xa_index = index; if (xas->xa_node) xas_set_offset(xas); } EXPORT_SYMBOL_GPL(xas_create_range); static void update_node(struct xa_state *xas, struct xa_node *node, int count, int values) { if (!node || (!count && !values)) return; node->count += count; node->nr_values += values; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE); xas_update(xas, node); if (count < 0) xas_delete_node(xas); } /** * xas_store() - Store this entry in the XArray. * @xas: XArray operation state. * @entry: New entry. * * If @xas is operating on a multi-index entry, the entry returned by this * function is essentially meaningless (it may be an internal entry or it * may be %NULL, even if there are non-NULL entries at some of the indices * covered by the range). This is not a problem for any current users, * and can be changed if needed. * * Return: The old entry at this index. */ void *xas_store(struct xa_state *xas, void *entry) { struct xa_node *node; void __rcu **slot = &xas->xa->xa_head; unsigned int offset, max; int count = 0; int values = 0; void *first, *next; bool value = xa_is_value(entry); if (entry) { bool allow_root = !xa_is_node(entry) && !xa_is_zero(entry); first = xas_create(xas, allow_root); } else { first = xas_load(xas); } if (xas_invalid(xas)) return first; node = xas->xa_node; if (node && (xas->xa_shift < node->shift)) xas->xa_sibs = 0; if ((first == entry) && !xas->xa_sibs) return first; next = first; offset = xas->xa_offset; max = xas->xa_offset + xas->xa_sibs; if (node) { slot = &node->slots[offset]; if (xas->xa_sibs) xas_squash_marks(xas); } if (!entry) xas_init_marks(xas); for (;;) { /* * Must clear the marks before setting the entry to NULL, * otherwise xas_for_each_marked may find a NULL entry and * stop early. rcu_assign_pointer contains a release barrier * so the mark clearing will appear to happen before the * entry is set to NULL. */ rcu_assign_pointer(*slot, entry); if (xa_is_node(next) && (!node || node->shift)) xas_free_nodes(xas, xa_to_node(next)); if (!node) break; count += !next - !entry; values += !xa_is_value(first) - !value; if (entry) { if (offset == max) break; if (!xa_is_sibling(entry)) entry = xa_mk_sibling(xas->xa_offset); } else { if (offset == XA_CHUNK_MASK) break; } next = xa_entry_locked(xas->xa, node, ++offset); if (!xa_is_sibling(next)) { if (!entry && (offset > max)) break; first = next; } slot++; } update_node(xas, node, count, values); return first; } EXPORT_SYMBOL_GPL(xas_store); /** * xas_get_mark() - Returns the state of this mark. * @xas: XArray operation state. * @mark: Mark number. * * Return: true if the mark is set, false if the mark is clear or @xas * is in an error state. */ bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark) { if (xas_invalid(xas)) return false; if (!xas->xa_node) return xa_marked(xas->xa, mark); return node_get_mark(xas->xa_node, xas->xa_offset, mark); } EXPORT_SYMBOL_GPL(xas_get_mark); /** * xas_set_mark() - Sets the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Sets the specified mark on this entry, and walks up the tree setting it * on all the ancestor entries. Does nothing if @xas has not been walked to * an entry, or is in an error state. */ void xas_set_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (node_set_mark(node, offset, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (!xa_marked(xas->xa, mark)) xa_mark_set(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_set_mark); /** * xas_clear_mark() - Clears the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Clears the specified mark on this entry, and walks back to the head * attempting to clear it on all the ancestor entries. Does nothing if * @xas has not been walked to an entry, or is in an error state. */ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (!node_clear_mark(node, offset, mark)) return; if (node_any_mark(node, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (xa_marked(xas->xa, mark)) xa_mark_clear(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_clear_mark); /** * xas_init_marks() - Initialise all marks for the entry * @xas: Array operations state. * * Initialise all marks for the entry specified by @xas. If we're tracking * free entries with a mark, we need to set it on all entries. All other * marks are cleared. * * This implementation is not as efficient as it could be; we may walk * up the tree multiple times. */ void xas_init_marks(const struct xa_state *xas) { xa_mark_t mark = 0; for (;;) { if (xa_track_free(xas->xa) && mark == XA_FREE_MARK) xas_set_mark(xas, mark); else xas_clear_mark(xas, mark); if (mark == XA_MARK_MAX) break; mark_inc(mark); } } EXPORT_SYMBOL_GPL(xas_init_marks); #ifdef CONFIG_XARRAY_MULTI static unsigned int node_get_marks(struct xa_node *node, unsigned int offset) { unsigned int marks = 0; xa_mark_t mark = XA_MARK_0; for (;;) { if (node_get_mark(node, offset, mark)) marks |= 1 << (__force unsigned int)mark; if (mark == XA_MARK_MAX) break; mark_inc(mark); } return marks; } static inline void node_mark_slots(struct xa_node *node, unsigned int sibs, xa_mark_t mark) { int i; if (sibs == 0) node_mark_all(node, mark); else { for (i = 0; i < XA_CHUNK_SIZE; i += sibs + 1) node_set_mark(node, i, mark); } } static void node_set_marks(struct xa_node *node, unsigned int offset, struct xa_node *child, unsigned int sibs, unsigned int marks) { xa_mark_t mark = XA_MARK_0; for (;;) { if (marks & (1 << (__force unsigned int)mark)) { node_set_mark(node, offset, mark); if (child) node_mark_slots(child, sibs, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } } /** * xas_split_alloc() - Allocate memory for splitting an entry. * @xas: XArray operation state. * @entry: New entry which will be stored in the array. * @order: Current entry order. * @gfp: Memory allocation flags. * * This function should be called before calling xas_split(). * If necessary, it will allocate new nodes (and fill them with @entry) * to prepare for the upcoming split of an entry of @order size into * entries of the order stored in the @xas. * * Context: May sleep if @gfp flags permit. */ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int mask = xas->xa_sibs; /* XXX: no support for splitting really large entries yet */ if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order)) goto nomem; if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; do { unsigned int i; void *sibling = NULL; struct xa_node *node; node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!node) goto nomem; node->array = xas->xa; for (i = 0; i < XA_CHUNK_SIZE; i++) { if ((i & mask) == 0) { RCU_INIT_POINTER(node->slots[i], entry); sibling = xa_mk_sibling(i); } else { RCU_INIT_POINTER(node->slots[i], sibling); } } RCU_INIT_POINTER(node->parent, xas->xa_alloc); xas->xa_alloc = node; } while (sibs-- > 0); return; nomem: xas_destroy(xas); xas_set_err(xas, -ENOMEM); } EXPORT_SYMBOL_GPL(xas_split_alloc); /** * xas_split() - Split a multi-index entry into smaller entries. * @xas: XArray operation state. * @entry: New entry to store in the array. * @order: Current entry order. * * The size of the new entries is set in @xas. The value in @entry is * copied to all the replacement entries. * * Context: Any context. The caller should hold the xa_lock. */ void xas_split(struct xa_state *xas, void *entry, unsigned int order) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int offset, marks; struct xa_node *node; void *curr = xas_load(xas); int values = 0; node = xas->xa_node; if (xas_top(node)) return; marks = node_get_marks(node, xas->xa_offset); offset = xas->xa_offset + sibs; do { if (xas->xa_shift < node->shift) { struct xa_node *child = xas->xa_alloc; xas->xa_alloc = rcu_dereference_raw(child->parent); child->shift = node->shift - XA_CHUNK_SHIFT; child->offset = offset; child->count = XA_CHUNK_SIZE; child->nr_values = xa_is_value(entry) ? XA_CHUNK_SIZE : 0; RCU_INIT_POINTER(child->parent, node); node_set_marks(node, offset, child, xas->xa_sibs, marks); rcu_assign_pointer(node->slots[offset], xa_mk_node(child)); if (xa_is_value(curr)) values--; xas_update(xas, child); } else { unsigned int canon = offset - xas->xa_sibs; node_set_marks(node, canon, NULL, 0, marks); rcu_assign_pointer(node->slots[canon], entry); while (offset > canon) rcu_assign_pointer(node->slots[offset--], xa_mk_sibling(canon)); values += (xa_is_value(entry) - xa_is_value(curr)) * (xas->xa_sibs + 1); } } while (offset-- > xas->xa_offset); node->nr_values += values; xas_update(xas, node); } EXPORT_SYMBOL_GPL(xas_split); #endif /** * xas_pause() - Pause a walk to drop a lock. * @xas: XArray operation state. * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @xas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call xas_pause(), the xa_for_each() * iterator may be more appropriate. * * Note that xas_pause() only works for forward iteration. If a user needs * to pause a reverse iteration, we will need a xas_pause_rev(). */ void xas_pause(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (xas_invalid(xas)) return; xas->xa_node = XAS_RESTART; if (node) { unsigned long offset = xas->xa_offset; while (++offset < XA_CHUNK_SIZE) { if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) break; } xas->xa_index += (offset - xas->xa_offset) << node->shift; if (xas->xa_index == 0) xas->xa_node = XAS_BOUNDS; } else { xas->xa_index++; } } EXPORT_SYMBOL_GPL(xas_pause); /* * __xas_prev() - Find the previous entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_prev() which handles all the complex cases * out of line. */ void *__xas_prev(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index--; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset--; while (xas->xa_offset == 255) { xas->xa_offset = xas->xa_node->offset - 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_prev); /* * __xas_next() - Find the next entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_next() which handles all the complex cases * out of line. */ void *__xas_next(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index++; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset++; while (xas->xa_offset == XA_CHUNK_SIZE) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_next); /** * xas_find() - Find the next present entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * * If the @xas has not yet been walked to an entry, return the entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we move to the * next entry. * * If no entry is found and the array is smaller than @max, the iterator * is set to the smallest index not yet in the array. This allows @xas * to be immediately passed to xas_store(). * * Return: The entry, if found, otherwise %NULL. */ void *xas_find(struct xa_state *xas, unsigned long max) { void *entry; if (xas_error(xas) || xas->xa_node == XAS_BOUNDS) return NULL; if (xas->xa_index > max) return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; return set_bounds(xas); } else if (xas->xa_node == XAS_RESTART) { entry = xas_load(xas); if (entry || xas_not_node(xas->xa_node)) return entry; } else if (!xas->xa_node->shift && xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) { xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; } xas_next_offset(xas); while (xas->xa_node && (xas->xa_index <= max)) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_node(entry)) { xas->xa_node = xa_to_node(entry); xas->xa_offset = 0; continue; } if (entry && !xa_is_sibling(entry)) return entry; xas_next_offset(xas); } if (!xas->xa_node) xas->xa_node = XAS_BOUNDS; return NULL; } EXPORT_SYMBOL_GPL(xas_find); /** * xas_find_marked() - Find the next marked entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark number to search for. * * If the @xas has not yet been walked to an entry, return the marked entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we return the * first marked entry with an index > xas.xa_index. * * If no marked entry is found and the array is smaller than @max, @xas is * set to the bounds state and xas->xa_index is set to the smallest index * not yet in the array. This allows @xas to be immediately passed to * xas_store(). * * If no entry is found before @max is reached, @xas is set to the restart * state. * * Return: The entry, if found, otherwise %NULL. */ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { bool advance = true; unsigned int offset; void *entry; if (xas_error(xas)) return NULL; if (xas->xa_index > max) goto max; if (!xas->xa_node) { xas->xa_index = 1; goto out; } else if (xas_top(xas->xa_node)) { advance = false; entry = xa_head(xas->xa); xas->xa_node = NULL; if (xas->xa_index > max_index(entry)) goto out; if (!xa_is_node(entry)) { if (xa_marked(xas->xa, mark)) return entry; xas->xa_index = 1; goto out; } xas->xa_node = xa_to_node(entry); xas->xa_offset = xas->xa_index >> xas->xa_node->shift; } while (xas->xa_index <= max) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) break; advance = false; continue; } if (!advance) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_sibling(entry)) { xas->xa_offset = xa_to_sibling(entry); xas_move_index(xas, xas->xa_offset); } } offset = xas_find_chunk(xas, advance, mark); if (offset > xas->xa_offset) { advance = false; xas_move_index(xas, offset); /* Mind the wrap */ if ((xas->xa_index - 1) >= max) goto max; xas->xa_offset = offset; if (offset == XA_CHUNK_SIZE) continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK)) continue; if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } out: if (xas->xa_index > max) goto max; return set_bounds(xas); max: xas->xa_node = XAS_RESTART; return NULL; } EXPORT_SYMBOL_GPL(xas_find_marked); /** * xas_find_conflict() - Find the next present entry in a range. * @xas: XArray operation state. * * The @xas describes both a range and a position within that range. * * Context: Any context. Expects xa_lock to be held. * Return: The next entry in the range covered by @xas or %NULL. */ void *xas_find_conflict(struct xa_state *xas) { void *curr; if (xas_error(xas)) return NULL; if (!xas->xa_node) return NULL; if (xas_top(xas->xa_node)) { curr = xas_start(xas); if (!curr) return NULL; while (xa_is_node(curr)) { struct xa_node *node = xa_to_node(curr); curr = xas_descend(xas, node); } if (curr) return curr; } if (xas->xa_node->shift > xas->xa_shift) return NULL; for (;;) { if (xas->xa_node->shift == xas->xa_shift) { if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs) break; } else if (xas->xa_offset == XA_CHUNK_MASK) { xas->xa_offset = xas->xa_node->offset; xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node); if (!xas->xa_node) break; continue; } curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset); if (xa_is_sibling(curr)) continue; while (xa_is_node(curr)) { xas->xa_node = xa_to_node(curr); xas->xa_offset = 0; curr = xa_entry_locked(xas->xa, xas->xa_node, 0); } if (curr) return curr; } xas->xa_offset -= xas->xa_sibs; return NULL; } EXPORT_SYMBOL_GPL(xas_find_conflict); /** * xa_load() - Load an entry from an XArray. * @xa: XArray. * @index: index into array. * * Context: Any context. Takes and releases the RCU lock. * Return: The entry at @index in @xa. */ void *xa_load(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); do { entry = xas_load(&xas); if (xa_is_zero(entry)) entry = NULL; } while (xas_retry(&xas, entry)); rcu_read_unlock(); return entry; } EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { if (xa_is_zero(curr)) return NULL; if (xas_error(xas)) curr = xas->xa_node; return curr; } /** * __xa_erase() - Erase this entry from the XArray while locked. * @xa: XArray. * @index: Index into array. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Expects xa_lock to be held on entry. * Return: The entry which used to be at this index. */ void *__xa_erase(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); return xas_result(&xas, xas_store(&xas, NULL)); } EXPORT_SYMBOL(__xa_erase); /** * xa_erase() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock. * Return: The entry which used to be at this index. */ void *xa_erase(struct xarray *xa, unsigned long index) { void *entry; xa_lock(xa); entry = __xa_erase(xa, index); xa_unlock(xa); return entry; } EXPORT_SYMBOL(xa_erase); /** * __xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); if (xa_track_free(xa) && !entry) entry = XA_ZERO_ENTRY; do { curr = xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_store); /** * xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from this index will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation * failed. */ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; xa_lock(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock(xa); return curr; } EXPORT_SYMBOL(xa_store); /** * __xa_cmpxchg() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); do { curr = xas_load(&xas); if (curr == old) { xas_store(&xas, entry); if (xa_track_free(xa) && entry && !curr) xas_clear_mark(&xas, XA_FREE_MARK); } } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_cmpxchg); /** * __xa_insert() - Store this entry in the XArray if no entry is present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { curr = xas_load(&xas); if (!curr) { xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } else { xas_set_err(&xas, -EBUSY); } } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_insert); #ifdef CONFIG_XARRAY_MULTI static void xas_set_range(struct xa_state *xas, unsigned long first, unsigned long last) { unsigned int shift = 0; unsigned long sibs = last - first; unsigned int offset = XA_CHUNK_MASK; xas_set(xas, first); while ((first & XA_CHUNK_MASK) == 0) { if (sibs < XA_CHUNK_MASK) break; if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK)) break; shift += XA_CHUNK_SHIFT; if (offset == XA_CHUNK_MASK) offset = sibs & XA_CHUNK_MASK; sibs >>= XA_CHUNK_SHIFT; first >>= XA_CHUNK_SHIFT; } offset = first & XA_CHUNK_MASK; if (offset + sibs > XA_CHUNK_MASK) sibs = XA_CHUNK_MASK - offset; if ((((first + sibs + 1) << shift) - 1) > last) sibs -= 1; xas->xa_shift = shift; xas->xa_sibs = sibs; } /** * xa_store_range() - Store this entry at a range of indices in the XArray. * @xa: XArray. * @first: First index to affect. * @last: Last index to affect. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from any index between @first and @last, * inclusive will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Process context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in * an XArray, or xa_err(-ENOMEM) if memory allocation failed. */ void *xa_store_range(struct xarray *xa, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_internal(entry))) return XA_ERROR(-EINVAL); if (last < first) return XA_ERROR(-EINVAL); do { xas_lock(&xas); if (entry) { unsigned int order = BITS_PER_LONG; if (last + 1) order = __ffs(last + 1); xas_set_order(&xas, last, order); xas_create(&xas, true); if (xas_error(&xas)) goto unlock; } do { xas_set_range(&xas, first, last); xas_store(&xas, entry); if (xas_error(&xas)) goto unlock; first += xas_size(&xas); } while (first <= last); unlock: xas_unlock(&xas); } while (xas_nomem(&xas, gfp)); return xas_result(&xas, NULL); } EXPORT_SYMBOL(xa_store_range); /** * xas_get_order() - Get the order of an entry. * @xas: XArray operation state. * * Called after xas_load, the xas should not be in an error state. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xas_get_order(struct xa_state *xas) { int order = 0; if (!xas->xa_node) return 0; for (;;) { unsigned int slot = xas->xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot))) break; order++; } order += xas->xa_node->shift; return order; } EXPORT_SYMBOL_GPL(xas_get_order); /** * xa_get_order() - Get the order of an entry. * @xa: XArray. * @index: Index of the entry. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xa_get_order(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); int order = 0; void *entry; rcu_read_lock(); entry = xas_load(&xas); if (entry) order = xas_get_order(&xas); rcu_read_unlock(); return order; } EXPORT_SYMBOL(xa_get_order); #endif /* CONFIG_XARRAY_MULTI */ /** * __xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @limit: Range for allocated ID. * @entry: New entry. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ int __xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (WARN_ON_ONCE(!xa_track_free(xa))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { xas.xa_index = limit.min; xas_find_marked(&xas, limit.max, XA_FREE_MARK); if (xas.xa_node == XAS_RESTART) xas_set_err(&xas, -EBUSY); else *id = xas.xa_index; xas_store(&xas, entry); xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_alloc); /** * __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { u32 min = limit.min; int ret; limit.min = max(min, *next); ret = __xa_alloc(xa, id, entry, limit, gfp); if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) { xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && limit.min > min) { limit.min = min; ret = __xa_alloc(xa, id, entry, limit, gfp); if (ret == 0) ret = 1; } if (ret >= 0) { *next = *id + 1; if (*next == 0) xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED; } return ret; } EXPORT_SYMBOL(__xa_alloc_cyclic); /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_set_mark(&xas, mark); } EXPORT_SYMBOL(__xa_set_mark); /** * __xa_clear_mark() - Clear this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_clear_mark(&xas, mark); } EXPORT_SYMBOL(__xa_clear_mark); /** * xa_get_mark() - Inquire whether this mark is set on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * This function uses the RCU read lock, so the result may be out of date * by the time it returns. If you need the result to be stable, use a lock. * * Context: Any context. Takes and releases the RCU lock. * Return: True if the entry at @index has this mark set, false if it doesn't. */ bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); entry = xas_start(&xas); while (xas_get_mark(&xas, mark)) { if (!xa_is_node(entry)) goto found; entry = xas_descend(&xas, xa_to_node(entry)); } rcu_read_unlock(); return false; found: rcu_read_unlock(); return true; } EXPORT_SYMBOL(xa_get_mark); /** * xa_set_mark() - Set this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Process context. Takes and releases the xa_lock. */ void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_set_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_set_mark); /** * xa_clear_mark() - Clear this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Clearing a mark always succeeds. * * Context: Process context. Takes and releases the xa_lock. */ void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_clear_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_clear_mark); /** * xa_find() - Search the XArray for an entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter, and has the lowest * index that is at least @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may not find * entries which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The entry, if found, otherwise %NULL. */ void *xa_find(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find); static bool xas_sibling(struct xa_state *xas) { struct xa_node *node = xas->xa_node; unsigned long mask; if (!IS_ENABLED(CONFIG_XARRAY_MULTI) || !node) return false; mask = (XA_CHUNK_SIZE << node->shift) - 1; return (xas->xa_index & mask) > ((unsigned long)xas->xa_offset << node->shift); } /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter and has the lowest * index that is above @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may miss entries * which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The pointer, if found, otherwise %NULL. */ void *xa_find_after(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp + 1); void *entry; if (xas.xa_index == 0) return NULL; rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); if (xas_invalid(&xas)) break; if (xas_sibling(&xas)) continue; if (!xas_retry(&xas, entry)) break; } rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find_after); static unsigned int xas_extract_present(struct xa_state *xas, void **dst, unsigned long max, unsigned int n) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each(xas, entry, max) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } static unsigned int xas_extract_marked(struct xa_state *xas, void **dst, unsigned long max, unsigned int n, xa_mark_t mark) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each_marked(xas, entry, max, mark) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } /** * xa_extract() - Copy selected entries from the XArray into a normal array. * @xa: The source XArray to copy from. * @dst: The buffer to copy entries into. * @start: The first index in the XArray eligible to be selected. * @max: The last index in the XArray eligible to be selected. * @n: The maximum number of entries to copy. * @filter: Selection criterion. * * Copies up to @n entries that match @filter from the XArray. The * copied entries will have indices between @start and @max, inclusive. * * The @filter may be an XArray mark value, in which case entries which are * marked with that mark will be copied. It may also be %XA_PRESENT, in * which case all entries which are not %NULL will be copied. * * The entries returned may not represent a snapshot of the XArray at a * moment in time. For example, if another thread stores to index 5, then * index 10, calling xa_extract() may return the old contents of index 5 * and the new contents of index 10. Indices not modified while this * function is running will not be skipped. * * If you need stronger guarantees, holding the xa_lock across calls to this * function will prevent concurrent modification. * * Context: Any context. Takes and releases the RCU lock. * Return: The number of entries copied. */ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t filter) { XA_STATE(xas, xa, start); if (!n) return 0; if ((__force unsigned int)filter < XA_MAX_MARKS) return xas_extract_marked(&xas, dst, max, n, filter); return xas_extract_present(&xas, dst, max, n); } EXPORT_SYMBOL(xa_extract); /** * xa_delete_node() - Private interface for workingset code. * @node: Node to be removed from the tree. * @update: Function to call to update ancestor nodes. * * Context: xa_lock must be held on entry and will not be released. */ void xa_delete_node(struct xa_node *node, xa_update_node_t update) { struct xa_state xas = { .xa = node->array, .xa_index = (unsigned long)node->offset << (node->shift + XA_CHUNK_SHIFT), .xa_shift = node->shift + XA_CHUNK_SHIFT, .xa_offset = node->offset, .xa_node = xa_parent_locked(node->array, node), .xa_update = update, }; xas_store(&xas, NULL); } EXPORT_SYMBOL_GPL(xa_delete_node); /* For the benefit of the test suite */ /** * xa_destroy() - Free all internal data structures. * @xa: XArray. * * After calling this function, the XArray is empty and has freed all memory * allocated for its internal data structures. You are responsible for * freeing the objects referenced by the XArray. * * Context: Any context. Takes and releases the xa_lock, interrupt-safe. */ void xa_destroy(struct xarray *xa) { XA_STATE(xas, xa, 0); unsigned long flags; void *entry; xas.xa_node = NULL; xas_lock_irqsave(&xas, flags); entry = xa_head_locked(xa); RCU_INIT_POINTER(xa->xa_head, NULL); xas_init_marks(&xas); if (xa_zero_busy(xa)) xa_mark_clear(xa, XA_FREE_MARK); /* lockdep checks we're still holding the lock in xas_free_nodes() */ if (xa_is_node(entry)) xas_free_nodes(&xas, xa_to_node(entry)); xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(xa_destroy); #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { unsigned i, j; if (!node) return; if ((unsigned long)node & 3) { pr_cont("node %px\n", node); return; } pr_cont("node %px %s %d parent %px shift %d count %d values %d " "array %px list %px %px marks", node, node->parent ? "offset" : "max", node->offset, node->parent, node->shift, node->count, node->nr_values, node->array, node->private_list.prev, node->private_list.next); for (i = 0; i < XA_MAX_MARKS; i++) for (j = 0; j < XA_MARK_LONGS; j++) pr_cont(" %lx", node->marks[i][j]); pr_cont("\n"); } void xa_dump_index(unsigned long index, unsigned int shift) { if (!shift) pr_info("%lu: ", index); else if (shift >= BITS_PER_LONG) pr_info("0-%lu: ", ~0UL); else pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1)); } void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift) { if (!entry) return; xa_dump_index(index, shift); if (xa_is_node(entry)) { if (shift == 0) { pr_cont("%px\n", entry); } else { unsigned long i; struct xa_node *node = xa_to_node(entry); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) xa_dump_entry(node->slots[i], index + (i << node->shift), node->shift); } } else if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (!xa_is_internal(entry)) pr_cont("%px\n", entry); else if (xa_is_retry(entry)) pr_cont("retry (%ld)\n", xa_to_internal(entry)); else if (xa_is_sibling(entry)) pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry)); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else pr_cont("UNKNOWN ENTRY (%px)\n", entry); } void xa_dump(const struct xarray *xa) { void *entry = xa->xa_head; unsigned int shift = 0; pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry, xa->xa_flags, xa_marked(xa, XA_MARK_0), xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2)); if (xa_is_node(entry)) shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT; xa_dump_entry(entry, 0, shift); } #endif |
| 5 5 3 2 5 5 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Transparent proxy support for Linux/iptables * * Copyright (c) 2006-2010 BalaBit IT Ltd. * Author: Balazs Scheidler, Krisztian Kovacs */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <net/checksum.h> #include <net/udp.h> #include <net/tcp.h> #include <net/inet_sock.h> #include <net/inet_hashtables.h> #include <linux/inetdevice.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) #define XT_TPROXY_HAVE_IPV6 1 #include <net/if_inet6.h> #include <net/addrconf.h> #include <net/inet6_hashtables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/netfilter/nf_tproxy.h> #include <linux/netfilter/xt_TPROXY.h> static unsigned int tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, u_int32_t mark_mask, u_int32_t mark_value) { const struct iphdr *iph = ip_hdr(skb); struct udphdr _hdr, *hp; struct sock *sk; hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (hp == NULL) return NF_DROP; /* check if there's an ongoing connection on the packet * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, iph->daddr, hp->source, hp->dest, skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED); laddr = nf_tproxy_laddr4(skb, laddr, iph->daddr); if (!lport) lport = hp->dest; /* UDP has no TCP_TIME_WAIT state, so we never enter here */ if (sk && sk->sk_state == TCP_TIME_WAIT) /* reopening a TIME_WAIT connection needs special handling */ sk = nf_tproxy_handle_time_wait4(net, skb, laddr, lport, sk); else if (!sk) /* no, there's no established connection, check if * there's a listener on the redirected addr/port */ sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, laddr, hp->source, lport, skb->dev, NF_TPROXY_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ if (sk && nf_tproxy_sk_is_transparent(sk)) { /* This should be in a separate target, but we don't do multiple targets on the same rule yet */ skb->mark = (skb->mark & ~mark_mask) ^ mark_value; nf_tproxy_assign_sock(skb, sk); return NF_ACCEPT; } return NF_DROP; } static unsigned int tproxy_tg4_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tproxy_target_info *tgi = par->targinfo; return tproxy_tg4(xt_net(par), skb, tgi->laddr, tgi->lport, tgi->mark_mask, tgi->mark_value); } static unsigned int tproxy_tg4_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; return tproxy_tg4(xt_net(par), skb, tgi->laddr.ip, tgi->lport, tgi->mark_mask, tgi->mark_value); } #ifdef XT_TPROXY_HAVE_IPV6 static unsigned int tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; struct udphdr _hdr, *hp; struct sock *sk; const struct in6_addr *laddr; __be16 lport; int thoff = 0; int tproto; tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); if (tproto < 0) return NF_DROP; hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); if (!hp) return NF_DROP; /* check if there's an ongoing connection on the packet * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto, &iph->saddr, &iph->daddr, hp->source, hp->dest, xt_in(par), NF_TPROXY_LOOKUP_ESTABLISHED); laddr = nf_tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr); lport = tgi->lport ? tgi->lport : hp->dest; /* UDP has no TCP_TIME_WAIT state, so we never enter here */ if (sk && sk->sk_state == TCP_TIME_WAIT) { const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; /* reopening a TIME_WAIT connection needs special handling */ sk = nf_tproxy_handle_time_wait6(skb, tproto, thoff, xt_net(par), &tgi->laddr.in6, tgi->lport, sk); } else if (!sk) /* no there's no established connection, check if * there's a listener on the redirected addr/port */ sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto, &iph->saddr, laddr, hp->source, lport, xt_in(par), NF_TPROXY_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ if (sk && nf_tproxy_sk_is_transparent(sk)) { /* This should be in a separate target, but we don't do multiple targets on the same rule yet */ skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value; nf_tproxy_assign_sock(skb, sk); return NF_ACCEPT; } return NF_DROP; } static int tproxy_tg6_check(const struct xt_tgchk_param *par) { const struct ip6t_ip6 *i = par->entryinfo; int err; err = nf_defrag_ipv6_enable(par->net); if (err) return err; if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) && !(i->invflags & IP6T_INV_PROTO)) return 0; pr_info_ratelimited("Can be used only with -p tcp or -p udp\n"); return -EINVAL; } static void tproxy_tg6_destroy(const struct xt_tgdtor_param *par) { nf_defrag_ipv6_disable(par->net); } #endif static int tproxy_tg4_check(const struct xt_tgchk_param *par) { const struct ipt_ip *i = par->entryinfo; int err; err = nf_defrag_ipv4_enable(par->net); if (err) return err; if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) && !(i->invflags & IPT_INV_PROTO)) return 0; pr_info_ratelimited("Can be used only with -p tcp or -p udp\n"); return -EINVAL; } static void tproxy_tg4_destroy(const struct xt_tgdtor_param *par) { nf_defrag_ipv4_disable(par->net); } static struct xt_target tproxy_tg_reg[] __read_mostly = { { .name = "TPROXY", .family = NFPROTO_IPV4, .table = "mangle", .target = tproxy_tg4_v0, .revision = 0, .targetsize = sizeof(struct xt_tproxy_target_info), .checkentry = tproxy_tg4_check, .destroy = tproxy_tg4_destroy, .hooks = 1 << NF_INET_PRE_ROUTING, .me = THIS_MODULE, }, { .name = "TPROXY", .family = NFPROTO_IPV4, .table = "mangle", .target = tproxy_tg4_v1, .revision = 1, .targetsize = sizeof(struct xt_tproxy_target_info_v1), .checkentry = tproxy_tg4_check, .destroy = tproxy_tg4_destroy, .hooks = 1 << NF_INET_PRE_ROUTING, .me = THIS_MODULE, }, #ifdef XT_TPROXY_HAVE_IPV6 { .name = "TPROXY", .family = NFPROTO_IPV6, .table = "mangle", .target = tproxy_tg6_v1, .revision = 1, .targetsize = sizeof(struct xt_tproxy_target_info_v1), .checkentry = tproxy_tg6_check, .destroy = tproxy_tg6_destroy, .hooks = 1 << NF_INET_PRE_ROUTING, .me = THIS_MODULE, }, #endif }; static int __init tproxy_tg_init(void) { return xt_register_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg)); } static void __exit tproxy_tg_exit(void) { xt_unregister_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg)); } module_init(tproxy_tg_init); module_exit(tproxy_tg_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs"); MODULE_DESCRIPTION("Netfilter transparent proxy (TPROXY) target module."); MODULE_ALIAS("ipt_TPROXY"); MODULE_ALIAS("ip6t_TPROXY"); |
| 82 112 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 | /* SPDX-License-Identifier: GPL-2.0 */ /* * INETPEER - A storage for permanent information about peers * * Authors: Andrey V. Savochkin <saw@msu.ru> */ #ifndef _NET_INETPEER_H #define _NET_INETPEER_H #include <linux/types.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/spinlock.h> #include <linux/rtnetlink.h> #include <net/ipv6.h> #include <linux/atomic.h> /* IPv4 address key for cache lookups */ struct ipv4_addr_key { __be32 addr; int vif; }; #define INETPEER_MAXKEYSZ (sizeof(struct in6_addr) / sizeof(u32)) struct inetpeer_addr { union { struct ipv4_addr_key a4; struct in6_addr a6; u32 key[INETPEER_MAXKEYSZ]; }; __u16 family; }; struct inet_peer { struct rb_node rb_node; struct inetpeer_addr daddr; u32 metrics[RTAX_MAX]; u32 rate_tokens; /* rate limiting for ICMP */ u32 n_redirects; unsigned long rate_last; /* * Once inet_peer is queued for deletion (refcnt == 0), following field * is not available: rid * We can share memory with rcu_head to help keep inet_peer small. */ union { struct { atomic_t rid; /* Frag reception counter */ }; struct rcu_head rcu; }; /* following fields might be frequently dirtied */ __u32 dtime; /* the time of last use of not referenced entries */ refcount_t refcnt; }; struct inet_peer_base { struct rb_root rb_root; seqlock_t lock; int total; }; void inet_peer_base_init(struct inet_peer_base *); void inet_initpeers(void) __init; #define INETPEER_METRICS_NEW (~(u32) 0) static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip) { iaddr->a4.addr = ip; iaddr->a4.vif = 0; iaddr->family = AF_INET; } static inline __be32 inetpeer_get_addr_v4(struct inetpeer_addr *iaddr) { return iaddr->a4.addr; } static inline void inetpeer_set_addr_v6(struct inetpeer_addr *iaddr, struct in6_addr *in6) { iaddr->a6 = *in6; iaddr->family = AF_INET6; } static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr) { return &iaddr->a6; } /* can be called with or without local BH being disabled */ struct inet_peer *inet_getpeer(struct inet_peer_base *base, const struct inetpeer_addr *daddr, int create); static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base, __be32 v4daddr, int vif, int create) { struct inetpeer_addr daddr; daddr.a4.addr = v4daddr; daddr.a4.vif = vif; daddr.family = AF_INET; return inet_getpeer(base, &daddr, create); } static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base, const struct in6_addr *v6daddr, int create) { struct inetpeer_addr daddr; daddr.a6 = *v6daddr; daddr.family = AF_INET6; return inet_getpeer(base, &daddr, create); } static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { int i, n; if (a->family == AF_INET) n = sizeof(a->a4) / sizeof(u32); else n = sizeof(a->a6) / sizeof(u32); for (i = 0; i < n; i++) { if (a->key[i] == b->key[i]) continue; if (a->key[i] < b->key[i]) return -1; return 1; } return 0; } /* can be called from BH context or outside */ void inet_putpeer(struct inet_peer *p); bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout); void inetpeer_invalidate_tree(struct inet_peer_base *); #endif /* _NET_INETPEER_H */ |
| 57 5 52 5 5 5 5 5 125 231 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright Red Hat Inc. 2017 * * This file is part of the SCTP kernel implementation * * These functions implement sctp stream message interleaving, mostly * including I-DATA and I-FORWARD-TSN chunks process. * * Please send any bug reports or fixes you make to the * email addresched(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * Xin Long <lucien.xin@gmail.com> */ #include <net/busy_poll.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/ulpevent.h> #include <linux/sctp.h> static struct sctp_chunk *sctp_make_idatafrag_empty( const struct sctp_association *asoc, const struct sctp_sndrcvinfo *sinfo, int len, __u8 flags, gfp_t gfp) { struct sctp_chunk *retval; struct sctp_idatahdr dp; memset(&dp, 0, sizeof(dp)); dp.stream = htons(sinfo->sinfo_stream); if (sinfo->sinfo_flags & SCTP_UNORDERED) flags |= SCTP_DATA_UNORDERED; retval = sctp_make_idata(asoc, flags, sizeof(dp) + len, gfp); if (!retval) return NULL; retval->subh.idata_hdr = sctp_addto_chunk(retval, sizeof(dp), &dp); memcpy(&retval->sinfo, sinfo, sizeof(struct sctp_sndrcvinfo)); return retval; } static void sctp_chunk_assign_mid(struct sctp_chunk *chunk) { struct sctp_stream *stream; struct sctp_chunk *lchunk; __u32 cfsn = 0; __u16 sid; if (chunk->has_mid) return; sid = sctp_chunk_stream_no(chunk); stream = &chunk->asoc->stream; list_for_each_entry(lchunk, &chunk->msg->chunks, frag_list) { struct sctp_idatahdr *hdr; __u32 mid; lchunk->has_mid = 1; hdr = lchunk->subh.idata_hdr; if (lchunk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG) hdr->ppid = lchunk->sinfo.sinfo_ppid; else hdr->fsn = htonl(cfsn++); if (lchunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) { mid = lchunk->chunk_hdr->flags & SCTP_DATA_LAST_FRAG ? sctp_mid_uo_next(stream, out, sid) : sctp_mid_uo_peek(stream, out, sid); } else { mid = lchunk->chunk_hdr->flags & SCTP_DATA_LAST_FRAG ? sctp_mid_next(stream, out, sid) : sctp_mid_peek(stream, out, sid); } hdr->mid = htonl(mid); } } static bool sctp_validate_data(struct sctp_chunk *chunk) { struct sctp_stream *stream; __u16 sid, ssn; if (chunk->chunk_hdr->type != SCTP_CID_DATA) return false; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) return true; stream = &chunk->asoc->stream; sid = sctp_chunk_stream_no(chunk); ssn = ntohs(chunk->subh.data_hdr->ssn); return !SSN_lt(ssn, sctp_ssn_peek(stream, in, sid)); } static bool sctp_validate_idata(struct sctp_chunk *chunk) { struct sctp_stream *stream; __u32 mid; __u16 sid; if (chunk->chunk_hdr->type != SCTP_CID_I_DATA) return false; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) return true; stream = &chunk->asoc->stream; sid = sctp_chunk_stream_no(chunk); mid = ntohl(chunk->subh.idata_hdr->mid); return !MID_lt(mid, sctp_mid_peek(stream, in, sid)); } static void sctp_intl_store_reasm(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_ulpevent *cevent; struct sk_buff *pos, *loc; pos = skb_peek_tail(&ulpq->reasm); if (!pos) { __skb_queue_tail(&ulpq->reasm, sctp_event2skb(event)); return; } cevent = sctp_skb2event(pos); if (event->stream == cevent->stream && event->mid == cevent->mid && (cevent->msg_flags & SCTP_DATA_FIRST_FRAG || (!(event->msg_flags & SCTP_DATA_FIRST_FRAG) && event->fsn > cevent->fsn))) { __skb_queue_tail(&ulpq->reasm, sctp_event2skb(event)); return; } if ((event->stream == cevent->stream && MID_lt(cevent->mid, event->mid)) || event->stream > cevent->stream) { __skb_queue_tail(&ulpq->reasm, sctp_event2skb(event)); return; } loc = NULL; skb_queue_walk(&ulpq->reasm, pos) { cevent = sctp_skb2event(pos); if (event->stream < cevent->stream || (event->stream == cevent->stream && MID_lt(event->mid, cevent->mid))) { loc = pos; break; } if (event->stream == cevent->stream && event->mid == cevent->mid && !(cevent->msg_flags & SCTP_DATA_FIRST_FRAG) && (event->msg_flags & SCTP_DATA_FIRST_FRAG || event->fsn < cevent->fsn)) { loc = pos; break; } } if (!loc) __skb_queue_tail(&ulpq->reasm, sctp_event2skb(event)); else __skb_queue_before(&ulpq->reasm, loc, sctp_event2skb(event)); } static struct sctp_ulpevent *sctp_intl_retrieve_partial( struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sk_buff *first_frag = NULL; struct sk_buff *last_frag = NULL; struct sctp_ulpevent *retval; struct sctp_stream_in *sin; struct sk_buff *pos; __u32 next_fsn = 0; int is_last = 0; sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); if (cevent->stream < event->stream) continue; if (cevent->stream > event->stream || cevent->mid != sin->mid) break; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: goto out; case SCTP_DATA_MIDDLE_FRAG: if (!first_frag) { if (cevent->fsn == sin->fsn) { first_frag = pos; last_frag = pos; next_fsn = cevent->fsn + 1; } } else if (cevent->fsn == next_fsn) { last_frag = pos; next_fsn++; } else { goto out; } break; case SCTP_DATA_LAST_FRAG: if (!first_frag) { if (cevent->fsn == sin->fsn) { first_frag = pos; last_frag = pos; next_fsn = 0; is_last = 1; } } else if (cevent->fsn == next_fsn) { last_frag = pos; next_fsn = 0; is_last = 1; } goto out; default: goto out; } } out: if (!first_frag) return NULL; retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm, first_frag, last_frag); if (retval) { sin->fsn = next_fsn; if (is_last) { retval->msg_flags |= MSG_EOR; sin->pd_mode = 0; } } return retval; } static struct sctp_ulpevent *sctp_intl_retrieve_reassembled( struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_association *asoc = ulpq->asoc; struct sk_buff *pos, *first_frag = NULL; struct sctp_ulpevent *retval = NULL; struct sk_buff *pd_first = NULL; struct sk_buff *pd_last = NULL; struct sctp_stream_in *sin; __u32 next_fsn = 0; __u32 pd_point = 0; __u32 pd_len = 0; __u32 mid = 0; sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); if (cevent->stream < event->stream) continue; if (cevent->stream > event->stream) break; if (MID_lt(cevent->mid, event->mid)) continue; if (MID_lt(event->mid, cevent->mid)) break; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: if (cevent->mid == sin->mid) { pd_first = pos; pd_last = pos; pd_len = pos->len; } first_frag = pos; next_fsn = 0; mid = cevent->mid; break; case SCTP_DATA_MIDDLE_FRAG: if (first_frag && cevent->mid == mid && cevent->fsn == next_fsn) { next_fsn++; if (pd_first) { pd_last = pos; pd_len += pos->len; } } else { first_frag = NULL; } break; case SCTP_DATA_LAST_FRAG: if (first_frag && cevent->mid == mid && cevent->fsn == next_fsn) goto found; else first_frag = NULL; break; } } if (!pd_first) goto out; pd_point = sctp_sk(asoc->base.sk)->pd_point; if (pd_point && pd_point <= pd_len) { retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm, pd_first, pd_last); if (retval) { sin->fsn = next_fsn; sin->pd_mode = 1; } } goto out; found: retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm, first_frag, pos); if (retval) retval->msg_flags |= MSG_EOR; out: return retval; } static struct sctp_ulpevent *sctp_intl_reasm(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_ulpevent *retval = NULL; struct sctp_stream_in *sin; if (SCTP_DATA_NOT_FRAG == (event->msg_flags & SCTP_DATA_FRAG_MASK)) { event->msg_flags |= MSG_EOR; return event; } sctp_intl_store_reasm(ulpq, event); sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); if (sin->pd_mode && event->mid == sin->mid && event->fsn == sin->fsn) retval = sctp_intl_retrieve_partial(ulpq, event); if (!retval) retval = sctp_intl_retrieve_reassembled(ulpq, event); return retval; } static void sctp_intl_store_ordered(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_ulpevent *cevent; struct sk_buff *pos, *loc; pos = skb_peek_tail(&ulpq->lobby); if (!pos) { __skb_queue_tail(&ulpq->lobby, sctp_event2skb(event)); return; } cevent = (struct sctp_ulpevent *)pos->cb; if (event->stream == cevent->stream && MID_lt(cevent->mid, event->mid)) { __skb_queue_tail(&ulpq->lobby, sctp_event2skb(event)); return; } if (event->stream > cevent->stream) { __skb_queue_tail(&ulpq->lobby, sctp_event2skb(event)); return; } loc = NULL; skb_queue_walk(&ulpq->lobby, pos) { cevent = (struct sctp_ulpevent *)pos->cb; if (cevent->stream > event->stream) { loc = pos; break; } if (cevent->stream == event->stream && MID_lt(event->mid, cevent->mid)) { loc = pos; break; } } if (!loc) __skb_queue_tail(&ulpq->lobby, sctp_event2skb(event)); else __skb_queue_before(&ulpq->lobby, loc, sctp_event2skb(event)); } static void sctp_intl_retrieve_ordered(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sk_buff_head *event_list; struct sctp_stream *stream; struct sk_buff *pos, *tmp; __u16 sid = event->stream; stream = &ulpq->asoc->stream; event_list = (struct sk_buff_head *)sctp_event2skb(event)->prev; sctp_skb_for_each(pos, &ulpq->lobby, tmp) { struct sctp_ulpevent *cevent = (struct sctp_ulpevent *)pos->cb; if (cevent->stream > sid) break; if (cevent->stream < sid) continue; if (cevent->mid != sctp_mid_peek(stream, in, sid)) break; sctp_mid_next(stream, in, sid); __skb_unlink(pos, &ulpq->lobby); __skb_queue_tail(event_list, pos); } } static struct sctp_ulpevent *sctp_intl_order(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_stream *stream; __u16 sid; stream = &ulpq->asoc->stream; sid = event->stream; if (event->mid != sctp_mid_peek(stream, in, sid)) { sctp_intl_store_ordered(ulpq, event); return NULL; } sctp_mid_next(stream, in, sid); sctp_intl_retrieve_ordered(ulpq, event); return event; } static int sctp_enqueue_event(struct sctp_ulpq *ulpq, struct sk_buff_head *skb_list) { struct sock *sk = ulpq->asoc->base.sk; struct sctp_sock *sp = sctp_sk(sk); struct sctp_ulpevent *event; struct sk_buff *skb; skb = __skb_peek(skb_list); event = sctp_skb2event(skb); if (sk->sk_shutdown & RCV_SHUTDOWN && (sk->sk_shutdown & SEND_SHUTDOWN || !sctp_ulpevent_is_notification(event))) goto out_free; if (!sctp_ulpevent_is_notification(event)) { sk_mark_napi_id(sk, skb); sk_incoming_cpu_update(sk); } if (!sctp_ulpevent_is_enabled(event, ulpq->asoc->subscribe)) goto out_free; skb_queue_splice_tail_init(skb_list, &sk->sk_receive_queue); if (!sp->data_ready_signalled) { sp->data_ready_signalled = 1; sk->sk_data_ready(sk); } return 1; out_free: sctp_queue_purge_ulpevents(skb_list); return 0; } static void sctp_intl_store_reasm_uo(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_ulpevent *cevent; struct sk_buff *pos; pos = skb_peek_tail(&ulpq->reasm_uo); if (!pos) { __skb_queue_tail(&ulpq->reasm_uo, sctp_event2skb(event)); return; } cevent = sctp_skb2event(pos); if (event->stream == cevent->stream && event->mid == cevent->mid && (cevent->msg_flags & SCTP_DATA_FIRST_FRAG || (!(event->msg_flags & SCTP_DATA_FIRST_FRAG) && event->fsn > cevent->fsn))) { __skb_queue_tail(&ulpq->reasm_uo, sctp_event2skb(event)); return; } if ((event->stream == cevent->stream && MID_lt(cevent->mid, event->mid)) || event->stream > cevent->stream) { __skb_queue_tail(&ulpq->reasm_uo, sctp_event2skb(event)); return; } skb_queue_walk(&ulpq->reasm_uo, pos) { cevent = sctp_skb2event(pos); if (event->stream < cevent->stream || (event->stream == cevent->stream && MID_lt(event->mid, cevent->mid))) break; if (event->stream == cevent->stream && event->mid == cevent->mid && !(cevent->msg_flags & SCTP_DATA_FIRST_FRAG) && (event->msg_flags & SCTP_DATA_FIRST_FRAG || event->fsn < cevent->fsn)) break; } __skb_queue_before(&ulpq->reasm_uo, pos, sctp_event2skb(event)); } static struct sctp_ulpevent *sctp_intl_retrieve_partial_uo( struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sk_buff *first_frag = NULL; struct sk_buff *last_frag = NULL; struct sctp_ulpevent *retval; struct sctp_stream_in *sin; struct sk_buff *pos; __u32 next_fsn = 0; int is_last = 0; sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); if (cevent->stream < event->stream) continue; if (cevent->stream > event->stream) break; if (MID_lt(cevent->mid, sin->mid_uo)) continue; if (MID_lt(sin->mid_uo, cevent->mid)) break; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: goto out; case SCTP_DATA_MIDDLE_FRAG: if (!first_frag) { if (cevent->fsn == sin->fsn_uo) { first_frag = pos; last_frag = pos; next_fsn = cevent->fsn + 1; } } else if (cevent->fsn == next_fsn) { last_frag = pos; next_fsn++; } else { goto out; } break; case SCTP_DATA_LAST_FRAG: if (!first_frag) { if (cevent->fsn == sin->fsn_uo) { first_frag = pos; last_frag = pos; next_fsn = 0; is_last = 1; } } else if (cevent->fsn == next_fsn) { last_frag = pos; next_fsn = 0; is_last = 1; } goto out; default: goto out; } } out: if (!first_frag) return NULL; retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm_uo, first_frag, last_frag); if (retval) { sin->fsn_uo = next_fsn; if (is_last) { retval->msg_flags |= MSG_EOR; sin->pd_mode_uo = 0; } } return retval; } static struct sctp_ulpevent *sctp_intl_retrieve_reassembled_uo( struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_association *asoc = ulpq->asoc; struct sk_buff *pos, *first_frag = NULL; struct sctp_ulpevent *retval = NULL; struct sk_buff *pd_first = NULL; struct sk_buff *pd_last = NULL; struct sctp_stream_in *sin; __u32 next_fsn = 0; __u32 pd_point = 0; __u32 pd_len = 0; __u32 mid = 0; sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); if (cevent->stream < event->stream) continue; if (cevent->stream > event->stream) break; if (MID_lt(cevent->mid, event->mid)) continue; if (MID_lt(event->mid, cevent->mid)) break; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: if (!sin->pd_mode_uo) { sin->mid_uo = cevent->mid; pd_first = pos; pd_last = pos; pd_len = pos->len; } first_frag = pos; next_fsn = 0; mid = cevent->mid; break; case SCTP_DATA_MIDDLE_FRAG: if (first_frag && cevent->mid == mid && cevent->fsn == next_fsn) { next_fsn++; if (pd_first) { pd_last = pos; pd_len += pos->len; } } else { first_frag = NULL; } break; case SCTP_DATA_LAST_FRAG: if (first_frag && cevent->mid == mid && cevent->fsn == next_fsn) goto found; else first_frag = NULL; break; } } if (!pd_first) goto out; pd_point = sctp_sk(asoc->base.sk)->pd_point; if (pd_point && pd_point <= pd_len) { retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm_uo, pd_first, pd_last); if (retval) { sin->fsn_uo = next_fsn; sin->pd_mode_uo = 1; } } goto out; found: retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm_uo, first_frag, pos); if (retval) retval->msg_flags |= MSG_EOR; out: return retval; } static struct sctp_ulpevent *sctp_intl_reasm_uo(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_ulpevent *retval = NULL; struct sctp_stream_in *sin; if (SCTP_DATA_NOT_FRAG == (event->msg_flags & SCTP_DATA_FRAG_MASK)) { event->msg_flags |= MSG_EOR; return event; } sctp_intl_store_reasm_uo(ulpq, event); sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); if (sin->pd_mode_uo && event->mid == sin->mid_uo && event->fsn == sin->fsn_uo) retval = sctp_intl_retrieve_partial_uo(ulpq, event); if (!retval) retval = sctp_intl_retrieve_reassembled_uo(ulpq, event); return retval; } static struct sctp_ulpevent *sctp_intl_retrieve_first_uo(struct sctp_ulpq *ulpq) { struct sctp_stream_in *csin, *sin = NULL; struct sk_buff *first_frag = NULL; struct sk_buff *last_frag = NULL; struct sctp_ulpevent *retval; struct sk_buff *pos; __u32 next_fsn = 0; __u16 sid = 0; skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); csin = sctp_stream_in(&ulpq->asoc->stream, cevent->stream); if (csin->pd_mode_uo) continue; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: if (first_frag) goto out; first_frag = pos; last_frag = pos; next_fsn = 0; sin = csin; sid = cevent->stream; sin->mid_uo = cevent->mid; break; case SCTP_DATA_MIDDLE_FRAG: if (!first_frag) break; if (cevent->stream == sid && cevent->mid == sin->mid_uo && cevent->fsn == next_fsn) { next_fsn++; last_frag = pos; } else { goto out; } break; case SCTP_DATA_LAST_FRAG: if (first_frag) goto out; break; default: break; } } if (!first_frag) return NULL; out: retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm_uo, first_frag, last_frag); if (retval) { sin->fsn_uo = next_fsn; sin->pd_mode_uo = 1; } return retval; } static int sctp_ulpevent_idata(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, gfp_t gfp) { struct sctp_ulpevent *event; struct sk_buff_head temp; int event_eor = 0; event = sctp_ulpevent_make_rcvmsg(chunk->asoc, chunk, gfp); if (!event) return -ENOMEM; event->mid = ntohl(chunk->subh.idata_hdr->mid); if (event->msg_flags & SCTP_DATA_FIRST_FRAG) event->ppid = chunk->subh.idata_hdr->ppid; else event->fsn = ntohl(chunk->subh.idata_hdr->fsn); if (!(event->msg_flags & SCTP_DATA_UNORDERED)) { event = sctp_intl_reasm(ulpq, event); if (event) { skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); if (event->msg_flags & MSG_EOR) event = sctp_intl_order(ulpq, event); } } else { event = sctp_intl_reasm_uo(ulpq, event); if (event) { skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); } } if (event) { event_eor = (event->msg_flags & MSG_EOR) ? 1 : 0; sctp_enqueue_event(ulpq, &temp); } return event_eor; } static struct sctp_ulpevent *sctp_intl_retrieve_first(struct sctp_ulpq *ulpq) { struct sctp_stream_in *csin, *sin = NULL; struct sk_buff *first_frag = NULL; struct sk_buff *last_frag = NULL; struct sctp_ulpevent *retval; struct sk_buff *pos; __u32 next_fsn = 0; __u16 sid = 0; skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); csin = sctp_stream_in(&ulpq->asoc->stream, cevent->stream); if (csin->pd_mode) continue; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: if (first_frag) goto out; if (cevent->mid == csin->mid) { first_frag = pos; last_frag = pos; next_fsn = 0; sin = csin; sid = cevent->stream; } break; case SCTP_DATA_MIDDLE_FRAG: if (!first_frag) break; if (cevent->stream == sid && cevent->mid == sin->mid && cevent->fsn == next_fsn) { next_fsn++; last_frag = pos; } else { goto out; } break; case SCTP_DATA_LAST_FRAG: if (first_frag) goto out; break; default: break; } } if (!first_frag) return NULL; out: retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm, first_frag, last_frag); if (retval) { sin->fsn = next_fsn; sin->pd_mode = 1; } return retval; } static void sctp_intl_start_pd(struct sctp_ulpq *ulpq, gfp_t gfp) { struct sctp_ulpevent *event; struct sk_buff_head temp; if (!skb_queue_empty(&ulpq->reasm)) { do { event = sctp_intl_retrieve_first(ulpq); if (event) { skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); sctp_enqueue_event(ulpq, &temp); } } while (event); } if (!skb_queue_empty(&ulpq->reasm_uo)) { do { event = sctp_intl_retrieve_first_uo(ulpq); if (event) { skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); sctp_enqueue_event(ulpq, &temp); } } while (event); } } static void sctp_renege_events(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, gfp_t gfp) { struct sctp_association *asoc = ulpq->asoc; __u32 freed = 0; __u16 needed; needed = ntohs(chunk->chunk_hdr->length) - sizeof(struct sctp_idata_chunk); if (skb_queue_empty(&asoc->base.sk->sk_receive_queue)) { freed = sctp_ulpq_renege_list(ulpq, &ulpq->lobby, needed); if (freed < needed) freed += sctp_ulpq_renege_list(ulpq, &ulpq->reasm, needed); if (freed < needed) freed += sctp_ulpq_renege_list(ulpq, &ulpq->reasm_uo, needed); } if (freed >= needed && sctp_ulpevent_idata(ulpq, chunk, gfp) <= 0) sctp_intl_start_pd(ulpq, gfp); } static void sctp_intl_stream_abort_pd(struct sctp_ulpq *ulpq, __u16 sid, __u32 mid, __u16 flags, gfp_t gfp) { struct sock *sk = ulpq->asoc->base.sk; struct sctp_ulpevent *ev = NULL; if (!sctp_ulpevent_type_enabled(ulpq->asoc->subscribe, SCTP_PARTIAL_DELIVERY_EVENT)) return; ev = sctp_ulpevent_make_pdapi(ulpq->asoc, SCTP_PARTIAL_DELIVERY_ABORTED, sid, mid, flags, gfp); if (ev) { struct sctp_sock *sp = sctp_sk(sk); __skb_queue_tail(&sk->sk_receive_queue, sctp_event2skb(ev)); if (!sp->data_ready_signalled) { sp->data_ready_signalled = 1; sk->sk_data_ready(sk); } } } static void sctp_intl_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid) { struct sctp_stream *stream = &ulpq->asoc->stream; struct sctp_ulpevent *cevent, *event = NULL; struct sk_buff_head *lobby = &ulpq->lobby; struct sk_buff *pos, *tmp; struct sk_buff_head temp; __u16 csid; __u32 cmid; skb_queue_head_init(&temp); sctp_skb_for_each(pos, lobby, tmp) { cevent = (struct sctp_ulpevent *)pos->cb; csid = cevent->stream; cmid = cevent->mid; if (csid > sid) break; if (csid < sid) continue; if (!MID_lt(cmid, sctp_mid_peek(stream, in, csid))) break; __skb_unlink(pos, lobby); if (!event) event = sctp_skb2event(pos); __skb_queue_tail(&temp, pos); } if (!event && pos != (struct sk_buff *)lobby) { cevent = (struct sctp_ulpevent *)pos->cb; csid = cevent->stream; cmid = cevent->mid; if (csid == sid && cmid == sctp_mid_peek(stream, in, csid)) { sctp_mid_next(stream, in, csid); __skb_unlink(pos, lobby); __skb_queue_tail(&temp, pos); event = sctp_skb2event(pos); } } if (event) { sctp_intl_retrieve_ordered(ulpq, event); sctp_enqueue_event(ulpq, &temp); } } static void sctp_intl_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp) { struct sctp_stream *stream = &ulpq->asoc->stream; __u16 sid; for (sid = 0; sid < stream->incnt; sid++) { struct sctp_stream_in *sin = SCTP_SI(stream, sid); __u32 mid; if (sin->pd_mode_uo) { sin->pd_mode_uo = 0; mid = sin->mid_uo; sctp_intl_stream_abort_pd(ulpq, sid, mid, 0x1, gfp); } if (sin->pd_mode) { sin->pd_mode = 0; mid = sin->mid; sctp_intl_stream_abort_pd(ulpq, sid, mid, 0, gfp); sctp_mid_skip(stream, in, sid, mid); sctp_intl_reap_ordered(ulpq, sid); } } /* intl abort pd happens only when all data needs to be cleaned */ sctp_ulpq_flush(ulpq); } static inline int sctp_get_skip_pos(struct sctp_ifwdtsn_skip *skiplist, int nskips, __be16 stream, __u8 flags) { int i; for (i = 0; i < nskips; i++) if (skiplist[i].stream == stream && skiplist[i].flags == flags) return i; return i; } #define SCTP_FTSN_U_BIT 0x1 static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) { struct sctp_ifwdtsn_skip ftsn_skip_arr[10]; struct sctp_association *asoc = q->asoc; struct sctp_chunk *ftsn_chunk = NULL; struct list_head *lchunk, *temp; int nskips = 0, skip_pos; struct sctp_chunk *chunk; __u32 tsn; if (!asoc->peer.prsctp_capable) return; if (TSN_lt(asoc->adv_peer_ack_point, ctsn)) asoc->adv_peer_ack_point = ctsn; list_for_each_safe(lchunk, temp, &q->abandoned) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); tsn = ntohl(chunk->subh.data_hdr->tsn); if (TSN_lte(tsn, ctsn)) { list_del_init(lchunk); sctp_chunk_free(chunk); } else if (TSN_lte(tsn, asoc->adv_peer_ack_point + 1)) { __be16 sid = chunk->subh.idata_hdr->stream; __be32 mid = chunk->subh.idata_hdr->mid; __u8 flags = 0; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) flags |= SCTP_FTSN_U_BIT; asoc->adv_peer_ack_point = tsn; skip_pos = sctp_get_skip_pos(&ftsn_skip_arr[0], nskips, sid, flags); ftsn_skip_arr[skip_pos].stream = sid; ftsn_skip_arr[skip_pos].reserved = 0; ftsn_skip_arr[skip_pos].flags = flags; ftsn_skip_arr[skip_pos].mid = mid; if (skip_pos == nskips) nskips++; if (nskips == 10) break; } else { break; } } if (asoc->adv_peer_ack_point > ctsn) ftsn_chunk = sctp_make_ifwdtsn(asoc, asoc->adv_peer_ack_point, nskips, &ftsn_skip_arr[0]); if (ftsn_chunk) { list_add_tail(&ftsn_chunk->list, &q->control_chunk_list); SCTP_INC_STATS(asoc->base.net, SCTP_MIB_OUTCTRLCHUNKS); } } #define _sctp_walk_ifwdtsn(pos, chunk, end) \ for (pos = (void *)(chunk->subh.ifwdtsn_hdr + 1); \ (void *)pos <= (void *)(chunk->subh.ifwdtsn_hdr + 1) + (end) - \ sizeof(struct sctp_ifwdtsn_skip); pos++) #define sctp_walk_ifwdtsn(pos, ch) \ _sctp_walk_ifwdtsn((pos), (ch), ntohs((ch)->chunk_hdr->length) - \ sizeof(struct sctp_ifwdtsn_chunk)) static bool sctp_validate_fwdtsn(struct sctp_chunk *chunk) { struct sctp_fwdtsn_skip *skip; __u16 incnt; if (chunk->chunk_hdr->type != SCTP_CID_FWD_TSN) return false; incnt = chunk->asoc->stream.incnt; sctp_walk_fwdtsn(skip, chunk) if (ntohs(skip->stream) >= incnt) return false; return true; } static bool sctp_validate_iftsn(struct sctp_chunk *chunk) { struct sctp_ifwdtsn_skip *skip; __u16 incnt; if (chunk->chunk_hdr->type != SCTP_CID_I_FWD_TSN) return false; incnt = chunk->asoc->stream.incnt; sctp_walk_ifwdtsn(skip, chunk) if (ntohs(skip->stream) >= incnt) return false; return true; } static void sctp_report_fwdtsn(struct sctp_ulpq *ulpq, __u32 ftsn) { /* Move the Cumulattive TSN Ack ahead. */ sctp_tsnmap_skip(&ulpq->asoc->peer.tsn_map, ftsn); /* purge the fragmentation queue */ sctp_ulpq_reasm_flushtsn(ulpq, ftsn); /* Abort any in progress partial delivery. */ sctp_ulpq_abort_pd(ulpq, GFP_ATOMIC); } static void sctp_intl_reasm_flushtsn(struct sctp_ulpq *ulpq, __u32 ftsn) { struct sk_buff *pos, *tmp; skb_queue_walk_safe(&ulpq->reasm, pos, tmp) { struct sctp_ulpevent *event = sctp_skb2event(pos); __u32 tsn = event->tsn; if (TSN_lte(tsn, ftsn)) { __skb_unlink(pos, &ulpq->reasm); sctp_ulpevent_free(event); } } skb_queue_walk_safe(&ulpq->reasm_uo, pos, tmp) { struct sctp_ulpevent *event = sctp_skb2event(pos); __u32 tsn = event->tsn; if (TSN_lte(tsn, ftsn)) { __skb_unlink(pos, &ulpq->reasm_uo); sctp_ulpevent_free(event); } } } static void sctp_report_iftsn(struct sctp_ulpq *ulpq, __u32 ftsn) { /* Move the Cumulattive TSN Ack ahead. */ sctp_tsnmap_skip(&ulpq->asoc->peer.tsn_map, ftsn); /* purge the fragmentation queue */ sctp_intl_reasm_flushtsn(ulpq, ftsn); /* abort only when it's for all data */ if (ftsn == sctp_tsnmap_get_max_tsn_seen(&ulpq->asoc->peer.tsn_map)) sctp_intl_abort_pd(ulpq, GFP_ATOMIC); } static void sctp_handle_fwdtsn(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk) { struct sctp_fwdtsn_skip *skip; /* Walk through all the skipped SSNs */ sctp_walk_fwdtsn(skip, chunk) sctp_ulpq_skip(ulpq, ntohs(skip->stream), ntohs(skip->ssn)); } static void sctp_intl_skip(struct sctp_ulpq *ulpq, __u16 sid, __u32 mid, __u8 flags) { struct sctp_stream_in *sin = sctp_stream_in(&ulpq->asoc->stream, sid); struct sctp_stream *stream = &ulpq->asoc->stream; if (flags & SCTP_FTSN_U_BIT) { if (sin->pd_mode_uo && MID_lt(sin->mid_uo, mid)) { sin->pd_mode_uo = 0; sctp_intl_stream_abort_pd(ulpq, sid, mid, 0x1, GFP_ATOMIC); } return; } if (MID_lt(mid, sctp_mid_peek(stream, in, sid))) return; if (sin->pd_mode) { sin->pd_mode = 0; sctp_intl_stream_abort_pd(ulpq, sid, mid, 0x0, GFP_ATOMIC); } sctp_mid_skip(stream, in, sid, mid); sctp_intl_reap_ordered(ulpq, sid); } static void sctp_handle_iftsn(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk) { struct sctp_ifwdtsn_skip *skip; /* Walk through all the skipped MIDs and abort stream pd if possible */ sctp_walk_ifwdtsn(skip, chunk) sctp_intl_skip(ulpq, ntohs(skip->stream), ntohl(skip->mid), skip->flags); } static int do_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sk_buff_head temp; skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); return sctp_ulpq_tail_event(ulpq, &temp); } static struct sctp_stream_interleave sctp_stream_interleave_0 = { .data_chunk_len = sizeof(struct sctp_data_chunk), .ftsn_chunk_len = sizeof(struct sctp_fwdtsn_chunk), /* DATA process functions */ .make_datafrag = sctp_make_datafrag_empty, .assign_number = sctp_chunk_assign_ssn, .validate_data = sctp_validate_data, .ulpevent_data = sctp_ulpq_tail_data, .enqueue_event = do_ulpq_tail_event, .renege_events = sctp_ulpq_renege, .start_pd = sctp_ulpq_partial_delivery, .abort_pd = sctp_ulpq_abort_pd, /* FORWARD-TSN process functions */ .generate_ftsn = sctp_generate_fwdtsn, .validate_ftsn = sctp_validate_fwdtsn, .report_ftsn = sctp_report_fwdtsn, .handle_ftsn = sctp_handle_fwdtsn, }; static int do_sctp_enqueue_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sk_buff_head temp; skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); return sctp_enqueue_event(ulpq, &temp); } static struct sctp_stream_interleave sctp_stream_interleave_1 = { .data_chunk_len = sizeof(struct sctp_idata_chunk), .ftsn_chunk_len = sizeof(struct sctp_ifwdtsn_chunk), /* I-DATA process functions */ .make_datafrag = sctp_make_idatafrag_empty, .assign_number = sctp_chunk_assign_mid, .validate_data = sctp_validate_idata, .ulpevent_data = sctp_ulpevent_idata, .enqueue_event = do_sctp_enqueue_event, .renege_events = sctp_renege_events, .start_pd = sctp_intl_start_pd, .abort_pd = sctp_intl_abort_pd, /* I-FORWARD-TSN process functions */ .generate_ftsn = sctp_generate_iftsn, .validate_ftsn = sctp_validate_iftsn, .report_ftsn = sctp_report_iftsn, .handle_ftsn = sctp_handle_iftsn, }; void sctp_stream_interleave_init(struct sctp_stream *stream) { struct sctp_association *asoc; asoc = container_of(stream, struct sctp_association, stream); stream->si = asoc->peer.intl_capable ? &sctp_stream_interleave_1 : &sctp_stream_interleave_0; } |
| 3 19 19 6 13 6 6 13 13 13 13 13 13 13 19 1 1 1 20 20 20 20 3 17 18 2 19 3 17 3 20 17 3 18 2 1 19 19 1 2 2 20 20 20 20 20 20 4 20 20 2 17 2 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * SME code for cfg80211 * both driver SME event handling and the SME implementation * (for nl80211's connect() and wext) * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2009, 2020, 2022-2024 Intel Corporation. All rights reserved. * Copyright 2017 Intel Deutschland GmbH */ #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/wireless.h> #include <linux/export.h> #include <net/iw_handler.h> #include <net/cfg80211.h> #include <net/rtnetlink.h> #include "nl80211.h" #include "reg.h" #include "rdev-ops.h" /* * Software SME in cfg80211, using auth/assoc/deauth calls to the * driver. This is for implementing nl80211's connect/disconnect * and wireless extensions (if configured.) */ struct cfg80211_conn { struct cfg80211_connect_params params; /* these are sub-states of the _CONNECTING sme_state */ enum { CFG80211_CONN_SCANNING, CFG80211_CONN_SCAN_AGAIN, CFG80211_CONN_AUTHENTICATE_NEXT, CFG80211_CONN_AUTHENTICATING, CFG80211_CONN_AUTH_FAILED_TIMEOUT, CFG80211_CONN_ASSOCIATE_NEXT, CFG80211_CONN_ASSOCIATING, CFG80211_CONN_ASSOC_FAILED, CFG80211_CONN_ASSOC_FAILED_TIMEOUT, CFG80211_CONN_DEAUTH, CFG80211_CONN_ABANDON, CFG80211_CONN_CONNECTED, } state; u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; const u8 *ie; size_t ie_len; bool auto_auth, prev_bssid_valid; }; static void cfg80211_sme_free(struct wireless_dev *wdev) { if (!wdev->conn) return; kfree(wdev->conn->ie); kfree(wdev->conn); wdev->conn = NULL; } static int cfg80211_conn_scan(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_scan_request *request; int n_channels, err; lockdep_assert_wiphy(wdev->wiphy); if (rdev->scan_req || rdev->scan_msg) return -EBUSY; if (wdev->conn->params.channel) n_channels = 1; else n_channels = ieee80211_get_num_supported_channels(wdev->wiphy); request = kzalloc(sizeof(*request) + sizeof(request->ssids[0]) + sizeof(request->channels[0]) * n_channels, GFP_KERNEL); if (!request) return -ENOMEM; if (wdev->conn->params.channel) { enum nl80211_band band = wdev->conn->params.channel->band; struct ieee80211_supported_band *sband = wdev->wiphy->bands[band]; if (!sband) { kfree(request); return -EINVAL; } request->channels[0] = wdev->conn->params.channel; request->rates[band] = (1 << sband->n_bitrates) - 1; } else { int i = 0, j; enum nl80211_band band; struct ieee80211_supported_band *bands; struct ieee80211_channel *channel; for (band = 0; band < NUM_NL80211_BANDS; band++) { bands = wdev->wiphy->bands[band]; if (!bands) continue; for (j = 0; j < bands->n_channels; j++) { channel = &bands->channels[j]; if (channel->flags & IEEE80211_CHAN_DISABLED) continue; request->channels[i++] = channel; } request->rates[band] = (1 << bands->n_bitrates) - 1; } n_channels = i; } request->n_channels = n_channels; request->ssids = (void *)&request->channels[n_channels]; request->n_ssids = 1; memcpy(request->ssids[0].ssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len); request->ssids[0].ssid_len = wdev->conn->params.ssid_len; eth_broadcast_addr(request->bssid); request->wdev = wdev; request->wiphy = &rdev->wiphy; request->scan_start = jiffies; rdev->scan_req = request; err = cfg80211_scan(rdev); if (!err) { wdev->conn->state = CFG80211_CONN_SCANNING; nl80211_send_scan_start(rdev, wdev); dev_hold(wdev->netdev); } else { rdev->scan_req = NULL; kfree(request); } return err; } static int cfg80211_conn_do_work(struct wireless_dev *wdev, enum nl80211_timeout_reason *treason) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_connect_params *params; struct cfg80211_auth_request auth_req = {}; struct cfg80211_assoc_request req = {}; int err; lockdep_assert_wiphy(wdev->wiphy); if (!wdev->conn) return 0; params = &wdev->conn->params; switch (wdev->conn->state) { case CFG80211_CONN_SCANNING: /* didn't find it during scan ... */ return -ENOENT; case CFG80211_CONN_SCAN_AGAIN: return cfg80211_conn_scan(wdev); case CFG80211_CONN_AUTHENTICATE_NEXT: if (WARN_ON(!rdev->ops->auth)) return -EOPNOTSUPP; wdev->conn->state = CFG80211_CONN_AUTHENTICATING; auth_req.key = params->key; auth_req.key_len = params->key_len; auth_req.key_idx = params->key_idx; auth_req.auth_type = params->auth_type; auth_req.bss = cfg80211_get_bss(&rdev->wiphy, params->channel, params->bssid, params->ssid, params->ssid_len, IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); auth_req.link_id = -1; err = cfg80211_mlme_auth(rdev, wdev->netdev, &auth_req); cfg80211_put_bss(&rdev->wiphy, auth_req.bss); return err; case CFG80211_CONN_AUTH_FAILED_TIMEOUT: *treason = NL80211_TIMEOUT_AUTH; return -ENOTCONN; case CFG80211_CONN_ASSOCIATE_NEXT: if (WARN_ON(!rdev->ops->assoc)) return -EOPNOTSUPP; wdev->conn->state = CFG80211_CONN_ASSOCIATING; if (wdev->conn->prev_bssid_valid) req.prev_bssid = wdev->conn->prev_bssid; req.ie = params->ie; req.ie_len = params->ie_len; req.use_mfp = params->mfp != NL80211_MFP_NO; req.crypto = params->crypto; req.flags = params->flags; req.ht_capa = params->ht_capa; req.ht_capa_mask = params->ht_capa_mask; req.vht_capa = params->vht_capa; req.vht_capa_mask = params->vht_capa_mask; req.link_id = -1; req.bss = cfg80211_get_bss(&rdev->wiphy, params->channel, params->bssid, params->ssid, params->ssid_len, IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); if (!req.bss) { err = -ENOENT; } else { err = cfg80211_mlme_assoc(rdev, wdev->netdev, &req, NULL); cfg80211_put_bss(&rdev->wiphy, req.bss); } if (err) cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); return err; case CFG80211_CONN_ASSOC_FAILED_TIMEOUT: *treason = NL80211_TIMEOUT_ASSOC; fallthrough; case CFG80211_CONN_ASSOC_FAILED: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); return -ENOTCONN; case CFG80211_CONN_DEAUTH: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); fallthrough; case CFG80211_CONN_ABANDON: /* free directly, disconnected event already sent */ cfg80211_sme_free(wdev); return 0; default: return 0; } } void cfg80211_conn_work(struct work_struct *work) { struct cfg80211_registered_device *rdev = container_of(work, struct cfg80211_registered_device, conn_work); struct wireless_dev *wdev; u8 bssid_buf[ETH_ALEN], *bssid = NULL; enum nl80211_timeout_reason treason; wiphy_lock(&rdev->wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (!wdev->netdev) continue; if (!netif_running(wdev->netdev)) continue; if (!wdev->conn || wdev->conn->state == CFG80211_CONN_CONNECTED) continue; if (wdev->conn->params.bssid) { memcpy(bssid_buf, wdev->conn->params.bssid, ETH_ALEN); bssid = bssid_buf; } treason = NL80211_TIMEOUT_UNSPECIFIED; if (cfg80211_conn_do_work(wdev, &treason)) { struct cfg80211_connect_resp_params cr; memset(&cr, 0, sizeof(cr)); cr.status = -1; cr.links[0].bssid = bssid; cr.timeout_reason = treason; __cfg80211_connect_result(wdev->netdev, &cr, false); } } wiphy_unlock(&rdev->wiphy); } static void cfg80211_step_auth_next(struct cfg80211_conn *conn, struct cfg80211_bss *bss) { memcpy(conn->bssid, bss->bssid, ETH_ALEN); conn->params.bssid = conn->bssid; conn->params.channel = bss->channel; conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; } /* Returned bss is reference counted and must be cleaned up appropriately. */ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; lockdep_assert_wiphy(wdev->wiphy); bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (!bss) return NULL; cfg80211_step_auth_next(wdev->conn, bss); schedule_work(&rdev->conn_work); return bss; } void cfg80211_sme_scan_done(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; lockdep_assert_wiphy(wdev->wiphy); if (!wdev->conn) return; if (wdev->conn->state != CFG80211_CONN_SCANNING && wdev->conn->state != CFG80211_CONN_SCAN_AGAIN) return; bss = cfg80211_get_conn_bss(wdev); if (bss) cfg80211_put_bss(&rdev->wiphy, bss); else schedule_work(&rdev->conn_work); } void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; u16 status_code = le16_to_cpu(mgmt->u.auth.status_code); lockdep_assert_wiphy(wdev->wiphy); if (!wdev->conn || wdev->conn->state == CFG80211_CONN_CONNECTED) return; if (status_code == WLAN_STATUS_NOT_SUPPORTED_AUTH_ALG && wdev->conn->auto_auth && wdev->conn->params.auth_type != NL80211_AUTHTYPE_NETWORK_EAP) { /* select automatically between only open, shared, leap */ switch (wdev->conn->params.auth_type) { case NL80211_AUTHTYPE_OPEN_SYSTEM: if (wdev->connect_keys) wdev->conn->params.auth_type = NL80211_AUTHTYPE_SHARED_KEY; else wdev->conn->params.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; break; case NL80211_AUTHTYPE_SHARED_KEY: wdev->conn->params.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; break; default: /* huh? */ wdev->conn->params.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; break; } wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; schedule_work(&rdev->conn_work); } else if (status_code != WLAN_STATUS_SUCCESS) { struct cfg80211_connect_resp_params cr; memset(&cr, 0, sizeof(cr)); cr.status = status_code; cr.links[0].bssid = mgmt->bssid; cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED; __cfg80211_connect_result(wdev->netdev, &cr, false); } else if (wdev->conn->state == CFG80211_CONN_AUTHENTICATING) { wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; schedule_work(&rdev->conn_work); } } bool cfg80211_sme_rx_assoc_resp(struct wireless_dev *wdev, u16 status) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return false; if (status == WLAN_STATUS_SUCCESS) { wdev->conn->state = CFG80211_CONN_CONNECTED; return false; } if (wdev->conn->prev_bssid_valid) { /* * Some stupid APs don't accept reassoc, so we * need to fall back to trying regular assoc; * return true so no event is sent to userspace. */ wdev->conn->prev_bssid_valid = false; wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; schedule_work(&rdev->conn_work); return true; } wdev->conn->state = CFG80211_CONN_ASSOC_FAILED; schedule_work(&rdev->conn_work); return false; } void cfg80211_sme_deauth(struct wireless_dev *wdev) { cfg80211_sme_free(wdev); } void cfg80211_sme_auth_timeout(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_AUTH_FAILED_TIMEOUT; schedule_work(&rdev->conn_work); } void cfg80211_sme_disassoc(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_DEAUTH; schedule_work(&rdev->conn_work); } void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_ASSOC_FAILED_TIMEOUT; schedule_work(&rdev->conn_work); } void cfg80211_sme_abandon_assoc(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_ABANDON; schedule_work(&rdev->conn_work); } static void cfg80211_wdev_release_bsses(struct wireless_dev *wdev) { unsigned int link; for_each_valid_link(wdev, link) { if (!wdev->links[link].client.current_bss) continue; cfg80211_unhold_bss(wdev->links[link].client.current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->links[link].client.current_bss->pub); wdev->links[link].client.current_bss = NULL; } } void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask) { unsigned int link; for_each_valid_link(wdev, link) { if (!wdev->links[link].client.current_bss || !(link_mask & BIT(link))) continue; cfg80211_unhold_bss(wdev->links[link].client.current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->links[link].client.current_bss->pub); wdev->links[link].client.current_bss = NULL; } } static int cfg80211_sme_get_conn_ies(struct wireless_dev *wdev, const u8 *ies, size_t ies_len, const u8 **out_ies, size_t *out_ies_len) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u8 *buf; size_t offs; if (!rdev->wiphy.extended_capabilities_len || (ies && cfg80211_find_ie(WLAN_EID_EXT_CAPABILITY, ies, ies_len))) { *out_ies = kmemdup(ies, ies_len, GFP_KERNEL); if (!*out_ies) return -ENOMEM; *out_ies_len = ies_len; return 0; } buf = kmalloc(ies_len + rdev->wiphy.extended_capabilities_len + 2, GFP_KERNEL); if (!buf) return -ENOMEM; if (ies_len) { static const u8 before_extcapa[] = { /* not listing IEs expected to be created by driver */ WLAN_EID_RSN, WLAN_EID_QOS_CAPA, WLAN_EID_RRM_ENABLED_CAPABILITIES, WLAN_EID_MOBILITY_DOMAIN, WLAN_EID_SUPPORTED_REGULATORY_CLASSES, WLAN_EID_BSS_COEX_2040, }; offs = ieee80211_ie_split(ies, ies_len, before_extcapa, ARRAY_SIZE(before_extcapa), 0); memcpy(buf, ies, offs); /* leave a whole for extended capabilities IE */ memcpy(buf + offs + rdev->wiphy.extended_capabilities_len + 2, ies + offs, ies_len - offs); } else { offs = 0; } /* place extended capabilities IE (with only driver capabilities) */ buf[offs] = WLAN_EID_EXT_CAPABILITY; buf[offs + 1] = rdev->wiphy.extended_capabilities_len; memcpy(buf + offs + 2, rdev->wiphy.extended_capabilities, rdev->wiphy.extended_capabilities_len); *out_ies = buf; *out_ies_len = ies_len + rdev->wiphy.extended_capabilities_len + 2; return 0; } static int cfg80211_sme_connect(struct wireless_dev *wdev, struct cfg80211_connect_params *connect, const u8 *prev_bssid) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; int err; if (!rdev->ops->auth || !rdev->ops->assoc) return -EOPNOTSUPP; cfg80211_wdev_release_bsses(wdev); if (wdev->connected) { cfg80211_sme_free(wdev); wdev->connected = false; } if (wdev->conn) return -EINPROGRESS; wdev->conn = kzalloc(sizeof(*wdev->conn), GFP_KERNEL); if (!wdev->conn) return -ENOMEM; /* * Copy all parameters, and treat explicitly IEs, BSSID, SSID. */ memcpy(&wdev->conn->params, connect, sizeof(*connect)); if (connect->bssid) { wdev->conn->params.bssid = wdev->conn->bssid; memcpy(wdev->conn->bssid, connect->bssid, ETH_ALEN); } if (cfg80211_sme_get_conn_ies(wdev, connect->ie, connect->ie_len, &wdev->conn->ie, &wdev->conn->params.ie_len)) { kfree(wdev->conn); wdev->conn = NULL; return -ENOMEM; } wdev->conn->params.ie = wdev->conn->ie; if (connect->auth_type == NL80211_AUTHTYPE_AUTOMATIC) { wdev->conn->auto_auth = true; /* start with open system ... should mostly work */ wdev->conn->params.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; } else { wdev->conn->auto_auth = false; } wdev->conn->params.ssid = wdev->u.client.ssid; wdev->conn->params.ssid_len = wdev->u.client.ssid_len; /* see if we have the bss already */ bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (prev_bssid) { memcpy(wdev->conn->prev_bssid, prev_bssid, ETH_ALEN); wdev->conn->prev_bssid_valid = true; } /* we're good if we have a matching bss struct */ if (bss) { enum nl80211_timeout_reason treason; cfg80211_step_auth_next(wdev->conn, bss); err = cfg80211_conn_do_work(wdev, &treason); cfg80211_put_bss(wdev->wiphy, bss); } else { /* otherwise we'll need to scan for the AP first */ err = cfg80211_conn_scan(wdev); /* * If we can't scan right now, then we need to scan again * after the current scan finished, since the parameters * changed (unless we find a good AP anyway). */ if (err == -EBUSY) { err = 0; wdev->conn->state = CFG80211_CONN_SCAN_AGAIN; } } if (err) cfg80211_sme_free(wdev); return err; } static int cfg80211_sme_disconnect(struct wireless_dev *wdev, u16 reason) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int err; if (!wdev->conn) return 0; if (!rdev->ops->deauth) return -EOPNOTSUPP; if (wdev->conn->state == CFG80211_CONN_SCANNING || wdev->conn->state == CFG80211_CONN_SCAN_AGAIN) { err = 0; goto out; } /* wdev->conn->params.bssid must be set if > SCANNING */ err = cfg80211_mlme_deauth(rdev, wdev->netdev, wdev->conn->params.bssid, NULL, 0, reason, false); out: cfg80211_sme_free(wdev); return err; } /* * code shared for in-device and software SME */ static bool cfg80211_is_all_idle(void) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; bool is_all_idle = true; /* * All devices must be idle as otherwise if you are actively * scanning some new beacon hints could be learned and would * count as new regulatory hints. * Also if there is any other active beaconing interface we * need not issue a disconnect hint and reset any info such * as chan dfs state, etc. */ for_each_rdev(rdev) { wiphy_lock(&rdev->wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (wdev->conn || wdev->connected || cfg80211_beaconing_iface_active(wdev)) is_all_idle = false; } wiphy_unlock(&rdev->wiphy); } return is_all_idle; } static void disconnect_work(struct work_struct *work) { rtnl_lock(); if (cfg80211_is_all_idle()) regulatory_hint_disconnect(); rtnl_unlock(); } DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); static void cfg80211_connect_result_release_bsses(struct wireless_dev *wdev, struct cfg80211_connect_resp_params *cr) { unsigned int link; for_each_valid_link(cr, link) { if (!cr->links[link].bss) continue; cfg80211_unhold_bss(bss_from_pub(cr->links[link].bss)); cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); } } /* * API calls for drivers implementing connect/disconnect and * SME event handling */ /* This method must consume bss one way or another */ void __cfg80211_connect_result(struct net_device *dev, struct cfg80211_connect_resp_params *cr, bool wextev) { struct wireless_dev *wdev = dev->ieee80211_ptr; const struct element *country_elem = NULL; const struct element *ssid; const u8 *country_data; u8 country_datalen; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif unsigned int link; const u8 *connected_addr; bool bss_not_found = false; lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) goto out; if (cr->valid_links) { if (WARN_ON(!cr->ap_mld_addr)) goto out; for_each_valid_link(cr, link) { if (WARN_ON(!cr->links[link].addr)) goto out; } if (WARN_ON(wdev->connect_keys)) goto out; } wdev->unprot_beacon_reported = 0; nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev, cr, GFP_KERNEL); connected_addr = cr->valid_links ? cr->ap_mld_addr : cr->links[0].bssid; #ifdef CONFIG_CFG80211_WEXT if (wextev && !cr->valid_links) { if (cr->req_ie && cr->status == WLAN_STATUS_SUCCESS) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = cr->req_ie_len; wireless_send_event(dev, IWEVASSOCREQIE, &wrqu, cr->req_ie); } if (cr->resp_ie && cr->status == WLAN_STATUS_SUCCESS) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = cr->resp_ie_len; wireless_send_event(dev, IWEVASSOCRESPIE, &wrqu, cr->resp_ie); } memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; if (connected_addr && cr->status == WLAN_STATUS_SUCCESS) { memcpy(wrqu.ap_addr.sa_data, connected_addr, ETH_ALEN); memcpy(wdev->wext.prev_bssid, connected_addr, ETH_ALEN); wdev->wext.prev_bssid_valid = true; } wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); } #endif if (cr->status == WLAN_STATUS_SUCCESS) { if (!wiphy_to_rdev(wdev->wiphy)->ops->connect) { for_each_valid_link(cr, link) { if (WARN_ON_ONCE(!cr->links[link].bss)) break; } } for_each_valid_link(cr, link) { /* don't do extra lookups for failures */ if (cr->links[link].status != WLAN_STATUS_SUCCESS) continue; if (cr->links[link].bss) continue; cr->links[link].bss = cfg80211_get_bss(wdev->wiphy, NULL, cr->links[link].bssid, wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (!cr->links[link].bss) { bss_not_found = true; break; } cfg80211_hold_bss(bss_from_pub(cr->links[link].bss)); } } cfg80211_wdev_release_bsses(wdev); if (cr->status != WLAN_STATUS_SUCCESS) { kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; wdev->u.client.ssid_len = 0; wdev->conn_owner_nlportid = 0; cfg80211_connect_result_release_bsses(wdev, cr); cfg80211_sme_free(wdev); return; } if (WARN_ON(bss_not_found)) { cfg80211_connect_result_release_bsses(wdev, cr); return; } memset(wdev->links, 0, sizeof(wdev->links)); for_each_valid_link(cr, link) { if (cr->links[link].status == WLAN_STATUS_SUCCESS) continue; cr->valid_links &= ~BIT(link); /* don't require bss pointer for failed links */ if (!cr->links[link].bss) continue; cfg80211_unhold_bss(bss_from_pub(cr->links[link].bss)); cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); } wdev->valid_links = cr->valid_links; for_each_valid_link(cr, link) wdev->links[link].client.current_bss = bss_from_pub(cr->links[link].bss); wdev->connected = true; ether_addr_copy(wdev->u.client.connected_addr, connected_addr); if (cr->valid_links) { for_each_valid_link(cr, link) memcpy(wdev->links[link].addr, cr->links[link].addr, ETH_ALEN); } cfg80211_upload_connect_keys(wdev); rcu_read_lock(); for_each_valid_link(cr, link) { country_elem = ieee80211_bss_get_elem(cr->links[link].bss, WLAN_EID_COUNTRY); if (country_elem) break; } if (!country_elem) { rcu_read_unlock(); return; } country_datalen = country_elem->datalen; country_data = kmemdup(country_elem->data, country_datalen, GFP_ATOMIC); rcu_read_unlock(); if (!country_data) return; regulatory_hint_country_ie(wdev->wiphy, cr->links[link].bss->channel->band, country_data, country_datalen); kfree(country_data); if (!wdev->u.client.ssid_len) { rcu_read_lock(); for_each_valid_link(cr, link) { ssid = ieee80211_bss_get_elem(cr->links[link].bss, WLAN_EID_SSID); if (!ssid || !ssid->datalen) continue; memcpy(wdev->u.client.ssid, ssid->data, ssid->datalen); wdev->u.client.ssid_len = ssid->datalen; break; } rcu_read_unlock(); } return; out: for_each_valid_link(cr, link) cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); } static void cfg80211_update_link_bss(struct wireless_dev *wdev, struct cfg80211_bss **bss) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_internal_bss *ibss; if (!*bss) return; ibss = bss_from_pub(*bss); if (list_empty(&ibss->list)) { struct cfg80211_bss *found = NULL, *tmp = *bss; found = cfg80211_get_bss(wdev->wiphy, NULL, (*bss)->bssid, wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (found) { /* The same BSS is already updated so use it * instead, as it has latest info. */ *bss = found; } else { /* Update with BSS provided by driver, it will * be freshly added and ref cnted, we can free * the old one. * * signal_valid can be false, as we are not * expecting the BSS to be found. * * keep the old timestamp to avoid confusion */ cfg80211_bss_update(rdev, ibss, false, ibss->ts); } cfg80211_put_bss(wdev->wiphy, tmp); } } /* Consumes bss object(s) one way or another */ void cfg80211_connect_done(struct net_device *dev, struct cfg80211_connect_resp_params *params, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; u8 *next; size_t link_info_size = 0; unsigned int link; for_each_valid_link(params, link) { cfg80211_update_link_bss(wdev, ¶ms->links[link].bss); link_info_size += params->links[link].bssid ? ETH_ALEN : 0; link_info_size += params->links[link].addr ? ETH_ALEN : 0; } ev = kzalloc(sizeof(*ev) + (params->ap_mld_addr ? ETH_ALEN : 0) + params->req_ie_len + params->resp_ie_len + params->fils.kek_len + params->fils.pmk_len + (params->fils.pmkid ? WLAN_PMKID_LEN : 0) + link_info_size, gfp); if (!ev) { for_each_valid_link(params, link) cfg80211_put_bss(wdev->wiphy, params->links[link].bss); return; } ev->type = EVENT_CONNECT_RESULT; next = ((u8 *)ev) + sizeof(*ev); if (params->ap_mld_addr) { ev->cr.ap_mld_addr = next; memcpy((void *)ev->cr.ap_mld_addr, params->ap_mld_addr, ETH_ALEN); next += ETH_ALEN; } if (params->req_ie_len) { ev->cr.req_ie = next; ev->cr.req_ie_len = params->req_ie_len; memcpy((void *)ev->cr.req_ie, params->req_ie, params->req_ie_len); next += params->req_ie_len; } if (params->resp_ie_len) { ev->cr.resp_ie = next; ev->cr.resp_ie_len = params->resp_ie_len; memcpy((void *)ev->cr.resp_ie, params->resp_ie, params->resp_ie_len); next += params->resp_ie_len; } if (params->fils.kek_len) { ev->cr.fils.kek = next; ev->cr.fils.kek_len = params->fils.kek_len; memcpy((void *)ev->cr.fils.kek, params->fils.kek, params->fils.kek_len); next += params->fils.kek_len; } if (params->fils.pmk_len) { ev->cr.fils.pmk = next; ev->cr.fils.pmk_len = params->fils.pmk_len; memcpy((void *)ev->cr.fils.pmk, params->fils.pmk, params->fils.pmk_len); next += params->fils.pmk_len; } if (params->fils.pmkid) { ev->cr.fils.pmkid = next; memcpy((void *)ev->cr.fils.pmkid, params->fils.pmkid, WLAN_PMKID_LEN); next += WLAN_PMKID_LEN; } ev->cr.fils.update_erp_next_seq_num = params->fils.update_erp_next_seq_num; if (params->fils.update_erp_next_seq_num) ev->cr.fils.erp_next_seq_num = params->fils.erp_next_seq_num; ev->cr.valid_links = params->valid_links; for_each_valid_link(params, link) { if (params->links[link].bss) cfg80211_hold_bss( bss_from_pub(params->links[link].bss)); ev->cr.links[link].bss = params->links[link].bss; if (params->links[link].addr) { ev->cr.links[link].addr = next; memcpy((void *)ev->cr.links[link].addr, params->links[link].addr, ETH_ALEN); next += ETH_ALEN; } if (params->links[link].bssid) { ev->cr.links[link].bssid = next; memcpy((void *)ev->cr.links[link].bssid, params->links[link].bssid, ETH_ALEN); next += ETH_ALEN; } } ev->cr.status = params->status; ev->cr.timeout_reason = params->timeout_reason; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_connect_done); /* Consumes bss object one way or another */ void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info) { #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif unsigned int link; const u8 *connected_addr; lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) goto out; if (WARN_ON(!wdev->connected)) goto out; if (info->valid_links) { if (WARN_ON(!info->ap_mld_addr)) goto out; for_each_valid_link(info, link) { if (WARN_ON(!info->links[link].addr)) goto out; } } cfg80211_wdev_release_bsses(wdev); for_each_valid_link(info, link) { if (WARN_ON(!info->links[link].bss)) goto out; } memset(wdev->links, 0, sizeof(wdev->links)); wdev->valid_links = info->valid_links; for_each_valid_link(info, link) { cfg80211_hold_bss(bss_from_pub(info->links[link].bss)); wdev->links[link].client.current_bss = bss_from_pub(info->links[link].bss); } connected_addr = info->valid_links ? info->ap_mld_addr : info->links[0].bss->bssid; ether_addr_copy(wdev->u.client.connected_addr, connected_addr); if (info->valid_links) { for_each_valid_link(info, link) memcpy(wdev->links[link].addr, info->links[link].addr, ETH_ALEN); } wdev->unprot_beacon_reported = 0; nl80211_send_roamed(wiphy_to_rdev(wdev->wiphy), wdev->netdev, info, GFP_KERNEL); #ifdef CONFIG_CFG80211_WEXT if (!info->valid_links) { if (info->req_ie) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = info->req_ie_len; wireless_send_event(wdev->netdev, IWEVASSOCREQIE, &wrqu, info->req_ie); } if (info->resp_ie) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = info->resp_ie_len; wireless_send_event(wdev->netdev, IWEVASSOCRESPIE, &wrqu, info->resp_ie); } memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; memcpy(wrqu.ap_addr.sa_data, connected_addr, ETH_ALEN); memcpy(wdev->wext.prev_bssid, connected_addr, ETH_ALEN); wdev->wext.prev_bssid_valid = true; wireless_send_event(wdev->netdev, SIOCGIWAP, &wrqu, NULL); } #endif return; out: for_each_valid_link(info, link) cfg80211_put_bss(wdev->wiphy, info->links[link].bss); } /* Consumes info->links.bss object(s) one way or another */ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; u8 *next; unsigned int link; size_t link_info_size = 0; bool bss_not_found = false; for_each_valid_link(info, link) { link_info_size += info->links[link].addr ? ETH_ALEN : 0; link_info_size += info->links[link].bssid ? ETH_ALEN : 0; if (info->links[link].bss) continue; info->links[link].bss = cfg80211_get_bss(wdev->wiphy, info->links[link].channel, info->links[link].bssid, wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (!info->links[link].bss) { bss_not_found = true; break; } } if (WARN_ON(bss_not_found)) goto out; ev = kzalloc(sizeof(*ev) + info->req_ie_len + info->resp_ie_len + info->fils.kek_len + info->fils.pmk_len + (info->fils.pmkid ? WLAN_PMKID_LEN : 0) + (info->ap_mld_addr ? ETH_ALEN : 0) + link_info_size, gfp); if (!ev) goto out; ev->type = EVENT_ROAMED; next = ((u8 *)ev) + sizeof(*ev); if (info->req_ie_len) { ev->rm.req_ie = next; ev->rm.req_ie_len = info->req_ie_len; memcpy((void *)ev->rm.req_ie, info->req_ie, info->req_ie_len); next += info->req_ie_len; } if (info->resp_ie_len) { ev->rm.resp_ie = next; ev->rm.resp_ie_len = info->resp_ie_len; memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); next += info->resp_ie_len; } if (info->fils.kek_len) { ev->rm.fils.kek = next; ev->rm.fils.kek_len = info->fils.kek_len; memcpy((void *)ev->rm.fils.kek, info->fils.kek, info->fils.kek_len); next += info->fils.kek_len; } if (info->fils.pmk_len) { ev->rm.fils.pmk = next; ev->rm.fils.pmk_len = info->fils.pmk_len; memcpy((void *)ev->rm.fils.pmk, info->fils.pmk, info->fils.pmk_len); next += info->fils.pmk_len; } if (info->fils.pmkid) { ev->rm.fils.pmkid = next; memcpy((void *)ev->rm.fils.pmkid, info->fils.pmkid, WLAN_PMKID_LEN); next += WLAN_PMKID_LEN; } ev->rm.fils.update_erp_next_seq_num = info->fils.update_erp_next_seq_num; if (info->fils.update_erp_next_seq_num) ev->rm.fils.erp_next_seq_num = info->fils.erp_next_seq_num; if (info->ap_mld_addr) { ev->rm.ap_mld_addr = next; memcpy((void *)ev->rm.ap_mld_addr, info->ap_mld_addr, ETH_ALEN); next += ETH_ALEN; } ev->rm.valid_links = info->valid_links; for_each_valid_link(info, link) { ev->rm.links[link].bss = info->links[link].bss; if (info->links[link].addr) { ev->rm.links[link].addr = next; memcpy((void *)ev->rm.links[link].addr, info->links[link].addr, ETH_ALEN); next += ETH_ALEN; } if (info->links[link].bssid) { ev->rm.links[link].bssid = next; memcpy((void *)ev->rm.links[link].bssid, info->links[link].bssid, ETH_ALEN); next += ETH_ALEN; } } spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); return; out: for_each_valid_link(info, link) cfg80211_put_bss(wdev->wiphy, info->links[link].bss); } EXPORT_SYMBOL(cfg80211_roamed); void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *peer_addr, const u8 *td_bitmap, u8 td_bitmap_len) { lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT && wdev->iftype != NL80211_IFTYPE_AP && wdev->iftype != NL80211_IFTYPE_P2P_GO)) return; if (wdev->iftype == NL80211_IFTYPE_STATION || wdev->iftype == NL80211_IFTYPE_P2P_CLIENT) { if (WARN_ON(!wdev->connected) || WARN_ON(!ether_addr_equal(wdev->u.client.connected_addr, peer_addr))) return; } nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, peer_addr, td_bitmap, td_bitmap_len); } void cfg80211_port_authorized(struct net_device *dev, const u8 *peer_addr, const u8 *td_bitmap, u8 td_bitmap_len, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; if (WARN_ON(!peer_addr)) return; ev = kzalloc(sizeof(*ev) + td_bitmap_len, gfp); if (!ev) return; ev->type = EVENT_PORT_AUTHORIZED; memcpy(ev->pa.peer_addr, peer_addr, ETH_ALEN); ev->pa.td_bitmap = ((u8 *)ev) + sizeof(*ev); ev->pa.td_bitmap_len = td_bitmap_len; memcpy((void *)ev->pa.td_bitmap, td_bitmap, td_bitmap_len); /* * Use the wdev event list so that if there are pending * connected/roamed events, they will be reported first. */ spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_port_authorized); void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, size_t ie_len, u16 reason, bool from_ap) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int i; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) return; cfg80211_wdev_release_bsses(wdev); wdev->valid_links = 0; wdev->connected = false; wdev->u.client.ssid_len = 0; wdev->conn_owner_nlportid = 0; kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); /* stop critical protocol if supported */ if (rdev->ops->crit_proto_stop && rdev->crit_proto_nlportid) { rdev->crit_proto_nlportid = 0; rdev_crit_proto_stop(rdev, wdev); } /* * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. */ if (rdev->ops->del_key) { int max_key_idx = 5; if (wiphy_ext_feature_isset( wdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION) || wiphy_ext_feature_isset( wdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT)) max_key_idx = 7; for (i = 0; i <= max_key_idx; i++) rdev_del_key(rdev, dev, -1, i, false, NULL); } rdev_set_qos_map(rdev, dev, NULL); #ifdef CONFIG_CFG80211_WEXT memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); wdev->wext.connect.ssid_len = 0; #endif schedule_work(&cfg80211_disconnect_work); cfg80211_schedule_channels_check(wdev); } void cfg80211_disconnected(struct net_device *dev, u16 reason, const u8 *ie, size_t ie_len, bool locally_generated, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; ev = kzalloc(sizeof(*ev) + ie_len, gfp); if (!ev) return; ev->type = EVENT_DISCONNECTED; ev->dc.ie = ((u8 *)ev) + sizeof(*ev); ev->dc.ie_len = ie_len; memcpy((void *)ev->dc.ie, ie, ie_len); ev->dc.reason = reason; ev->dc.locally_generated = locally_generated; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_disconnected); /* * API calls for nl80211/wext compatibility code */ int cfg80211_connect(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *connect, struct cfg80211_cached_keys *connkeys, const u8 *prev_bssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; lockdep_assert_wiphy(wdev->wiphy); /* * If we have an ssid_len, we're trying to connect or are * already connected, so reject a new SSID unless it's the * same (which is the case for re-association.) */ if (wdev->u.client.ssid_len && (wdev->u.client.ssid_len != connect->ssid_len || memcmp(wdev->u.client.ssid, connect->ssid, wdev->u.client.ssid_len))) return -EALREADY; /* * If connected, reject (re-)association unless prev_bssid * matches the current BSSID. */ if (wdev->connected) { if (!prev_bssid) return -EALREADY; if (!ether_addr_equal(prev_bssid, wdev->u.client.connected_addr)) return -ENOTCONN; } /* * Reject if we're in the process of connecting with WEP, * this case isn't very interesting and trying to handle * it would make the code much more complex. */ if (wdev->connect_keys) return -EINPROGRESS; cfg80211_oper_and_ht_capa(&connect->ht_capa_mask, rdev->wiphy.ht_capa_mod_mask); cfg80211_oper_and_vht_capa(&connect->vht_capa_mask, rdev->wiphy.vht_capa_mod_mask); if (connkeys && connkeys->def >= 0) { int idx; u32 cipher; idx = connkeys->def; cipher = connkeys->params[idx].cipher; /* If given a WEP key we may need it for shared key auth */ if (cipher == WLAN_CIPHER_SUITE_WEP40 || cipher == WLAN_CIPHER_SUITE_WEP104) { connect->key_idx = idx; connect->key = connkeys->params[idx].key; connect->key_len = connkeys->params[idx].key_len; /* * If ciphers are not set (e.g. when going through * iwconfig), we have to set them appropriately here. */ if (connect->crypto.cipher_group == 0) connect->crypto.cipher_group = cipher; if (connect->crypto.n_ciphers_pairwise == 0) { connect->crypto.n_ciphers_pairwise = 1; connect->crypto.ciphers_pairwise[0] = cipher; } } } else { if (WARN_ON(connkeys)) return -EINVAL; /* connect can point to wdev->wext.connect which * can hold key data from a previous connection */ connect->key = NULL; connect->key_len = 0; connect->key_idx = 0; } wdev->connect_keys = connkeys; memcpy(wdev->u.client.ssid, connect->ssid, connect->ssid_len); wdev->u.client.ssid_len = connect->ssid_len; wdev->conn_bss_type = connect->pbss ? IEEE80211_BSS_TYPE_PBSS : IEEE80211_BSS_TYPE_ESS; if (!rdev->ops->connect) err = cfg80211_sme_connect(wdev, connect, prev_bssid); else err = rdev_connect(rdev, dev, connect); if (err) { wdev->connect_keys = NULL; /* * This could be reassoc getting refused, don't clear * ssid_len in that case. */ if (!wdev->connected) wdev->u.client.ssid_len = 0; return err; } return 0; } int cfg80211_disconnect(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 reason, bool wextev) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err = 0; lockdep_assert_wiphy(wdev->wiphy); kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; wdev->conn_owner_nlportid = 0; if (wdev->conn) err = cfg80211_sme_disconnect(wdev, reason); else if (!rdev->ops->disconnect) cfg80211_mlme_down(rdev, dev); else if (wdev->u.client.ssid_len) err = rdev_disconnect(rdev, dev, reason); /* * Clear ssid_len unless we actually were fully connected, * in which case cfg80211_disconnected() will take care of * this later. */ if (!wdev->connected) wdev->u.client.ssid_len = 0; return err; } /* * Used to clean up after the connection / connection attempt owner socket * disconnects */ void cfg80211_autodisconnect_wk(struct work_struct *work) { struct wireless_dev *wdev = container_of(work, struct wireless_dev, disconnect_wk); struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); wiphy_lock(wdev->wiphy); if (wdev->conn_owner_nlportid) { switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, wdev->netdev, false); break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, wdev->netdev, -1, false); break; case NL80211_IFTYPE_MESH_POINT: cfg80211_leave_mesh(rdev, wdev->netdev); break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: /* * Use disconnect_bssid if still connecting and * ops->disconnect not implemented. Otherwise we can * use cfg80211_disconnect. */ if (rdev->ops->disconnect || wdev->connected) cfg80211_disconnect(rdev, wdev->netdev, WLAN_REASON_DEAUTH_LEAVING, true); else cfg80211_mlme_deauth(rdev, wdev->netdev, wdev->disconnect_bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); break; default: break; } } wiphy_unlock(wdev->wiphy); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/quotaops.h> #include <linux/uuid.h> #include "ext4.h" #include "xattr.h" #include "ext4_jbd2.h" static void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, const struct fscrypt_name *src) { memset(dst, 0, sizeof(*dst)); dst->usr_fname = src->usr_fname; dst->disk_name = src->disk_name; dst->hinfo.hash = src->hash; dst->hinfo.minor_hash = src->minor_hash; dst->crypto_buf = src->crypto_buf; } int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct ext4_filename *fname) { struct fscrypt_name name; int err; err = fscrypt_setup_filename(dir, iname, lookup, &name); if (err) return err; ext4_fname_from_fscrypt_name(fname, &name); #if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); if (err) ext4_fname_free_filename(fname); #endif return err; } int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, struct ext4_filename *fname) { struct fscrypt_name name; int err; err = fscrypt_prepare_lookup(dir, dentry, &name); if (err) return err; ext4_fname_from_fscrypt_name(fname, &name); #if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); if (err) ext4_fname_free_filename(fname); #endif return err; } void ext4_fname_free_filename(struct ext4_filename *fname) { struct fscrypt_name name; name.crypto_buf = fname->crypto_buf; fscrypt_free_filename(&name); fname->crypto_buf.name = NULL; fname->usr_fname = NULL; fname->disk_name.name = NULL; #if IS_ENABLED(CONFIG_UNICODE) kfree(fname->cf_name.name); fname->cf_name.name = NULL; #endif } static bool uuid_is_zero(__u8 u[16]) { int i; for (i = 0; i < 16; i++) if (u[i]) return false; return true; } int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg) { struct super_block *sb = file_inode(filp)->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); int err, err2; handle_t *handle; if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) { err = mnt_want_write_file(filp); if (err) return err; handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto pwsalt_err_exit; } err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh, EXT4_JTR_NONE); if (err) goto pwsalt_err_journal; lock_buffer(sbi->s_sbh); generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); ext4_superblock_csum_set(sb); unlock_buffer(sbi->s_sbh); err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); pwsalt_err_journal: err2 = ext4_journal_stop(handle); if (err2 && !err) err = err2; pwsalt_err_exit: mnt_drop_write_file(filp); if (err) return err; } if (copy_to_user(arg, sbi->s_es->s_encrypt_pw_salt, 16)) return -EFAULT; return 0; } static int ext4_get_context(struct inode *inode, void *ctx, size_t len) { return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len); } static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { handle_t *handle = fs_data; int res, res2, credits, retries = 0; /* * Encrypting the root directory is not allowed because e2fsck expects * lost+found to exist and be unencrypted, and encrypting the root * directory would imply encrypting the lost+found directory as well as * the filename "lost+found" itself. */ if (inode->i_ino == EXT4_ROOT_INO) return -EPERM; if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode))) return -EINVAL; if (ext4_test_inode_flag(inode, EXT4_INODE_DAX)) return -EOPNOTSUPP; res = ext4_convert_inline_data(inode); if (res) return res; /* * If a journal handle was specified, then the encryption context is * being set on a new inode via inheritance and is part of a larger * transaction to create the inode. Otherwise the encryption context is * being set on an existing inode in its own transaction. Only in the * latter case should the "retry on ENOSPC" logic be used. */ if (handle) { res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION, EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len, 0); if (!res) { ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); /* * Update inode->i_flags - S_ENCRYPTED will be enabled, * S_DAX may be disabled */ ext4_set_inode_flags(inode, false); } return res; } res = dquot_initialize(inode); if (res) return res; retry: res = ext4_xattr_set_credits(inode, len, false /* is_create */, &credits); if (res) return res; handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); if (IS_ERR(handle)) return PTR_ERR(handle); res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION, EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len, 0); if (!res) { ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); /* * Update inode->i_flags - S_ENCRYPTED will be enabled, * S_DAX may be disabled */ ext4_set_inode_flags(inode, false); res = ext4_mark_inode_dirty(handle, inode); if (res) EXT4_ERROR_INODE(inode, "Failed to mark inode dirty"); } res2 = ext4_journal_stop(handle); if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; if (!res) res = res2; return res; } static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb) { return EXT4_SB(sb)->s_dummy_enc_policy.policy; } static bool ext4_has_stable_inodes(struct super_block *sb) { return ext4_has_feature_stable_inodes(sb); } const struct fscrypt_operations ext4_cryptops = { .needs_bounce_pages = 1, .has_32bit_inodes = 1, .supports_subblock_data_units = 1, .legacy_key_prefix = "ext4:", .get_context = ext4_get_context, .set_context = ext4_set_context, .get_dummy_policy = ext4_get_dummy_policy, .empty_dir = ext4_empty_dir, .has_stable_inodes = ext4_has_stable_inodes, }; |
| 5 1 1 3 14 3 1 1 5 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 | // SPDX-License-Identifier: GPL-2.0-only /* * * Generic part shared by ipv4 and ipv6 backends. */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_fib.h> #define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \ NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF | \ NFTA_FIB_F_PRESENT) const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = { [NFTA_FIB_DREG] = { .type = NLA_U32 }, [NFTA_FIB_RESULT] = { .type = NLA_U32 }, [NFTA_FIB_FLAGS] = NLA_POLICY_MASK(NLA_BE32, NFTA_FIB_F_ALL), }; EXPORT_SYMBOL(nft_fib_policy); int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { const struct nft_fib *priv = nft_expr_priv(expr); unsigned int hooks; switch (priv->result) { case NFT_FIB_RESULT_OIF: case NFT_FIB_RESULT_OIFNAME: hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD); break; case NFT_FIB_RESULT_ADDRTYPE: if (priv->flags & NFTA_FIB_F_IIF) hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD); else if (priv->flags & NFTA_FIB_F_OIF) hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_FORWARD); else hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING); break; default: return -EINVAL; } return nft_chain_validate_hooks(ctx->chain, hooks); } EXPORT_SYMBOL_GPL(nft_fib_validate); int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_fib *priv = nft_expr_priv(expr); unsigned int len; int err; if (!tb[NFTA_FIB_DREG] || !tb[NFTA_FIB_RESULT] || !tb[NFTA_FIB_FLAGS]) return -EINVAL; priv->flags = ntohl(nla_get_be32(tb[NFTA_FIB_FLAGS])); if (priv->flags == 0) return -EINVAL; if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) == (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) return -EINVAL; if ((priv->flags & (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) == (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) return -EINVAL; if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) == 0) return -EINVAL; priv->result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT])); switch (priv->result) { case NFT_FIB_RESULT_OIF: if (priv->flags & NFTA_FIB_F_OIF) return -EINVAL; len = sizeof(int); break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_OIF) return -EINVAL; len = IFNAMSIZ; break; case NFT_FIB_RESULT_ADDRTYPE: len = sizeof(u32); break; default: return -EINVAL; } err = nft_parse_register_store(ctx, tb[NFTA_FIB_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, len); if (err < 0) return err; return 0; } EXPORT_SYMBOL_GPL(nft_fib_init); int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_fib *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_FIB_DREG, priv->dreg)) return -1; if (nla_put_be32(skb, NFTA_FIB_RESULT, htonl(priv->result))) return -1; if (nla_put_be32(skb, NFTA_FIB_FLAGS, htonl(priv->flags))) return -1; return 0; } EXPORT_SYMBOL_GPL(nft_fib_dump); void nft_fib_store_result(void *reg, const struct nft_fib *priv, const struct net_device *dev) { u32 *dreg = reg; int index; switch (priv->result) { case NFT_FIB_RESULT_OIF: index = dev ? dev->ifindex : 0; if (priv->flags & NFTA_FIB_F_PRESENT) nft_reg_store8(dreg, !!index); else *dreg = index; break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_PRESENT) nft_reg_store8(dreg, !!dev); else strscpy_pad(reg, dev ? dev->name : "", IFNAMSIZ); break; default: WARN_ON_ONCE(1); *dreg = 0; break; } } EXPORT_SYMBOL_GPL(nft_fib_store_result); bool nft_fib_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { const struct nft_fib *priv = nft_expr_priv(expr); unsigned int len = NFT_REG32_SIZE; const struct nft_fib *fib; switch (priv->result) { case NFT_FIB_RESULT_OIF: break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_PRESENT) len = NFT_REG32_SIZE; else len = IFNAMSIZ; break; case NFT_FIB_RESULT_ADDRTYPE: break; default: WARN_ON_ONCE(1); break; } if (!nft_reg_track_cmp(track, expr, priv->dreg)) { nft_reg_track_update(track, expr, priv->dreg, len); return false; } fib = nft_expr_priv(track->regs[priv->dreg].selector); if (priv->result != fib->result || priv->flags != fib->flags) { nft_reg_track_update(track, expr, priv->dreg, len); return false; } if (!track->regs[priv->dreg].bitwise) return true; return false; } EXPORT_SYMBOL_GPL(nft_fib_reduce); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Query routing table from nftables"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); |
| 3254 3458 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 | /* 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> /* * 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) || IS_ENABLED(CONFIG_IOMMUFD) 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; }; 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 */ |
| 5 3 3 1 2 7 1 6 7 1 4 3 3 3 1 3 3 3 3 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_mq.c Classful multiqueue dummy scheduler * * Copyright (c) 2009 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <net/netlink.h> #include <net/pkt_cls.h> #include <net/pkt_sched.h> #include <net/sch_generic.h> struct mq_sched { struct Qdisc **qdiscs; }; static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd) { struct net_device *dev = qdisc_dev(sch); struct tc_mq_qopt_offload opt = { .command = cmd, .handle = sch->handle, }; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt); } static int mq_offload_stats(struct Qdisc *sch) { struct tc_mq_qopt_offload opt = { .command = TC_MQ_STATS, .handle = sch->handle, .stats = { .bstats = &sch->bstats, .qstats = &sch->qstats, }, }; return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_MQ, &opt); } static void mq_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); unsigned int ntx; mq_offload(sch, TC_MQ_DESTROY); if (!priv->qdiscs) return; for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } static int mq_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); struct netdev_queue *dev_queue; struct Qdisc *qdisc; unsigned int ntx; if (sch->parent != TC_H_ROOT) return -EOPNOTSUPP; if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; /* pre-allocate qdiscs, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); if (!priv->qdiscs) return -ENOMEM; for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { dev_queue = netdev_get_tx_queue(dev, ntx); qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, ntx), TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(ntx + 1)), extack); if (!qdisc) return -ENOMEM; priv->qdiscs[ntx] = qdisc; qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } sch->flags |= TCQ_F_MQROOT; mq_offload(sch, TC_MQ_CREATE); return 0; } static void mq_attach(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); struct Qdisc *qdisc, *old; unsigned int ntx; for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) qdisc_put(old); #ifdef CONFIG_NET_SCHED if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); #endif } kfree(priv->qdiscs); priv->qdiscs = NULL; } static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct net_device *dev = qdisc_dev(sch); struct Qdisc *qdisc; unsigned int ntx; sch->q.qlen = 0; gnet_stats_basic_sync_init(&sch->bstats); memset(&sch->qstats, 0, sizeof(sch->qstats)); /* MQ supports lockless qdiscs. However, statistics accounting needs * to account for all, none, or a mix of locked and unlocked child * qdiscs. Percpu stats are added to counters in-band and locking * qdisc totals are added at end. */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping); spin_lock_bh(qdisc_lock(qdisc)); gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, &qdisc->bstats, false); gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats); sch->q.qlen += qdisc_qlen(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); } return mq_offload_stats(sch); } static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; return netdev_get_tx_queue(dev, ntx); } static struct netdev_queue *mq_select_queue(struct Qdisc *sch, struct tcmsg *tcm) { return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); } static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); struct tc_mq_qopt_offload graft_offload; struct net_device *dev = qdisc_dev(sch); if (dev->flags & IFF_UP) dev_deactivate(dev); *old = dev_graft_qdisc(dev_queue, new); if (new) new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); graft_offload.handle = sch->handle; graft_offload.graft_params.queue = cl - 1; graft_offload.graft_params.child_handle = new ? new->handle : 0; graft_offload.command = TC_MQ_GRAFT; qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old, TC_SETUP_QDISC_MQ, &graft_offload, extack); return 0; } static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long mq_find(struct Qdisc *sch, u32 classid) { unsigned int ntx = TC_H_MIN(classid); if (!mq_queue_get(sch, ntx)) return 0; return ntx; } static int mq_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; return 0; } static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); sch = rtnl_dereference(dev_queue->qdisc_sleeping); if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; } static void mq_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct net_device *dev = qdisc_dev(sch); unsigned int ntx; if (arg->stop) return; arg->count = arg->skip; for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { if (!tc_qdisc_stats_dump(sch, ntx + 1, arg)) break; } } static const struct Qdisc_class_ops mq_class_ops = { .select_queue = mq_select_queue, .graft = mq_graft, .leaf = mq_leaf, .find = mq_find, .walk = mq_walk, .dump = mq_dump_class, .dump_stats = mq_dump_class_stats, }; struct Qdisc_ops mq_qdisc_ops __read_mostly = { .cl_ops = &mq_class_ops, .id = "mq", .priv_size = sizeof(struct mq_sched), .init = mq_init, .destroy = mq_destroy, .attach = mq_attach, .change_real_num_tx = mq_change_real_num_tx, .dump = mq_dump, .owner = THIS_MODULE, }; |
| 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 7 1 1 16 16 9 2 9 9 9 16 10 1 7 7 7 1 7 7 5 8 20 20 20 20 3 3 3 3 7 7 7 7 2 2 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 | /* * llc_conn.c - Driver routines for connection component. * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/init.h> #include <linux/slab.h> #include <net/llc.h> #include <net/llc_c_ac.h> #include <net/llc_c_ev.h> #include <net/llc_c_st.h> #include <net/llc_conn.h> #include <net/llc_pdu.h> #include <net/llc_sap.h> #include <net/sock.h> #include <net/tcp_states.h> #if 0 #define dprintk(args...) printk(KERN_DEBUG args) #else #define dprintk(args...) #endif static int llc_find_offset(int state, int ev_type); static void llc_conn_send_pdus(struct sock *sk); static int llc_conn_service(struct sock *sk, struct sk_buff *skb); static int llc_exec_conn_trans_actions(struct sock *sk, struct llc_conn_state_trans *trans, struct sk_buff *ev); static struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk, struct sk_buff *skb); /* Offset table on connection states transition diagram */ static int llc_offset_table[NBR_CONN_STATES][NBR_CONN_EV]; int sysctl_llc2_ack_timeout = LLC2_ACK_TIME * HZ; int sysctl_llc2_p_timeout = LLC2_P_TIME * HZ; int sysctl_llc2_rej_timeout = LLC2_REJ_TIME * HZ; int sysctl_llc2_busy_timeout = LLC2_BUSY_TIME * HZ; /** * llc_conn_state_process - sends event to connection state machine * @sk: connection * @skb: occurred event * * Sends an event to connection state machine. After processing event * (executing it's actions and changing state), upper layer will be * indicated or confirmed, if needed. Returns 0 for success, 1 for * failure. The socket lock has to be held before calling this function. * * This function always consumes a reference to the skb. */ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) { int rc; struct llc_sock *llc = llc_sk(skb->sk); struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->ind_prim = ev->cfm_prim = 0; /* * Send event to state machine */ rc = llc_conn_service(skb->sk, skb); if (unlikely(rc != 0)) { printk(KERN_ERR "%s: llc_conn_service failed\n", __func__); goto out_skb_put; } switch (ev->ind_prim) { case LLC_DATA_PRIM: skb_get(skb); llc_save_primitive(sk, skb, LLC_DATA_PRIM); if (unlikely(sock_queue_rcv_skb(sk, skb))) { /* * shouldn't happen */ printk(KERN_ERR "%s: sock_queue_rcv_skb failed!\n", __func__); kfree_skb(skb); } break; case LLC_CONN_PRIM: /* * Can't be sock_queue_rcv_skb, because we have to leave the * skb->sk pointing to the newly created struct sock in * llc_conn_handler. -acme */ skb_get(skb); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_state_change(sk); break; case LLC_DISC_PRIM: sock_hold(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_ESTABLISHED) { sk->sk_shutdown = SHUTDOWN_MASK; sk->sk_socket->state = SS_UNCONNECTED; sk->sk_state = TCP_CLOSE; if (!sock_flag(sk, SOCK_DEAD)) { sock_set_flag(sk, SOCK_DEAD); sk->sk_state_change(sk); } } sock_put(sk); break; case LLC_RESET_PRIM: /* * FIXME: * RESET is not being notified to upper layers for now */ printk(KERN_INFO "%s: received a reset ind!\n", __func__); break; default: if (ev->ind_prim) printk(KERN_INFO "%s: received unknown %d prim!\n", __func__, ev->ind_prim); /* No indication */ break; } switch (ev->cfm_prim) { case LLC_DATA_PRIM: if (!llc_data_accept_state(llc->state)) sk->sk_write_space(sk); else rc = llc->failed_data_req = 1; break; case LLC_CONN_PRIM: if (sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_SYN_SENT) { if (ev->status) { sk->sk_socket->state = SS_UNCONNECTED; sk->sk_state = TCP_CLOSE; } else { sk->sk_socket->state = SS_CONNECTED; sk->sk_state = TCP_ESTABLISHED; } sk->sk_state_change(sk); } break; case LLC_DISC_PRIM: sock_hold(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_CLOSING) { sk->sk_socket->state = SS_UNCONNECTED; sk->sk_state = TCP_CLOSE; sk->sk_state_change(sk); } sock_put(sk); break; case LLC_RESET_PRIM: /* * FIXME: * RESET is not being notified to upper layers for now */ printk(KERN_INFO "%s: received a reset conf!\n", __func__); break; default: if (ev->cfm_prim) printk(KERN_INFO "%s: received unknown %d prim!\n", __func__, ev->cfm_prim); /* No confirmation */ break; } out_skb_put: kfree_skb(skb); return rc; } void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) { /* queue PDU to send to MAC layer */ skb_queue_tail(&sk->sk_write_queue, skb); llc_conn_send_pdus(sk); } /** * llc_conn_rtn_pdu - sends received data pdu to upper layer * @sk: Active connection * @skb: Received data frame * * Sends received data pdu to upper layer (by using indicate function). * Prepares service parameters (prim and prim_data). calling indication * function will be done in llc_conn_state_process. */ void llc_conn_rtn_pdu(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->ind_prim = LLC_DATA_PRIM; } /** * llc_conn_resend_i_pdu_as_cmd - resend all all unacknowledged I PDUs * @sk: active connection * @nr: NR * @first_p_bit: p_bit value of first pdu * * Resend all unacknowledged I PDUs, starting with the NR; send first as * command PDU with P bit equal first_p_bit; if more than one send * subsequent as command PDUs with P bit equal zero (0). */ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit) { struct sk_buff *skb; struct llc_pdu_sn *pdu; u16 nbr_unack_pdus; struct llc_sock *llc; u8 howmany_resend = 0; llc_conn_remove_acked_pdus(sk, nr, &nbr_unack_pdus); if (!nbr_unack_pdus) goto out; /* * Process unack PDUs only if unack queue is not empty; remove * appropriate PDUs, fix them up, and put them on mac_pdu_q. */ llc = llc_sk(sk); while ((skb = skb_dequeue(&llc->pdu_unack_q)) != NULL) { pdu = llc_pdu_sn_hdr(skb); llc_pdu_set_cmd_rsp(skb, LLC_PDU_CMD); llc_pdu_set_pf_bit(skb, first_p_bit); skb_queue_tail(&sk->sk_write_queue, skb); first_p_bit = 0; llc->vS = LLC_I_GET_NS(pdu); howmany_resend++; } if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ llc_conn_send_pdus(sk); out:; } /** * llc_conn_resend_i_pdu_as_rsp - Resend all unacknowledged I PDUs * @sk: active connection. * @nr: NR * @first_f_bit: f_bit value of first pdu. * * Resend all unacknowledged I PDUs, starting with the NR; send first as * response PDU with F bit equal first_f_bit; if more than one send * subsequent as response PDUs with F bit equal zero (0). */ void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit) { struct sk_buff *skb; u16 nbr_unack_pdus; struct llc_sock *llc = llc_sk(sk); u8 howmany_resend = 0; llc_conn_remove_acked_pdus(sk, nr, &nbr_unack_pdus); if (!nbr_unack_pdus) goto out; /* * Process unack PDUs only if unack queue is not empty; remove * appropriate PDUs, fix them up, and put them on mac_pdu_q */ while ((skb = skb_dequeue(&llc->pdu_unack_q)) != NULL) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); llc_pdu_set_cmd_rsp(skb, LLC_PDU_RSP); llc_pdu_set_pf_bit(skb, first_f_bit); skb_queue_tail(&sk->sk_write_queue, skb); first_f_bit = 0; llc->vS = LLC_I_GET_NS(pdu); howmany_resend++; } if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ llc_conn_send_pdus(sk); out:; } /** * llc_conn_remove_acked_pdus - Removes acknowledged pdus from tx queue * @sk: active connection * @nr: NR * @how_many_unacked: size of pdu_unack_q after removing acked pdus * * Removes acknowledged pdus from transmit queue (pdu_unack_q). Returns * the number of pdus that removed from queue. */ int llc_conn_remove_acked_pdus(struct sock *sk, u8 nr, u16 *how_many_unacked) { int pdu_pos, i; struct sk_buff *skb; struct llc_pdu_sn *pdu; int nbr_acked = 0; struct llc_sock *llc = llc_sk(sk); int q_len = skb_queue_len(&llc->pdu_unack_q); if (!q_len) goto out; skb = skb_peek(&llc->pdu_unack_q); pdu = llc_pdu_sn_hdr(skb); /* finding position of last acked pdu in queue */ pdu_pos = ((int)LLC_2_SEQ_NBR_MODULO + (int)nr - (int)LLC_I_GET_NS(pdu)) % LLC_2_SEQ_NBR_MODULO; for (i = 0; i < pdu_pos && i < q_len; i++) { skb = skb_dequeue(&llc->pdu_unack_q); kfree_skb(skb); nbr_acked++; } out: *how_many_unacked = skb_queue_len(&llc->pdu_unack_q); return nbr_acked; } /** * llc_conn_send_pdus - Sends queued PDUs * @sk: active connection * * Sends queued pdus to MAC layer for transmission. */ static void llc_conn_send_pdus(struct sock *sk) { struct sk_buff *skb; while ((skb = skb_dequeue(&sk->sk_write_queue)) != NULL) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); if (LLC_PDU_TYPE_IS_I(pdu) && !(skb->dev->flags & IFF_LOOPBACK)) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); skb_queue_tail(&llc_sk(sk)->pdu_unack_q, skb); if (!skb2) break; skb = skb2; } dev_queue_xmit(skb); } } /** * llc_conn_service - finds transition and changes state of connection * @sk: connection * @skb: happened event * * This function finds transition that matches with happened event, then * executes related actions and finally changes state of connection. * Returns 0 for success, 1 for failure. */ static int llc_conn_service(struct sock *sk, struct sk_buff *skb) { int rc = 1; struct llc_sock *llc = llc_sk(sk); struct llc_conn_state_trans *trans; if (llc->state > NBR_CONN_STATES) goto out; rc = 0; trans = llc_qualify_conn_ev(sk, skb); if (trans) { rc = llc_exec_conn_trans_actions(sk, trans, skb); if (!rc && trans->next_state != NO_STATE_CHANGE) { llc->state = trans->next_state; if (!llc_data_accept_state(llc->state)) sk->sk_state_change(sk); } } out: return rc; } /** * llc_qualify_conn_ev - finds transition for event * @sk: connection * @skb: happened event * * This function finds transition that matches with happened event. * Returns pointer to found transition on success, %NULL otherwise. */ static struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_trans **next_trans; const llc_conn_ev_qfyr_t *next_qualifier; struct llc_conn_state_ev *ev = llc_conn_ev(skb); struct llc_sock *llc = llc_sk(sk); struct llc_conn_state *curr_state = &llc_conn_state_table[llc->state - 1]; /* search thru events for this state until * list exhausted or until no more */ for (next_trans = curr_state->transitions + llc_find_offset(llc->state - 1, ev->type); (*next_trans)->ev; next_trans++) { if (!((*next_trans)->ev)(sk, skb)) { /* got POSSIBLE event match; the event may require * qualification based on the values of a number of * state flags; if all qualifications are met (i.e., * if all qualifying functions return success, or 0, * then this is THE event we're looking for */ for (next_qualifier = (*next_trans)->ev_qualifiers; next_qualifier && *next_qualifier && !(*next_qualifier)(sk, skb); next_qualifier++) /* nothing */; if (!next_qualifier || !*next_qualifier) /* all qualifiers executed successfully; this is * our transition; return it so we can perform * the associated actions & change the state */ return *next_trans; } } return NULL; } /** * llc_exec_conn_trans_actions - executes related actions * @sk: connection * @trans: transition that it's actions must be performed * @skb: event * * Executes actions that is related to happened event. Returns 0 for * success, 1 to indicate failure of at least one action. */ static int llc_exec_conn_trans_actions(struct sock *sk, struct llc_conn_state_trans *trans, struct sk_buff *skb) { int rc = 0; const llc_conn_action_t *next_action; for (next_action = trans->ev_actions; next_action && *next_action; next_action++) { int rc2 = (*next_action)(sk, skb); if (rc2 == 2) { rc = rc2; break; } else if (rc2) rc = 1; } return rc; } static inline bool llc_estab_match(const struct llc_sap *sap, const struct llc_addr *daddr, const struct llc_addr *laddr, const struct sock *sk, const struct net *net) { struct llc_sock *llc = llc_sk(sk); return net_eq(sock_net(sk), net) && llc->laddr.lsap == laddr->lsap && llc->daddr.lsap == daddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac) && ether_addr_equal(llc->daddr.mac, daddr->mac); } /** * __llc_lookup_established - Finds connection for the remote/local sap/mac * @sap: SAP * @daddr: address of remote LLC (MAC + SAP) * @laddr: address of local LLC (MAC + SAP) * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection using the remote * mac, remote sap, local mac, and local sap. Returns pointer for * connection found, %NULL otherwise. * Caller has to make sure local_bh is disabled. */ static struct sock *__llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, struct llc_addr *laddr, const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; int slot = llc_sk_laddr_hashfn(sap, laddr); struct hlist_nulls_head *laddr_hb = &sap->sk_laddr_hash[slot]; rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_estab_match(sap, daddr, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_estab_match(sap, daddr, laddr, rc, net))) { sock_put(rc); continue; } goto found; } } rc = NULL; /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (unlikely(get_nulls_value(node) != slot)) goto again; found: rcu_read_unlock(); return rc; } struct sock *llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, struct llc_addr *laddr, const struct net *net) { struct sock *sk; local_bh_disable(); sk = __llc_lookup_established(sap, daddr, laddr, net); local_bh_enable(); return sk; } static inline bool llc_listener_match(const struct llc_sap *sap, const struct llc_addr *laddr, const struct sock *sk, const struct net *net) { struct llc_sock *llc = llc_sk(sk); return net_eq(sock_net(sk), net) && sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && llc->laddr.lsap == laddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac); } static struct sock *__llc_lookup_listener(struct llc_sap *sap, struct llc_addr *laddr, const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; int slot = llc_sk_laddr_hashfn(sap, laddr); struct hlist_nulls_head *laddr_hb = &sap->sk_laddr_hash[slot]; rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_listener_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_listener_match(sap, laddr, rc, net))) { sock_put(rc); continue; } goto found; } } rc = NULL; /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (unlikely(get_nulls_value(node) != slot)) goto again; found: rcu_read_unlock(); return rc; } /** * llc_lookup_listener - Finds listener for local MAC + SAP * @sap: SAP * @laddr: address of local LLC (MAC + SAP) * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection listening on * local mac, and local sap. Returns pointer for parent socket found, * %NULL otherwise. * Caller has to make sure local_bh is disabled. */ static struct sock *llc_lookup_listener(struct llc_sap *sap, struct llc_addr *laddr, const struct net *net) { struct sock *rc = __llc_lookup_listener(sap, laddr, net); static struct llc_addr null_addr; if (!rc) rc = __llc_lookup_listener(sap, &null_addr, net); return rc; } static struct sock *__llc_lookup(struct llc_sap *sap, struct llc_addr *daddr, struct llc_addr *laddr, const struct net *net) { struct sock *sk = __llc_lookup_established(sap, daddr, laddr, net); return sk ? : llc_lookup_listener(sap, laddr, net); } /** * llc_data_accept_state - designates if in this state data can be sent. * @state: state of connection. * * Returns 0 if data can be sent, 1 otherwise. */ u8 llc_data_accept_state(u8 state) { return state != LLC_CONN_STATE_NORMAL && state != LLC_CONN_STATE_BUSY && state != LLC_CONN_STATE_REJ; } /** * llc_find_next_offset - finds offset for next category of transitions * @state: state table. * @offset: start offset. * * Finds offset of next category of transitions in transition table. * Returns the start index of next category. */ static u16 __init llc_find_next_offset(struct llc_conn_state *state, u16 offset) { u16 cnt = 0; struct llc_conn_state_trans **next_trans; for (next_trans = state->transitions + offset; (*next_trans)->ev; next_trans++) ++cnt; return cnt; } /** * llc_build_offset_table - builds offset table of connection * * Fills offset table of connection state transition table * (llc_offset_table). */ void __init llc_build_offset_table(void) { struct llc_conn_state *curr_state; int state, ev_type, next_offset; for (state = 0; state < NBR_CONN_STATES; state++) { curr_state = &llc_conn_state_table[state]; next_offset = 0; for (ev_type = 0; ev_type < NBR_CONN_EV; ev_type++) { llc_offset_table[state][ev_type] = next_offset; next_offset += llc_find_next_offset(curr_state, next_offset) + 1; } } } /** * llc_find_offset - finds start offset of category of transitions * @state: state of connection * @ev_type: type of happened event * * Finds start offset of desired category of transitions. Returns the * desired start offset. */ static int llc_find_offset(int state, int ev_type) { int rc = 0; /* at this stage, llc_offset_table[..][2] is not important. it is for * init_pf_cycle and I don't know what is it. */ switch (ev_type) { case LLC_CONN_EV_TYPE_PRIM: rc = llc_offset_table[state][0]; break; case LLC_CONN_EV_TYPE_PDU: rc = llc_offset_table[state][4]; break; case LLC_CONN_EV_TYPE_SIMPLE: rc = llc_offset_table[state][1]; break; case LLC_CONN_EV_TYPE_P_TMR: case LLC_CONN_EV_TYPE_ACK_TMR: case LLC_CONN_EV_TYPE_REJ_TMR: case LLC_CONN_EV_TYPE_BUSY_TMR: rc = llc_offset_table[state][3]; break; } return rc; } /** * llc_sap_add_socket - adds a socket to a SAP * @sap: SAP * @sk: socket * * This function adds a socket to the hash tables of a SAP. */ void llc_sap_add_socket(struct llc_sap *sap, struct sock *sk) { struct llc_sock *llc = llc_sk(sk); struct hlist_head *dev_hb = llc_sk_dev_hash(sap, llc->dev->ifindex); struct hlist_nulls_head *laddr_hb = llc_sk_laddr_hash(sap, &llc->laddr); llc_sap_hold(sap); llc_sk(sk)->sap = sap; spin_lock_bh(&sap->sk_lock); sock_set_flag(sk, SOCK_RCU_FREE); sap->sk_count++; sk_nulls_add_node_rcu(sk, laddr_hb); hlist_add_head(&llc->dev_hash_node, dev_hb); spin_unlock_bh(&sap->sk_lock); } /** * llc_sap_remove_socket - removes a socket from SAP * @sap: SAP * @sk: socket * * This function removes a connection from the hash tables of a SAP if * the connection was in this list. */ void llc_sap_remove_socket(struct llc_sap *sap, struct sock *sk) { struct llc_sock *llc = llc_sk(sk); spin_lock_bh(&sap->sk_lock); sk_nulls_del_node_init_rcu(sk); hlist_del(&llc->dev_hash_node); sap->sk_count--; spin_unlock_bh(&sap->sk_lock); llc_sap_put(sap); } /** * llc_conn_rcv - sends received pdus to the connection state machine * @sk: current connection structure. * @skb: received frame. * * Sends received pdus to the connection state machine. */ static int llc_conn_rcv(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->type = LLC_CONN_EV_TYPE_PDU; ev->reason = 0; return llc_conn_state_process(sk, skb); } static struct sock *llc_create_incoming_sock(struct sock *sk, struct net_device *dev, struct llc_addr *saddr, struct llc_addr *daddr) { struct sock *newsk = llc_sk_alloc(sock_net(sk), sk->sk_family, GFP_ATOMIC, sk->sk_prot, 0); struct llc_sock *newllc, *llc = llc_sk(sk); if (!newsk) goto out; newllc = llc_sk(newsk); memcpy(&newllc->laddr, daddr, sizeof(newllc->laddr)); memcpy(&newllc->daddr, saddr, sizeof(newllc->daddr)); newllc->dev = dev; dev_hold(dev); llc_sap_add_socket(llc->sap, newsk); llc_sap_hold(llc->sap); out: return newsk; } void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) { struct llc_addr saddr, daddr; struct sock *sk; llc_pdu_decode_sa(skb, saddr.mac); llc_pdu_decode_ssap(skb, &saddr.lsap); llc_pdu_decode_da(skb, daddr.mac); llc_pdu_decode_dsap(skb, &daddr.lsap); sk = __llc_lookup(sap, &saddr, &daddr, dev_net(skb->dev)); if (!sk) goto drop; bh_lock_sock(sk); /* * This has to be done here and not at the upper layer ->accept * method because of the way the PROCOM state machine works: * it needs to set several state variables (see, for instance, * llc_adm_actions_2 in net/llc/llc_c_st.c) and send a packet to * the originator of the new connection, and this state has to be * in the newly created struct sock private area. -acme */ if (unlikely(sk->sk_state == TCP_LISTEN)) { struct sock *newsk = llc_create_incoming_sock(sk, skb->dev, &saddr, &daddr); if (!newsk) goto drop_unlock; skb_set_owner_r(skb, newsk); } else { /* * Can't be skb_set_owner_r, this will be done at the * llc_conn_state_process function, later on, when we will use * skb_queue_rcv_skb to send it to upper layers, this is * another trick required to cope with how the PROCOM state * machine works. -acme */ skb_orphan(skb); sock_hold(sk); skb->sk = sk; skb->destructor = sock_efree; } if (!sock_owned_by_user(sk)) llc_conn_rcv(sk, skb); else { dprintk("%s: adding to backlog...\n", __func__); llc_set_backlog_type(skb, LLC_PACKET); if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) goto drop_unlock; } out: bh_unlock_sock(sk); sock_put(sk); return; drop: kfree_skb(skb); return; drop_unlock: kfree_skb(skb); goto out; } #undef LLC_REFCNT_DEBUG #ifdef LLC_REFCNT_DEBUG static atomic_t llc_sock_nr; #endif /** * llc_backlog_rcv - Processes rx frames and expired timers. * @sk: LLC sock (p8022 connection) * @skb: queued rx frame or event * * This function processes frames that has received and timers that has * expired during sending an I pdu (refer to data_req_handler). frames * queue by llc_rcv function (llc_mac.c) and timers queue by timer * callback functions(llc_c_ac.c). */ static int llc_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int rc = 0; struct llc_sock *llc = llc_sk(sk); if (likely(llc_backlog_type(skb) == LLC_PACKET)) { if (likely(llc->state > 1)) /* not closed */ rc = llc_conn_rcv(sk, skb); else goto out_kfree_skb; } else if (llc_backlog_type(skb) == LLC_EVENT) { /* timer expiration event */ if (likely(llc->state > 1)) /* not closed */ rc = llc_conn_state_process(sk, skb); else goto out_kfree_skb; } else { printk(KERN_ERR "%s: invalid skb in backlog\n", __func__); goto out_kfree_skb; } out: return rc; out_kfree_skb: kfree_skb(skb); goto out; } /** * llc_sk_init - Initializes a socket with default llc values. * @sk: socket to initialize. * * Initializes a socket with default llc values. */ static void llc_sk_init(struct sock *sk) { struct llc_sock *llc = llc_sk(sk); llc->state = LLC_CONN_STATE_ADM; llc->inc_cntr = llc->dec_cntr = 2; llc->dec_step = llc->connect_step = 1; timer_setup(&llc->ack_timer.timer, llc_conn_ack_tmr_cb, 0); llc->ack_timer.expire = sysctl_llc2_ack_timeout; timer_setup(&llc->pf_cycle_timer.timer, llc_conn_pf_cycle_tmr_cb, 0); llc->pf_cycle_timer.expire = sysctl_llc2_p_timeout; timer_setup(&llc->rej_sent_timer.timer, llc_conn_rej_tmr_cb, 0); llc->rej_sent_timer.expire = sysctl_llc2_rej_timeout; timer_setup(&llc->busy_state_timer.timer, llc_conn_busy_tmr_cb, 0); llc->busy_state_timer.expire = sysctl_llc2_busy_timeout; llc->n2 = 2; /* max retransmit */ llc->k = 2; /* tx win size, will adjust dynam */ llc->rw = 128; /* rx win size (opt and equal to * tx_win of remote LLC) */ skb_queue_head_init(&llc->pdu_unack_q); sk->sk_backlog_rcv = llc_backlog_rcv; } /** * llc_sk_alloc - Allocates LLC sock * @net: network namespace * @family: upper layer protocol family * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * @prot: struct proto associated with this new sock instance * @kern: is this to be a kernel socket? * * Allocates a LLC sock and initializes it. Returns the new LLC sock * or %NULL if there's no memory available for one */ struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern) { struct sock *sk = sk_alloc(net, family, priority, prot, kern); if (!sk) goto out; llc_sk_init(sk); sock_init_data(NULL, sk); #ifdef LLC_REFCNT_DEBUG atomic_inc(&llc_sock_nr); printk(KERN_DEBUG "LLC socket %p created in %s, now we have %d alive\n", sk, __func__, atomic_read(&llc_sock_nr)); #endif out: return sk; } void llc_sk_stop_all_timers(struct sock *sk, bool sync) { struct llc_sock *llc = llc_sk(sk); if (sync) { del_timer_sync(&llc->pf_cycle_timer.timer); del_timer_sync(&llc->ack_timer.timer); del_timer_sync(&llc->rej_sent_timer.timer); del_timer_sync(&llc->busy_state_timer.timer); } else { del_timer(&llc->pf_cycle_timer.timer); del_timer(&llc->ack_timer.timer); del_timer(&llc->rej_sent_timer.timer); del_timer(&llc->busy_state_timer.timer); } llc->ack_must_be_send = 0; llc->ack_pf = 0; } /** * llc_sk_free - Frees a LLC socket * @sk: - socket to free * * Frees a LLC socket */ void llc_sk_free(struct sock *sk) { struct llc_sock *llc = llc_sk(sk); llc->state = LLC_CONN_OUT_OF_SVC; /* Stop all (possibly) running timers */ llc_sk_stop_all_timers(sk, true); #ifdef DEBUG_LLC_CONN_ALLOC printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__, skb_queue_len(&llc->pdu_unack_q), skb_queue_len(&sk->sk_write_queue)); #endif skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); skb_queue_purge(&llc->pdu_unack_q); #ifdef LLC_REFCNT_DEBUG if (refcount_read(&sk->sk_refcnt) != 1) { printk(KERN_DEBUG "Destruction of LLC sock %p delayed in %s, cnt=%d\n", sk, __func__, refcount_read(&sk->sk_refcnt)); printk(KERN_DEBUG "%d LLC sockets are still alive\n", atomic_read(&llc_sock_nr)); } else { atomic_dec(&llc_sock_nr); printk(KERN_DEBUG "LLC socket %p released in %s, %d are still alive\n", sk, __func__, atomic_read(&llc_sock_nr)); } #endif sock_put(sk); } /** * llc_sk_reset - resets a connection * @sk: LLC socket to reset * * Resets a connection to the out of service state. Stops its timers * and frees any frames in the queues of the connection. */ void llc_sk_reset(struct sock *sk) { struct llc_sock *llc = llc_sk(sk); llc_conn_ac_stop_all_timers(sk, NULL); skb_queue_purge(&sk->sk_write_queue); skb_queue_purge(&llc->pdu_unack_q); llc->remote_busy_flag = 0; llc->cause_flag = 0; llc->retry_count = 0; llc_conn_set_p_flag(sk, 0); llc->f_flag = 0; llc->s_flag = 0; llc->ack_pf = 0; llc->first_pdu_Ns = 0; llc->ack_must_be_send = 0; llc->dec_step = 1; llc->inc_cntr = 2; llc->dec_cntr = 2; llc->X = 0; llc->failed_data_req = 0 ; llc->last_nr = 0; } |
| 15588 106 11 11 21 50 1051 1073 45 35 2 3 21 10 124 463 19 17 61 1113 3344 2090 873 943 2265 217 222 2 7 3 9 184 162 19 3 4 452 3 542 11 107 11503 641 19 5 10 56 644 553 42 872 838 155 146 14860 1881 58 53 2101 4133 144 10574 1 11723 1323 944 29 1234 60 100 28 1 1 1 101 13 29 16 4 31 16 48 270 23 2 101 15 2 40 19 4 52 9 358 717 10 7036 132 1180 130 3217 2018 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Linux Security Module Hook declarations. * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2001 James Morris <jmorris@intercode.com.au> * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) * Copyright (C) 2015 Intel Corporation. * Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com> * Copyright (C) 2016 Mellanox Techonologies * Copyright (C) 2020 Google LLC. */ /* * The macro LSM_HOOK is used to define the data structures required by * the LSM framework using the pattern: * * LSM_HOOK(<return_type>, <default_value>, <hook_name>, args...) * * struct security_hook_heads { * #define LSM_HOOK(RET, DEFAULT, NAME, ...) struct hlist_head NAME; * #include <linux/lsm_hook_defs.h> * #undef LSM_HOOK * }; */ LSM_HOOK(int, 0, binder_set_context_mgr, const struct cred *mgr) LSM_HOOK(int, 0, binder_transaction, const struct cred *from, const struct cred *to) LSM_HOOK(int, 0, binder_transfer_binder, const struct cred *from, const struct cred *to) LSM_HOOK(int, 0, binder_transfer_file, const struct cred *from, const struct cred *to, const struct file *file) LSM_HOOK(int, 0, ptrace_access_check, struct task_struct *child, unsigned int mode) LSM_HOOK(int, 0, ptrace_traceme, struct task_struct *parent) LSM_HOOK(int, 0, capget, const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) LSM_HOOK(int, 0, capset, struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) LSM_HOOK(int, 0, capable, const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) LSM_HOOK(int, 0, quotactl, int cmds, int type, int id, const struct super_block *sb) LSM_HOOK(int, 0, quota_on, struct dentry *dentry) LSM_HOOK(int, 0, syslog, int type) LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) LSM_HOOK(int, 1, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, const struct file *file) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, const struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, const struct linux_binprm *bprm) LSM_HOOK(int, 0, fs_context_submount, struct fs_context *fc, struct super_block *reference) LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, struct fs_context *src_sc) LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc, struct fs_parameter *param) LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_delete, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_mnt_opts, void *mnt_opts) LSM_HOOK(int, 0, sb_eat_lsm_opts, char *orig, void **mnt_opts) LSM_HOOK(int, 0, sb_mnt_opts_compat, struct super_block *sb, void *mnt_opts) LSM_HOOK(int, 0, sb_remount, struct super_block *sb, void *mnt_opts) LSM_HOOK(int, 0, sb_kern_mount, const struct super_block *sb) LSM_HOOK(int, 0, sb_show_options, struct seq_file *m, struct super_block *sb) LSM_HOOK(int, 0, sb_statfs, struct dentry *dentry) LSM_HOOK(int, 0, sb_mount, const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) LSM_HOOK(int, 0, sb_umount, struct vfsmount *mnt, int flags) LSM_HOOK(int, 0, sb_pivotroot, const struct path *old_path, const struct path *new_path) LSM_HOOK(int, 0, sb_set_mnt_opts, struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) LSM_HOOK(int, 0, sb_clone_mnt_opts, const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) #ifdef CONFIG_SECURITY_PATH LSM_HOOK(int, 0, path_unlink, const struct path *dir, struct dentry *dentry) LSM_HOOK(int, 0, path_mkdir, const struct path *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(int, 0, path_rmdir, const struct path *dir, struct dentry *dentry) LSM_HOOK(int, 0, path_mknod, const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) LSM_HOOK(void, LSM_RET_VOID, path_post_mknod, struct mnt_idmap *idmap, struct dentry *dentry) LSM_HOOK(int, 0, path_truncate, const struct path *path) LSM_HOOK(int, 0, path_symlink, const struct path *dir, struct dentry *dentry, const char *old_name) LSM_HOOK(int, 0, path_link, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) LSM_HOOK(int, 0, path_rename, const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, unsigned int flags) LSM_HOOK(int, 0, path_chmod, const struct path *path, umode_t mode) LSM_HOOK(int, 0, path_chown, const struct path *path, kuid_t uid, kgid_t gid) LSM_HOOK(int, 0, path_chroot, const struct path *path) #endif /* CONFIG_SECURITY_PATH */ /* Needed for inode based security check */ LSM_HOOK(int, 0, path_notify, const struct path *path, u64 mask, unsigned int obj_type) LSM_HOOK(int, 0, inode_alloc_security, struct inode *inode) LSM_HOOK(void, LSM_RET_VOID, inode_free_security, struct inode *inode) LSM_HOOK(int, -EOPNOTSUPP, inode_init_security, struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) LSM_HOOK(int, 0, inode_init_security_anon, struct inode *inode, const struct qstr *name, const struct inode *context_inode) LSM_HOOK(int, 0, inode_create, struct inode *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(void, LSM_RET_VOID, inode_post_create_tmpfile, struct mnt_idmap *idmap, struct inode *inode) LSM_HOOK(int, 0, inode_link, struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) LSM_HOOK(int, 0, inode_unlink, struct inode *dir, struct dentry *dentry) LSM_HOOK(int, 0, inode_symlink, struct inode *dir, struct dentry *dentry, const char *old_name) LSM_HOOK(int, 0, inode_mkdir, struct inode *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(int, 0, inode_rmdir, struct inode *dir, struct dentry *dentry) LSM_HOOK(int, 0, inode_mknod, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) LSM_HOOK(int, 0, inode_rename, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) LSM_HOOK(int, 0, inode_readlink, struct dentry *dentry) LSM_HOOK(int, 0, inode_follow_link, struct dentry *dentry, struct inode *inode, bool rcu) LSM_HOOK(int, 0, inode_permission, struct inode *inode, int mask) LSM_HOOK(int, 0, inode_setattr, struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) LSM_HOOK(void, LSM_RET_VOID, inode_post_setattr, struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) LSM_HOOK(int, 0, inode_getattr, const struct path *path) LSM_HOOK(int, 0, inode_setxattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(void, LSM_RET_VOID, inode_post_setxattr, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_getxattr, struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_listxattr, struct dentry *dentry) LSM_HOOK(int, 0, inode_removexattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name) LSM_HOOK(void, LSM_RET_VOID, inode_post_removexattr, struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_set_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) LSM_HOOK(void, LSM_RET_VOID, inode_post_set_acl, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) LSM_HOOK(int, 0, inode_get_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(int, 0, inode_remove_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(void, LSM_RET_VOID, inode_post_remove_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(int, 0, inode_need_killpriv, struct dentry *dentry) LSM_HOOK(int, 0, inode_killpriv, struct mnt_idmap *idmap, struct dentry *dentry) LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, size_t buffer_size) LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, struct dentry *src, const char *name) LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, struct kernfs_node *kn) LSM_HOOK(int, 0, file_permission, struct file *file, int mask) LSM_HOOK(int, 0, file_alloc_security, struct file *file) LSM_HOOK(void, LSM_RET_VOID, file_release, struct file *file) LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file) LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd, unsigned long arg) LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd, unsigned long arg) LSM_HOOK(int, 0, mmap_addr, unsigned long addr) LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) LSM_HOOK(int, 0, file_mprotect, struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) LSM_HOOK(int, 0, file_lock, struct file *file, unsigned int cmd) LSM_HOOK(int, 0, file_fcntl, struct file *file, unsigned int cmd, unsigned long arg) LSM_HOOK(void, LSM_RET_VOID, file_set_fowner, struct file *file) LSM_HOOK(int, 0, file_send_sigiotask, struct task_struct *tsk, struct fown_struct *fown, int sig) LSM_HOOK(int, 0, file_receive, struct file *file) LSM_HOOK(int, 0, file_open, struct file *file) LSM_HOOK(int, 0, file_post_open, struct file *file, int mask) LSM_HOOK(int, 0, file_truncate, struct file *file) LSM_HOOK(int, 0, task_alloc, struct task_struct *task, unsigned long clone_flags) LSM_HOOK(void, LSM_RET_VOID, task_free, struct task_struct *task) LSM_HOOK(int, 0, cred_alloc_blank, struct cred *cred, gfp_t gfp) LSM_HOOK(void, LSM_RET_VOID, cred_free, struct cred *cred) LSM_HOOK(int, 0, cred_prepare, struct cred *new, const struct cred *old, gfp_t gfp) LSM_HOOK(void, LSM_RET_VOID, cred_transfer, struct cred *new, const struct cred *old) LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid) LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid) LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode) LSM_HOOK(int, 0, kernel_module_request, char *kmod_name) LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents) LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size, enum kernel_load_data_id id, char *description) LSM_HOOK(int, 0, kernel_read_file, struct file *file, enum kernel_read_file_id id, bool contents) LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) LSM_HOOK(int, 0, task_fix_setuid, struct cred *new, const struct cred *old, int flags) LSM_HOOK(int, 0, task_fix_setgid, struct cred *new, const struct cred * old, int flags) LSM_HOOK(int, 0, task_fix_setgroups, struct cred *new, const struct cred * old) LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) LSM_HOOK(int, 0, task_getsid, struct task_struct *p) LSM_HOOK(void, LSM_RET_VOID, current_getsecid_subj, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, task_getsecid_obj, struct task_struct *p, u32 *secid) LSM_HOOK(int, 0, task_setnice, struct task_struct *p, int nice) LSM_HOOK(int, 0, task_setioprio, struct task_struct *p, int ioprio) LSM_HOOK(int, 0, task_getioprio, struct task_struct *p) LSM_HOOK(int, 0, task_prlimit, const struct cred *cred, const struct cred *tcred, unsigned int flags) LSM_HOOK(int, 0, task_setrlimit, struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) LSM_HOOK(int, 0, task_setscheduler, struct task_struct *p) LSM_HOOK(int, 0, task_getscheduler, struct task_struct *p) LSM_HOOK(int, 0, task_movememory, struct task_struct *p) LSM_HOOK(int, 0, task_kill, struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) LSM_HOOK(int, -ENOSYS, task_prctl, int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p, struct inode *inode) LSM_HOOK(int, 0, userns_create, const struct cred *cred) LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag) LSM_HOOK(void, LSM_RET_VOID, ipc_getsecid, struct kern_ipc_perm *ipcp, u32 *secid) LSM_HOOK(int, 0, msg_msg_alloc_security, struct msg_msg *msg) LSM_HOOK(void, LSM_RET_VOID, msg_msg_free_security, struct msg_msg *msg) LSM_HOOK(int, 0, msg_queue_alloc_security, struct kern_ipc_perm *perm) LSM_HOOK(void, LSM_RET_VOID, msg_queue_free_security, struct kern_ipc_perm *perm) LSM_HOOK(int, 0, msg_queue_associate, struct kern_ipc_perm *perm, int msqflg) LSM_HOOK(int, 0, msg_queue_msgctl, struct kern_ipc_perm *perm, int cmd) LSM_HOOK(int, 0, msg_queue_msgsnd, struct kern_ipc_perm *perm, struct msg_msg *msg, int msqflg) LSM_HOOK(int, 0, msg_queue_msgrcv, struct kern_ipc_perm *perm, struct msg_msg *msg, struct task_struct *target, long type, int mode) LSM_HOOK(int, 0, shm_alloc_security, struct kern_ipc_perm *perm) LSM_HOOK(void, LSM_RET_VOID, shm_free_security, struct kern_ipc_perm *perm) LSM_HOOK(int, 0, shm_associate, struct kern_ipc_perm *perm, int shmflg) LSM_HOOK(int, 0, shm_shmctl, struct kern_ipc_perm *perm, int cmd) LSM_HOOK(int, 0, shm_shmat, struct kern_ipc_perm *perm, char __user *shmaddr, int shmflg) LSM_HOOK(int, 0, sem_alloc_security, struct kern_ipc_perm *perm) LSM_HOOK(void, LSM_RET_VOID, sem_free_security, struct kern_ipc_perm *perm) LSM_HOOK(int, 0, sem_associate, struct kern_ipc_perm *perm, int semflg) LSM_HOOK(int, 0, sem_semctl, struct kern_ipc_perm *perm, int cmd) LSM_HOOK(int, 0, sem_semop, struct kern_ipc_perm *perm, struct sembuf *sops, unsigned nsops, int alter) LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb) LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry, struct inode *inode) LSM_HOOK(int, -EOPNOTSUPP, getselfattr, unsigned int attr, struct lsm_ctx __user *ctx, u32 *size, u32 flags) LSM_HOOK(int, -EOPNOTSUPP, setselfattr, unsigned int attr, struct lsm_ctx *ctx, u32 size, u32 flags) LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata, u32 *seclen) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode) LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen) LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen) LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, void **ctx, u32 *ctxlen) #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) LSM_HOOK(int, 0, post_notification, const struct cred *w_cred, const struct cred *cred, struct watch_notification *n) #endif /* CONFIG_SECURITY && CONFIG_WATCH_QUEUE */ #if defined(CONFIG_SECURITY) && defined(CONFIG_KEY_NOTIFICATIONS) LSM_HOOK(int, 0, watch_key, struct key *key) #endif /* CONFIG_SECURITY && CONFIG_KEY_NOTIFICATIONS */ #ifdef CONFIG_SECURITY_NETWORK LSM_HOOK(int, 0, unix_stream_connect, struct sock *sock, struct sock *other, struct sock *newsk) LSM_HOOK(int, 0, unix_may_send, struct socket *sock, struct socket *other) LSM_HOOK(int, 0, socket_create, int family, int type, int protocol, int kern) LSM_HOOK(int, 0, socket_post_create, struct socket *sock, int family, int type, int protocol, int kern) LSM_HOOK(int, 0, socket_socketpair, struct socket *socka, struct socket *sockb) LSM_HOOK(int, 0, socket_bind, struct socket *sock, struct sockaddr *address, int addrlen) LSM_HOOK(int, 0, socket_connect, struct socket *sock, struct sockaddr *address, int addrlen) LSM_HOOK(int, 0, socket_listen, struct socket *sock, int backlog) LSM_HOOK(int, 0, socket_accept, struct socket *sock, struct socket *newsock) LSM_HOOK(int, 0, socket_sendmsg, struct socket *sock, struct msghdr *msg, int size) LSM_HOOK(int, 0, socket_recvmsg, struct socket *sock, struct msghdr *msg, int size, int flags) LSM_HOOK(int, 0, socket_getsockname, struct socket *sock) LSM_HOOK(int, 0, socket_getpeername, struct socket *sock) LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how) LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb) LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock, struct sk_buff *skb, u32 *secid) LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority) LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk) LSM_HOOK(void, LSM_RET_VOID, sk_clone_security, const struct sock *sk, struct sock *newsk) LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, const struct sock *sk, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, sock_graft, struct sock *sk, struct socket *parent) LSM_HOOK(int, 0, inet_conn_request, const struct sock *sk, struct sk_buff *skb, struct request_sock *req) LSM_HOOK(void, LSM_RET_VOID, inet_csk_clone, struct sock *newsk, const struct request_sock *req) LSM_HOOK(void, LSM_RET_VOID, inet_conn_established, struct sock *sk, struct sk_buff *skb) LSM_HOOK(int, 0, secmark_relabel_packet, u32 secid) LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_inc, void) LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_dec, void) LSM_HOOK(void, LSM_RET_VOID, req_classify_flow, const struct request_sock *req, struct flowi_common *flic) LSM_HOOK(int, 0, tun_dev_alloc_security, void **security) LSM_HOOK(void, LSM_RET_VOID, tun_dev_free_security, void *security) LSM_HOOK(int, 0, tun_dev_create, void) LSM_HOOK(int, 0, tun_dev_attach_queue, void *security) LSM_HOOK(int, 0, tun_dev_attach, struct sock *sk, void *security) LSM_HOOK(int, 0, tun_dev_open, void *security) LSM_HOOK(int, 0, sctp_assoc_request, struct sctp_association *asoc, struct sk_buff *skb) LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) LSM_HOOK(int, 0, sctp_assoc_established, struct sctp_association *asoc, struct sk_buff *skb) LSM_HOOK(int, 0, mptcp_add_subflow, struct sock *sk, struct sock *ssk) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK(int, 0, ib_pkey_access, void *sec, u64 subnet_prefix, u16 pkey) LSM_HOOK(int, 0, ib_endport_manage_subnet, void *sec, const char *dev_name, u8 port_num) LSM_HOOK(int, 0, ib_alloc_security, void **sec) LSM_HOOK(void, LSM_RET_VOID, ib_free_security, void *sec) #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK(int, 0, xfrm_policy_alloc_security, struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp) LSM_HOOK(int, 0, xfrm_policy_clone_security, struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctx) LSM_HOOK(void, LSM_RET_VOID, xfrm_policy_free_security, struct xfrm_sec_ctx *ctx) LSM_HOOK(int, 0, xfrm_policy_delete_security, struct xfrm_sec_ctx *ctx) LSM_HOOK(int, 0, xfrm_state_alloc, struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) LSM_HOOK(int, 0, xfrm_state_alloc_acquire, struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) LSM_HOOK(void, LSM_RET_VOID, xfrm_state_free_security, struct xfrm_state *x) LSM_HOOK(int, 0, xfrm_state_delete_security, struct xfrm_state *x) LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid) LSM_HOOK(int, 1, xfrm_state_pol_flow_match, struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid, int ckall) #endif /* CONFIG_SECURITY_NETWORK_XFRM */ /* key management security hooks */ #ifdef CONFIG_KEYS LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, unsigned long flags) LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key) LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **buffer) LSM_HOOK(void, LSM_RET_VOID, key_post_create_or_update, struct key *keyring, struct key *key, const void *payload, size_t payload_len, unsigned long flags, bool create) #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp) LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule) LSM_HOOK(int, 0, audit_rule_match, u32 secid, u32 field, u32 op, void *lsmrule) LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size) LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token) LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, struct path *path) LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token) LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd) LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) #ifdef CONFIG_PERF_EVENTS LSM_HOOK(int, 0, perf_event_open, struct perf_event_attr *attr, int type) LSM_HOOK(int, 0, perf_event_alloc, struct perf_event *event) LSM_HOOK(void, LSM_RET_VOID, perf_event_free, struct perf_event *event) LSM_HOOK(int, 0, perf_event_read, struct perf_event *event) LSM_HOOK(int, 0, perf_event_write, struct perf_event *event) #endif /* CONFIG_PERF_EVENTS */ #ifdef CONFIG_IO_URING LSM_HOOK(int, 0, uring_override_creds, const struct cred *new) LSM_HOOK(int, 0, uring_sqpoll, void) LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd) #endif /* CONFIG_IO_URING */ |
| 11 11 11 4 4 4 1 4 3 1 1 1 2 3 2 2 2 8 8 6 1 2 3 3 1 2 1 2 5 3 1 15 3 3 5 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 | // SPDX-License-Identifier: GPL-2.0-or-later /* * taskstats.c - Export per-task statistics to userland * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 * (C) Balbir Singh, IBM Corp. 2006 */ #include <linux/kernel.h> #include <linux/taskstats_kern.h> #include <linux/tsacct_kern.h> #include <linux/acct.h> #include <linux/delayacct.h> #include <linux/cpumask.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/cgroupstats.h> #include <linux/cgroup.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/pid_namespace.h> #include <net/genetlink.h> #include <linux/atomic.h> #include <linux/sched/cputime.h> /* * Maximum length of a cpumask that can be specified in * the TASKSTATS_CMD_ATTR_REGISTER/DEREGISTER_CPUMASK attribute */ #define TASKSTATS_CPUMASK_MAXLEN (100+6*NR_CPUS) static DEFINE_PER_CPU(__u32, taskstats_seqnum); static int family_registered; struct kmem_cache *taskstats_cache; static struct genl_family family; static const struct nla_policy taskstats_cmd_get_policy[] = { [TASKSTATS_CMD_ATTR_PID] = { .type = NLA_U32 }, [TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 }, [TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING }, [TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },}; static const struct nla_policy cgroupstats_cmd_get_policy[] = { [CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 }, }; struct listener { struct list_head list; pid_t pid; char valid; }; struct listener_list { struct rw_semaphore sem; struct list_head list; }; static DEFINE_PER_CPU(struct listener_list, listener_array); enum actions { REGISTER, DEREGISTER, CPU_DONT_CARE }; static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, size_t size) { struct sk_buff *skb; void *reply; /* * If new attributes are added, please revisit this allocation */ skb = genlmsg_new(size, GFP_KERNEL); if (!skb) return -ENOMEM; if (!info) { int seq = this_cpu_inc_return(taskstats_seqnum) - 1; reply = genlmsg_put(skb, 0, seq, &family, 0, cmd); } else reply = genlmsg_put_reply(skb, info, &family, 0, cmd); if (reply == NULL) { nlmsg_free(skb); return -EINVAL; } *skbp = skb; return 0; } /* * Send taskstats data in @skb to listener with nl_pid @pid */ static int send_reply(struct sk_buff *skb, struct genl_info *info) { struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); void *reply = genlmsg_data(genlhdr); genlmsg_end(skb, reply); return genlmsg_reply(skb, info); } /* * Send taskstats data in @skb to listeners registered for @cpu's exit data */ static void send_cpu_listeners(struct sk_buff *skb, struct listener_list *listeners) { struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); struct listener *s, *tmp; struct sk_buff *skb_next, *skb_cur = skb; void *reply = genlmsg_data(genlhdr); int delcount = 0; genlmsg_end(skb, reply); down_read(&listeners->sem); list_for_each_entry(s, &listeners->list, list) { int rc; skb_next = NULL; if (!list_is_last(&s->list, &listeners->list)) { skb_next = skb_clone(skb_cur, GFP_KERNEL); if (!skb_next) break; } rc = genlmsg_unicast(&init_net, skb_cur, s->pid); if (rc == -ECONNREFUSED) { s->valid = 0; delcount++; } skb_cur = skb_next; } up_read(&listeners->sem); if (skb_cur) nlmsg_free(skb_cur); if (!delcount) return; /* Delete invalidated entries */ down_write(&listeners->sem); list_for_each_entry_safe(s, tmp, &listeners->list, list) { if (!s->valid) { list_del(&s->list); kfree(s); } } up_write(&listeners->sem); } static void exe_add_tsk(struct taskstats *stats, struct task_struct *tsk) { /* No idea if I'm allowed to access that here, now. */ struct file *exe_file = get_task_exe_file(tsk); if (exe_file) { /* Following cp_new_stat64() in stat.c . */ stats->ac_exe_dev = huge_encode_dev(exe_file->f_inode->i_sb->s_dev); stats->ac_exe_inode = exe_file->f_inode->i_ino; fput(exe_file); } else { stats->ac_exe_dev = 0; stats->ac_exe_inode = 0; } } static void fill_stats(struct user_namespace *user_ns, struct pid_namespace *pid_ns, struct task_struct *tsk, struct taskstats *stats) { memset(stats, 0, sizeof(*stats)); /* * Each accounting subsystem adds calls to its functions to * fill in relevant parts of struct taskstsats as follows * * per-task-foo(stats, tsk); */ delayacct_add_tsk(stats, tsk); /* fill in basic acct fields */ stats->version = TASKSTATS_VERSION; stats->nvcsw = tsk->nvcsw; stats->nivcsw = tsk->nivcsw; bacct_add_tsk(user_ns, pid_ns, stats, tsk); /* fill in extended acct fields */ xacct_add_tsk(stats, tsk); /* add executable info */ exe_add_tsk(stats, tsk); } static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) { struct task_struct *tsk; tsk = find_get_task_by_vpid(pid); if (!tsk) return -ESRCH; fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats); put_task_struct(tsk); return 0; } static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) { struct task_struct *tsk, *first; unsigned long flags; int rc = -ESRCH; u64 delta, utime, stime; u64 start_time; /* * Add additional stats from live tasks except zombie thread group * leaders who are already counted with the dead tasks */ rcu_read_lock(); first = find_task_by_vpid(tgid); if (!first || !lock_task_sighand(first, &flags)) goto out; if (first->signal->stats) memcpy(stats, first->signal->stats, sizeof(*stats)); else memset(stats, 0, sizeof(*stats)); start_time = ktime_get_ns(); for_each_thread(first, tsk) { if (tsk->exit_state) continue; /* * Accounting subsystem can call its functions here to * fill in relevant parts of struct taskstsats as follows * * per-task-foo(stats, tsk); */ delayacct_add_tsk(stats, tsk); /* calculate task elapsed time in nsec */ delta = start_time - tsk->start_time; /* Convert to micro seconds */ do_div(delta, NSEC_PER_USEC); stats->ac_etime += delta; task_cputime(tsk, &utime, &stime); stats->ac_utime += div_u64(utime, NSEC_PER_USEC); stats->ac_stime += div_u64(stime, NSEC_PER_USEC); stats->nvcsw += tsk->nvcsw; stats->nivcsw += tsk->nivcsw; } unlock_task_sighand(first, &flags); rc = 0; out: rcu_read_unlock(); stats->version = TASKSTATS_VERSION; /* * Accounting subsystems can also add calls here to modify * fields of taskstats. */ return rc; } static void fill_tgid_exit(struct task_struct *tsk) { unsigned long flags; spin_lock_irqsave(&tsk->sighand->siglock, flags); if (!tsk->signal->stats) goto ret; /* * Each accounting subsystem calls its functions here to * accumalate its per-task stats for tsk, into the per-tgid structure * * per-task-foo(tsk->signal->stats, tsk); */ delayacct_add_tsk(tsk->signal->stats, tsk); ret: spin_unlock_irqrestore(&tsk->sighand->siglock, flags); return; } static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) { struct listener_list *listeners; struct listener *s, *tmp, *s2; unsigned int cpu; int ret = 0; if (!cpumask_subset(mask, cpu_possible_mask)) return -EINVAL; if (current_user_ns() != &init_user_ns) return -EINVAL; if (task_active_pid_ns(current) != &init_pid_ns) return -EINVAL; if (isadd == REGISTER) { for_each_cpu(cpu, mask) { s = kmalloc_node(sizeof(struct listener), GFP_KERNEL, cpu_to_node(cpu)); if (!s) { ret = -ENOMEM; goto cleanup; } s->pid = pid; s->valid = 1; listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); list_for_each_entry(s2, &listeners->list, list) { if (s2->pid == pid && s2->valid) goto exists; } list_add(&s->list, &listeners->list); s = NULL; exists: up_write(&listeners->sem); kfree(s); /* nop if NULL */ } return 0; } /* Deregister or cleanup */ cleanup: for_each_cpu(cpu, mask) { listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); list_for_each_entry_safe(s, tmp, &listeners->list, list) { if (s->pid == pid) { list_del(&s->list); kfree(s); break; } } up_write(&listeners->sem); } return ret; } static int parse(struct nlattr *na, struct cpumask *mask) { char *data; int len; int ret; if (na == NULL) return 1; len = nla_len(na); if (len > TASKSTATS_CPUMASK_MAXLEN) return -E2BIG; if (len < 1) return -EINVAL; data = kmalloc(len, GFP_KERNEL); if (!data) return -ENOMEM; nla_strscpy(data, na, len); ret = cpulist_parse(data, mask); kfree(data); return ret; } static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) { struct nlattr *na, *ret; int aggr; aggr = (type == TASKSTATS_TYPE_PID) ? TASKSTATS_TYPE_AGGR_PID : TASKSTATS_TYPE_AGGR_TGID; na = nla_nest_start_noflag(skb, aggr); if (!na) goto err; if (nla_put(skb, type, sizeof(pid), &pid) < 0) { nla_nest_cancel(skb, na); goto err; } ret = nla_reserve_64bit(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats), TASKSTATS_TYPE_NULL); if (!ret) { nla_nest_cancel(skb, na); goto err; } nla_nest_end(skb, na); return nla_data(ret); err: return NULL; } static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) { int rc = 0; struct sk_buff *rep_skb; struct cgroupstats *stats; struct nlattr *na; size_t size; u32 fd; struct fd f; na = info->attrs[CGROUPSTATS_CMD_ATTR_FD]; if (!na) return -EINVAL; fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]); f = fdget(fd); if (!f.file) return 0; size = nla_total_size(sizeof(struct cgroupstats)); rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) goto err; na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS, sizeof(struct cgroupstats)); if (na == NULL) { nlmsg_free(rep_skb); rc = -EMSGSIZE; goto err; } stats = nla_data(na); memset(stats, 0, sizeof(*stats)); rc = cgroupstats_build(stats, f.file->f_path.dentry); if (rc < 0) { nlmsg_free(rep_skb); goto err; } rc = send_reply(rep_skb, info); err: fdput(f); return rc; } static int cmd_attr_register_cpumask(struct genl_info *info) { cpumask_var_t mask; int rc; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask); if (rc < 0) goto out; rc = add_del_listener(info->snd_portid, mask, REGISTER); out: free_cpumask_var(mask); return rc; } static int cmd_attr_deregister_cpumask(struct genl_info *info) { cpumask_var_t mask; int rc; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask); if (rc < 0) goto out; rc = add_del_listener(info->snd_portid, mask, DEREGISTER); out: free_cpumask_var(mask); return rc; } static size_t taskstats_packet_size(void) { size_t size; size = nla_total_size(sizeof(u32)) + nla_total_size_64bit(sizeof(struct taskstats)) + nla_total_size(0); return size; } static int cmd_attr_pid(struct genl_info *info) { struct taskstats *stats; struct sk_buff *rep_skb; size_t size; u32 pid; int rc; size = taskstats_packet_size(); rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return rc; rc = -EINVAL; pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]); stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid); if (!stats) goto err; rc = fill_stats_for_pid(pid, stats); if (rc < 0) goto err; return send_reply(rep_skb, info); err: nlmsg_free(rep_skb); return rc; } static int cmd_attr_tgid(struct genl_info *info) { struct taskstats *stats; struct sk_buff *rep_skb; size_t size; u32 tgid; int rc; size = taskstats_packet_size(); rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return rc; rc = -EINVAL; tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]); stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid); if (!stats) goto err; rc = fill_stats_for_tgid(tgid, stats); if (rc < 0) goto err; return send_reply(rep_skb, info); err: nlmsg_free(rep_skb); return rc; } static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) { if (info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK]) return cmd_attr_register_cpumask(info); else if (info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK]) return cmd_attr_deregister_cpumask(info); else if (info->attrs[TASKSTATS_CMD_ATTR_PID]) return cmd_attr_pid(info); else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) return cmd_attr_tgid(info); else return -EINVAL; } static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct taskstats *stats_new, *stats; /* Pairs with smp_store_release() below. */ stats = smp_load_acquire(&sig->stats); if (stats || thread_group_empty(tsk)) return stats; /* No problem if kmem_cache_zalloc() fails */ stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); spin_lock_irq(&tsk->sighand->siglock); stats = sig->stats; if (!stats) { /* * Pairs with smp_store_release() above and order the * kmem_cache_zalloc(). */ smp_store_release(&sig->stats, stats_new); stats = stats_new; stats_new = NULL; } spin_unlock_irq(&tsk->sighand->siglock); if (stats_new) kmem_cache_free(taskstats_cache, stats_new); return stats; } /* Send pid data out on exit */ void taskstats_exit(struct task_struct *tsk, int group_dead) { int rc; struct listener_list *listeners; struct taskstats *stats; struct sk_buff *rep_skb; size_t size; int is_thread_group; if (!family_registered) return; /* * Size includes space for nested attributes */ size = taskstats_packet_size(); is_thread_group = !!taskstats_tgid_alloc(tsk); if (is_thread_group) { /* PID + STATS + TGID + STATS */ size = 2 * size; /* fill the tsk->signal->stats structure */ fill_tgid_exit(tsk); } listeners = raw_cpu_ptr(&listener_array); if (list_empty(&listeners->list)) return; rc = prepare_reply(NULL, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return; stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, task_pid_nr_ns(tsk, &init_pid_ns)); if (!stats) goto err; fill_stats(&init_user_ns, &init_pid_ns, tsk, stats); if (group_dead) stats->ac_flag |= AGROUP; /* * Doesn't matter if tsk is the leader or the last group member leaving */ if (!is_thread_group || !group_dead) goto send; stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, task_tgid_nr_ns(tsk, &init_pid_ns)); if (!stats) goto err; memcpy(stats, tsk->signal->stats, sizeof(*stats)); send: send_cpu_listeners(rep_skb, listeners); return; err: nlmsg_free(rep_skb); } static const struct genl_ops taskstats_ops[] = { { .cmd = TASKSTATS_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = taskstats_user_cmd, .policy = taskstats_cmd_get_policy, .maxattr = ARRAY_SIZE(taskstats_cmd_get_policy) - 1, .flags = GENL_ADMIN_PERM, }, { .cmd = CGROUPSTATS_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = cgroupstats_user_cmd, .policy = cgroupstats_cmd_get_policy, .maxattr = ARRAY_SIZE(cgroupstats_cmd_get_policy) - 1, }, }; static struct genl_family family __ro_after_init = { .name = TASKSTATS_GENL_NAME, .version = TASKSTATS_GENL_VERSION, .module = THIS_MODULE, .ops = taskstats_ops, .n_ops = ARRAY_SIZE(taskstats_ops), .resv_start_op = CGROUPSTATS_CMD_GET + 1, .netnsok = true, }; /* Needed early in initialization */ void __init taskstats_init_early(void) { unsigned int i; taskstats_cache = KMEM_CACHE(taskstats, SLAB_PANIC); for_each_possible_cpu(i) { INIT_LIST_HEAD(&(per_cpu(listener_array, i).list)); init_rwsem(&(per_cpu(listener_array, i).sem)); } } static int __init taskstats_init(void) { int rc; rc = genl_register_family(&family); if (rc) return rc; family_registered = 1; pr_info("registered taskstats version %d\n", TASKSTATS_GENL_VERSION); return 0; } /* * late initcall ensures initialization of statistics collection * mechanisms precedes initialization of the taskstats interface */ late_initcall(taskstats_init); |
| 2 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * drivers/net/bond/bond_options.h - bonding options * Copyright (c) 2013 Nikolay Aleksandrov <nikolay@redhat.com> */ #ifndef _NET_BOND_OPTIONS_H #define _NET_BOND_OPTIONS_H #include <linux/bits.h> #include <linux/limits.h> #include <linux/types.h> #include <linux/string.h> struct netlink_ext_ack; struct nlattr; #define BOND_OPT_MAX_NAMELEN 32 #define BOND_OPT_VALID(opt) ((opt) < BOND_OPT_LAST) #define BOND_MODE_ALL_EX(x) (~(x)) /* Option flags: * BOND_OPTFLAG_NOSLAVES - check if the bond device is empty before setting * BOND_OPTFLAG_IFDOWN - check if the bond device is down before setting * BOND_OPTFLAG_RAWVAL - the option parses the value itself */ enum { BOND_OPTFLAG_NOSLAVES = BIT(0), BOND_OPTFLAG_IFDOWN = BIT(1), BOND_OPTFLAG_RAWVAL = BIT(2) }; /* Value type flags: * BOND_VALFLAG_DEFAULT - mark the value as default * BOND_VALFLAG_(MIN|MAX) - mark the value as min/max */ enum { BOND_VALFLAG_DEFAULT = BIT(0), BOND_VALFLAG_MIN = BIT(1), BOND_VALFLAG_MAX = BIT(2) }; /* Option IDs, their bit positions correspond to their IDs */ enum { BOND_OPT_MODE, BOND_OPT_PACKETS_PER_SLAVE, BOND_OPT_XMIT_HASH, BOND_OPT_ARP_VALIDATE, BOND_OPT_ARP_ALL_TARGETS, BOND_OPT_FAIL_OVER_MAC, BOND_OPT_ARP_INTERVAL, BOND_OPT_ARP_TARGETS, BOND_OPT_DOWNDELAY, BOND_OPT_UPDELAY, BOND_OPT_LACP_RATE, BOND_OPT_MINLINKS, BOND_OPT_AD_SELECT, BOND_OPT_NUM_PEER_NOTIF, BOND_OPT_MIIMON, BOND_OPT_PRIMARY, BOND_OPT_PRIMARY_RESELECT, BOND_OPT_USE_CARRIER, BOND_OPT_ACTIVE_SLAVE, BOND_OPT_QUEUE_ID, BOND_OPT_ALL_SLAVES_ACTIVE, BOND_OPT_RESEND_IGMP, BOND_OPT_LP_INTERVAL, BOND_OPT_SLAVES, BOND_OPT_TLB_DYNAMIC_LB, BOND_OPT_AD_ACTOR_SYS_PRIO, BOND_OPT_AD_ACTOR_SYSTEM, BOND_OPT_AD_USER_PORT_KEY, BOND_OPT_NUM_PEER_NOTIF_ALIAS, BOND_OPT_PEER_NOTIF_DELAY, BOND_OPT_LACP_ACTIVE, BOND_OPT_MISSED_MAX, BOND_OPT_NS_TARGETS, BOND_OPT_PRIO, BOND_OPT_COUPLED_CONTROL, BOND_OPT_LAST }; /* This structure is used for storing option values and for passing option * values when changing an option. The logic when used as an arg is as follows: * - if value != ULLONG_MAX -> parse value * - if string != NULL -> parse string * - if the opt is RAW data and length less than maxlen, * copy the data to extra storage */ #define BOND_OPT_EXTRA_MAXLEN 16 struct bond_opt_value { char *string; u64 value; u32 flags; union { char extra[BOND_OPT_EXTRA_MAXLEN]; struct net_device *slave_dev; }; }; struct bonding; struct bond_option { int id; const char *name; const char *desc; u32 flags; /* unsuppmodes is used to denote modes in which the option isn't * supported. */ unsigned long unsuppmodes; /* supported values which this option can have, can be a subset of * BOND_OPTVAL_RANGE's value range */ const struct bond_opt_value *values; int (*set)(struct bonding *bond, const struct bond_opt_value *val); }; int __bond_opt_set(struct bonding *bond, unsigned int option, struct bond_opt_value *val, struct nlattr *bad_attr, struct netlink_ext_ack *extack); int __bond_opt_set_notify(struct bonding *bond, unsigned int option, struct bond_opt_value *val); int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, struct bond_opt_value *val); const struct bond_option *bond_opt_get(unsigned int option); const struct bond_option *bond_opt_get_by_name(const char *name); const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val); /* This helper is used to initialize a bond_opt_value structure for parameter * passing. There should be either a valid string or value, but not both. * When value is ULLONG_MAX then string will be used. */ static inline void __bond_opt_init(struct bond_opt_value *optval, char *string, u64 value, void *extra, size_t extra_len) { memset(optval, 0, sizeof(*optval)); optval->value = ULLONG_MAX; if (value != ULLONG_MAX) optval->value = value; else if (string) optval->string = string; if (extra && extra_len <= BOND_OPT_EXTRA_MAXLEN) memcpy(optval->extra, extra, extra_len); } #define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value, NULL, 0) #define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX, NULL, 0) #define bond_opt_initextra(optval, extra, extra_len) \ __bond_opt_init(optval, NULL, ULLONG_MAX, extra, extra_len) #define bond_opt_slave_initval(optval, slave_dev, value) \ __bond_opt_init(optval, NULL, value, slave_dev, sizeof(struct net_device *)) void bond_option_arp_ip_targets_clear(struct bonding *bond); #if IS_ENABLED(CONFIG_IPV6) void bond_option_ns_ip6_targets_clear(struct bonding *bond); #endif #endif /* _NET_BOND_OPTIONS_H */ |
| 89 89 89 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/ptrace.c * * (C) Copyright 1999 Linus Torvalds * * Common interfaces for "ptrace()" which we do not want * to continually duplicate across every architecture. */ #include <linux/capability.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/signal.h> #include <linux/uio.h> #include <linux/audit.h> #include <linux/pid_namespace.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/regset.h> #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> #include <linux/compat.h> #include <linux/sched/signal.h> #include <linux/minmax.h> #include <linux/syscall_user_dispatch.h> #include <asm/syscall.h> /* for syscall_get_* */ /* * Access another process' address space via ptrace. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; if (!tsk->ptrace || (current != tsk->parent) || ((get_dumpable(mm) != SUID_DUMP_USER) && !ptracer_capable(tsk, mm->user_ns))) { mmput(mm); return 0; } ret = access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret; } void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred) { BUG_ON(!list_empty(&child->ptrace_entry)); list_add(&child->ptrace_entry, &new_parent->ptraced); child->parent = new_parent; child->ptracer_cred = get_cred(ptracer_cred); } /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */ static void ptrace_link(struct task_struct *child, struct task_struct *new_parent) { __ptrace_link(child, new_parent, current_cred()); } /** * __ptrace_unlink - unlink ptracee and restore its execution state * @child: ptracee to be unlinked * * Remove @child from the ptrace list, move it back to the original parent, * and restore the execution state so that it conforms to the group stop * state. * * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer * exiting. For PTRACE_DETACH, unless the ptracee has been killed between * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED. * If the ptracer is exiting, the ptracee can be in any state. * * After detach, the ptracee should be in a state which conforms to the * group stop. If the group is stopped or in the process of stopping, the * ptracee should be put into TASK_STOPPED; otherwise, it should be woken * up from TASK_TRACED. * * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED, * it goes through TRACED -> RUNNING -> STOPPED transition which is similar * to but in the opposite direction of what happens while attaching to a * stopped task. However, in this direction, the intermediate RUNNING * state is not hidden even from the current ptracer and if it immediately * re-attaches and performs a WNOHANG wait(2), it may fail. * * CONTEXT: * write_lock_irq(tasklist_lock) */ void __ptrace_unlink(struct task_struct *child) { const struct cred *old_cred; BUG_ON(!child->ptrace); clear_task_syscall_work(child, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(child, SYSCALL_EMU); #endif child->parent = child->real_parent; list_del_init(&child->ptrace_entry); old_cred = child->ptracer_cred; child->ptracer_cred = NULL; put_cred(old_cred); spin_lock(&child->sighand->siglock); child->ptrace = 0; /* * Clear all pending traps and TRAPPING. TRAPPING should be * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. */ task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK); task_clear_jobctl_trapping(child); /* * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and * @child isn't dead. */ if (!(child->flags & PF_EXITING) && (child->signal->flags & SIGNAL_STOP_STOPPED || child->signal->group_stop_count)) child->jobctl |= JOBCTL_STOP_PENDING; /* * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick * @child in the butt. Note that @resume should be used iff @child * is in TASK_TRACED; otherwise, we might unduly disrupt * TASK_KILLABLE sleeps. */ if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) ptrace_signal_wake_up(child, true); spin_unlock(&child->sighand->siglock); } static bool looks_like_a_spurious_pid(struct task_struct *task) { if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) return false; if (task_pid_vnr(task) == task->ptrace_message) return false; /* * The tracee changed its pid but the PTRACE_EVENT_EXEC event * was not wait()'ed, most probably debugger targets the old * leader which was destroyed in de_thread(). */ return true; } /* * Ensure that nothing can wake it up, even SIGKILL * * A task is switched to this state while a ptrace operation is in progress; * such that the ptrace operation is uninterruptible. */ static bool ptrace_freeze_traced(struct task_struct *task) { bool ret = false; /* Lockless, nobody but us can set this flag */ if (task->jobctl & JOBCTL_LISTENING) return ret; spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { task->jobctl |= JOBCTL_PTRACE_FROZEN; ret = true; } spin_unlock_irq(&task->sighand->siglock); return ret; } static void ptrace_unfreeze_traced(struct task_struct *task) { unsigned long flags; /* * The child may be awake and may have cleared * JOBCTL_PTRACE_FROZEN (see ptrace_resume). The child will * not set JOBCTL_PTRACE_FROZEN or enter __TASK_TRACED anew. */ if (lock_task_sighand(task, &flags)) { task->jobctl &= ~JOBCTL_PTRACE_FROZEN; if (__fatal_signal_pending(task)) { task->jobctl &= ~JOBCTL_TRACED; wake_up_state(task, __TASK_TRACED); } unlock_task_sighand(task, &flags); } } /** * ptrace_check_attach - check whether ptracee is ready for ptrace operation * @child: ptracee to check for * @ignore_state: don't check whether @child is currently %TASK_TRACED * * Check whether @child is being ptraced by %current and ready for further * ptrace operations. If @ignore_state is %false, @child also should be in * %TASK_TRACED state and on return the child is guaranteed to be traced * and not executing. If @ignore_state is %true, @child can be in any * state. * * CONTEXT: * Grabs and releases tasklist_lock and @child->sighand->siglock. * * RETURNS: * 0 on success, -ESRCH if %child is not ready. */ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) { int ret = -ESRCH; /* * We take the read lock around doing both checks to close a * possible race where someone else was tracing our child and * detached between these two checks. After this locked check, * we are sure that this is our traced child and that can only * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); if (child->ptrace && child->parent == current) { /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ if (ignore_state || ptrace_freeze_traced(child)) ret = 0; } read_unlock(&tasklist_lock); if (!ret && !ignore_state && WARN_ON_ONCE(!wait_task_inactive(child, __TASK_TRACED|TASK_FROZEN))) ret = -ESRCH; return ret; } static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { if (mode & PTRACE_MODE_NOAUDIT) return ns_capable_noaudit(ns, CAP_SYS_PTRACE); return ns_capable(ns, CAP_SYS_PTRACE); } /* Returns 0 on success, -errno on denial. */ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; struct mm_struct *mm; kuid_t caller_uid; kgid_t caller_gid; if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); return -EPERM; } /* May we inspect the given task? * This check is used both for attaching with ptrace * and for allowing access to sensitive information in /proc. * * ptrace_attach denies several cases that /proc allows * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); if (mode & PTRACE_MODE_FSCREDS) { caller_uid = cred->fsuid; caller_gid = cred->fsgid; } else { /* * Using the euid would make more sense here, but something * in userland might rely on the old behavior, and this * shouldn't be a security problem since * PTRACE_MODE_REALCREDS implies that the caller explicitly * used a syscall that requests access to another process * (and not a filesystem syscall to procfs). */ caller_uid = cred->uid; caller_gid = cred->gid; } tcred = __task_cred(task); if (uid_eq(caller_uid, tcred->euid) && uid_eq(caller_uid, tcred->suid) && uid_eq(caller_uid, tcred->uid) && gid_eq(caller_gid, tcred->egid) && gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; ok: rcu_read_unlock(); /* * If a task drops privileges and becomes nondumpable (through a syscall * like setresuid()) while we are trying to access it, we must ensure * that the dumpability is read after the credentials; otherwise, * we may be able to attach to a task that we shouldn't be able to * attach to (as if the task had dropped privileges without becoming * nondumpable). * Pairs with a write barrier in commit_creds(). */ smp_rmb(); mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); } bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; task_lock(task); err = __ptrace_may_access(task, mode); task_unlock(task); return !err; } static int check_ptrace_options(unsigned long data) { if (data & ~(unsigned long)PTRACE_O_MASK) return -EINVAL; if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || !IS_ENABLED(CONFIG_SECCOMP)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED || current->ptrace & PT_SUSPEND_SECCOMP) return -EPERM; } return 0; } static inline void ptrace_set_stopped(struct task_struct *task, bool seize) { guard(spinlock)(&task->sighand->siglock); /* SEIZE doesn't trap tracee on attach */ if (!seize) send_signal_locked(SIGSTOP, SEND_SIG_PRIV, task, PIDTYPE_PID); /* * If the task is already STOPPED, set JOBCTL_TRAP_STOP and * TRAPPING, and kick it so that it transits to TRACED. TRAPPING * will be cleared if the child completes the transition or any * event which clears the group stop states happens. We'll wait * for the transition to complete before returning from this * function. * * This hides STOPPED -> RUNNING -> TRACED transition from the * attaching thread but a different thread in the same group can * still observe the transient RUNNING state. IOW, if another * thread's WNOHANG wait(2) on the stopped tracee races against * ATTACH, the wait(2) may fail due to the transient RUNNING. * * The following task_is_stopped() test is safe as both transitions * in and out of STOPPED are protected by siglock. */ if (task_is_stopped(task) && task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) { task->jobctl &= ~JOBCTL_STOPPED; signal_wake_up_state(task, __TASK_STOPPED); } } static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags) { bool seize = (request == PTRACE_SEIZE); int retval; if (seize) { if (addr != 0) return -EIO; /* * This duplicates the check in check_ptrace_options() because * ptrace_attach() and ptrace_setoptions() have historically * used different error codes for unknown ptrace options. */ if (flags & ~(unsigned long)PTRACE_O_MASK) return -EIO; retval = check_ptrace_options(flags); if (retval) return retval; flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); } else { flags = PT_PTRACED; } audit_ptrace(task); if (unlikely(task->flags & PF_KTHREAD)) return -EPERM; if (same_thread_group(task, current)) return -EPERM; /* * Protect exec's credential calculations against our interference; * SUID, SGID and LSM creds get determined differently * under ptrace. */ scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR, &task->signal->cred_guard_mutex) { scoped_guard (task_lock, task) { retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); if (retval) return retval; } scoped_guard (write_lock_irq, &tasklist_lock) { if (unlikely(task->exit_state)) return -EPERM; if (task->ptrace) return -EPERM; task->ptrace = flags; ptrace_link(task, current); ptrace_set_stopped(task, seize); } } /* * We do not bother to change retval or clear JOBCTL_TRAPPING * if wait_on_bit() was interrupted by SIGKILL. The tracer will * not return to user-mode, it will exit and clear this bit in * __ptrace_unlink() if it wasn't already cleared by the tracee; * and until then nobody can ptrace this task. */ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE); proc_ptrace_connector(task, PTRACE_ATTACH); return 0; } /** * ptrace_traceme -- helper for PTRACE_TRACEME * * Performs checks and sets PT_PTRACED. * Should be used by all ptrace implementations for PTRACE_TRACEME. */ static int ptrace_traceme(void) { int ret = -EPERM; write_lock_irq(&tasklist_lock); /* Are we already being traced? */ if (!current->ptrace) { ret = security_ptrace_traceme(current->parent); /* * Check PF_EXITING to ensure ->real_parent has not passed * exit_ptrace(). Otherwise we don't report the error but * pretend ->real_parent untraces us right after return. */ if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace = PT_PTRACED; ptrace_link(current, current->real_parent); } } write_unlock_irq(&tasklist_lock); return ret; } /* * Called with irqs disabled, returns true if childs should reap themselves. */ static int ignoring_children(struct sighand_struct *sigh) { int ret; spin_lock(&sigh->siglock); ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); spin_unlock(&sigh->siglock); return ret; } /* * Called with tasklist_lock held for writing. * Unlink a traced task, and clean it up if it was a traced zombie. * Return true if it needs to be reaped with release_task(). * (We can't call release_task() here because we already hold tasklist_lock.) * * If it's a zombie, our attachedness prevented normal parent notification * or self-reaping. Do notification now if it would have happened earlier. * If it should reap itself, return true. * * If it's our own child, there is no notification to do. But if our normal * children self-reap, then this child was prevented by ptrace and we must * reap it now, in that case we must also wake up sub-threads sleeping in * do_wait(). */ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) { bool dead; __ptrace_unlink(p); if (p->exit_state != EXIT_ZOMBIE) return false; dead = !thread_group_leader(p); if (!dead && thread_group_empty(p)) { if (!same_thread_group(p->real_parent, tracer)) dead = do_notify_parent(p, p->exit_signal); else if (ignoring_children(tracer->sighand)) { __wake_up_parent(p, tracer); dead = true; } } /* Mark it as in the process of being reaped. */ if (dead) p->exit_state = EXIT_DEAD; return dead; } static int ptrace_detach(struct task_struct *child, unsigned int data) { if (!valid_signal(data)) return -EIO; /* Architecture-specific hardware disable .. */ ptrace_disable(child); write_lock_irq(&tasklist_lock); /* * We rely on ptrace_freeze_traced(). It can't be killed and * untraced by another thread, it can't be a zombie. */ WARN_ON(!child->ptrace || child->exit_state); /* * tasklist_lock avoids the race with wait_task_stopped(), see * the comment in ptrace_resume(). */ child->exit_code = data; __ptrace_detach(current, child); write_unlock_irq(&tasklist_lock); proc_ptrace_connector(child, PTRACE_DETACH); return 0; } /* * Detach all tasks we were using ptrace on. Called with tasklist held * for writing. */ void exit_ptrace(struct task_struct *tracer, struct list_head *dead) { struct task_struct *p, *n; list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { if (unlikely(p->ptrace & PT_EXITKILL)) send_sig_info(SIGKILL, SEND_SIG_PRIV, p); if (__ptrace_detach(tracer, p)) list_add(&p->ptrace_entry, dead); } } int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; retval = ptrace_access_vm(tsk, src, buf, this_len, FOLL_FORCE); if (!retval) { if (copied) break; return -EIO; } if (copy_to_user(dst, buf, retval)) return -EFAULT; copied += retval; src += retval; dst += retval; len -= retval; } return copied; } int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; if (copy_from_user(buf, src, this_len)) return -EFAULT; retval = ptrace_access_vm(tsk, dst, buf, this_len, FOLL_FORCE | FOLL_WRITE); if (!retval) { if (copied) break; return -EIO; } copied += retval; src += retval; dst += retval; len -= retval; } return copied; } static int ptrace_setoptions(struct task_struct *child, unsigned long data) { unsigned flags; int ret; ret = check_ptrace_options(data); if (ret) return ret; /* Avoid intermediate state when all opts are cleared */ flags = child->ptrace; flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT); flags |= (data << PT_OPT_FLAG_SHIFT); child->ptrace = flags; return 0; } static int ptrace_getsiginfo(struct task_struct *child, kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(info, child->last_siginfo); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_setsiginfo(struct task_struct *child, const kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(child->last_siginfo, info); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_peek_siginfo(struct task_struct *child, unsigned long addr, unsigned long data) { struct ptrace_peeksiginfo_args arg; struct sigpending *pending; struct sigqueue *q; int ret, i; ret = copy_from_user(&arg, (void __user *) addr, sizeof(struct ptrace_peeksiginfo_args)); if (ret) return -EFAULT; if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED) return -EINVAL; /* unknown flags */ if (arg.nr < 0) return -EINVAL; /* Ensure arg.off fits in an unsigned long */ if (arg.off > ULONG_MAX) return 0; if (arg.flags & PTRACE_PEEKSIGINFO_SHARED) pending = &child->signal->shared_pending; else pending = &child->pending; for (i = 0; i < arg.nr; ) { kernel_siginfo_t info; unsigned long off = arg.off + i; bool found = false; spin_lock_irq(&child->sighand->siglock); list_for_each_entry(q, &pending->list, list) { if (!off--) { found = true; copy_siginfo(&info, &q->info); break; } } spin_unlock_irq(&child->sighand->siglock); if (!found) /* beyond the end of the list */ break; #ifdef CONFIG_COMPAT if (unlikely(in_compat_syscall())) { compat_siginfo_t __user *uinfo = compat_ptr(data); if (copy_siginfo_to_user32(uinfo, &info)) { ret = -EFAULT; break; } } else #endif { siginfo_t __user *uinfo = (siginfo_t __user *) data; if (copy_siginfo_to_user(uinfo, &info)) { ret = -EFAULT; break; } } data += sizeof(siginfo_t); i++; if (signal_pending(current)) break; cond_resched(); } if (i > 0) return i; return ret; } #ifdef CONFIG_RSEQ static long ptrace_get_rseq_configuration(struct task_struct *task, unsigned long size, void __user *data) { struct ptrace_rseq_configuration conf = { .rseq_abi_pointer = (u64)(uintptr_t)task->rseq, .rseq_abi_size = task->rseq_len, .signature = task->rseq_sig, .flags = 0, }; size = min_t(unsigned long, size, sizeof(conf)); if (copy_to_user(data, &conf, size)) return -EFAULT; return sizeof(conf); } #endif #define is_singlestep(request) ((request) == PTRACE_SINGLESTEP) #ifdef PTRACE_SINGLEBLOCK #define is_singleblock(request) ((request) == PTRACE_SINGLEBLOCK) #else #define is_singleblock(request) 0 #endif #ifdef PTRACE_SYSEMU #define is_sysemu_singlestep(request) ((request) == PTRACE_SYSEMU_SINGLESTEP) #else #define is_sysemu_singlestep(request) 0 #endif static int ptrace_resume(struct task_struct *child, long request, unsigned long data) { if (!valid_signal(data)) return -EIO; if (request == PTRACE_SYSCALL) set_task_syscall_work(child, SYSCALL_TRACE); else clear_task_syscall_work(child, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP) set_task_syscall_work(child, SYSCALL_EMU); else clear_task_syscall_work(child, SYSCALL_EMU); #endif if (is_singleblock(request)) { if (unlikely(!arch_has_block_step())) return -EIO; user_enable_block_step(child); } else if (is_singlestep(request) || is_sysemu_singlestep(request)) { if (unlikely(!arch_has_single_step())) return -EIO; user_enable_single_step(child); } else { user_disable_single_step(child); } /* * Change ->exit_code and ->state under siglock to avoid the race * with wait_task_stopped() in between; a non-zero ->exit_code will * wrongly look like another report from tracee. * * Note that we need siglock even if ->exit_code == data and/or this * status was not reported yet, the new status must not be cleared by * wait_task_stopped() after resume. */ spin_lock_irq(&child->sighand->siglock); child->exit_code = data; child->jobctl &= ~JOBCTL_TRACED; wake_up_state(child, __TASK_TRACED); spin_unlock_irq(&child->sighand->siglock); return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK static const struct user_regset * find_regset(const struct user_regset_view *view, unsigned int type) { const struct user_regset *regset; int n; for (n = 0; n < view->n; ++n) { regset = view->regsets + n; if (regset->core_note_type == type) return regset; } return NULL; } static int ptrace_regset(struct task_struct *task, int req, unsigned int type, struct iovec *kiov) { const struct user_regset_view *view = task_user_regset_view(task); const struct user_regset *regset = find_regset(view, type); int regset_no; if (!regset || (kiov->iov_len % regset->size) != 0) return -EINVAL; regset_no = regset - view->regsets; kiov->iov_len = min(kiov->iov_len, (__kernel_size_t) (regset->n * regset->size)); if (req == PTRACE_GETREGSET) return copy_regset_to_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); else return copy_regset_from_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); } /* * This is declared in linux/regset.h and defined in machine-dependent * code. We put the export here, near the primary machine-neutral use, * to ensure no machine forgets it. */ EXPORT_SYMBOL_GPL(task_user_regset_view); static unsigned long ptrace_get_syscall_info_entry(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { unsigned long args[ARRAY_SIZE(info->entry.args)]; int i; info->op = PTRACE_SYSCALL_INFO_ENTRY; info->entry.nr = syscall_get_nr(child, regs); syscall_get_arguments(child, regs, args); for (i = 0; i < ARRAY_SIZE(args); i++) info->entry.args[i] = args[i]; /* args is the last field in struct ptrace_syscall_info.entry */ return offsetofend(struct ptrace_syscall_info, entry.args); } static unsigned long ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { /* * As struct ptrace_syscall_info.entry is currently a subset * of struct ptrace_syscall_info.seccomp, it makes sense to * initialize that subset using ptrace_get_syscall_info_entry(). * This can be reconsidered in the future if these structures * diverge significantly enough. */ ptrace_get_syscall_info_entry(child, regs, info); info->op = PTRACE_SYSCALL_INFO_SECCOMP; info->seccomp.ret_data = child->ptrace_message; /* ret_data is the last field in struct ptrace_syscall_info.seccomp */ return offsetofend(struct ptrace_syscall_info, seccomp.ret_data); } static unsigned long ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { info->op = PTRACE_SYSCALL_INFO_EXIT; info->exit.rval = syscall_get_error(child, regs); info->exit.is_error = !!info->exit.rval; if (!info->exit.is_error) info->exit.rval = syscall_get_return_value(child, regs); /* is_error is the last field in struct ptrace_syscall_info.exit */ return offsetofend(struct ptrace_syscall_info, exit.is_error); } static int ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size, void __user *datavp) { struct pt_regs *regs = task_pt_regs(child); struct ptrace_syscall_info info = { .op = PTRACE_SYSCALL_INFO_NONE, .arch = syscall_get_arch(child), .instruction_pointer = instruction_pointer(regs), .stack_pointer = user_stack_pointer(regs), }; unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry); unsigned long write_size; /* * This does not need lock_task_sighand() to access * child->last_siginfo because ptrace_freeze_traced() * called earlier by ptrace_check_attach() ensures that * the tracee cannot go away and clear its last_siginfo. */ switch (child->last_siginfo ? child->last_siginfo->si_code : 0) { case SIGTRAP | 0x80: switch (child->ptrace_message) { case PTRACE_EVENTMSG_SYSCALL_ENTRY: actual_size = ptrace_get_syscall_info_entry(child, regs, &info); break; case PTRACE_EVENTMSG_SYSCALL_EXIT: actual_size = ptrace_get_syscall_info_exit(child, regs, &info); break; } break; case SIGTRAP | (PTRACE_EVENT_SECCOMP << 8): actual_size = ptrace_get_syscall_info_seccomp(child, regs, &info); break; } write_size = min(actual_size, user_size); return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data) { bool seized = child->ptrace & PT_SEIZED; int ret = -EIO; kernel_siginfo_t siginfo, *si; void __user *datavp = (void __user *) data; unsigned long __user *datalp = datavp; unsigned long flags; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: return generic_ptrace_peekdata(child, addr, data); case PTRACE_POKETEXT: case PTRACE_POKEDATA: return generic_ptrace_pokedata(child, addr, data); #ifdef PTRACE_OLDSETOPTIONS case PTRACE_OLDSETOPTIONS: #endif case PTRACE_SETOPTIONS: ret = ptrace_setoptions(child, data); break; case PTRACE_GETEVENTMSG: ret = put_user(child->ptrace_message, datalp); break; case PTRACE_PEEKSIGINFO: ret = ptrace_peek_siginfo(child, addr, data); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user(datavp, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user(&siginfo, datavp); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; case PTRACE_GETSIGMASK: { sigset_t *mask; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (test_tsk_restore_sigmask(child)) mask = &child->saved_sigmask; else mask = &child->blocked; if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; } case PTRACE_SETSIGMASK: { sigset_t new_set; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (copy_from_user(&new_set, datavp, sizeof(sigset_t))) { ret = -EFAULT; break; } sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); /* * Every thread does recalc_sigpending() after resume, so * retarget_shared_pending() and recalc_sigpending() are not * called here. */ spin_lock_irq(&child->sighand->siglock); child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); clear_tsk_restore_sigmask(child); ret = 0; break; } case PTRACE_INTERRUPT: /* * Stop tracee without any side-effect on signal or job * control. At least one trap is guaranteed to happen * after this request. If @child is already trapped, the * current trap is not disturbed and another trap will * happen after the current trap is ended with PTRACE_CONT. * * The actual trap might not be PTRACE_EVENT_STOP trap but * the pending condition is cleared regardless. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; /* * INTERRUPT doesn't disturb existing trap sans one * exception. If ptracer issued LISTEN for the current * STOP, this INTERRUPT should clear LISTEN and re-trap * tracee into STOP. */ if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP))) ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING); unlock_task_sighand(child, &flags); ret = 0; break; case PTRACE_LISTEN: /* * Listen for events. Tracee must be in STOP. It's not * resumed per-se but is not considered to be in TRACED by * wait(2) or ptrace(2). If an async event (e.g. group * stop state change) happens, tracee will enter STOP trap * again. Alternatively, ptracer can issue INTERRUPT to * finish listening and re-trap tracee into STOP. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; si = child->last_siginfo; if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) { child->jobctl |= JOBCTL_LISTENING; /* * If NOTIFY is set, it means event happened between * start of this trap and now. Trigger re-trap. */ if (child->jobctl & JOBCTL_TRAP_NOTIFY) ptrace_signal_wake_up(child, true); ret = 0; } unlock_task_sighand(child, &flags); break; case PTRACE_DETACH: /* detach a process that was attached. */ ret = ptrace_detach(child, data); break; #ifdef CONFIG_BINFMT_ELF_FDPIC case PTRACE_GETFDPIC: { struct mm_struct *mm = get_task_mm(child); unsigned long tmp = 0; ret = -ESRCH; if (!mm) break; switch (addr) { case PTRACE_GETFDPIC_EXEC: tmp = mm->context.exec_fdpic_loadmap; break; case PTRACE_GETFDPIC_INTERP: tmp = mm->context.interp_fdpic_loadmap; break; default: break; } mmput(mm); ret = put_user(tmp, datalp); break; } #endif case PTRACE_SINGLESTEP: #ifdef PTRACE_SINGLEBLOCK case PTRACE_SINGLEBLOCK: #endif #ifdef PTRACE_SYSEMU case PTRACE_SYSEMU: case PTRACE_SYSEMU_SINGLESTEP: #endif case PTRACE_SYSCALL: case PTRACE_CONT: return ptrace_resume(child, request, data); case PTRACE_KILL: send_sig_info(SIGKILL, SEND_SIG_NOINFO, child); return 0; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct iovec __user *uiov = datavp; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(kiov.iov_base, &uiov->iov_base) || __get_user(kiov.iov_len, &uiov->iov_len)) return -EFAULT; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } case PTRACE_GET_SYSCALL_INFO: ret = ptrace_get_syscall_info(child, addr, datavp); break; #endif case PTRACE_SECCOMP_GET_FILTER: ret = seccomp_get_filter(child, addr, datavp); break; case PTRACE_SECCOMP_GET_METADATA: ret = seccomp_get_metadata(child, addr, datavp); break; #ifdef CONFIG_RSEQ case PTRACE_GET_RSEQ_CONFIGURATION: ret = ptrace_get_rseq_configuration(child, addr, datavp); break; #endif case PTRACE_SET_SYSCALL_USER_DISPATCH_CONFIG: ret = syscall_user_dispatch_set_config(child, addr, datavp); break; case PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG: ret = syscall_user_dispatch_get_config(child, addr, datavp); break; default: break; } return ret; } SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, unsigned long, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (ret < 0) goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); out_put_task_struct: put_task_struct(child); out: return ret; } int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, unsigned long data) { unsigned long tmp; int copied; copied = ptrace_access_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE); if (copied != sizeof(tmp)) return -EIO; return put_user(tmp, (unsigned long __user *)data); } int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data) { int copied; copied = ptrace_access_vm(tsk, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); return (copied == sizeof(data)) ? 0 : -EIO; } #if defined CONFIG_COMPAT int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data) { compat_ulong_t __user *datap = compat_ptr(data); compat_ulong_t word; kernel_siginfo_t siginfo; int ret; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: ret = ptrace_access_vm(child, addr, &word, sizeof(word), FOLL_FORCE); if (ret != sizeof(word)) ret = -EIO; else ret = put_user(word, datap); break; case PTRACE_POKETEXT: case PTRACE_POKEDATA: ret = ptrace_access_vm(child, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); ret = (ret != sizeof(data) ? -EIO : 0); break; case PTRACE_GETEVENTMSG: ret = put_user((compat_ulong_t) child->ptrace_message, datap); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user32( (struct compat_siginfo __user *) datap, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user32( &siginfo, (struct compat_siginfo __user *) datap); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct compat_iovec __user *uiov = (struct compat_iovec __user *) datap; compat_uptr_t ptr; compat_size_t len; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(ptr, &uiov->iov_base) || __get_user(len, &uiov->iov_len)) return -EFAULT; kiov.iov_base = compat_ptr(ptr); kiov.iov_len = len; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } #endif default: ret = ptrace_request(child, request, addr, data); } return ret; } COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid, compat_long_t, addr, compat_long_t, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (!ret) { ret = compat_arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); } out_put_task_struct: put_task_struct(child); out: return ret; } #endif /* CONFIG_COMPAT */ |
| 9 9 9 9 9 9 9 9 83 68 68 60 68 9 5 9 9 5 1 2 29 6 33 76 76 76 22 31 32 35 5 5 5 40 29 27 10 2 18 23 12 8 7 1 6 6 6 3 6 6 6 4 4 32 31 88 119 61 13 23 15 3 12 3 3 3 37 37 8 8 29 37 36 31 5 3 2 34 33 1 3 37 3 3 1 3 1 3 3 50 1 1 3 47 1 1 1 1 42 41 39 34 34 34 1 1 2 35 1 1 1 1 1 1 1 1 1 1 1 1 1 1 42 6 41 38 1 2 39 37 41 54 55 11 42 46 68 6 63 3 66 68 53 14 13 6 2 47 41 1 1 1 39 35 3 2 2 2 17 1 1 2 10 6 2 11 12 5 250 29 29 9 76 1 63 64 64 64 64 57 7 48 34 14 42 1 21 20 30 11 28 13 39 2 38 3 38 3 38 3 28 13 34 7 39 2 44 37 7 7 34 1 20 12 7 2 3 1 1 2 5 1 4 91 138 1 2 3 2 3 3 5 2 2 131 10 247 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 tunneling device * Linux INET6 implementation * * Authors: * Ville Nuorvala <vnuorval@tcs.hut.fi> * Yasuyuki Kozakai <kozakai@linux-ipv6.org> * * Based on: * linux/net/ipv6/sit.c and linux/net/ipv4/ipip.c * * RFC 2473 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/icmp.h> #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> #include <linux/etherdevice.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/ip6_tunnel.h> #include <net/xfrm.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/dst_metadata.h> MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); #define IP6_TUNNEL_HASH_SIZE_SHIFT 5 #define IP6_TUNNEL_HASH_SIZE (1 << IP6_TUNNEL_HASH_SIZE_SHIFT) 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 u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) { u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); return hash_32(hash, IP6_TUNNEL_HASH_SIZE_SHIFT); } static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); static struct rtnl_link_ops ip6_link_ops __read_mostly; static unsigned int ip6_tnl_net_id __read_mostly; struct ip6_tnl_net { /* the IPv6 tunnel fallback device */ struct net_device *fb_tnl_dev; /* lists for storing tunnels in use */ struct ip6_tnl __rcu *tnls_r_l[IP6_TUNNEL_HASH_SIZE]; struct ip6_tnl __rcu *tnls_wc[1]; struct ip6_tnl __rcu **tnls[2]; struct ip6_tnl __rcu *collect_md_tun; }; static inline int ip6_tnl_mpls_supported(void) { return IS_ENABLED(CONFIG_MPLS); } #define for_each_ip6_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses * @net: network namespace * @link: ifindex of underlying interface * @remote: the address of the tunnel exit-point * @local: the address of the tunnel entry-point * * Return: * tunnel matching given end-points if found, * else fallback tunnel if its device is up, * else %NULL **/ static struct ip6_tnl * ip6_tnl_lookup(struct net *net, int link, const struct in6_addr *remote, const struct in6_addr *local) { unsigned int hash = HASH(remote, local); struct ip6_tnl *t, *cand = NULL; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct in6_addr any; for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || !ipv6_addr_equal(remote, &t->parms.raddr) || !(t->dev->flags & IFF_UP)) continue; if (link == t->parms.link) return t; else cand = t; } memset(&any, 0, sizeof(any)); hash = HASH(&any, local); for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || !ipv6_addr_any(&t->parms.raddr) || !(t->dev->flags & IFF_UP)) continue; if (link == t->parms.link) return t; else if (!cand) cand = t; } hash = HASH(remote, &any); for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (!ipv6_addr_equal(remote, &t->parms.raddr) || !ipv6_addr_any(&t->parms.laddr) || !(t->dev->flags & IFF_UP)) continue; if (link == t->parms.link) return t; else if (!cand) cand = t; } if (cand) return cand; t = rcu_dereference(ip6n->collect_md_tun); if (t && t->dev->flags & IFF_UP) return t; t = rcu_dereference(ip6n->tnls_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } /** * ip6_tnl_bucket - get head of list matching given tunnel parameters * @ip6n: the private data for ip6_vti in the netns * @p: parameters containing tunnel end-points * * Description: * ip6_tnl_bucket() returns the head of the list matching the * &struct in6_addr entries laddr and raddr in @p. * * Return: head of IPv6 tunnel list **/ static struct ip6_tnl __rcu ** ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; unsigned int h = 0; int prio = 0; if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; h = HASH(remote, local); } return &ip6n->tnls[prio][h]; } /** * ip6_tnl_link - add tunnel to hash table * @ip6n: the private data for ip6_vti in the netns * @t: tunnel to be added **/ static void ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms); if (t->parms.collect_md) rcu_assign_pointer(ip6n->collect_md_tun, t); rcu_assign_pointer(t->next , rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } /** * ip6_tnl_unlink - remove tunnel from hash table * @ip6n: the private data for ip6_vti in the netns * @t: tunnel to be removed **/ static void ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp; struct ip6_tnl *iter; if (t->parms.collect_md) rcu_assign_pointer(ip6n->collect_md_tun, NULL); for (tp = ip6_tnl_bucket(ip6n, &t->parms); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static void ip6_dev_free(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); gro_cells_destroy(&t->gro_cells); dst_cache_destroy(&t->dst_cache); } static int ip6_tnl_create2(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); int err; dev->rtnl_link_ops = &ip6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); ip6_tnl_link(ip6n, t); return 0; out: return err; } /** * ip6_tnl_create - create a new tunnel * @net: network namespace * @p: tunnel parameters * * Description: * Create tunnel matching given parameters. * * Return: * created tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) { struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; int err = -E2BIG; if (p->name[0]) { if (!dev_valid_name(p->name)) goto failed; strscpy(name, p->name, IFNAMSIZ); } else { sprintf(name, "ip6tnl%%d"); } err = -ENOMEM; dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!dev) goto failed; dev_net_set(dev, net); t = netdev_priv(dev); t->parms = *p; t->net = dev_net(dev); err = ip6_tnl_create2(dev); if (err < 0) goto failed_free; return t; failed_free: free_netdev(dev); failed: return ERR_PTR(err); } /** * ip6_tnl_locate - find or create tunnel matching given parameters * @net: network namespace * @p: tunnel parameters * @create: != 0 if allowed to create new tunnel if no match found * * Description: * ip6_tnl_locate() first tries to locate an existing tunnel * based on @parms. If this is unsuccessful, but @create is set a new * tunnel device is created and registered for use. * * Return: * matching tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_locate(struct net *net, struct __ip6_tnl_parm *p, int create) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; struct ip6_tnl __rcu **tp; struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); for (tp = ip6_tnl_bucket(ip6n, p); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && p->link == t->parms.link) { if (create) return ERR_PTR(-EEXIST); return t; } } if (!create) return ERR_PTR(-ENODEV); return ip6_tnl_create(net, p); } /** * ip6_tnl_dev_uninit - tunnel device uninitializer * @dev: the device to be destroyed * * Description: * ip6_tnl_dev_uninit() removes tunnel from its list **/ static void ip6_tnl_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else ip6_tnl_unlink(ip6n, t); dst_cache_reset(&t->dst_cache); netdev_put(dev, &t->dev_tracker); } /** * ip6_tnl_parse_tlv_enc_lim - handle encapsulation limit option * @skb: received socket buffer * @raw: the ICMPv6 error message data * * Return: * 0 if none was found, * else index to encapsulation limit **/ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) { const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw; unsigned int nhoff = raw - skb->data; unsigned int off = nhoff + sizeof(*ipv6h); u8 nexthdr = ipv6h->nexthdr; while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) { struct ipv6_opt_hdr *hdr; u16 optlen; if (!pskb_may_pull(skb, off + sizeof(*hdr))) break; hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { optlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { optlen = ipv6_authlen(hdr); } else { optlen = ipv6_optlen(hdr); } if (!pskb_may_pull(skb, off + optlen)) break; hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { struct frag_hdr *frag_hdr = (struct frag_hdr *)hdr; if (frag_hdr->frag_off) break; } if (nexthdr == NEXTHDR_DEST) { u16 i = 2; while (1) { struct ipv6_tlv_tnl_enc_lim *tel; /* No more room for encapsulation limit */ if (i + sizeof(*tel) > optlen) break; tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i); /* return index of option if found and valid */ if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT && tel->length == 1) return i + off - nhoff; /* else jump to next option */ if (tel->type) i += tel->length + 2; else i++; } } nexthdr = hdr->nexthdr; off += optlen; } return 0; } EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim); /* ip6_tnl_err() should handle errors in the tunnel according to the * specifications in RFC 2473. */ static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, u8 *type, u8 *code, int *msg, __u32 *info, int offset) { const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data; struct net *net = dev_net(skb->dev); u8 rel_type = ICMPV6_DEST_UNREACH; u8 rel_code = ICMPV6_ADDR_UNREACH; __u32 rel_info = 0; struct ip6_tnl *t; int err = -ENOENT; int rel_msg = 0; u8 tproto; __u16 len; /* If the packet doesn't contain the original IPv6 header we are in trouble since we might need the source address for further processing of the error. */ rcu_read_lock(); t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->daddr, &ipv6h->saddr); if (!t) goto out; tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto out; err = 0; switch (*type) { case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); rel_msg = 1; break; case ICMPV6_TIME_EXCEED: if ((*code) == ICMPV6_EXC_HOPLIMIT) { net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", t->parms.name); rel_msg = 1; } break; case ICMPV6_PARAMPROB: { struct ipv6_tlv_tnl_enc_lim *tel; __u32 teli; teli = 0; if ((*code) == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); if (teli && teli == *info - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", t->parms.name); rel_msg = 1; } } else { net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n", t->parms.name); } break; } case ICMPV6_PKT_TOOBIG: { __u32 mtu; ip6_update_pmtu(skb, net, htonl(*info), 0, 0, sock_net_uid(net, NULL)); mtu = *info - offset; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len); if (len > mtu) { rel_type = ICMPV6_PKT_TOOBIG; rel_code = 0; rel_info = mtu; rel_msg = 1; } break; } case NDISC_REDIRECT: ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); break; } *type = rel_type; *code = rel_code; *info = rel_info; *msg = rel_msg; out: rcu_read_unlock(); return err; } static int ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __u32 rel_info = ntohl(info); const struct iphdr *eiph; struct sk_buff *skb2; int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; struct rtable *rt; struct flowi4 fl4; err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); if (err < 0) return err; if (rel_msg == 0) return 0; switch (rel_type) { case ICMPV6_DEST_UNREACH: if (rel_code != ICMPV6_ADDR_UNREACH) return 0; rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_HOST_UNREACH; break; case ICMPV6_PKT_TOOBIG: if (rel_code != 0) return 0; rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_FRAG_NEEDED; break; default: return 0; } if (!pskb_may_pull(skb, offset + sizeof(struct iphdr))) return 0; skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) return 0; skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); eiph = ip_hdr(skb2); /* Try to guess incoming interface */ rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr, 0, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); if (IS_ERR(rt)) goto out; skb2->dev = rt->dst.dev; ip_rt_put(rt); /* route "incoming" packet */ if (rt->rt_flags & RTCF_LOCAL) { rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->daddr, eiph->saddr, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; } skb_dst_set(skb2, &rt->dst); } else { if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6) goto out; } /* change mtu on this route */ if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) { if (rel_info > dst_mtu(skb_dst(skb2))) goto out; skb_dst_update_pmtu_no_confirm(skb2, rel_info); } icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); out: kfree_skb(skb2); return 0; } static int ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __u32 rel_info = ntohl(info); int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); if (err < 0) return err; if (rel_msg && pskb_may_pull(skb, offset + sizeof(struct ipv6hdr))) { struct rt6_info *rt; struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) return 0; skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); /* Try to guess incoming interface */ rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, skb2, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; icmpv6_send(skb2, rel_type, rel_code, rel_info); ip6_rt_put(rt); kfree_skb(skb2); } return 0; } static int mplsip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __u32 rel_info = ntohl(info); int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; err = ip6_tnl_err(skb, IPPROTO_MPLS, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); return err; } static int ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK; if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield); return IP6_ECN_decapsulate(ipv6h, skb); } static int ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb)); return IP6_ECN_decapsulate(ipv6h, skb); } static inline int mplsip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { /* ECN is not supported in AF_MPLS */ return 0; } __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ltype = ipv6_addr_type(laddr); int rtype = ipv6_addr_type(raddr); __u32 flags = 0; if (ltype == IPV6_ADDR_ANY || rtype == IPV6_ADDR_ANY) { flags = IP6_TNL_F_CAP_PER_PACKET; } else if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { if (ltype&IPV6_ADDR_UNICAST) flags |= IP6_TNL_F_CAP_XMIT; if (rtype&IPV6_ADDR_UNICAST) flags |= IP6_TNL_F_CAP_RCV; } return flags; } EXPORT_SYMBOL(ip6_tnl_get_cap); /* called with rcu_read_lock() */ int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = t->net; if ((p->flags & IP6_TNL_F_CAP_RCV) || ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_RCV))) { struct net_device *ldev = NULL; if (p->link) ldev = dev_get_by_index_rcu(net, p->link); if ((ipv6_addr_is_multicast(laddr) || likely(ipv6_chk_addr_and_flags(net, laddr, ldev, false, 0, IFA_F_TENTATIVE))) && ((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) || likely(!ipv6_chk_addr_and_flags(net, raddr, ldev, true, 0, IFA_F_TENTATIVE)))) ret = 1; } return ret; } EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl); static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb), bool log_ecn_err) { const struct ipv6hdr *ipv6h; int nh, err; if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; } skb->protocol = tpi->proto; /* Warning: All skb pointers will be invalidated! */ if (tunnel->dev->type == ARPHRD_ETHER) { if (!pskb_may_pull(skb, ETH_HLEN)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; skb_reset_mac_header(skb); } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } /* Get the outer header. */ ipv6h = (struct ipv6hdr *)(skb->head + nh); memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); err = dscp_ecn_decapsulate(tunnel, ipv6h, skb); if (unlikely(err)) { if (log_ecn_err) net_info_ratelimited("non-ECT from %pI6 with DS=%#x\n", &ipv6h->saddr, ipv6_get_dsfield(ipv6h)); if (err > 1) { DEV_STATS_INC(tunnel->dev, rx_frame_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } } dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); if (tun_dst) skb_dst_set(skb, (struct dst_entry *)tun_dst); gro_cells_receive(&tunnel->gro_cells, skb); return 0; drop: if (tun_dst) dst_release((struct dst_entry *)tun_dst); kfree_skb(skb); return 0; } int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_err) { int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb); dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate; if (tpi->proto == htons(ETH_P_IP)) dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate; return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_err); } EXPORT_SYMBOL(ip6_tnl_rcv); static const struct tnl_ptk_info tpi_v6 = { /* no tunnel info required for ipxip6. */ .proto = htons(ETH_P_IPV6), }; static const struct tnl_ptk_info tpi_v4 = { /* no tunnel info required for ipxip6. */ .proto = htons(ETH_P_IP), }; static const struct tnl_ptk_info tpi_mpls = { /* no tunnel info required for mplsip6. */ .proto = htons(ETH_P_MPLS_UC), }; static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, const struct tnl_ptk_info *tpi, int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb)) { struct ip6_tnl *t; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct metadata_dst *tun_dst = NULL; int ret = -1; rcu_read_lock(); t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->saddr, &ipv6h->daddr); if (t) { u8 tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto drop; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) goto drop; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (t->parms.collect_md) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; tun_dst = ipv6_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) goto drop; } ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_error); } rcu_read_unlock(); return ret; drop: rcu_read_unlock(); kfree_skb(skb); return 0; } static int ip4ip6_rcv(struct sk_buff *skb) { return ipxip6_rcv(skb, IPPROTO_IPIP, &tpi_v4, ip4ip6_dscp_ecn_decapsulate); } static int ip6ip6_rcv(struct sk_buff *skb) { return ipxip6_rcv(skb, IPPROTO_IPV6, &tpi_v6, ip6ip6_dscp_ecn_decapsulate); } static int mplsip6_rcv(struct sk_buff *skb) { return ipxip6_rcv(skb, IPPROTO_MPLS, &tpi_mpls, mplsip6_dscp_ecn_decapsulate); } struct ipv6_tel_txoption { struct ipv6_txoptions ops; __u8 dst_opt[8]; }; static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit) { memset(opt, 0, sizeof(struct ipv6_tel_txoption)); opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT; opt->dst_opt[3] = 1; opt->dst_opt[4] = encap_limit; opt->dst_opt[5] = IPV6_TLV_PADN; opt->dst_opt[6] = 1; opt->ops.dst1opt = (struct ipv6_opt_hdr *) opt->dst_opt; opt->ops.opt_nflen = 8; } /** * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device * @hdr: IPv6 header from the incoming packet * * Description: * Avoid trivial tunneling loop by checking that tunnel exit-point * doesn't match source of incoming packet. * * Return: * 1 if conflict, * 0 else **/ static inline bool ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = t->net; if (t->parms.collect_md) return 1; if ((p->flags & IP6_TNL_F_CAP_XMIT) || ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_XMIT))) { struct net_device *ldev = NULL; rcu_read_lock(); if (p->link) ldev = dev_get_by_index_rcu(net, p->link); if (unlikely(!ipv6_chk_addr_and_flags(net, laddr, ldev, false, 0, IFA_F_TENTATIVE))) pr_warn_ratelimited("%s xmit: Local address not yet configured!\n", p->name); else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && !ipv6_addr_is_multicast(raddr) && unlikely(ipv6_chk_addr_and_flags(net, raddr, ldev, true, 0, IFA_F_TENTATIVE))) pr_warn_ratelimited("%s xmit: Routing loop! Remote address found on this node!\n", p->name); else ret = 1; rcu_read_unlock(); } return ret; } EXPORT_SYMBOL_GPL(ip6_tnl_xmit_ctl); /** * ip6_tnl_xmit - encapsulate packet and send * @skb: the outgoing socket buffer * @dev: the outgoing tunnel device * @dsfield: dscp code for outer header * @fl6: flow of tunneled packet * @encap_limit: encapsulation limit * @pmtu: Path MTU is stored if packet is too big * @proto: next header value * * Description: * Build new header and do some sanity checks on the packet before sending * it. * * Return: * 0 on success * -1 fail * %-EMSGSIZE message too big. return mtu in this case. **/ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, struct flowi6 *fl6, int encap_limit, __u32 *pmtu, __u8 proto) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ipv6hdr *ipv6h; struct ipv6_tel_txoption opt; struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; int mtu; unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0; unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen; unsigned int max_headroom = psh_hlen; __be16 payload_protocol; bool use_cache = false; u8 hop_limit; int err = -1; payload_protocol = skb_protocol(skb, true); if (t->parms.collect_md) { hop_limit = skb_tunnel_info(skb)->key.ttl; goto route_lookup; } else { hop_limit = t->parms.hop_limit; } /* NBMA tunnel */ if (ipv6_addr_any(&t->parms.raddr)) { if (payload_protocol == htons(ETH_P_IPV6)) { struct in6_addr *addr6; struct neighbour *neigh; int addr_type; if (!skb_dst(skb)) goto tx_err_link_failure; neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (!neigh) goto tx_err_link_failure; addr6 = (struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) addr6 = &ipv6_hdr(skb)->daddr; memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); } else if (payload_protocol == htons(ETH_P_IP)) { const struct rtable *rt = skb_rtable(skb); if (!rt) goto tx_err_link_failure; if (rt->rt_gw_family == AF_INET6) memcpy(&fl6->daddr, &rt->rt_gw6, sizeof(fl6->daddr)); } } else if (t->parms.proto != 0 && !(t->parms.flags & (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { /* enable the cache only if neither the outer protocol nor the * routing decision depends on the current inner header value */ use_cache = true; } if (use_cache) dst = dst_cache_get(&t->dst_cache); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) goto tx_err_link_failure; if (!dst) { route_lookup: /* add dsfield to flowlabel for route lookup */ fl6->flowlabel = ip6_make_flowinfo(dsfield, fl6->flowlabel); dst = ip6_route_output(net, NULL, fl6); if (dst->error) goto tx_err_link_failure; dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } if (t->parms.collect_md && ipv6_addr_any(&fl6->saddr) && ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev, &fl6->daddr, 0, &fl6->saddr)) goto tx_err_link_failure; ndst = dst; } tdev = dst->dev; if (tdev == dev) { DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", t->parms.name); goto tx_err_dst_release; } mtu = dst_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen; if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; } mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ? IPV6_MIN_MTU : IPV4_MIN_MTU); skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; goto tx_err_dst_release; } if (t->err_count > 0) { if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO)) { t->err_count--; dst_link_failure(skb); } else { t->err_count = 0; } } skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom += LL_RESERVED_SPACE(tdev); if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb; new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) goto tx_err_dst_release; if (skb->sk) skb_set_owner_w(new_skb, skb->sk); consume_skb(skb); skb = new_skb; } if (t->parms.collect_md) { if (t->encap.type != TUNNEL_ENCAP_NONE) goto tx_err_dst_release; } else { if (use_cache && ndst) dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr); } skb_dst_set(skb, dst); if (hop_limit == 0) { if (payload_protocol == htons(ETH_P_IP)) hop_limit = ip_hdr(skb)->ttl; else if (payload_protocol == htons(ETH_P_IPV6)) hop_limit = ipv6_hdr(skb)->hop_limit; else hop_limit = ip6_dst_hoplimit(dst); } /* Calculate max headroom for all the headers and adjust * needed_headroom if necessary. */ max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; if (max_headroom > READ_ONCE(dev->needed_headroom)) WRITE_ONCE(dev->needed_headroom, max_headroom); err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) return err; if (encap_limit >= 0) { init_tel_txopt(&opt, encap_limit); ipv6_push_frag_opts(skb, &opt.ops, &proto); } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); ip6_flow_hdr(ipv6h, dsfield, ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6)); ipv6h->hop_limit = hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; ipv6h->daddr = fl6->daddr; ip6tunnel_xmit(NULL, skb, dev); return 0; tx_err_link_failure: DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); return err; } EXPORT_SYMBOL(ip6_tnl_xmit); static inline int ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, u8 protocol) { struct ip6_tnl *t = netdev_priv(dev); struct ipv6hdr *ipv6h; const struct iphdr *iph; int encap_limit = -1; __u16 offset; struct flowi6 fl6; __u8 dsfield, orig_dsfield; __u32 mtu; u8 tproto; int err; tproto = READ_ONCE(t->parms.proto); if (tproto != protocol && tproto != 0) return -1; if (t->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET6)) return -1; key = &tun_info->key; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = protocol; fl6.saddr = key->u.ipv6.src; fl6.daddr = key->u.ipv6.dst; fl6.flowlabel = key->label; dsfield = key->tos; switch (protocol) { case IPPROTO_IPIP: iph = ip_hdr(skb); orig_dsfield = ipv4_get_dsfield(iph); break; case IPPROTO_IPV6: ipv6h = ipv6_hdr(skb); orig_dsfield = ipv6_get_dsfield(ipv6h); break; default: orig_dsfield = dsfield; break; } } else { if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; if (protocol == IPPROTO_IPV6) { offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); /* ip6_tnl_parse_tlv_enc_lim() might have * reallocated skb->head */ if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; tel = (void *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { icmpv6_ndo_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offset + 2); return -1; } encap_limit = tel->encap_limit - 1; } } memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); fl6.flowi6_proto = protocol; if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) fl6.flowi6_mark = skb->mark; else fl6.flowi6_mark = t->parms.fwmark; switch (protocol) { case IPPROTO_IPIP: iph = ip_hdr(skb); orig_dsfield = ipv4_get_dsfield(iph); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) dsfield = orig_dsfield; else dsfield = ip6_tclass(t->parms.flowinfo); break; case IPPROTO_IPV6: ipv6h = ipv6_hdr(skb); orig_dsfield = ipv6_get_dsfield(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) dsfield = orig_dsfield; else dsfield = ip6_tclass(t->parms.flowinfo); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) fl6.flowlabel |= ip6_flowlabel(ipv6h); break; default: orig_dsfield = dsfield = ip6_tclass(t->parms.flowinfo); break; } } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); dsfield = INET_ECN_encapsulate(dsfield, orig_dsfield); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; skb_set_inner_ipproto(skb, protocol); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, protocol); if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) switch (protocol) { case IPPROTO_IPIP: icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); break; case IPPROTO_IPV6: icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); break; default: break; } return -1; } return 0; } static netdev_tx_t ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); u8 ipproto; int ret; if (!pskb_inet_may_pull(skb)) goto tx_err; switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP; break; case htons(ETH_P_IPV6): if (ip6_tnl_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; ipproto = IPPROTO_IPV6; break; case htons(ETH_P_MPLS_UC): ipproto = IPPROTO_MPLS; break; default: goto tx_err; } ret = ipxip6_tnl_xmit(skb, dev, ipproto); if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; struct net_device *tdev = NULL; struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; int t_hlen; int mtu; __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ fl6->saddr = p->laddr; fl6->daddr = p->raddr; fl6->flowi6_oif = p->link; fl6->flowlabel = 0; if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS)) fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET); p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV) dev->flags |= IFF_POINTOPOINT; else dev->flags &= ~IFF_POINTOPOINT; t->tun_hlen = 0; t->hlen = t->encap_hlen + t->tun_hlen; t_hlen = t->hlen + sizeof(struct ipv6hdr); if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, NULL, strict); if (rt) { tdev = rt->dst.dev; ip6_rt_put(rt); } if (!tdev && p->link) tdev = __dev_get_by_index(t->net, p->link); if (tdev) { dev->hard_header_len = tdev->hard_header_len + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); mtu = mtu - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) mtu -= 8; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; WRITE_ONCE(dev->mtu, mtu); } } } /** * ip6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters * * Description: * ip6_tnl_change() updates the tunnel parameters **/ static void ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; t->parms.flags = p->flags; t->parms.hop_limit = p->hop_limit; t->parms.encap_limit = p->encap_limit; t->parms.flowinfo = p->flowinfo; t->parms.link = p->link; t->parms.proto = p->proto; t->parms.fwmark = p->fwmark; dst_cache_reset(&t->dst_cache); ip6_tnl_link_config(t); } static void ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) { struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); ip6_tnl_unlink(ip6n, t); synchronize_net(); ip6_tnl_change(t, p); ip6_tnl_link(ip6n, t); netdev_state_change(t->dev); } static void ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) { /* for default tnl0 device allow to change only the proto */ t->parms.proto = p->proto; netdev_state_change(t->dev); } static void ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u) { p->laddr = u->laddr; p->raddr = u->raddr; p->flags = u->flags; p->hop_limit = u->hop_limit; p->encap_limit = u->encap_limit; p->flowinfo = u->flowinfo; p->link = u->link; p->proto = u->proto; memcpy(p->name, u->name, sizeof(u->name)); } static void ip6_tnl_parm_to_user(struct ip6_tnl_parm *u, const struct __ip6_tnl_parm *p) { u->laddr = p->laddr; u->raddr = p->raddr; u->flags = p->flags; u->hop_limit = p->hop_limit; u->encap_limit = p->encap_limit; u->flowinfo = p->flowinfo; u->link = p->link; u->proto = p->proto; memcpy(u->name, p->name, sizeof(u->name)); } /** * ip6_tnl_siocdevprivate - configure ipv6 tunnels from userspace * @dev: virtual device associated with tunnel * @ifr: unused * @data: parameters passed from userspace * @cmd: command to be performed * * Description: * ip6_tnl_ioctl() is used for managing IPv6 tunnels * from userspace. * * The possible commands are the following: * %SIOCGETTUNNEL: get tunnel parameters for device * %SIOCADDTUNNEL: add tunnel matching given tunnel parameters * %SIOCCHGTUNNEL: change tunnel parameters to those given * %SIOCDELTUNNEL: delete tunnel * * The fallback device "ip6tnl0", created during module * initialization, can be used for creating other tunnel devices. * * Return: * 0 on success, * %-EFAULT if unable to copy data to or from userspace, * %-EPERM if current process hasn't %CAP_NET_ADMIN set * %-EINVAL if passed tunnel parameters are invalid, * %-EEXIST if changing a tunnel's parameters would cause a conflict * %-ENODEV if attempting to change or delete a nonexisting device **/ static int ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { int err = 0; struct ip6_tnl_parm p; struct __ip6_tnl_parm p1; struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); memset(&p1, 0, sizeof(p1)); switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6n->fb_tnl_dev) { if (copy_from_user(&p, data, sizeof(p))) { err = -EFAULT; break; } ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); if (IS_ERR(t)) t = netdev_priv(dev); } else { memset(&p, 0, sizeof(p)); } ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; if (copy_from_user(&p, data, sizeof(p))) break; err = -EINVAL; if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP && p.proto != 0) break; ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL); if (cmd == SIOCCHGTUNNEL) { if (!IS_ERR(t)) { if (t->dev != dev) { err = -EEXIST; break; } } else t = netdev_priv(dev); if (dev == ip6n->fb_tnl_dev) ip6_tnl0_update(t, &p1); else ip6_tnl_update(t, &p1); } if (!IS_ERR(t)) { err = 0; ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; } else { err = PTR_ERR(t); } break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { err = -EFAULT; if (copy_from_user(&p, data, sizeof(p))) break; err = -ENOENT; ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); if (IS_ERR(t)) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) break; dev = t->dev; } err = 0; unregister_netdevice(dev); break; default: err = -EINVAL; } return err; } /** * ip6_tnl_change_mtu - change mtu manually for tunnel device * @dev: virtual device associated with tunnel * @new_mtu: the new mtu * * Return: * 0 on success, * %-EINVAL if mtu too small **/ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { struct ip6_tnl *tnl = netdev_priv(dev); if (tnl->parms.proto == IPPROTO_IPV6) { if (new_mtu < IPV6_MIN_MTU) return -EINVAL; } else { if (new_mtu < ETH_MIN_MTU) return -EINVAL; } if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) { if (new_mtu > IP6_MAX_MTU - dev->hard_header_len) return -EINVAL; } else { if (new_mtu > IP_MAX_MTU - dev->hard_header_len) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(ip6_tnl_change_mtu); int ip6_tnl_get_iflink(const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); return READ_ONCE(t->parms.link); } EXPORT_SYMBOL(ip6_tnl_get_iflink); int ip6_tnl_encap_add_ops(const struct ip6_tnl_encap_ops *ops, unsigned int num) { if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; return !cmpxchg((const struct ip6_tnl_encap_ops **) &ip6tun_encaps[num], NULL, ops) ? 0 : -1; } EXPORT_SYMBOL(ip6_tnl_encap_add_ops); int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *ops, unsigned int num) { int ret; if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; ret = (cmpxchg((const struct ip6_tnl_encap_ops **) &ip6tun_encaps[num], ops, NULL) == ops) ? 0 : -1; synchronize_net(); return ret; } EXPORT_SYMBOL(ip6_tnl_encap_del_ops); int ip6_tnl_encap_setup(struct ip6_tnl *t, struct ip_tunnel_encap *ipencap) { int hlen; memset(&t->encap, 0, sizeof(t->encap)); hlen = ip6_encap_hlen(ipencap); if (hlen < 0) return hlen; t->encap.type = ipencap->type; t->encap.sport = ipencap->sport; t->encap.dport = ipencap->dport; t->encap.flags = ipencap->flags; t->encap_hlen = hlen; t->hlen = t->encap_hlen + t->tun_hlen; return 0; } EXPORT_SYMBOL_GPL(ip6_tnl_encap_setup); static const struct net_device_ops ip6_tnl_netdev_ops = { .ndo_init = ip6_tnl_dev_init, .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_start_xmit, .ndo_siocdevprivate = ip6_tnl_siocdevprivate, .ndo_change_mtu = ip6_tnl_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; #define IPXIPX_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) /** * ip6_tnl_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel * * Description: * Initialize function pointers and device parameters **/ static void ip6_tnl_dev_setup(struct net_device *dev) { dev->netdev_ops = &ip6_tnl_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->features |= NETIF_F_LLTX; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); dev->features |= IPXIPX_FEATURES; dev->hw_features |= IPXIPX_FEATURES; /* This perm addr will be used as interface identifier by IPv6 */ dev->addr_assign_type = NET_ADDR_RANDOM; eth_random_addr(dev->perm_addr); } /** * ip6_tnl_dev_init_gen - general initializer for all tunnel devices * @dev: virtual device associated with tunnel **/ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int ret; int t_hlen; t->dev = dev; t->net = dev_net(dev); ret = dst_cache_init(&t->dst_cache, GFP_KERNEL); if (ret) return ret; ret = gro_cells_init(&t->gro_cells, dev); if (ret) goto destroy_dst; t->tun_hlen = 0; t->hlen = t->encap_hlen + t->tun_hlen; t_hlen = t->hlen + sizeof(struct ipv6hdr); dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); return 0; destroy_dst: dst_cache_destroy(&t->dst_cache); return ret; } /** * ip6_tnl_dev_init - initializer for all non fallback tunnel devices * @dev: virtual device associated with tunnel **/ static int ip6_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int err = ip6_tnl_dev_init_gen(dev); if (err) return err; ip6_tnl_link_config(t); if (t->parms.collect_md) netif_keep_dst(dev); return 0; } /** * ip6_fb_tnl_dev_init - initializer for fallback tunnel device * @dev: fallback device * * Return: 0 **/ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); t->parms.proto = IPPROTO_IPV6; rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } static int ip6_tnl_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_IPV6 && proto != IPPROTO_IPIP && proto != 0) return -EINVAL; return 0; } static void ip6_tnl_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_IPTUN_LINK]) parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); if (data[IFLA_IPTUN_LOCAL]) parms->laddr = nla_get_in6_addr(data[IFLA_IPTUN_LOCAL]); if (data[IFLA_IPTUN_REMOTE]) parms->raddr = nla_get_in6_addr(data[IFLA_IPTUN_REMOTE]); if (data[IFLA_IPTUN_TTL]) parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]); if (data[IFLA_IPTUN_ENCAP_LIMIT]) parms->encap_limit = nla_get_u8(data[IFLA_IPTUN_ENCAP_LIMIT]); if (data[IFLA_IPTUN_FLOWINFO]) parms->flowinfo = nla_get_be32(data[IFLA_IPTUN_FLOWINFO]); if (data[IFLA_IPTUN_FLAGS]) parms->flags = nla_get_u32(data[IFLA_IPTUN_FLAGS]); if (data[IFLA_IPTUN_PROTO]) parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (data[IFLA_IPTUN_COLLECT_METADATA]) parms->collect_md = true; if (data[IFLA_IPTUN_FWMARK]) parms->fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct ip_tunnel_encap ipencap; struct ip6_tnl *nt, *t; int err; nt = netdev_priv(dev); if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) return err; } ip6_tnl_netlink_parms(data, &nt->parms); if (nt->parms.collect_md) { if (rtnl_dereference(ip6n->collect_md_tun)) return -EEXIST; } else { t = ip6_tnl_locate(net, &nt->parms, 0); if (!IS_ERR(t)) return -EEXIST; } err = ip6_tnl_create2(dev); if (!err && tb[IFLA_MTU]) ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); return err; } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm p; struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct ip_tunnel_encap ipencap; if (dev == ip6n->fb_tnl_dev) return -EINVAL; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { int err = ip6_tnl_encap_setup(t, &ipencap); if (err < 0) return err; } ip6_tnl_netlink_parms(data, &p); if (p.collect_md) return -EINVAL; t = ip6_tnl_locate(net, &p, 0); if (!IS_ERR(t)) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); ip6_tnl_update(t, &p); return 0; } static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev != ip6n->fb_tnl_dev) unregister_netdevice_queue(dev, head); } static size_t ip6_tnl_get_size(const struct net_device *dev) { return /* IFLA_IPTUN_LINK */ nla_total_size(4) + /* IFLA_IPTUN_LOCAL */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_REMOTE */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_TTL */ nla_total_size(1) + /* IFLA_IPTUN_ENCAP_LIMIT */ nla_total_size(1) + /* IFLA_IPTUN_FLOWINFO */ nla_total_size(4) + /* IFLA_IPTUN_FLAGS */ nla_total_size(4) + /* IFLA_IPTUN_PROTO */ 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 ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); struct __ip6_tnl_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in6_addr(skb, IFLA_IPTUN_LOCAL, &parm->laddr) || nla_put_in6_addr(skb, IFLA_IPTUN_REMOTE, &parm->raddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, parm->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 (parm->collect_md) if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } struct net *ip6_tnl_get_link_net(const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); return READ_ONCE(tunnel->net); } EXPORT_SYMBOL(ip6_tnl_get_link_net); static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, [IFLA_IPTUN_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_REMOTE] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, [IFLA_IPTUN_ENCAP_LIMIT] = { .type = NLA_U8 }, [IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 }, [IFLA_IPTUN_FLAGS] = { .type = NLA_U32 }, [IFLA_IPTUN_PROTO] = { .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 ip6_link_ops __read_mostly = { .kind = "ip6tnl", .maxtype = IFLA_IPTUN_MAX, .policy = ip6_tnl_policy, .priv_size = sizeof(struct ip6_tnl), .setup = ip6_tnl_dev_setup, .validate = ip6_tnl_validate, .newlink = ip6_tnl_newlink, .changelink = ip6_tnl_changelink, .dellink = ip6_tnl_dellink, .get_size = ip6_tnl_get_size, .fill_info = ip6_tnl_fill_info, .get_link_net = ip6_tnl_get_link_net, }; static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { .handler = ip4ip6_rcv, .err_handler = ip4ip6_err, .priority = 1, }; static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .handler = ip6ip6_rcv, .err_handler = ip6ip6_err, .priority = 1, }; static struct xfrm6_tunnel mplsip6_handler __read_mostly = { .handler = mplsip6_rcv, .err_handler = mplsip6_err, .priority = 1, }; static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct net_device *dev, *aux; int h; struct ip6_tnl *t; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &ip6_link_ops) unregister_netdevice_queue(dev, list); for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, list); t = rtnl_dereference(t->next); } } t = rtnl_dereference(ip6n->tnls_wc[0]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, list); t = rtnl_dereference(t->next); } } static int __net_init ip6_tnl_init_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; if (!net_has_fallback_tunnels(net)) return 0; err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0", NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL; err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) goto err_register; err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; t = netdev_priv(ip6n->fb_tnl_dev); strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: free_netdev(ip6n->fb_tnl_dev); err_alloc_dev: return err; } static void __net_exit ip6_tnl_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) ip6_tnl_destroy_tunnels(net, dev_to_kill); } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, .exit_batch_rtnl = ip6_tnl_exit_batch_rtnl, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), }; /** * ip6_tunnel_init - register protocol and reserve needed resources * * Return: 0 on success **/ static int __init ip6_tunnel_init(void) { int err; if (!ipv6_mod_enabled()) return -EOPNOTSUPP; err = register_pernet_device(&ip6_tnl_net_ops); if (err < 0) goto out_pernet; err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET); if (err < 0) { pr_err("%s: can't register ip4ip6\n", __func__); goto out_ip4ip6; } err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6); if (err < 0) { pr_err("%s: can't register ip6ip6\n", __func__); goto out_ip6ip6; } if (ip6_tnl_mpls_supported()) { err = xfrm6_tunnel_register(&mplsip6_handler, AF_MPLS); if (err < 0) { pr_err("%s: can't register mplsip6\n", __func__); goto out_mplsip6; } } err = rtnl_link_register(&ip6_link_ops); if (err < 0) goto rtnl_link_failed; return 0; rtnl_link_failed: if (ip6_tnl_mpls_supported()) xfrm6_tunnel_deregister(&mplsip6_handler, AF_MPLS); out_mplsip6: xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6); out_ip6ip6: xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET); out_ip4ip6: unregister_pernet_device(&ip6_tnl_net_ops); out_pernet: return err; } /** * ip6_tunnel_cleanup - free resources and unregister protocol **/ static void __exit ip6_tunnel_cleanup(void) { rtnl_link_unregister(&ip6_link_ops); if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET)) pr_info("%s: can't deregister ip4ip6\n", __func__); if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6)) pr_info("%s: can't deregister ip6ip6\n", __func__); if (ip6_tnl_mpls_supported() && xfrm6_tunnel_deregister(&mplsip6_handler, AF_MPLS)) pr_info("%s: can't deregister mplsip6\n", __func__); unregister_pernet_device(&ip6_tnl_net_ops); } module_init(ip6_tunnel_init); module_exit(ip6_tunnel_cleanup); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sctp #if !defined(_TRACE_SCTP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SCTP_H #include <net/sctp/structs.h> #include <linux/tracepoint.h> TRACE_EVENT(sctp_probe_path, TP_PROTO(struct sctp_transport *sp, const struct sctp_association *asoc), TP_ARGS(sp, asoc), TP_STRUCT__entry( __field(__u64, asoc) __field(__u32, primary) __array(__u8, ipaddr, sizeof(union sctp_addr)) __field(__u32, state) __field(__u32, cwnd) __field(__u32, ssthresh) __field(__u32, flight_size) __field(__u32, partial_bytes_acked) __field(__u32, pathmtu) ), TP_fast_assign( __entry->asoc = (unsigned long)asoc; __entry->primary = (sp == asoc->peer.primary_path); memcpy(__entry->ipaddr, &sp->ipaddr, sizeof(union sctp_addr)); __entry->state = sp->state; __entry->cwnd = sp->cwnd; __entry->ssthresh = sp->ssthresh; __entry->flight_size = sp->flight_size; __entry->partial_bytes_acked = sp->partial_bytes_acked; __entry->pathmtu = sp->pathmtu; ), TP_printk("asoc=%#llx%s ipaddr=%pISpc state=%u cwnd=%u ssthresh=%u " "flight_size=%u partial_bytes_acked=%u pathmtu=%u", __entry->asoc, __entry->primary ? "(*)" : "", __entry->ipaddr, __entry->state, __entry->cwnd, __entry->ssthresh, __entry->flight_size, __entry->partial_bytes_acked, __entry->pathmtu) ); TRACE_EVENT(sctp_probe, TP_PROTO(const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk), TP_ARGS(ep, asoc, chunk), TP_STRUCT__entry( __field(__u64, asoc) __field(__u32, mark) __field(__u16, bind_port) __field(__u16, peer_port) __field(__u32, pathmtu) __field(__u32, rwnd) __field(__u16, unack_data) ), TP_fast_assign( struct sk_buff *skb = chunk->skb; __entry->asoc = (unsigned long)asoc; __entry->mark = skb->mark; __entry->bind_port = ep->base.bind_addr.port; __entry->peer_port = asoc->peer.port; __entry->pathmtu = asoc->pathmtu; __entry->rwnd = asoc->peer.rwnd; __entry->unack_data = asoc->unack_data; ), TP_printk("asoc=%#llx mark=%#x bind_port=%d peer_port=%d pathmtu=%d " "rwnd=%u unack_data=%d", __entry->asoc, __entry->mark, __entry->bind_port, __entry->peer_port, __entry->pathmtu, __entry->rwnd, __entry->unack_data) ); #endif /* _TRACE_SCTP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 26 26 26 18 16 16 12 26 14 14 14 14 14 14 28 28 50 50 31 35 35 35 19 11 1 14 14 14 14 26 26 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include "timers.h" #include "device.h" #include "peer.h" #include "socket.h" #include "messages.h" #include "cookie.h" #include <linux/uio.h> #include <linux/inetdevice.h> #include <linux/socket.h> #include <net/ip_tunnels.h> #include <net/udp.h> #include <net/sock.h> static void wg_packet_send_handshake_initiation(struct wg_peer *peer) { struct message_handshake_initiation packet; if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), REKEY_TIMEOUT)) return; /* This function is rate limited. */ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); net_dbg_ratelimited("%s: Sending handshake initiation to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_create_initiation(&packet, &peer->handshake)) { wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), HANDSHAKE_DSCP); wg_timers_handshake_initiated(peer); } } void wg_packet_handshake_send_worker(struct work_struct *work) { struct wg_peer *peer = container_of(work, struct wg_peer, transmit_handshake_work); wg_packet_send_handshake_initiation(peer); wg_peer_put(peer); } void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer, bool is_retry) { if (!is_retry) peer->timer_handshake_attempts = 0; rcu_read_lock_bh(); /* We check last_sent_handshake here in addition to the actual function * we're queueing up, so that we don't queue things if not strictly * necessary: */ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), REKEY_TIMEOUT) || unlikely(READ_ONCE(peer->is_dead))) goto out; wg_peer_get(peer); /* Queues up calling packet_send_queued_handshakes(peer), where we do a * peer_put(peer) after: */ if (!queue_work(peer->device->handshake_send_wq, &peer->transmit_handshake_work)) /* If the work was already queued, we want to drop the * extra reference: */ wg_peer_put(peer); out: rcu_read_unlock_bh(); } void wg_packet_send_handshake_response(struct wg_peer *peer) { struct message_handshake_response packet; atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); net_dbg_ratelimited("%s: Sending handshake response to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_create_response(&packet, &peer->handshake)) { wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); if (wg_noise_handshake_begin_session(&peer->handshake, &peer->keypairs)) { wg_timers_session_derived(peer); wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), HANDSHAKE_DSCP); } } } void wg_packet_send_handshake_cookie(struct wg_device *wg, struct sk_buff *initiating_skb, __le32 sender_index) { struct message_handshake_cookie packet; net_dbg_skb_ratelimited("%s: Sending cookie response for denied handshake message for %pISpfsc\n", wg->dev->name, initiating_skb); wg_cookie_message_create(&packet, initiating_skb, sender_index, &wg->cookie_checker); wg_socket_send_buffer_as_reply_to_skb(wg, initiating_skb, &packet, sizeof(packet)); } static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; bool send; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); send = keypair && READ_ONCE(keypair->sending.is_valid) && (atomic64_read(&keypair->sending_counter) > REKEY_AFTER_MESSAGES || (keypair->i_am_the_initiator && wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME))); rcu_read_unlock_bh(); if (unlikely(send)) wg_packet_send_queued_handshake_initiation(peer, false); } static unsigned int calculate_skb_padding(struct sk_buff *skb) { unsigned int padded_size, last_unit = skb->len; if (unlikely(!PACKET_CB(skb)->mtu)) return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit; /* We do this modulo business with the MTU, just in case the networking * layer gives us a packet that's bigger than the MTU. In that case, we * wouldn't want the final subtraction to overflow in the case of the * padded_size being clamped. Fortunately, that's very rarely the case, * so we optimize for that not happening. */ if (unlikely(last_unit > PACKET_CB(skb)->mtu)) last_unit %= PACKET_CB(skb)->mtu; padded_size = min(PACKET_CB(skb)->mtu, ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE)); return padded_size - last_unit; } static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) { unsigned int padding_len, plaintext_len, trailer_len; struct scatterlist sg[MAX_SKB_FRAGS + 8]; struct message_data *header; struct sk_buff *trailer; int num_frags; /* Force hash calculation before encryption so that flow analysis is * consistent over the inner packet. */ skb_get_hash(skb); /* Calculate lengths. */ padding_len = calculate_skb_padding(skb); trailer_len = padding_len + noise_encrypted_len(0); plaintext_len = skb->len + padding_len; /* Expand data section to have room for padding and auth tag. */ num_frags = skb_cow_data(skb, trailer_len, &trailer); if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg))) return false; /* Set the padding to zeros, and make sure it and the auth tag are part * of the skb. */ memset(skb_tail_pointer(trailer), 0, padding_len); /* Expand head section to have room for our header and the network * stack's headers. */ if (unlikely(skb_cow_head(skb, DATA_PACKET_HEAD_ROOM) < 0)) return false; /* Finalize checksum calculation for the inner packet, if required. */ if (unlikely(skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))) return false; /* Only after checksumming can we safely add on the padding at the end * and the header. */ skb_set_inner_network_header(skb, 0); header = (struct message_data *)skb_push(skb, sizeof(*header)); header->header.type = cpu_to_le32(MESSAGE_DATA); header->key_idx = keypair->remote_index; header->counter = cpu_to_le64(PACKET_CB(skb)->nonce); pskb_put(skb, trailer, trailer_len); /* Now we can encrypt the scattergather segments */ sg_init_table(sg, num_frags); if (skb_to_sgvec(skb, sg, sizeof(struct message_data), noise_encrypted_len(plaintext_len)) <= 0) return false; return chacha20poly1305_encrypt_sg_inplace(sg, plaintext_len, NULL, 0, PACKET_CB(skb)->nonce, keypair->sending.key); } void wg_packet_send_keepalive(struct wg_peer *peer) { struct sk_buff *skb; if (skb_queue_empty(&peer->staged_packet_queue)) { skb = alloc_skb(DATA_PACKET_HEAD_ROOM + MESSAGE_MINIMUM_LENGTH, GFP_ATOMIC); if (unlikely(!skb)) return; skb_reserve(skb, DATA_PACKET_HEAD_ROOM); skb->dev = peer->device->dev; PACKET_CB(skb)->mtu = skb->dev->mtu; skb_queue_tail(&peer->staged_packet_queue, skb); net_dbg_ratelimited("%s: Sending keepalive packet to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); } wg_packet_send_staged_packets(peer); } static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first) { struct sk_buff *skb, *next; bool is_keepalive, data_sent = false; wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); skb_list_walk_safe(first, skb, next) { is_keepalive = skb->len == message_data_len(0); if (likely(!wg_socket_send_skb_to_peer(peer, skb, PACKET_CB(skb)->ds) && !is_keepalive)) data_sent = true; } if (likely(data_sent)) wg_timers_data_sent(peer); keep_key_fresh(peer); } void wg_packet_tx_worker(struct work_struct *work) { struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work); struct noise_keypair *keypair; enum packet_state state; struct sk_buff *first; while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL && (state = atomic_read_acquire(&PACKET_CB(first)->state)) != PACKET_STATE_UNCRYPTED) { wg_prev_queue_drop_peeked(&peer->tx_queue); keypair = PACKET_CB(first)->keypair; if (likely(state == PACKET_STATE_CRYPTED)) wg_packet_create_data_done(peer, first); else kfree_skb_list(first); wg_noise_keypair_put(keypair, false); wg_peer_put(peer); if (need_resched()) cond_resched(); } } void wg_packet_encrypt_worker(struct work_struct *work) { struct crypt_queue *queue = container_of(work, struct multicore_worker, work)->ptr; struct sk_buff *first, *skb, *next; while ((first = ptr_ring_consume_bh(&queue->ring)) != NULL) { enum packet_state state = PACKET_STATE_CRYPTED; skb_list_walk_safe(first, skb, next) { if (likely(encrypt_packet(skb, PACKET_CB(first)->keypair))) { wg_reset_packet(skb, true); } else { state = PACKET_STATE_DEAD; break; } } wg_queue_enqueue_per_peer_tx(first, state); if (need_resched()) cond_resched(); } } static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) { struct wg_device *wg = peer->device; int ret = -EINVAL; rcu_read_lock_bh(); if (unlikely(READ_ONCE(peer->is_dead))) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); err: rcu_read_unlock_bh(); if (likely(!ret || ret == -EPIPE)) return; wg_noise_keypair_put(PACKET_CB(first)->keypair, false); wg_peer_put(peer); kfree_skb_list(first); } void wg_packet_purge_staged_packets(struct wg_peer *peer) { spin_lock_bh(&peer->staged_packet_queue.lock); DEV_STATS_ADD(peer->device->dev, tx_dropped, peer->staged_packet_queue.qlen); __skb_queue_purge(&peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); } void wg_packet_send_staged_packets(struct wg_peer *peer) { struct noise_keypair *keypair; struct sk_buff_head packets; struct sk_buff *skb; /* Steal the current queue into our local one. */ __skb_queue_head_init(&packets); spin_lock_bh(&peer->staged_packet_queue.lock); skb_queue_splice_init(&peer->staged_packet_queue, &packets); spin_unlock_bh(&peer->staged_packet_queue.lock); if (unlikely(skb_queue_empty(&packets))) return; /* First we make sure we have a valid reference to a valid key. */ rcu_read_lock_bh(); keypair = wg_noise_keypair_get( rcu_dereference_bh(peer->keypairs.current_keypair)); rcu_read_unlock_bh(); if (unlikely(!keypair)) goto out_nokey; if (unlikely(!READ_ONCE(keypair->sending.is_valid))) goto out_nokey; if (unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, REJECT_AFTER_TIME))) goto out_invalid; /* After we know we have a somewhat valid key, we now try to assign * nonces to all of the packets in the queue. If we can't assign nonces * for all of them, we just consider it a failure and wait for the next * handshake. */ skb_queue_walk(&packets, skb) { /* 0 for no outer TOS: no leak. TODO: at some later point, we * might consider using flowi->tos as outer instead. */ PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb); PACKET_CB(skb)->nonce = atomic64_inc_return(&keypair->sending_counter) - 1; if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES)) goto out_invalid; } packets.prev->next = NULL; wg_peer_get(keypair->entry.peer); PACKET_CB(packets.next)->keypair = keypair; wg_packet_create_data(peer, packets.next); return; out_invalid: WRITE_ONCE(keypair->sending.is_valid, false); out_nokey: wg_noise_keypair_put(keypair, false); /* We orphan the packets if we're waiting on a handshake, so that they * don't block a socket's pool. */ skb_queue_walk(&packets, skb) skb_orphan(skb); /* Then we put them back on the top of the queue. We're not too * concerned about accidentally getting things a little out of order if * packets are being added really fast, because this queue is for before * packets can even be sent and it's small anyway. */ spin_lock_bh(&peer->staged_packet_queue.lock); skb_queue_splice(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); /* If we're exiting because there's something wrong with the key, it * means we should initiate a new handshake. */ wg_packet_send_queued_handshake_initiation(peer, false); } |
| 25 1 231 9 24 134 99 170 44 319 23 319 13453 734 24 333 320 319 2 237 5 5 5 162 163 162 608 597 13 596 15 15 306 20 20 20 259 626 38 104 112 15169 89 87 32 4 86 89 577 577 34 47 391 168 40 20 22 223 90 31 176 113 80 160 10 3 1286 3 19 228 304 251 554 55 549 582 261 172 12569 223 |