| 45 45 3 3 85 88 83 14 82 11 11 72 72 18 71 68 90 89 71 48 68 45 37 1 1 1 68 31 68 1 1 1 1 1 1 2 2 2 2 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 | // SPDX-License-Identifier: GPL-2.0-only /* * DCCP connection tracking protocol helper * * Copyright (c) 2005, 2006, 2008 Patrick McHardy <kaber@trash.net> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/sysctl.h> #include <linux/spinlock.h> #include <linux/skbuff.h> #include <linux/dccp.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/netfilter/nfnetlink_conntrack.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_log.h> /* Timeouts are based on values from RFC4340: * * - REQUEST: * * 8.1.2. Client Request * * A client MAY give up on its DCCP-Requests after some time * (3 minutes, for example). * * - RESPOND: * * 8.1.3. Server Response * * It MAY also leave the RESPOND state for CLOSED after a timeout of * not less than 4MSL (8 minutes); * * - PARTOPEN: * * 8.1.5. Handshake Completion * * If the client remains in PARTOPEN for more than 4MSL (8 minutes), * it SHOULD reset the connection with Reset Code 2, "Aborted". * * - OPEN: * * The DCCP timestamp overflows after 11.9 hours. If the connection * stays idle this long the sequence number won't be recognized * as valid anymore. * * - CLOSEREQ/CLOSING: * * 8.3. Termination * * The retransmission timer should initially be set to go off in two * round-trip times and should back off to not less than once every * 64 seconds ... * * - TIMEWAIT: * * 4.3. States * * A server or client socket remains in this state for 2MSL (4 minutes) * after the connection has been town down, ... */ #define DCCP_MSL (2 * 60 * HZ) #ifdef CONFIG_NF_CONNTRACK_PROCFS static const char * const dccp_state_names[] = { [CT_DCCP_NONE] = "NONE", [CT_DCCP_REQUEST] = "REQUEST", [CT_DCCP_RESPOND] = "RESPOND", [CT_DCCP_PARTOPEN] = "PARTOPEN", [CT_DCCP_OPEN] = "OPEN", [CT_DCCP_CLOSEREQ] = "CLOSEREQ", [CT_DCCP_CLOSING] = "CLOSING", [CT_DCCP_TIMEWAIT] = "TIMEWAIT", [CT_DCCP_IGNORE] = "IGNORE", [CT_DCCP_INVALID] = "INVALID", }; #endif #define sNO CT_DCCP_NONE #define sRQ CT_DCCP_REQUEST #define sRS CT_DCCP_RESPOND #define sPO CT_DCCP_PARTOPEN #define sOP CT_DCCP_OPEN #define sCR CT_DCCP_CLOSEREQ #define sCG CT_DCCP_CLOSING #define sTW CT_DCCP_TIMEWAIT #define sIG CT_DCCP_IGNORE #define sIV CT_DCCP_INVALID /* * DCCP state transition table * * The assumption is the same as for TCP tracking: * * We are the man in the middle. All the packets go through us but might * get lost in transit to the destination. It is assumed that the destination * can't receive segments we haven't seen. * * The following states exist: * * NONE: Initial state, expecting Request * REQUEST: Request seen, waiting for Response from server * RESPOND: Response from server seen, waiting for Ack from client * PARTOPEN: Ack after Response seen, waiting for packet other than Response, * Reset or Sync from server * OPEN: Packet other than Response, Reset or Sync seen * CLOSEREQ: CloseReq from server seen, expecting Close from client * CLOSING: Close seen, expecting Reset * TIMEWAIT: Reset seen * IGNORE: Not determinable whether packet is valid * * Some states exist only on one side of the connection: REQUEST, RESPOND, * PARTOPEN, CLOSEREQ. For the other side these states are equivalent to * the one it was in before. * * Packets are marked as ignored (sIG) if we don't know if they're valid * (for example a reincarnation of a connection we didn't notice is dead * already) and the server may send back a connection closing Reset or a * Response. They're also used for Sync/SyncAck packets, which we don't * care about. */ static const u_int8_t dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = { [CT_DCCP_ROLE_CLIENT] = { [DCCP_PKT_REQUEST] = { /* * sNO -> sRQ Regular Request * sRQ -> sRQ Retransmitted Request or reincarnation * sRS -> sRS Retransmitted Request (apparently Response * got lost after we saw it) or reincarnation * sPO -> sIG Ignore, conntrack might be out of sync * sOP -> sIG Ignore, conntrack might be out of sync * sCR -> sIG Ignore, conntrack might be out of sync * sCG -> sIG Ignore, conntrack might be out of sync * sTW -> sRQ Reincarnation * * sNO, sRQ, sRS, sPO. sOP, sCR, sCG, sTW, */ sRQ, sRQ, sRS, sIG, sIG, sIG, sIG, sRQ, }, [DCCP_PKT_RESPONSE] = { /* * sNO -> sIV Invalid * sRQ -> sIG Ignore, might be response to ignored Request * sRS -> sIG Ignore, might be response to ignored Request * sPO -> sIG Ignore, might be response to ignored Request * sOP -> sIG Ignore, might be response to ignored Request * sCR -> sIG Ignore, might be response to ignored Request * sCG -> sIG Ignore, might be response to ignored Request * sTW -> sIV Invalid, reincarnation in reverse direction * goes through sRQ * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIV, }, [DCCP_PKT_ACK] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sPO Ack for Response, move to PARTOPEN (8.1.5.) * sPO -> sPO Retransmitted Ack for Response, remain in PARTOPEN * sOP -> sOP Regular ACK, remain in OPEN * sCR -> sCR Ack in CLOSEREQ MAY be processed (8.3.) * sCG -> sCG Ack in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sPO, sPO, sOP, sCR, sCG, sIV }, [DCCP_PKT_DATA] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sIV MUST use DataAck in PARTOPEN state (8.1.5.) * sOP -> sOP Regular Data packet * sCR -> sCR Data in CLOSEREQ MAY be processed (8.3.) * sCG -> sCG Data in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sIV, sOP, sCR, sCG, sIV, }, [DCCP_PKT_DATAACK] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sPO Ack for Response, move to PARTOPEN (8.1.5.) * sPO -> sPO Remain in PARTOPEN state * sOP -> sOP Regular DataAck packet in OPEN state * sCR -> sCR DataAck in CLOSEREQ MAY be processed (8.3.) * sCG -> sCG DataAck in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sPO, sPO, sOP, sCR, sCG, sIV }, [DCCP_PKT_CLOSEREQ] = { /* * CLOSEREQ may only be sent by the server. * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }, [DCCP_PKT_CLOSE] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sCG Client-initiated close * sOP -> sCG Client-initiated close * sCR -> sCG Close in response to CloseReq (8.3.) * sCG -> sCG Retransmit * sTW -> sIV Late retransmit, already in TIME_WAIT * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sCG, sCG, sCG, sIV, sIV }, [DCCP_PKT_RESET] = { /* * sNO -> sIV No connection * sRQ -> sTW Sync received or timeout, SHOULD send Reset (8.1.1.) * sRS -> sTW Response received without Request * sPO -> sTW Timeout, SHOULD send Reset (8.1.5.) * sOP -> sTW Connection reset * sCR -> sTW Connection reset * sCG -> sTW Connection reset * sTW -> sIG Ignore (don't refresh timer) * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sTW, sTW, sTW, sTW, sTW, sTW, sIG }, [DCCP_PKT_SYNC] = { /* * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, [CT_DCCP_ROLE_SERVER] = { [DCCP_PKT_REQUEST] = { /* * sNO -> sIV Invalid * sRQ -> sIG Ignore, conntrack might be out of sync * sRS -> sIG Ignore, conntrack might be out of sync * sPO -> sIG Ignore, conntrack might be out of sync * sOP -> sIG Ignore, conntrack might be out of sync * sCR -> sIG Ignore, conntrack might be out of sync * sCG -> sIG Ignore, conntrack might be out of sync * sTW -> sRQ Reincarnation, must reverse roles * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sRQ }, [DCCP_PKT_RESPONSE] = { /* * sNO -> sIV Response without Request * sRQ -> sRS Response to clients Request * sRS -> sRS Retransmitted Response (8.1.3. SHOULD NOT) * sPO -> sIG Response to an ignored Request or late retransmit * sOP -> sIG Ignore, might be response to ignored Request * sCR -> sIG Ignore, might be response to ignored Request * sCG -> sIG Ignore, might be response to ignored Request * sTW -> sIV Invalid, Request from client in sTW moves to sRQ * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sRS, sRS, sIG, sIG, sIG, sIG, sIV }, [DCCP_PKT_ACK] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sOP Enter OPEN state (8.1.5.) * sOP -> sOP Regular Ack in OPEN state * sCR -> sIV Waiting for Close from client * sCG -> sCG Ack in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV }, [DCCP_PKT_DATA] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sOP Enter OPEN state (8.1.5.) * sOP -> sOP Regular Data packet in OPEN state * sCR -> sIV Waiting for Close from client * sCG -> sCG Data in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV }, [DCCP_PKT_DATAACK] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sOP Enter OPEN state (8.1.5.) * sOP -> sOP Regular DataAck in OPEN state * sCR -> sIV Waiting for Close from client * sCG -> sCG Data in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV }, [DCCP_PKT_CLOSEREQ] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sOP -> sCR Move directly to CLOSEREQ (8.1.5.) * sOP -> sCR CloseReq in OPEN state * sCR -> sCR Retransmit * sCG -> sCR Simultaneous close, client sends another Close * sTW -> sIV Already closed * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sCR, sCR, sCR, sCR, sIV }, [DCCP_PKT_CLOSE] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sOP -> sCG Move direcly to CLOSING * sOP -> sCG Move to CLOSING * sCR -> sIV Close after CloseReq is invalid * sCG -> sCG Retransmit * sTW -> sIV Already closed * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sCG, sCG, sIV, sCG, sIV }, [DCCP_PKT_RESET] = { /* * sNO -> sIV No connection * sRQ -> sTW Reset in response to Request * sRS -> sTW Timeout, SHOULD send Reset (8.1.3.) * sPO -> sTW Timeout, SHOULD send Reset (8.1.3.) * sOP -> sTW * sCR -> sTW * sCG -> sTW * sTW -> sIG Ignore (don't refresh timer) * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW, sTW */ sIV, sTW, sTW, sTW, sTW, sTW, sTW, sTW, sIG }, [DCCP_PKT_SYNC] = { /* * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, }; static noinline bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, const struct dccp_hdr *dh, const struct nf_hook_state *hook_state) { struct net *net = nf_ct_net(ct); struct nf_dccp_net *dn; const char *msg; u_int8_t state; state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE]; switch (state) { default: dn = nf_dccp_pernet(net); if (dn->dccp_loose == 0) { msg = "not picking up existing connection "; goto out_invalid; } break; case CT_DCCP_REQUEST: break; case CT_DCCP_INVALID: msg = "invalid state transition "; goto out_invalid; } ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT; ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER; ct->proto.dccp.state = CT_DCCP_NONE; ct->proto.dccp.last_pkt = DCCP_PKT_REQUEST; ct->proto.dccp.last_dir = IP_CT_DIR_ORIGINAL; ct->proto.dccp.handshake_seq = 0; return true; out_invalid: nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", msg); return false; } static u64 dccp_ack_seq(const struct dccp_hdr *dh) { const struct dccp_hdr_ack_bits *dhack; dhack = (void *)dh + __dccp_basic_hdr_len(dh); return ((u64)ntohs(dhack->dccph_ack_nr_high) << 32) + ntohl(dhack->dccph_ack_nr_low); } static bool dccp_error(const struct dccp_hdr *dh, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { static const unsigned long require_seq48 = 1 << DCCP_PKT_REQUEST | 1 << DCCP_PKT_RESPONSE | 1 << DCCP_PKT_CLOSEREQ | 1 << DCCP_PKT_CLOSE | 1 << DCCP_PKT_RESET | 1 << DCCP_PKT_SYNC | 1 << DCCP_PKT_SYNCACK; unsigned int dccp_len = skb->len - dataoff; unsigned int cscov; const char *msg; u8 type; BUILD_BUG_ON(DCCP_PKT_INVALID >= BITS_PER_LONG); if (dh->dccph_doff * 4 < sizeof(struct dccp_hdr) || dh->dccph_doff * 4 > dccp_len) { msg = "nf_ct_dccp: truncated/malformed packet "; goto out_invalid; } cscov = dccp_len; if (dh->dccph_cscov) { cscov = (dh->dccph_cscov - 1) * 4; if (cscov > dccp_len) { msg = "nf_ct_dccp: bad checksum coverage "; goto out_invalid; } } if (state->hook == NF_INET_PRE_ROUTING && state->net->ct.sysctl_checksum && nf_checksum_partial(skb, state->hook, dataoff, cscov, IPPROTO_DCCP, state->pf)) { msg = "nf_ct_dccp: bad checksum "; goto out_invalid; } type = dh->dccph_type; if (type >= DCCP_PKT_INVALID) { msg = "nf_ct_dccp: reserved packet type "; goto out_invalid; } if (test_bit(type, &require_seq48) && !dh->dccph_x) { msg = "nf_ct_dccp: type lacks 48bit sequence numbers"; goto out_invalid; } return false; out_invalid: nf_l4proto_log_invalid(skb, state, IPPROTO_DCCP, "%s", msg); return true; } struct nf_conntrack_dccp_buf { struct dccp_hdr dh; /* generic header part */ struct dccp_hdr_ext ext; /* optional depending dh->dccph_x */ union { /* depends on header type */ struct dccp_hdr_ack_bits ack; struct dccp_hdr_request req; struct dccp_hdr_response response; struct dccp_hdr_reset rst; } u; }; static struct dccp_hdr * dccp_header_pointer(const struct sk_buff *skb, int offset, const struct dccp_hdr *dh, struct nf_conntrack_dccp_buf *buf) { unsigned int hdrlen = __dccp_hdr_len(dh); if (hdrlen > sizeof(*buf)) return NULL; return skb_header_pointer(skb, offset, hdrlen, buf); } int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct nf_conntrack_dccp_buf _dh; u_int8_t type, old_state, new_state; enum ct_dccp_roles role; unsigned int *timeouts; struct dccp_hdr *dh; dh = skb_header_pointer(skb, dataoff, sizeof(*dh), &_dh.dh); if (!dh) return NF_DROP; if (dccp_error(dh, skb, dataoff, state)) return -NF_ACCEPT; /* pull again, including possible 48 bit sequences and subtype header */ dh = dccp_header_pointer(skb, dataoff, dh, &_dh); if (!dh) return NF_DROP; type = dh->dccph_type; if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh, state)) return -NF_ACCEPT; if (type == DCCP_PKT_RESET && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { /* Tear down connection immediately if only reply is a RESET */ nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } spin_lock_bh(&ct->lock); role = ct->proto.dccp.role[dir]; old_state = ct->proto.dccp.state; new_state = dccp_state_table[role][type][old_state]; switch (new_state) { case CT_DCCP_REQUEST: if (old_state == CT_DCCP_TIMEWAIT && role == CT_DCCP_ROLE_SERVER) { /* Reincarnation in the reverse direction: reopen and * reverse client/server roles. */ ct->proto.dccp.role[dir] = CT_DCCP_ROLE_CLIENT; ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_SERVER; } break; case CT_DCCP_RESPOND: if (old_state == CT_DCCP_REQUEST) ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh); break; case CT_DCCP_PARTOPEN: if (old_state == CT_DCCP_RESPOND && type == DCCP_PKT_ACK && dccp_ack_seq(dh) == ct->proto.dccp.handshake_seq) set_bit(IPS_ASSURED_BIT, &ct->status); break; case CT_DCCP_IGNORE: /* * Connection tracking might be out of sync, so we ignore * packets that might establish a new connection and resync * if the server responds with a valid Response. */ if (ct->proto.dccp.last_dir == !dir && ct->proto.dccp.last_pkt == DCCP_PKT_REQUEST && type == DCCP_PKT_RESPONSE) { ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_CLIENT; ct->proto.dccp.role[dir] = CT_DCCP_ROLE_SERVER; ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh); new_state = CT_DCCP_RESPOND; break; } ct->proto.dccp.last_dir = dir; ct->proto.dccp.last_pkt = type; spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "%s", "invalid packet"); return NF_ACCEPT; case CT_DCCP_INVALID: spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "%s", "invalid state transition"); return -NF_ACCEPT; } ct->proto.dccp.last_dir = dir; ct->proto.dccp.last_pkt = type; ct->proto.dccp.state = new_state; spin_unlock_bh(&ct->lock); if (new_state != old_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = nf_dccp_pernet(nf_ct_net(ct))->dccp_timeout; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; } static bool dccp_can_early_drop(const struct nf_conn *ct) { switch (ct->proto.dccp.state) { case CT_DCCP_CLOSEREQ: case CT_DCCP_CLOSING: case CT_DCCP_TIMEWAIT: return true; default: break; } return false; } #ifdef CONFIG_NF_CONNTRACK_PROCFS static void dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]); } #endif #if IS_ENABLED(CONFIG_NF_CT_NETLINK) static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct, bool destroy) { struct nlattr *nest_parms; spin_lock_bh(&ct->lock); nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state)) goto nla_put_failure; if (destroy) goto skip_state; if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_ROLE, ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]) || nla_put_be64(skb, CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ, cpu_to_be64(ct->proto.dccp.handshake_seq), CTA_PROTOINFO_DCCP_PAD)) goto nla_put_failure; skip_state: nla_nest_end(skb, nest_parms); spin_unlock_bh(&ct->lock); return 0; nla_put_failure: spin_unlock_bh(&ct->lock); return -1; } static const struct nla_policy dccp_nla_policy[CTA_PROTOINFO_DCCP_MAX + 1] = { [CTA_PROTOINFO_DCCP_STATE] = { .type = NLA_U8 }, [CTA_PROTOINFO_DCCP_ROLE] = { .type = NLA_U8 }, [CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ] = { .type = NLA_U64 }, [CTA_PROTOINFO_DCCP_PAD] = { .type = NLA_UNSPEC }, }; #define DCCP_NLATTR_SIZE ( \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + sizeof(u64)) + \ NLA_ALIGN(NLA_HDRLEN + 0)) static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) { struct nlattr *attr = cda[CTA_PROTOINFO_DCCP]; struct nlattr *tb[CTA_PROTOINFO_DCCP_MAX + 1]; int err; if (!attr) return 0; err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_DCCP_MAX, attr, dccp_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_PROTOINFO_DCCP_STATE] || !tb[CTA_PROTOINFO_DCCP_ROLE] || nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) > CT_DCCP_ROLE_MAX || nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]) >= CT_DCCP_IGNORE) { return -EINVAL; } spin_lock_bh(&ct->lock); ct->proto.dccp.state = nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]); if (nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) == CT_DCCP_ROLE_CLIENT) { ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT; ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER; } else { ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_SERVER; ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_CLIENT; } if (tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ]) { ct->proto.dccp.handshake_seq = be64_to_cpu(nla_get_be64(tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ])); } spin_unlock_bh(&ct->lock); return 0; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { struct nf_dccp_net *dn = nf_dccp_pernet(net); unsigned int *timeouts = data; int i; if (!timeouts) timeouts = dn->dccp_timeout; /* set default DCCP timeouts. */ for (i=0; i<CT_DCCP_MAX; i++) timeouts[i] = dn->dccp_timeout[i]; /* there's a 1:1 mapping between attributes and protocol states. */ for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) { if (tb[i]) { timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } timeouts[CTA_TIMEOUT_DCCP_UNSPEC] = timeouts[CTA_TIMEOUT_DCCP_REQUEST]; return 0; } static int dccp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; int i; for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) { if (nla_put_be32(skb, i, htonl(timeouts[i] / HZ))) goto nla_put_failure; } return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = { [CTA_TIMEOUT_DCCP_REQUEST] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_RESPOND] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_PARTOPEN] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_OPEN] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_CLOSEREQ] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_CLOSING] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_TIMEWAIT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_dccp_init_net(struct net *net) { struct nf_dccp_net *dn = nf_dccp_pernet(net); /* default values */ dn->dccp_loose = 1; dn->dccp_timeout[CT_DCCP_REQUEST] = 2 * DCCP_MSL; dn->dccp_timeout[CT_DCCP_RESPOND] = 4 * DCCP_MSL; dn->dccp_timeout[CT_DCCP_PARTOPEN] = 4 * DCCP_MSL; dn->dccp_timeout[CT_DCCP_OPEN] = 12 * 3600 * HZ; dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; /* timeouts[0] is unused, make it same as SYN_SENT so * ->timeouts[0] contains 'new' timeout, like udp or icmp. */ dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST]; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp = { .l4proto = IPPROTO_DCCP, .can_early_drop = dccp_can_early_drop, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = dccp_print_conntrack, #endif #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_size = DCCP_NLATTR_SIZE, .to_nlattr = dccp_to_nlattr, .from_nlattr = nlattr_to_dccp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = dccp_timeout_nlattr_to_obj, .obj_to_nlattr = dccp_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_DCCP_MAX, .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, .nla_policy = dccp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 6 3 7 6 5 6 6 6 3 2 1 1 3 3 3 6 5 3 3 3 2 6 3 3 1 1 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 | // SPDX-License-Identifier: GPL-2.0-only /* * TCP Illinois congestion control. * Home page: * http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html * * The algorithm is described in: * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm * for High-Speed Networks" * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf * * Implemented from description in paper and ns-2 simulation. * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/inet_diag.h> #include <asm/div64.h> #include <net/tcp.h> #define ALPHA_SHIFT 7 #define ALPHA_SCALE (1u<<ALPHA_SHIFT) #define ALPHA_MIN ((3*ALPHA_SCALE)/10) /* ~0.3 */ #define ALPHA_MAX (10*ALPHA_SCALE) /* 10.0 */ #define ALPHA_BASE ALPHA_SCALE /* 1.0 */ #define RTT_MAX (U32_MAX / ALPHA_MAX) /* 3.3 secs */ #define BETA_SHIFT 6 #define BETA_SCALE (1u<<BETA_SHIFT) #define BETA_MIN (BETA_SCALE/8) /* 0.125 */ #define BETA_MAX (BETA_SCALE/2) /* 0.5 */ #define BETA_BASE BETA_MAX static int win_thresh __read_mostly = 15; module_param(win_thresh, int, 0); MODULE_PARM_DESC(win_thresh, "Window threshold for starting adaptive sizing"); static int theta __read_mostly = 5; module_param(theta, int, 0); MODULE_PARM_DESC(theta, "# of fast RTT's before full growth"); /* TCP Illinois Parameters */ struct illinois { u64 sum_rtt; /* sum of rtt's measured within last rtt */ u16 cnt_rtt; /* # of rtts measured within last rtt */ u32 base_rtt; /* min of all rtt in usec */ u32 max_rtt; /* max of all rtt in usec */ u32 end_seq; /* right edge of current RTT */ u32 alpha; /* Additive increase */ u32 beta; /* Muliplicative decrease */ u16 acked; /* # packets acked by current ACK */ u8 rtt_above; /* average rtt has gone above threshold */ u8 rtt_low; /* # of rtts measurements below threshold */ }; static void rtt_reset(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); ca->end_seq = tp->snd_nxt; ca->cnt_rtt = 0; ca->sum_rtt = 0; /* TODO: age max_rtt? */ } static void tcp_illinois_init(struct sock *sk) { struct illinois *ca = inet_csk_ca(sk); ca->alpha = ALPHA_MAX; ca->beta = BETA_BASE; ca->base_rtt = 0x7fffffff; ca->max_rtt = 0; ca->acked = 0; ca->rtt_low = 0; ca->rtt_above = 0; rtt_reset(sk); } /* Measure RTT for each ack. */ static void tcp_illinois_acked(struct sock *sk, const struct ack_sample *sample) { struct illinois *ca = inet_csk_ca(sk); s32 rtt_us = sample->rtt_us; ca->acked = sample->pkts_acked; /* dup ack, no rtt sample */ if (rtt_us < 0) return; /* ignore bogus values, this prevents wraparound in alpha math */ if (rtt_us > RTT_MAX) rtt_us = RTT_MAX; /* keep track of minimum RTT seen so far */ if (ca->base_rtt > rtt_us) ca->base_rtt = rtt_us; /* and max */ if (ca->max_rtt < rtt_us) ca->max_rtt = rtt_us; ++ca->cnt_rtt; ca->sum_rtt += rtt_us; } /* Maximum queuing delay */ static inline u32 max_delay(const struct illinois *ca) { return ca->max_rtt - ca->base_rtt; } /* Average queuing delay */ static inline u32 avg_delay(const struct illinois *ca) { u64 t = ca->sum_rtt; do_div(t, ca->cnt_rtt); return t - ca->base_rtt; } /* * Compute value of alpha used for additive increase. * If small window then use 1.0, equivalent to Reno. * * For larger windows, adjust based on average delay. * A. If average delay is at minimum (we are uncongested), * then use large alpha (10.0) to increase faster. * B. If average delay is at maximum (getting congested) * then use small alpha (0.3) * * The result is a convex window growth curve. */ static u32 alpha(struct illinois *ca, u32 da, u32 dm) { u32 d1 = dm / 100; /* Low threshold */ if (da <= d1) { /* If never got out of low delay zone, then use max */ if (!ca->rtt_above) return ALPHA_MAX; /* Wait for 5 good RTT's before allowing alpha to go alpha max. * This prevents one good RTT from causing sudden window increase. */ if (++ca->rtt_low < theta) return ca->alpha; ca->rtt_low = 0; ca->rtt_above = 0; return ALPHA_MAX; } ca->rtt_above = 1; /* * Based on: * * (dm - d1) amin amax * k1 = ------------------- * amax - amin * * (dm - d1) amin * k2 = ---------------- - d1 * amax - amin * * k1 * alpha = ---------- * k2 + da */ dm -= d1; da -= d1; return (dm * ALPHA_MAX) / (dm + (da * (ALPHA_MAX - ALPHA_MIN)) / ALPHA_MIN); } /* * Beta used for multiplicative decrease. * For small window sizes returns same value as Reno (0.5) * * If delay is small (10% of max) then beta = 1/8 * If delay is up to 80% of max then beta = 1/2 * In between is a linear function */ static u32 beta(u32 da, u32 dm) { u32 d2, d3; d2 = dm / 10; if (da <= d2) return BETA_MIN; d3 = (8 * dm) / 10; if (da >= d3 || d3 <= d2) return BETA_MAX; /* * Based on: * * bmin d3 - bmax d2 * k3 = ------------------- * d3 - d2 * * bmax - bmin * k4 = ------------- * d3 - d2 * * b = k3 + k4 da */ return (BETA_MIN * d3 - BETA_MAX * d2 + (BETA_MAX - BETA_MIN) * da) / (d3 - d2); } /* Update alpha and beta values once per RTT */ static void update_params(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); if (tcp_snd_cwnd(tp) < win_thresh) { ca->alpha = ALPHA_BASE; ca->beta = BETA_BASE; } else if (ca->cnt_rtt > 0) { u32 dm = max_delay(ca); u32 da = avg_delay(ca); ca->alpha = alpha(ca, da, dm); ca->beta = beta(da, dm); } rtt_reset(sk); } /* * In case of loss, reset to default values */ static void tcp_illinois_state(struct sock *sk, u8 new_state) { struct illinois *ca = inet_csk_ca(sk); if (new_state == TCP_CA_Loss) { ca->alpha = ALPHA_BASE; ca->beta = BETA_BASE; ca->rtt_low = 0; ca->rtt_above = 0; rtt_reset(sk); } } /* * Increase window in response to successful acknowledgment. */ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); if (after(ack, ca->end_seq)) update_params(sk); /* RFC2861 only increase cwnd if fully utilized */ if (!tcp_is_cwnd_limited(sk)) return; /* In slow start */ if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { u32 delta; /* snd_cwnd_cnt is # of packets since last cwnd increment */ tp->snd_cwnd_cnt += ca->acked; ca->acked = 1; /* This is close approximation of: * tp->snd_cwnd += alpha/tp->snd_cwnd */ delta = (tp->snd_cwnd_cnt * ca->alpha) >> ALPHA_SHIFT; if (delta >= tcp_snd_cwnd(tp)) { tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp) + delta / tcp_snd_cwnd(tp), (u32)tp->snd_cwnd_clamp)); tp->snd_cwnd_cnt = 0; } } } static u32 tcp_illinois_ssthresh(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); u32 decr; /* Multiplicative decrease */ decr = (tcp_snd_cwnd(tp) * ca->beta) >> BETA_SHIFT; return max(tcp_snd_cwnd(tp) - decr, 2U); } /* Extract info for Tcp socket info provided via netlink. */ static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { const struct illinois *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { info->vegas.tcpv_enabled = 1; info->vegas.tcpv_rttcnt = ca->cnt_rtt; info->vegas.tcpv_minrtt = ca->base_rtt; info->vegas.tcpv_rtt = 0; if (info->vegas.tcpv_rttcnt > 0) { u64 t = ca->sum_rtt; do_div(t, info->vegas.tcpv_rttcnt); info->vegas.tcpv_rtt = t; } *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); } return 0; } static struct tcp_congestion_ops tcp_illinois __read_mostly = { .init = tcp_illinois_init, .ssthresh = tcp_illinois_ssthresh, .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = tcp_illinois_cong_avoid, .set_state = tcp_illinois_state, .get_info = tcp_illinois_info, .pkts_acked = tcp_illinois_acked, .owner = THIS_MODULE, .name = "illinois", }; static int __init tcp_illinois_register(void) { BUILD_BUG_ON(sizeof(struct illinois) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcp_illinois); } static void __exit tcp_illinois_unregister(void) { tcp_unregister_congestion_control(&tcp_illinois); } module_init(tcp_illinois_register); module_exit(tcp_illinois_unregister); MODULE_AUTHOR("Stephen Hemminger, Shao Liu"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("TCP Illinois"); MODULE_VERSION("1.0"); |
| 1 1 1 1 1 1 1 1 1 1 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 | // SPDX-License-Identifier: GPL-2.0-only /* * The NFC Controller Interface is the communication protocol between an * NFC Controller (NFCC) and a Device Host (DH). * * Copyright (C) 2014 Marvell International Ltd. * Copyright (C) 2011 Texas Instruments, Inc. * * Written by Ilan Elias <ilane@ti.com> * * Acknowledgements: * This file is based on hci_event.c, which was written * by Maxim Krasnyansky. */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ #include <linux/types.h> #include <linux/interrupt.h> #include <linux/bitops.h> #include <linux/skbuff.h> #include "../nfc.h" #include <net/nfc/nci.h> #include <net/nfc/nci_core.h> #include <linux/nfc.h> /* Handle NCI Notification packets */ static void nci_core_reset_ntf_packet(struct nci_dev *ndev, const struct sk_buff *skb) { /* Handle NCI 2.x core reset notification */ const struct nci_core_reset_ntf *ntf = (void *)skb->data; ndev->nci_ver = ntf->nci_ver; pr_debug("nci_ver 0x%x, config_status 0x%x\n", ntf->nci_ver, ntf->config_status); ndev->manufact_id = ntf->manufact_id; ndev->manufact_specific_info = __le32_to_cpu(ntf->manufact_specific_info); nci_req_complete(ndev, NCI_STATUS_OK); } static void nci_core_conn_credits_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) { struct nci_core_conn_credit_ntf *ntf = (void *) skb->data; struct nci_conn_info *conn_info; int i; pr_debug("num_entries %d\n", ntf->num_entries); if (ntf->num_entries > NCI_MAX_NUM_CONN) ntf->num_entries = NCI_MAX_NUM_CONN; /* update the credits */ for (i = 0; i < ntf->num_entries; i++) { ntf->conn_entries[i].conn_id = nci_conn_id(&ntf->conn_entries[i].conn_id); pr_debug("entry[%d]: conn_id %d, credits %d\n", i, ntf->conn_entries[i].conn_id, ntf->conn_entries[i].credits); conn_info = nci_get_conn_info_by_conn_id(ndev, ntf->conn_entries[i].conn_id); if (!conn_info) return; atomic_add(ntf->conn_entries[i].credits, &conn_info->credits_cnt); } /* trigger the next tx */ if (!skb_queue_empty(&ndev->tx_q)) queue_work(ndev->tx_wq, &ndev->tx_work); } static void nci_core_generic_error_ntf_packet(struct nci_dev *ndev, const struct sk_buff *skb) { __u8 status = skb->data[0]; pr_debug("status 0x%x\n", status); if (atomic_read(&ndev->state) == NCI_W4_HOST_SELECT) { /* Activation failed, so complete the request (the state remains the same) */ nci_req_complete(ndev, status); } } static void nci_core_conn_intf_error_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) { struct nci_core_intf_error_ntf *ntf = (void *) skb->data; ntf->conn_id = nci_conn_id(&ntf->conn_id); pr_debug("status 0x%x, conn_id %d\n", ntf->status, ntf->conn_id); /* complete the data exchange transaction, if exists */ if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) nci_data_exchange_complete(ndev, NULL, ntf->conn_id, -EIO); } static const __u8 * nci_extract_rf_params_nfca_passive_poll(struct nci_dev *ndev, struct rf_tech_specific_params_nfca_poll *nfca_poll, const __u8 *data) { nfca_poll->sens_res = __le16_to_cpu(*((__le16 *)data)); data += 2; nfca_poll->nfcid1_len = min_t(__u8, *data++, NFC_NFCID1_MAXSIZE); pr_debug("sens_res 0x%x, nfcid1_len %d\n", nfca_poll->sens_res, nfca_poll->nfcid1_len); memcpy(nfca_poll->nfcid1, data, nfca_poll->nfcid1_len); data += nfca_poll->nfcid1_len; nfca_poll->sel_res_len = *data++; if (nfca_poll->sel_res_len != 0) nfca_poll->sel_res = *data++; pr_debug("sel_res_len %d, sel_res 0x%x\n", nfca_poll->sel_res_len, nfca_poll->sel_res); return data; } static const __u8 * nci_extract_rf_params_nfcb_passive_poll(struct nci_dev *ndev, struct rf_tech_specific_params_nfcb_poll *nfcb_poll, const __u8 *data) { nfcb_poll->sensb_res_len = min_t(__u8, *data++, NFC_SENSB_RES_MAXSIZE); pr_debug("sensb_res_len %d\n", nfcb_poll->sensb_res_len); memcpy(nfcb_poll->sensb_res, data, nfcb_poll->sensb_res_len); data += nfcb_poll->sensb_res_len; return data; } static const __u8 * nci_extract_rf_params_nfcf_passive_poll(struct nci_dev *ndev, struct rf_tech_specific_params_nfcf_poll *nfcf_poll, const __u8 *data) { nfcf_poll->bit_rate = *data++; nfcf_poll->sensf_res_len = min_t(__u8, *data++, NFC_SENSF_RES_MAXSIZE); pr_debug("bit_rate %d, sensf_res_len %d\n", nfcf_poll->bit_rate, nfcf_poll->sensf_res_len); memcpy(nfcf_poll->sensf_res, data, nfcf_poll->sensf_res_len); data += nfcf_poll->sensf_res_len; return data; } static const __u8 * nci_extract_rf_params_nfcv_passive_poll(struct nci_dev *ndev, struct rf_tech_specific_params_nfcv_poll *nfcv_poll, const __u8 *data) { ++data; nfcv_poll->dsfid = *data++; memcpy(nfcv_poll->uid, data, NFC_ISO15693_UID_MAXSIZE); data += NFC_ISO15693_UID_MAXSIZE; return data; } static const __u8 * nci_extract_rf_params_nfcf_passive_listen(struct nci_dev *ndev, struct rf_tech_specific_params_nfcf_listen *nfcf_listen, const __u8 *data) { nfcf_listen->local_nfcid2_len = min_t(__u8, *data++, NFC_NFCID2_MAXSIZE); memcpy(nfcf_listen->local_nfcid2, data, nfcf_listen->local_nfcid2_len); data += nfcf_listen->local_nfcid2_len; return data; } static __u32 nci_get_prop_rf_protocol(struct nci_dev *ndev, __u8 rf_protocol) { if (ndev->ops->get_rfprotocol) return ndev->ops->get_rfprotocol(ndev, rf_protocol); return 0; } static int nci_add_new_protocol(struct nci_dev *ndev, struct nfc_target *target, __u8 rf_protocol, __u8 rf_tech_and_mode, const void *params) { const struct rf_tech_specific_params_nfca_poll *nfca_poll; const struct rf_tech_specific_params_nfcb_poll *nfcb_poll; const struct rf_tech_specific_params_nfcf_poll *nfcf_poll; const struct rf_tech_specific_params_nfcv_poll *nfcv_poll; __u32 protocol; if (rf_protocol == NCI_RF_PROTOCOL_T1T) protocol = NFC_PROTO_JEWEL_MASK; else if (rf_protocol == NCI_RF_PROTOCOL_T2T) protocol = NFC_PROTO_MIFARE_MASK; else if (rf_protocol == NCI_RF_PROTOCOL_ISO_DEP) if (rf_tech_and_mode == NCI_NFC_A_PASSIVE_POLL_MODE) protocol = NFC_PROTO_ISO14443_MASK; else protocol = NFC_PROTO_ISO14443_B_MASK; else if (rf_protocol == NCI_RF_PROTOCOL_T3T) protocol = NFC_PROTO_FELICA_MASK; else if (rf_protocol == NCI_RF_PROTOCOL_NFC_DEP) protocol = NFC_PROTO_NFC_DEP_MASK; else if (rf_protocol == NCI_RF_PROTOCOL_T5T) protocol = NFC_PROTO_ISO15693_MASK; else protocol = nci_get_prop_rf_protocol(ndev, rf_protocol); if (!(protocol & ndev->poll_prots)) { pr_err("the target found does not have the desired protocol\n"); return -EPROTO; } if (rf_tech_and_mode == NCI_NFC_A_PASSIVE_POLL_MODE) { nfca_poll = (struct rf_tech_specific_params_nfca_poll *)params; target->sens_res = nfca_poll->sens_res; target->sel_res = nfca_poll->sel_res; target->nfcid1_len = nfca_poll->nfcid1_len; if (target->nfcid1_len > ARRAY_SIZE(target->nfcid1)) return -EPROTO; if (target->nfcid1_len > 0) { memcpy(target->nfcid1, nfca_poll->nfcid1, target->nfcid1_len); } } else if (rf_tech_and_mode == NCI_NFC_B_PASSIVE_POLL_MODE) { nfcb_poll = (struct rf_tech_specific_params_nfcb_poll *)params; target->sensb_res_len = nfcb_poll->sensb_res_len; if (target->sensb_res_len > ARRAY_SIZE(target->sensb_res)) return -EPROTO; if (target->sensb_res_len > 0) { memcpy(target->sensb_res, nfcb_poll->sensb_res, target->sensb_res_len); } } else if (rf_tech_and_mode == NCI_NFC_F_PASSIVE_POLL_MODE) { nfcf_poll = (struct rf_tech_specific_params_nfcf_poll *)params; target->sensf_res_len = nfcf_poll->sensf_res_len; if (target->sensf_res_len > ARRAY_SIZE(target->sensf_res)) return -EPROTO; if (target->sensf_res_len > 0) { memcpy(target->sensf_res, nfcf_poll->sensf_res, target->sensf_res_len); } } else if (rf_tech_and_mode == NCI_NFC_V_PASSIVE_POLL_MODE) { nfcv_poll = (struct rf_tech_specific_params_nfcv_poll *)params; target->is_iso15693 = 1; target->iso15693_dsfid = nfcv_poll->dsfid; memcpy(target->iso15693_uid, nfcv_poll->uid, NFC_ISO15693_UID_MAXSIZE); } else { pr_err("unsupported rf_tech_and_mode 0x%x\n", rf_tech_and_mode); return -EPROTO; } target->supported_protocols |= protocol; pr_debug("protocol 0x%x\n", protocol); return 0; } static void nci_add_new_target(struct nci_dev *ndev, const struct nci_rf_discover_ntf *ntf) { struct nfc_target *target; int i, rc; for (i = 0; i < ndev->n_targets; i++) { target = &ndev->targets[i]; if (target->logical_idx == ntf->rf_discovery_id) { /* This target already exists, add the new protocol */ nci_add_new_protocol(ndev, target, ntf->rf_protocol, ntf->rf_tech_and_mode, &ntf->rf_tech_specific_params); return; } } /* This is a new target, check if we've enough room */ if (ndev->n_targets == NCI_MAX_DISCOVERED_TARGETS) { pr_debug("not enough room, ignoring new target...\n"); return; } target = &ndev->targets[ndev->n_targets]; rc = nci_add_new_protocol(ndev, target, ntf->rf_protocol, ntf->rf_tech_and_mode, &ntf->rf_tech_specific_params); if (!rc) { target->logical_idx = ntf->rf_discovery_id; ndev->n_targets++; pr_debug("logical idx %d, n_targets %d\n", target->logical_idx, ndev->n_targets); } } void nci_clear_target_list(struct nci_dev *ndev) { memset(ndev->targets, 0, (sizeof(struct nfc_target)*NCI_MAX_DISCOVERED_TARGETS)); ndev->n_targets = 0; } static void nci_rf_discover_ntf_packet(struct nci_dev *ndev, const struct sk_buff *skb) { struct nci_rf_discover_ntf ntf; const __u8 *data = skb->data; bool add_target = true; ntf.rf_discovery_id = *data++; ntf.rf_protocol = *data++; ntf.rf_tech_and_mode = *data++; ntf.rf_tech_specific_params_len = *data++; pr_debug("rf_discovery_id %d\n", ntf.rf_discovery_id); pr_debug("rf_protocol 0x%x\n", ntf.rf_protocol); pr_debug("rf_tech_and_mode 0x%x\n", ntf.rf_tech_and_mode); pr_debug("rf_tech_specific_params_len %d\n", ntf.rf_tech_specific_params_len); if (ntf.rf_tech_specific_params_len > 0) { switch (ntf.rf_tech_and_mode) { case NCI_NFC_A_PASSIVE_POLL_MODE: data = nci_extract_rf_params_nfca_passive_poll(ndev, &(ntf.rf_tech_specific_params.nfca_poll), data); break; case NCI_NFC_B_PASSIVE_POLL_MODE: data = nci_extract_rf_params_nfcb_passive_poll(ndev, &(ntf.rf_tech_specific_params.nfcb_poll), data); break; case NCI_NFC_F_PASSIVE_POLL_MODE: data = nci_extract_rf_params_nfcf_passive_poll(ndev, &(ntf.rf_tech_specific_params.nfcf_poll), data); break; case NCI_NFC_V_PASSIVE_POLL_MODE: data = nci_extract_rf_params_nfcv_passive_poll(ndev, &(ntf.rf_tech_specific_params.nfcv_poll), data); break; default: pr_err("unsupported rf_tech_and_mode 0x%x\n", ntf.rf_tech_and_mode); data += ntf.rf_tech_specific_params_len; add_target = false; } } ntf.ntf_type = *data++; pr_debug("ntf_type %d\n", ntf.ntf_type); if (add_target == true) nci_add_new_target(ndev, &ntf); if (ntf.ntf_type == NCI_DISCOVER_NTF_TYPE_MORE) { atomic_set(&ndev->state, NCI_W4_ALL_DISCOVERIES); } else { atomic_set(&ndev->state, NCI_W4_HOST_SELECT); nfc_targets_found(ndev->nfc_dev, ndev->targets, ndev->n_targets); } } static int nci_extract_activation_params_iso_dep(struct nci_dev *ndev, struct nci_rf_intf_activated_ntf *ntf, const __u8 *data) { struct activation_params_nfca_poll_iso_dep *nfca_poll; struct activation_params_nfcb_poll_iso_dep *nfcb_poll; switch (ntf->activation_rf_tech_and_mode) { case NCI_NFC_A_PASSIVE_POLL_MODE: nfca_poll = &ntf->activation_params.nfca_poll_iso_dep; nfca_poll->rats_res_len = min_t(__u8, *data++, 20); pr_debug("rats_res_len %d\n", nfca_poll->rats_res_len); if (nfca_poll->rats_res_len > 0) { memcpy(nfca_poll->rats_res, data, nfca_poll->rats_res_len); } break; case NCI_NFC_B_PASSIVE_POLL_MODE: nfcb_poll = &ntf->activation_params.nfcb_poll_iso_dep; nfcb_poll->attrib_res_len = min_t(__u8, *data++, 50); pr_debug("attrib_res_len %d\n", nfcb_poll->attrib_res_len); if (nfcb_poll->attrib_res_len > 0) { memcpy(nfcb_poll->attrib_res, data, nfcb_poll->attrib_res_len); } break; default: pr_err("unsupported activation_rf_tech_and_mode 0x%x\n", ntf->activation_rf_tech_and_mode); return NCI_STATUS_RF_PROTOCOL_ERROR; } return NCI_STATUS_OK; } static int nci_extract_activation_params_nfc_dep(struct nci_dev *ndev, struct nci_rf_intf_activated_ntf *ntf, const __u8 *data) { struct activation_params_poll_nfc_dep *poll; struct activation_params_listen_nfc_dep *listen; switch (ntf->activation_rf_tech_and_mode) { case NCI_NFC_A_PASSIVE_POLL_MODE: case NCI_NFC_F_PASSIVE_POLL_MODE: poll = &ntf->activation_params.poll_nfc_dep; poll->atr_res_len = min_t(__u8, *data++, NFC_ATR_RES_MAXSIZE - 2); pr_debug("atr_res_len %d\n", poll->atr_res_len); if (poll->atr_res_len > 0) memcpy(poll->atr_res, data, poll->atr_res_len); break; case NCI_NFC_A_PASSIVE_LISTEN_MODE: case NCI_NFC_F_PASSIVE_LISTEN_MODE: listen = &ntf->activation_params.listen_nfc_dep; listen->atr_req_len = min_t(__u8, *data++, NFC_ATR_REQ_MAXSIZE - 2); pr_debug("atr_req_len %d\n", listen->atr_req_len); if (listen->atr_req_len > 0) memcpy(listen->atr_req, data, listen->atr_req_len); break; default: pr_err("unsupported activation_rf_tech_and_mode 0x%x\n", ntf->activation_rf_tech_and_mode); return NCI_STATUS_RF_PROTOCOL_ERROR; } return NCI_STATUS_OK; } static void nci_target_auto_activated(struct nci_dev *ndev, const struct nci_rf_intf_activated_ntf *ntf) { struct nfc_target *target; int rc; target = &ndev->targets[ndev->n_targets]; rc = nci_add_new_protocol(ndev, target, ntf->rf_protocol, ntf->activation_rf_tech_and_mode, &ntf->rf_tech_specific_params); if (rc) return; target->logical_idx = ntf->rf_discovery_id; ndev->n_targets++; pr_debug("logical idx %d, n_targets %d\n", target->logical_idx, ndev->n_targets); nfc_targets_found(ndev->nfc_dev, ndev->targets, ndev->n_targets); } static int nci_store_general_bytes_nfc_dep(struct nci_dev *ndev, const struct nci_rf_intf_activated_ntf *ntf) { ndev->remote_gb_len = 0; if (ntf->activation_params_len <= 0) return NCI_STATUS_OK; switch (ntf->activation_rf_tech_and_mode) { case NCI_NFC_A_PASSIVE_POLL_MODE: case NCI_NFC_F_PASSIVE_POLL_MODE: ndev->remote_gb_len = min_t(__u8, (ntf->activation_params.poll_nfc_dep.atr_res_len - NFC_ATR_RES_GT_OFFSET), NFC_ATR_RES_GB_MAXSIZE); memcpy(ndev->remote_gb, (ntf->activation_params.poll_nfc_dep.atr_res + NFC_ATR_RES_GT_OFFSET), ndev->remote_gb_len); break; case NCI_NFC_A_PASSIVE_LISTEN_MODE: case NCI_NFC_F_PASSIVE_LISTEN_MODE: ndev->remote_gb_len = min_t(__u8, (ntf->activation_params.listen_nfc_dep.atr_req_len - NFC_ATR_REQ_GT_OFFSET), NFC_ATR_REQ_GB_MAXSIZE); memcpy(ndev->remote_gb, (ntf->activation_params.listen_nfc_dep.atr_req + NFC_ATR_REQ_GT_OFFSET), ndev->remote_gb_len); break; default: pr_err("unsupported activation_rf_tech_and_mode 0x%x\n", ntf->activation_rf_tech_and_mode); return NCI_STATUS_RF_PROTOCOL_ERROR; } return NCI_STATUS_OK; } static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev, const struct sk_buff *skb) { struct nci_conn_info *conn_info; struct nci_rf_intf_activated_ntf ntf; const __u8 *data = skb->data; int err = NCI_STATUS_OK; ntf.rf_discovery_id = *data++; ntf.rf_interface = *data++; ntf.rf_protocol = *data++; ntf.activation_rf_tech_and_mode = *data++; ntf.max_data_pkt_payload_size = *data++; ntf.initial_num_credits = *data++; ntf.rf_tech_specific_params_len = *data++; pr_debug("rf_discovery_id %d\n", ntf.rf_discovery_id); pr_debug("rf_interface 0x%x\n", ntf.rf_interface); pr_debug("rf_protocol 0x%x\n", ntf.rf_protocol); pr_debug("activation_rf_tech_and_mode 0x%x\n", ntf.activation_rf_tech_and_mode); pr_debug("max_data_pkt_payload_size 0x%x\n", ntf.max_data_pkt_payload_size); pr_debug("initial_num_credits 0x%x\n", ntf.initial_num_credits); pr_debug("rf_tech_specific_params_len %d\n", ntf.rf_tech_specific_params_len); /* If this contains a value of 0x00 (NFCEE Direct RF * Interface) then all following parameters SHALL contain a * value of 0 and SHALL be ignored. */ if (ntf.rf_interface == NCI_RF_INTERFACE_NFCEE_DIRECT) goto listen; if (ntf.rf_tech_specific_params_len > 0) { switch (ntf.activation_rf_tech_and_mode) { case NCI_NFC_A_PASSIVE_POLL_MODE: data = nci_extract_rf_params_nfca_passive_poll(ndev, &(ntf.rf_tech_specific_params.nfca_poll), data); break; case NCI_NFC_B_PASSIVE_POLL_MODE: data = nci_extract_rf_params_nfcb_passive_poll(ndev, &(ntf.rf_tech_specific_params.nfcb_poll), data); break; case NCI_NFC_F_PASSIVE_POLL_MODE: data = nci_extract_rf_params_nfcf_passive_poll(ndev, &(ntf.rf_tech_specific_params.nfcf_poll), data); break; case NCI_NFC_V_PASSIVE_POLL_MODE: data = nci_extract_rf_params_nfcv_passive_poll(ndev, &(ntf.rf_tech_specific_params.nfcv_poll), data); break; case NCI_NFC_A_PASSIVE_LISTEN_MODE: /* no RF technology specific parameters */ break; case NCI_NFC_F_PASSIVE_LISTEN_MODE: data = nci_extract_rf_params_nfcf_passive_listen(ndev, &(ntf.rf_tech_specific_params.nfcf_listen), data); break; default: pr_err("unsupported activation_rf_tech_and_mode 0x%x\n", ntf.activation_rf_tech_and_mode); err = NCI_STATUS_RF_PROTOCOL_ERROR; goto exit; } } ntf.data_exch_rf_tech_and_mode = *data++; ntf.data_exch_tx_bit_rate = *data++; ntf.data_exch_rx_bit_rate = *data++; ntf.activation_params_len = *data++; pr_debug("data_exch_rf_tech_and_mode 0x%x\n", ntf.data_exch_rf_tech_and_mode); pr_debug("data_exch_tx_bit_rate 0x%x\n", ntf.data_exch_tx_bit_rate); pr_debug("data_exch_rx_bit_rate 0x%x\n", ntf.data_exch_rx_bit_rate); pr_debug("activation_params_len %d\n", ntf.activation_params_len); if (ntf.activation_params_len > 0) { switch (ntf.rf_interface) { case NCI_RF_INTERFACE_ISO_DEP: err = nci_extract_activation_params_iso_dep(ndev, &ntf, data); break; case NCI_RF_INTERFACE_NFC_DEP: err = nci_extract_activation_params_nfc_dep(ndev, &ntf, data); break; case NCI_RF_INTERFACE_FRAME: /* no activation params */ break; default: pr_err("unsupported rf_interface 0x%x\n", ntf.rf_interface); err = NCI_STATUS_RF_PROTOCOL_ERROR; break; } } exit: if (err == NCI_STATUS_OK) { conn_info = ndev->rf_conn_info; if (!conn_info) return; conn_info->max_pkt_payload_len = ntf.max_data_pkt_payload_size; conn_info->initial_num_credits = ntf.initial_num_credits; /* set the available credits to initial value */ atomic_set(&conn_info->credits_cnt, conn_info->initial_num_credits); /* store general bytes to be reported later in dep_link_up */ if (ntf.rf_interface == NCI_RF_INTERFACE_NFC_DEP) { err = nci_store_general_bytes_nfc_dep(ndev, &ntf); if (err != NCI_STATUS_OK) pr_err("unable to store general bytes\n"); } } if (!(ntf.activation_rf_tech_and_mode & NCI_RF_TECH_MODE_LISTEN_MASK)) { /* Poll mode */ if (atomic_read(&ndev->state) == NCI_DISCOVERY) { /* A single target was found and activated * automatically */ atomic_set(&ndev->state, NCI_POLL_ACTIVE); if (err == NCI_STATUS_OK) nci_target_auto_activated(ndev, &ntf); } else { /* ndev->state == NCI_W4_HOST_SELECT */ /* A selected target was activated, so complete the * request */ atomic_set(&ndev->state, NCI_POLL_ACTIVE); nci_req_complete(ndev, err); } } else { listen: /* Listen mode */ atomic_set(&ndev->state, NCI_LISTEN_ACTIVE); if (err == NCI_STATUS_OK && ntf.rf_protocol == NCI_RF_PROTOCOL_NFC_DEP) { err = nfc_tm_activated(ndev->nfc_dev, NFC_PROTO_NFC_DEP_MASK, NFC_COMM_PASSIVE, ndev->remote_gb, ndev->remote_gb_len); if (err != NCI_STATUS_OK) pr_err("error when signaling tm activation\n"); } } } static void nci_rf_deactivate_ntf_packet(struct nci_dev *ndev, const struct sk_buff *skb) { const struct nci_conn_info *conn_info; const struct nci_rf_deactivate_ntf *ntf = (void *)skb->data; pr_debug("entry, type 0x%x, reason 0x%x\n", ntf->type, ntf->reason); conn_info = ndev->rf_conn_info; if (!conn_info) return; /* drop tx data queue */ skb_queue_purge(&ndev->tx_q); /* drop partial rx data packet */ if (ndev->rx_data_reassembly) { kfree_skb(ndev->rx_data_reassembly); ndev->rx_data_reassembly = NULL; } /* complete the data exchange transaction, if exists */ if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) nci_data_exchange_complete(ndev, NULL, NCI_STATIC_RF_CONN_ID, -EIO); switch (ntf->type) { case NCI_DEACTIVATE_TYPE_IDLE_MODE: nci_clear_target_list(ndev); atomic_set(&ndev->state, NCI_IDLE); break; case NCI_DEACTIVATE_TYPE_SLEEP_MODE: case NCI_DEACTIVATE_TYPE_SLEEP_AF_MODE: atomic_set(&ndev->state, NCI_W4_HOST_SELECT); break; case NCI_DEACTIVATE_TYPE_DISCOVERY: nci_clear_target_list(ndev); atomic_set(&ndev->state, NCI_DISCOVERY); break; } nci_req_complete(ndev, NCI_STATUS_OK); } static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev, const struct sk_buff *skb) { u8 status = NCI_STATUS_OK; const struct nci_nfcee_discover_ntf *nfcee_ntf = (struct nci_nfcee_discover_ntf *)skb->data; /* NFCForum NCI 9.2.1 HCI Network Specific Handling * If the NFCC supports the HCI Network, it SHALL return one, * and only one, NFCEE_DISCOVER_NTF with a Protocol type of * “HCI Access”, even if the HCI Network contains multiple NFCEEs. */ ndev->hci_dev->nfcee_id = nfcee_ntf->nfcee_id; ndev->cur_params.id = nfcee_ntf->nfcee_id; nci_req_complete(ndev, status); } void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) { __u16 ntf_opcode = nci_opcode(skb->data); pr_debug("NCI RX: MT=ntf, PBF=%d, GID=0x%x, OID=0x%x, plen=%d\n", nci_pbf(skb->data), nci_opcode_gid(ntf_opcode), nci_opcode_oid(ntf_opcode), nci_plen(skb->data)); /* strip the nci control header */ skb_pull(skb, NCI_CTRL_HDR_SIZE); if (nci_opcode_gid(ntf_opcode) == NCI_GID_PROPRIETARY) { if (nci_prop_ntf_packet(ndev, ntf_opcode, skb) == -ENOTSUPP) { pr_err("unsupported ntf opcode 0x%x\n", ntf_opcode); } goto end; } switch (ntf_opcode) { case NCI_OP_CORE_RESET_NTF: nci_core_reset_ntf_packet(ndev, skb); break; case NCI_OP_CORE_CONN_CREDITS_NTF: nci_core_conn_credits_ntf_packet(ndev, skb); break; case NCI_OP_CORE_GENERIC_ERROR_NTF: nci_core_generic_error_ntf_packet(ndev, skb); break; case NCI_OP_CORE_INTF_ERROR_NTF: nci_core_conn_intf_error_ntf_packet(ndev, skb); break; case NCI_OP_RF_DISCOVER_NTF: nci_rf_discover_ntf_packet(ndev, skb); break; case NCI_OP_RF_INTF_ACTIVATED_NTF: nci_rf_intf_activated_ntf_packet(ndev, skb); break; case NCI_OP_RF_DEACTIVATE_NTF: nci_rf_deactivate_ntf_packet(ndev, skb); break; case NCI_OP_NFCEE_DISCOVER_NTF: nci_nfcee_discover_ntf_packet(ndev, skb); break; case NCI_OP_RF_NFCEE_ACTION_NTF: break; default: pr_err("unknown ntf opcode 0x%x\n", ntf_opcode); break; } nci_core_ntf_packet(ndev, ntf_opcode, skb); end: kfree_skb(skb); } |
| 48 48 48 2 2 15 15 17 16 17 2 15 17 37 37 38 38 24 37 24 23 24 24 65 42 42 65 29 14 10 25 25 25 25 1 24 3 25 25 47 48 47 41 8 8 8 48 42 47 48 65 65 65 64 65 25 48 48 65 65 65 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 15 15 15 15 9 15 15 15 13 1 1 6 3 1 1 1 1 1 1 1 1 5 5 5 5 5 5 5 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 5 1 5 2 2 2 2 14 14 10 10 1 1 1 5 5 5 5 5 5 5 5 5 5 5 7 7 2 42 42 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_inode_item.h" #include "xfs_quota.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_bmap_util.h" #include "xfs_dquot_item.h" #include "xfs_dquot.h" #include "xfs_reflink.h" #include "xfs_ialloc.h" #include "xfs_ag.h" #include "xfs_log_priv.h" #include <linux/iversion.h> /* Radix tree tags for incore inode tree. */ /* inode is to be reclaimed */ #define XFS_ICI_RECLAIM_TAG 0 /* Inode has speculative preallocations (posteof or cow) to clean. */ #define XFS_ICI_BLOCKGC_TAG 1 /* * The goal for walking incore inodes. These can correspond with incore inode * radix tree tags when convenient. Avoid existing XFS_IWALK namespace. */ enum xfs_icwalk_goal { /* Goals directly associated with tagged inodes. */ XFS_ICWALK_BLOCKGC = XFS_ICI_BLOCKGC_TAG, XFS_ICWALK_RECLAIM = XFS_ICI_RECLAIM_TAG, }; static int xfs_icwalk(struct xfs_mount *mp, enum xfs_icwalk_goal goal, struct xfs_icwalk *icw); static int xfs_icwalk_ag(struct xfs_perag *pag, enum xfs_icwalk_goal goal, struct xfs_icwalk *icw); /* * Private inode cache walk flags for struct xfs_icwalk. Must not * coincide with XFS_ICWALK_FLAGS_VALID. */ /* Stop scanning after icw_scan_limit inodes. */ #define XFS_ICWALK_FLAG_SCAN_LIMIT (1U << 28) #define XFS_ICWALK_FLAG_RECLAIM_SICK (1U << 27) #define XFS_ICWALK_FLAG_UNION (1U << 26) /* union filter algorithm */ #define XFS_ICWALK_PRIVATE_FLAGS (XFS_ICWALK_FLAG_SCAN_LIMIT | \ XFS_ICWALK_FLAG_RECLAIM_SICK | \ XFS_ICWALK_FLAG_UNION) /* * Allocate and initialise an xfs_inode. */ struct xfs_inode * xfs_inode_alloc( struct xfs_mount *mp, xfs_ino_t ino) { struct xfs_inode *ip; /* * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL * and return NULL here on ENOMEM. */ ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL); if (inode_init_always(mp->m_super, VFS_I(ip))) { kmem_cache_free(xfs_inode_cache, ip); return NULL; } /* VFS doesn't initialise i_mode or i_state! */ VFS_I(ip)->i_mode = 0; VFS_I(ip)->i_state = 0; mapping_set_large_folios(VFS_I(ip)->i_mapping); XFS_STATS_INC(mp, vn_active); ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(ip->i_ino == 0); /* initialise the xfs inode */ ip->i_ino = ino; ip->i_mount = mp; memset(&ip->i_imap, 0, sizeof(struct xfs_imap)); ip->i_cowfp = NULL; memset(&ip->i_af, 0, sizeof(ip->i_af)); ip->i_af.if_format = XFS_DINODE_FMT_EXTENTS; memset(&ip->i_df, 0, sizeof(ip->i_df)); ip->i_flags = 0; ip->i_delayed_blks = 0; ip->i_diflags2 = mp->m_ino_geo.new_diflags2; ip->i_nblocks = 0; ip->i_forkoff = 0; ip->i_sick = 0; ip->i_checked = 0; INIT_WORK(&ip->i_ioend_work, xfs_end_io); INIT_LIST_HEAD(&ip->i_ioend_list); spin_lock_init(&ip->i_ioend_lock); ip->i_next_unlinked = NULLAGINO; ip->i_prev_unlinked = 0; return ip; } STATIC void xfs_inode_free_callback( struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); struct xfs_inode *ip = XFS_I(inode); switch (VFS_I(ip)->i_mode & S_IFMT) { case S_IFREG: case S_IFDIR: case S_IFLNK: xfs_idestroy_fork(&ip->i_df); break; } xfs_ifork_zap_attr(ip); if (ip->i_cowfp) { xfs_idestroy_fork(ip->i_cowfp); kmem_cache_free(xfs_ifork_cache, ip->i_cowfp); } if (ip->i_itemp) { ASSERT(!test_bit(XFS_LI_IN_AIL, &ip->i_itemp->ili_item.li_flags)); xfs_inode_item_destroy(ip); ip->i_itemp = NULL; } kmem_cache_free(xfs_inode_cache, ip); } static void __xfs_inode_free( struct xfs_inode *ip) { /* asserts to verify all state is correct here */ ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list)); XFS_STATS_DEC(ip->i_mount, vn_active); call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback); } void xfs_inode_free( struct xfs_inode *ip) { ASSERT(!xfs_iflags_test(ip, XFS_IFLUSHING)); /* * Because we use RCU freeing we need to ensure the inode always * appears to be reclaimed with an invalid inode number when in the * free state. The ip->i_flags_lock provides the barrier against lookup * races. */ spin_lock(&ip->i_flags_lock); ip->i_flags = XFS_IRECLAIM; ip->i_ino = 0; spin_unlock(&ip->i_flags_lock); __xfs_inode_free(ip); } /* * Queue background inode reclaim work if there are reclaimable inodes and there * isn't reclaim work already scheduled or in progress. */ static void xfs_reclaim_work_queue( struct xfs_mount *mp) { rcu_read_lock(); if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) { queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work, msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10)); } rcu_read_unlock(); } /* * Background scanning to trim preallocated space. This is queued based on the * 'speculative_prealloc_lifetime' tunable (5m by default). */ static inline void xfs_blockgc_queue( struct xfs_perag *pag) { struct xfs_mount *mp = pag->pag_mount; if (!xfs_is_blockgc_enabled(mp)) return; rcu_read_lock(); if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG)) queue_delayed_work(pag->pag_mount->m_blockgc_wq, &pag->pag_blockgc_work, msecs_to_jiffies(xfs_blockgc_secs * 1000)); rcu_read_unlock(); } /* Set a tag on both the AG incore inode tree and the AG radix tree. */ static void xfs_perag_set_inode_tag( struct xfs_perag *pag, xfs_agino_t agino, unsigned int tag) { struct xfs_mount *mp = pag->pag_mount; bool was_tagged; lockdep_assert_held(&pag->pag_ici_lock); was_tagged = radix_tree_tagged(&pag->pag_ici_root, tag); radix_tree_tag_set(&pag->pag_ici_root, agino, tag); if (tag == XFS_ICI_RECLAIM_TAG) pag->pag_ici_reclaimable++; if (was_tagged) return; /* propagate the tag up into the perag radix tree */ spin_lock(&mp->m_perag_lock); radix_tree_tag_set(&mp->m_perag_tree, pag->pag_agno, tag); spin_unlock(&mp->m_perag_lock); /* start background work */ switch (tag) { case XFS_ICI_RECLAIM_TAG: xfs_reclaim_work_queue(mp); break; case XFS_ICI_BLOCKGC_TAG: xfs_blockgc_queue(pag); break; } trace_xfs_perag_set_inode_tag(pag, _RET_IP_); } /* Clear a tag on both the AG incore inode tree and the AG radix tree. */ static void xfs_perag_clear_inode_tag( struct xfs_perag *pag, xfs_agino_t agino, unsigned int tag) { struct xfs_mount *mp = pag->pag_mount; lockdep_assert_held(&pag->pag_ici_lock); /* * Reclaim can signal (with a null agino) that it cleared its own tag * by removing the inode from the radix tree. */ if (agino != NULLAGINO) radix_tree_tag_clear(&pag->pag_ici_root, agino, tag); else ASSERT(tag == XFS_ICI_RECLAIM_TAG); if (tag == XFS_ICI_RECLAIM_TAG) pag->pag_ici_reclaimable--; if (radix_tree_tagged(&pag->pag_ici_root, tag)) return; /* clear the tag from the perag radix tree */ spin_lock(&mp->m_perag_lock); radix_tree_tag_clear(&mp->m_perag_tree, pag->pag_agno, tag); spin_unlock(&mp->m_perag_lock); trace_xfs_perag_clear_inode_tag(pag, _RET_IP_); } /* * When we recycle a reclaimable inode, we need to re-initialise the VFS inode * part of the structure. This is made more complex by the fact we store * information about the on-disk values in the VFS inode and so we can't just * overwrite the values unconditionally. Hence we save the parameters we * need to retain across reinitialisation, and rewrite them into the VFS inode * after reinitialisation even if it fails. */ static int xfs_reinit_inode( struct xfs_mount *mp, struct inode *inode) { int error; uint32_t nlink = inode->i_nlink; uint32_t generation = inode->i_generation; uint64_t version = inode_peek_iversion(inode); umode_t mode = inode->i_mode; dev_t dev = inode->i_rdev; kuid_t uid = inode->i_uid; kgid_t gid = inode->i_gid; error = inode_init_always(mp->m_super, inode); set_nlink(inode, nlink); inode->i_generation = generation; inode_set_iversion_queried(inode, version); inode->i_mode = mode; inode->i_rdev = dev; inode->i_uid = uid; inode->i_gid = gid; mapping_set_large_folios(inode->i_mapping); return error; } /* * Carefully nudge an inode whose VFS state has been torn down back into a * usable state. Drops the i_flags_lock and the rcu read lock. */ static int xfs_iget_recycle( struct xfs_perag *pag, struct xfs_inode *ip) __releases(&ip->i_flags_lock) { struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); int error; trace_xfs_iget_recycle(ip); if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) return -EAGAIN; /* * We need to make it look like the inode is being reclaimed to prevent * the actual reclaim workers from stomping over us while we recycle * the inode. We can't clear the radix tree tag yet as it requires * pag_ici_lock to be held exclusive. */ ip->i_flags |= XFS_IRECLAIM; spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); ASSERT(!rwsem_is_locked(&inode->i_rwsem)); error = xfs_reinit_inode(mp, inode); xfs_iunlock(ip, XFS_ILOCK_EXCL); if (error) { /* * Re-initializing the inode failed, and we are in deep * trouble. Try to re-add it to the reclaim list. */ rcu_read_lock(); spin_lock(&ip->i_flags_lock); ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM); ASSERT(ip->i_flags & XFS_IRECLAIMABLE); spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); trace_xfs_iget_recycle_fail(ip); return error; } spin_lock(&pag->pag_ici_lock); spin_lock(&ip->i_flags_lock); /* * Clear the per-lifetime state in the inode as we are now effectively * a new inode and need to return to the initial state before reuse * occurs. */ ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS; ip->i_flags |= XFS_INEW; xfs_perag_clear_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG); inode->i_state = I_NEW; spin_unlock(&ip->i_flags_lock); spin_unlock(&pag->pag_ici_lock); return 0; } /* * If we are allocating a new inode, then check what was returned is * actually a free, empty inode. If we are not allocating an inode, * then check we didn't find a free inode. * * Returns: * 0 if the inode free state matches the lookup context * -ENOENT if the inode is free and we are not allocating * -EFSCORRUPTED if there is any state mismatch at all */ static int xfs_iget_check_free_state( struct xfs_inode *ip, int flags) { if (flags & XFS_IGET_CREATE) { /* should be a free inode */ if (VFS_I(ip)->i_mode != 0) { xfs_warn(ip->i_mount, "Corruption detected! Free inode 0x%llx not marked free! (mode 0x%x)", ip->i_ino, VFS_I(ip)->i_mode); return -EFSCORRUPTED; } if (ip->i_nblocks != 0) { xfs_warn(ip->i_mount, "Corruption detected! Free inode 0x%llx has blocks allocated!", ip->i_ino); return -EFSCORRUPTED; } return 0; } /* should be an allocated inode */ if (VFS_I(ip)->i_mode == 0) return -ENOENT; return 0; } /* Make all pending inactivation work start immediately. */ static bool xfs_inodegc_queue_all( struct xfs_mount *mp) { struct xfs_inodegc *gc; int cpu; bool ret = false; for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) { mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0); ret = true; } } return ret; } /* Wait for all queued work and collect errors */ static int xfs_inodegc_wait_all( struct xfs_mount *mp) { int cpu; int error = 0; flush_workqueue(mp->m_inodegc_wq); for_each_cpu(cpu, &mp->m_inodegc_cpumask) { struct xfs_inodegc *gc; gc = per_cpu_ptr(mp->m_inodegc, cpu); if (gc->error && !error) error = gc->error; gc->error = 0; } return error; } /* * Check the validity of the inode we just found it the cache */ static int xfs_iget_cache_hit( struct xfs_perag *pag, struct xfs_inode *ip, xfs_ino_t ino, int flags, int lock_flags) __releases(RCU) { struct inode *inode = VFS_I(ip); struct xfs_mount *mp = ip->i_mount; int error; /* * check for re-use of an inode within an RCU grace period due to the * radix tree nodes not being updated yet. We monitor for this by * setting the inode number to zero before freeing the inode structure. * If the inode has been reallocated and set up, then the inode number * will not match, so check for that, too. */ spin_lock(&ip->i_flags_lock); if (ip->i_ino != ino) goto out_skip; /* * If we are racing with another cache hit that is currently * instantiating this inode or currently recycling it out of * reclaimable state, wait for the initialisation to complete * before continuing. * * If we're racing with the inactivation worker we also want to wait. * If we're creating a new file, it's possible that the worker * previously marked the inode as free on disk but hasn't finished * updating the incore state yet. The AGI buffer will be dirty and * locked to the icreate transaction, so a synchronous push of the * inodegc workers would result in deadlock. For a regular iget, the * worker is running already, so we might as well wait. * * XXX(hch): eventually we should do something equivalent to * wait_on_inode to wait for these flags to be cleared * instead of polling for it. */ if (ip->i_flags & (XFS_INEW | XFS_IRECLAIM | XFS_INACTIVATING)) goto out_skip; if (ip->i_flags & XFS_NEED_INACTIVE) { /* Unlinked inodes cannot be re-grabbed. */ if (VFS_I(ip)->i_nlink == 0) { error = -ENOENT; goto out_error; } goto out_inodegc_flush; } /* * Check the inode free state is valid. This also detects lookup * racing with unlinks. */ error = xfs_iget_check_free_state(ip, flags); if (error) goto out_error; /* Skip inodes that have no vfs state. */ if ((flags & XFS_IGET_INCORE) && (ip->i_flags & XFS_IRECLAIMABLE)) goto out_skip; /* The inode fits the selection criteria; process it. */ if (ip->i_flags & XFS_IRECLAIMABLE) { /* Drops i_flags_lock and RCU read lock. */ error = xfs_iget_recycle(pag, ip); if (error == -EAGAIN) goto out_skip; if (error) return error; } else { /* If the VFS inode is being torn down, pause and try again. */ if (!igrab(inode)) goto out_skip; /* We've got a live one. */ spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); trace_xfs_iget_hit(ip); } if (lock_flags != 0) xfs_ilock(ip, lock_flags); if (!(flags & XFS_IGET_INCORE)) xfs_iflags_clear(ip, XFS_ISTALE); XFS_STATS_INC(mp, xs_ig_found); return 0; out_skip: trace_xfs_iget_skip(ip); XFS_STATS_INC(mp, xs_ig_frecycle); error = -EAGAIN; out_error: spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); return error; out_inodegc_flush: spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); /* * Do not wait for the workers, because the caller could hold an AGI * buffer lock. We're just going to sleep in a loop anyway. */ if (xfs_is_inodegc_enabled(mp)) xfs_inodegc_queue_all(mp); return -EAGAIN; } static int xfs_iget_cache_miss( struct xfs_mount *mp, struct xfs_perag *pag, xfs_trans_t *tp, xfs_ino_t ino, struct xfs_inode **ipp, int flags, int lock_flags) { struct xfs_inode *ip; int error; xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ino); int iflags; ip = xfs_inode_alloc(mp, ino); if (!ip) return -ENOMEM; error = xfs_imap(pag, tp, ip->i_ino, &ip->i_imap, flags); if (error) goto out_destroy; /* * For version 5 superblocks, if we are initialising a new inode and we * are not utilising the XFS_FEAT_IKEEP inode cluster mode, we can * simply build the new inode core with a random generation number. * * For version 4 (and older) superblocks, log recovery is dependent on * the i_flushiter field being initialised from the current on-disk * value and hence we must also read the inode off disk even when * initializing new inodes. */ if (xfs_has_v3inodes(mp) && (flags & XFS_IGET_CREATE) && !xfs_has_ikeep(mp)) { VFS_I(ip)->i_generation = get_random_u32(); } else { struct xfs_buf *bp; error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp); if (error) goto out_destroy; error = xfs_inode_from_disk(ip, xfs_buf_offset(bp, ip->i_imap.im_boffset)); if (!error) xfs_buf_set_ref(bp, XFS_INO_REF); xfs_trans_brelse(tp, bp); if (error) goto out_destroy; } trace_xfs_iget_miss(ip); /* * Check the inode free state is valid. This also detects lookup * racing with unlinks. */ error = xfs_iget_check_free_state(ip, flags); if (error) goto out_destroy; /* * Preload the radix tree so we can insert safely under the * write spinlock. Note that we cannot sleep inside the preload * region. Since we can be called from transaction context, don't * recurse into the file system. */ if (radix_tree_preload(GFP_NOFS)) { error = -EAGAIN; goto out_destroy; } /* * Because the inode hasn't been added to the radix-tree yet it can't * be found by another thread, so we can do the non-sleeping lock here. */ if (lock_flags) { if (!xfs_ilock_nowait(ip, lock_flags)) BUG(); } /* * These values must be set before inserting the inode into the radix * tree as the moment it is inserted a concurrent lookup (allowed by the * RCU locking mechanism) can find it and that lookup must see that this * is an inode currently under construction (i.e. that XFS_INEW is set). * The ip->i_flags_lock that protects the XFS_INEW flag forms the * memory barrier that ensures this detection works correctly at lookup * time. */ iflags = XFS_INEW; if (flags & XFS_IGET_DONTCACHE) d_mark_dontcache(VFS_I(ip)); ip->i_udquot = NULL; ip->i_gdquot = NULL; ip->i_pdquot = NULL; xfs_iflags_set(ip, iflags); /* insert the new inode */ spin_lock(&pag->pag_ici_lock); error = radix_tree_insert(&pag->pag_ici_root, agino, ip); if (unlikely(error)) { WARN_ON(error != -EEXIST); XFS_STATS_INC(mp, xs_ig_dup); error = -EAGAIN; goto out_preload_end; } spin_unlock(&pag->pag_ici_lock); radix_tree_preload_end(); *ipp = ip; return 0; out_preload_end: spin_unlock(&pag->pag_ici_lock); radix_tree_preload_end(); if (lock_flags) xfs_iunlock(ip, lock_flags); out_destroy: __destroy_inode(VFS_I(ip)); xfs_inode_free(ip); return error; } /* * Look up an inode by number in the given file system. The inode is looked up * in the cache held in each AG. If the inode is found in the cache, initialise * the vfs inode if necessary. * * If it is not in core, read it in from the file system's device, add it to the * cache and initialise the vfs inode. * * The inode is locked according to the value of the lock_flags parameter. * Inode lookup is only done during metadata operations and not as part of the * data IO path. Hence we only allow locking of the XFS_ILOCK during lookup. */ int xfs_iget( struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino, uint flags, uint lock_flags, struct xfs_inode **ipp) { struct xfs_inode *ip; struct xfs_perag *pag; xfs_agino_t agino; int error; ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0); /* reject inode numbers outside existing AGs */ if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount) return -EINVAL; XFS_STATS_INC(mp, xs_ig_attempts); /* get the perag structure and ensure that it's inode capable */ pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino)); agino = XFS_INO_TO_AGINO(mp, ino); again: error = 0; rcu_read_lock(); ip = radix_tree_lookup(&pag->pag_ici_root, agino); if (ip) { error = xfs_iget_cache_hit(pag, ip, ino, flags, lock_flags); if (error) goto out_error_or_again; } else { rcu_read_unlock(); if (flags & XFS_IGET_INCORE) { error = -ENODATA; goto out_error_or_again; } XFS_STATS_INC(mp, xs_ig_missed); error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip, flags, lock_flags); if (error) goto out_error_or_again; } xfs_perag_put(pag); *ipp = ip; /* * If we have a real type for an on-disk inode, we can setup the inode * now. If it's a new inode being created, xfs_init_new_inode will * handle it. */ if (xfs_iflags_test(ip, XFS_INEW) && VFS_I(ip)->i_mode != 0) xfs_setup_existing_inode(ip); return 0; out_error_or_again: if (!(flags & (XFS_IGET_INCORE | XFS_IGET_NORETRY)) && error == -EAGAIN) { delay(1); goto again; } xfs_perag_put(pag); return error; } /* * Grab the inode for reclaim exclusively. * * We have found this inode via a lookup under RCU, so the inode may have * already been freed, or it may be in the process of being recycled by * xfs_iget(). In both cases, the inode will have XFS_IRECLAIM set. If the inode * has been fully recycled by the time we get the i_flags_lock, XFS_IRECLAIMABLE * will not be set. Hence we need to check for both these flag conditions to * avoid inodes that are no longer reclaim candidates. * * Note: checking for other state flags here, under the i_flags_lock or not, is * racy and should be avoided. Those races should be resolved only after we have * ensured that we are able to reclaim this inode and the world can see that we * are going to reclaim it. * * Return true if we grabbed it, false otherwise. */ static bool xfs_reclaim_igrab( struct xfs_inode *ip, struct xfs_icwalk *icw) { ASSERT(rcu_read_lock_held()); spin_lock(&ip->i_flags_lock); if (!__xfs_iflags_test(ip, XFS_IRECLAIMABLE) || __xfs_iflags_test(ip, XFS_IRECLAIM)) { /* not a reclaim candidate. */ spin_unlock(&ip->i_flags_lock); return false; } /* Don't reclaim a sick inode unless the caller asked for it. */ if (ip->i_sick && (!icw || !(icw->icw_flags & XFS_ICWALK_FLAG_RECLAIM_SICK))) { spin_unlock(&ip->i_flags_lock); return false; } __xfs_iflags_set(ip, XFS_IRECLAIM); spin_unlock(&ip->i_flags_lock); return true; } /* * Inode reclaim is non-blocking, so the default action if progress cannot be * made is to "requeue" the inode for reclaim by unlocking it and clearing the * XFS_IRECLAIM flag. If we are in a shutdown state, we don't care about * blocking anymore and hence we can wait for the inode to be able to reclaim * it. * * We do no IO here - if callers require inodes to be cleaned they must push the * AIL first to trigger writeback of dirty inodes. This enables writeback to be * done in the background in a non-blocking manner, and enables memory reclaim * to make progress without blocking. */ static void xfs_reclaim_inode( struct xfs_inode *ip, struct xfs_perag *pag) { xfs_ino_t ino = ip->i_ino; /* for radix_tree_delete */ if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) goto out; if (xfs_iflags_test_and_set(ip, XFS_IFLUSHING)) goto out_iunlock; /* * Check for log shutdown because aborting the inode can move the log * tail and corrupt in memory state. This is fine if the log is shut * down, but if the log is still active and only the mount is shut down * then the in-memory log tail movement caused by the abort can be * incorrectly propagated to disk. */ if (xlog_is_shutdown(ip->i_mount->m_log)) { xfs_iunpin_wait(ip); xfs_iflush_shutdown_abort(ip); goto reclaim; } if (xfs_ipincount(ip)) goto out_clear_flush; if (!xfs_inode_clean(ip)) goto out_clear_flush; xfs_iflags_clear(ip, XFS_IFLUSHING); reclaim: trace_xfs_inode_reclaiming(ip); /* * Because we use RCU freeing we need to ensure the inode always appears * to be reclaimed with an invalid inode number when in the free state. * We do this as early as possible under the ILOCK so that * xfs_iflush_cluster() and xfs_ifree_cluster() can be guaranteed to * detect races with us here. By doing this, we guarantee that once * xfs_iflush_cluster() or xfs_ifree_cluster() has locked XFS_ILOCK that * it will see either a valid inode that will serialise correctly, or it * will see an invalid inode that it can skip. */ spin_lock(&ip->i_flags_lock); ip->i_flags = XFS_IRECLAIM; ip->i_ino = 0; ip->i_sick = 0; ip->i_checked = 0; spin_unlock(&ip->i_flags_lock); ASSERT(!ip->i_itemp || ip->i_itemp->ili_item.li_buf == NULL); xfs_iunlock(ip, XFS_ILOCK_EXCL); XFS_STATS_INC(ip->i_mount, xs_ig_reclaims); /* * Remove the inode from the per-AG radix tree. * * Because radix_tree_delete won't complain even if the item was never * added to the tree assert that it's been there before to catch * problems with the inode life time early on. */ spin_lock(&pag->pag_ici_lock); if (!radix_tree_delete(&pag->pag_ici_root, XFS_INO_TO_AGINO(ip->i_mount, ino))) ASSERT(0); xfs_perag_clear_inode_tag(pag, NULLAGINO, XFS_ICI_RECLAIM_TAG); spin_unlock(&pag->pag_ici_lock); /* * Here we do an (almost) spurious inode lock in order to coordinate * with inode cache radix tree lookups. This is because the lookup * can reference the inodes in the cache without taking references. * * We make that OK here by ensuring that we wait until the inode is * unlocked after the lookup before we go ahead and free it. */ xfs_ilock(ip, XFS_ILOCK_EXCL); ASSERT(!ip->i_udquot && !ip->i_gdquot && !ip->i_pdquot); xfs_iunlock(ip, XFS_ILOCK_EXCL); ASSERT(xfs_inode_clean(ip)); __xfs_inode_free(ip); return; out_clear_flush: xfs_iflags_clear(ip, XFS_IFLUSHING); out_iunlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); out: xfs_iflags_clear(ip, XFS_IRECLAIM); } /* Reclaim sick inodes if we're unmounting or the fs went down. */ static inline bool xfs_want_reclaim_sick( struct xfs_mount *mp) { return xfs_is_unmounting(mp) || xfs_has_norecovery(mp) || xfs_is_shutdown(mp); } void xfs_reclaim_inodes( struct xfs_mount *mp) { struct xfs_icwalk icw = { .icw_flags = 0, }; if (xfs_want_reclaim_sick(mp)) icw.icw_flags |= XFS_ICWALK_FLAG_RECLAIM_SICK; while (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) { xfs_ail_push_all_sync(mp->m_ail); xfs_icwalk(mp, XFS_ICWALK_RECLAIM, &icw); } } /* * The shrinker infrastructure determines how many inodes we should scan for * reclaim. We want as many clean inodes ready to reclaim as possible, so we * push the AIL here. We also want to proactively free up memory if we can to * minimise the amount of work memory reclaim has to do so we kick the * background reclaim if it isn't already scheduled. */ long xfs_reclaim_inodes_nr( struct xfs_mount *mp, unsigned long nr_to_scan) { struct xfs_icwalk icw = { .icw_flags = XFS_ICWALK_FLAG_SCAN_LIMIT, .icw_scan_limit = min_t(unsigned long, LONG_MAX, nr_to_scan), }; if (xfs_want_reclaim_sick(mp)) icw.icw_flags |= XFS_ICWALK_FLAG_RECLAIM_SICK; /* kick background reclaimer and push the AIL */ xfs_reclaim_work_queue(mp); xfs_ail_push_all(mp->m_ail); xfs_icwalk(mp, XFS_ICWALK_RECLAIM, &icw); return 0; } /* * Return the number of reclaimable inodes in the filesystem for * the shrinker to determine how much to reclaim. */ long xfs_reclaim_inodes_count( struct xfs_mount *mp) { struct xfs_perag *pag; xfs_agnumber_t ag = 0; long reclaimable = 0; while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) { ag = pag->pag_agno + 1; reclaimable += pag->pag_ici_reclaimable; xfs_perag_put(pag); } return reclaimable; } STATIC bool xfs_icwalk_match_id( struct xfs_inode *ip, struct xfs_icwalk *icw) { if ((icw->icw_flags & XFS_ICWALK_FLAG_UID) && !uid_eq(VFS_I(ip)->i_uid, icw->icw_uid)) return false; if ((icw->icw_flags & XFS_ICWALK_FLAG_GID) && !gid_eq(VFS_I(ip)->i_gid, icw->icw_gid)) return false; if ((icw->icw_flags & XFS_ICWALK_FLAG_PRID) && ip->i_projid != icw->icw_prid) return false; return true; } /* * A union-based inode filtering algorithm. Process the inode if any of the * criteria match. This is for global/internal scans only. */ STATIC bool xfs_icwalk_match_id_union( struct xfs_inode *ip, struct xfs_icwalk *icw) { if ((icw->icw_flags & XFS_ICWALK_FLAG_UID) && uid_eq(VFS_I(ip)->i_uid, icw->icw_uid)) return true; if ((icw->icw_flags & XFS_ICWALK_FLAG_GID) && gid_eq(VFS_I(ip)->i_gid, icw->icw_gid)) return true; if ((icw->icw_flags & XFS_ICWALK_FLAG_PRID) && ip->i_projid == icw->icw_prid) return true; return false; } /* * Is this inode @ip eligible for eof/cow block reclamation, given some * filtering parameters @icw? The inode is eligible if @icw is null or * if the predicate functions match. */ static bool xfs_icwalk_match( struct xfs_inode *ip, struct xfs_icwalk *icw) { bool match; if (!icw) return true; if (icw->icw_flags & XFS_ICWALK_FLAG_UNION) match = xfs_icwalk_match_id_union(ip, icw); else match = xfs_icwalk_match_id(ip, icw); if (!match) return false; /* skip the inode if the file size is too small */ if ((icw->icw_flags & XFS_ICWALK_FLAG_MINFILESIZE) && XFS_ISIZE(ip) < icw->icw_min_file_size) return false; return true; } /* * This is a fast pass over the inode cache to try to get reclaim moving on as * many inodes as possible in a short period of time. It kicks itself every few * seconds, as well as being kicked by the inode cache shrinker when memory * goes low. */ void xfs_reclaim_worker( struct work_struct *work) { struct xfs_mount *mp = container_of(to_delayed_work(work), struct xfs_mount, m_reclaim_work); xfs_icwalk(mp, XFS_ICWALK_RECLAIM, NULL); xfs_reclaim_work_queue(mp); } STATIC int xfs_inode_free_eofblocks( struct xfs_inode *ip, struct xfs_icwalk *icw, unsigned int *lockflags) { bool wait; wait = icw && (icw->icw_flags & XFS_ICWALK_FLAG_SYNC); if (!xfs_iflags_test(ip, XFS_IEOFBLOCKS)) return 0; /* * If the mapping is dirty the operation can block and wait for some * time. Unless we are waiting, skip it. */ if (!wait && mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY)) return 0; if (!xfs_icwalk_match(ip, icw)) return 0; /* * If the caller is waiting, return -EAGAIN to keep the background * scanner moving and revisit the inode in a subsequent pass. */ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { if (wait) return -EAGAIN; return 0; } *lockflags |= XFS_IOLOCK_EXCL; if (xfs_can_free_eofblocks(ip, false)) return xfs_free_eofblocks(ip); /* inode could be preallocated or append-only */ trace_xfs_inode_free_eofblocks_invalid(ip); xfs_inode_clear_eofblocks_tag(ip); return 0; } static void xfs_blockgc_set_iflag( struct xfs_inode *ip, unsigned long iflag) { struct xfs_mount *mp = ip->i_mount; struct xfs_perag *pag; ASSERT((iflag & ~(XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0); /* * Don't bother locking the AG and looking up in the radix trees * if we already know that we have the tag set. */ if (ip->i_flags & iflag) return; spin_lock(&ip->i_flags_lock); ip->i_flags |= iflag; spin_unlock(&ip->i_flags_lock); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); spin_lock(&pag->pag_ici_lock); xfs_perag_set_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_BLOCKGC_TAG); spin_unlock(&pag->pag_ici_lock); xfs_perag_put(pag); } void xfs_inode_set_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_eofblocks_tag(ip); return xfs_blockgc_set_iflag(ip, XFS_IEOFBLOCKS); } static void xfs_blockgc_clear_iflag( struct xfs_inode *ip, unsigned long iflag) { struct xfs_mount *mp = ip->i_mount; struct xfs_perag *pag; bool clear_tag; ASSERT((iflag & ~(XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0); spin_lock(&ip->i_flags_lock); ip->i_flags &= ~iflag; clear_tag = (ip->i_flags & (XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0; spin_unlock(&ip->i_flags_lock); if (!clear_tag) return; pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); spin_lock(&pag->pag_ici_lock); xfs_perag_clear_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_BLOCKGC_TAG); spin_unlock(&pag->pag_ici_lock); xfs_perag_put(pag); } void xfs_inode_clear_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_eofblocks_tag(ip); return xfs_blockgc_clear_iflag(ip, XFS_IEOFBLOCKS); } /* * Set ourselves up to free CoW blocks from this file. If it's already clean * then we can bail out quickly, but otherwise we must back off if the file * is undergoing some kind of write. */ static bool xfs_prep_free_cowblocks( struct xfs_inode *ip) { /* * Just clear the tag if we have an empty cow fork or none at all. It's * possible the inode was fully unshared since it was originally tagged. */ if (!xfs_inode_has_cow_data(ip)) { trace_xfs_inode_free_cowblocks_invalid(ip); xfs_inode_clear_cowblocks_tag(ip); return false; } /* * If the mapping is dirty or under writeback we cannot touch the * CoW fork. Leave it alone if we're in the midst of a directio. */ if ((VFS_I(ip)->i_state & I_DIRTY_PAGES) || mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) || mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_WRITEBACK) || atomic_read(&VFS_I(ip)->i_dio_count)) return false; return true; } /* * Automatic CoW Reservation Freeing * * These functions automatically garbage collect leftover CoW reservations * that were made on behalf of a cowextsize hint when we start to run out * of quota or when the reservations sit around for too long. If the file * has dirty pages or is undergoing writeback, its CoW reservations will * be retained. * * The actual garbage collection piggybacks off the same code that runs * the speculative EOF preallocation garbage collector. */ STATIC int xfs_inode_free_cowblocks( struct xfs_inode *ip, struct xfs_icwalk *icw, unsigned int *lockflags) { bool wait; int ret = 0; wait = icw && (icw->icw_flags & XFS_ICWALK_FLAG_SYNC); if (!xfs_iflags_test(ip, XFS_ICOWBLOCKS)) return 0; if (!xfs_prep_free_cowblocks(ip)) return 0; if (!xfs_icwalk_match(ip, icw)) return 0; /* * If the caller is waiting, return -EAGAIN to keep the background * scanner moving and revisit the inode in a subsequent pass. */ if (!(*lockflags & XFS_IOLOCK_EXCL) && !xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { if (wait) return -EAGAIN; return 0; } *lockflags |= XFS_IOLOCK_EXCL; if (!xfs_ilock_nowait(ip, XFS_MMAPLOCK_EXCL)) { if (wait) return -EAGAIN; return 0; } *lockflags |= XFS_MMAPLOCK_EXCL; /* * Check again, nobody else should be able to dirty blocks or change * the reflink iflag now that we have the first two locks held. */ if (xfs_prep_free_cowblocks(ip)) ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false); return ret; } void xfs_inode_set_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_cowblocks_tag(ip); return xfs_blockgc_set_iflag(ip, XFS_ICOWBLOCKS); } void xfs_inode_clear_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_cowblocks_tag(ip); return xfs_blockgc_clear_iflag(ip, XFS_ICOWBLOCKS); } /* Disable post-EOF and CoW block auto-reclamation. */ void xfs_blockgc_stop( struct xfs_mount *mp) { struct xfs_perag *pag; xfs_agnumber_t agno; if (!xfs_clear_blockgc_enabled(mp)) return; for_each_perag(mp, agno, pag) cancel_delayed_work_sync(&pag->pag_blockgc_work); trace_xfs_blockgc_stop(mp, __return_address); } /* Enable post-EOF and CoW block auto-reclamation. */ void xfs_blockgc_start( struct xfs_mount *mp) { struct xfs_perag *pag; xfs_agnumber_t agno; if (xfs_set_blockgc_enabled(mp)) return; trace_xfs_blockgc_start(mp, __return_address); for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) xfs_blockgc_queue(pag); } /* Don't try to run block gc on an inode that's in any of these states. */ #define XFS_BLOCKGC_NOGRAB_IFLAGS (XFS_INEW | \ XFS_NEED_INACTIVE | \ XFS_INACTIVATING | \ XFS_IRECLAIMABLE | \ XFS_IRECLAIM) /* * Decide if the given @ip is eligible for garbage collection of speculative * preallocations, and grab it if so. Returns true if it's ready to go or * false if we should just ignore it. */ static bool xfs_blockgc_igrab( struct xfs_inode *ip) { struct inode *inode = VFS_I(ip); ASSERT(rcu_read_lock_held()); /* Check for stale RCU freed inode */ spin_lock(&ip->i_flags_lock); if (!ip->i_ino) goto out_unlock_noent; if (ip->i_flags & XFS_BLOCKGC_NOGRAB_IFLAGS) goto out_unlock_noent; spin_unlock(&ip->i_flags_lock); /* nothing to sync during shutdown */ if (xfs_is_shutdown(ip->i_mount)) return false; /* If we can't grab the inode, it must on it's way to reclaim. */ if (!igrab(inode)) return false; /* inode is valid */ return true; out_unlock_noent: spin_unlock(&ip->i_flags_lock); return false; } /* Scan one incore inode for block preallocations that we can remove. */ static int xfs_blockgc_scan_inode( struct xfs_inode *ip, struct xfs_icwalk *icw) { unsigned int lockflags = 0; int error; error = xfs_inode_free_eofblocks(ip, icw, &lockflags); if (error) goto unlock; error = xfs_inode_free_cowblocks(ip, icw, &lockflags); unlock: if (lockflags) xfs_iunlock(ip, lockflags); xfs_irele(ip); return error; } /* Background worker that trims preallocated space. */ void xfs_blockgc_worker( struct work_struct *work) { struct xfs_perag *pag = container_of(to_delayed_work(work), struct xfs_perag, pag_blockgc_work); struct xfs_mount *mp = pag->pag_mount; int error; trace_xfs_blockgc_worker(mp, __return_address); error = xfs_icwalk_ag(pag, XFS_ICWALK_BLOCKGC, NULL); if (error) xfs_info(mp, "AG %u preallocation gc worker failed, err=%d", pag->pag_agno, error); xfs_blockgc_queue(pag); } /* * Try to free space in the filesystem by purging inactive inodes, eofblocks * and cowblocks. */ int xfs_blockgc_free_space( struct xfs_mount *mp, struct xfs_icwalk *icw) { int error; trace_xfs_blockgc_free_space(mp, icw, _RET_IP_); error = xfs_icwalk(mp, XFS_ICWALK_BLOCKGC, icw); if (error) return error; return xfs_inodegc_flush(mp); } /* * Reclaim all the free space that we can by scheduling the background blockgc * and inodegc workers immediately and waiting for them all to clear. */ int xfs_blockgc_flush_all( struct xfs_mount *mp) { struct xfs_perag *pag; xfs_agnumber_t agno; trace_xfs_blockgc_flush_all(mp, __return_address); /* * For each blockgc worker, move its queue time up to now. If it * wasn't queued, it will not be requeued. Then flush whatever's * left. */ for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) mod_delayed_work(pag->pag_mount->m_blockgc_wq, &pag->pag_blockgc_work, 0); for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) flush_delayed_work(&pag->pag_blockgc_work); return xfs_inodegc_flush(mp); } /* * Run cow/eofblocks scans on the supplied dquots. We don't know exactly which * quota caused an allocation failure, so we make a best effort by including * each quota under low free space conditions (less than 1% free space) in the * scan. * * Callers must not hold any inode's ILOCK. If requesting a synchronous scan * (XFS_ICWALK_FLAG_SYNC), the caller also must not hold any inode's IOLOCK or * MMAPLOCK. */ int xfs_blockgc_free_dquots( struct xfs_mount *mp, struct xfs_dquot *udqp, struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, unsigned int iwalk_flags) { struct xfs_icwalk icw = {0}; bool do_work = false; if (!udqp && !gdqp && !pdqp) return 0; /* * Run a scan to free blocks using the union filter to cover all * applicable quotas in a single scan. */ icw.icw_flags = XFS_ICWALK_FLAG_UNION | iwalk_flags; if (XFS_IS_UQUOTA_ENFORCED(mp) && udqp && xfs_dquot_lowsp(udqp)) { icw.icw_uid = make_kuid(mp->m_super->s_user_ns, udqp->q_id); icw.icw_flags |= XFS_ICWALK_FLAG_UID; do_work = true; } if (XFS_IS_UQUOTA_ENFORCED(mp) && gdqp && xfs_dquot_lowsp(gdqp)) { icw.icw_gid = make_kgid(mp->m_super->s_user_ns, gdqp->q_id); icw.icw_flags |= XFS_ICWALK_FLAG_GID; do_work = true; } if (XFS_IS_PQUOTA_ENFORCED(mp) && pdqp && xfs_dquot_lowsp(pdqp)) { icw.icw_prid = pdqp->q_id; icw.icw_flags |= XFS_ICWALK_FLAG_PRID; do_work = true; } if (!do_work) return 0; return xfs_blockgc_free_space(mp, &icw); } /* Run cow/eofblocks scans on the quotas attached to the inode. */ int xfs_blockgc_free_quota( struct xfs_inode *ip, unsigned int iwalk_flags) { return xfs_blockgc_free_dquots(ip->i_mount, xfs_inode_dquot(ip, XFS_DQTYPE_USER), xfs_inode_dquot(ip, XFS_DQTYPE_GROUP), xfs_inode_dquot(ip, XFS_DQTYPE_PROJ), iwalk_flags); } /* XFS Inode Cache Walking Code */ /* * The inode lookup is done in batches to keep the amount of lock traffic and * radix tree lookups to a minimum. The batch size is a trade off between * lookup reduction and stack usage. This is in the reclaim path, so we can't * be too greedy. */ #define XFS_LOOKUP_BATCH 32 /* * Decide if we want to grab this inode in anticipation of doing work towards * the goal. */ static inline bool xfs_icwalk_igrab( enum xfs_icwalk_goal goal, struct xfs_inode *ip, struct xfs_icwalk *icw) { switch (goal) { case XFS_ICWALK_BLOCKGC: return xfs_blockgc_igrab(ip); case XFS_ICWALK_RECLAIM: return xfs_reclaim_igrab(ip, icw); default: return false; } } /* * Process an inode. Each processing function must handle any state changes * made by the icwalk igrab function. Return -EAGAIN to skip an inode. */ static inline int xfs_icwalk_process_inode( enum xfs_icwalk_goal goal, struct xfs_inode *ip, struct xfs_perag *pag, struct xfs_icwalk *icw) { int error = 0; switch (goal) { case XFS_ICWALK_BLOCKGC: error = xfs_blockgc_scan_inode(ip, icw); break; case XFS_ICWALK_RECLAIM: xfs_reclaim_inode(ip, pag); break; } return error; } /* * For a given per-AG structure @pag and a goal, grab qualifying inodes and * process them in some manner. */ static int xfs_icwalk_ag( struct xfs_perag *pag, enum xfs_icwalk_goal goal, struct xfs_icwalk *icw) { struct xfs_mount *mp = pag->pag_mount; uint32_t first_index; int last_error = 0; int skipped; bool done; int nr_found; restart: done = false; skipped = 0; if (goal == XFS_ICWALK_RECLAIM) first_index = READ_ONCE(pag->pag_ici_reclaim_cursor); else first_index = 0; nr_found = 0; do { struct xfs_inode *batch[XFS_LOOKUP_BATCH]; int error = 0; int i; rcu_read_lock(); nr_found = radix_tree_gang_lookup_tag(&pag->pag_ici_root, (void **) batch, first_index, XFS_LOOKUP_BATCH, goal); if (!nr_found) { done = true; rcu_read_unlock(); break; } /* * Grab the inodes before we drop the lock. if we found * nothing, nr == 0 and the loop will be skipped. */ for (i = 0; i < nr_found; i++) { struct xfs_inode *ip = batch[i]; if (done || !xfs_icwalk_igrab(goal, ip, icw)) batch[i] = NULL; /* * Update the index for the next lookup. Catch * overflows into the next AG range which can occur if * we have inodes in the last block of the AG and we * are currently pointing to the last inode. * * Because we may see inodes that are from the wrong AG * due to RCU freeing and reallocation, only update the * index if it lies in this AG. It was a race that lead * us to see this inode, so another lookup from the * same index will not find it again. */ if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno) continue; first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1); if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) done = true; } /* unlock now we've grabbed the inodes. */ rcu_read_unlock(); for (i = 0; i < nr_found; i++) { if (!batch[i]) continue; error = xfs_icwalk_process_inode(goal, batch[i], pag, icw); if (error == -EAGAIN) { skipped++; continue; } if (error && last_error != -EFSCORRUPTED) last_error = error; } /* bail out if the filesystem is corrupted. */ if (error == -EFSCORRUPTED) break; cond_resched(); if (icw && (icw->icw_flags & XFS_ICWALK_FLAG_SCAN_LIMIT)) { icw->icw_scan_limit -= XFS_LOOKUP_BATCH; if (icw->icw_scan_limit <= 0) break; } } while (nr_found && !done); if (goal == XFS_ICWALK_RECLAIM) { if (done) first_index = 0; WRITE_ONCE(pag->pag_ici_reclaim_cursor, first_index); } if (skipped) { delay(1); goto restart; } return last_error; } /* Walk all incore inodes to achieve a given goal. */ static int xfs_icwalk( struct xfs_mount *mp, enum xfs_icwalk_goal goal, struct xfs_icwalk *icw) { struct xfs_perag *pag; int error = 0; int last_error = 0; xfs_agnumber_t agno; for_each_perag_tag(mp, agno, pag, goal) { error = xfs_icwalk_ag(pag, goal, icw); if (error) { last_error = error; if (error == -EFSCORRUPTED) { xfs_perag_rele(pag); break; } } } return last_error; BUILD_BUG_ON(XFS_ICWALK_PRIVATE_FLAGS & XFS_ICWALK_FLAGS_VALID); } #ifdef DEBUG static void xfs_check_delalloc( struct xfs_inode *ip, int whichfork) { struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec got; struct xfs_iext_cursor icur; if (!ifp || !xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got)) return; do { if (isnullstartblock(got.br_startblock)) { xfs_warn(ip->i_mount, "ino %llx %s fork has delalloc extent at [0x%llx:0x%llx]", ip->i_ino, whichfork == XFS_DATA_FORK ? "data" : "cow", got.br_startoff, got.br_blockcount); } } while (xfs_iext_next_extent(ifp, &icur, &got)); } #else #define xfs_check_delalloc(ip, whichfork) do { } while (0) #endif /* Schedule the inode for reclaim. */ static void xfs_inodegc_set_reclaimable( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_perag *pag; if (!xfs_is_shutdown(mp) && ip->i_delayed_blks) { xfs_check_delalloc(ip, XFS_DATA_FORK); xfs_check_delalloc(ip, XFS_COW_FORK); ASSERT(0); } pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); spin_lock(&pag->pag_ici_lock); spin_lock(&ip->i_flags_lock); trace_xfs_inode_set_reclaimable(ip); ip->i_flags &= ~(XFS_NEED_INACTIVE | XFS_INACTIVATING); ip->i_flags |= XFS_IRECLAIMABLE; xfs_perag_set_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG); spin_unlock(&ip->i_flags_lock); spin_unlock(&pag->pag_ici_lock); xfs_perag_put(pag); } /* * Free all speculative preallocations and possibly even the inode itself. * This is the last chance to make changes to an otherwise unreferenced file * before incore reclamation happens. */ static int xfs_inodegc_inactivate( struct xfs_inode *ip) { int error; trace_xfs_inode_inactivating(ip); error = xfs_inactive(ip); xfs_inodegc_set_reclaimable(ip); return error; } void xfs_inodegc_worker( struct work_struct *work) { struct xfs_inodegc *gc = container_of(to_delayed_work(work), struct xfs_inodegc, work); struct llist_node *node = llist_del_all(&gc->list); struct xfs_inode *ip, *n; struct xfs_mount *mp = gc->mp; unsigned int nofs_flag; /* * Clear the cpu mask bit and ensure that we have seen the latest * update of the gc structure associated with this CPU. This matches * with the release semantics used when setting the cpumask bit in * xfs_inodegc_queue. */ cpumask_clear_cpu(gc->cpu, &mp->m_inodegc_cpumask); smp_mb__after_atomic(); WRITE_ONCE(gc->items, 0); if (!node) return; /* * We can allocate memory here while doing writeback on behalf of * memory reclaim. To avoid memory allocation deadlocks set the * task-wide nofs context for the following operations. */ nofs_flag = memalloc_nofs_save(); ip = llist_entry(node, struct xfs_inode, i_gclist); trace_xfs_inodegc_worker(mp, READ_ONCE(gc->shrinker_hits)); WRITE_ONCE(gc->shrinker_hits, 0); llist_for_each_entry_safe(ip, n, node, i_gclist) { int error; xfs_iflags_set(ip, XFS_INACTIVATING); error = xfs_inodegc_inactivate(ip); if (error && !gc->error) gc->error = error; } memalloc_nofs_restore(nofs_flag); } /* * Expedite all pending inodegc work to run immediately. This does not wait for * completion of the work. */ void xfs_inodegc_push( struct xfs_mount *mp) { if (!xfs_is_inodegc_enabled(mp)) return; trace_xfs_inodegc_push(mp, __return_address); xfs_inodegc_queue_all(mp); } /* * Force all currently queued inode inactivation work to run immediately and * wait for the work to finish. */ int xfs_inodegc_flush( struct xfs_mount *mp) { xfs_inodegc_push(mp); trace_xfs_inodegc_flush(mp, __return_address); return xfs_inodegc_wait_all(mp); } /* * Flush all the pending work and then disable the inode inactivation background * workers and wait for them to stop. Caller must hold sb->s_umount to * coordinate changes in the inodegc_enabled state. */ void xfs_inodegc_stop( struct xfs_mount *mp) { bool rerun; if (!xfs_clear_inodegc_enabled(mp)) return; /* * Drain all pending inodegc work, including inodes that could be * queued by racing xfs_inodegc_queue or xfs_inodegc_shrinker_scan * threads that sample the inodegc state just prior to us clearing it. * The inodegc flag state prevents new threads from queuing more * inodes, so we queue pending work items and flush the workqueue until * all inodegc lists are empty. IOWs, we cannot use drain_workqueue * here because it does not allow other unserialized mechanisms to * reschedule inodegc work while this draining is in progress. */ xfs_inodegc_queue_all(mp); do { flush_workqueue(mp->m_inodegc_wq); rerun = xfs_inodegc_queue_all(mp); } while (rerun); trace_xfs_inodegc_stop(mp, __return_address); } /* * Enable the inode inactivation background workers and schedule deferred inode * inactivation work if there is any. Caller must hold sb->s_umount to * coordinate changes in the inodegc_enabled state. */ void xfs_inodegc_start( struct xfs_mount *mp) { if (xfs_set_inodegc_enabled(mp)) return; trace_xfs_inodegc_start(mp, __return_address); xfs_inodegc_queue_all(mp); } #ifdef CONFIG_XFS_RT static inline bool xfs_inodegc_want_queue_rt_file( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; if (!XFS_IS_REALTIME_INODE(ip)) return false; if (__percpu_counter_compare(&mp->m_frextents, mp->m_low_rtexts[XFS_LOWSP_5_PCNT], XFS_FDBLOCKS_BATCH) < 0) return true; return false; } #else # define xfs_inodegc_want_queue_rt_file(ip) (false) #endif /* CONFIG_XFS_RT */ /* * Schedule the inactivation worker when: * * - We've accumulated more than one inode cluster buffer's worth of inodes. * - There is less than 5% free space left. * - Any of the quotas for this inode are near an enforcement limit. */ static inline bool xfs_inodegc_want_queue_work( struct xfs_inode *ip, unsigned int items) { struct xfs_mount *mp = ip->i_mount; if (items > mp->m_ino_geo.inodes_per_cluster) return true; if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_low_space[XFS_LOWSP_5_PCNT], XFS_FDBLOCKS_BATCH) < 0) return true; if (xfs_inodegc_want_queue_rt_file(ip)) return true; if (xfs_inode_near_dquot_enforcement(ip, XFS_DQTYPE_USER)) return true; if (xfs_inode_near_dquot_enforcement(ip, XFS_DQTYPE_GROUP)) return true; if (xfs_inode_near_dquot_enforcement(ip, XFS_DQTYPE_PROJ)) return true; return false; } /* * Upper bound on the number of inodes in each AG that can be queued for * inactivation at any given time, to avoid monopolizing the workqueue. */ #define XFS_INODEGC_MAX_BACKLOG (4 * XFS_INODES_PER_CHUNK) /* * Make the frontend wait for inactivations when: * * - Memory shrinkers queued the inactivation worker and it hasn't finished. * - The queue depth exceeds the maximum allowable percpu backlog. * * Note: If the current thread is running a transaction, we don't ever want to * wait for other transactions because that could introduce a deadlock. */ static inline bool xfs_inodegc_want_flush_work( struct xfs_inode *ip, unsigned int items, unsigned int shrinker_hits) { if (current->journal_info) return false; if (shrinker_hits > 0) return true; if (items > XFS_INODEGC_MAX_BACKLOG) return true; return false; } /* * Queue a background inactivation worker if there are inodes that need to be * inactivated and higher level xfs code hasn't disabled the background * workers. */ static void xfs_inodegc_queue( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_inodegc *gc; int items; unsigned int shrinker_hits; unsigned int cpu_nr; unsigned long queue_delay = 1; trace_xfs_inode_set_need_inactive(ip); spin_lock(&ip->i_flags_lock); ip->i_flags |= XFS_NEED_INACTIVE; spin_unlock(&ip->i_flags_lock); cpu_nr = get_cpu(); gc = this_cpu_ptr(mp->m_inodegc); llist_add(&ip->i_gclist, &gc->list); items = READ_ONCE(gc->items); WRITE_ONCE(gc->items, items + 1); shrinker_hits = READ_ONCE(gc->shrinker_hits); /* * Ensure the list add is always seen by anyone who finds the cpumask * bit set. This effectively gives the cpumask bit set operation * release ordering semantics. */ smp_mb__before_atomic(); if (!cpumask_test_cpu(cpu_nr, &mp->m_inodegc_cpumask)) cpumask_test_and_set_cpu(cpu_nr, &mp->m_inodegc_cpumask); /* * We queue the work while holding the current CPU so that the work * is scheduled to run on this CPU. */ if (!xfs_is_inodegc_enabled(mp)) { put_cpu(); return; } if (xfs_inodegc_want_queue_work(ip, items)) queue_delay = 0; trace_xfs_inodegc_queue(mp, __return_address); mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work, queue_delay); put_cpu(); if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) { trace_xfs_inodegc_throttle(mp, __return_address); flush_delayed_work(&gc->work); } } /* * We set the inode flag atomically with the radix tree tag. Once we get tag * lookups on the radix tree, this inode flag can go away. * * We always use background reclaim here because even if the inode is clean, it * still may be under IO and hence we have wait for IO completion to occur * before we can reclaim the inode. The background reclaim path handles this * more efficiently than we can here, so simply let background reclaim tear down * all inodes. */ void xfs_inode_mark_reclaimable( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; bool need_inactive; XFS_STATS_INC(mp, vn_reclaim); /* * We should never get here with any of the reclaim flags already set. */ ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_ALL_IRECLAIM_FLAGS)); need_inactive = xfs_inode_needs_inactive(ip); if (need_inactive) { xfs_inodegc_queue(ip); return; } /* Going straight to reclaim, so drop the dquots. */ xfs_qm_dqdetach(ip); xfs_inodegc_set_reclaimable(ip); } /* * Register a phony shrinker so that we can run background inodegc sooner when * there's memory pressure. Inactivation does not itself free any memory but * it does make inodes reclaimable, which eventually frees memory. * * The count function, seek value, and batch value are crafted to trigger the * scan function during the second round of scanning. Hopefully this means * that we reclaimed enough memory that initiating metadata transactions won't * make things worse. */ #define XFS_INODEGC_SHRINKER_COUNT (1UL << DEF_PRIORITY) #define XFS_INODEGC_SHRINKER_BATCH ((XFS_INODEGC_SHRINKER_COUNT / 2) + 1) static unsigned long xfs_inodegc_shrinker_count( struct shrinker *shrink, struct shrink_control *sc) { struct xfs_mount *mp = shrink->private_data; struct xfs_inodegc *gc; int cpu; if (!xfs_is_inodegc_enabled(mp)) return 0; for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) return XFS_INODEGC_SHRINKER_COUNT; } return 0; } static unsigned long xfs_inodegc_shrinker_scan( struct shrinker *shrink, struct shrink_control *sc) { struct xfs_mount *mp = shrink->private_data; struct xfs_inodegc *gc; int cpu; bool no_items = true; if (!xfs_is_inodegc_enabled(mp)) return SHRINK_STOP; trace_xfs_inodegc_shrinker_scan(mp, sc, __return_address); for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) { unsigned int h = READ_ONCE(gc->shrinker_hits); WRITE_ONCE(gc->shrinker_hits, h + 1); mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0); no_items = false; } } /* * If there are no inodes to inactivate, we don't want the shrinker * to think there's deferred work to call us back about. */ if (no_items) return LONG_MAX; return SHRINK_STOP; } /* Register a shrinker so we can accelerate inodegc and throttle queuing. */ int xfs_inodegc_register_shrinker( struct xfs_mount *mp) { mp->m_inodegc_shrinker = shrinker_alloc(SHRINKER_NONSLAB, "xfs-inodegc:%s", mp->m_super->s_id); if (!mp->m_inodegc_shrinker) return -ENOMEM; mp->m_inodegc_shrinker->count_objects = xfs_inodegc_shrinker_count; mp->m_inodegc_shrinker->scan_objects = xfs_inodegc_shrinker_scan; mp->m_inodegc_shrinker->seeks = 0; mp->m_inodegc_shrinker->batch = XFS_INODEGC_SHRINKER_BATCH; mp->m_inodegc_shrinker->private_data = mp; shrinker_register(mp->m_inodegc_shrinker); return 0; } |
| 3971 3972 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 | // 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)); if (nr_vecs > inline_vecs) { bip->bip_max_vcnt = nr_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_max_vcnt = 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); /** * 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_BLOCK_INTEGRITY) kfree(bvec_virt(bip->bip_vec)); __bio_integrity_free(bs, bip); bio->bi_integrity = NULL; bio->bi_opf &= ~REQ_INTEGRITY; } /** * 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); /** * 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); __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); } |
| 14 14 14 14 14 14 14 14 14 14 14 14 14 14 13 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 13 12 12 12 12 12 12 12 10 10 10 12 12 12 12 12 14 14 12 14 14 14 14 14 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/power/snapshot.c * * This file provides system snapshot/restore functionality for swsusp. * * Copyright (C) 1998-2005 Pavel Machek <pavel@ucw.cz> * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> */ #define pr_fmt(fmt) "PM: hibernation: " fmt #include <linux/version.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/suspend.h> #include <linux/delay.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/kernel.h> #include <linux/pm.h> #include <linux/device.h> #include <linux/init.h> #include <linux/memblock.h> #include <linux/nmi.h> #include <linux/syscalls.h> #include <linux/console.h> #include <linux/highmem.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/compiler.h> #include <linux/ktime.h> #include <linux/set_memory.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include <asm/io.h> #include "power.h" #if defined(CONFIG_STRICT_KERNEL_RWX) && defined(CONFIG_ARCH_HAS_SET_MEMORY) static bool hibernate_restore_protection; static bool hibernate_restore_protection_active; void enable_restore_image_protection(void) { hibernate_restore_protection = true; } static inline void hibernate_restore_protection_begin(void) { hibernate_restore_protection_active = hibernate_restore_protection; } static inline void hibernate_restore_protection_end(void) { hibernate_restore_protection_active = false; } static inline void hibernate_restore_protect_page(void *page_address) { if (hibernate_restore_protection_active) set_memory_ro((unsigned long)page_address, 1); } static inline void hibernate_restore_unprotect_page(void *page_address) { if (hibernate_restore_protection_active) set_memory_rw((unsigned long)page_address, 1); } #else static inline void hibernate_restore_protection_begin(void) {} static inline void hibernate_restore_protection_end(void) {} static inline void hibernate_restore_protect_page(void *page_address) {} static inline void hibernate_restore_unprotect_page(void *page_address) {} #endif /* CONFIG_STRICT_KERNEL_RWX && CONFIG_ARCH_HAS_SET_MEMORY */ /* * The calls to set_direct_map_*() should not fail because remapping a page * here means that we only update protection bits in an existing PTE. * It is still worth to have a warning here if something changes and this * will no longer be the case. */ static inline void hibernate_map_page(struct page *page) { if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) { int ret = set_direct_map_default_noflush(page); if (ret) pr_warn_once("Failed to remap page\n"); } else { debug_pagealloc_map_pages(page, 1); } } static inline void hibernate_unmap_page(struct page *page) { if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) { unsigned long addr = (unsigned long)page_address(page); int ret = set_direct_map_invalid_noflush(page); if (ret) pr_warn_once("Failed to remap page\n"); flush_tlb_kernel_range(addr, addr + PAGE_SIZE); } else { debug_pagealloc_unmap_pages(page, 1); } } static int swsusp_page_is_free(struct page *); static void swsusp_set_page_forbidden(struct page *); static void swsusp_unset_page_forbidden(struct page *); /* * Number of bytes to reserve for memory allocations made by device drivers * from their ->freeze() and ->freeze_noirq() callbacks so that they don't * cause image creation to fail (tunable via /sys/power/reserved_size). */ unsigned long reserved_size; void __init hibernate_reserved_size_init(void) { reserved_size = SPARE_PAGES * PAGE_SIZE; } /* * Preferred image size in bytes (tunable via /sys/power/image_size). * When it is set to N, swsusp will do its best to ensure the image * size will not exceed N bytes, but if that is impossible, it will * try to create the smallest image possible. */ unsigned long image_size; void __init hibernate_image_size_init(void) { image_size = ((totalram_pages() * 2) / 5) * PAGE_SIZE; } /* * List of PBEs needed for restoring the pages that were allocated before * the suspend and included in the suspend image, but have also been * allocated by the "resume" kernel, so their contents cannot be written * directly to their "original" page frames. */ struct pbe *restore_pblist; /* struct linked_page is used to build chains of pages */ #define LINKED_PAGE_DATA_SIZE (PAGE_SIZE - sizeof(void *)) struct linked_page { struct linked_page *next; char data[LINKED_PAGE_DATA_SIZE]; } __packed; /* * List of "safe" pages (ie. pages that were not used by the image kernel * before hibernation) that may be used as temporary storage for image kernel * memory contents. */ static struct linked_page *safe_pages_list; /* Pointer to an auxiliary buffer (1 page) */ static void *buffer; #define PG_ANY 0 #define PG_SAFE 1 #define PG_UNSAFE_CLEAR 1 #define PG_UNSAFE_KEEP 0 static unsigned int allocated_unsafe_pages; /** * get_image_page - Allocate a page for a hibernation image. * @gfp_mask: GFP mask for the allocation. * @safe_needed: Get pages that were not used before hibernation (restore only) * * During image restoration, for storing the PBE list and the image data, we can * only use memory pages that do not conflict with the pages used before * hibernation. The "unsafe" pages have PageNosaveFree set and we count them * using allocated_unsafe_pages. * * Each allocated image page is marked as PageNosave and PageNosaveFree so that * swsusp_free() can release it. */ static void *get_image_page(gfp_t gfp_mask, int safe_needed) { void *res; res = (void *)get_zeroed_page(gfp_mask); if (safe_needed) while (res && swsusp_page_is_free(virt_to_page(res))) { /* The page is unsafe, mark it for swsusp_free() */ swsusp_set_page_forbidden(virt_to_page(res)); allocated_unsafe_pages++; res = (void *)get_zeroed_page(gfp_mask); } if (res) { swsusp_set_page_forbidden(virt_to_page(res)); swsusp_set_page_free(virt_to_page(res)); } return res; } static void *__get_safe_page(gfp_t gfp_mask) { if (safe_pages_list) { void *ret = safe_pages_list; safe_pages_list = safe_pages_list->next; memset(ret, 0, PAGE_SIZE); return ret; } return get_image_page(gfp_mask, PG_SAFE); } unsigned long get_safe_page(gfp_t gfp_mask) { return (unsigned long)__get_safe_page(gfp_mask); } static struct page *alloc_image_page(gfp_t gfp_mask) { struct page *page; page = alloc_page(gfp_mask); if (page) { swsusp_set_page_forbidden(page); swsusp_set_page_free(page); } return page; } static void recycle_safe_page(void *page_address) { struct linked_page *lp = page_address; lp->next = safe_pages_list; safe_pages_list = lp; } /** * free_image_page - Free a page allocated for hibernation image. * @addr: Address of the page to free. * @clear_nosave_free: If set, clear the PageNosaveFree bit for the page. * * The page to free should have been allocated by get_image_page() (page flags * set by it are affected). */ static inline void free_image_page(void *addr, int clear_nosave_free) { struct page *page; BUG_ON(!virt_addr_valid(addr)); page = virt_to_page(addr); swsusp_unset_page_forbidden(page); if (clear_nosave_free) swsusp_unset_page_free(page); __free_page(page); } static inline void free_list_of_pages(struct linked_page *list, int clear_page_nosave) { while (list) { struct linked_page *lp = list->next; free_image_page(list, clear_page_nosave); list = lp; } } /* * struct chain_allocator is used for allocating small objects out of * a linked list of pages called 'the chain'. * * The chain grows each time when there is no room for a new object in * the current page. The allocated objects cannot be freed individually. * It is only possible to free them all at once, by freeing the entire * chain. * * NOTE: The chain allocator may be inefficient if the allocated objects * are not much smaller than PAGE_SIZE. */ struct chain_allocator { struct linked_page *chain; /* the chain */ unsigned int used_space; /* total size of objects allocated out of the current page */ gfp_t gfp_mask; /* mask for allocating pages */ int safe_needed; /* if set, only "safe" pages are allocated */ }; static void chain_init(struct chain_allocator *ca, gfp_t gfp_mask, int safe_needed) { ca->chain = NULL; ca->used_space = LINKED_PAGE_DATA_SIZE; ca->gfp_mask = gfp_mask; ca->safe_needed = safe_needed; } static void *chain_alloc(struct chain_allocator *ca, unsigned int size) { void *ret; if (LINKED_PAGE_DATA_SIZE - ca->used_space < size) { struct linked_page *lp; lp = ca->safe_needed ? __get_safe_page(ca->gfp_mask) : get_image_page(ca->gfp_mask, PG_ANY); if (!lp) return NULL; lp->next = ca->chain; ca->chain = lp; ca->used_space = 0; } ret = ca->chain->data + ca->used_space; ca->used_space += size; return ret; } /* * Data types related to memory bitmaps. * * Memory bitmap is a structure consisting of many linked lists of * objects. The main list's elements are of type struct zone_bitmap * and each of them corresponds to one zone. For each zone bitmap * object there is a list of objects of type struct bm_block that * represent each blocks of bitmap in which information is stored. * * struct memory_bitmap contains a pointer to the main list of zone * bitmap objects, a struct bm_position used for browsing the bitmap, * and a pointer to the list of pages used for allocating all of the * zone bitmap objects and bitmap block objects. * * NOTE: It has to be possible to lay out the bitmap in memory * using only allocations of order 0. Additionally, the bitmap is * designed to work with arbitrary number of zones (this is over the * top for now, but let's avoid making unnecessary assumptions ;-). * * struct zone_bitmap contains a pointer to a list of bitmap block * objects and a pointer to the bitmap block object that has been * most recently used for setting bits. Additionally, it contains the * PFNs that correspond to the start and end of the represented zone. * * struct bm_block contains a pointer to the memory page in which * information is stored (in the form of a block of bitmap) * It also contains the pfns that correspond to the start and end of * the represented memory area. * * The memory bitmap is organized as a radix tree to guarantee fast random * access to the bits. There is one radix tree for each zone (as returned * from create_mem_extents). * * One radix tree is represented by one struct mem_zone_bm_rtree. There are * two linked lists for the nodes of the tree, one for the inner nodes and * one for the leave nodes. The linked leave nodes are used for fast linear * access of the memory bitmap. * * The struct rtree_node represents one node of the radix tree. */ #define BM_END_OF_MAP (~0UL) #define BM_BITS_PER_BLOCK (PAGE_SIZE * BITS_PER_BYTE) #define BM_BLOCK_SHIFT (PAGE_SHIFT + 3) #define BM_BLOCK_MASK ((1UL << BM_BLOCK_SHIFT) - 1) /* * struct rtree_node is a wrapper struct to link the nodes * of the rtree together for easy linear iteration over * bits and easy freeing */ struct rtree_node { struct list_head list; unsigned long *data; }; /* * struct mem_zone_bm_rtree represents a bitmap used for one * populated memory zone. */ struct mem_zone_bm_rtree { struct list_head list; /* Link Zones together */ struct list_head nodes; /* Radix Tree inner nodes */ struct list_head leaves; /* Radix Tree leaves */ unsigned long start_pfn; /* Zone start page frame */ unsigned long end_pfn; /* Zone end page frame + 1 */ struct rtree_node *rtree; /* Radix Tree Root */ int levels; /* Number of Radix Tree Levels */ unsigned int blocks; /* Number of Bitmap Blocks */ }; /* struct bm_position is used for browsing memory bitmaps */ struct bm_position { struct mem_zone_bm_rtree *zone; struct rtree_node *node; unsigned long node_pfn; unsigned long cur_pfn; int node_bit; }; struct memory_bitmap { struct list_head zones; struct linked_page *p_list; /* list of pages used to store zone bitmap objects and bitmap block objects */ struct bm_position cur; /* most recently used bit position */ }; /* Functions that operate on memory bitmaps */ #define BM_ENTRIES_PER_LEVEL (PAGE_SIZE / sizeof(unsigned long)) #if BITS_PER_LONG == 32 #define BM_RTREE_LEVEL_SHIFT (PAGE_SHIFT - 2) #else #define BM_RTREE_LEVEL_SHIFT (PAGE_SHIFT - 3) #endif #define BM_RTREE_LEVEL_MASK ((1UL << BM_RTREE_LEVEL_SHIFT) - 1) /** * alloc_rtree_node - Allocate a new node and add it to the radix tree. * @gfp_mask: GFP mask for the allocation. * @safe_needed: Get pages not used before hibernation (restore only) * @ca: Pointer to a linked list of pages ("a chain") to allocate from * @list: Radix Tree node to add. * * This function is used to allocate inner nodes as well as the * leave nodes of the radix tree. It also adds the node to the * corresponding linked list passed in by the *list parameter. */ static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca, struct list_head *list) { struct rtree_node *node; node = chain_alloc(ca, sizeof(struct rtree_node)); if (!node) return NULL; node->data = get_image_page(gfp_mask, safe_needed); if (!node->data) return NULL; list_add_tail(&node->list, list); return node; } /** * add_rtree_block - Add a new leave node to the radix tree. * * The leave nodes need to be allocated in order to keep the leaves * linked list in order. This is guaranteed by the zone->blocks * counter. */ static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca) { struct rtree_node *node, *block, **dst; unsigned int levels_needed, block_nr; int i; block_nr = zone->blocks; levels_needed = 0; /* How many levels do we need for this block nr? */ while (block_nr) { levels_needed += 1; block_nr >>= BM_RTREE_LEVEL_SHIFT; } /* Make sure the rtree has enough levels */ for (i = zone->levels; i < levels_needed; i++) { node = alloc_rtree_node(gfp_mask, safe_needed, ca, &zone->nodes); if (!node) return -ENOMEM; node->data[0] = (unsigned long)zone->rtree; zone->rtree = node; zone->levels += 1; } /* Allocate new block */ block = alloc_rtree_node(gfp_mask, safe_needed, ca, &zone->leaves); if (!block) return -ENOMEM; /* Now walk the rtree to insert the block */ node = zone->rtree; dst = &zone->rtree; block_nr = zone->blocks; for (i = zone->levels; i > 0; i--) { int index; if (!node) { node = alloc_rtree_node(gfp_mask, safe_needed, ca, &zone->nodes); if (!node) return -ENOMEM; *dst = node; } index = block_nr >> ((i - 1) * BM_RTREE_LEVEL_SHIFT); index &= BM_RTREE_LEVEL_MASK; dst = (struct rtree_node **)&((*dst)->data[index]); node = *dst; } zone->blocks += 1; *dst = block; return 0; } static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, int clear_nosave_free); /** * create_zone_bm_rtree - Create a radix tree for one zone. * * Allocated the mem_zone_bm_rtree structure and initializes it. * This function also allocated and builds the radix tree for the * zone. */ static struct mem_zone_bm_rtree *create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca, unsigned long start, unsigned long end) { struct mem_zone_bm_rtree *zone; unsigned int i, nr_blocks; unsigned long pages; pages = end - start; zone = chain_alloc(ca, sizeof(struct mem_zone_bm_rtree)); if (!zone) return NULL; INIT_LIST_HEAD(&zone->nodes); INIT_LIST_HEAD(&zone->leaves); zone->start_pfn = start; zone->end_pfn = end; nr_blocks = DIV_ROUND_UP(pages, BM_BITS_PER_BLOCK); for (i = 0; i < nr_blocks; i++) { if (add_rtree_block(zone, gfp_mask, safe_needed, ca)) { free_zone_bm_rtree(zone, PG_UNSAFE_CLEAR); return NULL; } } return zone; } /** * free_zone_bm_rtree - Free the memory of the radix tree. * * Free all node pages of the radix tree. The mem_zone_bm_rtree * structure itself is not freed here nor are the rtree_node * structs. */ static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, int clear_nosave_free) { struct rtree_node *node; list_for_each_entry(node, &zone->nodes, list) free_image_page(node->data, clear_nosave_free); list_for_each_entry(node, &zone->leaves, list) free_image_page(node->data, clear_nosave_free); } static void memory_bm_position_reset(struct memory_bitmap *bm) { bm->cur.zone = list_entry(bm->zones.next, struct mem_zone_bm_rtree, list); bm->cur.node = list_entry(bm->cur.zone->leaves.next, struct rtree_node, list); bm->cur.node_pfn = 0; bm->cur.cur_pfn = BM_END_OF_MAP; bm->cur.node_bit = 0; } static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free); struct mem_extent { struct list_head hook; unsigned long start; unsigned long end; }; /** * free_mem_extents - Free a list of memory extents. * @list: List of extents to free. */ static void free_mem_extents(struct list_head *list) { struct mem_extent *ext, *aux; list_for_each_entry_safe(ext, aux, list, hook) { list_del(&ext->hook); kfree(ext); } } /** * create_mem_extents - Create a list of memory extents. * @list: List to put the extents into. * @gfp_mask: Mask to use for memory allocations. * * The extents represent contiguous ranges of PFNs. */ static int create_mem_extents(struct list_head *list, gfp_t gfp_mask) { struct zone *zone; INIT_LIST_HEAD(list); for_each_populated_zone(zone) { unsigned long zone_start, zone_end; struct mem_extent *ext, *cur, *aux; zone_start = zone->zone_start_pfn; zone_end = zone_end_pfn(zone); list_for_each_entry(ext, list, hook) if (zone_start <= ext->end) break; if (&ext->hook == list || zone_end < ext->start) { /* New extent is necessary */ struct mem_extent *new_ext; new_ext = kzalloc(sizeof(struct mem_extent), gfp_mask); if (!new_ext) { free_mem_extents(list); return -ENOMEM; } new_ext->start = zone_start; new_ext->end = zone_end; list_add_tail(&new_ext->hook, &ext->hook); continue; } /* Merge this zone's range of PFNs with the existing one */ if (zone_start < ext->start) ext->start = zone_start; if (zone_end > ext->end) ext->end = zone_end; /* More merging may be possible */ cur = ext; list_for_each_entry_safe_continue(cur, aux, list, hook) { if (zone_end < cur->start) break; if (zone_end < cur->end) ext->end = cur->end; list_del(&cur->hook); kfree(cur); } } return 0; } /** * memory_bm_create - Allocate memory for a memory bitmap. */ static int memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed) { struct chain_allocator ca; struct list_head mem_extents; struct mem_extent *ext; int error; chain_init(&ca, gfp_mask, safe_needed); INIT_LIST_HEAD(&bm->zones); error = create_mem_extents(&mem_extents, gfp_mask); if (error) return error; list_for_each_entry(ext, &mem_extents, hook) { struct mem_zone_bm_rtree *zone; zone = create_zone_bm_rtree(gfp_mask, safe_needed, &ca, ext->start, ext->end); if (!zone) { error = -ENOMEM; goto Error; } list_add_tail(&zone->list, &bm->zones); } bm->p_list = ca.chain; memory_bm_position_reset(bm); Exit: free_mem_extents(&mem_extents); return error; Error: bm->p_list = ca.chain; memory_bm_free(bm, PG_UNSAFE_CLEAR); goto Exit; } /** * memory_bm_free - Free memory occupied by the memory bitmap. * @bm: Memory bitmap. */ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) { struct mem_zone_bm_rtree *zone; list_for_each_entry(zone, &bm->zones, list) free_zone_bm_rtree(zone, clear_nosave_free); free_list_of_pages(bm->p_list, clear_nosave_free); INIT_LIST_HEAD(&bm->zones); } /** * memory_bm_find_bit - Find the bit for a given PFN in a memory bitmap. * * Find the bit in memory bitmap @bm that corresponds to the given PFN. * The cur.zone, cur.block and cur.node_pfn members of @bm are updated. * * Walk the radix tree to find the page containing the bit that represents @pfn * and return the position of the bit in @addr and @bit_nr. */ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, void **addr, unsigned int *bit_nr) { struct mem_zone_bm_rtree *curr, *zone; struct rtree_node *node; int i, block_nr; zone = bm->cur.zone; if (pfn >= zone->start_pfn && pfn < zone->end_pfn) goto zone_found; zone = NULL; /* Find the right zone */ list_for_each_entry(curr, &bm->zones, list) { if (pfn >= curr->start_pfn && pfn < curr->end_pfn) { zone = curr; break; } } if (!zone) return -EFAULT; zone_found: /* * We have found the zone. Now walk the radix tree to find the leaf node * for our PFN. */ /* * If the zone we wish to scan is the current zone and the * pfn falls into the current node then we do not need to walk * the tree. */ node = bm->cur.node; if (zone == bm->cur.zone && ((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn) goto node_found; node = zone->rtree; block_nr = (pfn - zone->start_pfn) >> BM_BLOCK_SHIFT; for (i = zone->levels; i > 0; i--) { int index; index = block_nr >> ((i - 1) * BM_RTREE_LEVEL_SHIFT); index &= BM_RTREE_LEVEL_MASK; BUG_ON(node->data[index] == 0); node = (struct rtree_node *)node->data[index]; } node_found: /* Update last position */ bm->cur.zone = zone; bm->cur.node = node; bm->cur.node_pfn = (pfn - zone->start_pfn) & ~BM_BLOCK_MASK; bm->cur.cur_pfn = pfn; /* Set return values */ *addr = node->data; *bit_nr = (pfn - zone->start_pfn) & BM_BLOCK_MASK; return 0; } static void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn) { void *addr; unsigned int bit; int error; error = memory_bm_find_bit(bm, pfn, &addr, &bit); BUG_ON(error); set_bit(bit, addr); } static int mem_bm_set_bit_check(struct memory_bitmap *bm, unsigned long pfn) { void *addr; unsigned int bit; int error; error = memory_bm_find_bit(bm, pfn, &addr, &bit); if (!error) set_bit(bit, addr); return error; } static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn) { void *addr; unsigned int bit; int error; error = memory_bm_find_bit(bm, pfn, &addr, &bit); BUG_ON(error); clear_bit(bit, addr); } static void memory_bm_clear_current(struct memory_bitmap *bm) { int bit; bit = max(bm->cur.node_bit - 1, 0); clear_bit(bit, bm->cur.node->data); } static unsigned long memory_bm_get_current(struct memory_bitmap *bm) { return bm->cur.cur_pfn; } static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn) { void *addr; unsigned int bit; int error; error = memory_bm_find_bit(bm, pfn, &addr, &bit); BUG_ON(error); return test_bit(bit, addr); } static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn) { void *addr; unsigned int bit; return !memory_bm_find_bit(bm, pfn, &addr, &bit); } /* * rtree_next_node - Jump to the next leaf node. * * Set the position to the beginning of the next node in the * memory bitmap. This is either the next node in the current * zone's radix tree or the first node in the radix tree of the * next zone. * * Return true if there is a next node, false otherwise. */ static bool rtree_next_node(struct memory_bitmap *bm) { if (!list_is_last(&bm->cur.node->list, &bm->cur.zone->leaves)) { bm->cur.node = list_entry(bm->cur.node->list.next, struct rtree_node, list); bm->cur.node_pfn += BM_BITS_PER_BLOCK; bm->cur.node_bit = 0; touch_softlockup_watchdog(); return true; } /* No more nodes, goto next zone */ if (!list_is_last(&bm->cur.zone->list, &bm->zones)) { bm->cur.zone = list_entry(bm->cur.zone->list.next, struct mem_zone_bm_rtree, list); bm->cur.node = list_entry(bm->cur.zone->leaves.next, struct rtree_node, list); bm->cur.node_pfn = 0; bm->cur.node_bit = 0; return true; } /* No more zones */ return false; } /** * memory_bm_next_pfn - Find the next set bit in a memory bitmap. * @bm: Memory bitmap. * * Starting from the last returned position this function searches for the next * set bit in @bm and returns the PFN represented by it. If no more bits are * set, BM_END_OF_MAP is returned. * * It is required to run memory_bm_position_reset() before the first call to * this function for the given memory bitmap. */ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) { unsigned long bits, pfn, pages; int bit; do { pages = bm->cur.zone->end_pfn - bm->cur.zone->start_pfn; bits = min(pages - bm->cur.node_pfn, BM_BITS_PER_BLOCK); bit = find_next_bit(bm->cur.node->data, bits, bm->cur.node_bit); if (bit < bits) { pfn = bm->cur.zone->start_pfn + bm->cur.node_pfn + bit; bm->cur.node_bit = bit + 1; bm->cur.cur_pfn = pfn; return pfn; } } while (rtree_next_node(bm)); bm->cur.cur_pfn = BM_END_OF_MAP; return BM_END_OF_MAP; } /* * This structure represents a range of page frames the contents of which * should not be saved during hibernation. */ struct nosave_region { struct list_head list; unsigned long start_pfn; unsigned long end_pfn; }; static LIST_HEAD(nosave_regions); static void recycle_zone_bm_rtree(struct mem_zone_bm_rtree *zone) { struct rtree_node *node; list_for_each_entry(node, &zone->nodes, list) recycle_safe_page(node->data); list_for_each_entry(node, &zone->leaves, list) recycle_safe_page(node->data); } static void memory_bm_recycle(struct memory_bitmap *bm) { struct mem_zone_bm_rtree *zone; struct linked_page *p_list; list_for_each_entry(zone, &bm->zones, list) recycle_zone_bm_rtree(zone); p_list = bm->p_list; while (p_list) { struct linked_page *lp = p_list; p_list = lp->next; recycle_safe_page(lp); } } /** * register_nosave_region - Register a region of unsaveable memory. * * Register a range of page frames the contents of which should not be saved * during hibernation (to be used in the early initialization code). */ void __init register_nosave_region(unsigned long start_pfn, unsigned long end_pfn) { struct nosave_region *region; if (start_pfn >= end_pfn) return; if (!list_empty(&nosave_regions)) { /* Try to extend the previous region (they should be sorted) */ region = list_entry(nosave_regions.prev, struct nosave_region, list); if (region->end_pfn == start_pfn) { region->end_pfn = end_pfn; goto Report; } } /* This allocation cannot fail */ region = memblock_alloc(sizeof(struct nosave_region), SMP_CACHE_BYTES); if (!region) panic("%s: Failed to allocate %zu bytes\n", __func__, sizeof(struct nosave_region)); region->start_pfn = start_pfn; region->end_pfn = end_pfn; list_add_tail(®ion->list, &nosave_regions); Report: pr_info("Registered nosave memory: [mem %#010llx-%#010llx]\n", (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1); } /* * Set bits in this map correspond to the page frames the contents of which * should not be saved during the suspend. */ static struct memory_bitmap *forbidden_pages_map; /* Set bits in this map correspond to free page frames. */ static struct memory_bitmap *free_pages_map; /* * Each page frame allocated for creating the image is marked by setting the * corresponding bits in forbidden_pages_map and free_pages_map simultaneously */ void swsusp_set_page_free(struct page *page) { if (free_pages_map) memory_bm_set_bit(free_pages_map, page_to_pfn(page)); } static int swsusp_page_is_free(struct page *page) { return free_pages_map ? memory_bm_test_bit(free_pages_map, page_to_pfn(page)) : 0; } void swsusp_unset_page_free(struct page *page) { if (free_pages_map) memory_bm_clear_bit(free_pages_map, page_to_pfn(page)); } static void swsusp_set_page_forbidden(struct page *page) { if (forbidden_pages_map) memory_bm_set_bit(forbidden_pages_map, page_to_pfn(page)); } int swsusp_page_is_forbidden(struct page *page) { return forbidden_pages_map ? memory_bm_test_bit(forbidden_pages_map, page_to_pfn(page)) : 0; } static void swsusp_unset_page_forbidden(struct page *page) { if (forbidden_pages_map) memory_bm_clear_bit(forbidden_pages_map, page_to_pfn(page)); } /** * mark_nosave_pages - Mark pages that should not be saved. * @bm: Memory bitmap. * * Set the bits in @bm that correspond to the page frames the contents of which * should not be saved. */ static void mark_nosave_pages(struct memory_bitmap *bm) { struct nosave_region *region; if (list_empty(&nosave_regions)) return; list_for_each_entry(region, &nosave_regions, list) { unsigned long pfn; pr_debug("Marking nosave pages: [mem %#010llx-%#010llx]\n", (unsigned long long) region->start_pfn << PAGE_SHIFT, ((unsigned long long) region->end_pfn << PAGE_SHIFT) - 1); for (pfn = region->start_pfn; pfn < region->end_pfn; pfn++) if (pfn_valid(pfn)) { /* * It is safe to ignore the result of * mem_bm_set_bit_check() here, since we won't * touch the PFNs for which the error is * returned anyway. */ mem_bm_set_bit_check(bm, pfn); } } } /** * create_basic_memory_bitmaps - Create bitmaps to hold basic page information. * * Create bitmaps needed for marking page frames that should not be saved and * free page frames. The forbidden_pages_map and free_pages_map pointers are * only modified if everything goes well, because we don't want the bits to be * touched before both bitmaps are set up. */ int create_basic_memory_bitmaps(void) { struct memory_bitmap *bm1, *bm2; int error = 0; if (forbidden_pages_map && free_pages_map) return 0; else BUG_ON(forbidden_pages_map || free_pages_map); bm1 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL); if (!bm1) return -ENOMEM; error = memory_bm_create(bm1, GFP_KERNEL, PG_ANY); if (error) goto Free_first_object; bm2 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL); if (!bm2) goto Free_first_bitmap; error = memory_bm_create(bm2, GFP_KERNEL, PG_ANY); if (error) goto Free_second_object; forbidden_pages_map = bm1; free_pages_map = bm2; mark_nosave_pages(forbidden_pages_map); pr_debug("Basic memory bitmaps created\n"); return 0; Free_second_object: kfree(bm2); Free_first_bitmap: memory_bm_free(bm1, PG_UNSAFE_CLEAR); Free_first_object: kfree(bm1); return -ENOMEM; } /** * free_basic_memory_bitmaps - Free memory bitmaps holding basic information. * * Free memory bitmaps allocated by create_basic_memory_bitmaps(). The * auxiliary pointers are necessary so that the bitmaps themselves are not * referred to while they are being freed. */ void free_basic_memory_bitmaps(void) { struct memory_bitmap *bm1, *bm2; if (WARN_ON(!(forbidden_pages_map && free_pages_map))) return; bm1 = forbidden_pages_map; bm2 = free_pages_map; forbidden_pages_map = NULL; free_pages_map = NULL; memory_bm_free(bm1, PG_UNSAFE_CLEAR); kfree(bm1); memory_bm_free(bm2, PG_UNSAFE_CLEAR); kfree(bm2); pr_debug("Basic memory bitmaps freed\n"); } static void clear_or_poison_free_page(struct page *page) { if (page_poisoning_enabled_static()) __kernel_poison_pages(page, 1); else if (want_init_on_free()) clear_highpage(page); } void clear_or_poison_free_pages(void) { struct memory_bitmap *bm = free_pages_map; unsigned long pfn; if (WARN_ON(!(free_pages_map))) return; if (page_poisoning_enabled() || want_init_on_free()) { memory_bm_position_reset(bm); pfn = memory_bm_next_pfn(bm); while (pfn != BM_END_OF_MAP) { if (pfn_valid(pfn)) clear_or_poison_free_page(pfn_to_page(pfn)); pfn = memory_bm_next_pfn(bm); } memory_bm_position_reset(bm); pr_info("free pages cleared after restore\n"); } } /** * snapshot_additional_pages - Estimate the number of extra pages needed. * @zone: Memory zone to carry out the computation for. * * Estimate the number of additional pages needed for setting up a hibernation * image data structures for @zone (usually, the returned value is greater than * the exact number). */ unsigned int snapshot_additional_pages(struct zone *zone) { unsigned int rtree, nodes; rtree = nodes = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK); rtree += DIV_ROUND_UP(rtree * sizeof(struct rtree_node), LINKED_PAGE_DATA_SIZE); while (nodes > 1) { nodes = DIV_ROUND_UP(nodes, BM_ENTRIES_PER_LEVEL); rtree += nodes; } return 2 * rtree; } /* * Touch the watchdog for every WD_PAGE_COUNT pages. */ #define WD_PAGE_COUNT (128*1024) static void mark_free_pages(struct zone *zone) { unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT; unsigned long flags; unsigned int order, t; struct page *page; if (zone_is_empty(zone)) return; spin_lock_irqsave(&zone->lock, flags); max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (pfn_valid(pfn)) { page = pfn_to_page(pfn); if (!--page_count) { touch_nmi_watchdog(); page_count = WD_PAGE_COUNT; } if (page_zone(page) != zone) continue; if (!swsusp_page_is_forbidden(page)) swsusp_unset_page_free(page); } for_each_migratetype_order(order, t) { list_for_each_entry(page, &zone->free_area[order].free_list[t], buddy_list) { unsigned long i; pfn = page_to_pfn(page); for (i = 0; i < (1UL << order); i++) { if (!--page_count) { touch_nmi_watchdog(); page_count = WD_PAGE_COUNT; } swsusp_set_page_free(pfn_to_page(pfn + i)); } } } spin_unlock_irqrestore(&zone->lock, flags); } #ifdef CONFIG_HIGHMEM /** * count_free_highmem_pages - Compute the total number of free highmem pages. * * The returned number is system-wide. */ static unsigned int count_free_highmem_pages(void) { struct zone *zone; unsigned int cnt = 0; for_each_populated_zone(zone) if (is_highmem(zone)) cnt += zone_page_state(zone, NR_FREE_PAGES); return cnt; } /** * saveable_highmem_page - Check if a highmem page is saveable. * * Determine whether a highmem page should be included in a hibernation image. * * We should save the page if it isn't Nosave or NosaveFree, or Reserved, * and it isn't part of a free chunk of pages. */ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) { struct page *page; if (!pfn_valid(pfn)) return NULL; page = pfn_to_online_page(pfn); if (!page || page_zone(page) != zone) return NULL; BUG_ON(!PageHighMem(page)); if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page)) return NULL; if (PageReserved(page) || PageOffline(page)) return NULL; if (page_is_guard(page)) return NULL; return page; } /** * count_highmem_pages - Compute the total number of saveable highmem pages. */ static unsigned int count_highmem_pages(void) { struct zone *zone; unsigned int n = 0; for_each_populated_zone(zone) { unsigned long pfn, max_zone_pfn; if (!is_highmem(zone)) continue; mark_free_pages(zone); max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (saveable_highmem_page(zone, pfn)) n++; } return n; } #else static inline void *saveable_highmem_page(struct zone *z, unsigned long p) { return NULL; } #endif /* CONFIG_HIGHMEM */ /** * saveable_page - Check if the given page is saveable. * * Determine whether a non-highmem page should be included in a hibernation * image. * * We should save the page if it isn't Nosave, and is not in the range * of pages statically defined as 'unsaveable', and it isn't part of * a free chunk of pages. */ static struct page *saveable_page(struct zone *zone, unsigned long pfn) { struct page *page; if (!pfn_valid(pfn)) return NULL; page = pfn_to_online_page(pfn); if (!page || page_zone(page) != zone) return NULL; BUG_ON(PageHighMem(page)); if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page)) return NULL; if (PageOffline(page)) return NULL; if (PageReserved(page) && (!kernel_page_present(page) || pfn_is_nosave(pfn))) return NULL; if (page_is_guard(page)) return NULL; return page; } /** * count_data_pages - Compute the total number of saveable non-highmem pages. */ static unsigned int count_data_pages(void) { struct zone *zone; unsigned long pfn, max_zone_pfn; unsigned int n = 0; for_each_populated_zone(zone) { if (is_highmem(zone)) continue; mark_free_pages(zone); max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (saveable_page(zone, pfn)) n++; } return n; } /* * This is needed, because copy_page and memcpy are not usable for copying * task structs. Returns true if the page was filled with only zeros, * otherwise false. */ static inline bool do_copy_page(long *dst, long *src) { long z = 0; int n; for (n = PAGE_SIZE / sizeof(long); n; n--) { z |= *src; *dst++ = *src++; } return !z; } /** * safe_copy_page - Copy a page in a safe way. * * Check if the page we are going to copy is marked as present in the kernel * page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or * CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present() * always returns 'true'. Returns true if the page was entirely composed of * zeros, otherwise it will return false. */ static bool safe_copy_page(void *dst, struct page *s_page) { bool zeros_only; if (kernel_page_present(s_page)) { zeros_only = do_copy_page(dst, page_address(s_page)); } else { hibernate_map_page(s_page); zeros_only = do_copy_page(dst, page_address(s_page)); hibernate_unmap_page(s_page); } return zeros_only; } #ifdef CONFIG_HIGHMEM static inline struct page *page_is_saveable(struct zone *zone, unsigned long pfn) { return is_highmem(zone) ? saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn); } static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) { struct page *s_page, *d_page; void *src, *dst; bool zeros_only; s_page = pfn_to_page(src_pfn); d_page = pfn_to_page(dst_pfn); if (PageHighMem(s_page)) { src = kmap_atomic(s_page); dst = kmap_atomic(d_page); zeros_only = do_copy_page(dst, src); kunmap_atomic(dst); kunmap_atomic(src); } else { if (PageHighMem(d_page)) { /* * The page pointed to by src may contain some kernel * data modified by kmap_atomic() */ zeros_only = safe_copy_page(buffer, s_page); dst = kmap_atomic(d_page); copy_page(dst, buffer); kunmap_atomic(dst); } else { zeros_only = safe_copy_page(page_address(d_page), s_page); } } return zeros_only; } #else #define page_is_saveable(zone, pfn) saveable_page(zone, pfn) static inline int copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) { return safe_copy_page(page_address(pfn_to_page(dst_pfn)), pfn_to_page(src_pfn)); } #endif /* CONFIG_HIGHMEM */ /* * Copy data pages will copy all pages into pages pulled from the copy_bm. * If a page was entirely filled with zeros it will be marked in the zero_bm. * * Returns the number of pages copied. */ static unsigned long copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm, struct memory_bitmap *zero_bm) { unsigned long copied_pages = 0; struct zone *zone; unsigned long pfn, copy_pfn; for_each_populated_zone(zone) { unsigned long max_zone_pfn; mark_free_pages(zone); max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (page_is_saveable(zone, pfn)) memory_bm_set_bit(orig_bm, pfn); } memory_bm_position_reset(orig_bm); memory_bm_position_reset(copy_bm); copy_pfn = memory_bm_next_pfn(copy_bm); for(;;) { pfn = memory_bm_next_pfn(orig_bm); if (unlikely(pfn == BM_END_OF_MAP)) break; if (copy_data_page(copy_pfn, pfn)) { memory_bm_set_bit(zero_bm, pfn); /* Use this copy_pfn for a page that is not full of zeros */ continue; } copied_pages++; copy_pfn = memory_bm_next_pfn(copy_bm); } return copied_pages; } /* Total number of image pages */ static unsigned int nr_copy_pages; /* Number of pages needed for saving the original pfns of the image pages */ static unsigned int nr_meta_pages; /* Number of zero pages */ static unsigned int nr_zero_pages; /* * Numbers of normal and highmem page frames allocated for hibernation image * before suspending devices. */ static unsigned int alloc_normal, alloc_highmem; /* * Memory bitmap used for marking saveable pages (during hibernation) or * hibernation image pages (during restore) */ static struct memory_bitmap orig_bm; /* * Memory bitmap used during hibernation for marking allocated page frames that * will contain copies of saveable pages. During restore it is initially used * for marking hibernation image pages, but then the set bits from it are * duplicated in @orig_bm and it is released. On highmem systems it is next * used for marking "safe" highmem pages, but it has to be reinitialized for * this purpose. */ static struct memory_bitmap copy_bm; /* Memory bitmap which tracks which saveable pages were zero filled. */ static struct memory_bitmap zero_bm; /** * swsusp_free - Free pages allocated for hibernation image. * * Image pages are allocated before snapshot creation, so they need to be * released after resume. */ void swsusp_free(void) { unsigned long fb_pfn, fr_pfn; if (!forbidden_pages_map || !free_pages_map) goto out; memory_bm_position_reset(forbidden_pages_map); memory_bm_position_reset(free_pages_map); loop: fr_pfn = memory_bm_next_pfn(free_pages_map); fb_pfn = memory_bm_next_pfn(forbidden_pages_map); /* * Find the next bit set in both bitmaps. This is guaranteed to * terminate when fb_pfn == fr_pfn == BM_END_OF_MAP. */ do { if (fb_pfn < fr_pfn) fb_pfn = memory_bm_next_pfn(forbidden_pages_map); if (fr_pfn < fb_pfn) fr_pfn = memory_bm_next_pfn(free_pages_map); } while (fb_pfn != fr_pfn); if (fr_pfn != BM_END_OF_MAP && pfn_valid(fr_pfn)) { struct page *page = pfn_to_page(fr_pfn); memory_bm_clear_current(forbidden_pages_map); memory_bm_clear_current(free_pages_map); hibernate_restore_unprotect_page(page_address(page)); __free_page(page); goto loop; } out: nr_copy_pages = 0; nr_meta_pages = 0; nr_zero_pages = 0; restore_pblist = NULL; buffer = NULL; alloc_normal = 0; alloc_highmem = 0; hibernate_restore_protection_end(); } /* Helper functions used for the shrinking of memory. */ #define GFP_IMAGE (GFP_KERNEL | __GFP_NOWARN) /** * preallocate_image_pages - Allocate a number of pages for hibernation image. * @nr_pages: Number of page frames to allocate. * @mask: GFP flags to use for the allocation. * * Return value: Number of page frames actually allocated */ static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask) { unsigned long nr_alloc = 0; while (nr_pages > 0) { struct page *page; page = alloc_image_page(mask); if (!page) break; memory_bm_set_bit(©_bm, page_to_pfn(page)); if (PageHighMem(page)) alloc_highmem++; else alloc_normal++; nr_pages--; nr_alloc++; } return nr_alloc; } static unsigned long preallocate_image_memory(unsigned long nr_pages, unsigned long avail_normal) { unsigned long alloc; if (avail_normal <= alloc_normal) return 0; alloc = avail_normal - alloc_normal; if (nr_pages < alloc) alloc = nr_pages; return preallocate_image_pages(alloc, GFP_IMAGE); } #ifdef CONFIG_HIGHMEM static unsigned long preallocate_image_highmem(unsigned long nr_pages) { return preallocate_image_pages(nr_pages, GFP_IMAGE | __GFP_HIGHMEM); } /** * __fraction - Compute (an approximation of) x * (multiplier / base). */ static unsigned long __fraction(u64 x, u64 multiplier, u64 base) { return div64_u64(x * multiplier, base); } static unsigned long preallocate_highmem_fraction(unsigned long nr_pages, unsigned long highmem, unsigned long total) { unsigned long alloc = __fraction(nr_pages, highmem, total); return preallocate_image_pages(alloc, GFP_IMAGE | __GFP_HIGHMEM); } #else /* CONFIG_HIGHMEM */ static inline unsigned long preallocate_image_highmem(unsigned long nr_pages) { return 0; } static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages, unsigned long highmem, unsigned long total) { return 0; } #endif /* CONFIG_HIGHMEM */ /** * free_unnecessary_pages - Release preallocated pages not needed for the image. */ static unsigned long free_unnecessary_pages(void) { unsigned long save, to_free_normal, to_free_highmem, free; save = count_data_pages(); if (alloc_normal >= save) { to_free_normal = alloc_normal - save; save = 0; } else { to_free_normal = 0; save -= alloc_normal; } save += count_highmem_pages(); if (alloc_highmem >= save) { to_free_highmem = alloc_highmem - save; } else { to_free_highmem = 0; save -= alloc_highmem; if (to_free_normal > save) to_free_normal -= save; else to_free_normal = 0; } free = to_free_normal + to_free_highmem; memory_bm_position_reset(©_bm); while (to_free_normal > 0 || to_free_highmem > 0) { unsigned long pfn = memory_bm_next_pfn(©_bm); struct page *page = pfn_to_page(pfn); if (PageHighMem(page)) { if (!to_free_highmem) continue; to_free_highmem--; alloc_highmem--; } else { if (!to_free_normal) continue; to_free_normal--; alloc_normal--; } memory_bm_clear_bit(©_bm, pfn); swsusp_unset_page_forbidden(page); swsusp_unset_page_free(page); __free_page(page); } return free; } /** * minimum_image_size - Estimate the minimum acceptable size of an image. * @saveable: Number of saveable pages in the system. * * We want to avoid attempting to free too much memory too hard, so estimate the * minimum acceptable size of a hibernation image to use as the lower limit for * preallocating memory. * * We assume that the minimum image size should be proportional to * * [number of saveable pages] - [number of pages that can be freed in theory] * * where the second term is the sum of (1) reclaimable slab pages, (2) active * and (3) inactive anonymous pages, (4) active and (5) inactive file pages. */ static unsigned long minimum_image_size(unsigned long saveable) { unsigned long size; size = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) + global_node_page_state(NR_ACTIVE_ANON) + global_node_page_state(NR_INACTIVE_ANON) + global_node_page_state(NR_ACTIVE_FILE) + global_node_page_state(NR_INACTIVE_FILE); return saveable <= size ? 0 : saveable - size; } /** * hibernate_preallocate_memory - Preallocate memory for hibernation image. * * To create a hibernation image it is necessary to make a copy of every page * frame in use. We also need a number of page frames to be free during * hibernation for allocations made while saving the image and for device * drivers, in case they need to allocate memory from their hibernation * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough * estimate) and reserved_size divided by PAGE_SIZE (which is tunable through * /sys/power/reserved_size, respectively). To make this happen, we compute the * total number of available page frames and allocate at least * * ([page frames total] - PAGES_FOR_IO - [metadata pages]) / 2 * - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE) * * of them, which corresponds to the maximum size of a hibernation image. * * If image_size is set below the number following from the above formula, * the preallocation of memory is continued until the total number of saveable * pages in the system is below the requested image size or the minimum * acceptable image size returned by minimum_image_size(), whichever is greater. */ int hibernate_preallocate_memory(void) { struct zone *zone; unsigned long saveable, size, max_size, count, highmem, pages = 0; unsigned long alloc, save_highmem, pages_highmem, avail_normal; ktime_t start, stop; int error; pr_info("Preallocating image memory\n"); start = ktime_get(); error = memory_bm_create(&orig_bm, GFP_IMAGE, PG_ANY); if (error) { pr_err("Cannot allocate original bitmap\n"); goto err_out; } error = memory_bm_create(©_bm, GFP_IMAGE, PG_ANY); if (error) { pr_err("Cannot allocate copy bitmap\n"); goto err_out; } error = memory_bm_create(&zero_bm, GFP_IMAGE, PG_ANY); if (error) { pr_err("Cannot allocate zero bitmap\n"); goto err_out; } alloc_normal = 0; alloc_highmem = 0; nr_zero_pages = 0; /* Count the number of saveable data pages. */ save_highmem = count_highmem_pages(); saveable = count_data_pages(); /* * Compute the total number of page frames we can use (count) and the * number of pages needed for image metadata (size). */ count = saveable; saveable += save_highmem; highmem = save_highmem; size = 0; for_each_populated_zone(zone) { size += snapshot_additional_pages(zone); if (is_highmem(zone)) highmem += zone_page_state(zone, NR_FREE_PAGES); else count += zone_page_state(zone, NR_FREE_PAGES); } avail_normal = count; count += highmem; count -= totalreserve_pages; /* Compute the maximum number of saveable pages to leave in memory. */ max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE); /* Compute the desired number of image pages specified by image_size. */ size = DIV_ROUND_UP(image_size, PAGE_SIZE); if (size > max_size) size = max_size; /* * If the desired number of image pages is at least as large as the * current number of saveable pages in memory, allocate page frames for * the image and we're done. */ if (size >= saveable) { pages = preallocate_image_highmem(save_highmem); pages += preallocate_image_memory(saveable - pages, avail_normal); goto out; } /* Estimate the minimum size of the image. */ pages = minimum_image_size(saveable); /* * To avoid excessive pressure on the normal zone, leave room in it to * accommodate an image of the minimum size (unless it's already too * small, in which case don't preallocate pages from it at all). */ if (avail_normal > pages) avail_normal -= pages; else avail_normal = 0; if (size < pages) size = min_t(unsigned long, pages, max_size); /* * Let the memory management subsystem know that we're going to need a * large number of page frames to allocate and make it free some memory. * NOTE: If this is not done, performance will be hurt badly in some * test cases. */ shrink_all_memory(saveable - size); /* * The number of saveable pages in memory was too high, so apply some * pressure to decrease it. First, make room for the largest possible * image and fail if that doesn't work. Next, try to decrease the size * of the image as much as indicated by 'size' using allocations from * highmem and non-highmem zones separately. */ pages_highmem = preallocate_image_highmem(highmem / 2); alloc = count - max_size; if (alloc > pages_highmem) alloc -= pages_highmem; else alloc = 0; pages = preallocate_image_memory(alloc, avail_normal); if (pages < alloc) { /* We have exhausted non-highmem pages, try highmem. */ alloc -= pages; pages += pages_highmem; pages_highmem = preallocate_image_highmem(alloc); if (pages_highmem < alloc) { pr_err("Image allocation is %lu pages short\n", alloc - pages_highmem); goto err_out; } pages += pages_highmem; /* * size is the desired number of saveable pages to leave in * memory, so try to preallocate (all memory - size) pages. */ alloc = (count - pages) - size; pages += preallocate_image_highmem(alloc); } else { /* * There are approximately max_size saveable pages at this point * and we want to reduce this number down to size. */ alloc = max_size - size; size = preallocate_highmem_fraction(alloc, highmem, count); pages_highmem += size; alloc -= size; size = preallocate_image_memory(alloc, avail_normal); pages_highmem += preallocate_image_highmem(alloc - size); pages += pages_highmem + size; } /* * We only need as many page frames for the image as there are saveable * pages in memory, but we have allocated more. Release the excessive * ones now. */ pages -= free_unnecessary_pages(); out: stop = ktime_get(); pr_info("Allocated %lu pages for snapshot\n", pages); swsusp_show_speed(start, stop, pages, "Allocated"); return 0; err_out: swsusp_free(); return -ENOMEM; } #ifdef CONFIG_HIGHMEM /** * count_pages_for_highmem - Count non-highmem pages needed for copying highmem. * * Compute the number of non-highmem pages that will be necessary for creating * copies of highmem pages. */ static unsigned int count_pages_for_highmem(unsigned int nr_highmem) { unsigned int free_highmem = count_free_highmem_pages() + alloc_highmem; if (free_highmem >= nr_highmem) nr_highmem = 0; else nr_highmem -= free_highmem; return nr_highmem; } #else static unsigned int count_pages_for_highmem(unsigned int nr_highmem) { return 0; } #endif /* CONFIG_HIGHMEM */ /** * enough_free_mem - Check if there is enough free memory for the image. */ static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem) { struct zone *zone; unsigned int free = alloc_normal; for_each_populated_zone(zone) if (!is_highmem(zone)) free += zone_page_state(zone, NR_FREE_PAGES); nr_pages += count_pages_for_highmem(nr_highmem); pr_debug("Normal pages needed: %u + %u, available pages: %u\n", nr_pages, PAGES_FOR_IO, free); return free > nr_pages + PAGES_FOR_IO; } #ifdef CONFIG_HIGHMEM /** * get_highmem_buffer - Allocate a buffer for highmem pages. * * If there are some highmem pages in the hibernation image, we may need a * buffer to copy them and/or load their data. */ static inline int get_highmem_buffer(int safe_needed) { buffer = get_image_page(GFP_ATOMIC, safe_needed); return buffer ? 0 : -ENOMEM; } /** * alloc_highmem_pages - Allocate some highmem pages for the image. * * Try to allocate as many pages as needed, but if the number of free highmem * pages is less than that, allocate them all. */ static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem) { unsigned int to_alloc = count_free_highmem_pages(); if (to_alloc > nr_highmem) to_alloc = nr_highmem; nr_highmem -= to_alloc; while (to_alloc-- > 0) { struct page *page; page = alloc_image_page(__GFP_HIGHMEM|__GFP_KSWAPD_RECLAIM); memory_bm_set_bit(bm, page_to_pfn(page)); } return nr_highmem; } #else static inline int get_highmem_buffer(int safe_needed) { return 0; } static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm, unsigned int n) { return 0; } #endif /* CONFIG_HIGHMEM */ /** * swsusp_alloc - Allocate memory for hibernation image. * * We first try to allocate as many highmem pages as there are * saveable highmem pages in the system. If that fails, we allocate * non-highmem pages for the copies of the remaining highmem ones. * * In this approach it is likely that the copies of highmem pages will * also be located in the high memory, because of the way in which * copy_data_pages() works. */ static int swsusp_alloc(struct memory_bitmap *copy_bm, unsigned int nr_pages, unsigned int nr_highmem) { if (nr_highmem > 0) { if (get_highmem_buffer(PG_ANY)) goto err_out; if (nr_highmem > alloc_highmem) { nr_highmem -= alloc_highmem; nr_pages += alloc_highmem_pages(copy_bm, nr_highmem); } } if (nr_pages > alloc_normal) { nr_pages -= alloc_normal; while (nr_pages-- > 0) { struct page *page; page = alloc_image_page(GFP_ATOMIC); if (!page) goto err_out; memory_bm_set_bit(copy_bm, page_to_pfn(page)); } } return 0; err_out: swsusp_free(); return -ENOMEM; } asmlinkage __visible int swsusp_save(void) { unsigned int nr_pages, nr_highmem; pr_info("Creating image:\n"); drain_local_pages(NULL); nr_pages = count_data_pages(); nr_highmem = count_highmem_pages(); pr_info("Need to copy %u pages\n", nr_pages + nr_highmem); if (!enough_free_mem(nr_pages, nr_highmem)) { pr_err("Not enough free memory\n"); return -ENOMEM; } if (swsusp_alloc(©_bm, nr_pages, nr_highmem)) { pr_err("Memory allocation failed\n"); return -ENOMEM; } /* * During allocating of suspend pagedir, new cold pages may appear. * Kill them. */ drain_local_pages(NULL); nr_copy_pages = copy_data_pages(©_bm, &orig_bm, &zero_bm); /* * End of critical section. From now on, we can write to memory, * but we should not touch disk. This specially means we must _not_ * touch swap space! Except we must write out our image of course. */ nr_pages += nr_highmem; /* We don't actually copy the zero pages */ nr_zero_pages = nr_pages - nr_copy_pages; nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE); pr_info("Image created (%d pages copied, %d zero pages)\n", nr_copy_pages, nr_zero_pages); return 0; } #ifndef CONFIG_ARCH_HIBERNATION_HEADER static int init_header_complete(struct swsusp_info *info) { memcpy(&info->uts, init_utsname(), sizeof(struct new_utsname)); info->version_code = LINUX_VERSION_CODE; return 0; } static const char *check_image_kernel(struct swsusp_info *info) { if (info->version_code != LINUX_VERSION_CODE) return "kernel version"; if (strcmp(info->uts.sysname,init_utsname()->sysname)) return "system type"; if (strcmp(info->uts.release,init_utsname()->release)) return "kernel release"; if (strcmp(info->uts.version,init_utsname()->version)) return "version"; if (strcmp(info->uts.machine,init_utsname()->machine)) return "machine"; return NULL; } #endif /* CONFIG_ARCH_HIBERNATION_HEADER */ unsigned long snapshot_get_image_size(void) { return nr_copy_pages + nr_meta_pages + 1; } static int init_header(struct swsusp_info *info) { memset(info, 0, sizeof(struct swsusp_info)); info->num_physpages = get_num_physpages(); info->image_pages = nr_copy_pages; info->pages = snapshot_get_image_size(); info->size = info->pages; info->size <<= PAGE_SHIFT; return init_header_complete(info); } #define ENCODED_PFN_ZERO_FLAG ((unsigned long)1 << (BITS_PER_LONG - 1)) #define ENCODED_PFN_MASK (~ENCODED_PFN_ZERO_FLAG) /** * pack_pfns - Prepare PFNs for saving. * @bm: Memory bitmap. * @buf: Memory buffer to store the PFNs in. * @zero_bm: Memory bitmap containing PFNs of zero pages. * * PFNs corresponding to set bits in @bm are stored in the area of memory * pointed to by @buf (1 page at a time). Pages which were filled with only * zeros will have the highest bit set in the packed format to distinguish * them from PFNs which will be contained in the image file. */ static inline void pack_pfns(unsigned long *buf, struct memory_bitmap *bm, struct memory_bitmap *zero_bm) { int j; for (j = 0; j < PAGE_SIZE / sizeof(long); j++) { buf[j] = memory_bm_next_pfn(bm); if (unlikely(buf[j] == BM_END_OF_MAP)) break; if (memory_bm_test_bit(zero_bm, buf[j])) buf[j] |= ENCODED_PFN_ZERO_FLAG; } } /** * snapshot_read_next - Get the address to read the next image page from. * @handle: Snapshot handle to be used for the reading. * * On the first call, @handle should point to a zeroed snapshot_handle * structure. The structure gets populated then and a pointer to it should be * passed to this function every next time. * * On success, the function returns a positive number. Then, the caller * is allowed to read up to the returned number of bytes from the memory * location computed by the data_of() macro. * * The function returns 0 to indicate the end of the data stream condition, * and negative numbers are returned on errors. If that happens, the structure * pointed to by @handle is not updated and should not be used any more. */ int snapshot_read_next(struct snapshot_handle *handle) { if (handle->cur > nr_meta_pages + nr_copy_pages) return 0; if (!buffer) { /* This makes the buffer be freed by swsusp_free() */ buffer = get_image_page(GFP_ATOMIC, PG_ANY); if (!buffer) return -ENOMEM; } if (!handle->cur) { int error; error = init_header((struct swsusp_info *)buffer); if (error) return error; handle->buffer = buffer; memory_bm_position_reset(&orig_bm); memory_bm_position_reset(©_bm); } else if (handle->cur <= nr_meta_pages) { clear_page(buffer); pack_pfns(buffer, &orig_bm, &zero_bm); } else { struct page *page; page = pfn_to_page(memory_bm_next_pfn(©_bm)); if (PageHighMem(page)) { /* * Highmem pages are copied to the buffer, * because we can't return with a kmapped * highmem page (we may not be called again). */ void *kaddr; kaddr = kmap_atomic(page); copy_page(buffer, kaddr); kunmap_atomic(kaddr); handle->buffer = buffer; } else { handle->buffer = page_address(page); } } handle->cur++; return PAGE_SIZE; } static void duplicate_memory_bitmap(struct memory_bitmap *dst, struct memory_bitmap *src) { unsigned long pfn; memory_bm_position_reset(src); pfn = memory_bm_next_pfn(src); while (pfn != BM_END_OF_MAP) { memory_bm_set_bit(dst, pfn); pfn = memory_bm_next_pfn(src); } } /** * mark_unsafe_pages - Mark pages that were used before hibernation. * * Mark the pages that cannot be used for storing the image during restoration, * because they conflict with the pages that had been used before hibernation. */ static void mark_unsafe_pages(struct memory_bitmap *bm) { unsigned long pfn; /* Clear the "free"/"unsafe" bit for all PFNs */ memory_bm_position_reset(free_pages_map); pfn = memory_bm_next_pfn(free_pages_map); while (pfn != BM_END_OF_MAP) { memory_bm_clear_current(free_pages_map); pfn = memory_bm_next_pfn(free_pages_map); } /* Mark pages that correspond to the "original" PFNs as "unsafe" */ duplicate_memory_bitmap(free_pages_map, bm); allocated_unsafe_pages = 0; } static int check_header(struct swsusp_info *info) { const char *reason; reason = check_image_kernel(info); if (!reason && info->num_physpages != get_num_physpages()) reason = "memory size"; if (reason) { pr_err("Image mismatch: %s\n", reason); return -EPERM; } return 0; } /** * load_header - Check the image header and copy the data from it. */ static int load_header(struct swsusp_info *info) { int error; restore_pblist = NULL; error = check_header(info); if (!error) { nr_copy_pages = info->image_pages; nr_meta_pages = info->pages - info->image_pages - 1; } return error; } /** * unpack_orig_pfns - Set bits corresponding to given PFNs in a memory bitmap. * @bm: Memory bitmap. * @buf: Area of memory containing the PFNs. * @zero_bm: Memory bitmap with the zero PFNs marked. * * For each element of the array pointed to by @buf (1 page at a time), set the * corresponding bit in @bm. If the page was originally populated with only * zeros then a corresponding bit will also be set in @zero_bm. */ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm, struct memory_bitmap *zero_bm) { unsigned long decoded_pfn; bool zero; int j; for (j = 0; j < PAGE_SIZE / sizeof(long); j++) { if (unlikely(buf[j] == BM_END_OF_MAP)) break; zero = !!(buf[j] & ENCODED_PFN_ZERO_FLAG); decoded_pfn = buf[j] & ENCODED_PFN_MASK; if (pfn_valid(decoded_pfn) && memory_bm_pfn_present(bm, decoded_pfn)) { memory_bm_set_bit(bm, decoded_pfn); if (zero) { memory_bm_set_bit(zero_bm, decoded_pfn); nr_zero_pages++; } } else { if (!pfn_valid(decoded_pfn)) pr_err(FW_BUG "Memory map mismatch at 0x%llx after hibernation\n", (unsigned long long)PFN_PHYS(decoded_pfn)); return -EFAULT; } } return 0; } #ifdef CONFIG_HIGHMEM /* * struct highmem_pbe is used for creating the list of highmem pages that * should be restored atomically during the resume from disk, because the page * frames they have occupied before the suspend are in use. */ struct highmem_pbe { struct page *copy_page; /* data is here now */ struct page *orig_page; /* data was here before the suspend */ struct highmem_pbe *next; }; /* * List of highmem PBEs needed for restoring the highmem pages that were * allocated before the suspend and included in the suspend image, but have * also been allocated by the "resume" kernel, so their contents cannot be * written directly to their "original" page frames. */ static struct highmem_pbe *highmem_pblist; /** * count_highmem_image_pages - Compute the number of highmem pages in the image. * @bm: Memory bitmap. * * The bits in @bm that correspond to image pages are assumed to be set. */ static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) { unsigned long pfn; unsigned int cnt = 0; memory_bm_position_reset(bm); pfn = memory_bm_next_pfn(bm); while (pfn != BM_END_OF_MAP) { if (PageHighMem(pfn_to_page(pfn))) cnt++; pfn = memory_bm_next_pfn(bm); } return cnt; } static unsigned int safe_highmem_pages; static struct memory_bitmap *safe_highmem_bm; /** * prepare_highmem_image - Allocate memory for loading highmem data from image. * @bm: Pointer to an uninitialized memory bitmap structure. * @nr_highmem_p: Pointer to the number of highmem image pages. * * Try to allocate as many highmem pages as there are highmem image pages * (@nr_highmem_p points to the variable containing the number of highmem image * pages). The pages that are "safe" (ie. will not be overwritten when the * hibernation image is restored entirely) have the corresponding bits set in * @bm (it must be uninitialized). * * NOTE: This function should not be called if there are no highmem image pages. */ static int prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) { unsigned int to_alloc; if (memory_bm_create(bm, GFP_ATOMIC, PG_SAFE)) return -ENOMEM; if (get_highmem_buffer(PG_SAFE)) return -ENOMEM; to_alloc = count_free_highmem_pages(); if (to_alloc > *nr_highmem_p) to_alloc = *nr_highmem_p; else *nr_highmem_p = to_alloc; safe_highmem_pages = 0; while (to_alloc-- > 0) { struct page *page; page = alloc_page(__GFP_HIGHMEM); if (!swsusp_page_is_free(page)) { /* The page is "safe", set its bit the bitmap */ memory_bm_set_bit(bm, page_to_pfn(page)); safe_highmem_pages++; } /* Mark the page as allocated */ swsusp_set_page_forbidden(page); swsusp_set_page_free(page); } memory_bm_position_reset(bm); safe_highmem_bm = bm; return 0; } static struct page *last_highmem_page; /** * get_highmem_page_buffer - Prepare a buffer to store a highmem image page. * * For a given highmem image page get a buffer that suspend_write_next() should * return to its caller to write to. * * If the page is to be saved to its "original" page frame or a copy of * the page is to be made in the highmem, @buffer is returned. Otherwise, * the copy of the page is to be made in normal memory, so the address of * the copy is returned. * * If @buffer is returned, the caller of suspend_write_next() will write * the page's contents to @buffer, so they will have to be copied to the * right location on the next call to suspend_write_next() and it is done * with the help of copy_last_highmem_page(). For this purpose, if * @buffer is returned, @last_highmem_page is set to the page to which * the data will have to be copied from @buffer. */ static void *get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) { struct highmem_pbe *pbe; void *kaddr; if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) { /* * We have allocated the "original" page frame and we can * use it directly to store the loaded page. */ last_highmem_page = page; return buffer; } /* * The "original" page frame has not been allocated and we have to * use a "safe" page frame to store the loaded page. */ pbe = chain_alloc(ca, sizeof(struct highmem_pbe)); if (!pbe) { swsusp_free(); return ERR_PTR(-ENOMEM); } pbe->orig_page = page; if (safe_highmem_pages > 0) { struct page *tmp; /* Copy of the page will be stored in high memory */ kaddr = buffer; tmp = pfn_to_page(memory_bm_next_pfn(safe_highmem_bm)); safe_highmem_pages--; last_highmem_page = tmp; pbe->copy_page = tmp; } else { /* Copy of the page will be stored in normal memory */ kaddr = __get_safe_page(ca->gfp_mask); if (!kaddr) return ERR_PTR(-ENOMEM); pbe->copy_page = virt_to_page(kaddr); } pbe->next = highmem_pblist; highmem_pblist = pbe; return kaddr; } /** * copy_last_highmem_page - Copy most the most recent highmem image page. * * Copy the contents of a highmem image from @buffer, where the caller of * snapshot_write_next() has stored them, to the right location represented by * @last_highmem_page . */ static void copy_last_highmem_page(void) { if (last_highmem_page) { void *dst; dst = kmap_atomic(last_highmem_page); copy_page(dst, buffer); kunmap_atomic(dst); last_highmem_page = NULL; } } static inline int last_highmem_page_copied(void) { return !last_highmem_page; } static inline void free_highmem_data(void) { if (safe_highmem_bm) memory_bm_free(safe_highmem_bm, PG_UNSAFE_CLEAR); if (buffer) free_image_page(buffer, PG_UNSAFE_CLEAR); } #else static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) { return 0; } static inline int prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) { return 0; } static inline void *get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) { return ERR_PTR(-EINVAL); } static inline void copy_last_highmem_page(void) {} static inline int last_highmem_page_copied(void) { return 1; } static inline void free_highmem_data(void) {} #endif /* CONFIG_HIGHMEM */ #define PBES_PER_LINKED_PAGE (LINKED_PAGE_DATA_SIZE / sizeof(struct pbe)) /** * prepare_image - Make room for loading hibernation image. * @new_bm: Uninitialized memory bitmap structure. * @bm: Memory bitmap with unsafe pages marked. * @zero_bm: Memory bitmap containing the zero pages. * * Use @bm to mark the pages that will be overwritten in the process of * restoring the system memory state from the suspend image ("unsafe" pages) * and allocate memory for the image. * * The idea is to allocate a new memory bitmap first and then allocate * as many pages as needed for image data, but without specifying what those * pages will be used for just yet. Instead, we mark them all as allocated and * create a lists of "safe" pages to be used later. On systems with high * memory a list of "safe" highmem pages is created too. * * Because it was not known which pages were unsafe when @zero_bm was created, * make a copy of it and recreate it within safe pages. */ static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm, struct memory_bitmap *zero_bm) { unsigned int nr_pages, nr_highmem; struct memory_bitmap tmp; struct linked_page *lp; int error; /* If there is no highmem, the buffer will not be necessary */ free_image_page(buffer, PG_UNSAFE_CLEAR); buffer = NULL; nr_highmem = count_highmem_image_pages(bm); mark_unsafe_pages(bm); error = memory_bm_create(new_bm, GFP_ATOMIC, PG_SAFE); if (error) goto Free; duplicate_memory_bitmap(new_bm, bm); memory_bm_free(bm, PG_UNSAFE_KEEP); /* Make a copy of zero_bm so it can be created in safe pages */ error = memory_bm_create(&tmp, GFP_ATOMIC, PG_SAFE); if (error) goto Free; duplicate_memory_bitmap(&tmp, zero_bm); memory_bm_free(zero_bm, PG_UNSAFE_KEEP); /* Recreate zero_bm in safe pages */ error = memory_bm_create(zero_bm, GFP_ATOMIC, PG_SAFE); if (error) goto Free; duplicate_memory_bitmap(zero_bm, &tmp); memory_bm_free(&tmp, PG_UNSAFE_CLEAR); /* At this point zero_bm is in safe pages and it can be used for restoring. */ if (nr_highmem > 0) { error = prepare_highmem_image(bm, &nr_highmem); if (error) goto Free; } /* * Reserve some safe pages for potential later use. * * NOTE: This way we make sure there will be enough safe pages for the * chain_alloc() in get_buffer(). It is a bit wasteful, but * nr_copy_pages cannot be greater than 50% of the memory anyway. * * nr_copy_pages cannot be less than allocated_unsafe_pages too. */ nr_pages = (nr_zero_pages + nr_copy_pages) - nr_highmem - allocated_unsafe_pages; nr_pages = DIV_ROUND_UP(nr_pages, PBES_PER_LINKED_PAGE); while (nr_pages > 0) { lp = get_image_page(GFP_ATOMIC, PG_SAFE); if (!lp) { error = -ENOMEM; goto Free; } lp->next = safe_pages_list; safe_pages_list = lp; nr_pages--; } /* Preallocate memory for the image */ nr_pages = (nr_zero_pages + nr_copy_pages) - nr_highmem - allocated_unsafe_pages; while (nr_pages > 0) { lp = (struct linked_page *)get_zeroed_page(GFP_ATOMIC); if (!lp) { error = -ENOMEM; goto Free; } if (!swsusp_page_is_free(virt_to_page(lp))) { /* The page is "safe", add it to the list */ lp->next = safe_pages_list; safe_pages_list = lp; } /* Mark the page as allocated */ swsusp_set_page_forbidden(virt_to_page(lp)); swsusp_set_page_free(virt_to_page(lp)); nr_pages--; } return 0; Free: swsusp_free(); return error; } /** * get_buffer - Get the address to store the next image data page. * * Get the address that snapshot_write_next() should return to its caller to * write to. */ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) { struct pbe *pbe; struct page *page; unsigned long pfn = memory_bm_next_pfn(bm); if (pfn == BM_END_OF_MAP) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); if (PageHighMem(page)) return get_highmem_page_buffer(page, ca); if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) /* * We have allocated the "original" page frame and we can * use it directly to store the loaded page. */ return page_address(page); /* * The "original" page frame has not been allocated and we have to * use a "safe" page frame to store the loaded page. */ pbe = chain_alloc(ca, sizeof(struct pbe)); if (!pbe) { swsusp_free(); return ERR_PTR(-ENOMEM); } pbe->orig_address = page_address(page); pbe->address = __get_safe_page(ca->gfp_mask); if (!pbe->address) return ERR_PTR(-ENOMEM); pbe->next = restore_pblist; restore_pblist = pbe; return pbe->address; } /** * snapshot_write_next - Get the address to store the next image page. * @handle: Snapshot handle structure to guide the writing. * * On the first call, @handle should point to a zeroed snapshot_handle * structure. The structure gets populated then and a pointer to it should be * passed to this function every next time. * * On success, the function returns a positive number. Then, the caller * is allowed to write up to the returned number of bytes to the memory * location computed by the data_of() macro. * * The function returns 0 to indicate the "end of file" condition. Negative * numbers are returned on errors, in which cases the structure pointed to by * @handle is not updated and should not be used any more. */ int snapshot_write_next(struct snapshot_handle *handle) { static struct chain_allocator ca; int error = 0; next: /* Check if we have already loaded the entire image */ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages + nr_zero_pages) return 0; if (!handle->cur) { if (!buffer) /* This makes the buffer be freed by swsusp_free() */ buffer = get_image_page(GFP_ATOMIC, PG_ANY); if (!buffer) return -ENOMEM; handle->buffer = buffer; } else if (handle->cur == 1) { error = load_header(buffer); if (error) return error; safe_pages_list = NULL; error = memory_bm_create(©_bm, GFP_ATOMIC, PG_ANY); if (error) return error; error = memory_bm_create(&zero_bm, GFP_ATOMIC, PG_ANY); if (error) return error; nr_zero_pages = 0; hibernate_restore_protection_begin(); } else if (handle->cur <= nr_meta_pages + 1) { error = unpack_orig_pfns(buffer, ©_bm, &zero_bm); if (error) return error; if (handle->cur == nr_meta_pages + 1) { error = prepare_image(&orig_bm, ©_bm, &zero_bm); if (error) return error; chain_init(&ca, GFP_ATOMIC, PG_SAFE); memory_bm_position_reset(&orig_bm); memory_bm_position_reset(&zero_bm); restore_pblist = NULL; handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); } } else { copy_last_highmem_page(); hibernate_restore_protect_page(handle->buffer); handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); } handle->sync_read = (handle->buffer == buffer); handle->cur++; /* Zero pages were not included in the image, memset it and move on. */ if (handle->cur > nr_meta_pages + 1 && memory_bm_test_bit(&zero_bm, memory_bm_get_current(&orig_bm))) { memset(handle->buffer, 0, PAGE_SIZE); goto next; } return PAGE_SIZE; } /** * snapshot_write_finalize - Complete the loading of a hibernation image. * * Must be called after the last call to snapshot_write_next() in case the last * page in the image happens to be a highmem page and its contents should be * stored in highmem. Additionally, it recycles bitmap memory that's not * necessary any more. */ void snapshot_write_finalize(struct snapshot_handle *handle) { copy_last_highmem_page(); hibernate_restore_protect_page(handle->buffer); /* Do that only if we have loaded the image entirely */ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages + nr_zero_pages) { memory_bm_recycle(&orig_bm); free_highmem_data(); } } int snapshot_image_loaded(struct snapshot_handle *handle) { return !(!nr_copy_pages || !last_highmem_page_copied() || handle->cur <= nr_meta_pages + nr_copy_pages + nr_zero_pages); } #ifdef CONFIG_HIGHMEM /* Assumes that @buf is ready and points to a "safe" page */ static inline void swap_two_pages_data(struct page *p1, struct page *p2, void *buf) { void *kaddr1, *kaddr2; kaddr1 = kmap_atomic(p1); kaddr2 = kmap_atomic(p2); copy_page(buf, kaddr1); copy_page(kaddr1, kaddr2); copy_page(kaddr2, buf); kunmap_atomic(kaddr2); kunmap_atomic(kaddr1); } /** * restore_highmem - Put highmem image pages into their original locations. * * For each highmem page that was in use before hibernation and is included in * the image, and also has been allocated by the "restore" kernel, swap its * current contents with the previous (ie. "before hibernation") ones. * * If the restore eventually fails, we can call this function once again and * restore the highmem state as seen by the restore kernel. */ int restore_highmem(void) { struct highmem_pbe *pbe = highmem_pblist; void *buf; if (!pbe) return 0; buf = get_image_page(GFP_ATOMIC, PG_SAFE); if (!buf) return -ENOMEM; while (pbe) { swap_two_pages_data(pbe->copy_page, pbe->orig_page, buf); pbe = pbe->next; } free_image_page(buf, PG_UNSAFE_CLEAR); return 0; } #endif /* CONFIG_HIGHMEM */ |
| 60 39 39 38 60 60 60 39 39 39 39 39 285 285 11143 146 11144 11141 11115 11120 11118 11145 11144 11120 11144 8195 8198 8197 8151 8195 8200 8146 8200 11043 7693 630 5 629 10422 7338 368 8 368 3043 5372 3 3 3 3 3 3 2 2 2 8 8 3 3 3 3 2 2 8 1 1 1 1 1 1 2 2 4 3 1 1 4 22 22 22 156 158 2 19 17 17 2 8 1 7 7 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/highuid.h> #include <linux/cred.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/projid.h> #include <linux/fs_struct.h> #include <linux/bsearch.h> #include <linux/sort.h> static struct kmem_cache *user_ns_cachep __ro_after_init; static DEFINE_MUTEX(userns_state_mutex); static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *map); static void free_user_ns(struct work_struct *work); static struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid) { return inc_ucount(ns, uid, UCOUNT_USER_NAMESPACES); } static void dec_user_namespaces(struct ucounts *ucounts) { return dec_ucount(ucounts, UCOUNT_USER_NAMESPACES); } static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) { /* Start with the same capabilities as init but useless for doing * anything as the capabilities are bound to the new user namespace. */ cred->securebits = SECUREBITS_DEFAULT; cred->cap_inheritable = CAP_EMPTY_SET; cred->cap_permitted = CAP_FULL_SET; cred->cap_effective = CAP_FULL_SET; cred->cap_ambient = CAP_EMPTY_SET; cred->cap_bset = CAP_FULL_SET; #ifdef CONFIG_KEYS key_put(cred->request_key_auth); cred->request_key_auth = NULL; #endif /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ cred->user_ns = user_ns; } static unsigned long enforced_nproc_rlimit(void) { unsigned long limit = RLIM_INFINITY; /* Is RLIMIT_NPROC currently enforced? */ if (!uid_eq(current_uid(), GLOBAL_ROOT_UID) || (current_user_ns() != &init_user_ns)) limit = rlimit(RLIMIT_NPROC); return limit; } /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the * new namespace. * * This is called by copy_creds(), which will finish setting the target task's * credentials. */ int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; kuid_t owner = new->euid; kgid_t group = new->egid; struct ucounts *ucounts; int ret, i; ret = -ENOSPC; if (parent_ns->level > 32) goto fail; ucounts = inc_user_namespaces(parent_ns, owner); if (!ucounts) goto fail; /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, * by verifying that the root directory is at the root of the * mount namespace which allows all files to be accessed. */ ret = -EPERM; if (current_chrooted()) goto fail_dec; /* The creator needs a mapping in the parent user namespace * or else we won't be able to reasonably tell userspace who * created a user_namespace. */ ret = -EPERM; if (!kuid_has_mapping(parent_ns, owner) || !kgid_has_mapping(parent_ns, group)) goto fail_dec; ret = security_create_user_ns(new); if (ret < 0) goto fail_dec; ret = -ENOMEM; ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL); if (!ns) goto fail_dec; ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP); ret = ns_alloc_inum(&ns->ns); if (ret) goto fail_free; ns->ns.ops = &userns_operations; refcount_set(&ns->ns.count, 1); /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; ns->level = parent_ns->level + 1; ns->owner = owner; ns->group = group; INIT_WORK(&ns->work, free_user_ns); for (i = 0; i < UCOUNT_COUNTS; i++) { ns->ucount_max[i] = INT_MAX; } set_userns_rlimit_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit()); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE)); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING)); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK)); ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ mutex_lock(&userns_state_mutex); ns->flags = parent_ns->flags; mutex_unlock(&userns_state_mutex); #ifdef CONFIG_KEYS INIT_LIST_HEAD(&ns->keyring_name_list); init_rwsem(&ns->keyring_sem); #endif ret = -ENOMEM; if (!setup_userns_sysctls(ns)) goto fail_keyring; set_cred_user_ns(new, ns); return 0; fail_keyring: #ifdef CONFIG_PERSISTENT_KEYRINGS key_put(ns->persistent_keyring_register); #endif ns_free_inum(&ns->ns); fail_free: kmem_cache_free(user_ns_cachep, ns); fail_dec: dec_user_namespaces(ucounts); fail: return ret; } int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { struct cred *cred; int err = -ENOMEM; if (!(unshare_flags & CLONE_NEWUSER)) return 0; cred = prepare_creds(); if (cred) { err = create_user_ns(cred); if (err) put_cred(cred); else *new_cred = cred; } return err; } static void free_user_ns(struct work_struct *work) { struct user_namespace *parent, *ns = container_of(work, struct user_namespace, work); do { struct ucounts *ucounts = ns->ucounts; parent = ns->parent; if (ns->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->gid_map.forward); kfree(ns->gid_map.reverse); } if (ns->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->uid_map.forward); kfree(ns->uid_map.reverse); } if (ns->projid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->projid_map.forward); kfree(ns->projid_map.reverse); } #if IS_ENABLED(CONFIG_BINFMT_MISC) kfree(ns->binfmt_misc); #endif retire_userns_sysctls(ns); key_free_user_ns(ns); ns_free_inum(&ns->ns); kmem_cache_free(user_ns_cachep, ns); dec_user_namespaces(ucounts); ns = parent; } while (refcount_dec_and_test(&parent->ns.count)); } void __put_user_ns(struct user_namespace *ns) { schedule_work(&ns->work); } EXPORT_SYMBOL(__put_user_ns); /** * struct idmap_key - holds the information necessary to find an idmapping in a * sorted idmap array. It is passed to cmp_map_id() as first argument. */ struct idmap_key { bool map_up; /* true -> id from kid; false -> kid from id */ u32 id; /* id to find */ u32 count; /* == 0 unless used with map_id_range_down() */ }; /** * cmp_map_id - Function to be passed to bsearch() to find the requested * idmapping. Expects struct idmap_key to be passed via @k. */ static int cmp_map_id(const void *k, const void *e) { u32 first, last, id2; const struct idmap_key *key = k; const struct uid_gid_extent *el = e; id2 = key->id + key->count - 1; /* handle map_id_{down,up}() */ if (key->map_up) first = el->lower_first; else first = el->first; last = first + el->count - 1; if (key->id >= first && key->id <= last && (id2 >= first && id2 <= last)) return 0; if (key->id < first || id2 < first) return -1; return 1; } /** * map_id_range_down_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { struct idmap_key key; key.map_up = false; key.count = count; key.id = id; return bsearch(&key, map->forward, extents, sizeof(struct uid_gid_extent), cmp_map_id); } /** * map_id_range_down_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_base(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { unsigned idx; u32 first, last, id2; id2 = id + count - 1; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last && (id2 >= first && id2 <= last)) return &map->extent[idx]; } return NULL; } static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_range_down_base(extents, map, id, count); else extent = map_id_range_down_max(extents, map, id, count); /* Map the id or note failure */ if (extent) id = (id - extent->first) + extent->lower_first; else id = (u32) -1; return id; } static u32 map_id_down(struct uid_gid_map *map, u32 id) { return map_id_range_down(map, id, 1); } /** * map_id_up_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_base(unsigned extents, struct uid_gid_map *map, u32 id) { unsigned idx; u32 first, last; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].lower_first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last) return &map->extent[idx]; } return NULL; } /** * map_id_up_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id) { struct idmap_key key; key.map_up = true; key.count = 1; key.id = id; return bsearch(&key, map->reverse, extents, sizeof(struct uid_gid_extent), cmp_map_id); } static u32 map_id_up(struct uid_gid_map *map, u32 id) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_up_base(extents, map, id); else extent = map_id_up_max(extents, map, id); /* Map the id or note failure */ if (extent) id = (id - extent->lower_first) + extent->first; else id = (u32) -1; return id; } /** * make_kuid - Map a user-namespace uid pair into a kuid. * @ns: User namespace that the uid is in * @uid: User identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace uid * pair INVALID_UID is returned. Callers are expected to test * for and handle INVALID_UID being returned. INVALID_UID * may be tested for using uid_valid(). */ kuid_t make_kuid(struct user_namespace *ns, uid_t uid) { /* Map the uid to a global kernel uid */ return KUIDT_INIT(map_id_down(&ns->uid_map, uid)); } EXPORT_SYMBOL(make_kuid); /** * from_kuid - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * If @kuid has no mapping in @targ (uid_t)-1 is returned. */ uid_t from_kuid(struct user_namespace *targ, kuid_t kuid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->uid_map, __kuid_val(kuid)); } EXPORT_SYMBOL(from_kuid); /** * from_kuid_munged - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kuid from_kuid_munged never fails and always * returns a valid uid. This makes from_kuid_munged appropriate * for use in syscalls like stat and getuid where failing the * system call and failing to provide a valid uid are not an * options. * * If @kuid has no mapping in @targ overflowuid is returned. */ uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid) { uid_t uid; uid = from_kuid(targ, kuid); if (uid == (uid_t) -1) uid = overflowuid; return uid; } EXPORT_SYMBOL(from_kuid_munged); /** * make_kgid - Map a user-namespace gid pair into a kgid. * @ns: User namespace that the gid is in * @gid: group identifier * * Maps a user-namespace gid pair into a kernel internal kgid, * and returns that kgid. * * When there is no mapping defined for the user-namespace gid * pair INVALID_GID is returned. Callers are expected to test * for and handle INVALID_GID being returned. INVALID_GID may be * tested for using gid_valid(). */ kgid_t make_kgid(struct user_namespace *ns, gid_t gid) { /* Map the gid to a global kernel gid */ return KGIDT_INIT(map_id_down(&ns->gid_map, gid)); } EXPORT_SYMBOL(make_kgid); /** * from_kgid - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * If @kgid has no mapping in @targ (gid_t)-1 is returned. */ gid_t from_kgid(struct user_namespace *targ, kgid_t kgid) { /* Map the gid from a global kernel gid */ return map_id_up(&targ->gid_map, __kgid_val(kgid)); } EXPORT_SYMBOL(from_kgid); /** * from_kgid_munged - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kgid from_kgid_munged never fails and always * returns a valid gid. This makes from_kgid_munged appropriate * for use in syscalls like stat and getgid where failing the * system call and failing to provide a valid gid are not options. * * If @kgid has no mapping in @targ overflowgid is returned. */ gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid) { gid_t gid; gid = from_kgid(targ, kgid); if (gid == (gid_t) -1) gid = overflowgid; return gid; } EXPORT_SYMBOL(from_kgid_munged); /** * make_kprojid - Map a user-namespace projid pair into a kprojid. * @ns: User namespace that the projid is in * @projid: Project identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace projid * pair INVALID_PROJID is returned. Callers are expected to test * for and handle INVALID_PROJID being returned. INVALID_PROJID * may be tested for using projid_valid(). */ kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid) { /* Map the uid to a global kernel uid */ return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid)); } EXPORT_SYMBOL(make_kprojid); /** * from_kprojid - Create a projid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal project identifier to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * If @kprojid has no mapping in @targ (projid_t)-1 is returned. */ projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->projid_map, __kprojid_val(kprojid)); } EXPORT_SYMBOL(from_kprojid); /** * from_kprojid_munged - Create a projiid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal projid to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kprojid from_kprojid_munged never fails and always * returns a valid projid. This makes from_kprojid_munged * appropriate for use in syscalls like stat and where * failing the system call and failing to provide a valid projid are * not an options. * * If @kprojid has no mapping in @targ OVERFLOW_PROJID is returned. */ projid_t from_kprojid_munged(struct user_namespace *targ, kprojid_t kprojid) { projid_t projid; projid = from_kprojid(targ, kprojid); if (projid == (projid_t) -1) projid = OVERFLOW_PROJID; return projid; } EXPORT_SYMBOL(from_kprojid_munged); static int uid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; uid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int gid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; gid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int projid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; projid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map) { loff_t pos = *ppos; unsigned extents = map->nr_extents; smp_rmb(); if (pos >= extents) return NULL; if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return &map->extent[pos]; return &map->forward[pos]; } static void *uid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->uid_map); } static void *gid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->gid_map); } static void *projid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->projid_map); } static void *m_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; return seq->op->start(seq, pos); } static void m_stop(struct seq_file *seq, void *v) { return; } const struct seq_operations proc_uid_seq_operations = { .start = uid_m_start, .stop = m_stop, .next = m_next, .show = uid_m_show, }; const struct seq_operations proc_gid_seq_operations = { .start = gid_m_start, .stop = m_stop, .next = m_next, .show = gid_m_show, }; const struct seq_operations proc_projid_seq_operations = { .start = projid_m_start, .stop = m_stop, .next = m_next, .show = projid_m_show, }; static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent *extent) { u32 upper_first, lower_first, upper_last, lower_last; unsigned idx; upper_first = extent->first; lower_first = extent->lower_first; upper_last = upper_first + extent->count - 1; lower_last = lower_first + extent->count - 1; for (idx = 0; idx < new_map->nr_extents; idx++) { u32 prev_upper_first, prev_lower_first; u32 prev_upper_last, prev_lower_last; struct uid_gid_extent *prev; if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) prev = &new_map->extent[idx]; else prev = &new_map->forward[idx]; prev_upper_first = prev->first; prev_lower_first = prev->lower_first; prev_upper_last = prev_upper_first + prev->count - 1; prev_lower_last = prev_lower_first + prev->count - 1; /* Does the upper range intersect a previous extent? */ if ((prev_upper_first <= upper_last) && (prev_upper_last >= upper_first)) return true; /* Does the lower range intersect a previous extent? */ if ((prev_lower_first <= lower_last) && (prev_lower_last >= lower_first)) return true; } return false; } /** * insert_extent - Safely insert a new idmap extent into struct uid_gid_map. * Takes care to allocate a 4K block of memory if the number of mappings exceeds * UID_GID_MAP_MAX_BASE_EXTENTS. */ static int insert_extent(struct uid_gid_map *map, struct uid_gid_extent *extent) { struct uid_gid_extent *dest; if (map->nr_extents == UID_GID_MAP_MAX_BASE_EXTENTS) { struct uid_gid_extent *forward; /* Allocate memory for 340 mappings. */ forward = kmalloc_array(UID_GID_MAP_MAX_EXTENTS, sizeof(struct uid_gid_extent), GFP_KERNEL); if (!forward) return -ENOMEM; /* Copy over memory. Only set up memory for the forward pointer. * Defer the memory setup for the reverse pointer. */ memcpy(forward, map->extent, map->nr_extents * sizeof(map->extent[0])); map->forward = forward; map->reverse = NULL; } if (map->nr_extents < UID_GID_MAP_MAX_BASE_EXTENTS) dest = &map->extent[map->nr_extents]; else dest = &map->forward[map->nr_extents]; *dest = *extent; map->nr_extents++; return 0; } /* cmp function to sort() forward mappings */ static int cmp_extents_forward(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->first < e2->first) return -1; if (e1->first > e2->first) return 1; return 0; } /* cmp function to sort() reverse mappings */ static int cmp_extents_reverse(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->lower_first < e2->lower_first) return -1; if (e1->lower_first > e2->lower_first) return 1; return 0; } /** * sort_idmaps - Sorts an array of idmap entries. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static int sort_idmaps(struct uid_gid_map *map) { if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return 0; /* Sort forward array. */ sort(map->forward, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_forward, NULL); /* Only copy the memory from forward we actually need. */ map->reverse = kmemdup(map->forward, map->nr_extents * sizeof(struct uid_gid_extent), GFP_KERNEL); if (!map->reverse) return -ENOMEM; /* Sort reverse array. */ sort(map->reverse, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_reverse, NULL); return 0; } /** * verify_root_map() - check the uid 0 mapping * @file: idmapping file * @map_ns: user namespace of the target process * @new_map: requested idmap * * If a process requests mapping parent uid 0 into the new ns, verify that the * process writing the map had the CAP_SETFCAP capability as the target process * will be able to write fscaps that are valid in ancestor user namespaces. * * Return: true if the mapping is allowed, false if not. */ static bool verify_root_map(const struct file *file, struct user_namespace *map_ns, struct uid_gid_map *new_map) { int idx; const struct user_namespace *file_ns = file->f_cred->user_ns; struct uid_gid_extent *extent0 = NULL; for (idx = 0; idx < new_map->nr_extents; idx++) { if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent0 = &new_map->extent[idx]; else extent0 = &new_map->forward[idx]; if (extent0->lower_first == 0) break; extent0 = NULL; } if (!extent0) return true; if (map_ns == file_ns) { /* The process unshared its ns and is writing to its own * /proc/self/uid_map. User already has full capabilites in * the new namespace. Verify that the parent had CAP_SETFCAP * when it unshared. * */ if (!file_ns->parent_could_setfcap) return false; } else { /* Process p1 is writing to uid_map of p2, who is in a child * user namespace to p1's. Verify that the opener of the map * file has CAP_SETFCAP against the parent of the new map * namespace */ if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP)) return false; } return true; } static ssize_t map_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos, int cap_setid, struct uid_gid_map *map, struct uid_gid_map *parent_map) { struct seq_file *seq = file->private_data; struct user_namespace *map_ns = seq->private; struct uid_gid_map new_map; unsigned idx; struct uid_gid_extent extent; char *kbuf = NULL, *pos, *next_line; ssize_t ret; /* Only allow < page size writes at the beginning of the file */ if ((*ppos != 0) || (count >= PAGE_SIZE)) return -EINVAL; /* Slurp in the user data */ kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); /* * The userns_state_mutex serializes all writes to any given map. * * Any map is only ever written once. * * An id map fits within 1 cache line on most architectures. * * On read nothing needs to be done unless you are on an * architecture with a crazy cache coherency model like alpha. * * There is a one time data dependency between reading the * count of the extents and the values of the extents. The * desired behavior is to see the values of the extents that * were written before the count of the extents. * * To achieve this smp_wmb() is used on guarantee the write * order and smp_rmb() is guaranteed that we don't have crazy * architectures returning stale data. */ mutex_lock(&userns_state_mutex); memset(&new_map, 0, sizeof(struct uid_gid_map)); ret = -EPERM; /* Only allow one successful write to the map */ if (map->nr_extents != 0) goto out; /* * Adjusting namespace settings requires capabilities on the target. */ if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN)) goto out; /* Parse the user data */ ret = -EINVAL; pos = kbuf; for (; pos; pos = next_line) { /* Find the end of line and ensure I don't look past it */ next_line = strchr(pos, '\n'); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; } pos = skip_spaces(pos); extent.first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.lower_first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.count = simple_strtoul(pos, &pos, 10); if (*pos && !isspace(*pos)) goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; /* Verify we have been given valid starting values */ if ((extent.first == (u32) -1) || (extent.lower_first == (u32) -1)) goto out; /* Verify count is not zero and does not cause the * extent to wrap */ if ((extent.first + extent.count) <= extent.first) goto out; if ((extent.lower_first + extent.count) <= extent.lower_first) goto out; /* Do the ranges in extent overlap any previous extents? */ if (mappings_overlap(&new_map, &extent)) goto out; if ((new_map.nr_extents + 1) == UID_GID_MAP_MAX_EXTENTS && (next_line != NULL)) goto out; ret = insert_extent(&new_map, &extent); if (ret < 0) goto out; ret = -EINVAL; } /* Be very certain the new map actually exists */ if (new_map.nr_extents == 0) goto out; ret = -EPERM; /* Validate the user is allowed to use user id's mapped to. */ if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map)) goto out; ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. */ for (idx = 0; idx < new_map.nr_extents; idx++) { struct uid_gid_extent *e; u32 lower_first; if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) e = &new_map.extent[idx]; else e = &new_map.forward[idx]; lower_first = map_id_range_down(parent_map, e->lower_first, e->count); /* Fail if we can not map the specified extent to * the kernel global id space. */ if (lower_first == (u32) -1) goto out; e->lower_first = lower_first; } /* * If we want to use binary search for lookup, this clones the extent * array and sorts both copies. */ ret = sort_idmaps(&new_map); if (ret < 0) goto out; /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, new_map.nr_extents * sizeof(new_map.extent[0])); } else { map->forward = new_map.forward; map->reverse = new_map.reverse; } smp_wmb(); map->nr_extents = new_map.nr_extents; *ppos = count; ret = count; out: if (ret < 0 && new_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(new_map.forward); kfree(new_map.reverse); map->forward = NULL; map->reverse = NULL; map->nr_extents = 0; } mutex_unlock(&userns_state_mutex); kfree(kbuf); return ret; } ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETUID, &ns->uid_map, &ns->parent->uid_map); } ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETGID, &ns->gid_map, &ns->parent->gid_map); } ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; /* Anyone can set any valid project id no capability needed */ return map_write(file, buf, size, ppos, -1, &ns->projid_map, &ns->parent->projid_map); } static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { const struct cred *cred = file->f_cred; if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map)) return false; /* Don't allow mappings that would allow anything that wouldn't * be allowed without the establishment of unprivileged mappings. */ if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && uid_eq(ns->owner, cred->euid)) { u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); if (uid_eq(uid, cred->euid)) return true; } else if (cap_setid == CAP_SETGID) { kgid_t gid = make_kgid(ns->parent, id); if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && gid_eq(gid, cred->egid)) return true; } } /* Allow anyone to set a mapping that doesn't require privilege */ if (!cap_valid(cap_setid)) return true; /* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. * And the opener of the id file also has the appropriate capability. */ if (ns_capable(ns->parent, cap_setid) && file_ns_capable(file, ns->parent, cap_setid)) return true; return false; } int proc_setgroups_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; unsigned long userns_flags = READ_ONCE(ns->flags); seq_printf(seq, "%s\n", (userns_flags & USERNS_SETGROUPS_ALLOWED) ? "allow" : "deny"); return 0; } ssize_t proc_setgroups_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; char kbuf[8], *pos; bool setgroups_allowed; ssize_t ret; /* Only allow a very narrow range of strings to be written */ ret = -EINVAL; if ((*ppos != 0) || (count >= sizeof(kbuf))) goto out; /* What was written? */ ret = -EFAULT; if (copy_from_user(kbuf, buf, count)) goto out; kbuf[count] = '\0'; pos = kbuf; /* What is being requested? */ ret = -EINVAL; if (strncmp(pos, "allow", 5) == 0) { pos += 5; setgroups_allowed = true; } else if (strncmp(pos, "deny", 4) == 0) { pos += 4; setgroups_allowed = false; } else goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; ret = -EPERM; mutex_lock(&userns_state_mutex); if (setgroups_allowed) { /* Enabling setgroups after setgroups has been disabled * is not allowed. */ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED)) goto out_unlock; } else { /* Permanently disabling setgroups after setgroups has * been enabled by writing the gid_map is not allowed. */ if (ns->gid_map.nr_extents != 0) goto out_unlock; ns->flags &= ~USERNS_SETGROUPS_ALLOWED; } mutex_unlock(&userns_state_mutex); /* Report a successful write */ *ppos = count; ret = count; out: return ret; out_unlock: mutex_unlock(&userns_state_mutex); goto out; } bool userns_may_setgroups(const struct user_namespace *ns) { bool allowed; mutex_lock(&userns_state_mutex); /* It is not safe to use setgroups until a gid mapping in * the user namespace has been established. */ allowed = ns->gid_map.nr_extents != 0; /* Is setgroups allowed? */ allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); mutex_unlock(&userns_state_mutex); return allowed; } /* * Returns true if @child is the same namespace or a descendant of * @ancestor. */ bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { const struct user_namespace *ns; for (ns = child; ns->level > ancestor->level; ns = ns->parent) ; return (ns == ancestor); } bool current_in_userns(const struct user_namespace *target_ns) { return in_userns(target_ns, current_user_ns()); } EXPORT_SYMBOL(current_in_userns); static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); } static struct ns_common *userns_get(struct task_struct *task) { struct user_namespace *user_ns; rcu_read_lock(); user_ns = get_user_ns(__task_cred(task)->user_ns); rcu_read_unlock(); return user_ns ? &user_ns->ns : NULL; } static void userns_put(struct ns_common *ns) { put_user_ns(to_user_ns(ns)); } static int userns_install(struct nsset *nsset, struct ns_common *ns) { struct user_namespace *user_ns = to_user_ns(ns); struct cred *cred; /* Don't allow gaining capabilities by reentering * the same user namespace. */ if (user_ns == current_user_ns()) return -EINVAL; /* Tasks that share a thread group must share a user namespace */ if (!thread_group_empty(current)) return -EINVAL; if (current->fs->users != 1) return -EINVAL; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; cred = nsset_cred(nsset); if (!cred) return -EINVAL; put_user_ns(cred->user_ns); set_cred_user_ns(cred, get_user_ns(user_ns)); if (set_cred_ucounts(cred) < 0) return -EINVAL; return 0; } struct ns_common *ns_get_owner(struct ns_common *ns) { struct user_namespace *my_user_ns = current_user_ns(); struct user_namespace *owner, *p; /* See if the owner is in the current user namespace */ owner = p = ns->ops->owner(ns); for (;;) { if (!p) return ERR_PTR(-EPERM); if (p == my_user_ns) break; p = p->parent; } return &get_user_ns(owner)->ns; } static struct user_namespace *userns_owner(struct ns_common *ns) { return to_user_ns(ns)->parent; } const struct proc_ns_operations userns_operations = { .name = "user", .type = CLONE_NEWUSER, .get = userns_get, .put = userns_put, .install = userns_install, .owner = userns_owner, .get_parent = ns_get_owner, }; static __init int user_namespaces_init(void) { user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC | SLAB_ACCOUNT); return 0; } subsys_initcall(user_namespaces_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2001-2005 Edouard TISSERANT <edouard.tisserant@wanadoo.fr> * Copyright (c) 2004-2005 Stephane VOLTZ <svoltz@numericable.fr> * * USB Acecad "Acecad Flair" tablet support * * Changelog: * v3.2 - Added sysfs support */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/usb/input.h> MODULE_AUTHOR("Edouard TISSERANT <edouard.tisserant@wanadoo.fr>"); MODULE_DESCRIPTION("USB Acecad Flair tablet driver"); MODULE_LICENSE("GPL"); #define USB_VENDOR_ID_ACECAD 0x0460 #define USB_DEVICE_ID_FLAIR 0x0004 #define USB_DEVICE_ID_302 0x0008 struct usb_acecad { char name[128]; char phys[64]; struct usb_interface *intf; struct input_dev *input; struct urb *irq; unsigned char *data; dma_addr_t data_dma; }; static void usb_acecad_irq(struct urb *urb) { struct usb_acecad *acecad = urb->context; unsigned char *data = acecad->data; struct input_dev *dev = acecad->input; struct usb_interface *intf = acecad->intf; struct usb_device *udev = interface_to_usbdev(intf); int prox, status; switch (urb->status) { case 0: /* success */ break; case -ECONNRESET: case -ENOENT: case -ESHUTDOWN: /* this urb is terminated, clean up */ dev_dbg(&intf->dev, "%s - urb shutting down with status: %d\n", __func__, urb->status); return; default: dev_dbg(&intf->dev, "%s - nonzero urb status received: %d\n", __func__, urb->status); goto resubmit; } prox = (data[0] & 0x04) >> 2; input_report_key(dev, BTN_TOOL_PEN, prox); if (prox) { int x = data[1] | (data[2] << 8); int y = data[3] | (data[4] << 8); /* Pressure should compute the same way for flair and 302 */ int pressure = data[5] | (data[6] << 8); int touch = data[0] & 0x01; int stylus = (data[0] & 0x10) >> 4; int stylus2 = (data[0] & 0x20) >> 5; input_report_abs(dev, ABS_X, x); input_report_abs(dev, ABS_Y, y); input_report_abs(dev, ABS_PRESSURE, pressure); input_report_key(dev, BTN_TOUCH, touch); input_report_key(dev, BTN_STYLUS, stylus); input_report_key(dev, BTN_STYLUS2, stylus2); } /* event termination */ input_sync(dev); resubmit: status = usb_submit_urb(urb, GFP_ATOMIC); if (status) dev_err(&intf->dev, "can't resubmit intr, %s-%s/input0, status %d\n", udev->bus->bus_name, udev->devpath, status); } static int usb_acecad_open(struct input_dev *dev) { struct usb_acecad *acecad = input_get_drvdata(dev); acecad->irq->dev = interface_to_usbdev(acecad->intf); if (usb_submit_urb(acecad->irq, GFP_KERNEL)) return -EIO; return 0; } static void usb_acecad_close(struct input_dev *dev) { struct usb_acecad *acecad = input_get_drvdata(dev); usb_kill_urb(acecad->irq); } static int usb_acecad_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *dev = interface_to_usbdev(intf); struct usb_host_interface *interface = intf->cur_altsetting; struct usb_endpoint_descriptor *endpoint; struct usb_acecad *acecad; struct input_dev *input_dev; int pipe, maxp; int err; if (interface->desc.bNumEndpoints != 1) return -ENODEV; endpoint = &interface->endpoint[0].desc; if (!usb_endpoint_is_int_in(endpoint)) return -ENODEV; pipe = usb_rcvintpipe(dev, endpoint->bEndpointAddress); maxp = usb_maxpacket(dev, pipe); acecad = kzalloc(sizeof(struct usb_acecad), GFP_KERNEL); input_dev = input_allocate_device(); if (!acecad || !input_dev) { err = -ENOMEM; goto fail1; } acecad->data = usb_alloc_coherent(dev, 8, GFP_KERNEL, &acecad->data_dma); if (!acecad->data) { err= -ENOMEM; goto fail1; } acecad->irq = usb_alloc_urb(0, GFP_KERNEL); if (!acecad->irq) { err = -ENOMEM; goto fail2; } acecad->intf = intf; acecad->input = input_dev; if (dev->manufacturer) strscpy(acecad->name, dev->manufacturer, sizeof(acecad->name)); if (dev->product) { if (dev->manufacturer) strlcat(acecad->name, " ", sizeof(acecad->name)); strlcat(acecad->name, dev->product, sizeof(acecad->name)); } usb_make_path(dev, acecad->phys, sizeof(acecad->phys)); strlcat(acecad->phys, "/input0", sizeof(acecad->phys)); input_dev->name = acecad->name; input_dev->phys = acecad->phys; usb_to_input_id(dev, &input_dev->id); input_dev->dev.parent = &intf->dev; input_set_drvdata(input_dev, acecad); input_dev->open = usb_acecad_open; input_dev->close = usb_acecad_close; input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS); input_dev->keybit[BIT_WORD(BTN_DIGI)] = BIT_MASK(BTN_TOOL_PEN) | BIT_MASK(BTN_TOUCH) | BIT_MASK(BTN_STYLUS) | BIT_MASK(BTN_STYLUS2); switch (id->driver_info) { case 0: input_set_abs_params(input_dev, ABS_X, 0, 5000, 4, 0); input_set_abs_params(input_dev, ABS_Y, 0, 3750, 4, 0); input_set_abs_params(input_dev, ABS_PRESSURE, 0, 512, 0, 0); if (!strlen(acecad->name)) snprintf(acecad->name, sizeof(acecad->name), "USB Acecad Flair Tablet %04x:%04x", le16_to_cpu(dev->descriptor.idVendor), le16_to_cpu(dev->descriptor.idProduct)); break; case 1: input_set_abs_params(input_dev, ABS_X, 0, 53000, 4, 0); input_set_abs_params(input_dev, ABS_Y, 0, 2250, 4, 0); input_set_abs_params(input_dev, ABS_PRESSURE, 0, 1024, 0, 0); if (!strlen(acecad->name)) snprintf(acecad->name, sizeof(acecad->name), "USB Acecad 302 Tablet %04x:%04x", le16_to_cpu(dev->descriptor.idVendor), le16_to_cpu(dev->descriptor.idProduct)); break; } usb_fill_int_urb(acecad->irq, dev, pipe, acecad->data, maxp > 8 ? 8 : maxp, usb_acecad_irq, acecad, endpoint->bInterval); acecad->irq->transfer_dma = acecad->data_dma; acecad->irq->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; err = input_register_device(acecad->input); if (err) goto fail3; usb_set_intfdata(intf, acecad); return 0; fail3: usb_free_urb(acecad->irq); fail2: usb_free_coherent(dev, 8, acecad->data, acecad->data_dma); fail1: input_free_device(input_dev); kfree(acecad); return err; } static void usb_acecad_disconnect(struct usb_interface *intf) { struct usb_acecad *acecad = usb_get_intfdata(intf); struct usb_device *udev = interface_to_usbdev(intf); usb_set_intfdata(intf, NULL); input_unregister_device(acecad->input); usb_free_urb(acecad->irq); usb_free_coherent(udev, 8, acecad->data, acecad->data_dma); kfree(acecad); } static const struct usb_device_id usb_acecad_id_table[] = { { USB_DEVICE(USB_VENDOR_ID_ACECAD, USB_DEVICE_ID_FLAIR), .driver_info = 0 }, { USB_DEVICE(USB_VENDOR_ID_ACECAD, USB_DEVICE_ID_302), .driver_info = 1 }, { } }; MODULE_DEVICE_TABLE(usb, usb_acecad_id_table); static struct usb_driver usb_acecad_driver = { .name = "usb_acecad", .probe = usb_acecad_probe, .disconnect = usb_acecad_disconnect, .id_table = usb_acecad_id_table, }; module_usb_driver(usb_acecad_driver); |
| 88 24 94 16 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015-2017 Intel Deutschland GmbH * Copyright(c) 2020-2023 Intel Corporation */ #ifndef STA_INFO_H #define STA_INFO_H #include <linux/list.h> #include <linux/types.h> #include <linux/if_ether.h> #include <linux/workqueue.h> #include <linux/average.h> #include <linux/bitfield.h> #include <linux/etherdevice.h> #include <linux/rhashtable.h> #include <linux/u64_stats_sync.h> #include "key.h" /** * enum ieee80211_sta_info_flags - Stations flags * * These flags are used with &struct sta_info's @flags member, but * only indirectly with set_sta_flag() and friends. * * @WLAN_STA_AUTH: Station is authenticated. * @WLAN_STA_ASSOC: Station is associated. * @WLAN_STA_PS_STA: Station is in power-save mode * @WLAN_STA_AUTHORIZED: Station is authorized to send/receive traffic. * This bit is always checked so needs to be enabled for all stations * when virtual port control is not in use. * @WLAN_STA_SHORT_PREAMBLE: Station is capable of receiving short-preamble * frames. * @WLAN_STA_WDS: Station is one of our WDS peers. * @WLAN_STA_CLEAR_PS_FILT: Clear PS filter in hardware (using the * IEEE80211_TX_CTL_CLEAR_PS_FILT control flag) when the next * frame to this station is transmitted. * @WLAN_STA_MFP: Management frame protection is used with this STA. * @WLAN_STA_BLOCK_BA: Used to deny ADDBA requests (both TX and RX) * during suspend/resume and station removal. * @WLAN_STA_PS_DRIVER: driver requires keeping this station in * power-save mode logically to flush frames that might still * be in the queues * @WLAN_STA_PSPOLL: Station sent PS-poll while driver was keeping * station in power-save mode, reply when the driver unblocks. * @WLAN_STA_TDLS_PEER: Station is a TDLS peer. * @WLAN_STA_TDLS_PEER_AUTH: This TDLS peer is authorized to send direct * packets. This means the link is enabled. * @WLAN_STA_TDLS_INITIATOR: We are the initiator of the TDLS link with this * station. * @WLAN_STA_TDLS_CHAN_SWITCH: This TDLS peer supports TDLS channel-switching * @WLAN_STA_TDLS_OFF_CHANNEL: The local STA is currently off-channel with this * TDLS peer * @WLAN_STA_TDLS_WIDER_BW: This TDLS peer supports working on a wider bw on * the BSS base channel. * @WLAN_STA_UAPSD: Station requested unscheduled SP while driver was * keeping station in power-save mode, reply when the driver * unblocks the station. * @WLAN_STA_SP: Station is in a service period, so don't try to * reply to other uAPSD trigger frames or PS-Poll. * @WLAN_STA_4ADDR_EVENT: 4-addr event was already sent for this frame. * @WLAN_STA_INSERTED: This station is inserted into the hash table. * @WLAN_STA_RATE_CONTROL: rate control was initialized for this station. * @WLAN_STA_TOFFSET_KNOWN: toffset calculated for this station is valid. * @WLAN_STA_MPSP_OWNER: local STA is owner of a mesh Peer Service Period. * @WLAN_STA_MPSP_RECIPIENT: local STA is recipient of a MPSP. * @WLAN_STA_PS_DELIVER: station woke up, but we're still blocking TX * until pending frames are delivered * @WLAN_STA_USES_ENCRYPTION: This station was configured for encryption, * so drop all packets without a key later. * @WLAN_STA_DECAP_OFFLOAD: This station uses rx decap offload * * @NUM_WLAN_STA_FLAGS: number of defined flags */ enum ieee80211_sta_info_flags { WLAN_STA_AUTH, WLAN_STA_ASSOC, WLAN_STA_PS_STA, WLAN_STA_AUTHORIZED, WLAN_STA_SHORT_PREAMBLE, WLAN_STA_WDS, WLAN_STA_CLEAR_PS_FILT, WLAN_STA_MFP, WLAN_STA_BLOCK_BA, WLAN_STA_PS_DRIVER, WLAN_STA_PSPOLL, WLAN_STA_TDLS_PEER, WLAN_STA_TDLS_PEER_AUTH, WLAN_STA_TDLS_INITIATOR, WLAN_STA_TDLS_CHAN_SWITCH, WLAN_STA_TDLS_OFF_CHANNEL, WLAN_STA_TDLS_WIDER_BW, WLAN_STA_UAPSD, WLAN_STA_SP, WLAN_STA_4ADDR_EVENT, WLAN_STA_INSERTED, WLAN_STA_RATE_CONTROL, WLAN_STA_TOFFSET_KNOWN, WLAN_STA_MPSP_OWNER, WLAN_STA_MPSP_RECIPIENT, WLAN_STA_PS_DELIVER, WLAN_STA_USES_ENCRYPTION, WLAN_STA_DECAP_OFFLOAD, NUM_WLAN_STA_FLAGS, }; #define ADDBA_RESP_INTERVAL HZ #define HT_AGG_MAX_RETRIES 15 #define HT_AGG_BURST_RETRIES 3 #define HT_AGG_RETRIES_PERIOD (15 * HZ) #define HT_AGG_STATE_DRV_READY 0 #define HT_AGG_STATE_RESPONSE_RECEIVED 1 #define HT_AGG_STATE_OPERATIONAL 2 #define HT_AGG_STATE_STOPPING 3 #define HT_AGG_STATE_WANT_START 4 #define HT_AGG_STATE_WANT_STOP 5 #define HT_AGG_STATE_START_CB 6 #define HT_AGG_STATE_STOP_CB 7 #define HT_AGG_STATE_SENT_ADDBA 8 DECLARE_EWMA(avg_signal, 10, 8) enum ieee80211_agg_stop_reason { AGG_STOP_DECLINED, AGG_STOP_LOCAL_REQUEST, AGG_STOP_PEER_REQUEST, AGG_STOP_DESTROY_STA, }; /* Debugfs flags to enable/disable use of RX/TX airtime in scheduler */ #define AIRTIME_USE_TX BIT(0) #define AIRTIME_USE_RX BIT(1) struct airtime_info { u64 rx_airtime; u64 tx_airtime; u32 last_active; s32 deficit; atomic_t aql_tx_pending; /* Estimated airtime for frames pending */ u32 aql_limit_low; u32 aql_limit_high; }; void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, struct sta_info *sta, u8 ac, u16 tx_airtime, bool tx_completed); struct sta_info; /** * struct tid_ampdu_tx - TID aggregation information (Tx). * * @rcu_head: rcu head for freeing structure * @session_timer: check if we keep Tx-ing on the TID (by timeout value) * @addba_resp_timer: timer for peer's response to addba request * @pending: pending frames queue -- use sta's spinlock to protect * @sta: station we are attached to * @dialog_token: dialog token for aggregation session * @timeout: session timeout value to be filled in ADDBA requests * @tid: TID number * @state: session state (see above) * @last_tx: jiffies of last tx activity * @stop_initiator: initiator of a session stop * @tx_stop: TX DelBA frame when stopping * @buf_size: reorder buffer size at receiver * @failed_bar_ssn: ssn of the last failed BAR tx attempt * @bar_pending: BAR needs to be re-sent * @amsdu: support A-MSDU withing A-MDPU * @ssn: starting sequence number of the session * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. * * The TX path can access it under RCU lock-free if, and * only if, the state has the flag %HT_AGG_STATE_OPERATIONAL * set. Otherwise, the TX path must also acquire the spinlock * and re-check the state, see comments in the tx code * touching it. */ struct tid_ampdu_tx { struct rcu_head rcu_head; struct timer_list session_timer; struct timer_list addba_resp_timer; struct sk_buff_head pending; struct sta_info *sta; unsigned long state; unsigned long last_tx; u16 timeout; u8 dialog_token; u8 stop_initiator; bool tx_stop; u16 buf_size; u16 ssn; u16 failed_bar_ssn; bool bar_pending; bool amsdu; u8 tid; }; /** * struct tid_ampdu_rx - TID aggregation information (Rx). * * @reorder_buf: buffer to reorder incoming aggregated MPDUs. An MPDU may be an * A-MSDU with individually reported subframes. * @reorder_buf_filtered: bitmap indicating where there are filtered frames in * the reorder buffer that should be ignored when releasing frames * @reorder_time: jiffies when skb was added * @session_timer: check if peer keeps Tx-ing on the TID (by timeout value) * @reorder_timer: releases expired frames from the reorder buffer. * @sta: station we are attached to * @last_rx: jiffies of last rx activity * @head_seq_num: head sequence number in reordering buffer. * @stored_mpdu_num: number of MPDUs in reordering buffer * @ssn: Starting Sequence Number expected to be aggregated. * @buf_size: buffer size for incoming A-MPDUs * @timeout: reset timer value (in TUs). * @tid: TID number * @rcu_head: RCU head used for freeing this struct * @reorder_lock: serializes access to reorder buffer, see below. * @auto_seq: used for offloaded BA sessions to automatically pick head_seq_and * and ssn. * @removed: this session is removed (but might have been found due to RCU) * @started: this session has started (head ssn or higher was received) * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. * * The @reorder_lock is used to protect the members of this * struct, except for @timeout, @buf_size and @dialog_token, * which are constant across the lifetime of the struct (the * dialog token being used only for debugging). */ struct tid_ampdu_rx { struct rcu_head rcu_head; spinlock_t reorder_lock; u64 reorder_buf_filtered; struct sk_buff_head *reorder_buf; unsigned long *reorder_time; struct sta_info *sta; struct timer_list session_timer; struct timer_list reorder_timer; unsigned long last_rx; u16 head_seq_num; u16 stored_mpdu_num; u16 ssn; u16 buf_size; u16 timeout; u8 tid; u8 auto_seq:1, removed:1, started:1; }; /** * struct sta_ampdu_mlme - STA aggregation information. * * @tid_rx: aggregation info for Rx per TID -- RCU protected * @tid_rx_token: dialog tokens for valid aggregation sessions * @tid_rx_timer_expired: bitmap indicating on which TIDs the * RX timer expired until the work for it runs * @tid_rx_stop_requested: bitmap indicating which BA sessions per TID the * driver requested to close until the work for it runs * @tid_rx_manage_offl: bitmap indicating which BA sessions were requested * to be treated as started/stopped due to offloading * @agg_session_valid: bitmap indicating which TID has a rx BA session open on * @unexpected_agg: bitmap indicating which TID already sent a delBA due to * unexpected aggregation related frames outside a session * @work: work struct for starting/stopping aggregation * @tid_tx: aggregation info for Tx per TID * @tid_start_tx: sessions where start was requested, not just protected * by wiphy mutex but also sta->lock * @last_addba_req_time: timestamp of the last addBA request. * @addba_req_num: number of times addBA request has been sent. * @dialog_token_allocator: dialog token enumerator for each new session; */ struct sta_ampdu_mlme { /* rx */ struct tid_ampdu_rx __rcu *tid_rx[IEEE80211_NUM_TIDS]; u8 tid_rx_token[IEEE80211_NUM_TIDS]; unsigned long tid_rx_timer_expired[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; unsigned long tid_rx_stop_requested[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; unsigned long tid_rx_manage_offl[BITS_TO_LONGS(2 * IEEE80211_NUM_TIDS)]; unsigned long agg_session_valid[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; unsigned long unexpected_agg[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; /* tx */ struct wiphy_work work; struct tid_ampdu_tx __rcu *tid_tx[IEEE80211_NUM_TIDS]; struct tid_ampdu_tx *tid_start_tx[IEEE80211_NUM_TIDS]; unsigned long last_addba_req_time[IEEE80211_NUM_TIDS]; u8 addba_req_num[IEEE80211_NUM_TIDS]; u8 dialog_token_allocator; }; /* Value to indicate no TID reservation */ #define IEEE80211_TID_UNRESERVED 0xff #define IEEE80211_FAST_XMIT_MAX_IV 18 /** * struct ieee80211_fast_tx - TX fastpath information * @key: key to use for hw crypto * @hdr: the 802.11 header to put with the frame * @hdr_len: actual 802.11 header length * @sa_offs: offset of the SA * @da_offs: offset of the DA * @pn_offs: offset where to put PN for crypto (or 0 if not needed) * @band: band this will be transmitted on, for tx_info * @rcu_head: RCU head to free this struct * * This struct is small enough so that the common case (maximum crypto * header length of 8 like for CCMP/GCMP) fits into a single 64-byte * cache line. */ struct ieee80211_fast_tx { struct ieee80211_key *key; u8 hdr_len; u8 sa_offs, da_offs, pn_offs; u8 band; u8 hdr[30 + 2 + IEEE80211_FAST_XMIT_MAX_IV + sizeof(rfc1042_header)] __aligned(2); struct rcu_head rcu_head; }; /** * struct ieee80211_fast_rx - RX fastpath information * @dev: netdevice for reporting the SKB * @vif_type: (P2P-less) interface type of the original sdata (sdata->vif.type) * @vif_addr: interface address * @rfc1042_hdr: copy of the RFC 1042 SNAP header (to have in cache) * @control_port_protocol: control port protocol copied from sdata * @expected_ds_bits: from/to DS bits expected * @icv_len: length of the MIC if present * @key: bool indicating encryption is expected (key is set) * @internal_forward: forward froms internally on AP/VLAN type interfaces * @uses_rss: copy of USES_RSS hw flag * @da_offs: offset of the DA in the header (for header conversion) * @sa_offs: offset of the SA in the header (for header conversion) * @rcu_head: RCU head for freeing this structure */ struct ieee80211_fast_rx { struct net_device *dev; enum nl80211_iftype vif_type; u8 vif_addr[ETH_ALEN] __aligned(2); u8 rfc1042_hdr[6] __aligned(2); __be16 control_port_protocol; __le16 expected_ds_bits; u8 icv_len; u8 key:1, internal_forward:1, uses_rss:1; u8 da_offs, sa_offs; struct rcu_head rcu_head; }; /* we use only values in the range 0-100, so pick a large precision */ DECLARE_EWMA(mesh_fail_avg, 20, 8) DECLARE_EWMA(mesh_tx_rate_avg, 8, 16) /** * struct mesh_sta - mesh STA information * @plink_lock: serialize access to plink fields * @llid: Local link ID * @plid: Peer link ID * @aid: local aid supplied by peer * @reason: Cancel reason on PLINK_HOLDING state * @plink_retries: Retries in establishment * @plink_state: peer link state * @plink_timeout: timeout of peer link * @plink_timer: peer link watch timer * @plink_sta: peer link watch timer's sta_info * @t_offset: timing offset relative to this host * @t_offset_setpoint: reference timing offset of this sta to be used when * calculating clockdrift * @local_pm: local link-specific power save mode * @peer_pm: peer-specific power save mode towards local STA * @nonpeer_pm: STA power save mode towards non-peer neighbors * @processed_beacon: set to true after peer rates and capabilities are * processed * @connected_to_gate: true if mesh STA has a path to a mesh gate * @connected_to_as: true if mesh STA has a path to a authentication server * @fail_avg: moving percentage of failed MSDUs * @tx_rate_avg: moving average of tx bitrate */ struct mesh_sta { struct timer_list plink_timer; struct sta_info *plink_sta; s64 t_offset; s64 t_offset_setpoint; spinlock_t plink_lock; u16 llid; u16 plid; u16 aid; u16 reason; u8 plink_retries; bool processed_beacon; bool connected_to_gate; bool connected_to_as; enum nl80211_plink_state plink_state; u32 plink_timeout; /* mesh power save */ enum nl80211_mesh_power_mode local_pm; enum nl80211_mesh_power_mode peer_pm; enum nl80211_mesh_power_mode nonpeer_pm; /* moving percentage of failed MSDUs */ struct ewma_mesh_fail_avg fail_avg; /* moving average of tx bitrate */ struct ewma_mesh_tx_rate_avg tx_rate_avg; }; DECLARE_EWMA(signal, 10, 8) struct ieee80211_sta_rx_stats { unsigned long packets; unsigned long last_rx; unsigned long num_duplicates; unsigned long fragments; unsigned long dropped; int last_signal; u8 chains; s8 chain_signal_last[IEEE80211_MAX_CHAINS]; u32 last_rate; struct u64_stats_sync syncp; u64 bytes; u64 msdu[IEEE80211_NUM_TIDS + 1]; }; /* * IEEE 802.11-2016 (10.6 "Defragmentation") recommends support for "concurrent * reception of at least one MSDU per access category per associated STA" * on APs, or "at least one MSDU per access category" on other interface types. * * This limit can be increased by changing this define, at the cost of slower * frame reassembly and increased memory use while fragments are pending. */ #define IEEE80211_FRAGMENT_MAX 4 struct ieee80211_fragment_entry { struct sk_buff_head skb_list; unsigned long first_frag_time; u16 seq; u16 extra_len; u16 last_frag; u8 rx_queue; u8 check_sequential_pn:1, /* needed for CCMP/GCMP */ is_protected:1; u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ unsigned int key_color; }; struct ieee80211_fragment_cache { struct ieee80211_fragment_entry entries[IEEE80211_FRAGMENT_MAX]; unsigned int next; }; /* * The bandwidth threshold below which the per-station CoDel parameters will be * scaled to be more lenient (to prevent starvation of slow stations). This * value will be scaled by the number of active stations when it is being * applied. */ #define STA_SLOW_THRESHOLD 6000 /* 6 Mbps */ /** * struct link_sta_info - Link STA information * All link specific sta info are stored here for reference. This can be * a single entry for non-MLD STA or multiple entries for MLD STA * @addr: Link MAC address - Can be same as MLD STA mac address and is always * same for non-MLD STA. This is used as key for searching link STA * @link_id: Link ID uniquely identifying the link STA. This is 0 for non-MLD * and set to the corresponding vif LinkId for MLD STA * @link_hash_node: hash node for rhashtable * @sta: Points to the STA info * @gtk: group keys negotiated with this station, if any * @tx_stats: TX statistics * @tx_stats.packets: # of packets transmitted * @tx_stats.bytes: # of bytes in all packets transmitted * @tx_stats.last_rate: last TX rate * @tx_stats.msdu: # of transmitted MSDUs per TID * @rx_stats: RX statistics * @rx_stats_avg: averaged RX statistics * @rx_stats_avg.signal: averaged signal * @rx_stats_avg.chain_signal: averaged per-chain signal * @pcpu_rx_stats: per-CPU RX statistics, assigned only if the driver needs * this (by advertising the USES_RSS hw flag) * @status_stats: TX status statistics * @status_stats.filtered: # of filtered frames * @status_stats.retry_failed: # of frames that failed after retry * @status_stats.retry_count: # of retries attempted * @status_stats.lost_packets: # of lost packets * @status_stats.last_pkt_time: timestamp of last ACKed packet * @status_stats.msdu_retries: # of MSDU retries * @status_stats.msdu_failed: # of failed MSDUs * @status_stats.last_ack: last ack timestamp (jiffies) * @status_stats.last_ack_signal: last ACK signal * @status_stats.ack_signal_filled: last ACK signal validity * @status_stats.avg_ack_signal: average ACK signal * @cur_max_bandwidth: maximum bandwidth to use for TX to the station, * taken from HT/VHT capabilities or VHT operating mode notification * @debugfs_dir: debug filesystem directory dentry * @pub: public (driver visible) link STA data * TODO Move other link params from sta_info as required for MLD operation */ struct link_sta_info { u8 addr[ETH_ALEN]; u8 link_id; struct rhlist_head link_hash_node; struct sta_info *sta; struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + NUM_DEFAULT_BEACON_KEYS]; struct ieee80211_sta_rx_stats __percpu *pcpu_rx_stats; /* Updated from RX path only, no locking requirements */ struct ieee80211_sta_rx_stats rx_stats; struct { struct ewma_signal signal; struct ewma_signal chain_signal[IEEE80211_MAX_CHAINS]; } rx_stats_avg; /* Updated from TX status path only, no locking requirements */ struct { unsigned long filtered; unsigned long retry_failed, retry_count; unsigned int lost_packets; unsigned long last_pkt_time; u64 msdu_retries[IEEE80211_NUM_TIDS + 1]; u64 msdu_failed[IEEE80211_NUM_TIDS + 1]; unsigned long last_ack; s8 last_ack_signal; bool ack_signal_filled; struct ewma_avg_signal avg_ack_signal; } status_stats; /* Updated from TX path only, no locking requirements */ struct { u64 packets[IEEE80211_NUM_ACS]; u64 bytes[IEEE80211_NUM_ACS]; struct ieee80211_tx_rate last_rate; struct rate_info last_rate_info; u64 msdu[IEEE80211_NUM_TIDS + 1]; } tx_stats; enum ieee80211_sta_rx_bandwidth cur_max_bandwidth; #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *debugfs_dir; #endif struct ieee80211_link_sta *pub; }; /** * struct sta_info - STA information * * This structure collects information about a station that * mac80211 is communicating with. * * @list: global linked list entry * @free_list: list entry for keeping track of stations to free * @hash_node: hash node for rhashtable * @addr: station's MAC address - duplicated from public part to * let the hash table work with just a single cacheline * @local: pointer to the global information * @sdata: virtual interface this station belongs to * @ptk: peer keys negotiated with this station, if any * @ptk_idx: last installed peer key index * @rate_ctrl: rate control algorithm reference * @rate_ctrl_lock: spinlock used to protect rate control data * (data inside the algorithm, so serializes calls there) * @rate_ctrl_priv: rate control private per-STA pointer * @lock: used for locking all fields that require locking, see comments * in the header file. * @drv_deliver_wk: used for delivering frames after driver PS unblocking * @listen_interval: listen interval of this station, when we're acting as AP * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly * @ps_lock: used for powersave (when mac80211 is the AP) related locking * @ps_tx_buf: buffers (per AC) of frames to transmit to this station * when it leaves power saving state or polls * @tx_filtered: buffers (per AC) of frames we already tried to * transmit but were filtered by hardware due to STA having * entered power saving state, these are also delivered to * the station when it leaves powersave or polls for frames * @driver_buffered_tids: bitmap of TIDs the driver has data buffered on * @txq_buffered_tids: bitmap of TIDs that mac80211 has txq data buffered on * @assoc_at: clock boottime (in ns) of last association * @last_connected: time (in seconds) when a station got connected * @last_seq_ctrl: last received seq/frag number from this STA (per TID * plus one for non-QoS frames) * @tid_seq: per-TID sequence numbers for sending to this STA * @airtime: per-AC struct airtime_info describing airtime statistics for this * station * @airtime_weight: station weight for airtime fairness calculation purposes * @ampdu_mlme: A-MPDU state machine state * @mesh: mesh STA information * @debugfs_dir: debug filesystem directory dentry * @dead: set to true when sta is unlinked * @removed: set to true when sta is being removed from sta_list * @uploaded: set to true when sta is uploaded to the driver * @sta: station information we share with the driver * @sta_state: duplicates information about station state (for debug) * @rcu_head: RCU head used for freeing this station struct * @cparams: CoDel parameters for this station. * @reserved_tid: reserved TID (if any, otherwise IEEE80211_TID_UNRESERVED) * @amsdu_mesh_control: track the mesh A-MSDU format used by the peer: * * * -1: not yet known * * 0: non-mesh A-MSDU length field * * 1: big-endian mesh A-MSDU length field * * 2: little-endian mesh A-MSDU length field * * @fast_tx: TX fastpath information * @fast_rx: RX fastpath information * @tdls_chandef: a TDLS peer can have a wider chandef that is compatible to * the BSS one. * @frags: fragment cache * @cur: storage for aggregation data * &struct ieee80211_sta points either here or to deflink.agg. * @deflink: This is the default link STA information, for non MLO STA all link * specific STA information is accessed through @deflink or through * link[0] which points to address of @deflink. For MLO Link STA * the first added link STA will point to deflink. * @link: reference to Link Sta entries. For Non MLO STA, except 1st link, * i.e link[0] all links would be assigned to NULL by default and * would access link information via @deflink or link[0]. For MLO * STA, first link STA being added will point its link pointer to * @deflink address and remaining would be allocated and the address * would be assigned to link[link_id] where link_id is the id assigned * by the AP. */ struct sta_info { /* General information, mostly static */ struct list_head list, free_list; struct rcu_head rcu_head; struct rhlist_head hash_node; u8 addr[ETH_ALEN]; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; struct ieee80211_key __rcu *ptk[NUM_DEFAULT_KEYS]; u8 ptk_idx; struct rate_control_ref *rate_ctrl; void *rate_ctrl_priv; spinlock_t rate_ctrl_lock; spinlock_t lock; struct ieee80211_fast_tx __rcu *fast_tx; struct ieee80211_fast_rx __rcu *fast_rx; #ifdef CONFIG_MAC80211_MESH struct mesh_sta *mesh; #endif struct work_struct drv_deliver_wk; u16 listen_interval; bool dead; bool removed; bool uploaded; enum ieee80211_sta_state sta_state; /* use the accessors defined below */ unsigned long _flags; /* STA powersave lock and frame queues */ spinlock_t ps_lock; struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS]; struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS]; unsigned long driver_buffered_tids; unsigned long txq_buffered_tids; u64 assoc_at; long last_connected; /* Plus 1 for non-QoS frames */ __le16 last_seq_ctrl[IEEE80211_NUM_TIDS + 1]; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; struct airtime_info airtime[IEEE80211_NUM_ACS]; u16 airtime_weight; /* * Aggregation information, locked with lock. */ struct sta_ampdu_mlme ampdu_mlme; #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *debugfs_dir; #endif struct codel_params cparams; u8 reserved_tid; s8 amsdu_mesh_control; struct cfg80211_chan_def tdls_chandef; struct ieee80211_fragment_cache frags; struct ieee80211_sta_aggregates cur; struct link_sta_info deflink; struct link_sta_info __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; /* keep last! */ struct ieee80211_sta sta; }; static inline enum nl80211_plink_state sta_plink_state(struct sta_info *sta) { #ifdef CONFIG_MAC80211_MESH return sta->mesh->plink_state; #endif return NL80211_PLINK_LISTEN; } static inline void set_sta_flag(struct sta_info *sta, enum ieee80211_sta_info_flags flag) { WARN_ON(flag == WLAN_STA_AUTH || flag == WLAN_STA_ASSOC || flag == WLAN_STA_AUTHORIZED); set_bit(flag, &sta->_flags); } static inline void clear_sta_flag(struct sta_info *sta, enum ieee80211_sta_info_flags flag) { WARN_ON(flag == WLAN_STA_AUTH || flag == WLAN_STA_ASSOC || flag == WLAN_STA_AUTHORIZED); clear_bit(flag, &sta->_flags); } static inline int test_sta_flag(struct sta_info *sta, enum ieee80211_sta_info_flags flag) { return test_bit(flag, &sta->_flags); } static inline int test_and_clear_sta_flag(struct sta_info *sta, enum ieee80211_sta_info_flags flag) { WARN_ON(flag == WLAN_STA_AUTH || flag == WLAN_STA_ASSOC || flag == WLAN_STA_AUTHORIZED); return test_and_clear_bit(flag, &sta->_flags); } static inline int test_and_set_sta_flag(struct sta_info *sta, enum ieee80211_sta_info_flags flag) { WARN_ON(flag == WLAN_STA_AUTH || flag == WLAN_STA_ASSOC || flag == WLAN_STA_AUTHORIZED); return test_and_set_bit(flag, &sta->_flags); } int sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state); static inline void sta_info_pre_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state) { int ret; WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED)); ret = sta_info_move_state(sta, new_state); WARN_ON_ONCE(ret); } void ieee80211_assign_tid_tx(struct sta_info *sta, int tid, struct tid_ampdu_tx *tid_tx); #define rcu_dereference_protected_tid_tx(sta, tid) \ rcu_dereference_protected((sta)->ampdu_mlme.tid_tx[tid], \ lockdep_is_held(&(sta)->lock) || \ lockdep_is_held(&(sta)->local->hw.wiphy->mtx)); /* Maximum number of frames to buffer per power saving station per AC */ #define STA_MAX_TX_BUFFER 64 /* Minimum buffered frame expiry time. If STA uses listen interval that is * smaller than this value, the minimum value here is used instead. */ #define STA_TX_BUFFER_EXPIRE (10 * HZ) /* How often station data is cleaned up (e.g., expiration of buffered frames) */ #define STA_INFO_CLEANUP_INTERVAL (10 * HZ) struct rhlist_head *sta_info_hash_lookup(struct ieee80211_local *local, const u8 *addr); /* * Get a STA info, must be under RCU read lock. */ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, const u8 *addr); struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr); /* user must hold wiphy mutex or be in RCU critical section */ struct sta_info *sta_info_get_by_addrs(struct ieee80211_local *local, const u8 *sta_addr, const u8 *vif_addr); #define for_each_sta_info(local, _addr, _sta, _tmp) \ rhl_for_each_entry_rcu(_sta, _tmp, \ sta_info_hash_lookup(local, _addr), hash_node) struct rhlist_head *link_sta_info_hash_lookup(struct ieee80211_local *local, const u8 *addr); #define for_each_link_sta_info(local, _addr, _sta, _tmp) \ rhl_for_each_entry_rcu(_sta, _tmp, \ link_sta_info_hash_lookup(local, _addr), \ link_hash_node) struct link_sta_info * link_sta_info_get_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr); /* * Get STA info by index, BROKEN! */ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata, int idx); /* * Create a new STA info, caller owns returned structure * until sta_info_insert(). */ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, const u8 *addr, gfp_t gfp); struct sta_info *sta_info_alloc_with_link(struct ieee80211_sub_if_data *sdata, const u8 *mld_addr, unsigned int link_id, const u8 *link_addr, gfp_t gfp); void sta_info_free(struct ieee80211_local *local, struct sta_info *sta); /* * Insert STA info into hash table/list, returns zero or a * -EEXIST if (if the same MAC address is already present). * * Calling the non-rcu version makes the caller relinquish, * the _rcu version calls read_lock_rcu() and must be called * without it held. */ int sta_info_insert(struct sta_info *sta); int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU); int __must_check __sta_info_destroy(struct sta_info *sta); int sta_info_destroy_addr(struct ieee80211_sub_if_data *sdata, const u8 *addr); int sta_info_destroy_addr_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr); void sta_info_recalc_tim(struct sta_info *sta); int sta_info_init(struct ieee80211_local *local); void sta_info_stop(struct ieee80211_local *local); /** * __sta_info_flush - flush matching STA entries from the STA table * * Returns the number of removed STA entries. * * @sdata: sdata to remove all stations from * @vlans: if the given interface is an AP interface, also flush VLANs */ int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans); /** * sta_info_flush - flush matching STA entries from the STA table * * Returns the number of removed STA entries. * * @sdata: sdata to remove all stations from */ static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata) { return __sta_info_flush(sdata, false); } void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo); void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, bool tidstats); u32 sta_get_expected_throughput(struct sta_info *sta); void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, unsigned long exp_time); int ieee80211_sta_allocate_link(struct sta_info *sta, unsigned int link_id); void ieee80211_sta_free_link(struct sta_info *sta, unsigned int link_id); int ieee80211_sta_activate_link(struct sta_info *sta, unsigned int link_id); void ieee80211_sta_remove_link(struct sta_info *sta, unsigned int link_id); void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta); void ieee80211_sta_ps_deliver_poll_response(struct sta_info *sta); void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta); unsigned long ieee80211_sta_last_active(struct sta_info *sta); void ieee80211_sta_set_max_amsdu_subframes(struct sta_info *sta, const u8 *ext_capab, unsigned int ext_capab_len); void __ieee80211_sta_recalc_aggregates(struct sta_info *sta, u16 active_links); enum sta_stats_type { STA_STATS_RATE_TYPE_INVALID = 0, STA_STATS_RATE_TYPE_LEGACY, STA_STATS_RATE_TYPE_HT, STA_STATS_RATE_TYPE_VHT, STA_STATS_RATE_TYPE_HE, STA_STATS_RATE_TYPE_S1G, STA_STATS_RATE_TYPE_EHT, }; #define STA_STATS_FIELD_HT_MCS GENMASK( 7, 0) #define STA_STATS_FIELD_LEGACY_IDX GENMASK( 3, 0) #define STA_STATS_FIELD_LEGACY_BAND GENMASK( 7, 4) #define STA_STATS_FIELD_VHT_MCS GENMASK( 3, 0) #define STA_STATS_FIELD_VHT_NSS GENMASK( 7, 4) #define STA_STATS_FIELD_HE_MCS GENMASK( 3, 0) #define STA_STATS_FIELD_HE_NSS GENMASK( 7, 4) #define STA_STATS_FIELD_EHT_MCS GENMASK( 3, 0) #define STA_STATS_FIELD_EHT_NSS GENMASK( 7, 4) #define STA_STATS_FIELD_BW GENMASK(12, 8) #define STA_STATS_FIELD_SGI GENMASK(13, 13) #define STA_STATS_FIELD_TYPE GENMASK(16, 14) #define STA_STATS_FIELD_HE_RU GENMASK(19, 17) #define STA_STATS_FIELD_HE_GI GENMASK(21, 20) #define STA_STATS_FIELD_HE_DCM GENMASK(22, 22) #define STA_STATS_FIELD_EHT_RU GENMASK(20, 17) #define STA_STATS_FIELD_EHT_GI GENMASK(22, 21) #define STA_STATS_FIELD(_n, _v) FIELD_PREP(STA_STATS_FIELD_ ## _n, _v) #define STA_STATS_GET(_n, _v) FIELD_GET(STA_STATS_FIELD_ ## _n, _v) #define STA_STATS_RATE_INVALID 0 static inline u32 sta_stats_encode_rate(struct ieee80211_rx_status *s) { u32 r; r = STA_STATS_FIELD(BW, s->bw); if (s->enc_flags & RX_ENC_FLAG_SHORT_GI) r |= STA_STATS_FIELD(SGI, 1); switch (s->encoding) { case RX_ENC_VHT: r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_VHT); r |= STA_STATS_FIELD(VHT_NSS, s->nss); r |= STA_STATS_FIELD(VHT_MCS, s->rate_idx); break; case RX_ENC_HT: r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_HT); r |= STA_STATS_FIELD(HT_MCS, s->rate_idx); break; case RX_ENC_LEGACY: r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_LEGACY); r |= STA_STATS_FIELD(LEGACY_BAND, s->band); r |= STA_STATS_FIELD(LEGACY_IDX, s->rate_idx); break; case RX_ENC_HE: r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_HE); r |= STA_STATS_FIELD(HE_NSS, s->nss); r |= STA_STATS_FIELD(HE_MCS, s->rate_idx); r |= STA_STATS_FIELD(HE_GI, s->he_gi); r |= STA_STATS_FIELD(HE_RU, s->he_ru); r |= STA_STATS_FIELD(HE_DCM, s->he_dcm); break; case RX_ENC_EHT: r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_EHT); r |= STA_STATS_FIELD(EHT_NSS, s->nss); r |= STA_STATS_FIELD(EHT_MCS, s->rate_idx); r |= STA_STATS_FIELD(EHT_GI, s->eht.gi); r |= STA_STATS_FIELD(EHT_RU, s->eht.ru); break; default: WARN_ON(1); return STA_STATS_RATE_INVALID; } return r; } #endif /* STA_INFO_H */ |
| 2 67 1 2 1 1 591 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ #ifndef __IPVLAN_H #define __IPVLAN_H #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/if_link.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/inetdevice.h> #include <linux/netfilter.h> #include <net/ip.h> #include <net/ip6_route.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/route.h> #include <net/addrconf.h> #include <net/l3mdev.h> #define IPVLAN_DRV "ipvlan" #define IPV_DRV_VER "0.1" #define IPVLAN_HASH_SIZE (1 << BITS_PER_BYTE) #define IPVLAN_HASH_MASK (IPVLAN_HASH_SIZE - 1) #define IPVLAN_MAC_FILTER_BITS 8 #define IPVLAN_MAC_FILTER_SIZE (1 << IPVLAN_MAC_FILTER_BITS) #define IPVLAN_MAC_FILTER_MASK (IPVLAN_MAC_FILTER_SIZE - 1) #define IPVLAN_QBACKLOG_LIMIT 1000 typedef enum { IPVL_IPV6 = 0, IPVL_ICMPV6, IPVL_IPV4, IPVL_ARP, } ipvl_hdr_type; struct ipvl_pcpu_stats { u64_stats_t rx_pkts; u64_stats_t rx_bytes; u64_stats_t rx_mcast; u64_stats_t tx_pkts; u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errs; u32 tx_drps; }; struct ipvl_port; struct ipvl_dev { struct net_device *dev; struct list_head pnode; struct ipvl_port *port; struct net_device *phy_dev; struct list_head addrs; struct ipvl_pcpu_stats __percpu *pcpu_stats; DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE); netdev_features_t sfeatures; u32 msg_enable; spinlock_t addrs_lock; }; struct ipvl_addr { struct ipvl_dev *master; /* Back pointer to master */ union { struct in6_addr ip6; /* IPv6 address on logical interface */ struct in_addr ip4; /* IPv4 address on logical interface */ } ipu; #define ip6addr ipu.ip6 #define ip4addr ipu.ip4 struct hlist_node hlnode; /* Hash-table linkage */ struct list_head anode; /* logical-interface linkage */ ipvl_hdr_type atype; struct rcu_head rcu; }; struct ipvl_port { struct net_device *dev; possible_net_t pnet; struct hlist_head hlhead[IPVLAN_HASH_SIZE]; struct list_head ipvlans; u16 mode; u16 flags; u16 dev_id_start; struct work_struct wq; struct sk_buff_head backlog; int count; struct ida ida; netdevice_tracker dev_tracker; }; struct ipvl_skb_cb { bool tx_pkt; }; #define IPVL_SKB_CB(_skb) ((struct ipvl_skb_cb *)&((_skb)->cb[0])) static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d) { return rcu_dereference(d->rx_handler_data); } static inline struct ipvl_port *ipvlan_port_get_rcu_bh(const struct net_device *d) { return rcu_dereference_bh(d->rx_handler_data); } static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d) { return rtnl_dereference(d->rx_handler_data); } static inline bool ipvlan_is_private(const struct ipvl_port *port) { return !!(port->flags & IPVLAN_F_PRIVATE); } static inline void ipvlan_mark_private(struct ipvl_port *port) { port->flags |= IPVLAN_F_PRIVATE; } static inline void ipvlan_clear_private(struct ipvl_port *port) { port->flags &= ~IPVLAN_F_PRIVATE; } static inline bool ipvlan_is_vepa(const struct ipvl_port *port) { return !!(port->flags & IPVLAN_F_VEPA); } static inline void ipvlan_mark_vepa(struct ipvl_port *port) { port->flags |= IPVLAN_F_VEPA; } static inline void ipvlan_clear_vepa(struct ipvl_port *port) { port->flags &= ~IPVLAN_F_VEPA; } void ipvlan_init_secret(void); unsigned int ipvlan_mac_hash(const unsigned char *addr); rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb); void ipvlan_process_multicast(struct work_struct *work); int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev); void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr); struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6); bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6); void ipvlan_ht_addr_del(struct ipvl_addr *addr); struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, int addr_type, bool use_dest); void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type); void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast); int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); void ipvlan_link_delete(struct net_device *dev, struct list_head *head); void ipvlan_link_setup(struct net_device *dev); int ipvlan_link_register(struct rtnl_link_ops *ops); #ifdef CONFIG_IPVLAN_L3S int ipvlan_l3s_register(struct ipvl_port *port); void ipvlan_l3s_unregister(struct ipvl_port *port); void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet); int ipvlan_l3s_init(void); void ipvlan_l3s_cleanup(void); #else static inline int ipvlan_l3s_register(struct ipvl_port *port) { return -ENOTSUPP; } static inline void ipvlan_l3s_unregister(struct ipvl_port *port) { } static inline void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet) { } static inline int ipvlan_l3s_init(void) { return 0; } static inline void ipvlan_l3s_cleanup(void) { } #endif /* CONFIG_IPVLAN_L3S */ static inline bool netif_is_ipvlan_port(const struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == ipvlan_handle_frame; } #endif /* __IPVLAN_H */ |
| 7 7 7 7 7 7 7 7 7 7 7 7 7 7 6 7 2 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 2 7 7 7 7 7 7 7 6 6 7 7 7 7 7 7 7 7 7 7 6 6 6 6 6 6 6 6 5 7 7 6 6 6 6 6 6 6 6 6 5 7 7 7 7 2 7 7 7 7 7 7 6 7 7 2 2 7 7 7 7 7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) International Business Machines Corp., 2006 * * Author: Artem Bityutskiy (Битюцкий Артём) */ /* * UBI attaching sub-system. * * This sub-system is responsible for attaching MTD devices and it also * implements flash media scanning. * * The attaching information is represented by a &struct ubi_attach_info' * object. Information about volumes is represented by &struct ubi_ainf_volume * objects which are kept in volume RB-tree with root at the @volumes field. * The RB-tree is indexed by the volume ID. * * Logical eraseblocks are represented by &struct ubi_ainf_peb objects. These * objects are kept in per-volume RB-trees with the root at the corresponding * &struct ubi_ainf_volume object. To put it differently, we keep an RB-tree of * per-volume objects and each of these objects is the root of RB-tree of * per-LEB objects. * * Corrupted physical eraseblocks are put to the @corr list, free physical * eraseblocks are put to the @free list and the physical eraseblock to be * erased are put to the @erase list. * * About corruptions * ~~~~~~~~~~~~~~~~~ * * UBI protects EC and VID headers with CRC-32 checksums, so it can detect * whether the headers are corrupted or not. Sometimes UBI also protects the * data with CRC-32, e.g., when it executes the atomic LEB change operation, or * when it moves the contents of a PEB for wear-leveling purposes. * * UBI tries to distinguish between 2 types of corruptions. * * 1. Corruptions caused by power cuts. These are expected corruptions and UBI * tries to handle them gracefully, without printing too many warnings and * error messages. The idea is that we do not lose important data in these * cases - we may lose only the data which were being written to the media just * before the power cut happened, and the upper layers (e.g., UBIFS) are * supposed to handle such data losses (e.g., by using the FS journal). * * When UBI detects a corruption (CRC-32 mismatch) in a PEB, and it looks like * the reason is a power cut, UBI puts this PEB to the @erase list, and all * PEBs in the @erase list are scheduled for erasure later. * * 2. Unexpected corruptions which are not caused by power cuts. During * attaching, such PEBs are put to the @corr list and UBI preserves them. * Obviously, this lessens the amount of available PEBs, and if at some point * UBI runs out of free PEBs, it switches to R/O mode. UBI also loudly informs * about such PEBs every time the MTD device is attached. * * However, it is difficult to reliably distinguish between these types of * corruptions and UBI's strategy is as follows (in case of attaching by * scanning). UBI assumes corruption type 2 if the VID header is corrupted and * the data area does not contain all 0xFFs, and there were no bit-flips or * integrity errors (e.g., ECC errors in case of NAND) while reading the data * area. Otherwise UBI assumes corruption type 1. So the decision criteria * are as follows. * o If the data area contains only 0xFFs, there are no data, and it is safe * to just erase this PEB - this is corruption type 1. * o If the data area has bit-flips or data integrity errors (ECC errors on * NAND), it is probably a PEB which was being erased when power cut * happened, so this is corruption type 1. However, this is just a guess, * which might be wrong. * o Otherwise this is corruption type 2. */ #include <linux/err.h> #include <linux/slab.h> #include <linux/crc32.h> #include <linux/math64.h> #include <linux/random.h> #include "ubi.h" static int self_check_ai(struct ubi_device *ubi, struct ubi_attach_info *ai); #define AV_FIND BIT(0) #define AV_ADD BIT(1) #define AV_FIND_OR_ADD (AV_FIND | AV_ADD) /** * find_or_add_av - internal function to find a volume, add a volume or do * both (find and add if missing). * @ai: attaching information * @vol_id: the requested volume ID * @flags: a combination of the %AV_FIND and %AV_ADD flags describing the * expected operation. If only %AV_ADD is set, -EEXIST is returned * if the volume already exists. If only %AV_FIND is set, NULL is * returned if the volume does not exist. And if both flags are * set, the helper first tries to find an existing volume, and if * it does not exist it creates a new one. * @created: in value used to inform the caller whether it"s a newly created * volume or not. * * This function returns a pointer to a volume description or an ERR_PTR if * the operation failed. It can also return NULL if only %AV_FIND is set and * the volume does not exist. */ static struct ubi_ainf_volume *find_or_add_av(struct ubi_attach_info *ai, int vol_id, unsigned int flags, bool *created) { struct ubi_ainf_volume *av; struct rb_node **p = &ai->volumes.rb_node, *parent = NULL; /* Walk the volume RB-tree to look if this volume is already present */ while (*p) { parent = *p; av = rb_entry(parent, struct ubi_ainf_volume, rb); if (vol_id == av->vol_id) { *created = false; if (!(flags & AV_FIND)) return ERR_PTR(-EEXIST); return av; } if (vol_id > av->vol_id) p = &(*p)->rb_left; else p = &(*p)->rb_right; } if (!(flags & AV_ADD)) return NULL; /* The volume is absent - add it */ av = kzalloc(sizeof(*av), GFP_KERNEL); if (!av) return ERR_PTR(-ENOMEM); av->vol_id = vol_id; if (vol_id > ai->highest_vol_id) ai->highest_vol_id = vol_id; rb_link_node(&av->rb, parent, p); rb_insert_color(&av->rb, &ai->volumes); ai->vols_found += 1; *created = true; dbg_bld("added volume %d", vol_id); return av; } /** * ubi_find_or_add_av - search for a volume in the attaching information and * add one if it does not exist. * @ai: attaching information * @vol_id: the requested volume ID * @created: whether the volume has been created or not * * This function returns a pointer to the new volume description or an * ERR_PTR if the operation failed. */ static struct ubi_ainf_volume *ubi_find_or_add_av(struct ubi_attach_info *ai, int vol_id, bool *created) { return find_or_add_av(ai, vol_id, AV_FIND_OR_ADD, created); } /** * ubi_alloc_aeb - allocate an aeb element * @ai: attaching information * @pnum: physical eraseblock number * @ec: erase counter of the physical eraseblock * * Allocate an aeb object and initialize the pnum and ec information. * vol_id and lnum are set to UBI_UNKNOWN, and the other fields are * initialized to zero. * Note that the element is not added in any list or RB tree. */ struct ubi_ainf_peb *ubi_alloc_aeb(struct ubi_attach_info *ai, int pnum, int ec) { struct ubi_ainf_peb *aeb; aeb = kmem_cache_zalloc(ai->aeb_slab_cache, GFP_KERNEL); if (!aeb) return NULL; aeb->pnum = pnum; aeb->ec = ec; aeb->vol_id = UBI_UNKNOWN; aeb->lnum = UBI_UNKNOWN; return aeb; } /** * ubi_free_aeb - free an aeb element * @ai: attaching information * @aeb: the element to free * * Free an aeb object. The caller must have removed the element from any list * or RB tree. */ void ubi_free_aeb(struct ubi_attach_info *ai, struct ubi_ainf_peb *aeb) { kmem_cache_free(ai->aeb_slab_cache, aeb); } /** * add_to_list - add physical eraseblock to a list. * @ai: attaching information * @pnum: physical eraseblock number to add * @vol_id: the last used volume id for the PEB * @lnum: the last used LEB number for the PEB * @ec: erase counter of the physical eraseblock * @to_head: if not zero, add to the head of the list * @list: the list to add to * * This function allocates a 'struct ubi_ainf_peb' object for physical * eraseblock @pnum and adds it to the "free", "erase", or "alien" lists. * It stores the @lnum and @vol_id alongside, which can both be * %UBI_UNKNOWN if they are not available, not readable, or not assigned. * If @to_head is not zero, PEB will be added to the head of the list, which * basically means it will be processed first later. E.g., we add corrupted * PEBs (corrupted due to power cuts) to the head of the erase list to make * sure we erase them first and get rid of corruptions ASAP. This function * returns zero in case of success and a negative error code in case of * failure. */ static int add_to_list(struct ubi_attach_info *ai, int pnum, int vol_id, int lnum, int ec, int to_head, struct list_head *list) { struct ubi_ainf_peb *aeb; if (list == &ai->free) { dbg_bld("add to free: PEB %d, EC %d", pnum, ec); } else if (list == &ai->erase) { dbg_bld("add to erase: PEB %d, EC %d", pnum, ec); } else if (list == &ai->alien) { dbg_bld("add to alien: PEB %d, EC %d", pnum, ec); ai->alien_peb_count += 1; } else BUG(); aeb = ubi_alloc_aeb(ai, pnum, ec); if (!aeb) return -ENOMEM; aeb->vol_id = vol_id; aeb->lnum = lnum; if (to_head) list_add(&aeb->u.list, list); else list_add_tail(&aeb->u.list, list); return 0; } /** * add_corrupted - add a corrupted physical eraseblock. * @ai: attaching information * @pnum: physical eraseblock number to add * @ec: erase counter of the physical eraseblock * * This function allocates a 'struct ubi_ainf_peb' object for a corrupted * physical eraseblock @pnum and adds it to the 'corr' list. The corruption * was presumably not caused by a power cut. Returns zero in case of success * and a negative error code in case of failure. */ static int add_corrupted(struct ubi_attach_info *ai, int pnum, int ec) { struct ubi_ainf_peb *aeb; dbg_bld("add to corrupted: PEB %d, EC %d", pnum, ec); aeb = ubi_alloc_aeb(ai, pnum, ec); if (!aeb) return -ENOMEM; ai->corr_peb_count += 1; list_add(&aeb->u.list, &ai->corr); return 0; } /** * add_fastmap - add a Fastmap related physical eraseblock. * @ai: attaching information * @pnum: physical eraseblock number the VID header came from * @vid_hdr: the volume identifier header * @ec: erase counter of the physical eraseblock * * This function allocates a 'struct ubi_ainf_peb' object for a Fastamp * physical eraseblock @pnum and adds it to the 'fastmap' list. * Such blocks can be Fastmap super and data blocks from both the most * recent Fastmap we're attaching from or from old Fastmaps which will * be erased. */ static int add_fastmap(struct ubi_attach_info *ai, int pnum, struct ubi_vid_hdr *vid_hdr, int ec) { struct ubi_ainf_peb *aeb; aeb = ubi_alloc_aeb(ai, pnum, ec); if (!aeb) return -ENOMEM; aeb->vol_id = be32_to_cpu(vid_hdr->vol_id); aeb->sqnum = be64_to_cpu(vid_hdr->sqnum); list_add(&aeb->u.list, &ai->fastmap); dbg_bld("add to fastmap list: PEB %d, vol_id %d, sqnum: %llu", pnum, aeb->vol_id, aeb->sqnum); return 0; } /** * validate_vid_hdr - check volume identifier header. * @ubi: UBI device description object * @vid_hdr: the volume identifier header to check * @av: information about the volume this logical eraseblock belongs to * @pnum: physical eraseblock number the VID header came from * * This function checks that data stored in @vid_hdr is consistent. Returns * non-zero if an inconsistency was found and zero if not. * * Note, UBI does sanity check of everything it reads from the flash media. * Most of the checks are done in the I/O sub-system. Here we check that the * information in the VID header is consistent to the information in other VID * headers of the same volume. */ static int validate_vid_hdr(const struct ubi_device *ubi, const struct ubi_vid_hdr *vid_hdr, const struct ubi_ainf_volume *av, int pnum) { int vol_type = vid_hdr->vol_type; int vol_id = be32_to_cpu(vid_hdr->vol_id); int used_ebs = be32_to_cpu(vid_hdr->used_ebs); int data_pad = be32_to_cpu(vid_hdr->data_pad); if (av->leb_count != 0) { int av_vol_type; /* * This is not the first logical eraseblock belonging to this * volume. Ensure that the data in its VID header is consistent * to the data in previous logical eraseblock headers. */ if (vol_id != av->vol_id) { ubi_err(ubi, "inconsistent vol_id"); goto bad; } if (av->vol_type == UBI_STATIC_VOLUME) av_vol_type = UBI_VID_STATIC; else av_vol_type = UBI_VID_DYNAMIC; if (vol_type != av_vol_type) { ubi_err(ubi, "inconsistent vol_type"); goto bad; } if (used_ebs != av->used_ebs) { ubi_err(ubi, "inconsistent used_ebs"); goto bad; } if (data_pad != av->data_pad) { ubi_err(ubi, "inconsistent data_pad"); goto bad; } } return 0; bad: ubi_err(ubi, "inconsistent VID header at PEB %d", pnum); ubi_dump_vid_hdr(vid_hdr); ubi_dump_av(av); return -EINVAL; } /** * add_volume - add volume to the attaching information. * @ai: attaching information * @vol_id: ID of the volume to add * @pnum: physical eraseblock number * @vid_hdr: volume identifier header * * If the volume corresponding to the @vid_hdr logical eraseblock is already * present in the attaching information, this function does nothing. Otherwise * it adds corresponding volume to the attaching information. Returns a pointer * to the allocated "av" object in case of success and a negative error code in * case of failure. */ static struct ubi_ainf_volume *add_volume(struct ubi_attach_info *ai, int vol_id, int pnum, const struct ubi_vid_hdr *vid_hdr) { struct ubi_ainf_volume *av; bool created; ubi_assert(vol_id == be32_to_cpu(vid_hdr->vol_id)); av = ubi_find_or_add_av(ai, vol_id, &created); if (IS_ERR(av) || !created) return av; av->used_ebs = be32_to_cpu(vid_hdr->used_ebs); av->data_pad = be32_to_cpu(vid_hdr->data_pad); av->compat = vid_hdr->compat; av->vol_type = vid_hdr->vol_type == UBI_VID_DYNAMIC ? UBI_DYNAMIC_VOLUME : UBI_STATIC_VOLUME; return av; } /** * ubi_compare_lebs - find out which logical eraseblock is newer. * @ubi: UBI device description object * @aeb: first logical eraseblock to compare * @pnum: physical eraseblock number of the second logical eraseblock to * compare * @vid_hdr: volume identifier header of the second logical eraseblock * * This function compares 2 copies of a LEB and informs which one is newer. In * case of success this function returns a positive value, in case of failure, a * negative error code is returned. The success return codes use the following * bits: * o bit 0 is cleared: the first PEB (described by @aeb) is newer than the * second PEB (described by @pnum and @vid_hdr); * o bit 0 is set: the second PEB is newer; * o bit 1 is cleared: no bit-flips were detected in the newer LEB; * o bit 1 is set: bit-flips were detected in the newer LEB; * o bit 2 is cleared: the older LEB is not corrupted; * o bit 2 is set: the older LEB is corrupted. */ int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb, int pnum, const struct ubi_vid_hdr *vid_hdr) { int len, err, second_is_newer, bitflips = 0, corrupted = 0; uint32_t data_crc, crc; struct ubi_vid_io_buf *vidb = NULL; unsigned long long sqnum2 = be64_to_cpu(vid_hdr->sqnum); if (sqnum2 == aeb->sqnum) { /* * This must be a really ancient UBI image which has been * created before sequence numbers support has been added. At * that times we used 32-bit LEB versions stored in logical * eraseblocks. That was before UBI got into mainline. We do not * support these images anymore. Well, those images still work, * but only if no unclean reboots happened. */ ubi_err(ubi, "unsupported on-flash UBI format"); return -EINVAL; } /* Obviously the LEB with lower sequence counter is older */ second_is_newer = (sqnum2 > aeb->sqnum); /* * Now we know which copy is newer. If the copy flag of the PEB with * newer version is not set, then we just return, otherwise we have to * check data CRC. For the second PEB we already have the VID header, * for the first one - we'll need to re-read it from flash. * * Note: this may be optimized so that we wouldn't read twice. */ if (second_is_newer) { if (!vid_hdr->copy_flag) { /* It is not a copy, so it is newer */ dbg_bld("second PEB %d is newer, copy_flag is unset", pnum); return 1; } } else { if (!aeb->copy_flag) { /* It is not a copy, so it is newer */ dbg_bld("first PEB %d is newer, copy_flag is unset", pnum); return bitflips << 1; } vidb = ubi_alloc_vid_buf(ubi, GFP_KERNEL); if (!vidb) return -ENOMEM; pnum = aeb->pnum; err = ubi_io_read_vid_hdr(ubi, pnum, vidb, 0); if (err) { if (err == UBI_IO_BITFLIPS) bitflips = 1; else { ubi_err(ubi, "VID of PEB %d header is bad, but it was OK earlier, err %d", pnum, err); if (err > 0) err = -EIO; goto out_free_vidh; } } vid_hdr = ubi_get_vid_hdr(vidb); } /* Read the data of the copy and check the CRC */ len = be32_to_cpu(vid_hdr->data_size); mutex_lock(&ubi->buf_mutex); err = ubi_io_read_data(ubi, ubi->peb_buf, pnum, 0, len); if (err && err != UBI_IO_BITFLIPS && !mtd_is_eccerr(err)) goto out_unlock; data_crc = be32_to_cpu(vid_hdr->data_crc); crc = crc32(UBI_CRC32_INIT, ubi->peb_buf, len); if (crc != data_crc) { dbg_bld("PEB %d CRC error: calculated %#08x, must be %#08x", pnum, crc, data_crc); corrupted = 1; bitflips = 0; second_is_newer = !second_is_newer; } else { dbg_bld("PEB %d CRC is OK", pnum); bitflips |= !!err; } mutex_unlock(&ubi->buf_mutex); ubi_free_vid_buf(vidb); if (second_is_newer) dbg_bld("second PEB %d is newer, copy_flag is set", pnum); else dbg_bld("first PEB %d is newer, copy_flag is set", pnum); return second_is_newer | (bitflips << 1) | (corrupted << 2); out_unlock: mutex_unlock(&ubi->buf_mutex); out_free_vidh: ubi_free_vid_buf(vidb); return err; } /** * ubi_add_to_av - add used physical eraseblock to the attaching information. * @ubi: UBI device description object * @ai: attaching information * @pnum: the physical eraseblock number * @ec: erase counter * @vid_hdr: the volume identifier header * @bitflips: if bit-flips were detected when this physical eraseblock was read * * This function adds information about a used physical eraseblock to the * 'used' tree of the corresponding volume. The function is rather complex * because it has to handle cases when this is not the first physical * eraseblock belonging to the same logical eraseblock, and the newer one has * to be picked, while the older one has to be dropped. This function returns * zero in case of success and a negative error code in case of failure. */ int ubi_add_to_av(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum, int ec, const struct ubi_vid_hdr *vid_hdr, int bitflips) { int err, vol_id, lnum; unsigned long long sqnum; struct ubi_ainf_volume *av; struct ubi_ainf_peb *aeb; struct rb_node **p, *parent = NULL; vol_id = be32_to_cpu(vid_hdr->vol_id); lnum = be32_to_cpu(vid_hdr->lnum); sqnum = be64_to_cpu(vid_hdr->sqnum); dbg_bld("PEB %d, LEB %d:%d, EC %d, sqnum %llu, bitflips %d", pnum, vol_id, lnum, ec, sqnum, bitflips); av = add_volume(ai, vol_id, pnum, vid_hdr); if (IS_ERR(av)) return PTR_ERR(av); if (ai->max_sqnum < sqnum) ai->max_sqnum = sqnum; /* * Walk the RB-tree of logical eraseblocks of volume @vol_id to look * if this is the first instance of this logical eraseblock or not. */ p = &av->root.rb_node; while (*p) { int cmp_res; parent = *p; aeb = rb_entry(parent, struct ubi_ainf_peb, u.rb); if (lnum != aeb->lnum) { if (lnum < aeb->lnum) p = &(*p)->rb_left; else p = &(*p)->rb_right; continue; } /* * There is already a physical eraseblock describing the same * logical eraseblock present. */ dbg_bld("this LEB already exists: PEB %d, sqnum %llu, EC %d", aeb->pnum, aeb->sqnum, aeb->ec); /* * Make sure that the logical eraseblocks have different * sequence numbers. Otherwise the image is bad. * * However, if the sequence number is zero, we assume it must * be an ancient UBI image from the era when UBI did not have * sequence numbers. We still can attach these images, unless * there is a need to distinguish between old and new * eraseblocks, in which case we'll refuse the image in * 'ubi_compare_lebs()'. In other words, we attach old clean * images, but refuse attaching old images with duplicated * logical eraseblocks because there was an unclean reboot. */ if (aeb->sqnum == sqnum && sqnum != 0) { ubi_err(ubi, "two LEBs with same sequence number %llu", sqnum); ubi_dump_aeb(aeb, 0); ubi_dump_vid_hdr(vid_hdr); return -EINVAL; } /* * Now we have to drop the older one and preserve the newer * one. */ cmp_res = ubi_compare_lebs(ubi, aeb, pnum, vid_hdr); if (cmp_res < 0) return cmp_res; if (cmp_res & 1) { /* * This logical eraseblock is newer than the one * found earlier. */ err = validate_vid_hdr(ubi, vid_hdr, av, pnum); if (err) return err; err = add_to_list(ai, aeb->pnum, aeb->vol_id, aeb->lnum, aeb->ec, cmp_res & 4, &ai->erase); if (err) return err; aeb->ec = ec; aeb->pnum = pnum; aeb->vol_id = vol_id; aeb->lnum = lnum; aeb->scrub = ((cmp_res & 2) || bitflips); aeb->copy_flag = vid_hdr->copy_flag; aeb->sqnum = sqnum; if (av->highest_lnum == lnum) av->last_data_size = be32_to_cpu(vid_hdr->data_size); return 0; } else { /* * This logical eraseblock is older than the one found * previously. */ return add_to_list(ai, pnum, vol_id, lnum, ec, cmp_res & 4, &ai->erase); } } /* * We've met this logical eraseblock for the first time, add it to the * attaching information. */ err = validate_vid_hdr(ubi, vid_hdr, av, pnum); if (err) return err; aeb = ubi_alloc_aeb(ai, pnum, ec); if (!aeb) return -ENOMEM; aeb->vol_id = vol_id; aeb->lnum = lnum; aeb->scrub = bitflips; aeb->copy_flag = vid_hdr->copy_flag; aeb->sqnum = sqnum; if (av->highest_lnum <= lnum) { av->highest_lnum = lnum; av->last_data_size = be32_to_cpu(vid_hdr->data_size); } av->leb_count += 1; rb_link_node(&aeb->u.rb, parent, p); rb_insert_color(&aeb->u.rb, &av->root); return 0; } /** * ubi_add_av - add volume to the attaching information. * @ai: attaching information * @vol_id: the requested volume ID * * This function returns a pointer to the new volume description or an * ERR_PTR if the operation failed. */ struct ubi_ainf_volume *ubi_add_av(struct ubi_attach_info *ai, int vol_id) { bool created; return find_or_add_av(ai, vol_id, AV_ADD, &created); } /** * ubi_find_av - find volume in the attaching information. * @ai: attaching information * @vol_id: the requested volume ID * * This function returns a pointer to the volume description or %NULL if there * are no data about this volume in the attaching information. */ struct ubi_ainf_volume *ubi_find_av(const struct ubi_attach_info *ai, int vol_id) { bool created; return find_or_add_av((struct ubi_attach_info *)ai, vol_id, AV_FIND, &created); } static void destroy_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av, struct list_head *list); /** * ubi_remove_av - delete attaching information about a volume. * @ai: attaching information * @av: the volume attaching information to delete */ void ubi_remove_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av) { dbg_bld("remove attaching information about volume %d", av->vol_id); rb_erase(&av->rb, &ai->volumes); destroy_av(ai, av, &ai->erase); ai->vols_found -= 1; } /** * early_erase_peb - erase a physical eraseblock. * @ubi: UBI device description object * @ai: attaching information * @pnum: physical eraseblock number to erase; * @ec: erase counter value to write (%UBI_UNKNOWN if it is unknown) * * This function erases physical eraseblock 'pnum', and writes the erase * counter header to it. This function should only be used on UBI device * initialization stages, when the EBA sub-system had not been yet initialized. * This function returns zero in case of success and a negative error code in * case of failure. */ static int early_erase_peb(struct ubi_device *ubi, const struct ubi_attach_info *ai, int pnum, int ec) { int err; struct ubi_ec_hdr *ec_hdr; if ((long long)ec >= UBI_MAX_ERASECOUNTER) { /* * Erase counter overflow. Upgrade UBI and use 64-bit * erase counters internally. */ ubi_err(ubi, "erase counter overflow at PEB %d, EC %d", pnum, ec); return -EINVAL; } ec_hdr = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL); if (!ec_hdr) return -ENOMEM; ec_hdr->ec = cpu_to_be64(ec); err = ubi_io_sync_erase(ubi, pnum, 0); if (err < 0) goto out_free; err = ubi_io_write_ec_hdr(ubi, pnum, ec_hdr); out_free: kfree(ec_hdr); return err; } /** * ubi_early_get_peb - get a free physical eraseblock. * @ubi: UBI device description object * @ai: attaching information * * This function returns a free physical eraseblock. It is supposed to be * called on the UBI initialization stages when the wear-leveling sub-system is * not initialized yet. This function picks a physical eraseblocks from one of * the lists, writes the EC header if it is needed, and removes it from the * list. * * This function returns a pointer to the "aeb" of the found free PEB in case * of success and an error code in case of failure. */ struct ubi_ainf_peb *ubi_early_get_peb(struct ubi_device *ubi, struct ubi_attach_info *ai) { int err = 0; struct ubi_ainf_peb *aeb, *tmp_aeb; if (!list_empty(&ai->free)) { aeb = list_entry(ai->free.next, struct ubi_ainf_peb, u.list); list_del(&aeb->u.list); dbg_bld("return free PEB %d, EC %d", aeb->pnum, aeb->ec); return aeb; } /* * We try to erase the first physical eraseblock from the erase list * and pick it if we succeed, or try to erase the next one if not. And * so forth. We don't want to take care about bad eraseblocks here - * they'll be handled later. */ list_for_each_entry_safe(aeb, tmp_aeb, &ai->erase, u.list) { if (aeb->ec == UBI_UNKNOWN) aeb->ec = ai->mean_ec; err = early_erase_peb(ubi, ai, aeb->pnum, aeb->ec+1); if (err) continue; aeb->ec += 1; list_del(&aeb->u.list); dbg_bld("return PEB %d, EC %d", aeb->pnum, aeb->ec); return aeb; } ubi_err(ubi, "no free eraseblocks"); return ERR_PTR(-ENOSPC); } /** * check_corruption - check the data area of PEB. * @ubi: UBI device description object * @vid_hdr: the (corrupted) VID header of this PEB * @pnum: the physical eraseblock number to check * * This is a helper function which is used to distinguish between VID header * corruptions caused by power cuts and other reasons. If the PEB contains only * 0xFF bytes in the data area, the VID header is most probably corrupted * because of a power cut (%0 is returned in this case). Otherwise, it was * probably corrupted for some other reasons (%1 is returned in this case). A * negative error code is returned if a read error occurred. * * If the corruption reason was a power cut, UBI can safely erase this PEB. * Otherwise, it should preserve it to avoid possibly destroying important * information. */ static int check_corruption(struct ubi_device *ubi, struct ubi_vid_hdr *vid_hdr, int pnum) { int err; mutex_lock(&ubi->buf_mutex); memset(ubi->peb_buf, 0x00, ubi->leb_size); err = ubi_io_read(ubi, ubi->peb_buf, pnum, ubi->leb_start, ubi->leb_size); if (err == UBI_IO_BITFLIPS || mtd_is_eccerr(err)) { /* * Bit-flips or integrity errors while reading the data area. * It is difficult to say for sure what type of corruption is * this, but presumably a power cut happened while this PEB was * erased, so it became unstable and corrupted, and should be * erased. */ err = 0; goto out_unlock; } if (err) goto out_unlock; if (ubi_check_pattern(ubi->peb_buf, 0xFF, ubi->leb_size)) goto out_unlock; ubi_err(ubi, "PEB %d contains corrupted VID header, and the data does not contain all 0xFF", pnum); ubi_err(ubi, "this may be a non-UBI PEB or a severe VID header corruption which requires manual inspection"); ubi_dump_vid_hdr(vid_hdr); pr_err("hexdump of PEB %d offset %d, length %d", pnum, ubi->leb_start, ubi->leb_size); ubi_dbg_print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 32, 1, ubi->peb_buf, ubi->leb_size, 1); err = 1; out_unlock: mutex_unlock(&ubi->buf_mutex); return err; } static bool vol_ignored(int vol_id) { switch (vol_id) { case UBI_LAYOUT_VOLUME_ID: return true; } #ifdef CONFIG_MTD_UBI_FASTMAP return ubi_is_fm_vol(vol_id); #else return false; #endif } /** * scan_peb - scan and process UBI headers of a PEB. * @ubi: UBI device description object * @ai: attaching information * @pnum: the physical eraseblock number * @fast: true if we're scanning for a Fastmap * * This function reads UBI headers of PEB @pnum, checks them, and adds * information about this PEB to the corresponding list or RB-tree in the * "attaching info" structure. Returns zero if the physical eraseblock was * successfully handled and a negative error code in case of failure. */ static int scan_peb(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum, bool fast) { struct ubi_ec_hdr *ech = ai->ech; struct ubi_vid_io_buf *vidb = ai->vidb; struct ubi_vid_hdr *vidh = ubi_get_vid_hdr(vidb); long long ec; int err, bitflips = 0, vol_id = -1, ec_err = 0; dbg_bld("scan PEB %d", pnum); /* Skip bad physical eraseblocks */ err = ubi_io_is_bad(ubi, pnum); if (err < 0) return err; else if (err) { ai->bad_peb_count += 1; return 0; } err = ubi_io_read_ec_hdr(ubi, pnum, ech, 0); if (err < 0) return err; switch (err) { case 0: break; case UBI_IO_BITFLIPS: bitflips = 1; break; case UBI_IO_FF: ai->empty_peb_count += 1; return add_to_list(ai, pnum, UBI_UNKNOWN, UBI_UNKNOWN, UBI_UNKNOWN, 0, &ai->erase); case UBI_IO_FF_BITFLIPS: ai->empty_peb_count += 1; return add_to_list(ai, pnum, UBI_UNKNOWN, UBI_UNKNOWN, UBI_UNKNOWN, 1, &ai->erase); case UBI_IO_BAD_HDR_EBADMSG: case UBI_IO_BAD_HDR: /* * We have to also look at the VID header, possibly it is not * corrupted. Set %bitflips flag in order to make this PEB be * moved and EC be re-created. */ ec_err = err; ec = UBI_UNKNOWN; bitflips = 1; break; default: ubi_err(ubi, "'ubi_io_read_ec_hdr()' returned unknown code %d", err); return -EINVAL; } if (!ec_err) { int image_seq; /* Make sure UBI version is OK */ if (ech->version != UBI_VERSION) { ubi_err(ubi, "this UBI version is %d, image version is %d", UBI_VERSION, (int)ech->version); return -EINVAL; } ec = be64_to_cpu(ech->ec); if (ec > UBI_MAX_ERASECOUNTER) { /* * Erase counter overflow. The EC headers have 64 bits * reserved, but we anyway make use of only 31 bit * values, as this seems to be enough for any existing * flash. Upgrade UBI and use 64-bit erase counters * internally. */ ubi_err(ubi, "erase counter overflow, max is %d", UBI_MAX_ERASECOUNTER); ubi_dump_ec_hdr(ech); return -EINVAL; } /* * Make sure that all PEBs have the same image sequence number. * This allows us to detect situations when users flash UBI * images incorrectly, so that the flash has the new UBI image * and leftovers from the old one. This feature was added * relatively recently, and the sequence number was always * zero, because old UBI implementations always set it to zero. * For this reasons, we do not panic if some PEBs have zero * sequence number, while other PEBs have non-zero sequence * number. */ image_seq = be32_to_cpu(ech->image_seq); if (!ubi->image_seq) ubi->image_seq = image_seq; if (image_seq && ubi->image_seq != image_seq) { ubi_err(ubi, "bad image sequence number %d in PEB %d, expected %d", image_seq, pnum, ubi->image_seq); ubi_dump_ec_hdr(ech); return -EINVAL; } } /* OK, we've done with the EC header, let's look at the VID header */ err = ubi_io_read_vid_hdr(ubi, pnum, vidb, 0); if (err < 0) return err; switch (err) { case 0: break; case UBI_IO_BITFLIPS: bitflips = 1; break; case UBI_IO_BAD_HDR_EBADMSG: if (ec_err == UBI_IO_BAD_HDR_EBADMSG) /* * Both EC and VID headers are corrupted and were read * with data integrity error, probably this is a bad * PEB, bit it is not marked as bad yet. This may also * be a result of power cut during erasure. */ ai->maybe_bad_peb_count += 1; fallthrough; case UBI_IO_BAD_HDR: /* * If we're facing a bad VID header we have to drop *all* * Fastmap data structures we find. The most recent Fastmap * could be bad and therefore there is a chance that we attach * from an old one. On a fine MTD stack a PEB must not render * bad all of a sudden, but the reality is different. * So, let's be paranoid and help finding the root cause by * falling back to scanning mode instead of attaching with a * bad EBA table and cause data corruption which is hard to * analyze. */ if (fast) ai->force_full_scan = 1; if (ec_err) /* * Both headers are corrupted. There is a possibility * that this a valid UBI PEB which has corresponding * LEB, but the headers are corrupted. However, it is * impossible to distinguish it from a PEB which just * contains garbage because of a power cut during erase * operation. So we just schedule this PEB for erasure. * * Besides, in case of NOR flash, we deliberately * corrupt both headers because NOR flash erasure is * slow and can start from the end. */ err = 0; else /* * The EC was OK, but the VID header is corrupted. We * have to check what is in the data area. */ err = check_corruption(ubi, vidh, pnum); if (err < 0) return err; else if (!err) /* This corruption is caused by a power cut */ err = add_to_list(ai, pnum, UBI_UNKNOWN, UBI_UNKNOWN, ec, 1, &ai->erase); else /* This is an unexpected corruption */ err = add_corrupted(ai, pnum, ec); if (err) return err; goto adjust_mean_ec; case UBI_IO_FF_BITFLIPS: err = add_to_list(ai, pnum, UBI_UNKNOWN, UBI_UNKNOWN, ec, 1, &ai->erase); if (err) return err; goto adjust_mean_ec; case UBI_IO_FF: if (ec_err || bitflips) err = add_to_list(ai, pnum, UBI_UNKNOWN, UBI_UNKNOWN, ec, 1, &ai->erase); else err = add_to_list(ai, pnum, UBI_UNKNOWN, UBI_UNKNOWN, ec, 0, &ai->free); if (err) return err; goto adjust_mean_ec; default: ubi_err(ubi, "'ubi_io_read_vid_hdr()' returned unknown code %d", err); return -EINVAL; } vol_id = be32_to_cpu(vidh->vol_id); if (vol_id > UBI_MAX_VOLUMES && !vol_ignored(vol_id)) { int lnum = be32_to_cpu(vidh->lnum); /* Unsupported internal volume */ switch (vidh->compat) { case UBI_COMPAT_DELETE: ubi_msg(ubi, "\"delete\" compatible internal volume %d:%d found, will remove it", vol_id, lnum); err = add_to_list(ai, pnum, vol_id, lnum, ec, 1, &ai->erase); if (err) return err; return 0; case UBI_COMPAT_RO: ubi_msg(ubi, "read-only compatible internal volume %d:%d found, switch to read-only mode", vol_id, lnum); ubi->ro_mode = 1; break; case UBI_COMPAT_PRESERVE: ubi_msg(ubi, "\"preserve\" compatible internal volume %d:%d found", vol_id, lnum); err = add_to_list(ai, pnum, vol_id, lnum, ec, 0, &ai->alien); if (err) return err; return 0; case UBI_COMPAT_REJECT: ubi_err(ubi, "incompatible internal volume %d:%d found", vol_id, lnum); return -EINVAL; } } if (ec_err) ubi_warn(ubi, "valid VID header but corrupted EC header at PEB %d", pnum); if (ubi_is_fm_vol(vol_id)) err = add_fastmap(ai, pnum, vidh, ec); else err = ubi_add_to_av(ubi, ai, pnum, ec, vidh, bitflips); if (err) return err; adjust_mean_ec: if (!ec_err) { ai->ec_sum += ec; ai->ec_count += 1; if (ec > ai->max_ec) ai->max_ec = ec; if (ec < ai->min_ec) ai->min_ec = ec; } return 0; } /** * late_analysis - analyze the overall situation with PEB. * @ubi: UBI device description object * @ai: attaching information * * This is a helper function which takes a look what PEBs we have after we * gather information about all of them ("ai" is compete). It decides whether * the flash is empty and should be formatted of whether there are too many * corrupted PEBs and we should not attach this MTD device. Returns zero if we * should proceed with attaching the MTD device, and %-EINVAL if we should not. */ static int late_analysis(struct ubi_device *ubi, struct ubi_attach_info *ai) { struct ubi_ainf_peb *aeb; int max_corr, peb_count; peb_count = ubi->peb_count - ai->bad_peb_count - ai->alien_peb_count; max_corr = peb_count / 20 ?: 8; /* * Few corrupted PEBs is not a problem and may be just a result of * unclean reboots. However, many of them may indicate some problems * with the flash HW or driver. */ if (ai->corr_peb_count) { ubi_err(ubi, "%d PEBs are corrupted and preserved", ai->corr_peb_count); pr_err("Corrupted PEBs are:"); list_for_each_entry(aeb, &ai->corr, u.list) pr_cont(" %d", aeb->pnum); pr_cont("\n"); /* * If too many PEBs are corrupted, we refuse attaching, * otherwise, only print a warning. */ if (ai->corr_peb_count >= max_corr) { ubi_err(ubi, "too many corrupted PEBs, refusing"); return -EINVAL; } } if (ai->empty_peb_count + ai->maybe_bad_peb_count == peb_count) { /* * All PEBs are empty, or almost all - a couple PEBs look like * they may be bad PEBs which were not marked as bad yet. * * This piece of code basically tries to distinguish between * the following situations: * * 1. Flash is empty, but there are few bad PEBs, which are not * marked as bad so far, and which were read with error. We * want to go ahead and format this flash. While formatting, * the faulty PEBs will probably be marked as bad. * * 2. Flash contains non-UBI data and we do not want to format * it and destroy possibly important information. */ if (ai->maybe_bad_peb_count <= 2) { ai->is_empty = 1; ubi_msg(ubi, "empty MTD device detected"); get_random_bytes(&ubi->image_seq, sizeof(ubi->image_seq)); } else { ubi_err(ubi, "MTD device is not UBI-formatted and possibly contains non-UBI data - refusing it"); return -EINVAL; } } return 0; } /** * destroy_av - free volume attaching information. * @av: volume attaching information * @ai: attaching information * @list: put the aeb elements in there if !NULL, otherwise free them * * This function destroys the volume attaching information. */ static void destroy_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av, struct list_head *list) { struct ubi_ainf_peb *aeb; struct rb_node *this = av->root.rb_node; while (this) { if (this->rb_left) this = this->rb_left; else if (this->rb_right) this = this->rb_right; else { aeb = rb_entry(this, struct ubi_ainf_peb, u.rb); this = rb_parent(this); if (this) { if (this->rb_left == &aeb->u.rb) this->rb_left = NULL; else this->rb_right = NULL; } if (list) list_add_tail(&aeb->u.list, list); else ubi_free_aeb(ai, aeb); } } kfree(av); } /** * destroy_ai - destroy attaching information. * @ai: attaching information */ static void destroy_ai(struct ubi_attach_info *ai) { struct ubi_ainf_peb *aeb, *aeb_tmp; struct ubi_ainf_volume *av; struct rb_node *rb; list_for_each_entry_safe(aeb, aeb_tmp, &ai->alien, u.list) { list_del(&aeb->u.list); ubi_free_aeb(ai, aeb); } list_for_each_entry_safe(aeb, aeb_tmp, &ai->erase, u.list) { list_del(&aeb->u.list); ubi_free_aeb(ai, aeb); } list_for_each_entry_safe(aeb, aeb_tmp, &ai->corr, u.list) { list_del(&aeb->u.list); ubi_free_aeb(ai, aeb); } list_for_each_entry_safe(aeb, aeb_tmp, &ai->free, u.list) { list_del(&aeb->u.list); ubi_free_aeb(ai, aeb); } list_for_each_entry_safe(aeb, aeb_tmp, &ai->fastmap, u.list) { list_del(&aeb->u.list); ubi_free_aeb(ai, aeb); } /* Destroy the volume RB-tree */ rb = ai->volumes.rb_node; while (rb) { if (rb->rb_left) rb = rb->rb_left; else if (rb->rb_right) rb = rb->rb_right; else { av = rb_entry(rb, struct ubi_ainf_volume, rb); rb = rb_parent(rb); if (rb) { if (rb->rb_left == &av->rb) rb->rb_left = NULL; else rb->rb_right = NULL; } destroy_av(ai, av, NULL); } } kmem_cache_destroy(ai->aeb_slab_cache); kfree(ai); } /** * scan_all - scan entire MTD device. * @ubi: UBI device description object * @ai: attach info object * @start: start scanning at this PEB * * This function does full scanning of an MTD device and returns complete * information about it in form of a "struct ubi_attach_info" object. In case * of failure, an error code is returned. */ static int scan_all(struct ubi_device *ubi, struct ubi_attach_info *ai, int start) { int err, pnum; struct rb_node *rb1, *rb2; struct ubi_ainf_volume *av; struct ubi_ainf_peb *aeb; err = -ENOMEM; ai->ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL); if (!ai->ech) return err; ai->vidb = ubi_alloc_vid_buf(ubi, GFP_KERNEL); if (!ai->vidb) goto out_ech; for (pnum = start; pnum < ubi->peb_count; pnum++) { cond_resched(); dbg_gen("process PEB %d", pnum); err = scan_peb(ubi, ai, pnum, false); if (err < 0) goto out_vidh; } ubi_msg(ubi, "scanning is finished"); /* Calculate mean erase counter */ if (ai->ec_count) ai->mean_ec = div_u64(ai->ec_sum, ai->ec_count); err = late_analysis(ubi, ai); if (err) goto out_vidh; /* * In case of unknown erase counter we use the mean erase counter * value. */ ubi_rb_for_each_entry(rb1, av, &ai->volumes, rb) { ubi_rb_for_each_entry(rb2, aeb, &av->root, u.rb) if (aeb->ec == UBI_UNKNOWN) aeb->ec = ai->mean_ec; } list_for_each_entry(aeb, &ai->free, u.list) { if (aeb->ec == UBI_UNKNOWN) aeb->ec = ai->mean_ec; } list_for_each_entry(aeb, &ai->corr, u.list) if (aeb->ec == UBI_UNKNOWN) aeb->ec = ai->mean_ec; list_for_each_entry(aeb, &ai->erase, u.list) if (aeb->ec == UBI_UNKNOWN) aeb->ec = ai->mean_ec; err = self_check_ai(ubi, ai); if (err) goto out_vidh; ubi_free_vid_buf(ai->vidb); kfree(ai->ech); return 0; out_vidh: ubi_free_vid_buf(ai->vidb); out_ech: kfree(ai->ech); return err; } static struct ubi_attach_info *alloc_ai(void) { struct ubi_attach_info *ai; ai = kzalloc(sizeof(struct ubi_attach_info), GFP_KERNEL); if (!ai) return ai; INIT_LIST_HEAD(&ai->corr); INIT_LIST_HEAD(&ai->free); INIT_LIST_HEAD(&ai->erase); INIT_LIST_HEAD(&ai->alien); INIT_LIST_HEAD(&ai->fastmap); ai->volumes = RB_ROOT; ai->aeb_slab_cache = kmem_cache_create("ubi_aeb_slab_cache", sizeof(struct ubi_ainf_peb), 0, 0, NULL); if (!ai->aeb_slab_cache) { kfree(ai); ai = NULL; } return ai; } #ifdef CONFIG_MTD_UBI_FASTMAP /** * scan_fast - try to find a fastmap and attach from it. * @ubi: UBI device description object * @ai: attach info object * * Returns 0 on success, negative return values indicate an internal * error. * UBI_NO_FASTMAP denotes that no fastmap was found. * UBI_BAD_FASTMAP denotes that the found fastmap was invalid. */ static int scan_fast(struct ubi_device *ubi, struct ubi_attach_info **ai) { int err, pnum; struct ubi_attach_info *scan_ai; err = -ENOMEM; scan_ai = alloc_ai(); if (!scan_ai) goto out; scan_ai->ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL); if (!scan_ai->ech) goto out_ai; scan_ai->vidb = ubi_alloc_vid_buf(ubi, GFP_KERNEL); if (!scan_ai->vidb) goto out_ech; for (pnum = 0; pnum < UBI_FM_MAX_START; pnum++) { cond_resched(); dbg_gen("process PEB %d", pnum); err = scan_peb(ubi, scan_ai, pnum, true); if (err < 0) goto out_vidh; } ubi_free_vid_buf(scan_ai->vidb); kfree(scan_ai->ech); if (scan_ai->force_full_scan) err = UBI_NO_FASTMAP; else err = ubi_scan_fastmap(ubi, *ai, scan_ai); if (err) { /* * Didn't attach via fastmap, do a full scan but reuse what * we've aready scanned. */ destroy_ai(*ai); *ai = scan_ai; } else destroy_ai(scan_ai); return err; out_vidh: ubi_free_vid_buf(scan_ai->vidb); out_ech: kfree(scan_ai->ech); out_ai: destroy_ai(scan_ai); out: return err; } #endif /** * ubi_attach - attach an MTD device. * @ubi: UBI device descriptor * @force_scan: if set to non-zero attach by scanning * * This function returns zero in case of success and a negative error code in * case of failure. */ int ubi_attach(struct ubi_device *ubi, int force_scan) { int err; struct ubi_attach_info *ai; ai = alloc_ai(); if (!ai) return -ENOMEM; #ifdef CONFIG_MTD_UBI_FASTMAP /* On small flash devices we disable fastmap in any case. */ if ((int)mtd_div_by_eb(ubi->mtd->size, ubi->mtd) <= UBI_FM_MAX_START) { ubi->fm_disabled = 1; force_scan = 1; } if (force_scan) err = scan_all(ubi, ai, 0); else { err = scan_fast(ubi, &ai); if (err > 0 || mtd_is_eccerr(err)) { if (err != UBI_NO_FASTMAP) { destroy_ai(ai); ai = alloc_ai(); if (!ai) return -ENOMEM; err = scan_all(ubi, ai, 0); } else { err = scan_all(ubi, ai, UBI_FM_MAX_START); } } } #else err = scan_all(ubi, ai, 0); #endif if (err) goto out_ai; ubi->bad_peb_count = ai->bad_peb_count; ubi->good_peb_count = ubi->peb_count - ubi->bad_peb_count; ubi->corr_peb_count = ai->corr_peb_count; ubi->max_ec = ai->max_ec; ubi->mean_ec = ai->mean_ec; dbg_gen("max. sequence number: %llu", ai->max_sqnum); err = ubi_read_volume_table(ubi, ai); if (err) goto out_ai; err = ubi_wl_init(ubi, ai); if (err) goto out_vtbl; err = ubi_eba_init(ubi, ai); if (err) goto out_wl; #ifdef CONFIG_MTD_UBI_FASTMAP if (ubi->fm && ubi_dbg_chk_fastmap(ubi)) { struct ubi_attach_info *scan_ai; scan_ai = alloc_ai(); if (!scan_ai) { err = -ENOMEM; goto out_wl; } err = scan_all(ubi, scan_ai, 0); if (err) { destroy_ai(scan_ai); goto out_wl; } err = self_check_eba(ubi, ai, scan_ai); destroy_ai(scan_ai); if (err) goto out_wl; } #endif destroy_ai(ai); return 0; out_wl: ubi_wl_close(ubi); out_vtbl: ubi_free_all_volumes(ubi); vfree(ubi->vtbl); out_ai: destroy_ai(ai); return err; } /** * self_check_ai - check the attaching information. * @ubi: UBI device description object * @ai: attaching information * * This function returns zero if the attaching information is all right, and a * negative error code if not or if an error occurred. */ static int self_check_ai(struct ubi_device *ubi, struct ubi_attach_info *ai) { struct ubi_vid_io_buf *vidb = ai->vidb; struct ubi_vid_hdr *vidh = ubi_get_vid_hdr(vidb); int pnum, err, vols_found = 0; struct rb_node *rb1, *rb2; struct ubi_ainf_volume *av; struct ubi_ainf_peb *aeb, *last_aeb; uint8_t *buf; if (!ubi_dbg_chk_gen(ubi)) return 0; /* * At first, check that attaching information is OK. */ ubi_rb_for_each_entry(rb1, av, &ai->volumes, rb) { int leb_count = 0; cond_resched(); vols_found += 1; if (ai->is_empty) { ubi_err(ubi, "bad is_empty flag"); goto bad_av; } if (av->vol_id < 0 || av->highest_lnum < 0 || av->leb_count < 0 || av->vol_type < 0 || av->used_ebs < 0 || av->data_pad < 0 || av->last_data_size < 0) { ubi_err(ubi, "negative values"); goto bad_av; } if (av->vol_id >= UBI_MAX_VOLUMES && av->vol_id < UBI_INTERNAL_VOL_START) { ubi_err(ubi, "bad vol_id"); goto bad_av; } if (av->vol_id > ai->highest_vol_id) { ubi_err(ubi, "highest_vol_id is %d, but vol_id %d is there", ai->highest_vol_id, av->vol_id); goto out; } if (av->vol_type != UBI_DYNAMIC_VOLUME && av->vol_type != UBI_STATIC_VOLUME) { ubi_err(ubi, "bad vol_type"); goto bad_av; } if (av->data_pad > ubi->leb_size / 2) { ubi_err(ubi, "bad data_pad"); goto bad_av; } last_aeb = NULL; ubi_rb_for_each_entry(rb2, aeb, &av->root, u.rb) { cond_resched(); last_aeb = aeb; leb_count += 1; if (aeb->pnum < 0 || aeb->ec < 0) { ubi_err(ubi, "negative values"); goto bad_aeb; } if (aeb->ec < ai->min_ec) { ubi_err(ubi, "bad ai->min_ec (%d), %d found", ai->min_ec, aeb->ec); goto bad_aeb; } if (aeb->ec > ai->max_ec) { ubi_err(ubi, "bad ai->max_ec (%d), %d found", ai->max_ec, aeb->ec); goto bad_aeb; } if (aeb->pnum >= ubi->peb_count) { ubi_err(ubi, "too high PEB number %d, total PEBs %d", aeb->pnum, ubi->peb_count); goto bad_aeb; } if (av->vol_type == UBI_STATIC_VOLUME) { if (aeb->lnum >= av->used_ebs) { ubi_err(ubi, "bad lnum or used_ebs"); goto bad_aeb; } } else { if (av->used_ebs != 0) { ubi_err(ubi, "non-zero used_ebs"); goto bad_aeb; } } if (aeb->lnum > av->highest_lnum) { ubi_err(ubi, "incorrect highest_lnum or lnum"); goto bad_aeb; } } if (av->leb_count != leb_count) { ubi_err(ubi, "bad leb_count, %d objects in the tree", leb_count); goto bad_av; } if (!last_aeb) continue; aeb = last_aeb; if (aeb->lnum != av->highest_lnum) { ubi_err(ubi, "bad highest_lnum"); goto bad_aeb; } } if (vols_found != ai->vols_found) { ubi_err(ubi, "bad ai->vols_found %d, should be %d", ai->vols_found, vols_found); goto out; } /* Check that attaching information is correct */ ubi_rb_for_each_entry(rb1, av, &ai->volumes, rb) { last_aeb = NULL; ubi_rb_for_each_entry(rb2, aeb, &av->root, u.rb) { int vol_type; cond_resched(); last_aeb = aeb; err = ubi_io_read_vid_hdr(ubi, aeb->pnum, vidb, 1); if (err && err != UBI_IO_BITFLIPS) { ubi_err(ubi, "VID header is not OK (%d)", err); if (err > 0) err = -EIO; return err; } vol_type = vidh->vol_type == UBI_VID_DYNAMIC ? UBI_DYNAMIC_VOLUME : UBI_STATIC_VOLUME; if (av->vol_type != vol_type) { ubi_err(ubi, "bad vol_type"); goto bad_vid_hdr; } if (aeb->sqnum != be64_to_cpu(vidh->sqnum)) { ubi_err(ubi, "bad sqnum %llu", aeb->sqnum); goto bad_vid_hdr; } if (av->vol_id != be32_to_cpu(vidh->vol_id)) { ubi_err(ubi, "bad vol_id %d", av->vol_id); goto bad_vid_hdr; } if (av->compat != vidh->compat) { ubi_err(ubi, "bad compat %d", vidh->compat); goto bad_vid_hdr; } if (aeb->lnum != be32_to_cpu(vidh->lnum)) { ubi_err(ubi, "bad lnum %d", aeb->lnum); goto bad_vid_hdr; } if (av->used_ebs != be32_to_cpu(vidh->used_ebs)) { ubi_err(ubi, "bad used_ebs %d", av->used_ebs); goto bad_vid_hdr; } if (av->data_pad != be32_to_cpu(vidh->data_pad)) { ubi_err(ubi, "bad data_pad %d", av->data_pad); goto bad_vid_hdr; } } if (!last_aeb) continue; if (av->highest_lnum != be32_to_cpu(vidh->lnum)) { ubi_err(ubi, "bad highest_lnum %d", av->highest_lnum); goto bad_vid_hdr; } if (av->last_data_size != be32_to_cpu(vidh->data_size)) { ubi_err(ubi, "bad last_data_size %d", av->last_data_size); goto bad_vid_hdr; } } /* * Make sure that all the physical eraseblocks are in one of the lists * or trees. */ buf = kzalloc(ubi->peb_count, GFP_KERNEL); if (!buf) return -ENOMEM; for (pnum = 0; pnum < ubi->peb_count; pnum++) { err = ubi_io_is_bad(ubi, pnum); if (err < 0) { kfree(buf); return err; } else if (err) buf[pnum] = 1; } ubi_rb_for_each_entry(rb1, av, &ai->volumes, rb) ubi_rb_for_each_entry(rb2, aeb, &av->root, u.rb) buf[aeb->pnum] = 1; list_for_each_entry(aeb, &ai->free, u.list) buf[aeb->pnum] = 1; list_for_each_entry(aeb, &ai->corr, u.list) buf[aeb->pnum] = 1; list_for_each_entry(aeb, &ai->erase, u.list) buf[aeb->pnum] = 1; list_for_each_entry(aeb, &ai->alien, u.list) buf[aeb->pnum] = 1; err = 0; for (pnum = 0; pnum < ubi->peb_count; pnum++) if (!buf[pnum]) { ubi_err(ubi, "PEB %d is not referred", pnum); err = 1; } kfree(buf); if (err) goto out; return 0; bad_aeb: ubi_err(ubi, "bad attaching information about LEB %d", aeb->lnum); ubi_dump_aeb(aeb, 0); ubi_dump_av(av); goto out; bad_av: ubi_err(ubi, "bad attaching information about volume %d", av->vol_id); ubi_dump_av(av); goto out; bad_vid_hdr: ubi_err(ubi, "bad attaching information about volume %d", av->vol_id); ubi_dump_av(av); ubi_dump_vid_hdr(vidh); out: dump_stack(); return -EINVAL; } |
| 14 1 13 4 2 11 7 1 6 5 3 1 4 2 1 14 5 4 1 5 2 1 9 4 1 9 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 | // SPDX-License-Identifier: GPL-2.0-only /* Kernel module to match L2TP header parameters. */ /* (C) 2013 James Chapman <jchapman@katalix.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/if_ether.h> #include <net/ip.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include <net/udp.h> #include <linux/l2tp.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_tcpudp.h> #include <linux/netfilter/xt_l2tp.h> /* L2TP header masks */ #define L2TP_HDR_T_BIT 0x8000 #define L2TP_HDR_L_BIT 0x4000 #define L2TP_HDR_VER 0x000f MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("Xtables: L2TP header match"); MODULE_ALIAS("ipt_l2tp"); MODULE_ALIAS("ip6t_l2tp"); /* The L2TP fields that can be matched */ struct l2tp_data { u32 tid; u32 sid; u8 type; u8 version; }; union l2tp_val { __be16 val16[2]; __be32 val32; }; static bool l2tp_match(const struct xt_l2tp_info *info, struct l2tp_data *data) { if ((info->flags & XT_L2TP_TYPE) && (info->type != data->type)) return false; if ((info->flags & XT_L2TP_VERSION) && (info->version != data->version)) return false; /* Check tid only for L2TPv3 control or any L2TPv2 packets */ if ((info->flags & XT_L2TP_TID) && ((data->type == XT_L2TP_TYPE_CONTROL) || (data->version == 2)) && (info->tid != data->tid)) return false; /* Check sid only for L2TP data packets */ if ((info->flags & XT_L2TP_SID) && (data->type == XT_L2TP_TYPE_DATA) && (info->sid != data->sid)) return false; return true; } /* Parse L2TP header fields when UDP encapsulation is used. Handles * L2TPv2 and L2TPv3. Note the L2TPv3 control and data packets have a * different format. See * RFC2661, Section 3.1, L2TPv2 Header Format * RFC3931, Section 3.2.1, L2TPv3 Control Message Header * RFC3931, Section 3.2.2, L2TPv3 Data Message Header * RFC3931, Section 4.1.2.1, L2TPv3 Session Header over UDP */ static bool l2tp_udp_mt(const struct sk_buff *skb, struct xt_action_param *par, u16 thoff) { const struct xt_l2tp_info *info = par->matchinfo; int uhlen = sizeof(struct udphdr); int offs = thoff + uhlen; union l2tp_val *lh; union l2tp_val lhbuf; u16 flags; struct l2tp_data data = { 0, }; if (par->fragoff != 0) return false; /* Extract L2TP header fields. The flags in the first 16 bits * tell us where the other fields are. */ lh = skb_header_pointer(skb, offs, 2, &lhbuf); if (lh == NULL) return false; flags = ntohs(lh->val16[0]); if (flags & L2TP_HDR_T_BIT) data.type = XT_L2TP_TYPE_CONTROL; else data.type = XT_L2TP_TYPE_DATA; data.version = (u8) flags & L2TP_HDR_VER; /* Now extract the L2TP tid/sid. These are in different places * for L2TPv2 (rfc2661) and L2TPv3 (rfc3931). For L2TPv2, we * must also check to see if the length field is present, * since this affects the offsets into the packet of the * tid/sid fields. */ if (data.version == 3) { lh = skb_header_pointer(skb, offs + 4, 4, &lhbuf); if (lh == NULL) return false; if (data.type == XT_L2TP_TYPE_CONTROL) data.tid = ntohl(lh->val32); else data.sid = ntohl(lh->val32); } else if (data.version == 2) { if (flags & L2TP_HDR_L_BIT) offs += 2; lh = skb_header_pointer(skb, offs + 2, 4, &lhbuf); if (lh == NULL) return false; data.tid = (u32) ntohs(lh->val16[0]); data.sid = (u32) ntohs(lh->val16[1]); } else return false; return l2tp_match(info, &data); } /* Parse L2TP header fields for IP encapsulation (no UDP header). * L2TPv3 data packets have a different form with IP encap. See * RC3931, Section 4.1.1.1, L2TPv3 Session Header over IP. * RC3931, Section 4.1.1.2, L2TPv3 Control and Data Traffic over IP. */ static bool l2tp_ip_mt(const struct sk_buff *skb, struct xt_action_param *par, u16 thoff) { const struct xt_l2tp_info *info = par->matchinfo; union l2tp_val *lh; union l2tp_val lhbuf; struct l2tp_data data = { 0, }; /* For IP encap, the L2TP sid is the first 32-bits. */ lh = skb_header_pointer(skb, thoff, sizeof(lhbuf), &lhbuf); if (lh == NULL) return false; if (lh->val32 == 0) { /* Must be a control packet. The L2TP tid is further * into the packet. */ data.type = XT_L2TP_TYPE_CONTROL; lh = skb_header_pointer(skb, thoff + 8, sizeof(lhbuf), &lhbuf); if (lh == NULL) return false; data.tid = ntohl(lh->val32); } else { data.sid = ntohl(lh->val32); data.type = XT_L2TP_TYPE_DATA; } data.version = 3; return l2tp_match(info, &data); } static bool l2tp_mt4(const struct sk_buff *skb, struct xt_action_param *par) { struct iphdr *iph = ip_hdr(skb); u8 ipproto = iph->protocol; /* l2tp_mt_check4 already restricts the transport protocol */ switch (ipproto) { case IPPROTO_UDP: return l2tp_udp_mt(skb, par, par->thoff); case IPPROTO_L2TP: return l2tp_ip_mt(skb, par, par->thoff); } return false; } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static bool l2tp_mt6(const struct sk_buff *skb, struct xt_action_param *par) { unsigned int thoff = 0; unsigned short fragoff = 0; int ipproto; ipproto = ipv6_find_hdr(skb, &thoff, -1, &fragoff, NULL); if (fragoff != 0) return false; /* l2tp_mt_check6 already restricts the transport protocol */ switch (ipproto) { case IPPROTO_UDP: return l2tp_udp_mt(skb, par, thoff); case IPPROTO_L2TP: return l2tp_ip_mt(skb, par, thoff); } return false; } #endif static int l2tp_mt_check(const struct xt_mtchk_param *par) { const struct xt_l2tp_info *info = par->matchinfo; /* Check for invalid flags */ if (info->flags & ~(XT_L2TP_TID | XT_L2TP_SID | XT_L2TP_VERSION | XT_L2TP_TYPE)) { pr_info_ratelimited("unknown flags: %x\n", info->flags); return -EINVAL; } /* At least one of tid, sid or type=control must be specified */ if ((!(info->flags & XT_L2TP_TID)) && (!(info->flags & XT_L2TP_SID)) && ((!(info->flags & XT_L2TP_TYPE)) || (info->type != XT_L2TP_TYPE_CONTROL))) { pr_info_ratelimited("invalid flags combination: %x\n", info->flags); return -EINVAL; } /* If version 2 is specified, check that incompatible params * are not supplied */ if (info->flags & XT_L2TP_VERSION) { if ((info->version < 2) || (info->version > 3)) { pr_info_ratelimited("wrong L2TP version: %u\n", info->version); return -EINVAL; } if (info->version == 2) { if ((info->flags & XT_L2TP_TID) && (info->tid > 0xffff)) { pr_info_ratelimited("v2 tid > 0xffff: %u\n", info->tid); return -EINVAL; } if ((info->flags & XT_L2TP_SID) && (info->sid > 0xffff)) { pr_info_ratelimited("v2 sid > 0xffff: %u\n", info->sid); return -EINVAL; } } } return 0; } static int l2tp_mt_check4(const struct xt_mtchk_param *par) { const struct xt_l2tp_info *info = par->matchinfo; const struct ipt_entry *e = par->entryinfo; const struct ipt_ip *ip = &e->ip; int ret; ret = l2tp_mt_check(par); if (ret != 0) return ret; if ((ip->proto != IPPROTO_UDP) && (ip->proto != IPPROTO_L2TP)) { pr_info_ratelimited("missing protocol rule (udp|l2tpip)\n"); return -EINVAL; } if ((ip->proto == IPPROTO_L2TP) && (info->version == 2)) { pr_info_ratelimited("v2 doesn't support IP mode\n"); return -EINVAL; } return 0; } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static int l2tp_mt_check6(const struct xt_mtchk_param *par) { const struct xt_l2tp_info *info = par->matchinfo; const struct ip6t_entry *e = par->entryinfo; const struct ip6t_ip6 *ip = &e->ipv6; int ret; ret = l2tp_mt_check(par); if (ret != 0) return ret; if ((ip->proto != IPPROTO_UDP) && (ip->proto != IPPROTO_L2TP)) { pr_info_ratelimited("missing protocol rule (udp|l2tpip)\n"); return -EINVAL; } if ((ip->proto == IPPROTO_L2TP) && (info->version == 2)) { pr_info_ratelimited("v2 doesn't support IP mode\n"); return -EINVAL; } return 0; } #endif static struct xt_match l2tp_mt_reg[] __read_mostly = { { .name = "l2tp", .revision = 0, .family = NFPROTO_IPV4, .match = l2tp_mt4, .matchsize = XT_ALIGN(sizeof(struct xt_l2tp_info)), .checkentry = l2tp_mt_check4, .hooks = ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD)), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "l2tp", .revision = 0, .family = NFPROTO_IPV6, .match = l2tp_mt6, .matchsize = XT_ALIGN(sizeof(struct xt_l2tp_info)), .checkentry = l2tp_mt_check6, .hooks = ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD)), .me = THIS_MODULE, }, #endif }; static int __init l2tp_mt_init(void) { return xt_register_matches(&l2tp_mt_reg[0], ARRAY_SIZE(l2tp_mt_reg)); } static void __exit l2tp_mt_exit(void) { xt_unregister_matches(&l2tp_mt_reg[0], ARRAY_SIZE(l2tp_mt_reg)); } module_init(l2tp_mt_init); module_exit(l2tp_mt_exit); |
| 4 2 57 9 48 36 2 171 173 141 11 24 9 34 9 23 15 12 11 12 23 10 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 | /* SPDX-License-Identifier: GPL-1.0+ */ /* * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. * * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes * NCM: Network and Communications Management, Inc. * * BUT, I'm the one who modified it for ethernet, so: * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov * */ #ifndef _NET_BONDING_H #define _NET_BONDING_H #include <linux/timer.h> #include <linux/proc_fs.h> #include <linux/if_bonding.h> #include <linux/cpumask.h> #include <linux/in6.h> #include <linux/netpoll.h> #include <linux/inetdevice.h> #include <linux/etherdevice.h> #include <linux/reciprocal_div.h> #include <linux/if_link.h> #include <net/bond_3ad.h> #include <net/bond_alb.h> #include <net/bond_options.h> #include <net/ipv6.h> #include <net/addrconf.h> #define BOND_MAX_ARP_TARGETS 16 #define BOND_MAX_NS_TARGETS BOND_MAX_ARP_TARGETS #define BOND_DEFAULT_MIIMON 100 #ifndef __long_aligned #define __long_aligned __attribute__((aligned((sizeof(long))))) #endif #define slave_info(bond_dev, slave_dev, fmt, ...) \ netdev_info(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_warn(bond_dev, slave_dev, fmt, ...) \ netdev_warn(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_dbg(bond_dev, slave_dev, fmt, ...) \ netdev_dbg(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_err(bond_dev, slave_dev, fmt, ...) \ netdev_err(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define BOND_MODE(bond) ((bond)->params.mode) /* slave list primitives */ #define bond_slave_list(bond) (&(bond)->dev->adj_list.lower) #define bond_has_slaves(bond) !list_empty(bond_slave_list(bond)) /* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ #define bond_first_slave(bond) \ (bond_has_slaves(bond) ? \ netdev_adjacent_get_private(bond_slave_list(bond)->next) : \ NULL) #define bond_last_slave(bond) \ (bond_has_slaves(bond) ? \ netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \ NULL) /* Caller must have rcu_read_lock */ #define bond_first_slave_rcu(bond) \ netdev_lower_get_first_private_rcu(bond->dev) #define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond)) #define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond)) /** * bond_for_each_slave - iterate over all slaves * @bond: the bond holding this list * @pos: current slave * @iter: list_head * iterator * * Caller must hold RTNL */ #define bond_for_each_slave(bond, pos, iter) \ netdev_for_each_lower_private((bond)->dev, pos, iter) /* Caller must have rcu_read_lock */ #define bond_for_each_slave_rcu(bond, pos, iter) \ netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; static inline void block_netpoll_tx(void) { atomic_inc(&netpoll_block_tx); } static inline void unblock_netpoll_tx(void) { atomic_dec(&netpoll_block_tx); } static inline int is_netpoll_tx_blocked(struct net_device *dev) { if (unlikely(netpoll_tx_running(dev))) return atomic_read(&netpoll_block_tx); return 0; } #else #define block_netpoll_tx() #define unblock_netpoll_tx() #define is_netpoll_tx_blocked(dev) (0) #endif struct bond_params { int mode; int xmit_policy; int miimon; u8 num_peer_notif; u8 missed_max; int arp_interval; int arp_validate; int arp_all_targets; int use_carrier; int fail_over_mac; int updelay; int downdelay; int peer_notif_delay; int lacp_active; int lacp_fast; unsigned int min_links; int ad_select; char primary[IFNAMSIZ]; int primary_reselect; __be32 arp_targets[BOND_MAX_ARP_TARGETS]; int tx_queues; int all_slaves_active; int resend_igmp; int lp_interval; int packets_per_slave; int tlb_dynamic_lb; struct reciprocal_value reciprocal_packets_per_slave; u16 ad_actor_sys_prio; u16 ad_user_port_key; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ns_targets[BOND_MAX_NS_TARGETS]; #endif /* 2 bytes of padding : see ether_addr_equal_64bits() */ u8 ad_actor_system[ETH_ALEN + 2]; }; struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ int delay; /* all 4 in jiffies */ unsigned long last_link_up; unsigned long last_tx; unsigned long last_rx; unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ s8 link_new_state; /* one of BOND_LINK_XXXX */ u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ inactive:1, /* indicates inactive slave */ should_notify:1, /* indicates whether the state changed */ should_notify_link:1; /* indicates whether the link changed */ u8 duplex; u32 original_mtu; u32 link_failure_count; u32 speed; u16 queue_id; u8 perm_hwaddr[MAX_ADDR_LEN]; int prio; struct ad_slave_info *ad_info; struct tlb_slave_info tlb_info; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *np; #endif struct delayed_work notify_work; struct kobject kobj; struct rtnl_link_stats64 slave_stats; }; static inline struct slave *to_slave(struct kobject *kobj) { return container_of(kobj, struct slave, kobj); } struct bond_up_slave { unsigned int count; struct rcu_head rcu; struct slave *arr[]; }; /* * Link pseudo-state only used internally by monitors */ #define BOND_LINK_NOCHANGE -1 struct bond_ipsec { struct list_head list; struct xfrm_state *xs; }; /* * Here are the locking policies for the two bonding locks: * Get rcu_read_lock when reading or RTNL when writing slave list. */ struct bonding { struct net_device *dev; /* first - useful for panic debug */ struct slave __rcu *curr_active_slave; struct slave __rcu *current_arp_slave; struct slave __rcu *primary_slave; struct bond_up_slave __rcu *usable_slaves; struct bond_up_slave __rcu *all_slaves; bool force_primary; bool notifier_ctx; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); /* mode_lock is used for mode-specific locking needs, currently used by: * 3ad mode (4) - protect against running bond_3ad_unbind_slave() and * bond_3ad_state_machine_handler() concurrently and also * the access to the state machine shared variables. * TLB mode (5) - to sync the use and modifications of its hash table * ALB mode (6) - to sync the use and modifications of its hash table */ spinlock_t mode_lock; spinlock_t stats_lock; u32 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; char proc_file_name[IFNAMSIZ]; #endif /* CONFIG_PROC_FS */ struct list_head bond_list; u32 __percpu *rr_tx_counter; struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params; struct workqueue_struct *wq; struct delayed_work mii_work; struct delayed_work arp_work; struct delayed_work alb_work; struct delayed_work ad_work; struct delayed_work mcast_work; struct delayed_work slave_arr_work; #ifdef CONFIG_DEBUG_FS /* debugging support via debugfs */ struct dentry *debug_dir; #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; #ifdef CONFIG_XFRM_OFFLOAD struct list_head ipsec_list; /* protecting ipsec_list */ spinlock_t ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ struct bpf_prog *xdp_prog; }; #define bond_slave_get_rcu(dev) \ ((struct slave *) rcu_dereference(dev->rx_handler_data)) #define bond_slave_get_rtnl(dev) \ ((struct slave *) rtnl_dereference(dev->rx_handler_data)) void bond_queue_slave_event(struct slave *slave); void bond_lower_state_changed(struct slave *slave); struct bond_vlan_tag { __be16 vlan_proto; unsigned short vlan_id; }; /* * Returns NULL if the net_device does not belong to any of the bond's slaves * * Caller must hold bond lock for read */ static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, struct net_device *slave_dev) { return netdev_lower_dev_get_private(bond->dev, slave_dev); } static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) { return slave->bond; } static inline bool bond_should_override_tx_queue(struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || BOND_MODE(bond) == BOND_MODE_ROUNDROBIN; } static inline bool bond_is_lb(const struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_TLB || BOND_MODE(bond) == BOND_MODE_ALB; } static inline bool bond_needs_speed_duplex(const struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_8023AD || bond_is_lb(bond); } static inline bool bond_is_nondyn_tlb(const struct bonding *bond) { return (bond_is_lb(bond) && bond->params.tlb_dynamic_lb == 0); } static inline bool bond_mode_can_use_xmit_hash(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_8023AD || BOND_MODE(bond) == BOND_MODE_XOR || BOND_MODE(bond) == BOND_MODE_TLB || BOND_MODE(bond) == BOND_MODE_ALB); } static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_8023AD || BOND_MODE(bond) == BOND_MODE_XOR || bond_is_nondyn_tlb(bond)); } static inline bool bond_mode_uses_arp(int mode) { return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB && mode != BOND_MODE_ALB; } static inline bool bond_mode_uses_primary(int mode) { return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB || mode == BOND_MODE_ALB; } static inline bool bond_uses_primary(struct bonding *bond) { return bond_mode_uses_primary(BOND_MODE(bond)); } static inline struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond) { struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); return bond_uses_primary(bond) && slave ? slave->dev : NULL; } static inline bool bond_slave_is_up(struct slave *slave) { return netif_running(slave->dev) && netif_carrier_ok(slave->dev); } static inline void bond_set_active_slave(struct slave *slave) { if (slave->backup) { slave->backup = 0; bond_queue_slave_event(slave); bond_lower_state_changed(slave); } } static inline void bond_set_backup_slave(struct slave *slave) { if (!slave->backup) { slave->backup = 1; bond_queue_slave_event(slave); bond_lower_state_changed(slave); } } static inline void bond_set_slave_state(struct slave *slave, int slave_state, bool notify) { if (slave->backup == slave_state) return; slave->backup = slave_state; if (notify) { bond_lower_state_changed(slave); bond_queue_slave_event(slave); slave->should_notify = 0; } else { if (slave->should_notify) slave->should_notify = 0; else slave->should_notify = 1; } } static inline void bond_slave_state_change(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->link == BOND_LINK_UP) bond_set_active_slave(tmp); else if (tmp->link == BOND_LINK_DOWN) bond_set_backup_slave(tmp); } } static inline void bond_slave_state_notify(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify) { bond_lower_state_changed(tmp); tmp->should_notify = 0; } } } static inline int bond_slave_state(struct slave *slave) { return slave->backup; } static inline bool bond_is_active_slave(struct slave *slave) { return !bond_slave_state(slave); } static inline bool bond_slave_can_tx(struct slave *slave) { return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP && bond_is_active_slave(slave); } static inline bool bond_is_active_slave_dev(const struct net_device *slave_dev) { struct slave *slave; bool active; rcu_read_lock(); slave = bond_slave_get_rcu(slave_dev); active = bond_is_active_slave(slave); rcu_read_unlock(); return active; } static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len) { if (len == ETH_ALEN) { ether_addr_copy(dst, src); return; } memcpy(dst, src, len); } #define BOND_PRI_RESELECT_ALWAYS 0 #define BOND_PRI_RESELECT_BETTER 1 #define BOND_PRI_RESELECT_FAILURE 2 #define BOND_FOM_NONE 0 #define BOND_FOM_ACTIVE 1 #define BOND_FOM_FOLLOW 2 #define BOND_ARP_TARGETS_ANY 0 #define BOND_ARP_TARGETS_ALL 1 #define BOND_ARP_VALIDATE_NONE 0 #define BOND_ARP_VALIDATE_ACTIVE (1 << BOND_STATE_ACTIVE) #define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP) #define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_VALIDATE_BACKUP) #define BOND_ARP_FILTER (BOND_ARP_VALIDATE_ALL + 1) #define BOND_ARP_FILTER_ACTIVE (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_FILTER) #define BOND_ARP_FILTER_BACKUP (BOND_ARP_VALIDATE_BACKUP | \ BOND_ARP_FILTER) #define BOND_SLAVE_NOTIFY_NOW true #define BOND_SLAVE_NOTIFY_LATER false static inline int slave_do_arp_validate(struct bonding *bond, struct slave *slave) { return bond->params.arp_validate & (1 << bond_slave_state(slave)); } static inline int slave_do_arp_validate_only(struct bonding *bond) { return bond->params.arp_validate & BOND_ARP_FILTER; } static inline int bond_is_ip_target_ok(__be32 addr) { return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); } #if IS_ENABLED(CONFIG_IPV6) static inline int bond_is_ip6_target_ok(struct in6_addr *addr) { return !ipv6_addr_any(addr) && !ipv6_addr_loopback(addr) && !ipv6_addr_is_multicast(addr); } #endif /* Get the oldest arp which we've received on this slave for bond's * arp_targets. */ static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, struct slave *slave) { int i = 1; unsigned long ret = slave->target_last_arp_rx[0]; for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) if (time_before(slave->target_last_arp_rx[i], ret)) ret = slave->target_last_arp_rx[i]; return ret; } static inline unsigned long slave_last_rx(struct bonding *bond, struct slave *slave) { if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) return slave_oldest_target_arp_rx(bond, slave); return slave->last_rx; } static inline void slave_update_last_tx(struct slave *slave) { WRITE_ONCE(slave->last_tx, jiffies); } static inline unsigned long slave_last_tx(struct slave *slave) { return READ_ONCE(slave->last_tx); } #ifdef CONFIG_NET_POLL_CONTROLLER static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { return netpoll_send_skb(slave->np, skb); } #else static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { BUG(); return NETDEV_TX_OK; } #endif static inline void bond_set_slave_inactive_flags(struct slave *slave, bool notify) { if (!bond_is_lb(slave->bond)) bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); if (!slave->bond->params.all_slaves_active) slave->inactive = 1; } static inline void bond_set_slave_active_flags(struct slave *slave, bool notify) { bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); slave->inactive = 0; } static inline bool bond_is_slave_inactive(struct slave *slave) { return slave->inactive; } static inline void bond_propose_link_state(struct slave *slave, int state) { slave->link_new_state = state; } static inline void bond_commit_link_state(struct slave *slave, bool notify) { if (slave->link_new_state == BOND_LINK_NOCHANGE) return; slave->link = slave->link_new_state; if (notify) { bond_queue_slave_event(slave); bond_lower_state_changed(slave); slave->should_notify_link = 0; } else { if (slave->should_notify_link) slave->should_notify_link = 0; else slave->should_notify_link = 1; } } static inline void bond_set_slave_link_state(struct slave *slave, int state, bool notify) { bond_propose_link_state(slave, state); bond_commit_link_state(slave, notify); } static inline void bond_slave_link_notify(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify_link) { bond_queue_slave_event(tmp); bond_lower_state_changed(tmp); tmp->should_notify_link = 0; } } } static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local) { struct in_device *in_dev; __be32 addr = 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local, RT_SCOPE_HOST); rcu_read_unlock(); return addr; } struct bond_net { struct net *net; /* Associated network namespace */ struct list_head dev_list; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_dir; #endif struct class_attribute class_attr_bonding_masters; }; int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); int bond_create(struct net *net, const char *name); int bond_create_sysfs(struct bond_net *net); void bond_destroy_sysfs(struct bond_net *net); void bond_prepare_sysfs_group(struct bonding *bond); int bond_sysfs_slave_add(struct slave *slave); void bond_sysfs_slave_del(struct slave *slave); void bond_xdp_set_features(struct net_device *bond_dev); int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb); int bond_set_carrier(struct bonding *bond); void bond_select_active_slave(struct bonding *bond); void bond_change_active_slave(struct bonding *bond, struct slave *new_active); void bond_create_debugfs(void); void bond_destroy_debugfs(void); void bond_debug_register(struct bonding *bond); void bond_debug_unregister(struct bonding *bond); void bond_debug_reregister(struct bonding *bond); const char *bond_mode_name(int mode); void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); int bond_netlink_init(void); void bond_netlink_fini(void); struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond); const char *bond_slave_link_status(s8 link); struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, struct net_device *end_dev, int level); int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave); void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay); void bond_work_init_all(struct bonding *bond); #ifdef CONFIG_PROC_FS void bond_create_proc_entry(struct bonding *bond); void bond_remove_proc_entry(struct bonding *bond); void bond_create_proc_dir(struct bond_net *bn); void bond_destroy_proc_dir(struct bond_net *bn); #else static inline void bond_create_proc_entry(struct bonding *bond) { } static inline void bond_remove_proc_entry(struct bonding *bond) { } static inline void bond_create_proc_dir(struct bond_net *bn) { } static inline void bond_destroy_proc_dir(struct bond_net *bn) { } #endif static inline struct slave *bond_slave_has_mac(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return tmp; return NULL; } /* Caller must hold rcu_read_lock() for read */ static inline bool bond_slave_has_mac_rcu(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; bond_for_each_slave_rcu(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return true; return false; } /* Check if the ip is present in arp ip list, or first free slot if ip == 0 * Returns -1 if not found, index if found */ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) { int i; for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) if (targets[i] == ip) return i; else if (targets[i] == 0) break; return -1; } #if IS_ENABLED(CONFIG_IPV6) static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) { struct in6_addr mcaddr; int i; for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { addrconf_addr_solict_mult(&targets[i], &mcaddr); if ((ipv6_addr_equal(&targets[i], ip)) || (ipv6_addr_equal(&mcaddr, ip))) return i; else if (ipv6_addr_any(&targets[i])) break; } return -1; } #endif /* exported from bond_main.c */ extern unsigned int bond_net_id; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; /* exported from bond_sysfs_slave.c */ extern const struct sysfs_ops slave_sysfs_ops; /* exported from bond_3ad.c */ extern const u8 lacpdu_mcast_addr[]; static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); return NET_XMIT_DROP; } #endif /* _NET_BONDING_H */ |
| 56 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_CRASH_DUMP_H #define LINUX_CRASH_DUMP_H #include <linux/kexec.h> #include <linux/proc_fs.h> #include <linux/elf.h> #include <linux/pgtable.h> #include <uapi/linux/vmcore.h> /* For IS_ENABLED(CONFIG_CRASH_DUMP) */ #define ELFCORE_ADDR_MAX (-1ULL) #define ELFCORE_ADDR_ERR (-2ULL) extern unsigned long long elfcorehdr_addr; extern unsigned long long elfcorehdr_size; #ifdef CONFIG_CRASH_DUMP extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size); extern void elfcorehdr_free(unsigned long long addr); extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos); extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot); ssize_t copy_oldmem_page(struct iov_iter *i, unsigned long pfn, size_t csize, unsigned long offset); ssize_t copy_oldmem_page_encrypted(struct iov_iter *iter, unsigned long pfn, size_t csize, unsigned long offset); void vmcore_cleanup(void); /* Architecture code defines this if there are other possible ELF * machine types, e.g. on bi-arch capable hardware. */ #ifndef vmcore_elf_check_arch_cross #define vmcore_elf_check_arch_cross(x) 0 #endif /* * Architecture code can redefine this if there are any special checks * needed for 32-bit ELF or 64-bit ELF vmcores. In case of 32-bit * only architecture, vmcore_elf64_check_arch can be set to zero. */ #ifndef vmcore_elf32_check_arch #define vmcore_elf32_check_arch(x) elf_check_arch(x) #endif #ifndef vmcore_elf64_check_arch #define vmcore_elf64_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x)) #endif #ifndef is_kdump_kernel /* * is_kdump_kernel() checks whether this kernel is booting after a panic of * previous kernel or not. This is determined by checking if previous kernel * has passed the elf core header address on command line. * * This is not just a test if CONFIG_CRASH_DUMP is enabled or not. It will * return true if CONFIG_CRASH_DUMP=y and if kernel is booting after a panic * of previous kernel. */ static inline bool is_kdump_kernel(void) { return elfcorehdr_addr != ELFCORE_ADDR_MAX; } #endif /* is_vmcore_usable() checks if the kernel is booting after a panic and * the vmcore region is usable. * * This makes use of the fact that due to alignment -2ULL is not * a valid pointer, much in the vain of IS_ERR(), except * dealing directly with an unsigned long long rather than a pointer. */ static inline int is_vmcore_usable(void) { return elfcorehdr_addr != ELFCORE_ADDR_ERR && elfcorehdr_addr != ELFCORE_ADDR_MAX ? 1 : 0; } /* vmcore_unusable() marks the vmcore as unusable, * without disturbing the logic of is_kdump_kernel() */ static inline void vmcore_unusable(void) { elfcorehdr_addr = ELFCORE_ADDR_ERR; } /** * struct vmcore_cb - driver callbacks for /proc/vmcore handling * @pfn_is_ram: check whether a PFN really is RAM and should be accessed when * reading the vmcore. Will return "true" if it is RAM or if the * callback cannot tell. If any callback returns "false", it's not * RAM and the page must not be accessed; zeroes should be * indicated in the vmcore instead. For example, a ballooned page * contains no data and reading from such a page will cause high * load in the hypervisor. * @next: List head to manage registered callbacks internally; initialized by * register_vmcore_cb(). * * vmcore callbacks allow drivers managing physical memory ranges to * coordinate with vmcore handling code, for example, to prevent accessing * physical memory ranges that should not be accessed when reading the vmcore, * although included in the vmcore header as memory ranges to dump. */ struct vmcore_cb { bool (*pfn_is_ram)(struct vmcore_cb *cb, unsigned long pfn); struct list_head next; }; extern void register_vmcore_cb(struct vmcore_cb *cb); extern void unregister_vmcore_cb(struct vmcore_cb *cb); #else /* !CONFIG_CRASH_DUMP */ static inline bool is_kdump_kernel(void) { return false; } #endif /* CONFIG_CRASH_DUMP */ /* Device Dump information to be filled by drivers */ struct vmcoredd_data { char dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Unique name of the dump */ unsigned int size; /* Size of the dump */ /* Driver's registered callback to be invoked to collect dump */ int (*vmcoredd_callback)(struct vmcoredd_data *data, void *buf); }; #ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP int vmcore_add_device_dump(struct vmcoredd_data *data); #else static inline int vmcore_add_device_dump(struct vmcoredd_data *data) { return -EOPNOTSUPP; } #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ #ifdef CONFIG_PROC_VMCORE ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, u64 *ppos, bool encrypted); #else static inline ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, u64 *ppos, bool encrypted) { return -EOPNOTSUPP; } #endif /* CONFIG_PROC_VMCORE */ #endif /* LINUX_CRASHDUMP_H */ |
| 2 2 2 2 2 5 2 2 5 6 6 6 6 6 6 5 5 5 5 6 1 1 2 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Volume-level cache cookie handling. * * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define FSCACHE_DEBUG_LEVEL COOKIE #include <linux/export.h> #include <linux/slab.h> #include "internal.h" #define fscache_volume_hash_shift 10 static struct hlist_bl_head fscache_volume_hash[1 << fscache_volume_hash_shift]; static atomic_t fscache_volume_debug_id; static LIST_HEAD(fscache_volumes); static void fscache_create_volume_work(struct work_struct *work); struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, enum fscache_volume_trace where) { int ref; __refcount_inc(&volume->ref, &ref); trace_fscache_volume(volume->debug_id, ref + 1, where); return volume; } static void fscache_see_volume(struct fscache_volume *volume, enum fscache_volume_trace where) { int ref = refcount_read(&volume->ref); trace_fscache_volume(volume->debug_id, ref, where); } /* * Pin the cache behind a volume so that we can access it. */ static void __fscache_begin_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, enum fscache_access_trace why) { int n_accesses; n_accesses = atomic_inc_return(&volume->n_accesses); smp_mb__after_atomic(); trace_fscache_access_volume(volume->debug_id, cookie ? cookie->debug_id : 0, refcount_read(&volume->ref), n_accesses, why); } /** * fscache_begin_volume_access - Pin a cache so a volume can be accessed * @volume: The volume cookie * @cookie: A datafile cookie for a tracing reference (or NULL) * @why: An indication of the circumstances of the access for tracing * * Attempt to pin the cache to prevent it from going away whilst we're * accessing a volume and returns true if successful. This works as follows: * * (1) If the cache tests as not live (state is not FSCACHE_CACHE_IS_ACTIVE), * then we return false to indicate access was not permitted. * * (2) If the cache tests as live, then we increment the volume's n_accesses * count and then recheck the cache liveness, ending the access if it * ceased to be live. * * (3) When we end the access, we decrement the volume's n_accesses and wake * up the any waiters if it reaches 0. * * (4) Whilst the cache is caching, the volume's n_accesses is kept * artificially incremented to prevent wakeups from happening. * * (5) When the cache is taken offline, the state is changed to prevent new * accesses, the volume's n_accesses is decremented and we wait for it to * become 0. * * The datafile @cookie and the @why indicator are merely provided for tracing * purposes. */ bool fscache_begin_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, enum fscache_access_trace why) { if (!fscache_cache_is_live(volume->cache)) return false; __fscache_begin_volume_access(volume, cookie, why); if (!fscache_cache_is_live(volume->cache)) { fscache_end_volume_access(volume, cookie, fscache_access_unlive); return false; } return true; } /** * fscache_end_volume_access - Unpin a cache at the end of an access. * @volume: The volume cookie * @cookie: A datafile cookie for a tracing reference (or NULL) * @why: An indication of the circumstances of the access for tracing * * Unpin a cache volume after we've accessed it. The datafile @cookie and the * @why indicator are merely provided for tracing purposes. */ void fscache_end_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, enum fscache_access_trace why) { int n_accesses; smp_mb__before_atomic(); n_accesses = atomic_dec_return(&volume->n_accesses); trace_fscache_access_volume(volume->debug_id, cookie ? cookie->debug_id : 0, refcount_read(&volume->ref), n_accesses, why); if (n_accesses == 0) wake_up_var(&volume->n_accesses); } EXPORT_SYMBOL(fscache_end_volume_access); static bool fscache_volume_same(const struct fscache_volume *a, const struct fscache_volume *b) { size_t klen; if (a->key_hash != b->key_hash || a->cache != b->cache || a->key[0] != b->key[0]) return false; klen = round_up(a->key[0] + 1, sizeof(__le32)); return memcmp(a->key, b->key, klen) == 0; } static bool fscache_is_acquire_pending(struct fscache_volume *volume) { return test_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &volume->flags); } static void fscache_wait_on_volume_collision(struct fscache_volume *candidate, unsigned int collidee_debug_id) { wait_on_bit_timeout(&candidate->flags, FSCACHE_VOLUME_ACQUIRE_PENDING, TASK_UNINTERRUPTIBLE, 20 * HZ); if (fscache_is_acquire_pending(candidate)) { pr_notice("Potential volume collision new=%08x old=%08x", candidate->debug_id, collidee_debug_id); fscache_stat(&fscache_n_volumes_collision); wait_on_bit(&candidate->flags, FSCACHE_VOLUME_ACQUIRE_PENDING, TASK_UNINTERRUPTIBLE); } } /* * Attempt to insert the new volume into the hash. If there's a collision, we * wait for the old volume to complete if it's being relinquished and an error * otherwise. */ static bool fscache_hash_volume(struct fscache_volume *candidate) { struct fscache_volume *cursor; struct hlist_bl_head *h; struct hlist_bl_node *p; unsigned int bucket, collidee_debug_id = 0; bucket = candidate->key_hash & (ARRAY_SIZE(fscache_volume_hash) - 1); h = &fscache_volume_hash[bucket]; hlist_bl_lock(h); hlist_bl_for_each_entry(cursor, p, h, hash_link) { if (fscache_volume_same(candidate, cursor)) { if (!test_bit(FSCACHE_VOLUME_RELINQUISHED, &cursor->flags)) goto collision; fscache_see_volume(cursor, fscache_volume_get_hash_collision); set_bit(FSCACHE_VOLUME_COLLIDED_WITH, &cursor->flags); set_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &candidate->flags); collidee_debug_id = cursor->debug_id; break; } } hlist_bl_add_head(&candidate->hash_link, h); hlist_bl_unlock(h); if (fscache_is_acquire_pending(candidate)) fscache_wait_on_volume_collision(candidate, collidee_debug_id); return true; collision: fscache_see_volume(cursor, fscache_volume_collision); hlist_bl_unlock(h); return false; } /* * Allocate and initialise a volume representation cookie. */ static struct fscache_volume *fscache_alloc_volume(const char *volume_key, const char *cache_name, const void *coherency_data, size_t coherency_len) { struct fscache_volume *volume; struct fscache_cache *cache; size_t klen, hlen; u8 *key; klen = strlen(volume_key); if (klen > NAME_MAX) return NULL; if (!coherency_data) coherency_len = 0; cache = fscache_lookup_cache(cache_name, false); if (IS_ERR(cache)) return NULL; volume = kzalloc(struct_size(volume, coherency, coherency_len), GFP_KERNEL); if (!volume) goto err_cache; volume->cache = cache; volume->coherency_len = coherency_len; if (coherency_data) memcpy(volume->coherency, coherency_data, coherency_len); INIT_LIST_HEAD(&volume->proc_link); INIT_WORK(&volume->work, fscache_create_volume_work); refcount_set(&volume->ref, 1); spin_lock_init(&volume->lock); /* Stick the length on the front of the key and pad it out to make * hashing easier. */ hlen = round_up(1 + klen + 1, sizeof(__le32)); key = kzalloc(hlen, GFP_KERNEL); if (!key) goto err_vol; key[0] = klen; memcpy(key + 1, volume_key, klen); volume->key = key; volume->key_hash = fscache_hash(0, key, hlen); volume->debug_id = atomic_inc_return(&fscache_volume_debug_id); down_write(&fscache_addremove_sem); atomic_inc(&cache->n_volumes); list_add_tail(&volume->proc_link, &fscache_volumes); fscache_see_volume(volume, fscache_volume_new_acquire); fscache_stat(&fscache_n_volumes); up_write(&fscache_addremove_sem); _leave(" = v=%x", volume->debug_id); return volume; err_vol: kfree(volume); err_cache: fscache_put_cache(cache, fscache_cache_put_alloc_volume); fscache_stat(&fscache_n_volumes_nomem); return NULL; } /* * Create a volume's representation on disk. Have a volume ref and a cache * access we have to release. */ static void fscache_create_volume_work(struct work_struct *work) { const struct fscache_cache_ops *ops; struct fscache_volume *volume = container_of(work, struct fscache_volume, work); fscache_see_volume(volume, fscache_volume_see_create_work); ops = volume->cache->ops; if (ops->acquire_volume) ops->acquire_volume(volume); fscache_end_cache_access(volume->cache, fscache_access_acquire_volume_end); clear_and_wake_up_bit(FSCACHE_VOLUME_CREATING, &volume->flags); fscache_put_volume(volume, fscache_volume_put_create_work); } /* * Dispatch a worker thread to create a volume's representation on disk. */ void fscache_create_volume(struct fscache_volume *volume, bool wait) { if (test_and_set_bit(FSCACHE_VOLUME_CREATING, &volume->flags)) goto maybe_wait; if (volume->cache_priv) goto no_wait; /* We raced */ if (!fscache_begin_cache_access(volume->cache, fscache_access_acquire_volume)) goto no_wait; fscache_get_volume(volume, fscache_volume_get_create_work); if (!schedule_work(&volume->work)) fscache_put_volume(volume, fscache_volume_put_create_work); maybe_wait: if (wait) { fscache_see_volume(volume, fscache_volume_wait_create_work); wait_on_bit(&volume->flags, FSCACHE_VOLUME_CREATING, TASK_UNINTERRUPTIBLE); } return; no_wait: clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags); wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING); } /* * Acquire a volume representation cookie and link it to a (proposed) cache. */ struct fscache_volume *__fscache_acquire_volume(const char *volume_key, const char *cache_name, const void *coherency_data, size_t coherency_len) { struct fscache_volume *volume; volume = fscache_alloc_volume(volume_key, cache_name, coherency_data, coherency_len); if (!volume) return ERR_PTR(-ENOMEM); if (!fscache_hash_volume(volume)) { fscache_put_volume(volume, fscache_volume_put_hash_collision); return ERR_PTR(-EBUSY); } fscache_create_volume(volume, false); return volume; } EXPORT_SYMBOL(__fscache_acquire_volume); static void fscache_wake_pending_volume(struct fscache_volume *volume, struct hlist_bl_head *h) { struct fscache_volume *cursor; struct hlist_bl_node *p; hlist_bl_for_each_entry(cursor, p, h, hash_link) { if (fscache_volume_same(cursor, volume)) { fscache_see_volume(cursor, fscache_volume_see_hash_wake); clear_and_wake_up_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &cursor->flags); return; } } } /* * Remove a volume cookie from the hash table. */ static void fscache_unhash_volume(struct fscache_volume *volume) { struct hlist_bl_head *h; unsigned int bucket; bucket = volume->key_hash & (ARRAY_SIZE(fscache_volume_hash) - 1); h = &fscache_volume_hash[bucket]; hlist_bl_lock(h); hlist_bl_del(&volume->hash_link); if (test_bit(FSCACHE_VOLUME_COLLIDED_WITH, &volume->flags)) fscache_wake_pending_volume(volume, h); hlist_bl_unlock(h); } /* * Drop a cache's volume attachments. */ static void fscache_free_volume(struct fscache_volume *volume) { struct fscache_cache *cache = volume->cache; if (volume->cache_priv) { __fscache_begin_volume_access(volume, NULL, fscache_access_relinquish_volume); if (volume->cache_priv) cache->ops->free_volume(volume); fscache_end_volume_access(volume, NULL, fscache_access_relinquish_volume_end); } down_write(&fscache_addremove_sem); list_del_init(&volume->proc_link); atomic_dec(&volume->cache->n_volumes); up_write(&fscache_addremove_sem); if (!hlist_bl_unhashed(&volume->hash_link)) fscache_unhash_volume(volume); trace_fscache_volume(volume->debug_id, 0, fscache_volume_free); kfree(volume->key); kfree(volume); fscache_stat_d(&fscache_n_volumes); fscache_put_cache(cache, fscache_cache_put_volume); } /* * Drop a reference to a volume cookie. */ void fscache_put_volume(struct fscache_volume *volume, enum fscache_volume_trace where) { if (volume) { unsigned int debug_id = volume->debug_id; bool zero; int ref; zero = __refcount_dec_and_test(&volume->ref, &ref); trace_fscache_volume(debug_id, ref - 1, where); if (zero) fscache_free_volume(volume); } } /* * Relinquish a volume representation cookie. */ void __fscache_relinquish_volume(struct fscache_volume *volume, const void *coherency_data, bool invalidate) { if (WARN_ON(test_and_set_bit(FSCACHE_VOLUME_RELINQUISHED, &volume->flags))) return; if (invalidate) { set_bit(FSCACHE_VOLUME_INVALIDATE, &volume->flags); } else if (coherency_data) { memcpy(volume->coherency, coherency_data, volume->coherency_len); } fscache_put_volume(volume, fscache_volume_put_relinquish); } EXPORT_SYMBOL(__fscache_relinquish_volume); /** * fscache_withdraw_volume - Withdraw a volume from being cached * @volume: Volume cookie * * Withdraw a cache volume from service, waiting for all accesses to complete * before returning. */ void fscache_withdraw_volume(struct fscache_volume *volume) { int n_accesses; _debug("withdraw V=%x", volume->debug_id); /* Allow wakeups on dec-to-0 */ n_accesses = atomic_dec_return(&volume->n_accesses); trace_fscache_access_volume(volume->debug_id, 0, refcount_read(&volume->ref), n_accesses, fscache_access_cache_unpin); wait_var_event(&volume->n_accesses, atomic_read(&volume->n_accesses) == 0); } EXPORT_SYMBOL(fscache_withdraw_volume); #ifdef CONFIG_PROC_FS /* * Generate a list of volumes in /proc/fs/fscache/volumes */ static int fscache_volumes_seq_show(struct seq_file *m, void *v) { struct fscache_volume *volume; if (v == &fscache_volumes) { seq_puts(m, "VOLUME REF nCOOK ACC FL CACHE KEY\n" "======== ===== ===== === == =============== ================\n"); return 0; } volume = list_entry(v, struct fscache_volume, proc_link); seq_printf(m, "%08x %5d %5d %3d %02lx %-15.15s %s\n", volume->debug_id, refcount_read(&volume->ref), atomic_read(&volume->n_cookies), atomic_read(&volume->n_accesses), volume->flags, volume->cache->name ?: "-", volume->key + 1); return 0; } static void *fscache_volumes_seq_start(struct seq_file *m, loff_t *_pos) __acquires(&fscache_addremove_sem) { down_read(&fscache_addremove_sem); return seq_list_start_head(&fscache_volumes, *_pos); } static void *fscache_volumes_seq_next(struct seq_file *m, void *v, loff_t *_pos) { return seq_list_next(v, &fscache_volumes, _pos); } static void fscache_volumes_seq_stop(struct seq_file *m, void *v) __releases(&fscache_addremove_sem) { up_read(&fscache_addremove_sem); } const struct seq_operations fscache_volumes_seq_ops = { .start = fscache_volumes_seq_start, .next = fscache_volumes_seq_next, .stop = fscache_volumes_seq_stop, .show = fscache_volumes_seq_show, }; #endif /* CONFIG_PROC_FS */ |
| 4 5 5 5 5 5 5 5 5 5 5 21 10 13 13 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 1999 Hans Reiser, see reiserfs/README for licensing and copyright * details */ #include <linux/time.h> #include <linux/pagemap.h> #include <linux/buffer_head.h> #include "reiserfs.h" /* * access to tail : when one is going to read tail it must make sure, that is * not running. direct2indirect and indirect2direct can not run concurrently */ /* * Converts direct items to an unformatted node. Panics if file has no * tail. -ENOSPC if no disk space for conversion */ /* * path points to first direct item of the file regardless of how many of * them are there */ int direct2indirect(struct reiserfs_transaction_handle *th, struct inode *inode, struct treepath *path, struct buffer_head *unbh, loff_t tail_offset) { struct super_block *sb = inode->i_sb; struct buffer_head *up_to_date_bh; struct item_head *p_le_ih = tp_item_head(path); unsigned long total_tail = 0; /* Key to search for the last byte of the converted item. */ struct cpu_key end_key; /* * new indirect item to be inserted or key * of unfm pointer to be pasted */ struct item_head ind_ih; int blk_size; /* returned value for reiserfs_insert_item and clones */ int retval; /* Handle on an unformatted node that will be inserted in the tree. */ unp_t unfm_ptr; BUG_ON(!th->t_trans_id); REISERFS_SB(sb)->s_direct2indirect++; blk_size = sb->s_blocksize; /* * and key to search for append or insert pointer to the new * unformatted node. */ copy_item_head(&ind_ih, p_le_ih); set_le_ih_k_offset(&ind_ih, tail_offset); set_le_ih_k_type(&ind_ih, TYPE_INDIRECT); /* Set the key to search for the place for new unfm pointer */ make_cpu_key(&end_key, inode, tail_offset, TYPE_INDIRECT, 4); /* FIXME: we could avoid this */ if (search_for_position_by_key(sb, &end_key, path) == POSITION_FOUND) { reiserfs_error(sb, "PAP-14030", "pasted or inserted byte exists in " "the tree %K. Use fsck to repair.", &end_key); pathrelse(path); return -EIO; } p_le_ih = tp_item_head(path); unfm_ptr = cpu_to_le32(unbh->b_blocknr); if (is_statdata_le_ih(p_le_ih)) { /* Insert new indirect item. */ set_ih_free_space(&ind_ih, 0); /* delete at nearest future */ put_ih_item_len(&ind_ih, UNFM_P_SIZE); PATH_LAST_POSITION(path)++; retval = reiserfs_insert_item(th, path, &end_key, &ind_ih, inode, (char *)&unfm_ptr); } else { /* Paste into last indirect item of an object. */ retval = reiserfs_paste_into_item(th, path, &end_key, inode, (char *)&unfm_ptr, UNFM_P_SIZE); } if (retval) { return retval; } /* * note: from here there are two keys which have matching first * three key components. They only differ by the fourth one. */ /* Set the key to search for the direct items of the file */ make_cpu_key(&end_key, inode, max_reiserfs_offset(inode), TYPE_DIRECT, 4); /* * Move bytes from the direct items to the new unformatted node * and delete them. */ while (1) { int tail_size; /* * end_key.k_offset is set so, that we will always have found * last item of the file */ if (search_for_position_by_key(sb, &end_key, path) == POSITION_FOUND) reiserfs_panic(sb, "PAP-14050", "direct item (%K) not found", &end_key); p_le_ih = tp_item_head(path); RFALSE(!is_direct_le_ih(p_le_ih), "vs-14055: direct item expected(%K), found %h", &end_key, p_le_ih); tail_size = (le_ih_k_offset(p_le_ih) & (blk_size - 1)) + ih_item_len(p_le_ih) - 1; /* * we only send the unbh pointer if the buffer is not * up to date. this avoids overwriting good data from * writepage() with old data from the disk or buffer cache * Special case: unbh->b_page will be NULL if we are coming * through DIRECT_IO handler here. */ if (!unbh->b_page || buffer_uptodate(unbh) || PageUptodate(unbh->b_page)) { up_to_date_bh = NULL; } else { up_to_date_bh = unbh; } retval = reiserfs_delete_item(th, path, &end_key, inode, up_to_date_bh); total_tail += retval; /* done: file does not have direct items anymore */ if (tail_size == retval) break; } /* * if we've copied bytes from disk into the page, we need to zero * out the unused part of the block (it was not up to date before) */ if (up_to_date_bh) { unsigned pgoff = (tail_offset + total_tail - 1) & (PAGE_SIZE - 1); char *kaddr = kmap_atomic(up_to_date_bh->b_page); memset(kaddr + pgoff, 0, blk_size - total_tail); kunmap_atomic(kaddr); } REISERFS_I(inode)->i_first_direct_byte = U32_MAX; return 0; } /* stolen from fs/buffer.c */ void reiserfs_unmap_buffer(struct buffer_head *bh) { lock_buffer(bh); if (buffer_journaled(bh) || buffer_journal_dirty(bh)) { BUG(); } clear_buffer_dirty(bh); /* * Remove the buffer from whatever list it belongs to. We are mostly * interested in removing it from per-sb j_dirty_buffers list, to avoid * BUG() on attempt to write not mapped buffer */ if ((!list_empty(&bh->b_assoc_buffers) || bh->b_private) && bh->b_page) { struct inode *inode = bh->b_folio->mapping->host; struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb); spin_lock(&j->j_dirty_buffers_lock); list_del_init(&bh->b_assoc_buffers); reiserfs_free_jh(bh); spin_unlock(&j->j_dirty_buffers_lock); } clear_buffer_mapped(bh); clear_buffer_req(bh); clear_buffer_new(bh); bh->b_bdev = NULL; unlock_buffer(bh); } /* * this first locks inode (neither reads nor sync are permitted), * reads tail through page cache, insert direct item. When direct item * inserted successfully inode is left locked. Return value is always * what we expect from it (number of cut bytes). But when tail remains * in the unformatted node, we set mode to SKIP_BALANCING and unlock * inode */ int indirect2direct(struct reiserfs_transaction_handle *th, struct inode *inode, struct page *page, struct treepath *path, /* path to the indirect item. */ const struct cpu_key *item_key, /* Key to look for * unformatted node * pointer to be cut. */ loff_t n_new_file_size, /* New file size. */ char *mode) { struct super_block *sb = inode->i_sb; struct item_head s_ih; unsigned long block_size = sb->s_blocksize; char *tail; int tail_len, round_tail_len; loff_t pos, pos1; /* position of first byte of the tail */ struct cpu_key key; BUG_ON(!th->t_trans_id); REISERFS_SB(sb)->s_indirect2direct++; *mode = M_SKIP_BALANCING; /* store item head path points to. */ copy_item_head(&s_ih, tp_item_head(path)); tail_len = (n_new_file_size & (block_size - 1)); if (get_inode_sd_version(inode) == STAT_DATA_V2) round_tail_len = ROUND_UP(tail_len); else round_tail_len = tail_len; pos = le_ih_k_offset(&s_ih) - 1 + (ih_item_len(&s_ih) / UNFM_P_SIZE - 1) * sb->s_blocksize; pos1 = pos; /* * we are protected by i_mutex. The tail can not disapper, not * append can be done either * we are in truncate or packing tail in file_release */ tail = (char *)kmap(page); /* this can schedule */ if (path_changed(&s_ih, path)) { /* re-search indirect item */ if (search_for_position_by_key(sb, item_key, path) == POSITION_NOT_FOUND) reiserfs_panic(sb, "PAP-5520", "item to be converted %K does not exist", item_key); copy_item_head(&s_ih, tp_item_head(path)); #ifdef CONFIG_REISERFS_CHECK pos = le_ih_k_offset(&s_ih) - 1 + (ih_item_len(&s_ih) / UNFM_P_SIZE - 1) * sb->s_blocksize; if (pos != pos1) reiserfs_panic(sb, "vs-5530", "tail position " "changed while we were reading it"); #endif } /* Set direct item header to insert. */ make_le_item_head(&s_ih, NULL, get_inode_item_key_version(inode), pos1 + 1, TYPE_DIRECT, round_tail_len, 0xffff /*ih_free_space */ ); /* * we want a pointer to the first byte of the tail in the page. * the page was locked and this part of the page was up to date when * indirect2direct was called, so we know the bytes are still valid */ tail = tail + (pos & (PAGE_SIZE - 1)); PATH_LAST_POSITION(path)++; key = *item_key; set_cpu_key_k_type(&key, TYPE_DIRECT); key.key_length = 4; /* Insert tail as new direct item in the tree */ if (reiserfs_insert_item(th, path, &key, &s_ih, inode, tail ? tail : NULL) < 0) { /* * No disk memory. So we can not convert last unformatted node * to the direct item. In this case we used to adjust * indirect items's ih_free_space. Now ih_free_space is not * used, it would be ideal to write zeros to corresponding * unformatted node. For now i_size is considered as guard for * going out of file size */ kunmap(page); return block_size - round_tail_len; } kunmap(page); /* make sure to get the i_blocks changes from reiserfs_insert_item */ reiserfs_update_sd(th, inode); /* * note: we have now the same as in above direct2indirect * conversion: there are two keys which have matching first three * key components. They only differ by the fourth one. */ /* * We have inserted new direct item and must remove last * unformatted node. */ *mode = M_CUT; /* we store position of first direct item in the in-core inode */ /* mark_file_with_tail (inode, pos1 + 1); */ REISERFS_I(inode)->i_first_direct_byte = pos1 + 1; return block_size - round_tail_len; } |
| 17 16 19 33 35 20 35 35 35 29 7 35 18 18 20 3 6 20 17 17 17 18 32 7 17 20 7 18 18 18 18 3 3 3 18 18 18 18 7 7 7 21 20 20 20 17 20 17 16 16 31 32 17 32 32 32 16 16 16 16 16 88 90 3 3 3 3 3 3 128 126 127 82 3 1 1 1 8 10 10 10 3 7 7 19 16 16 13 68 94 1 1 1 2 4 4 1 1 1 3 2 3 3 2 1 3 3 5 2 1 1 2 1 1 2 6 4 4 4 2 2 1 2 4 1 1 1 1 4 4 6 144 144 144 144 15 15 15 15 15 15 14 13 11 30 30 15 1 1 29 18 17 5 5 1 5 19 15 15 8 2 2 2 2 2 7 7 3 6 6 6 6 29 2 2 14 16 208 14 266 83 2 1 1 47 47 47 47 15 47 15 47 47 47 19 46 46 47 27 23 46 14 46 3 2 2 3 1 2 2 2 2 2 2 1 1 1 2 1 1 2 2 7 3 5 5 2 1 3 3 2 3 3 7 3 10 1 9 3 9 1 8 7 6 6 3 6 1 6 6 21 19 1 10 6 15 21 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/switchdev.h> #include "br_private.h" #include "br_private_tunnel.h" static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid); static inline int br_vlan_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct net_bridge_vlan *vle = ptr; u16 vid = *(u16 *)arg->key; return vle->vid != vid; } static const struct rhashtable_params br_vlan_rht_params = { .head_offset = offsetof(struct net_bridge_vlan, vnode), .key_offset = offsetof(struct net_bridge_vlan, vid), .key_len = sizeof(u16), .nelem_hint = 3, .max_size = VLAN_N_VID, .obj_cmpfn = br_vlan_cmp, .automatic_shrinking = true, }; static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) { return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); } static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, const struct net_bridge_vlan *v) { if (vg->pvid == v->vid) return; smp_wmb(); br_vlan_set_pvid_state(vg, v->state); vg->pvid = v->vid; } static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid) { if (vg->pvid != vid) return; smp_wmb(); vg->pvid = 0; } /* Update the BRIDGE_VLAN_INFO_PVID and BRIDGE_VLAN_INFO_UNTAGGED flags of @v. * If @commit is false, return just whether the BRIDGE_VLAN_INFO_PVID and * BRIDGE_VLAN_INFO_UNTAGGED bits of @flags would produce any change onto @v. */ static bool __vlan_flags_update(struct net_bridge_vlan *v, u16 flags, bool commit) { struct net_bridge_vlan_group *vg; bool change; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); /* check if anything would be changed on commit */ change = !!(flags & BRIDGE_VLAN_INFO_PVID) == !!(vg->pvid != v->vid) || ((flags ^ v->flags) & BRIDGE_VLAN_INFO_UNTAGGED); if (!commit) goto out; if (flags & BRIDGE_VLAN_INFO_PVID) __vlan_add_pvid(vg, v); else __vlan_delete_pvid(vg, v->vid); if (flags & BRIDGE_VLAN_INFO_UNTAGGED) v->flags |= BRIDGE_VLAN_INFO_UNTAGGED; else v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; out: return change; } static bool __vlan_flags_would_change(struct net_bridge_vlan *v, u16 flags) { return __vlan_flags_update(v, flags, false); } static void __vlan_flags_commit(struct net_bridge_vlan *v, u16 flags) { __vlan_flags_update(v, flags, true); } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, struct net_bridge_vlan *v, u16 flags, struct netlink_ext_ack *extack) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q add. */ err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err == -EOPNOTSUPP) return vlan_vid_add(dev, br->vlan_proto, v->vid); v->priv_flags |= BR_VLFLAG_ADDED_BY_SWITCHDEV; return err; } static void __vlan_add_list(struct net_bridge_vlan *v) { struct net_bridge_vlan_group *vg; struct list_head *headp, *hpos; struct net_bridge_vlan *vent; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); headp = &vg->vlan_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct net_bridge_vlan, vlist); if (v->vid >= vent->vid) break; } list_add_rcu(&v->vlist, hpos); } static void __vlan_del_list(struct net_bridge_vlan *v) { list_del_rcu(&v->vlist); } static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, const struct net_bridge_vlan *v) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q del. */ err = br_switchdev_port_vlan_del(dev, v->vid); if (!(v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)) vlan_vid_del(dev, br->vlan_proto, v->vid); return err == -EOPNOTSUPP ? 0 : err; } /* Returns a master vlan, if it didn't exist it gets created. In all cases * a reference is taken to the master vlan before returning. */ static struct net_bridge_vlan * br_vlan_get_master(struct net_bridge *br, u16 vid, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *masterv; vg = br_vlan_group(br); masterv = br_vlan_find(vg, vid); if (!masterv) { bool changed; /* missing global ctx, create it now */ if (br_vlan_add(br, vid, 0, &changed, extack)) return NULL; masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; refcount_set(&masterv->refcnt, 1); return masterv; } refcount_inc(&masterv->refcnt); return masterv; } static void br_master_vlan_rcu_free(struct rcu_head *rcu) { struct net_bridge_vlan *v; v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(!br_vlan_is_master(v)); free_percpu(v->stats); v->stats = NULL; kfree(v); } static void br_vlan_put_master(struct net_bridge_vlan *masterv) { struct net_bridge_vlan_group *vg; if (!br_vlan_is_master(masterv)) return; vg = br_vlan_group(masterv->br); if (refcount_dec_and_test(&masterv->refcnt)) { rhashtable_remove_fast(&vg->vlan_hash, &masterv->vnode, br_vlan_rht_params); __vlan_del_list(masterv); br_multicast_toggle_one_vlan(masterv, false); br_multicast_ctx_deinit(&masterv->br_mcast_ctx); call_rcu(&masterv->rcu, br_master_vlan_rcu_free); } } static void nbp_vlan_rcu_free(struct rcu_head *rcu) { struct net_bridge_vlan *v; v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(br_vlan_is_master(v)); /* if we had per-port stats configured then free them here */ if (v->priv_flags & BR_VLFLAG_PER_PORT_STATS) free_percpu(v->stats); v->stats = NULL; kfree(v); } static void br_vlan_init_state(struct net_bridge_vlan *v) { struct net_bridge *br; if (br_vlan_is_master(v)) br = v->br; else br = v->port->br; if (br_opt_get(br, BROPT_MST_ENABLED)) { br_mst_vlan_init_state(v); return; } v->state = BR_STATE_FORWARDING; v->msti = 0; } /* This is the shared VLAN add function which works for both ports and bridge * devices. There are four possible calls to this function in terms of the * vlan entry type: * 1. vlan is being added on a port (no master flags, global entry exists) * 2. vlan is being added on a bridge (both master and brentry flags) * 3. vlan is being added on a port, but a global entry didn't exist which * is being created right now (master flag set, brentry flag unset), the * global entry is used for global per-vlan features, but not for filtering * 4. same as 3 but with both master and brentry flags set so the entry * will be used for filtering in both the port and the bridge */ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge_vlan *masterv = NULL; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_device *dev; struct net_bridge *br; int err; if (br_vlan_is_master(v)) { br = v->br; dev = br->dev; vg = br_vlan_group(br); } else { p = v->port; br = p->br; dev = p->dev; vg = nbp_vlan_group(p); } if (p) { /* Add VLAN to the device filter if it is supported. * This ensures tagged traffic enters the bridge when * promiscuous mode is disabled by br_manage_promisc(). */ err = __vlan_vid_add(dev, br, v, flags, extack); if (err) goto out; /* need to work on the master vlan too */ if (flags & BRIDGE_VLAN_INFO_MASTER) { bool changed; err = br_vlan_add(br, v->vid, flags | BRIDGE_VLAN_INFO_BRENTRY, &changed, extack); if (err) goto out_filt; if (changed) br_vlan_notify(br, NULL, v->vid, 0, RTM_NEWVLAN); } masterv = br_vlan_get_master(br, v->vid, extack); if (!masterv) { err = -ENOMEM; goto out_filt; } v->brvlan = masterv; if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) { v->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!v->stats) { err = -ENOMEM; goto out_filt; } v->priv_flags |= BR_VLFLAG_PER_PORT_STATS; } else { v->stats = masterv->stats; } br_multicast_port_ctx_init(p, v, &v->port_mcast_ctx); } else { if (br_vlan_should_use(v)) { err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err && err != -EOPNOTSUPP) goto out; } br_multicast_ctx_init(br, v, &v->br_mcast_ctx); v->priv_flags |= BR_VLFLAG_GLOBAL_MCAST_ENABLED; } /* Add the dev mac and count the vlan only if it's usable */ if (br_vlan_should_use(v)) { err = br_fdb_add_local(br, p, dev->dev_addr, v->vid); if (err) { br_err(br, "failed insert local address into bridge forwarding table\n"); goto out_filt; } vg->num_vlans++; } /* set the state before publishing */ br_vlan_init_state(v); err = rhashtable_lookup_insert_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); if (err) goto out_fdb_insert; __vlan_add_list(v); __vlan_flags_commit(v, flags); br_multicast_toggle_one_vlan(v, true); if (p) nbp_vlan_set_vlan_dev_state(p, v->vid); out: return err; out_fdb_insert: if (br_vlan_should_use(v)) { br_fdb_find_delete_local(br, p, dev->dev_addr, v->vid); vg->num_vlans--; } out_filt: if (p) { __vlan_vid_del(dev, br, v); if (masterv) { if (v->stats && masterv->stats != v->stats) free_percpu(v->stats); v->stats = NULL; br_vlan_put_master(masterv); v->brvlan = NULL; } } else { br_switchdev_port_vlan_del(dev, v->vid); } goto out; } static int __vlan_del(struct net_bridge_vlan *v) { struct net_bridge_vlan *masterv = v; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; int err = 0; if (br_vlan_is_master(v)) { vg = br_vlan_group(v->br); } else { p = v->port; vg = nbp_vlan_group(v->port); masterv = v->brvlan; } __vlan_delete_pvid(vg, v->vid); if (p) { err = __vlan_vid_del(p->dev, p->br, v); if (err) goto out; } else { err = br_switchdev_port_vlan_del(v->br->dev, v->vid); if (err && err != -EOPNOTSUPP) goto out; err = 0; } if (br_vlan_should_use(v)) { v->flags &= ~BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans--; } if (masterv != v) { vlan_tunnel_info_del(vg, v); rhashtable_remove_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); __vlan_del_list(v); nbp_vlan_set_vlan_dev_state(p, v->vid); br_multicast_toggle_one_vlan(v, false); br_multicast_port_ctx_deinit(&v->port_mcast_ctx); call_rcu(&v->rcu, nbp_vlan_rcu_free); } br_vlan_put_master(masterv); out: return err; } static void __vlan_group_free(struct net_bridge_vlan_group *vg) { WARN_ON(!list_empty(&vg->vlan_list)); rhashtable_destroy(&vg->vlan_hash); vlan_tunnel_deinit(vg); kfree(vg); } static void __vlan_flush(const struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *vlan, *tmp; u16 v_start = 0, v_end = 0; int err; __vlan_delete_pvid(vg, vg->pvid); list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) { /* take care of disjoint ranges */ if (!v_start) { v_start = vlan->vid; } else if (vlan->vid - v_end != 1) { /* found range end, notify and start next one */ br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); v_start = vlan->vid; } v_end = vlan->vid; err = __vlan_del(vlan); if (err) { br_err(br, "port %u(%s) failed to delete vlan %d: %pe\n", (unsigned int) p->port_no, p->dev->name, vlan->vid, ERR_PTR(err)); } } /* notify about the last/whole vlan range */ if (v_start) br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); } struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_vlan_group *vg, struct sk_buff *skb) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; /* At this point, we know that the frame was filtered and contains * a valid vlan id. If the vlan id has untagged flag set, * send untagged; otherwise, send tagged. */ br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); /* Vlan entry must be configured at this point. The * only exception is the bridge is set in promisc mode and the * packet is destined for the bridge device. In this case * pass the packet as is. */ if (!v || !br_vlan_should_use(v)) { if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) { goto out; } else { kfree_skb(skb); return NULL; } } if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->tx_bytes, skb->len); u64_stats_inc(&stats->tx_packets); u64_stats_update_end(&stats->syncp); } /* If the skb will be sent using forwarding offload, the assumption is * that the switchdev will inject the packet into hardware together * with the bridge VLAN, so that it can be forwarded according to that * VLAN. The switchdev should deal with popping the VLAN header in * hardware on each egress port as appropriate. So only strip the VLAN * header if forwarding offload is not being used. */ if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED && !br_switchdev_frame_uses_tx_fwd_offload(skb)) __vlan_hwaccel_clear_tag(skb); if (p && (p->flags & BR_VLAN_TUNNEL) && br_handle_egress_vlan_tunnel(skb, v)) { kfree_skb(skb); return NULL; } out: return skb; } /* Called under RCU */ static bool __allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, u8 *state, struct net_bridge_vlan **vlan) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; bool tagged; BR_INPUT_SKB_CB(skb)->vlan_filtered = true; /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. */ if (unlikely(!skb_vlan_tag_present(skb) && skb->protocol == br->vlan_proto)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) return false; } if (!br_vlan_get_tag(skb, vid)) { /* Tagged frame */ if (skb->vlan_proto != br->vlan_proto) { /* Protocol-mismatch, empty out vlan_tci for new tag */ skb_push(skb, ETH_HLEN); skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (unlikely(!skb)) return false; skb_pull(skb, ETH_HLEN); skb_reset_mac_len(skb); *vid = 0; tagged = false; } else { tagged = true; } } else { /* Untagged frame */ tagged = false; } if (!*vid) { u16 pvid = br_get_pvid(vg); /* Frame had a tag with VID 0 or did not have a tag. * See if pvid is set on this port. That tells us which * vlan untagged or priority-tagged traffic belongs to. */ if (!pvid) goto drop; /* PVID is set on this port. Any untagged or priority-tagged * ingress frame is considered to belong to this vlan. */ *vid = pvid; if (likely(!tagged)) /* Untagged Frame. */ __vlan_hwaccel_put_tag(skb, br->vlan_proto, pvid); else /* Priority-tagged Frame. * At this point, we know that skb->vlan_tci VID * field was 0. * We update only VID field and preserve PCP field. */ skb->vlan_tci |= pvid; /* if snooping and stats are disabled we can avoid the lookup */ if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) && !br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_pvid_state(vg); if (!br_vlan_state_allowed(*state, true)) goto drop; } return true; } } v = br_vlan_find(vg, *vid); if (!v || !br_vlan_should_use(v)) goto drop; if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_state(v); if (!br_vlan_state_allowed(*state, true)) goto drop; } if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->rx_bytes, skb->len); u64_stats_inc(&stats->rx_packets); u64_stats_update_end(&stats->syncp); } *vlan = v; return true; drop: kfree_skb(skb); return false; } bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, u8 *state, struct net_bridge_vlan **vlan) { /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ *vlan = NULL; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) { BR_INPUT_SKB_CB(skb)->vlan_filtered = false; return true; } return __allowed_ingress(br, vg, skb, vid, state, vlan); } /* Called under RCU. */ bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { const struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); if (v && br_vlan_should_use(v) && br_vlan_state_allowed(br_vlan_get_state(v), false)) return true; return false; } /* Called under RCU */ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) { struct net_bridge_vlan_group *vg; struct net_bridge *br = p->br; struct net_bridge_vlan *v; /* If filtering was disabled at input, let it pass. */ if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return true; vg = nbp_vlan_group_rcu(p); if (!vg || !vg->num_vlans) return false; if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto) *vid = 0; if (!*vid) { *vid = br_get_pvid(vg); if (!*vid || !br_vlan_state_allowed(br_vlan_get_pvid_state(vg), true)) return false; return true; } v = br_vlan_find(vg, *vid); if (v && br_vlan_state_allowed(br_vlan_get_state(v), true)) return true; return false; } static int br_vlan_add_existing(struct net_bridge *br, struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u16 flags, bool *changed, struct netlink_ext_ack *extack) { bool would_change = __vlan_flags_would_change(vlan, flags); bool becomes_brentry = false; int err; if (!br_vlan_is_brentry(vlan)) { /* Trying to change flags of non-existent bridge vlan */ if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) return -EINVAL; becomes_brentry = true; } /* Master VLANs that aren't brentries weren't notified before, * time to notify them now. */ if (becomes_brentry || would_change) { err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags, would_change, extack); if (err && err != -EOPNOTSUPP) return err; } if (becomes_brentry) { /* It was only kept for port vlans, now make it real */ err = br_fdb_add_local(br, NULL, br->dev->dev_addr, vlan->vid); if (err) { br_err(br, "failed to insert local address into bridge forwarding table\n"); goto err_fdb_insert; } refcount_inc(&vlan->refcnt); vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans++; *changed = true; br_multicast_toggle_one_vlan(vlan, true); } __vlan_flags_commit(vlan, flags); if (would_change) *changed = true; return 0; err_fdb_insert: br_switchdev_port_vlan_del(br->dev, vlan->vid); return err; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); *changed = false; vg = br_vlan_group(br); vlan = br_vlan_find(vg, vid); if (vlan) return br_vlan_add_existing(br, vg, vlan, flags, changed, extack); vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); if (!vlan) return -ENOMEM; vlan->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!vlan->stats) { kfree(vlan); return -ENOMEM; } vlan->vid = vid; vlan->flags = flags | BRIDGE_VLAN_INFO_MASTER; vlan->flags &= ~BRIDGE_VLAN_INFO_PVID; vlan->br = br; if (flags & BRIDGE_VLAN_INFO_BRENTRY) refcount_set(&vlan->refcnt, 1); ret = __vlan_add(vlan, flags, extack); if (ret) { free_percpu(vlan->stats); kfree(vlan); } else { *changed = true; } return ret; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int br_vlan_delete(struct net_bridge *br, u16 vid) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; ASSERT_RTNL(); vg = br_vlan_group(br); v = br_vlan_find(vg, vid); if (!v || !br_vlan_is_brentry(v)) return -ENOENT; br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); br_fdb_delete_by_port(br, NULL, vid, 0); vlan_tunnel_info_del(vg, v); return __vlan_del(v); } void br_vlan_flush(struct net_bridge *br) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = br_vlan_group(br); __vlan_flush(br, NULL, vg); RCU_INIT_POINTER(br->vlgrp, NULL); synchronize_rcu(); __vlan_group_free(vg); } struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid) { if (!vg) return NULL; return br_vlan_lookup(&vg->vlan_hash, vid); } /* Must be protected by RTNL. */ static void recalculate_group_addr(struct net_bridge *br) { if (br_opt_get(br, BROPT_GROUP_ADDR_SET)) return; spin_lock_bh(&br->lock); if (!br_opt_get(br, BROPT_VLAN_ENABLED) || br->vlan_proto == htons(ETH_P_8021Q)) { /* Bridge Group Address */ br->group_addr[5] = 0x00; } else { /* vlan_enabled && ETH_P_8021AD */ /* Provider Bridge Group Address */ br->group_addr[5] = 0x08; } spin_unlock_bh(&br->lock); } /* Must be protected by RTNL. */ void br_recalculate_fwd_mask(struct net_bridge *br) { if (!br_opt_get(br, BROPT_VLAN_ENABLED) || br->vlan_proto == htons(ETH_P_8021Q)) br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT; else /* vlan_enabled && ETH_P_8021AD */ br->group_fwd_mask_required = BR_GROUPFWD_8021AD & ~(1u << br->group_addr[5]); } int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_filtering = val, }; int err; if (br_opt_get(br, BROPT_VLAN_ENABLED) == !!val) return 0; br_opt_toggle(br, BROPT_VLAN_ENABLED, !!val); err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) { br_opt_toggle(br, BROPT_VLAN_ENABLED, !val); return err; } br_manage_promisc(br); recalculate_group_addr(br); br_recalculate_fwd_mask(br); if (!val && br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { br_info(br, "vlan filtering disabled, automatically disabling multicast vlan snooping\n"); br_multicast_toggle_vlan_snooping(br, false, NULL); } return 0; } bool br_vlan_enabled(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); return br_opt_get(br, BROPT_VLAN_ENABLED); } EXPORT_SYMBOL_GPL(br_vlan_enabled); int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto) { struct net_bridge *br = netdev_priv(dev); *p_proto = ntohs(br->vlan_proto); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_proto); int __br_vlan_set_proto(struct net_bridge *br, __be16 proto, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_protocol = ntohs(proto), }; int err = 0; struct net_bridge_port *p; struct net_bridge_vlan *vlan; struct net_bridge_vlan_group *vg; __be16 oldproto = br->vlan_proto; if (br->vlan_proto == proto) return 0; err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) return err; /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; } } br->vlan_proto = proto; recalculate_group_addr(br); br_recalculate_fwd_mask(br); /* Delete VLANs for the old proto from the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, oldproto, vlan->vid); } } return 0; err_filt: attr.u.vlan_protocol = ntohs(oldproto); switchdev_port_attr_set(br->dev, &attr, NULL); list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, proto, vlan->vid); } list_for_each_entry_continue_reverse(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, proto, vlan->vid); } } return err; } int br_vlan_set_proto(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { if (!eth_type_vlan(htons(val))) return -EPROTONOSUPPORT; return __br_vlan_set_proto(br, htons(val), extack); } int br_vlan_set_stats(struct net_bridge *br, unsigned long val) { switch (val) { case 0: case 1: br_opt_toggle(br, BROPT_VLAN_STATS_ENABLED, !!val); break; default: return -EINVAL; } return 0; } int br_vlan_set_stats_per_port(struct net_bridge *br, unsigned long val) { struct net_bridge_port *p; /* allow to change the option if there are no port vlans configured */ list_for_each_entry(p, &br->port_list, list) { struct net_bridge_vlan_group *vg = nbp_vlan_group(p); if (vg->num_vlans) return -EBUSY; } switch (val) { case 0: case 1: br_opt_toggle(br, BROPT_VLAN_STATS_PER_PORT, !!val); break; default: return -EINVAL; } return 0; } static bool vlan_default_pvid(struct net_bridge_vlan_group *vg, u16 vid) { struct net_bridge_vlan *v; if (vid != vg->pvid) return false; v = br_vlan_lookup(&vg->vlan_hash, vid); if (v && br_vlan_should_use(v) && (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) return true; return false; } static void br_vlan_disable_default_pvid(struct net_bridge *br) { struct net_bridge_port *p; u16 pvid = br->default_pvid; /* Disable default_pvid on all ports where it is still * configured. */ if (vlan_default_pvid(br_vlan_group(br), pvid)) { if (!br_vlan_delete(br, pvid)) br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } list_for_each_entry(p, &br->port_list, list) { if (vlan_default_pvid(nbp_vlan_group(p), pvid) && !nbp_vlan_delete(p, pvid)) br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } br->default_pvid = 0; } int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid, struct netlink_ext_ack *extack) { const struct net_bridge_vlan *pvent; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; unsigned long *changed; bool vlchange; u16 old_pvid; int err = 0; if (!pvid) { br_vlan_disable_default_pvid(br); return 0; } changed = bitmap_zalloc(BR_MAX_PORTS, GFP_KERNEL); if (!changed) return -ENOMEM; old_pvid = br->default_pvid; /* Update default_pvid config only if we do not conflict with * user configuration. */ vg = br_vlan_group(br); pvent = br_vlan_find(vg, pvid); if ((!old_pvid || vlan_default_pvid(vg, old_pvid)) && (!pvent || !br_vlan_should_use(pvent))) { err = br_vlan_add(br, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, extack); if (err) goto out; if (br_vlan_delete(br, old_pvid)) br_vlan_notify(br, NULL, old_pvid, 0, RTM_DELVLAN); br_vlan_notify(br, NULL, pvid, 0, RTM_NEWVLAN); __set_bit(0, changed); } list_for_each_entry(p, &br->port_list, list) { /* Update default_pvid config only if we do not conflict with * user configuration. */ vg = nbp_vlan_group(p); if ((old_pvid && !vlan_default_pvid(vg, old_pvid)) || br_vlan_find(vg, pvid)) continue; err = nbp_vlan_add(p, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, extack); if (err) goto err_port; if (nbp_vlan_delete(p, old_pvid)) br_vlan_notify(br, p, old_pvid, 0, RTM_DELVLAN); br_vlan_notify(p->br, p, pvid, 0, RTM_NEWVLAN); __set_bit(p->port_no, changed); } br->default_pvid = pvid; out: bitmap_free(changed); return err; err_port: list_for_each_entry_continue_reverse(p, &br->port_list, list) { if (!test_bit(p->port_no, changed)) continue; if (old_pvid) { nbp_vlan_add(p, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, NULL); br_vlan_notify(p->br, p, old_pvid, 0, RTM_NEWVLAN); } nbp_vlan_delete(p, pvid); br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } if (test_bit(0, changed)) { if (old_pvid) { br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, NULL); br_vlan_notify(br, NULL, old_pvid, 0, RTM_NEWVLAN); } br_vlan_delete(br, pvid); br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } goto out; } int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { u16 pvid = val; int err = 0; if (val >= VLAN_VID_MASK) return -EINVAL; if (pvid == br->default_pvid) goto out; /* Only allow default pvid change when filtering is disabled */ if (br_opt_get(br, BROPT_VLAN_ENABLED)) { pr_info_once("Please disable vlan filtering to change default_pvid\n"); err = -EPERM; goto out; } err = __br_vlan_set_default_pvid(br, pvid, extack); out: return err; } int br_vlan_init(struct net_bridge *br) { struct net_bridge_vlan_group *vg; int ret = -ENOMEM; vg = kzalloc(sizeof(*vg), GFP_KERNEL); if (!vg) goto out; ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; ret = vlan_tunnel_init(vg); if (ret) goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; rcu_assign_pointer(br->vlgrp, vg); out: return ret; err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: kfree(vg); goto out; } int nbp_vlan_init(struct net_bridge_port *p, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = p->br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_filtering = br_opt_get(p->br, BROPT_VLAN_ENABLED), }; struct net_bridge_vlan_group *vg; int ret = -ENOMEM; vg = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); if (!vg) goto out; ret = switchdev_port_attr_set(p->dev, &attr, extack); if (ret && ret != -EOPNOTSUPP) goto err_vlan_enabled; ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; ret = vlan_tunnel_init(vg); if (ret) goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); rcu_assign_pointer(p->vlgrp, vg); if (p->br->default_pvid) { bool changed; ret = nbp_vlan_add(p, p->br->default_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &changed, extack); if (ret) goto err_vlan_add; br_vlan_notify(p->br, p, p->br->default_pvid, 0, RTM_NEWVLAN); } out: return ret; err_vlan_add: RCU_INIT_POINTER(p->vlgrp, NULL); synchronize_rcu(); vlan_tunnel_deinit(vg); err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: err_vlan_enabled: kfree(vg); goto out; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, bool *changed, struct netlink_ext_ack *extack) { struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); *changed = false; vlan = br_vlan_find(nbp_vlan_group(port), vid); if (vlan) { bool would_change = __vlan_flags_would_change(vlan, flags); if (would_change) { /* Pass the flags to the hardware bridge */ ret = br_switchdev_port_vlan_add(port->dev, vid, flags, true, extack); if (ret && ret != -EOPNOTSUPP) return ret; } __vlan_flags_commit(vlan, flags); *changed = would_change; return 0; } vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); if (!vlan) return -ENOMEM; vlan->vid = vid; vlan->port = port; ret = __vlan_add(vlan, flags, extack); if (ret) kfree(vlan); else *changed = true; return ret; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { struct net_bridge_vlan *v; ASSERT_RTNL(); v = br_vlan_find(nbp_vlan_group(port), vid); if (!v) return -ENOENT; br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); br_fdb_delete_by_port(port->br, port, vid, 0); return __vlan_del(v); } void nbp_vlan_flush(struct net_bridge_port *port) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = nbp_vlan_group(port); __vlan_flush(port->br, port, vg); RCU_INIT_POINTER(port->vlgrp, NULL); synchronize_rcu(); __vlan_group_free(vg); } void br_vlan_get_stats(const struct net_bridge_vlan *v, struct pcpu_sw_netstats *stats) { int i; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(i) { u64 rxpackets, rxbytes, txpackets, txbytes; struct pcpu_sw_netstats *cpu_stats; unsigned int start; cpu_stats = per_cpu_ptr(v->stats, i); do { start = u64_stats_fetch_begin(&cpu_stats->syncp); rxpackets = u64_stats_read(&cpu_stats->rx_packets); rxbytes = u64_stats_read(&cpu_stats->rx_bytes); txbytes = u64_stats_read(&cpu_stats->tx_bytes); txpackets = u64_stats_read(&cpu_stats->tx_packets); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->rx_packets, rxpackets); u64_stats_add(&stats->rx_bytes, rxbytes); u64_stats_add(&stats->tx_bytes, txbytes); u64_stats_add(&stats->tx_packets, txpackets); } } int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group(netdev_priv(dev)); else return -EINVAL; *p_pvid = br_get_pvid(vg); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid); int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p; p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group_rcu(netdev_priv(dev)); else return -EINVAL; *p_pvid = br_get_pvid(vg); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu); void br_vlan_fill_forward_path_pvid(struct net_bridge *br, struct net_device_path_ctx *ctx, struct net_device_path *path) { struct net_bridge_vlan_group *vg; int idx = ctx->num_vlans - 1; u16 vid; path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return; vg = br_vlan_group(br); if (idx >= 0 && ctx->vlan[idx].proto == br->vlan_proto) { vid = ctx->vlan[idx].id; } else { path->bridge.vlan_mode = DEV_PATH_BR_VLAN_TAG; vid = br_get_pvid(vg); } path->bridge.vlan_id = vid; path->bridge.vlan_proto = br->vlan_proto; } int br_vlan_fill_forward_path_mode(struct net_bridge *br, struct net_bridge_port *dst, struct net_device_path *path) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return 0; vg = nbp_vlan_group_rcu(dst); v = br_vlan_find(vg, path->bridge.vlan_id); if (!v || !br_vlan_should_use(v)) return -EINVAL; if (!(v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) return 0; if (path->bridge.vlan_mode == DEV_PATH_BR_VLAN_TAG) path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; else if (v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG_HW; else path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG; return 0; } int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group(netdev_priv(dev)); else return -EINVAL; v = br_vlan_find(vg, vid); if (!v) return -ENOENT; p_vinfo->vid = vid; p_vinfo->flags = v->flags; if (vid == br_get_pvid(vg)) p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_info); int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group_rcu(netdev_priv(dev)); else return -EINVAL; v = br_vlan_find(vg, vid); if (!v) return -ENOENT; p_vinfo->vid = vid; p_vinfo->flags = v->flags; if (vid == br_get_pvid(vg)) p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_info_rcu); static int br_vlan_is_bind_vlan_dev(const struct net_device *dev) { return is_vlan_dev(dev) && !!(vlan_dev_priv(dev)->flags & VLAN_FLAG_BRIDGE_BINDING); } static int br_vlan_is_bind_vlan_dev_fn(struct net_device *dev, __always_unused struct netdev_nested_priv *priv) { return br_vlan_is_bind_vlan_dev(dev); } static bool br_vlan_has_upper_bind_vlan_dev(struct net_device *dev) { int found; rcu_read_lock(); found = netdev_walk_all_upper_dev_rcu(dev, br_vlan_is_bind_vlan_dev_fn, NULL); rcu_read_unlock(); return !!found; } struct br_vlan_bind_walk_data { u16 vid; struct net_device *result; }; static int br_vlan_match_bind_vlan_dev_fn(struct net_device *dev, struct netdev_nested_priv *priv) { struct br_vlan_bind_walk_data *data = priv->data; int found = 0; if (br_vlan_is_bind_vlan_dev(dev) && vlan_dev_priv(dev)->vlan_id == data->vid) { data->result = dev; found = 1; } return found; } static struct net_device * br_vlan_get_upper_bind_vlan_dev(struct net_device *dev, u16 vid) { struct br_vlan_bind_walk_data data = { .vid = vid, }; struct netdev_nested_priv priv = { .data = (void *)&data, }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_match_bind_vlan_dev_fn, &priv); rcu_read_unlock(); return data.result; } static bool br_vlan_is_dev_up(const struct net_device *dev) { return !!(dev->flags & IFF_UP) && netif_oper_up(dev); } static void br_vlan_set_vlan_dev_state(const struct net_bridge *br, struct net_device *vlan_dev) { u16 vid = vlan_dev_priv(vlan_dev)->vlan_id; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; bool has_carrier = false; if (!netif_carrier_ok(br->dev)) { netif_carrier_off(vlan_dev); return; } list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); if (br_vlan_find(vg, vid) && br_vlan_is_dev_up(p->dev)) { has_carrier = true; break; } } if (has_carrier) netif_carrier_on(vlan_dev); else netif_carrier_off(vlan_dev); } static void br_vlan_set_all_vlan_dev_state(struct net_bridge_port *p) { struct net_bridge_vlan_group *vg = nbp_vlan_group(p); struct net_bridge_vlan *vlan; struct net_device *vlan_dev; list_for_each_entry(vlan, &vg->vlan_list, vlist) { vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vlan->vid); if (vlan_dev) { if (br_vlan_is_dev_up(p->dev)) { if (netif_carrier_ok(p->br->dev)) netif_carrier_on(vlan_dev); } else { br_vlan_set_vlan_dev_state(p->br, vlan_dev); } } } } static void br_vlan_upper_change(struct net_device *dev, struct net_device *upper_dev, bool linking) { struct net_bridge *br = netdev_priv(dev); if (!br_vlan_is_bind_vlan_dev(upper_dev)) return; if (linking) { br_vlan_set_vlan_dev_state(br, upper_dev); br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, true); } else { br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, br_vlan_has_upper_bind_vlan_dev(dev)); } } struct br_vlan_link_state_walk_data { struct net_bridge *br; }; static int br_vlan_link_state_change_fn(struct net_device *vlan_dev, struct netdev_nested_priv *priv) { struct br_vlan_link_state_walk_data *data = priv->data; if (br_vlan_is_bind_vlan_dev(vlan_dev)) br_vlan_set_vlan_dev_state(data->br, vlan_dev); return 0; } static void br_vlan_link_state_change(struct net_device *dev, struct net_bridge *br) { struct br_vlan_link_state_walk_data data = { .br = br }; struct netdev_nested_priv priv = { .data = (void *)&data, }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_link_state_change_fn, &priv); rcu_read_unlock(); } /* Must be protected by RTNL. */ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid) { struct net_device *vlan_dev; if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING)) return; vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vid); if (vlan_dev) br_vlan_set_vlan_dev_state(p->br, vlan_dev); } /* Must be protected by RTNL. */ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; struct net_bridge *br = netdev_priv(dev); int vlcmd = 0, ret = 0; bool changed = false; switch (event) { case NETDEV_REGISTER: ret = br_vlan_add(br, br->default_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); vlcmd = RTM_NEWVLAN; break; case NETDEV_UNREGISTER: changed = !br_vlan_delete(br, br->default_pvid); vlcmd = RTM_DELVLAN; break; case NETDEV_CHANGEUPPER: info = ptr; br_vlan_upper_change(dev, info->upper_dev, info->linking); break; case NETDEV_CHANGE: case NETDEV_UP: if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING)) break; br_vlan_link_state_change(dev, br); break; } if (changed) br_vlan_notify(br, NULL, br->default_pvid, 0, vlcmd); return ret; } /* Must be protected by RTNL. */ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event) { if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING)) return; switch (event) { case NETDEV_CHANGE: case NETDEV_DOWN: case NETDEV_UP: br_vlan_set_all_vlan_dev_state(p); break; } } static bool br_vlan_stats_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) { struct pcpu_sw_netstats stats; struct nlattr *nest; nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY_STATS); if (!nest) return false; br_vlan_get_stats(v, &stats); if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_BYTES, u64_stats_read(&stats.rx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_PACKETS, u64_stats_read(&stats.rx_packets), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_BYTES, u64_stats_read(&stats.tx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_PACKETS, u64_stats_read(&stats.tx_packets), BRIDGE_VLANDB_STATS_PAD)) goto out_err; nla_nest_end(skb, nest); return true; out_err: nla_nest_cancel(skb, nest); return false; } /* v_opts is used to dump the options which must be equal in the whole range */ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts, const struct net_bridge_port *p, u16 flags, bool dump_stats) { struct bridge_vlan_info info; struct nlattr *nest; nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY); if (!nest) return false; memset(&info, 0, sizeof(info)); info.vid = vid; if (flags & BRIDGE_VLAN_INFO_UNTAGGED) info.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (flags & BRIDGE_VLAN_INFO_PVID) info.flags |= BRIDGE_VLAN_INFO_PVID; if (nla_put(skb, BRIDGE_VLANDB_ENTRY_INFO, sizeof(info), &info)) goto out_err; if (vid_range && vid < vid_range && !(flags & BRIDGE_VLAN_INFO_PVID) && nla_put_u16(skb, BRIDGE_VLANDB_ENTRY_RANGE, vid_range)) goto out_err; if (v_opts) { if (!br_vlan_opts_fill(skb, v_opts, p)) goto out_err; if (dump_stats && !br_vlan_stats_fill(skb, v_opts)) goto out_err; } nla_nest_end(skb, nest); return true; out_err: nla_nest_cancel(skb, nest); return false; } static size_t rtnl_vlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct br_vlan_msg)) + nla_total_size(0) /* BRIDGE_VLANDB_ENTRY */ + nla_total_size(sizeof(u16)) /* BRIDGE_VLANDB_ENTRY_RANGE */ + nla_total_size(sizeof(struct bridge_vlan_info)) /* BRIDGE_VLANDB_ENTRY_INFO */ + br_vlan_opts_nl_size(); /* bridge vlan options */ } void br_vlan_notify(const struct net_bridge *br, const struct net_bridge_port *p, u16 vid, u16 vid_range, int cmd) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v = NULL; struct br_vlan_msg *bvm; struct nlmsghdr *nlh; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 flags = 0; int ifindex; /* right now notifications are done only with rtnl held */ ASSERT_RTNL(); if (p) { ifindex = p->dev->ifindex; vg = nbp_vlan_group(p); net = dev_net(p->dev); } else { ifindex = br->dev->ifindex; vg = br_vlan_group(br); net = dev_net(br->dev); } skb = nlmsg_new(rtnl_vlan_nlmsg_size(), GFP_KERNEL); if (!skb) goto out_err; err = -EMSGSIZE; nlh = nlmsg_put(skb, 0, 0, cmd, sizeof(*bvm), 0); if (!nlh) goto out_err; bvm = nlmsg_data(nlh); memset(bvm, 0, sizeof(*bvm)); bvm->family = AF_BRIDGE; bvm->ifindex = ifindex; switch (cmd) { case RTM_NEWVLAN: /* need to find the vlan due to flags/options */ v = br_vlan_find(vg, vid); if (!v || !br_vlan_should_use(v)) goto out_kfree; flags = v->flags; if (br_get_pvid(vg) == v->vid) flags |= BRIDGE_VLAN_INFO_PVID; break; case RTM_DELVLAN: break; default: goto out_kfree; } if (!br_vlan_fill_vids(skb, vid, vid_range, v, p, flags, false)) goto out_err; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_BRVLAN, NULL, GFP_KERNEL); return; out_err: rtnl_set_sk_err(net, RTNLGRP_BRVLAN, err); out_kfree: kfree_skb(skb); } /* check if v_curr can enter a range ending in range_end */ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end) { return v_curr->vid - range_end->vid == 1 && range_end->flags == v_curr->flags && br_vlan_opts_eq_range(v_curr, range_end); } static int br_vlan_dump_dev(const struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb, u32 dump_flags) { struct net_bridge_vlan *v, *range_start = NULL, *range_end = NULL; bool dump_global = !!(dump_flags & BRIDGE_VLANDB_DUMPF_GLOBAL); bool dump_stats = !!(dump_flags & BRIDGE_VLANDB_DUMPF_STATS); struct net_bridge_vlan_group *vg; int idx = 0, s_idx = cb->args[1]; struct nlmsghdr *nlh = NULL; struct net_bridge_port *p; struct br_vlan_msg *bvm; struct net_bridge *br; int err = 0; u16 pvid; if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) return -EINVAL; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); p = NULL; } else { /* global options are dumped only for bridge devices */ if (dump_global) return 0; p = br_port_get_rcu(dev); if (WARN_ON(!p)) return -EINVAL; vg = nbp_vlan_group_rcu(p); br = p->br; } if (!vg) return 0; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWVLAN, sizeof(*bvm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; bvm = nlmsg_data(nlh); memset(bvm, 0, sizeof(*bvm)); bvm->family = PF_BRIDGE; bvm->ifindex = dev->ifindex; pvid = br_get_pvid(vg); /* idx must stay at range's beginning until it is filled in */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!dump_global && !br_vlan_should_use(v)) continue; if (idx < s_idx) { idx++; continue; } if (!range_start) { range_start = v; range_end = v; continue; } if (dump_global) { if (br_vlan_global_opts_can_enter_range(v, range_end)) goto update_end; if (!br_vlan_global_opts_fill(skb, range_start->vid, range_end->vid, range_start)) { err = -EMSGSIZE; break; } /* advance number of filled vlans */ idx += range_end->vid - range_start->vid + 1; range_start = v; } else if (dump_stats || v->vid == pvid || !br_vlan_can_enter_range(v, range_end)) { u16 vlan_flags = br_vlan_flags(range_start, pvid); if (!br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, p, vlan_flags, dump_stats)) { err = -EMSGSIZE; break; } /* advance number of filled vlans */ idx += range_end->vid - range_start->vid + 1; range_start = v; } update_end: range_end = v; } /* err will be 0 and range_start will be set in 3 cases here: * - first vlan (range_start == range_end) * - last vlan (range_start == range_end, not in range) * - last vlan range (range_start != range_end, in range) */ if (!err && range_start) { if (dump_global && !br_vlan_global_opts_fill(skb, range_start->vid, range_end->vid, range_start)) err = -EMSGSIZE; else if (!dump_global && !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, p, br_vlan_flags(range_start, pvid), dump_stats)) err = -EMSGSIZE; } cb->args[1] = err ? idx : 0; nlmsg_end(skb, nlh); return err; } static const struct nla_policy br_vlan_db_dump_pol[BRIDGE_VLANDB_DUMP_MAX + 1] = { [BRIDGE_VLANDB_DUMP_FLAGS] = { .type = NLA_U32 }, }; static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *dtb[BRIDGE_VLANDB_DUMP_MAX + 1]; int idx = 0, err = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); struct br_vlan_msg *bvm; struct net_device *dev; u32 dump_flags = 0; err = nlmsg_parse(cb->nlh, sizeof(*bvm), dtb, BRIDGE_VLANDB_DUMP_MAX, br_vlan_db_dump_pol, cb->extack); if (err < 0) return err; bvm = nlmsg_data(cb->nlh); if (dtb[BRIDGE_VLANDB_DUMP_FLAGS]) dump_flags = nla_get_u32(dtb[BRIDGE_VLANDB_DUMP_FLAGS]); rcu_read_lock(); if (bvm->ifindex) { dev = dev_get_by_index_rcu(net, bvm->ifindex); if (!dev) { err = -ENODEV; goto out_err; } err = br_vlan_dump_dev(dev, skb, cb, dump_flags); /* if the dump completed without an error we return 0 here */ if (err != -EMSGSIZE) goto out_err; } else { for_each_netdev_rcu(net, dev) { if (idx < s_idx) goto skip; err = br_vlan_dump_dev(dev, skb, cb, dump_flags); if (err == -EMSGSIZE) break; skip: idx++; } } cb->args[0] = idx; rcu_read_unlock(); return skb->len; out_err: rcu_read_unlock(); return err; } static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = { [BRIDGE_VLANDB_ENTRY_INFO] = NLA_POLICY_EXACT_LEN(sizeof(struct bridge_vlan_info)), [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 }, [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, [BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS] = { .type = NLA_REJECT }, [BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, [BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1), }; static int br_vlan_rtm_process_one(struct net_device *dev, const struct nlattr *attr, int cmd, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo, vrange_end, *vinfo_last = NULL; struct nlattr *tb[BRIDGE_VLANDB_ENTRY_MAX + 1]; bool changed = false, skip_processing = false; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; int err = 0, cmdmap = 0; struct net_bridge *br; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { p = br_port_get_rtnl(dev); if (WARN_ON(!p)) return -ENODEV; br = p->br; vg = nbp_vlan_group(p); } if (WARN_ON(!vg)) return -ENODEV; err = nla_parse_nested(tb, BRIDGE_VLANDB_ENTRY_MAX, attr, br_vlan_db_policy, extack); if (err) return err; if (!tb[BRIDGE_VLANDB_ENTRY_INFO]) { NL_SET_ERR_MSG_MOD(extack, "Missing vlan entry info"); return -EINVAL; } memset(&vrange_end, 0, sizeof(vrange_end)); vinfo = nla_data(tb[BRIDGE_VLANDB_ENTRY_INFO]); if (vinfo->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN | BRIDGE_VLAN_INFO_RANGE_END)) { NL_SET_ERR_MSG_MOD(extack, "Old-style vlan ranges are not allowed when using RTM vlan calls"); return -EINVAL; } if (!br_vlan_valid_id(vinfo->vid, extack)) return -EINVAL; if (tb[BRIDGE_VLANDB_ENTRY_RANGE]) { vrange_end.vid = nla_get_u16(tb[BRIDGE_VLANDB_ENTRY_RANGE]); /* validate user-provided flags without RANGE_BEGIN */ vrange_end.flags = BRIDGE_VLAN_INFO_RANGE_END | vinfo->flags; vinfo->flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN; /* vinfo_last is the range start, vinfo the range end */ vinfo_last = vinfo; vinfo = &vrange_end; if (!br_vlan_valid_id(vinfo->vid, extack) || !br_vlan_valid_range(vinfo, vinfo_last, extack)) return -EINVAL; } switch (cmd) { case RTM_NEWVLAN: cmdmap = RTM_SETLINK; skip_processing = !!(vinfo->flags & BRIDGE_VLAN_INFO_ONLY_OPTS); break; case RTM_DELVLAN: cmdmap = RTM_DELLINK; break; } if (!skip_processing) { struct bridge_vlan_info *tmp_last = vinfo_last; /* br_process_vlan_info may overwrite vinfo_last */ err = br_process_vlan_info(br, p, cmdmap, vinfo, &tmp_last, &changed, extack); /* notify first if anything changed */ if (changed) br_ifinfo_notify(cmdmap, br, p); if (err) return err; } /* deal with options */ if (cmd == RTM_NEWVLAN) { struct net_bridge_vlan *range_start, *range_end; if (vinfo_last) { range_start = br_vlan_find(vg, vinfo_last->vid); range_end = br_vlan_find(vg, vinfo->vid); } else { range_start = br_vlan_find(vg, vinfo->vid); range_end = range_start; } err = br_vlan_process_options(br, p, range_start, range_end, tb, extack); } return err; } static int br_vlan_rtm_process(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct br_vlan_msg *bvm; struct net_device *dev; struct nlattr *attr; int err, vlans = 0; int rem; /* this should validate the header and check for remaining bytes */ err = nlmsg_parse(nlh, sizeof(*bvm), NULL, BRIDGE_VLANDB_MAX, NULL, extack); if (err < 0) return err; bvm = nlmsg_data(nlh); dev = __dev_get_by_index(net, bvm->ifindex); if (!dev) return -ENODEV; if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) { NL_SET_ERR_MSG_MOD(extack, "The device is not a valid bridge or bridge port"); return -EINVAL; } nlmsg_for_each_attr(attr, nlh, sizeof(*bvm), rem) { switch (nla_type(attr)) { case BRIDGE_VLANDB_ENTRY: err = br_vlan_rtm_process_one(dev, attr, nlh->nlmsg_type, extack); break; case BRIDGE_VLANDB_GLOBAL_OPTIONS: err = br_vlan_rtm_process_global_options(dev, attr, nlh->nlmsg_type, extack); break; default: continue; } vlans++; if (err) break; } if (!vlans) { NL_SET_ERR_MSG_MOD(extack, "No vlans found to process"); err = -EINVAL; } return err; } void br_vlan_rtnl_init(void) { rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_GETVLAN, NULL, br_vlan_rtm_dump, 0); rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_NEWVLAN, br_vlan_rtm_process, NULL, 0); rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_DELVLAN, br_vlan_rtm_process, NULL, 0); } void br_vlan_rtnl_uninit(void) { rtnl_unregister(PF_BRIDGE, RTM_GETVLAN); rtnl_unregister(PF_BRIDGE, RTM_NEWVLAN); rtnl_unregister(PF_BRIDGE, RTM_DELVLAN); } |
| 1 1 1 1 1 1 1 1 4 1 3 2 1 4 3 1 4 1 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | // SPDX-License-Identifier: GPL-2.0-only /* * AppArmor security module * * This file contains AppArmor /proc/<pid>/attr/ interface functions * * Copyright (C) 1998-2008 Novell/SUSE * Copyright 2009-2010 Canonical Ltd. */ #include "include/apparmor.h" #include "include/cred.h" #include "include/policy.h" #include "include/policy_ns.h" #include "include/domain.h" #include "include/procattr.h" /** * aa_getprocattr - Return the label information for @label * @label: the label to print label info about (NOT NULL) * @string: Returns - string containing the label info (NOT NULL) * @newline: indicates that a newline should be added * * Requires: label != NULL && string != NULL * * Creates a string containing the label information for @label. * * Returns: size of string placed in @string else error code on failure */ int aa_getprocattr(struct aa_label *label, char **string, bool newline) { struct aa_ns *ns = labels_ns(label); struct aa_ns *current_ns = aa_get_current_ns(); int len; if (!aa_ns_visible(current_ns, ns, true)) { aa_put_ns(current_ns); return -EACCES; } len = aa_label_snxprint(NULL, 0, current_ns, label, FLAG_SHOW_MODE | FLAG_VIEW_SUBNS | FLAG_HIDDEN_UNCONFINED); AA_BUG(len < 0); *string = kmalloc(len + 2, GFP_KERNEL); if (!*string) { aa_put_ns(current_ns); return -ENOMEM; } len = aa_label_snxprint(*string, len + 2, current_ns, label, FLAG_SHOW_MODE | FLAG_VIEW_SUBNS | FLAG_HIDDEN_UNCONFINED); if (len < 0) { aa_put_ns(current_ns); return len; } if (newline) (*string)[len++] = '\n'; (*string)[len] = 0; aa_put_ns(current_ns); return len; } /** * split_token_from_name - separate a string of form <token>^<name> * @op: operation being checked * @args: string to parse (NOT NULL) * @token: stores returned parsed token value (NOT NULL) * * Returns: start position of name after token else NULL on failure */ static char *split_token_from_name(const char *op, char *args, u64 *token) { char *name; *token = simple_strtoull(args, &name, 16); if ((name == args) || *name != '^') { AA_ERROR("%s: Invalid input '%s'", op, args); return ERR_PTR(-EINVAL); } name++; /* skip ^ */ if (!*name) name = NULL; return name; } /** * aa_setprocattr_changehat - handle procattr interface to change_hat * @args: args received from writing to /proc/<pid>/attr/current (NOT NULL) * @size: size of the args * @flags: set of flags governing behavior * * Returns: %0 or error code if change_hat fails */ int aa_setprocattr_changehat(char *args, size_t size, int flags) { char *hat; u64 token; const char *hats[16]; /* current hard limit on # of names */ int count = 0; hat = split_token_from_name(OP_CHANGE_HAT, args, &token); if (IS_ERR(hat)) return PTR_ERR(hat); if (!hat && !token) { AA_ERROR("change_hat: Invalid input, NULL hat and NULL magic"); return -EINVAL; } if (hat) { /* set up hat name vector, args guaranteed null terminated * at args[size] by setprocattr. * * If there are multiple hat names in the buffer each is * separated by a \0. Ie. userspace writes them pre tokenized */ char *end = args + size; for (count = 0; (hat < end) && count < 16; ++count) { char *next = hat + strlen(hat) + 1; hats[count] = hat; AA_DEBUG("%s: (pid %d) Magic 0x%llx count %d hat '%s'\n" , __func__, current->pid, token, count, hat); hat = next; } } else AA_DEBUG("%s: (pid %d) Magic 0x%llx count %d Hat '%s'\n", __func__, current->pid, token, count, "<NULL>"); return aa_change_hat(hats, count, token, flags); } |
| 30 21 21 2 2 2 2 2 2 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 * Phillip Lougher <phillip@squashfs.org.uk> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/pagemap.h> #include "squashfs_fs_sb.h" #include "decompressor.h" #include "page_actor.h" /* * This file contains implementations of page_actor for decompressing into * an intermediate buffer, and for decompressing directly into the * page cache. * * Calling code should avoid sleeping between calls to squashfs_first_page() * and squashfs_finish_page(). */ /* Implementation of page_actor for decompressing into intermediate buffer */ static void *cache_first_page(struct squashfs_page_actor *actor) { actor->next_page = 1; return actor->buffer[0]; } static void *cache_next_page(struct squashfs_page_actor *actor) { if (actor->next_page == actor->pages) return NULL; return actor->buffer[actor->next_page++]; } static void cache_finish_page(struct squashfs_page_actor *actor) { /* empty */ } struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, int pages, int length) { struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); if (actor == NULL) return NULL; actor->length = length ? : pages * PAGE_SIZE; actor->buffer = buffer; actor->pages = pages; actor->next_page = 0; actor->tmp_buffer = NULL; actor->squashfs_first_page = cache_first_page; actor->squashfs_next_page = cache_next_page; actor->squashfs_finish_page = cache_finish_page; return actor; } /* Implementation of page_actor for decompressing directly into page cache. */ static void *handle_next_page(struct squashfs_page_actor *actor) { int max_pages = (actor->length + PAGE_SIZE - 1) >> PAGE_SHIFT; if (actor->returned_pages == max_pages) return NULL; if ((actor->next_page == actor->pages) || (actor->next_index != actor->page[actor->next_page]->index)) { actor->next_index++; actor->returned_pages++; actor->last_page = NULL; return actor->alloc_buffer ? actor->tmp_buffer : ERR_PTR(-ENOMEM); } actor->next_index++; actor->returned_pages++; actor->last_page = actor->page[actor->next_page]; return actor->pageaddr = kmap_local_page(actor->page[actor->next_page++]); } static void *direct_first_page(struct squashfs_page_actor *actor) { return handle_next_page(actor); } static void *direct_next_page(struct squashfs_page_actor *actor) { if (actor->pageaddr) { kunmap_local(actor->pageaddr); actor->pageaddr = NULL; } return handle_next_page(actor); } static void direct_finish_page(struct squashfs_page_actor *actor) { if (actor->pageaddr) kunmap_local(actor->pageaddr); } struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_info *msblk, struct page **page, int pages, int length) { struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); if (actor == NULL) return NULL; if (msblk->decompressor->alloc_buffer) { actor->tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); if (actor->tmp_buffer == NULL) { kfree(actor); return NULL; } } else actor->tmp_buffer = NULL; actor->length = length ? : pages * PAGE_SIZE; actor->page = page; actor->pages = pages; actor->next_page = 0; actor->returned_pages = 0; actor->next_index = page[0]->index & ~((1 << (msblk->block_log - PAGE_SHIFT)) - 1); actor->pageaddr = NULL; actor->last_page = NULL; actor->alloc_buffer = msblk->decompressor->alloc_buffer; actor->squashfs_first_page = direct_first_page; actor->squashfs_next_page = direct_next_page; actor->squashfs_finish_page = direct_finish_page; return actor; } |
| 1633 26 2 518 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_NULLS_H #define _LINUX_LIST_NULLS_H #include <linux/poison.h> #include <linux/const.h> /* * Special version of lists, where end of list is not a NULL pointer, * but a 'nulls' marker, which can have many different values. * (up to 2^31 different values guaranteed on all platforms) * * In the standard hlist, termination of a list is the NULL pointer. * In this special 'nulls' variant, we use the fact that objects stored in * a list are aligned on a word (4 or 8 bytes alignment). * We therefore use the last significant bit of 'ptr' : * Set to 1 : This is a 'nulls' end-of-list marker (ptr >> 1) * Set to 0 : This is a pointer to some object (ptr) */ struct hlist_nulls_head { struct hlist_nulls_node *first; }; struct hlist_nulls_node { struct hlist_nulls_node *next, **pprev; }; #define NULLS_MARKER(value) (1UL | (((long)value) << 1)) #define INIT_HLIST_NULLS_HEAD(ptr, nulls) \ ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_nulls_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \ }) /** * ptr_is_a_nulls - Test if a ptr is a nulls * @ptr: ptr to be tested * */ static inline int is_a_nulls(const struct hlist_nulls_node *ptr) { return ((unsigned long)ptr & 1); } /** * get_nulls_value - Get the 'nulls' value of the end of chain * @ptr: end of chain * * Should be called only if is_a_nulls(ptr); */ static inline unsigned long get_nulls_value(const struct hlist_nulls_node *ptr) { return ((unsigned long)ptr) >> 1; } /** * hlist_nulls_unhashed - Has node been removed and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed state. * For example, hlist_del_init_rcu() leaves the node in unhashed state, * but hlist_nulls_del() does not. */ static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) { return !h->pprev; } /** * hlist_nulls_unhashed_lockless - Has node been removed and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed state. * For example, hlist_del_init_rcu() leaves the node in unhashed state, * but hlist_nulls_del() does not. Unlike hlist_nulls_unhashed(), this * function may be used locklessly. */ static inline int hlist_nulls_unhashed_lockless(const struct hlist_nulls_node *h) { return !READ_ONCE(h->pprev); } static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) { return is_a_nulls(READ_ONCE(h->first)); } static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); h->first = n; if (!is_a_nulls(first)) WRITE_ONCE(first->pprev, &n->next); } static inline void __hlist_nulls_del(struct hlist_nulls_node *n) { struct hlist_nulls_node *next = n->next; struct hlist_nulls_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (!is_a_nulls(next)) WRITE_ONCE(next->pprev, pprev); } static inline void hlist_nulls_del(struct hlist_nulls_node *n) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_nulls_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_nulls_for_each_entry(tpos, pos, head, member) \ for (pos = (head)->first; \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_nulls_for_each_entry_from - iterate over a hlist continuing from current point * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @member: the name of the hlist_node within the struct. * */ #define hlist_nulls_for_each_entry_from(tpos, pos, member) \ for (; (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) #endif |
| 34 34 1 12 28 3 34 13 13 13 13 1 1 1 11 3 3 3 3 1 1 2 2 3 2 3 1 28 28 28 27 28 28 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 | /* * Resizable simple ram filesystem for Linux. * * Copyright (C) 2000 Linus Torvalds. * 2000 Transmeta Corp. * * Usage limits added by David Gibson, Linuxcare Australia. * This file is released under the GPL. */ /* * NOTE! This filesystem is probably most useful * not as a real filesystem, but as an example of * how virtual filesystems can be written. * * It doesn't get much simpler than this. Consider * that this file implements the full semantics of * a POSIX-compliant read-write filesystem. * * Note in particular how the filesystem does not * need to implement any data structures of its own * to keep track of the virtual data: using the VFS * caches is sufficient. */ #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/time.h> #include <linux/init.h> #include <linux/string.h> #include <linux/backing-dev.h> #include <linux/ramfs.h> #include <linux/sched.h> #include <linux/parser.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/seq_file.h> #include "internal.h" struct ramfs_mount_opts { umode_t mode; }; struct ramfs_fs_info { struct ramfs_mount_opts mount_opts; }; #define RAMFS_DEFAULT_MODE 0755 static const struct super_operations ramfs_ops; static const struct inode_operations ramfs_dir_inode_operations; struct inode *ramfs_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode, dev_t dev) { struct inode * inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_mapping->a_ops = &ram_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); simple_inode_init_ts(inode); switch (mode & S_IFMT) { default: init_special_inode(inode, mode, dev); break; case S_IFREG: inode->i_op = &ramfs_file_inode_operations; inode->i_fop = &ramfs_file_operations; break; case S_IFDIR: inode->i_op = &ramfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; inode_nohighmem(inode); break; } } return inode; } /* * File creation. Allocate an inode, and we're done.. */ /* SMP-safe */ static int ramfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode * inode = ramfs_get_inode(dir->i_sb, dir, mode, dev); int error = -ENOSPC; if (inode) { d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ error = 0; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); } return error; } static int ramfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int retval = ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); return retval; } static int ramfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0); } static int ramfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct inode *inode; int error = -ENOSPC; inode = ramfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0); if (inode) { int l = strlen(symname)+1; error = page_symlink(inode, symname, l); if (!error) { d_instantiate(dentry, inode); dget(dentry); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); } else iput(inode); } return error; } static int ramfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode; inode = ramfs_get_inode(dir->i_sb, dir, mode, 0); if (!inode) return -ENOSPC; d_tmpfile(file, inode); return finish_open_simple(file, 0); } static const struct inode_operations ramfs_dir_inode_operations = { .create = ramfs_create, .lookup = simple_lookup, .link = simple_link, .unlink = simple_unlink, .symlink = ramfs_symlink, .mkdir = ramfs_mkdir, .rmdir = simple_rmdir, .mknod = ramfs_mknod, .rename = simple_rename, .tmpfile = ramfs_tmpfile, }; /* * Display the mount options in /proc/mounts. */ static int ramfs_show_options(struct seq_file *m, struct dentry *root) { struct ramfs_fs_info *fsi = root->d_sb->s_fs_info; if (fsi->mount_opts.mode != RAMFS_DEFAULT_MODE) seq_printf(m, ",mode=%o", fsi->mount_opts.mode); return 0; } static const struct super_operations ramfs_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = ramfs_show_options, }; enum ramfs_param { Opt_mode, }; const struct fs_parameter_spec ramfs_fs_parameters[] = { fsparam_u32oct("mode", Opt_mode), {} }; static int ramfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; struct ramfs_fs_info *fsi = fc->s_fs_info; int opt; opt = fs_parse(fc, ramfs_fs_parameters, param, &result); if (opt == -ENOPARAM) { opt = vfs_parse_fs_param_source(fc, param); if (opt != -ENOPARAM) return opt; /* * We might like to report bad mount options here; * but traditionally ramfs has ignored all mount options, * and as it is used as a !CONFIG_SHMEM simple substitute * for tmpfs, better continue to ignore other mount options. */ return 0; } if (opt < 0) return opt; switch (opt) { case Opt_mode: fsi->mount_opts.mode = result.uint_32 & S_IALLUGO; break; } return 0; } static int ramfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct ramfs_fs_info *fsi = sb->s_fs_info; struct inode *inode; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = RAMFS_MAGIC; sb->s_op = &ramfs_ops; sb->s_time_gran = 1; inode = ramfs_get_inode(sb, NULL, S_IFDIR | fsi->mount_opts.mode, 0); sb->s_root = d_make_root(inode); if (!sb->s_root) return -ENOMEM; return 0; } static int ramfs_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, ramfs_fill_super); } static void ramfs_free_fc(struct fs_context *fc) { kfree(fc->s_fs_info); } static const struct fs_context_operations ramfs_context_ops = { .free = ramfs_free_fc, .parse_param = ramfs_parse_param, .get_tree = ramfs_get_tree, }; int ramfs_init_fs_context(struct fs_context *fc) { struct ramfs_fs_info *fsi; fsi = kzalloc(sizeof(*fsi), GFP_KERNEL); if (!fsi) return -ENOMEM; fsi->mount_opts.mode = RAMFS_DEFAULT_MODE; fc->s_fs_info = fsi; fc->ops = &ramfs_context_ops; return 0; } void ramfs_kill_sb(struct super_block *sb) { kfree(sb->s_fs_info); kill_litter_super(sb); } static struct file_system_type ramfs_fs_type = { .name = "ramfs", .init_fs_context = ramfs_init_fs_context, .parameters = ramfs_fs_parameters, .kill_sb = ramfs_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; static int __init init_ramfs_fs(void) { return register_filesystem(&ramfs_fs_type); } fs_initcall(init_ramfs_fs); |
| 12 12 11 11 12 18 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 | /* * linux/fs/nls/nls_cp874.c * * Charset cp874 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2026, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, /* 0x90*/ 0x0000, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, /* 0xa0*/ 0x00a0, 0x0e01, 0x0e02, 0x0e03, 0x0e04, 0x0e05, 0x0e06, 0x0e07, 0x0e08, 0x0e09, 0x0e0a, 0x0e0b, 0x0e0c, 0x0e0d, 0x0e0e, 0x0e0f, /* 0xb0*/ 0x0e10, 0x0e11, 0x0e12, 0x0e13, 0x0e14, 0x0e15, 0x0e16, 0x0e17, 0x0e18, 0x0e19, 0x0e1a, 0x0e1b, 0x0e1c, 0x0e1d, 0x0e1e, 0x0e1f, /* 0xc0*/ 0x0e20, 0x0e21, 0x0e22, 0x0e23, 0x0e24, 0x0e25, 0x0e26, 0x0e27, 0x0e28, 0x0e29, 0x0e2a, 0x0e2b, 0x0e2c, 0x0e2d, 0x0e2e, 0x0e2f, /* 0xd0*/ 0x0e30, 0x0e31, 0x0e32, 0x0e33, 0x0e34, 0x0e35, 0x0e36, 0x0e37, 0x0e38, 0x0e39, 0x0e3a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0e3f, /* 0xe0*/ 0x0e40, 0x0e41, 0x0e42, 0x0e43, 0x0e44, 0x0e45, 0x0e46, 0x0e47, 0x0e48, 0x0e49, 0x0e4a, 0x0e4b, 0x0e4c, 0x0e4d, 0x0e4e, 0x0e4f, /* 0xf0*/ 0x0e50, 0x0e51, 0x0e52, 0x0e53, 0x0e54, 0x0e55, 0x0e56, 0x0e57, 0x0e58, 0x0e59, 0x0e5a, 0x0e5b, 0x0000, 0x0000, 0x0000, 0x0000, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xa0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char page0e[256] = { 0x00, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0x00-0x07 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0x08-0x0f */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0x10-0x17 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0x18-0x1f */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0x20-0x27 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0x28-0x2f */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0x30-0x37 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0xdf, /* 0x38-0x3f */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0x40-0x47 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0x48-0x4f */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0x50-0x57 */ 0xf8, 0xf9, 0xfa, 0xfb, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x96, 0x97, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x91, 0x92, 0x00, 0x00, 0x93, 0x94, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x95, 0x00, 0x00, 0x00, 0x85, 0x00, /* 0x20-0x27 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page0e, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp874", .alias = "tis-620", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp874(void) { return register_nls(&table); } static void __exit exit_nls_cp874(void) { unregister_nls(&table); } module_init(init_nls_cp874) module_exit(exit_nls_cp874) MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS_NLS(tis-620); |
| 7 2 10 10 8 7 8 7 11 5 3 5 5 5 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 | // SPDX-License-Identifier: GPL-2.0-only /* * TCP Vegas congestion control * * This is based on the congestion detection/avoidance scheme described in * Lawrence S. Brakmo and Larry L. Peterson. * "TCP Vegas: End to end congestion avoidance on a global internet." * IEEE Journal on Selected Areas in Communication, 13(8):1465--1480, * October 1995. Available from: * ftp://ftp.cs.arizona.edu/xkernel/Papers/jsac.ps * * See http://www.cs.arizona.edu/xkernel/ for their implementation. * The main aspects that distinguish this implementation from the * Arizona Vegas implementation are: * o We do not change the loss detection or recovery mechanisms of * Linux in any way. Linux already recovers from losses quite well, * using fine-grained timers, NewReno, and FACK. * o To avoid the performance penalty imposed by increasing cwnd * only every-other RTT during slow start, we increase during * every RTT during slow start, just like Reno. * o Largely to allow continuous cwnd growth during slow start, * we use the rate at which ACKs come back as the "actual" * rate, rather than the rate at which data is sent. * o To speed convergence to the right rate, we set the cwnd * to achieve the right ("actual") rate when we exit slow start. * o To filter out the noise caused by delayed ACKs, we use the * minimum RTT sample observed during the last RTT to calculate * the actual rate. * o When the sender re-starts from idle, it waits until it has * received ACKs for an entire flight of new data before making * a cwnd adjustment decision. The original Vegas implementation * assumed senders never went idle. */ #include <linux/mm.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/inet_diag.h> #include <net/tcp.h> #include "tcp_vegas.h" static int alpha = 2; static int beta = 4; static int gamma = 1; module_param(alpha, int, 0644); MODULE_PARM_DESC(alpha, "lower bound of packets in network"); module_param(beta, int, 0644); MODULE_PARM_DESC(beta, "upper bound of packets in network"); module_param(gamma, int, 0644); MODULE_PARM_DESC(gamma, "limit on increase (scale by 2)"); /* There are several situations when we must "re-start" Vegas: * * o when a connection is established * o after an RTO * o after fast recovery * o when we send a packet and there is no outstanding * unacknowledged data (restarting an idle connection) * * In these circumstances we cannot do a Vegas calculation at the * end of the first RTT, because any calculation we do is using * stale info -- both the saved cwnd and congestion feedback are * stale. * * Instead we must wait until the completion of an RTT during * which we actually receive ACKs. */ static void vegas_enable(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct vegas *vegas = inet_csk_ca(sk); /* Begin taking Vegas samples next time we send something. */ vegas->doing_vegas_now = 1; /* Set the beginning of the next send window. */ vegas->beg_snd_nxt = tp->snd_nxt; vegas->cntRTT = 0; vegas->minRTT = 0x7fffffff; } /* Stop taking Vegas samples for now. */ static inline void vegas_disable(struct sock *sk) { struct vegas *vegas = inet_csk_ca(sk); vegas->doing_vegas_now = 0; } void tcp_vegas_init(struct sock *sk) { struct vegas *vegas = inet_csk_ca(sk); vegas->baseRTT = 0x7fffffff; vegas_enable(sk); } EXPORT_SYMBOL_GPL(tcp_vegas_init); /* Do RTT sampling needed for Vegas. * Basically we: * o min-filter RTT samples from within an RTT to get the current * propagation delay + queuing delay (we are min-filtering to try to * avoid the effects of delayed ACKs) * o min-filter RTT samples from a much longer window (forever for now) * to find the propagation delay (baseRTT) */ void tcp_vegas_pkts_acked(struct sock *sk, const struct ack_sample *sample) { struct vegas *vegas = inet_csk_ca(sk); u32 vrtt; if (sample->rtt_us < 0) return; /* Never allow zero rtt or baseRTT */ vrtt = sample->rtt_us + 1; /* Filter to find propagation delay: */ if (vrtt < vegas->baseRTT) vegas->baseRTT = vrtt; /* Find the min RTT during the last RTT to find * the current prop. delay + queuing delay: */ vegas->minRTT = min(vegas->minRTT, vrtt); vegas->cntRTT++; } EXPORT_SYMBOL_GPL(tcp_vegas_pkts_acked); void tcp_vegas_state(struct sock *sk, u8 ca_state) { if (ca_state == TCP_CA_Open) vegas_enable(sk); else vegas_disable(sk); } EXPORT_SYMBOL_GPL(tcp_vegas_state); /* * If the connection is idle and we are restarting, * then we don't want to do any Vegas calculations * until we get fresh RTT samples. So when we * restart, we reset our Vegas state to a clean * slate. After we get acks for this flight of * packets, _then_ we can make Vegas calculations * again. */ void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_CWND_RESTART || event == CA_EVENT_TX_START) tcp_vegas_init(sk); } EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event); static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp) { return min(tp->snd_ssthresh, tcp_snd_cwnd(tp)); } static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct vegas *vegas = inet_csk_ca(sk); if (!vegas->doing_vegas_now) { tcp_reno_cong_avoid(sk, ack, acked); return; } if (after(ack, vegas->beg_snd_nxt)) { /* Do the Vegas once-per-RTT cwnd adjustment. */ /* Save the extent of the current window so we can use this * at the end of the next RTT. */ vegas->beg_snd_nxt = tp->snd_nxt; /* We do the Vegas calculations only if we got enough RTT * samples that we can be reasonably sure that we got * at least one RTT sample that wasn't from a delayed ACK. * If we only had 2 samples total, * then that means we're getting only 1 ACK per RTT, which * means they're almost certainly delayed ACKs. * If we have 3 samples, we should be OK. */ if (vegas->cntRTT <= 2) { /* We don't have enough RTT samples to do the Vegas * calculation, so we'll behave like Reno. */ tcp_reno_cong_avoid(sk, ack, acked); } else { u32 rtt, diff; u64 target_cwnd; /* We have enough RTT samples, so, using the Vegas * algorithm, we determine if we should increase or * decrease cwnd, and by how much. */ /* Pluck out the RTT we are using for the Vegas * calculations. This is the min RTT seen during the * last RTT. Taking the min filters out the effects * of delayed ACKs, at the cost of noticing congestion * a bit later. */ rtt = vegas->minRTT; /* Calculate the cwnd we should have, if we weren't * going too fast. * * This is: * (actual rate in segments) * baseRTT */ target_cwnd = (u64)tcp_snd_cwnd(tp) * vegas->baseRTT; do_div(target_cwnd, rtt); /* Calculate the difference between the window we had, * and the window we would like to have. This quantity * is the "Diff" from the Arizona Vegas papers. */ diff = tcp_snd_cwnd(tp) * (rtt-vegas->baseRTT) / vegas->baseRTT; if (diff > gamma && tcp_in_slow_start(tp)) { /* Going too fast. Time to slow down * and switch to congestion avoidance. */ /* Set cwnd to match the actual rate * exactly: * cwnd = (actual rate) * baseRTT * Then we add 1 because the integer * truncation robs us of full link * utilization. */ tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp), (u32)target_cwnd + 1)); tp->snd_ssthresh = tcp_vegas_ssthresh(tp); } else if (tcp_in_slow_start(tp)) { /* Slow start. */ tcp_slow_start(tp, acked); } else { /* Congestion avoidance. */ /* Figure out where we would like cwnd * to be. */ if (diff > beta) { /* The old window was too fast, so * we slow down. */ tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) - 1); tp->snd_ssthresh = tcp_vegas_ssthresh(tp); } else if (diff < alpha) { /* We don't have enough extra packets * in the network, so speed up. */ tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + 1); } else { /* Sending just as fast as we * should be. */ } } if (tcp_snd_cwnd(tp) < 2) tcp_snd_cwnd_set(tp, 2); else if (tcp_snd_cwnd(tp) > tp->snd_cwnd_clamp) tcp_snd_cwnd_set(tp, tp->snd_cwnd_clamp); tp->snd_ssthresh = tcp_current_ssthresh(sk); } /* Wipe the slate clean for the next RTT. */ vegas->cntRTT = 0; vegas->minRTT = 0x7fffffff; } /* Use normal slow start */ else if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); } /* Extract info for Tcp socket info provided via netlink. */ size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { const struct vegas *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { info->vegas.tcpv_enabled = ca->doing_vegas_now; info->vegas.tcpv_rttcnt = ca->cntRTT; info->vegas.tcpv_rtt = ca->baseRTT; info->vegas.tcpv_minrtt = ca->minRTT; *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); } return 0; } EXPORT_SYMBOL_GPL(tcp_vegas_get_info); static struct tcp_congestion_ops tcp_vegas __read_mostly = { .init = tcp_vegas_init, .ssthresh = tcp_reno_ssthresh, .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = tcp_vegas_cong_avoid, .pkts_acked = tcp_vegas_pkts_acked, .set_state = tcp_vegas_state, .cwnd_event = tcp_vegas_cwnd_event, .get_info = tcp_vegas_get_info, .owner = THIS_MODULE, .name = "vegas", }; static int __init tcp_vegas_register(void) { BUILD_BUG_ON(sizeof(struct vegas) > ICSK_CA_PRIV_SIZE); tcp_register_congestion_control(&tcp_vegas); return 0; } static void __exit tcp_vegas_unregister(void) { tcp_unregister_congestion_control(&tcp_vegas); } module_init(tcp_vegas_register); module_exit(tcp_vegas_unregister); MODULE_AUTHOR("Stephen Hemminger"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("TCP Vegas"); |
| 15 11 5 17 17 9 17 17 9 8 17 17 17 16 17 17 17 10 17 9 9 17 15 15 3 1 3 17 17 17 10 6 6 2 10 10 2 10 2 8 3 17 17 17 13 13 2 4 9 9 7 9 5 6 3 14 14 14 14 14 14 14 14 9 14 14 13 13 14 14 14 13 3 13 13 13 44 44 14 44 44 17 17 17 1 14 14 1 6 14 17 14 14 17 17 14 14 14 14 14 44 16 13 13 44 44 16 16 16 44 8 8 8 9 9 16 16 16 16 16 16 44 41 41 41 41 41 44 16 13 13 16 16 16 13 16 16 16 16 7 44 8 44 2 44 7 5 44 42 14 44 12 12 44 44 14 41 14 14 14 14 14 14 14 3 2 2 2 2 2 9 9 6 16 24 14 14 14 10 9 14 14 14 44 44 43 43 16 16 16 44 10 9 10 10 10 44 6 6 6 6 6 44 44 44 44 44 43 44 44 44 44 44 44 10 10 10 10 10 10 44 6 6 6 6 6 6 44 44 14 44 44 44 44 44 44 17 17 16 17 14 12 6 6 12 44 44 44 44 44 44 44 44 44 43 44 44 14 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README */ #include <linux/time.h> #include <linux/slab.h> #include <linux/string.h> #include "reiserfs.h" #include <linux/buffer_head.h> /* * To make any changes in the tree we find a node that contains item * to be changed/deleted or position in the node we insert a new item * to. We call this node S. To do balancing we need to decide what we * will shift to left/right neighbor, or to a new node, where new item * will be etc. To make this analysis simpler we build virtual * node. Virtual node is an array of items, that will replace items of * node S. (For instance if we are going to delete an item, virtual * node does not contain it). Virtual node keeps information about * item sizes and types, mergeability of first and last items, sizes * of all entries in directory item. We use this array of items when * calculating what we can shift to neighbors and how many nodes we * have to have if we do not any shiftings, if we shift to left/right * neighbor or to both. */ /* * Takes item number in virtual node, returns number of item * that it has in source buffer */ static inline int old_item_num(int new_num, int affected_item_num, int mode) { if (mode == M_PASTE || mode == M_CUT || new_num < affected_item_num) return new_num; if (mode == M_INSERT) { RFALSE(new_num == 0, "vs-8005: for INSERT mode and item number of inserted item"); return new_num - 1; } RFALSE(mode != M_DELETE, "vs-8010: old_item_num: mode must be M_DELETE (mode = \'%c\'", mode); /* delete mode */ return new_num + 1; } static void create_virtual_node(struct tree_balance *tb, int h) { struct item_head *ih; struct virtual_node *vn = tb->tb_vn; int new_num; struct buffer_head *Sh; /* this comes from tb->S[h] */ Sh = PATH_H_PBUFFER(tb->tb_path, h); /* size of changed node */ vn->vn_size = MAX_CHILD_SIZE(Sh) - B_FREE_SPACE(Sh) + tb->insert_size[h]; /* for internal nodes array if virtual items is not created */ if (h) { vn->vn_nr_item = (vn->vn_size - DC_SIZE) / (DC_SIZE + KEY_SIZE); return; } /* number of items in virtual node */ vn->vn_nr_item = B_NR_ITEMS(Sh) + ((vn->vn_mode == M_INSERT) ? 1 : 0) - ((vn->vn_mode == M_DELETE) ? 1 : 0); /* first virtual item */ vn->vn_vi = (struct virtual_item *)(tb->tb_vn + 1); memset(vn->vn_vi, 0, vn->vn_nr_item * sizeof(struct virtual_item)); vn->vn_free_ptr += vn->vn_nr_item * sizeof(struct virtual_item); /* first item in the node */ ih = item_head(Sh, 0); /* define the mergeability for 0-th item (if it is not being deleted) */ if (op_is_left_mergeable(&ih->ih_key, Sh->b_size) && (vn->vn_mode != M_DELETE || vn->vn_affected_item_num)) vn->vn_vi[0].vi_type |= VI_TYPE_LEFT_MERGEABLE; /* * go through all items that remain in the virtual * node (except for the new (inserted) one) */ for (new_num = 0; new_num < vn->vn_nr_item; new_num++) { int j; struct virtual_item *vi = vn->vn_vi + new_num; int is_affected = ((new_num != vn->vn_affected_item_num) ? 0 : 1); if (is_affected && vn->vn_mode == M_INSERT) continue; /* get item number in source node */ j = old_item_num(new_num, vn->vn_affected_item_num, vn->vn_mode); vi->vi_item_len += ih_item_len(ih + j) + IH_SIZE; vi->vi_ih = ih + j; vi->vi_item = ih_item_body(Sh, ih + j); vi->vi_uarea = vn->vn_free_ptr; /* * FIXME: there is no check that item operation did not * consume too much memory */ vn->vn_free_ptr += op_create_vi(vn, vi, is_affected, tb->insert_size[0]); if (tb->vn_buf + tb->vn_buf_size < vn->vn_free_ptr) reiserfs_panic(tb->tb_sb, "vs-8030", "virtual node space consumed"); if (!is_affected) /* this is not being changed */ continue; if (vn->vn_mode == M_PASTE || vn->vn_mode == M_CUT) { vn->vn_vi[new_num].vi_item_len += tb->insert_size[0]; /* pointer to data which is going to be pasted */ vi->vi_new_data = vn->vn_data; } } /* virtual inserted item is not defined yet */ if (vn->vn_mode == M_INSERT) { struct virtual_item *vi = vn->vn_vi + vn->vn_affected_item_num; RFALSE(vn->vn_ins_ih == NULL, "vs-8040: item header of inserted item is not specified"); vi->vi_item_len = tb->insert_size[0]; vi->vi_ih = vn->vn_ins_ih; vi->vi_item = vn->vn_data; vi->vi_uarea = vn->vn_free_ptr; op_create_vi(vn, vi, 0 /*not pasted or cut */ , tb->insert_size[0]); } /* * set right merge flag we take right delimiting key and * check whether it is a mergeable item */ if (tb->CFR[0]) { struct reiserfs_key *key; key = internal_key(tb->CFR[0], tb->rkey[0]); if (op_is_left_mergeable(key, Sh->b_size) && (vn->vn_mode != M_DELETE || vn->vn_affected_item_num != B_NR_ITEMS(Sh) - 1)) vn->vn_vi[vn->vn_nr_item - 1].vi_type |= VI_TYPE_RIGHT_MERGEABLE; #ifdef CONFIG_REISERFS_CHECK if (op_is_left_mergeable(key, Sh->b_size) && !(vn->vn_mode != M_DELETE || vn->vn_affected_item_num != B_NR_ITEMS(Sh) - 1)) { /* * we delete last item and it could be merged * with right neighbor's first item */ if (! (B_NR_ITEMS(Sh) == 1 && is_direntry_le_ih(item_head(Sh, 0)) && ih_entry_count(item_head(Sh, 0)) == 1)) { /* * node contains more than 1 item, or item * is not directory item, or this item * contains more than 1 entry */ print_block(Sh, 0, -1, -1); reiserfs_panic(tb->tb_sb, "vs-8045", "rdkey %k, affected item==%d " "(mode==%c) Must be %c", key, vn->vn_affected_item_num, vn->vn_mode, M_DELETE); } } #endif } } /* * Using virtual node check, how many items can be * shifted to left neighbor */ static void check_left(struct tree_balance *tb, int h, int cur_free) { int i; struct virtual_node *vn = tb->tb_vn; struct virtual_item *vi; int d_size, ih_size; RFALSE(cur_free < 0, "vs-8050: cur_free (%d) < 0", cur_free); /* internal level */ if (h > 0) { tb->lnum[h] = cur_free / (DC_SIZE + KEY_SIZE); return; } /* leaf level */ if (!cur_free || !vn->vn_nr_item) { /* no free space or nothing to move */ tb->lnum[h] = 0; tb->lbytes = -1; return; } RFALSE(!PATH_H_PPARENT(tb->tb_path, 0), "vs-8055: parent does not exist or invalid"); vi = vn->vn_vi; if ((unsigned int)cur_free >= (vn->vn_size - ((vi->vi_type & VI_TYPE_LEFT_MERGEABLE) ? IH_SIZE : 0))) { /* all contents of S[0] fits into L[0] */ RFALSE(vn->vn_mode == M_INSERT || vn->vn_mode == M_PASTE, "vs-8055: invalid mode or balance condition failed"); tb->lnum[0] = vn->vn_nr_item; tb->lbytes = -1; return; } d_size = 0, ih_size = IH_SIZE; /* first item may be merge with last item in left neighbor */ if (vi->vi_type & VI_TYPE_LEFT_MERGEABLE) d_size = -((int)IH_SIZE), ih_size = 0; tb->lnum[0] = 0; for (i = 0; i < vn->vn_nr_item; i++, ih_size = IH_SIZE, d_size = 0, vi++) { d_size += vi->vi_item_len; if (cur_free >= d_size) { /* the item can be shifted entirely */ cur_free -= d_size; tb->lnum[0]++; continue; } /* the item cannot be shifted entirely, try to split it */ /* * check whether L[0] can hold ih and at least one byte * of the item body */ /* cannot shift even a part of the current item */ if (cur_free <= ih_size) { tb->lbytes = -1; return; } cur_free -= ih_size; tb->lbytes = op_check_left(vi, cur_free, 0, 0); if (tb->lbytes != -1) /* count partially shifted item */ tb->lnum[0]++; break; } return; } /* * Using virtual node check, how many items can be * shifted to right neighbor */ static void check_right(struct tree_balance *tb, int h, int cur_free) { int i; struct virtual_node *vn = tb->tb_vn; struct virtual_item *vi; int d_size, ih_size; RFALSE(cur_free < 0, "vs-8070: cur_free < 0"); /* internal level */ if (h > 0) { tb->rnum[h] = cur_free / (DC_SIZE + KEY_SIZE); return; } /* leaf level */ if (!cur_free || !vn->vn_nr_item) { /* no free space */ tb->rnum[h] = 0; tb->rbytes = -1; return; } RFALSE(!PATH_H_PPARENT(tb->tb_path, 0), "vs-8075: parent does not exist or invalid"); vi = vn->vn_vi + vn->vn_nr_item - 1; if ((unsigned int)cur_free >= (vn->vn_size - ((vi->vi_type & VI_TYPE_RIGHT_MERGEABLE) ? IH_SIZE : 0))) { /* all contents of S[0] fits into R[0] */ RFALSE(vn->vn_mode == M_INSERT || vn->vn_mode == M_PASTE, "vs-8080: invalid mode or balance condition failed"); tb->rnum[h] = vn->vn_nr_item; tb->rbytes = -1; return; } d_size = 0, ih_size = IH_SIZE; /* last item may be merge with first item in right neighbor */ if (vi->vi_type & VI_TYPE_RIGHT_MERGEABLE) d_size = -(int)IH_SIZE, ih_size = 0; tb->rnum[0] = 0; for (i = vn->vn_nr_item - 1; i >= 0; i--, d_size = 0, ih_size = IH_SIZE, vi--) { d_size += vi->vi_item_len; if (cur_free >= d_size) { /* the item can be shifted entirely */ cur_free -= d_size; tb->rnum[0]++; continue; } /* * check whether R[0] can hold ih and at least one * byte of the item body */ /* cannot shift even a part of the current item */ if (cur_free <= ih_size) { tb->rbytes = -1; return; } /* * R[0] can hold the header of the item and at least * one byte of its body */ cur_free -= ih_size; /* cur_free is still > 0 */ tb->rbytes = op_check_right(vi, cur_free); if (tb->rbytes != -1) /* count partially shifted item */ tb->rnum[0]++; break; } return; } /* * from - number of items, which are shifted to left neighbor entirely * to - number of item, which are shifted to right neighbor entirely * from_bytes - number of bytes of boundary item (or directory entries) * which are shifted to left neighbor * to_bytes - number of bytes of boundary item (or directory entries) * which are shifted to right neighbor */ static int get_num_ver(int mode, struct tree_balance *tb, int h, int from, int from_bytes, int to, int to_bytes, short *snum012, int flow) { int i; int units; struct virtual_node *vn = tb->tb_vn; int total_node_size, max_node_size, current_item_size; int needed_nodes; /* position of item we start filling node from */ int start_item; /* position of item we finish filling node by */ int end_item; /* * number of first bytes (entries for directory) of start_item-th item * we do not include into node that is being filled */ int start_bytes; /* * number of last bytes (entries for directory) of end_item-th item * we do node include into node that is being filled */ int end_bytes; /* * these are positions in virtual item of items, that are split * between S[0] and S1new and S1new and S2new */ int split_item_positions[2]; split_item_positions[0] = -1; split_item_positions[1] = -1; /* * We only create additional nodes if we are in insert or paste mode * or we are in replace mode at the internal level. If h is 0 and * the mode is M_REPLACE then in fix_nodes we change the mode to * paste or insert before we get here in the code. */ RFALSE(tb->insert_size[h] < 0 || (mode != M_INSERT && mode != M_PASTE), "vs-8100: insert_size < 0 in overflow"); max_node_size = MAX_CHILD_SIZE(PATH_H_PBUFFER(tb->tb_path, h)); /* * snum012 [0-2] - number of items, that lay * to S[0], first new node and second new node */ snum012[3] = -1; /* s1bytes */ snum012[4] = -1; /* s2bytes */ /* internal level */ if (h > 0) { i = ((to - from) * (KEY_SIZE + DC_SIZE) + DC_SIZE); if (i == max_node_size) return 1; return (i / max_node_size + 1); } /* leaf level */ needed_nodes = 1; total_node_size = 0; /* start from 'from'-th item */ start_item = from; /* skip its first 'start_bytes' units */ start_bytes = ((from_bytes != -1) ? from_bytes : 0); /* last included item is the 'end_item'-th one */ end_item = vn->vn_nr_item - to - 1; /* do not count last 'end_bytes' units of 'end_item'-th item */ end_bytes = (to_bytes != -1) ? to_bytes : 0; /* * go through all item beginning from the start_item-th item * and ending by the end_item-th item. Do not count first * 'start_bytes' units of 'start_item'-th item and last * 'end_bytes' of 'end_item'-th item */ for (i = start_item; i <= end_item; i++) { struct virtual_item *vi = vn->vn_vi + i; int skip_from_end = ((i == end_item) ? end_bytes : 0); RFALSE(needed_nodes > 3, "vs-8105: too many nodes are needed"); /* get size of current item */ current_item_size = vi->vi_item_len; /* * do not take in calculation head part (from_bytes) * of from-th item */ current_item_size -= op_part_size(vi, 0 /*from start */ , start_bytes); /* do not take in calculation tail part of last item */ current_item_size -= op_part_size(vi, 1 /*from end */ , skip_from_end); /* if item fits into current node entierly */ if (total_node_size + current_item_size <= max_node_size) { snum012[needed_nodes - 1]++; total_node_size += current_item_size; start_bytes = 0; continue; } /* * virtual item length is longer, than max size of item in * a node. It is impossible for direct item */ if (current_item_size > max_node_size) { RFALSE(is_direct_le_ih(vi->vi_ih), "vs-8110: " "direct item length is %d. It can not be longer than %d", current_item_size, max_node_size); /* we will try to split it */ flow = 1; } /* as we do not split items, take new node and continue */ if (!flow) { needed_nodes++; i--; total_node_size = 0; continue; } /* * calculate number of item units which fit into node being * filled */ { int free_space; free_space = max_node_size - total_node_size - IH_SIZE; units = op_check_left(vi, free_space, start_bytes, skip_from_end); /* * nothing fits into current node, take new * node and continue */ if (units == -1) { needed_nodes++, i--, total_node_size = 0; continue; } } /* something fits into the current node */ start_bytes += units; snum012[needed_nodes - 1 + 3] = units; if (needed_nodes > 2) reiserfs_warning(tb->tb_sb, "vs-8111", "split_item_position is out of range"); snum012[needed_nodes - 1]++; split_item_positions[needed_nodes - 1] = i; needed_nodes++; /* continue from the same item with start_bytes != -1 */ start_item = i; i--; total_node_size = 0; } /* * sum012[4] (if it is not -1) contains number of units of which * are to be in S1new, snum012[3] - to be in S0. They are supposed * to be S1bytes and S2bytes correspondingly, so recalculate */ if (snum012[4] > 0) { int split_item_num; int bytes_to_r, bytes_to_l; int bytes_to_S1new; split_item_num = split_item_positions[1]; bytes_to_l = ((from == split_item_num && from_bytes != -1) ? from_bytes : 0); bytes_to_r = ((end_item == split_item_num && end_bytes != -1) ? end_bytes : 0); bytes_to_S1new = ((split_item_positions[0] == split_item_positions[1]) ? snum012[3] : 0); /* s2bytes */ snum012[4] = op_unit_num(&vn->vn_vi[split_item_num]) - snum012[4] - bytes_to_r - bytes_to_l - bytes_to_S1new; if (vn->vn_vi[split_item_num].vi_index != TYPE_DIRENTRY && vn->vn_vi[split_item_num].vi_index != TYPE_INDIRECT) reiserfs_warning(tb->tb_sb, "vs-8115", "not directory or indirect item"); } /* now we know S2bytes, calculate S1bytes */ if (snum012[3] > 0) { int split_item_num; int bytes_to_r, bytes_to_l; int bytes_to_S2new; split_item_num = split_item_positions[0]; bytes_to_l = ((from == split_item_num && from_bytes != -1) ? from_bytes : 0); bytes_to_r = ((end_item == split_item_num && end_bytes != -1) ? end_bytes : 0); bytes_to_S2new = ((split_item_positions[0] == split_item_positions[1] && snum012[4] != -1) ? snum012[4] : 0); /* s1bytes */ snum012[3] = op_unit_num(&vn->vn_vi[split_item_num]) - snum012[3] - bytes_to_r - bytes_to_l - bytes_to_S2new; } return needed_nodes; } /* * Set parameters for balancing. * Performs write of results of analysis of balancing into structure tb, * where it will later be used by the functions that actually do the balancing. * Parameters: * tb tree_balance structure; * h current level of the node; * lnum number of items from S[h] that must be shifted to L[h]; * rnum number of items from S[h] that must be shifted to R[h]; * blk_num number of blocks that S[h] will be splitted into; * s012 number of items that fall into splitted nodes. * lbytes number of bytes which flow to the left neighbor from the * item that is not shifted entirely * rbytes number of bytes which flow to the right neighbor from the * item that is not shifted entirely * s1bytes number of bytes which flow to the first new node when * S[0] splits (this number is contained in s012 array) */ static void set_parameters(struct tree_balance *tb, int h, int lnum, int rnum, int blk_num, short *s012, int lb, int rb) { tb->lnum[h] = lnum; tb->rnum[h] = rnum; tb->blknum[h] = blk_num; /* only for leaf level */ if (h == 0) { if (s012 != NULL) { tb->s0num = *s012++; tb->snum[0] = *s012++; tb->snum[1] = *s012++; tb->sbytes[0] = *s012++; tb->sbytes[1] = *s012; } tb->lbytes = lb; tb->rbytes = rb; } PROC_INFO_ADD(tb->tb_sb, lnum[h], lnum); PROC_INFO_ADD(tb->tb_sb, rnum[h], rnum); PROC_INFO_ADD(tb->tb_sb, lbytes[h], lb); PROC_INFO_ADD(tb->tb_sb, rbytes[h], rb); } /* * check if node disappears if we shift tb->lnum[0] items to left * neighbor and tb->rnum[0] to the right one. */ static int is_leaf_removable(struct tree_balance *tb) { struct virtual_node *vn = tb->tb_vn; int to_left, to_right; int size; int remain_items; /* * number of items that will be shifted to left (right) neighbor * entirely */ to_left = tb->lnum[0] - ((tb->lbytes != -1) ? 1 : 0); to_right = tb->rnum[0] - ((tb->rbytes != -1) ? 1 : 0); remain_items = vn->vn_nr_item; /* how many items remain in S[0] after shiftings to neighbors */ remain_items -= (to_left + to_right); /* all content of node can be shifted to neighbors */ if (remain_items < 1) { set_parameters(tb, 0, to_left, vn->vn_nr_item - to_left, 0, NULL, -1, -1); return 1; } /* S[0] is not removable */ if (remain_items > 1 || tb->lbytes == -1 || tb->rbytes == -1) return 0; /* check whether we can divide 1 remaining item between neighbors */ /* get size of remaining item (in item units) */ size = op_unit_num(&vn->vn_vi[to_left]); if (tb->lbytes + tb->rbytes >= size) { set_parameters(tb, 0, to_left + 1, to_right + 1, 0, NULL, tb->lbytes, -1); return 1; } return 0; } /* check whether L, S, R can be joined in one node */ static int are_leaves_removable(struct tree_balance *tb, int lfree, int rfree) { struct virtual_node *vn = tb->tb_vn; int ih_size; struct buffer_head *S0; S0 = PATH_H_PBUFFER(tb->tb_path, 0); ih_size = 0; if (vn->vn_nr_item) { if (vn->vn_vi[0].vi_type & VI_TYPE_LEFT_MERGEABLE) ih_size += IH_SIZE; if (vn->vn_vi[vn->vn_nr_item - 1]. vi_type & VI_TYPE_RIGHT_MERGEABLE) ih_size += IH_SIZE; } else { /* there was only one item and it will be deleted */ struct item_head *ih; RFALSE(B_NR_ITEMS(S0) != 1, "vs-8125: item number must be 1: it is %d", B_NR_ITEMS(S0)); ih = item_head(S0, 0); if (tb->CFR[0] && !comp_short_le_keys(&ih->ih_key, internal_key(tb->CFR[0], tb->rkey[0]))) /* * Directory must be in correct state here: that is * somewhere at the left side should exist first * directory item. But the item being deleted can * not be that first one because its right neighbor * is item of the same directory. (But first item * always gets deleted in last turn). So, neighbors * of deleted item can be merged, so we can save * ih_size */ if (is_direntry_le_ih(ih)) { ih_size = IH_SIZE; /* * we might check that left neighbor exists * and is of the same directory */ RFALSE(le_ih_k_offset(ih) == DOT_OFFSET, "vs-8130: first directory item can not be removed until directory is not empty"); } } if (MAX_CHILD_SIZE(S0) + vn->vn_size <= rfree + lfree + ih_size) { set_parameters(tb, 0, -1, -1, -1, NULL, -1, -1); PROC_INFO_INC(tb->tb_sb, leaves_removable); return 1; } return 0; } /* when we do not split item, lnum and rnum are numbers of entire items */ #define SET_PAR_SHIFT_LEFT \ if (h)\ {\ int to_l;\ \ to_l = (MAX_NR_KEY(Sh)+1 - lpar + vn->vn_nr_item + 1) / 2 -\ (MAX_NR_KEY(Sh) + 1 - lpar);\ \ set_parameters (tb, h, to_l, 0, lnver, NULL, -1, -1);\ }\ else \ {\ if (lset==LEFT_SHIFT_FLOW)\ set_parameters (tb, h, lpar, 0, lnver, snum012+lset,\ tb->lbytes, -1);\ else\ set_parameters (tb, h, lpar - (tb->lbytes!=-1), 0, lnver, snum012+lset,\ -1, -1);\ } #define SET_PAR_SHIFT_RIGHT \ if (h)\ {\ int to_r;\ \ to_r = (MAX_NR_KEY(Sh)+1 - rpar + vn->vn_nr_item + 1) / 2 - (MAX_NR_KEY(Sh) + 1 - rpar);\ \ set_parameters (tb, h, 0, to_r, rnver, NULL, -1, -1);\ }\ else \ {\ if (rset==RIGHT_SHIFT_FLOW)\ set_parameters (tb, h, 0, rpar, rnver, snum012+rset,\ -1, tb->rbytes);\ else\ set_parameters (tb, h, 0, rpar - (tb->rbytes!=-1), rnver, snum012+rset,\ -1, -1);\ } static void free_buffers_in_tb(struct tree_balance *tb) { int i; pathrelse(tb->tb_path); for (i = 0; i < MAX_HEIGHT; i++) { brelse(tb->L[i]); brelse(tb->R[i]); brelse(tb->FL[i]); brelse(tb->FR[i]); brelse(tb->CFL[i]); brelse(tb->CFR[i]); tb->L[i] = NULL; tb->R[i] = NULL; tb->FL[i] = NULL; tb->FR[i] = NULL; tb->CFL[i] = NULL; tb->CFR[i] = NULL; } } /* * Get new buffers for storing new nodes that are created while balancing. * Returns: SCHEDULE_OCCURRED - schedule occurred while the function worked; * CARRY_ON - schedule didn't occur while the function worked; * NO_DISK_SPACE - no disk space. */ /* The function is NOT SCHEDULE-SAFE! */ static int get_empty_nodes(struct tree_balance *tb, int h) { struct buffer_head *new_bh, *Sh = PATH_H_PBUFFER(tb->tb_path, h); b_blocknr_t *blocknr, blocknrs[MAX_AMOUNT_NEEDED] = { 0, }; int counter, number_of_freeblk; int amount_needed; /* number of needed empty blocks */ int retval = CARRY_ON; struct super_block *sb = tb->tb_sb; /* * number_of_freeblk is the number of empty blocks which have been * acquired for use by the balancing algorithm minus the number of * empty blocks used in the previous levels of the analysis, * number_of_freeblk = tb->cur_blknum can be non-zero if a schedule * occurs after empty blocks are acquired, and the balancing analysis * is then restarted, amount_needed is the number needed by this * level (h) of the balancing analysis. * * Note that for systems with many processes writing, it would be * more layout optimal to calculate the total number needed by all * levels and then to run reiserfs_new_blocks to get all of them at * once. */ /* * Initiate number_of_freeblk to the amount acquired prior to the * restart of the analysis or 0 if not restarted, then subtract the * amount needed by all of the levels of the tree below h. */ /* blknum includes S[h], so we subtract 1 in this calculation */ for (counter = 0, number_of_freeblk = tb->cur_blknum; counter < h; counter++) number_of_freeblk -= (tb->blknum[counter]) ? (tb->blknum[counter] - 1) : 0; /* Allocate missing empty blocks. */ /* if Sh == 0 then we are getting a new root */ amount_needed = (Sh) ? (tb->blknum[h] - 1) : 1; /* * Amount_needed = the amount that we need more than the * amount that we have. */ if (amount_needed > number_of_freeblk) amount_needed -= number_of_freeblk; else /* If we have enough already then there is nothing to do. */ return CARRY_ON; /* * No need to check quota - is not allocated for blocks used * for formatted nodes */ if (reiserfs_new_form_blocknrs(tb, blocknrs, amount_needed) == NO_DISK_SPACE) return NO_DISK_SPACE; /* for each blocknumber we just got, get a buffer and stick it on FEB */ for (blocknr = blocknrs, counter = 0; counter < amount_needed; blocknr++, counter++) { RFALSE(!*blocknr, "PAP-8135: reiserfs_new_blocknrs failed when got new blocks"); new_bh = sb_getblk(sb, *blocknr); RFALSE(buffer_dirty(new_bh) || buffer_journaled(new_bh) || buffer_journal_dirty(new_bh), "PAP-8140: journaled or dirty buffer %b for the new block", new_bh); /* Put empty buffers into the array. */ RFALSE(tb->FEB[tb->cur_blknum], "PAP-8141: busy slot for new buffer"); set_buffer_journal_new(new_bh); tb->FEB[tb->cur_blknum++] = new_bh; } if (retval == CARRY_ON && FILESYSTEM_CHANGED_TB(tb)) retval = REPEAT_SEARCH; return retval; } /* * Get free space of the left neighbor, which is stored in the parent * node of the left neighbor. */ static int get_lfree(struct tree_balance *tb, int h) { struct buffer_head *l, *f; int order; if ((f = PATH_H_PPARENT(tb->tb_path, h)) == NULL || (l = tb->FL[h]) == NULL) return 0; if (f == l) order = PATH_H_B_ITEM_ORDER(tb->tb_path, h) - 1; else { order = B_NR_ITEMS(l); f = l; } return (MAX_CHILD_SIZE(f) - dc_size(B_N_CHILD(f, order))); } /* * Get free space of the right neighbor, * which is stored in the parent node of the right neighbor. */ static int get_rfree(struct tree_balance *tb, int h) { struct buffer_head *r, *f; int order; if ((f = PATH_H_PPARENT(tb->tb_path, h)) == NULL || (r = tb->FR[h]) == NULL) return 0; if (f == r) order = PATH_H_B_ITEM_ORDER(tb->tb_path, h) + 1; else { order = 0; f = r; } return (MAX_CHILD_SIZE(f) - dc_size(B_N_CHILD(f, order))); } /* Check whether left neighbor is in memory. */ static int is_left_neighbor_in_cache(struct tree_balance *tb, int h) { struct buffer_head *father, *left; struct super_block *sb = tb->tb_sb; b_blocknr_t left_neighbor_blocknr; int left_neighbor_position; /* Father of the left neighbor does not exist. */ if (!tb->FL[h]) return 0; /* Calculate father of the node to be balanced. */ father = PATH_H_PBUFFER(tb->tb_path, h + 1); RFALSE(!father || !B_IS_IN_TREE(father) || !B_IS_IN_TREE(tb->FL[h]) || !buffer_uptodate(father) || !buffer_uptodate(tb->FL[h]), "vs-8165: F[h] (%b) or FL[h] (%b) is invalid", father, tb->FL[h]); /* * Get position of the pointer to the left neighbor * into the left father. */ left_neighbor_position = (father == tb->FL[h]) ? tb->lkey[h] : B_NR_ITEMS(tb->FL[h]); /* Get left neighbor block number. */ left_neighbor_blocknr = B_N_CHILD_NUM(tb->FL[h], left_neighbor_position); /* Look for the left neighbor in the cache. */ if ((left = sb_find_get_block(sb, left_neighbor_blocknr))) { RFALSE(buffer_uptodate(left) && !B_IS_IN_TREE(left), "vs-8170: left neighbor (%b %z) is not in the tree", left, left); put_bh(left); return 1; } return 0; } #define LEFT_PARENTS 'l' #define RIGHT_PARENTS 'r' static void decrement_key(struct cpu_key *key) { /* call item specific function for this key */ item_ops[cpu_key_k_type(key)]->decrement_key(key); } /* * Calculate far left/right parent of the left/right neighbor of the * current node, that is calculate the left/right (FL[h]/FR[h]) neighbor * of the parent F[h]. * Calculate left/right common parent of the current node and L[h]/R[h]. * Calculate left/right delimiting key position. * Returns: PATH_INCORRECT - path in the tree is not correct * SCHEDULE_OCCURRED - schedule occurred while the function worked * CARRY_ON - schedule didn't occur while the function * worked */ static int get_far_parent(struct tree_balance *tb, int h, struct buffer_head **pfather, struct buffer_head **pcom_father, char c_lr_par) { struct buffer_head *parent; INITIALIZE_PATH(s_path_to_neighbor_father); struct treepath *path = tb->tb_path; struct cpu_key s_lr_father_key; int counter, position = INT_MAX, first_last_position = 0, path_offset = PATH_H_PATH_OFFSET(path, h); /* * Starting from F[h] go upwards in the tree, and look for the common * ancestor of F[h], and its neighbor l/r, that should be obtained. */ counter = path_offset; RFALSE(counter < FIRST_PATH_ELEMENT_OFFSET, "PAP-8180: invalid path length"); for (; counter > FIRST_PATH_ELEMENT_OFFSET; counter--) { /* * Check whether parent of the current buffer in the path * is really parent in the tree. */ if (!B_IS_IN_TREE (parent = PATH_OFFSET_PBUFFER(path, counter - 1))) return REPEAT_SEARCH; /* Check whether position in the parent is correct. */ if ((position = PATH_OFFSET_POSITION(path, counter - 1)) > B_NR_ITEMS(parent)) return REPEAT_SEARCH; /* * Check whether parent at the path really points * to the child. */ if (B_N_CHILD_NUM(parent, position) != PATH_OFFSET_PBUFFER(path, counter)->b_blocknr) return REPEAT_SEARCH; /* * Return delimiting key if position in the parent is not * equal to first/last one. */ if (c_lr_par == RIGHT_PARENTS) first_last_position = B_NR_ITEMS(parent); if (position != first_last_position) { *pcom_father = parent; get_bh(*pcom_father); /*(*pcom_father = parent)->b_count++; */ break; } } /* if we are in the root of the tree, then there is no common father */ if (counter == FIRST_PATH_ELEMENT_OFFSET) { /* * Check whether first buffer in the path is the * root of the tree. */ if (PATH_OFFSET_PBUFFER (tb->tb_path, FIRST_PATH_ELEMENT_OFFSET)->b_blocknr == SB_ROOT_BLOCK(tb->tb_sb)) { *pfather = *pcom_father = NULL; return CARRY_ON; } return REPEAT_SEARCH; } RFALSE(B_LEVEL(*pcom_father) <= DISK_LEAF_NODE_LEVEL, "PAP-8185: (%b %z) level too small", *pcom_father, *pcom_father); /* Check whether the common parent is locked. */ if (buffer_locked(*pcom_father)) { /* Release the write lock while the buffer is busy */ int depth = reiserfs_write_unlock_nested(tb->tb_sb); __wait_on_buffer(*pcom_father); reiserfs_write_lock_nested(tb->tb_sb, depth); if (FILESYSTEM_CHANGED_TB(tb)) { brelse(*pcom_father); return REPEAT_SEARCH; } } /* * So, we got common parent of the current node and its * left/right neighbor. Now we are getting the parent of the * left/right neighbor. */ /* Form key to get parent of the left/right neighbor. */ le_key2cpu_key(&s_lr_father_key, internal_key(*pcom_father, (c_lr_par == LEFT_PARENTS) ? (tb->lkey[h - 1] = position - 1) : (tb->rkey[h - 1] = position))); if (c_lr_par == LEFT_PARENTS) decrement_key(&s_lr_father_key); if (search_by_key (tb->tb_sb, &s_lr_father_key, &s_path_to_neighbor_father, h + 1) == IO_ERROR) /* path is released */ return IO_ERROR; if (FILESYSTEM_CHANGED_TB(tb)) { pathrelse(&s_path_to_neighbor_father); brelse(*pcom_father); return REPEAT_SEARCH; } *pfather = PATH_PLAST_BUFFER(&s_path_to_neighbor_father); RFALSE(B_LEVEL(*pfather) != h + 1, "PAP-8190: (%b %z) level too small", *pfather, *pfather); RFALSE(s_path_to_neighbor_father.path_length < FIRST_PATH_ELEMENT_OFFSET, "PAP-8192: path length is too small"); s_path_to_neighbor_father.path_length--; pathrelse(&s_path_to_neighbor_father); return CARRY_ON; } /* * Get parents of neighbors of node in the path(S[path_offset]) and * common parents of S[path_offset] and L[path_offset]/R[path_offset]: * F[path_offset], FL[path_offset], FR[path_offset], CFL[path_offset], * CFR[path_offset]. * Calculate numbers of left and right delimiting keys position: * lkey[path_offset], rkey[path_offset]. * Returns: SCHEDULE_OCCURRED - schedule occurred while the function worked * CARRY_ON - schedule didn't occur while the function worked */ static int get_parents(struct tree_balance *tb, int h) { struct treepath *path = tb->tb_path; int position, ret, path_offset = PATH_H_PATH_OFFSET(tb->tb_path, h); struct buffer_head *curf, *curcf; /* Current node is the root of the tree or will be root of the tree */ if (path_offset <= FIRST_PATH_ELEMENT_OFFSET) { /* * The root can not have parents. * Release nodes which previously were obtained as * parents of the current node neighbors. */ brelse(tb->FL[h]); brelse(tb->CFL[h]); brelse(tb->FR[h]); brelse(tb->CFR[h]); tb->FL[h] = NULL; tb->CFL[h] = NULL; tb->FR[h] = NULL; tb->CFR[h] = NULL; return CARRY_ON; } /* Get parent FL[path_offset] of L[path_offset]. */ position = PATH_OFFSET_POSITION(path, path_offset - 1); if (position) { /* Current node is not the first child of its parent. */ curf = PATH_OFFSET_PBUFFER(path, path_offset - 1); curcf = PATH_OFFSET_PBUFFER(path, path_offset - 1); get_bh(curf); get_bh(curf); tb->lkey[h] = position - 1; } else { /* * Calculate current parent of L[path_offset], which is the * left neighbor of the current node. Calculate current * common parent of L[path_offset] and the current node. * Note that CFL[path_offset] not equal FL[path_offset] and * CFL[path_offset] not equal F[path_offset]. * Calculate lkey[path_offset]. */ if ((ret = get_far_parent(tb, h + 1, &curf, &curcf, LEFT_PARENTS)) != CARRY_ON) return ret; } brelse(tb->FL[h]); tb->FL[h] = curf; /* New initialization of FL[h]. */ brelse(tb->CFL[h]); tb->CFL[h] = curcf; /* New initialization of CFL[h]. */ RFALSE((curf && !B_IS_IN_TREE(curf)) || (curcf && !B_IS_IN_TREE(curcf)), "PAP-8195: FL (%b) or CFL (%b) is invalid", curf, curcf); /* Get parent FR[h] of R[h]. */ /* Current node is the last child of F[h]. FR[h] != F[h]. */ if (position == B_NR_ITEMS(PATH_H_PBUFFER(path, h + 1))) { /* * Calculate current parent of R[h], which is the right * neighbor of F[h]. Calculate current common parent of * R[h] and current node. Note that CFR[h] not equal * FR[path_offset] and CFR[h] not equal F[h]. */ if ((ret = get_far_parent(tb, h + 1, &curf, &curcf, RIGHT_PARENTS)) != CARRY_ON) return ret; } else { /* Current node is not the last child of its parent F[h]. */ curf = PATH_OFFSET_PBUFFER(path, path_offset - 1); curcf = PATH_OFFSET_PBUFFER(path, path_offset - 1); get_bh(curf); get_bh(curf); tb->rkey[h] = position; } brelse(tb->FR[h]); /* New initialization of FR[path_offset]. */ tb->FR[h] = curf; brelse(tb->CFR[h]); /* New initialization of CFR[path_offset]. */ tb->CFR[h] = curcf; RFALSE((curf && !B_IS_IN_TREE(curf)) || (curcf && !B_IS_IN_TREE(curcf)), "PAP-8205: FR (%b) or CFR (%b) is invalid", curf, curcf); return CARRY_ON; } /* * it is possible to remove node as result of shiftings to * neighbors even when we insert or paste item. */ static inline int can_node_be_removed(int mode, int lfree, int sfree, int rfree, struct tree_balance *tb, int h) { struct buffer_head *Sh = PATH_H_PBUFFER(tb->tb_path, h); int levbytes = tb->insert_size[h]; struct item_head *ih; struct reiserfs_key *r_key = NULL; ih = item_head(Sh, 0); if (tb->CFR[h]) r_key = internal_key(tb->CFR[h], tb->rkey[h]); if (lfree + rfree + sfree < MAX_CHILD_SIZE(Sh) + levbytes /* shifting may merge items which might save space */ - ((!h && op_is_left_mergeable(&ih->ih_key, Sh->b_size)) ? IH_SIZE : 0) - ((!h && r_key && op_is_left_mergeable(r_key, Sh->b_size)) ? IH_SIZE : 0) + ((h) ? KEY_SIZE : 0)) { /* node can not be removed */ if (sfree >= levbytes) { /* new item fits into node S[h] without any shifting */ if (!h) tb->s0num = B_NR_ITEMS(Sh) + ((mode == M_INSERT) ? 1 : 0); set_parameters(tb, h, 0, 0, 1, NULL, -1, -1); return NO_BALANCING_NEEDED; } } PROC_INFO_INC(tb->tb_sb, can_node_be_removed[h]); return !NO_BALANCING_NEEDED; } /* * Check whether current node S[h] is balanced when increasing its size by * Inserting or Pasting. * Calculate parameters for balancing for current level h. * Parameters: * tb tree_balance structure; * h current level of the node; * inum item number in S[h]; * mode i - insert, p - paste; * Returns: 1 - schedule occurred; * 0 - balancing for higher levels needed; * -1 - no balancing for higher levels needed; * -2 - no disk space. */ /* ip means Inserting or Pasting */ static int ip_check_balance(struct tree_balance *tb, int h) { struct virtual_node *vn = tb->tb_vn; /* * Number of bytes that must be inserted into (value is negative * if bytes are deleted) buffer which contains node being balanced. * The mnemonic is that the attempted change in node space used * level is levbytes bytes. */ int levbytes; int ret; int lfree, sfree, rfree /* free space in L, S and R */ ; /* * nver is short for number of vertixes, and lnver is the number if * we shift to the left, rnver is the number if we shift to the * right, and lrnver is the number if we shift in both directions. * The goal is to minimize first the number of vertixes, and second, * the number of vertixes whose contents are changed by shifting, * and third the number of uncached vertixes whose contents are * changed by shifting and must be read from disk. */ int nver, lnver, rnver, lrnver; /* * used at leaf level only, S0 = S[0] is the node being balanced, * sInum [ I = 0,1,2 ] is the number of items that will * remain in node SI after balancing. S1 and S2 are new * nodes that might be created. */ /* * we perform 8 calls to get_num_ver(). For each call we * calculate five parameters. where 4th parameter is s1bytes * and 5th - s2bytes * * s0num, s1num, s2num for 8 cases * 0,1 - do not shift and do not shift but bottle * 2 - shift only whole item to left * 3 - shift to left and bottle as much as possible * 4,5 - shift to right (whole items and as much as possible * 6,7 - shift to both directions (whole items and as much as possible) */ short snum012[40] = { 0, }; /* Sh is the node whose balance is currently being checked */ struct buffer_head *Sh; Sh = PATH_H_PBUFFER(tb->tb_path, h); levbytes = tb->insert_size[h]; /* Calculate balance parameters for creating new root. */ if (!Sh) { if (!h) reiserfs_panic(tb->tb_sb, "vs-8210", "S[0] can not be 0"); switch (ret = get_empty_nodes(tb, h)) { /* no balancing for higher levels needed */ case CARRY_ON: set_parameters(tb, h, 0, 0, 1, NULL, -1, -1); return NO_BALANCING_NEEDED; case NO_DISK_SPACE: case REPEAT_SEARCH: return ret; default: reiserfs_panic(tb->tb_sb, "vs-8215", "incorrect " "return value of get_empty_nodes"); } } /* get parents of S[h] neighbors. */ ret = get_parents(tb, h); if (ret != CARRY_ON) return ret; sfree = B_FREE_SPACE(Sh); /* get free space of neighbors */ rfree = get_rfree(tb, h); lfree = get_lfree(tb, h); /* and new item fits into node S[h] without any shifting */ if (can_node_be_removed(vn->vn_mode, lfree, sfree, rfree, tb, h) == NO_BALANCING_NEEDED) return NO_BALANCING_NEEDED; create_virtual_node(tb, h); /* * determine maximal number of items we can shift to the left * neighbor (in tb structure) and the maximal number of bytes * that can flow to the left neighbor from the left most liquid * item that cannot be shifted from S[0] entirely (returned value) */ check_left(tb, h, lfree); /* * determine maximal number of items we can shift to the right * neighbor (in tb structure) and the maximal number of bytes * that can flow to the right neighbor from the right most liquid * item that cannot be shifted from S[0] entirely (returned value) */ check_right(tb, h, rfree); /* * all contents of internal node S[h] can be moved into its * neighbors, S[h] will be removed after balancing */ if (h && (tb->rnum[h] + tb->lnum[h] >= vn->vn_nr_item + 1)) { int to_r; /* * Since we are working on internal nodes, and our internal * nodes have fixed size entries, then we can balance by the * number of items rather than the space they consume. In this * routine we set the left node equal to the right node, * allowing a difference of less than or equal to 1 child * pointer. */ to_r = ((MAX_NR_KEY(Sh) << 1) + 2 - tb->lnum[h] - tb->rnum[h] + vn->vn_nr_item + 1) / 2 - (MAX_NR_KEY(Sh) + 1 - tb->rnum[h]); set_parameters(tb, h, vn->vn_nr_item + 1 - to_r, to_r, 0, NULL, -1, -1); return CARRY_ON; } /* * this checks balance condition, that any two neighboring nodes * can not fit in one node */ RFALSE(h && (tb->lnum[h] >= vn->vn_nr_item + 1 || tb->rnum[h] >= vn->vn_nr_item + 1), "vs-8220: tree is not balanced on internal level"); RFALSE(!h && ((tb->lnum[h] >= vn->vn_nr_item && (tb->lbytes == -1)) || (tb->rnum[h] >= vn->vn_nr_item && (tb->rbytes == -1))), "vs-8225: tree is not balanced on leaf level"); /* * all contents of S[0] can be moved into its neighbors * S[0] will be removed after balancing. */ if (!h && is_leaf_removable(tb)) return CARRY_ON; /* * why do we perform this check here rather than earlier?? * Answer: we can win 1 node in some cases above. Moreover we * checked it above, when we checked, that S[0] is not removable * in principle */ /* new item fits into node S[h] without any shifting */ if (sfree >= levbytes) { if (!h) tb->s0num = vn->vn_nr_item; set_parameters(tb, h, 0, 0, 1, NULL, -1, -1); return NO_BALANCING_NEEDED; } { int lpar, rpar, nset, lset, rset, lrset; /* regular overflowing of the node */ /* * get_num_ver works in 2 modes (FLOW & NO_FLOW) * lpar, rpar - number of items we can shift to left/right * neighbor (including splitting item) * nset, lset, rset, lrset - shows, whether flowing items * give better packing */ #define FLOW 1 #define NO_FLOW 0 /* do not any splitting */ /* we choose one of the following */ #define NOTHING_SHIFT_NO_FLOW 0 #define NOTHING_SHIFT_FLOW 5 #define LEFT_SHIFT_NO_FLOW 10 #define LEFT_SHIFT_FLOW 15 #define RIGHT_SHIFT_NO_FLOW 20 #define RIGHT_SHIFT_FLOW 25 #define LR_SHIFT_NO_FLOW 30 #define LR_SHIFT_FLOW 35 lpar = tb->lnum[h]; rpar = tb->rnum[h]; /* * calculate number of blocks S[h] must be split into when * nothing is shifted to the neighbors, as well as number of * items in each part of the split node (s012 numbers), * and number of bytes (s1bytes) of the shared drop which * flow to S1 if any */ nset = NOTHING_SHIFT_NO_FLOW; nver = get_num_ver(vn->vn_mode, tb, h, 0, -1, h ? vn->vn_nr_item : 0, -1, snum012, NO_FLOW); if (!h) { int nver1; /* * note, that in this case we try to bottle * between S[0] and S1 (S1 - the first new node) */ nver1 = get_num_ver(vn->vn_mode, tb, h, 0, -1, 0, -1, snum012 + NOTHING_SHIFT_FLOW, FLOW); if (nver > nver1) nset = NOTHING_SHIFT_FLOW, nver = nver1; } /* * calculate number of blocks S[h] must be split into when * l_shift_num first items and l_shift_bytes of the right * most liquid item to be shifted are shifted to the left * neighbor, as well as number of items in each part of the * splitted node (s012 numbers), and number of bytes * (s1bytes) of the shared drop which flow to S1 if any */ lset = LEFT_SHIFT_NO_FLOW; lnver = get_num_ver(vn->vn_mode, tb, h, lpar - ((h || tb->lbytes == -1) ? 0 : 1), -1, h ? vn->vn_nr_item : 0, -1, snum012 + LEFT_SHIFT_NO_FLOW, NO_FLOW); if (!h) { int lnver1; lnver1 = get_num_ver(vn->vn_mode, tb, h, lpar - ((tb->lbytes != -1) ? 1 : 0), tb->lbytes, 0, -1, snum012 + LEFT_SHIFT_FLOW, FLOW); if (lnver > lnver1) lset = LEFT_SHIFT_FLOW, lnver = lnver1; } /* * calculate number of blocks S[h] must be split into when * r_shift_num first items and r_shift_bytes of the left most * liquid item to be shifted are shifted to the right neighbor, * as well as number of items in each part of the splitted * node (s012 numbers), and number of bytes (s1bytes) of the * shared drop which flow to S1 if any */ rset = RIGHT_SHIFT_NO_FLOW; rnver = get_num_ver(vn->vn_mode, tb, h, 0, -1, h ? (vn->vn_nr_item - rpar) : (rpar - ((tb-> rbytes != -1) ? 1 : 0)), -1, snum012 + RIGHT_SHIFT_NO_FLOW, NO_FLOW); if (!h) { int rnver1; rnver1 = get_num_ver(vn->vn_mode, tb, h, 0, -1, (rpar - ((tb->rbytes != -1) ? 1 : 0)), tb->rbytes, snum012 + RIGHT_SHIFT_FLOW, FLOW); if (rnver > rnver1) rset = RIGHT_SHIFT_FLOW, rnver = rnver1; } /* * calculate number of blocks S[h] must be split into when * items are shifted in both directions, as well as number * of items in each part of the splitted node (s012 numbers), * and number of bytes (s1bytes) of the shared drop which * flow to S1 if any */ lrset = LR_SHIFT_NO_FLOW; lrnver = get_num_ver(vn->vn_mode, tb, h, lpar - ((h || tb->lbytes == -1) ? 0 : 1), -1, h ? (vn->vn_nr_item - rpar) : (rpar - ((tb-> rbytes != -1) ? 1 : 0)), -1, snum012 + LR_SHIFT_NO_FLOW, NO_FLOW); if (!h) { int lrnver1; lrnver1 = get_num_ver(vn->vn_mode, tb, h, lpar - ((tb->lbytes != -1) ? 1 : 0), tb->lbytes, (rpar - ((tb->rbytes != -1) ? 1 : 0)), tb->rbytes, snum012 + LR_SHIFT_FLOW, FLOW); if (lrnver > lrnver1) lrset = LR_SHIFT_FLOW, lrnver = lrnver1; } /* * Our general shifting strategy is: * 1) to minimized number of new nodes; * 2) to minimized number of neighbors involved in shifting; * 3) to minimized number of disk reads; */ /* we can win TWO or ONE nodes by shifting in both directions */ if (lrnver < lnver && lrnver < rnver) { RFALSE(h && (tb->lnum[h] != 1 || tb->rnum[h] != 1 || lrnver != 1 || rnver != 2 || lnver != 2 || h != 1), "vs-8230: bad h"); if (lrset == LR_SHIFT_FLOW) set_parameters(tb, h, tb->lnum[h], tb->rnum[h], lrnver, snum012 + lrset, tb->lbytes, tb->rbytes); else set_parameters(tb, h, tb->lnum[h] - ((tb->lbytes == -1) ? 0 : 1), tb->rnum[h] - ((tb->rbytes == -1) ? 0 : 1), lrnver, snum012 + lrset, -1, -1); return CARRY_ON; } /* * if shifting doesn't lead to better packing * then don't shift */ if (nver == lrnver) { set_parameters(tb, h, 0, 0, nver, snum012 + nset, -1, -1); return CARRY_ON; } /* * now we know that for better packing shifting in only one * direction either to the left or to the right is required */ /* * if shifting to the left is better than * shifting to the right */ if (lnver < rnver) { SET_PAR_SHIFT_LEFT; return CARRY_ON; } /* * if shifting to the right is better than * shifting to the left */ if (lnver > rnver) { SET_PAR_SHIFT_RIGHT; return CARRY_ON; } /* * now shifting in either direction gives the same number * of nodes and we can make use of the cached neighbors */ if (is_left_neighbor_in_cache(tb, h)) { SET_PAR_SHIFT_LEFT; return CARRY_ON; } /* * shift to the right independently on whether the * right neighbor in cache or not */ SET_PAR_SHIFT_RIGHT; return CARRY_ON; } } /* * Check whether current node S[h] is balanced when Decreasing its size by * Deleting or Cutting for INTERNAL node of S+tree. * Calculate parameters for balancing for current level h. * Parameters: * tb tree_balance structure; * h current level of the node; * inum item number in S[h]; * mode i - insert, p - paste; * Returns: 1 - schedule occurred; * 0 - balancing for higher levels needed; * -1 - no balancing for higher levels needed; * -2 - no disk space. * * Note: Items of internal nodes have fixed size, so the balance condition for * the internal part of S+tree is as for the B-trees. */ static int dc_check_balance_internal(struct tree_balance *tb, int h) { struct virtual_node *vn = tb->tb_vn; /* * Sh is the node whose balance is currently being checked, * and Fh is its father. */ struct buffer_head *Sh, *Fh; int ret; int lfree, rfree /* free space in L and R */ ; Sh = PATH_H_PBUFFER(tb->tb_path, h); Fh = PATH_H_PPARENT(tb->tb_path, h); /* * using tb->insert_size[h], which is negative in this case, * create_virtual_node calculates: * new_nr_item = number of items node would have if operation is * performed without balancing (new_nr_item); */ create_virtual_node(tb, h); if (!Fh) { /* S[h] is the root. */ /* no balancing for higher levels needed */ if (vn->vn_nr_item > 0) { set_parameters(tb, h, 0, 0, 1, NULL, -1, -1); return NO_BALANCING_NEEDED; } /* * new_nr_item == 0. * Current root will be deleted resulting in * decrementing the tree height. */ set_parameters(tb, h, 0, 0, 0, NULL, -1, -1); return CARRY_ON; } if ((ret = get_parents(tb, h)) != CARRY_ON) return ret; /* get free space of neighbors */ rfree = get_rfree(tb, h); lfree = get_lfree(tb, h); /* determine maximal number of items we can fit into neighbors */ check_left(tb, h, lfree); check_right(tb, h, rfree); /* * Balance condition for the internal node is valid. * In this case we balance only if it leads to better packing. */ if (vn->vn_nr_item >= MIN_NR_KEY(Sh)) { /* * Here we join S[h] with one of its neighbors, * which is impossible with greater values of new_nr_item. */ if (vn->vn_nr_item == MIN_NR_KEY(Sh)) { /* All contents of S[h] can be moved to L[h]. */ if (tb->lnum[h] >= vn->vn_nr_item + 1) { int n; int order_L; order_L = ((n = PATH_H_B_ITEM_ORDER(tb->tb_path, h)) == 0) ? B_NR_ITEMS(tb->FL[h]) : n - 1; n = dc_size(B_N_CHILD(tb->FL[h], order_L)) / (DC_SIZE + KEY_SIZE); set_parameters(tb, h, -n - 1, 0, 0, NULL, -1, -1); return CARRY_ON; } /* All contents of S[h] can be moved to R[h]. */ if (tb->rnum[h] >= vn->vn_nr_item + 1) { int n; int order_R; order_R = ((n = PATH_H_B_ITEM_ORDER(tb->tb_path, h)) == B_NR_ITEMS(Fh)) ? 0 : n + 1; n = dc_size(B_N_CHILD(tb->FR[h], order_R)) / (DC_SIZE + KEY_SIZE); set_parameters(tb, h, 0, -n - 1, 0, NULL, -1, -1); return CARRY_ON; } } /* * All contents of S[h] can be moved to the neighbors * (L[h] & R[h]). */ if (tb->rnum[h] + tb->lnum[h] >= vn->vn_nr_item + 1) { int to_r; to_r = ((MAX_NR_KEY(Sh) << 1) + 2 - tb->lnum[h] - tb->rnum[h] + vn->vn_nr_item + 1) / 2 - (MAX_NR_KEY(Sh) + 1 - tb->rnum[h]); set_parameters(tb, h, vn->vn_nr_item + 1 - to_r, to_r, 0, NULL, -1, -1); return CARRY_ON; } /* Balancing does not lead to better packing. */ set_parameters(tb, h, 0, 0, 1, NULL, -1, -1); return NO_BALANCING_NEEDED; } /* * Current node contain insufficient number of items. * Balancing is required. */ /* Check whether we can merge S[h] with left neighbor. */ if (tb->lnum[h] >= vn->vn_nr_item + 1) if (is_left_neighbor_in_cache(tb, h) || tb->rnum[h] < vn->vn_nr_item + 1 || !tb->FR[h]) { int n; int order_L; order_L = ((n = PATH_H_B_ITEM_ORDER(tb->tb_path, h)) == 0) ? B_NR_ITEMS(tb->FL[h]) : n - 1; n = dc_size(B_N_CHILD(tb->FL[h], order_L)) / (DC_SIZE + KEY_SIZE); set_parameters(tb, h, -n - 1, 0, 0, NULL, -1, -1); return CARRY_ON; } /* Check whether we can merge S[h] with right neighbor. */ if (tb->rnum[h] >= vn->vn_nr_item + 1) { int n; int order_R; order_R = ((n = PATH_H_B_ITEM_ORDER(tb->tb_path, h)) == B_NR_ITEMS(Fh)) ? 0 : (n + 1); n = dc_size(B_N_CHILD(tb->FR[h], order_R)) / (DC_SIZE + KEY_SIZE); set_parameters(tb, h, 0, -n - 1, 0, NULL, -1, -1); return CARRY_ON; } /* All contents of S[h] can be moved to the neighbors (L[h] & R[h]). */ if (tb->rnum[h] + tb->lnum[h] >= vn->vn_nr_item + 1) { int to_r; to_r = ((MAX_NR_KEY(Sh) << 1) + 2 - tb->lnum[h] - tb->rnum[h] + vn->vn_nr_item + 1) / 2 - (MAX_NR_KEY(Sh) + 1 - tb->rnum[h]); set_parameters(tb, h, vn->vn_nr_item + 1 - to_r, to_r, 0, NULL, -1, -1); return CARRY_ON; } /* For internal nodes try to borrow item from a neighbor */ RFALSE(!tb->FL[h] && !tb->FR[h], "vs-8235: trying to borrow for root"); /* Borrow one or two items from caching neighbor */ if (is_left_neighbor_in_cache(tb, h) || !tb->FR[h]) { int from_l; from_l = (MAX_NR_KEY(Sh) + 1 - tb->lnum[h] + vn->vn_nr_item + 1) / 2 - (vn->vn_nr_item + 1); set_parameters(tb, h, -from_l, 0, 1, NULL, -1, -1); return CARRY_ON; } set_parameters(tb, h, 0, -((MAX_NR_KEY(Sh) + 1 - tb->rnum[h] + vn->vn_nr_item + 1) / 2 - (vn->vn_nr_item + 1)), 1, NULL, -1, -1); return CARRY_ON; } /* * Check whether current node S[h] is balanced when Decreasing its size by * Deleting or Truncating for LEAF node of S+tree. * Calculate parameters for balancing for current level h. * Parameters: * tb tree_balance structure; * h current level of the node; * inum item number in S[h]; * mode i - insert, p - paste; * Returns: 1 - schedule occurred; * 0 - balancing for higher levels needed; * -1 - no balancing for higher levels needed; * -2 - no disk space. */ static int dc_check_balance_leaf(struct tree_balance *tb, int h) { struct virtual_node *vn = tb->tb_vn; /* * Number of bytes that must be deleted from * (value is negative if bytes are deleted) buffer which * contains node being balanced. The mnemonic is that the * attempted change in node space used level is levbytes bytes. */ int levbytes; /* the maximal item size */ int maxsize, ret; /* * S0 is the node whose balance is currently being checked, * and F0 is its father. */ struct buffer_head *S0, *F0; int lfree, rfree /* free space in L and R */ ; S0 = PATH_H_PBUFFER(tb->tb_path, 0); F0 = PATH_H_PPARENT(tb->tb_path, 0); levbytes = tb->insert_size[h]; maxsize = MAX_CHILD_SIZE(S0); /* maximal possible size of an item */ if (!F0) { /* S[0] is the root now. */ RFALSE(-levbytes >= maxsize - B_FREE_SPACE(S0), "vs-8240: attempt to create empty buffer tree"); set_parameters(tb, h, 0, 0, 1, NULL, -1, -1); return NO_BALANCING_NEEDED; } if ((ret = get_parents(tb, h)) != CARRY_ON) return ret; /* get free space of neighbors */ rfree = get_rfree(tb, h); lfree = get_lfree(tb, h); create_virtual_node(tb, h); /* if 3 leaves can be merge to one, set parameters and return */ if (are_leaves_removable(tb, lfree, rfree)) return CARRY_ON; /* * determine maximal number of items we can shift to the left/right * neighbor and the maximal number of bytes that can flow to the * left/right neighbor from the left/right most liquid item that * cannot be shifted from S[0] entirely */ check_left(tb, h, lfree); check_right(tb, h, rfree); /* check whether we can merge S with left neighbor. */ if (tb->lnum[0] >= vn->vn_nr_item && tb->lbytes == -1) if (is_left_neighbor_in_cache(tb, h) || ((tb->rnum[0] - ((tb->rbytes == -1) ? 0 : 1)) < vn->vn_nr_item) || /* S can not be merged with R */ !tb->FR[h]) { RFALSE(!tb->FL[h], "vs-8245: dc_check_balance_leaf: FL[h] must exist"); /* set parameter to merge S[0] with its left neighbor */ set_parameters(tb, h, -1, 0, 0, NULL, -1, -1); return CARRY_ON; } /* check whether we can merge S[0] with right neighbor. */ if (tb->rnum[0] >= vn->vn_nr_item && tb->rbytes == -1) { set_parameters(tb, h, 0, -1, 0, NULL, -1, -1); return CARRY_ON; } /* * All contents of S[0] can be moved to the neighbors (L[0] & R[0]). * Set parameters and return */ if (is_leaf_removable(tb)) return CARRY_ON; /* Balancing is not required. */ tb->s0num = vn->vn_nr_item; set_parameters(tb, h, 0, 0, 1, NULL, -1, -1); return NO_BALANCING_NEEDED; } /* * Check whether current node S[h] is balanced when Decreasing its size by * Deleting or Cutting. * Calculate parameters for balancing for current level h. * Parameters: * tb tree_balance structure; * h current level of the node; * inum item number in S[h]; * mode d - delete, c - cut. * Returns: 1 - schedule occurred; * 0 - balancing for higher levels needed; * -1 - no balancing for higher levels needed; * -2 - no disk space. */ static int dc_check_balance(struct tree_balance *tb, int h) { RFALSE(!(PATH_H_PBUFFER(tb->tb_path, h)), "vs-8250: S is not initialized"); if (h) return dc_check_balance_internal(tb, h); else return dc_check_balance_leaf(tb, h); } /* * Check whether current node S[h] is balanced. * Calculate parameters for balancing for current level h. * Parameters: * * tb tree_balance structure: * * tb is a large structure that must be read about in the header * file at the same time as this procedure if the reader is * to successfully understand this procedure * * h current level of the node; * inum item number in S[h]; * mode i - insert, p - paste, d - delete, c - cut. * Returns: 1 - schedule occurred; * 0 - balancing for higher levels needed; * -1 - no balancing for higher levels needed; * -2 - no disk space. */ static int check_balance(int mode, struct tree_balance *tb, int h, int inum, int pos_in_item, struct item_head *ins_ih, const void *data) { struct virtual_node *vn; vn = tb->tb_vn = (struct virtual_node *)(tb->vn_buf); vn->vn_free_ptr = (char *)(tb->tb_vn + 1); vn->vn_mode = mode; vn->vn_affected_item_num = inum; vn->vn_pos_in_item = pos_in_item; vn->vn_ins_ih = ins_ih; vn->vn_data = data; RFALSE(mode == M_INSERT && !vn->vn_ins_ih, "vs-8255: ins_ih can not be 0 in insert mode"); /* Calculate balance parameters when size of node is increasing. */ if (tb->insert_size[h] > 0) return ip_check_balance(tb, h); /* Calculate balance parameters when size of node is decreasing. */ return dc_check_balance(tb, h); } /* Check whether parent at the path is the really parent of the current node.*/ static int get_direct_parent(struct tree_balance *tb, int h) { struct buffer_head *bh; struct treepath *path = tb->tb_path; int position, path_offset = PATH_H_PATH_OFFSET(tb->tb_path, h); /* We are in the root or in the new root. */ if (path_offset <= FIRST_PATH_ELEMENT_OFFSET) { RFALSE(path_offset < FIRST_PATH_ELEMENT_OFFSET - 1, "PAP-8260: invalid offset in the path"); if (PATH_OFFSET_PBUFFER(path, FIRST_PATH_ELEMENT_OFFSET)-> b_blocknr == SB_ROOT_BLOCK(tb->tb_sb)) { /* Root is not changed. */ PATH_OFFSET_PBUFFER(path, path_offset - 1) = NULL; PATH_OFFSET_POSITION(path, path_offset - 1) = 0; return CARRY_ON; } /* Root is changed and we must recalculate the path. */ return REPEAT_SEARCH; } /* Parent in the path is not in the tree. */ if (!B_IS_IN_TREE (bh = PATH_OFFSET_PBUFFER(path, path_offset - 1))) return REPEAT_SEARCH; if ((position = PATH_OFFSET_POSITION(path, path_offset - 1)) > B_NR_ITEMS(bh)) return REPEAT_SEARCH; /* Parent in the path is not parent of the current node in the tree. */ if (B_N_CHILD_NUM(bh, position) != PATH_OFFSET_PBUFFER(path, path_offset)->b_blocknr) return REPEAT_SEARCH; if (buffer_locked(bh)) { int depth = reiserfs_write_unlock_nested(tb->tb_sb); __wait_on_buffer(bh); reiserfs_write_lock_nested(tb->tb_sb, depth); if (FILESYSTEM_CHANGED_TB(tb)) return REPEAT_SEARCH; } /* * Parent in the path is unlocked and really parent * of the current node. */ return CARRY_ON; } /* * Using lnum[h] and rnum[h] we should determine what neighbors * of S[h] we * need in order to balance S[h], and get them if necessary. * Returns: SCHEDULE_OCCURRED - schedule occurred while the function worked; * CARRY_ON - schedule didn't occur while the function worked; */ static int get_neighbors(struct tree_balance *tb, int h) { int child_position, path_offset = PATH_H_PATH_OFFSET(tb->tb_path, h + 1); unsigned long son_number; struct super_block *sb = tb->tb_sb; struct buffer_head *bh; int depth; PROC_INFO_INC(sb, get_neighbors[h]); if (tb->lnum[h]) { /* We need left neighbor to balance S[h]. */ PROC_INFO_INC(sb, need_l_neighbor[h]); bh = PATH_OFFSET_PBUFFER(tb->tb_path, path_offset); RFALSE(bh == tb->FL[h] && !PATH_OFFSET_POSITION(tb->tb_path, path_offset), "PAP-8270: invalid position in the parent"); child_position = (bh == tb->FL[h]) ? tb->lkey[h] : B_NR_ITEMS(tb-> FL[h]); son_number = B_N_CHILD_NUM(tb->FL[h], child_position); depth = reiserfs_write_unlock_nested(tb->tb_sb); bh = sb_bread(sb, son_number); reiserfs_write_lock_nested(tb->tb_sb, depth); if (!bh) return IO_ERROR; if (FILESYSTEM_CHANGED_TB(tb)) { brelse(bh); PROC_INFO_INC(sb, get_neighbors_restart[h]); return REPEAT_SEARCH; } RFALSE(!B_IS_IN_TREE(tb->FL[h]) || child_position > B_NR_ITEMS(tb->FL[h]) || B_N_CHILD_NUM(tb->FL[h], child_position) != bh->b_blocknr, "PAP-8275: invalid parent"); RFALSE(!B_IS_IN_TREE(bh), "PAP-8280: invalid child"); RFALSE(!h && B_FREE_SPACE(bh) != MAX_CHILD_SIZE(bh) - dc_size(B_N_CHILD(tb->FL[0], child_position)), "PAP-8290: invalid child size of left neighbor"); brelse(tb->L[h]); tb->L[h] = bh; } /* We need right neighbor to balance S[path_offset]. */ if (tb->rnum[h]) { PROC_INFO_INC(sb, need_r_neighbor[h]); bh = PATH_OFFSET_PBUFFER(tb->tb_path, path_offset); RFALSE(bh == tb->FR[h] && PATH_OFFSET_POSITION(tb->tb_path, path_offset) >= B_NR_ITEMS(bh), "PAP-8295: invalid position in the parent"); child_position = (bh == tb->FR[h]) ? tb->rkey[h] + 1 : 0; son_number = B_N_CHILD_NUM(tb->FR[h], child_position); depth = reiserfs_write_unlock_nested(tb->tb_sb); bh = sb_bread(sb, son_number); reiserfs_write_lock_nested(tb->tb_sb, depth); if (!bh) return IO_ERROR; if (FILESYSTEM_CHANGED_TB(tb)) { brelse(bh); PROC_INFO_INC(sb, get_neighbors_restart[h]); return REPEAT_SEARCH; } brelse(tb->R[h]); tb->R[h] = bh; RFALSE(!h && B_FREE_SPACE(bh) != MAX_CHILD_SIZE(bh) - dc_size(B_N_CHILD(tb->FR[0], child_position)), "PAP-8300: invalid child size of right neighbor (%d != %d - %d)", B_FREE_SPACE(bh), MAX_CHILD_SIZE(bh), dc_size(B_N_CHILD(tb->FR[0], child_position))); } return CARRY_ON; } static int get_virtual_node_size(struct super_block *sb, struct buffer_head *bh) { int max_num_of_items; int max_num_of_entries; unsigned long blocksize = sb->s_blocksize; #define MIN_NAME_LEN 1 max_num_of_items = (blocksize - BLKH_SIZE) / (IH_SIZE + MIN_ITEM_LEN); max_num_of_entries = (blocksize - BLKH_SIZE - IH_SIZE) / (DEH_SIZE + MIN_NAME_LEN); return sizeof(struct virtual_node) + max(max_num_of_items * sizeof(struct virtual_item), sizeof(struct virtual_item) + struct_size_t(struct direntry_uarea, entry_sizes, max_num_of_entries)); } /* * maybe we should fail balancing we are going to perform when kmalloc * fails several times. But now it will loop until kmalloc gets * required memory */ static int get_mem_for_virtual_node(struct tree_balance *tb) { int check_fs = 0; int size; char *buf; size = get_virtual_node_size(tb->tb_sb, PATH_PLAST_BUFFER(tb->tb_path)); /* we have to allocate more memory for virtual node */ if (size > tb->vn_buf_size) { if (tb->vn_buf) { /* free memory allocated before */ kfree(tb->vn_buf); /* this is not needed if kfree is atomic */ check_fs = 1; } /* virtual node requires now more memory */ tb->vn_buf_size = size; /* get memory for virtual item */ buf = kmalloc(size, GFP_ATOMIC | __GFP_NOWARN); if (!buf) { /* * getting memory with GFP_KERNEL priority may involve * balancing now (due to indirect_to_direct conversion * on dcache shrinking). So, release path and collected * resources here */ free_buffers_in_tb(tb); buf = kmalloc(size, GFP_NOFS); if (!buf) { tb->vn_buf_size = 0; } tb->vn_buf = buf; schedule(); return REPEAT_SEARCH; } tb->vn_buf = buf; } if (check_fs && FILESYSTEM_CHANGED_TB(tb)) return REPEAT_SEARCH; return CARRY_ON; } #ifdef CONFIG_REISERFS_CHECK static void tb_buffer_sanity_check(struct super_block *sb, struct buffer_head *bh, const char *descr, int level) { if (bh) { if (atomic_read(&(bh->b_count)) <= 0) reiserfs_panic(sb, "jmacd-1", "negative or zero " "reference counter for buffer %s[%d] " "(%b)", descr, level, bh); if (!buffer_uptodate(bh)) reiserfs_panic(sb, "jmacd-2", "buffer is not up " "to date %s[%d] (%b)", descr, level, bh); if (!B_IS_IN_TREE(bh)) reiserfs_panic(sb, "jmacd-3", "buffer is not " "in tree %s[%d] (%b)", descr, level, bh); if (bh->b_bdev != sb->s_bdev) reiserfs_panic(sb, "jmacd-4", "buffer has wrong " "device %s[%d] (%b)", descr, level, bh); if (bh->b_size != sb->s_blocksize) reiserfs_panic(sb, "jmacd-5", "buffer has wrong " "blocksize %s[%d] (%b)", descr, level, bh); if (bh->b_blocknr > SB_BLOCK_COUNT(sb)) reiserfs_panic(sb, "jmacd-6", "buffer block " "number too high %s[%d] (%b)", descr, level, bh); } } #else static void tb_buffer_sanity_check(struct super_block *sb, struct buffer_head *bh, const char *descr, int level) {; } #endif static int clear_all_dirty_bits(struct super_block *s, struct buffer_head *bh) { return reiserfs_prepare_for_journal(s, bh, 0); } static int wait_tb_buffers_until_unlocked(struct tree_balance *tb) { struct buffer_head *locked; #ifdef CONFIG_REISERFS_CHECK int repeat_counter = 0; #endif int i; do { locked = NULL; for (i = tb->tb_path->path_length; !locked && i > ILLEGAL_PATH_ELEMENT_OFFSET; i--) { if (PATH_OFFSET_PBUFFER(tb->tb_path, i)) { /* * if I understand correctly, we can only * be sure the last buffer in the path is * in the tree --clm */ #ifdef CONFIG_REISERFS_CHECK if (PATH_PLAST_BUFFER(tb->tb_path) == PATH_OFFSET_PBUFFER(tb->tb_path, i)) tb_buffer_sanity_check(tb->tb_sb, PATH_OFFSET_PBUFFER (tb->tb_path, i), "S", tb->tb_path-> path_length - i); #endif if (!clear_all_dirty_bits(tb->tb_sb, PATH_OFFSET_PBUFFER (tb->tb_path, i))) { locked = PATH_OFFSET_PBUFFER(tb->tb_path, i); } } } for (i = 0; !locked && i < MAX_HEIGHT && tb->insert_size[i]; i++) { if (tb->lnum[i]) { if (tb->L[i]) { tb_buffer_sanity_check(tb->tb_sb, tb->L[i], "L", i); if (!clear_all_dirty_bits (tb->tb_sb, tb->L[i])) locked = tb->L[i]; } if (!locked && tb->FL[i]) { tb_buffer_sanity_check(tb->tb_sb, tb->FL[i], "FL", i); if (!clear_all_dirty_bits (tb->tb_sb, tb->FL[i])) locked = tb->FL[i]; } if (!locked && tb->CFL[i]) { tb_buffer_sanity_check(tb->tb_sb, tb->CFL[i], "CFL", i); if (!clear_all_dirty_bits (tb->tb_sb, tb->CFL[i])) locked = tb->CFL[i]; } } if (!locked && (tb->rnum[i])) { if (tb->R[i]) { tb_buffer_sanity_check(tb->tb_sb, tb->R[i], "R", i); if (!clear_all_dirty_bits (tb->tb_sb, tb->R[i])) locked = tb->R[i]; } if (!locked && tb->FR[i]) { tb_buffer_sanity_check(tb->tb_sb, tb->FR[i], "FR", i); if (!clear_all_dirty_bits (tb->tb_sb, tb->FR[i])) locked = tb->FR[i]; } if (!locked && tb->CFR[i]) { tb_buffer_sanity_check(tb->tb_sb, tb->CFR[i], "CFR", i); if (!clear_all_dirty_bits (tb->tb_sb, tb->CFR[i])) locked = tb->CFR[i]; } } } /* * as far as I can tell, this is not required. The FEB list * seems to be full of newly allocated nodes, which will * never be locked, dirty, or anything else. * To be safe, I'm putting in the checks and waits in. * For the moment, they are needed to keep the code in * journal.c from complaining about the buffer. * That code is inside CONFIG_REISERFS_CHECK as well. --clm */ for (i = 0; !locked && i < MAX_FEB_SIZE; i++) { if (tb->FEB[i]) { if (!clear_all_dirty_bits (tb->tb_sb, tb->FEB[i])) locked = tb->FEB[i]; } } if (locked) { int depth; #ifdef CONFIG_REISERFS_CHECK repeat_counter++; if ((repeat_counter % 10000) == 0) { reiserfs_warning(tb->tb_sb, "reiserfs-8200", "too many iterations waiting " "for buffer to unlock " "(%b)", locked); /* Don't loop forever. Try to recover from possible error. */ return (FILESYSTEM_CHANGED_TB(tb)) ? REPEAT_SEARCH : CARRY_ON; } #endif depth = reiserfs_write_unlock_nested(tb->tb_sb); __wait_on_buffer(locked); reiserfs_write_lock_nested(tb->tb_sb, depth); if (FILESYSTEM_CHANGED_TB(tb)) return REPEAT_SEARCH; } } while (locked); return CARRY_ON; } /* * Prepare for balancing, that is * get all necessary parents, and neighbors; * analyze what and where should be moved; * get sufficient number of new nodes; * Balancing will start only after all resources will be collected at a time. * * When ported to SMP kernels, only at the last moment after all needed nodes * are collected in cache, will the resources be locked using the usual * textbook ordered lock acquisition algorithms. Note that ensuring that * this code neither write locks what it does not need to write lock nor locks * out of order will be a pain in the butt that could have been avoided. * Grumble grumble. -Hans * * fix is meant in the sense of render unchanging * * Latency might be improved by first gathering a list of what buffers * are needed and then getting as many of them in parallel as possible? -Hans * * Parameters: * op_mode i - insert, d - delete, c - cut (truncate), p - paste (append) * tb tree_balance structure; * inum item number in S[h]; * pos_in_item - comment this if you can * ins_ih item head of item being inserted * data inserted item or data to be pasted * Returns: 1 - schedule occurred while the function worked; * 0 - schedule didn't occur while the function worked; * -1 - if no_disk_space */ int fix_nodes(int op_mode, struct tree_balance *tb, struct item_head *ins_ih, const void *data) { int ret, h, item_num = PATH_LAST_POSITION(tb->tb_path); int pos_in_item; /* * we set wait_tb_buffers_run when we have to restore any dirty * bits cleared during wait_tb_buffers_run */ int wait_tb_buffers_run = 0; struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path); ++REISERFS_SB(tb->tb_sb)->s_fix_nodes; pos_in_item = tb->tb_path->pos_in_item; tb->fs_gen = get_generation(tb->tb_sb); /* * we prepare and log the super here so it will already be in the * transaction when do_balance needs to change it. * This way do_balance won't have to schedule when trying to prepare * the super for logging */ reiserfs_prepare_for_journal(tb->tb_sb, SB_BUFFER_WITH_SB(tb->tb_sb), 1); journal_mark_dirty(tb->transaction_handle, SB_BUFFER_WITH_SB(tb->tb_sb)); if (FILESYSTEM_CHANGED_TB(tb)) return REPEAT_SEARCH; /* if it possible in indirect_to_direct conversion */ if (buffer_locked(tbS0)) { int depth = reiserfs_write_unlock_nested(tb->tb_sb); __wait_on_buffer(tbS0); reiserfs_write_lock_nested(tb->tb_sb, depth); if (FILESYSTEM_CHANGED_TB(tb)) return REPEAT_SEARCH; } #ifdef CONFIG_REISERFS_CHECK if (REISERFS_SB(tb->tb_sb)->cur_tb) { print_cur_tb("fix_nodes"); reiserfs_panic(tb->tb_sb, "PAP-8305", "there is pending do_balance"); } if (!buffer_uptodate(tbS0) || !B_IS_IN_TREE(tbS0)) reiserfs_panic(tb->tb_sb, "PAP-8320", "S[0] (%b %z) is " "not uptodate at the beginning of fix_nodes " "or not in tree (mode %c)", tbS0, tbS0, op_mode); /* Check parameters. */ switch (op_mode) { case M_INSERT: if (item_num <= 0 || item_num > B_NR_ITEMS(tbS0)) reiserfs_panic(tb->tb_sb, "PAP-8330", "Incorrect " "item number %d (in S0 - %d) in case " "of insert", item_num, B_NR_ITEMS(tbS0)); break; case M_PASTE: case M_DELETE: case M_CUT: if (item_num < 0 || item_num >= B_NR_ITEMS(tbS0)) { print_block(tbS0, 0, -1, -1); reiserfs_panic(tb->tb_sb, "PAP-8335", "Incorrect " "item number(%d); mode = %c " "insert_size = %d", item_num, op_mode, tb->insert_size[0]); } break; default: reiserfs_panic(tb->tb_sb, "PAP-8340", "Incorrect mode " "of operation"); } #endif if (get_mem_for_virtual_node(tb) == REPEAT_SEARCH) /* FIXME: maybe -ENOMEM when tb->vn_buf == 0? Now just repeat */ return REPEAT_SEARCH; /* Starting from the leaf level; for all levels h of the tree. */ for (h = 0; h < MAX_HEIGHT && tb->insert_size[h]; h++) { ret = get_direct_parent(tb, h); if (ret != CARRY_ON) goto repeat; ret = check_balance(op_mode, tb, h, item_num, pos_in_item, ins_ih, data); if (ret != CARRY_ON) { if (ret == NO_BALANCING_NEEDED) { /* No balancing for higher levels needed. */ ret = get_neighbors(tb, h); if (ret != CARRY_ON) goto repeat; if (h != MAX_HEIGHT - 1) tb->insert_size[h + 1] = 0; /* * ok, analysis and resource gathering * are complete */ break; } goto repeat; } ret = get_neighbors(tb, h); if (ret != CARRY_ON) goto repeat; /* * No disk space, or schedule occurred and analysis may be * invalid and needs to be redone. */ ret = get_empty_nodes(tb, h); if (ret != CARRY_ON) goto repeat; /* * We have a positive insert size but no nodes exist on this * level, this means that we are creating a new root. */ if (!PATH_H_PBUFFER(tb->tb_path, h)) { RFALSE(tb->blknum[h] != 1, "PAP-8350: creating new empty root"); if (h < MAX_HEIGHT - 1) tb->insert_size[h + 1] = 0; } else if (!PATH_H_PBUFFER(tb->tb_path, h + 1)) { /* * The tree needs to be grown, so this node S[h] * which is the root node is split into two nodes, * and a new node (S[h+1]) will be created to * become the root node. */ if (tb->blknum[h] > 1) { RFALSE(h == MAX_HEIGHT - 1, "PAP-8355: attempt to create too high of a tree"); tb->insert_size[h + 1] = (DC_SIZE + KEY_SIZE) * (tb->blknum[h] - 1) + DC_SIZE; } else if (h < MAX_HEIGHT - 1) tb->insert_size[h + 1] = 0; } else tb->insert_size[h + 1] = (DC_SIZE + KEY_SIZE) * (tb->blknum[h] - 1); } ret = wait_tb_buffers_until_unlocked(tb); if (ret == CARRY_ON) { if (FILESYSTEM_CHANGED_TB(tb)) { wait_tb_buffers_run = 1; ret = REPEAT_SEARCH; goto repeat; } else { return CARRY_ON; } } else { wait_tb_buffers_run = 1; goto repeat; } repeat: /* * fix_nodes was unable to perform its calculation due to * filesystem got changed under us, lack of free disk space or i/o * failure. If the first is the case - the search will be * repeated. For now - free all resources acquired so far except * for the new allocated nodes */ { int i; /* Release path buffers. */ if (wait_tb_buffers_run) { pathrelse_and_restore(tb->tb_sb, tb->tb_path); } else { pathrelse(tb->tb_path); } /* brelse all resources collected for balancing */ for (i = 0; i < MAX_HEIGHT; i++) { if (wait_tb_buffers_run) { reiserfs_restore_prepared_buffer(tb->tb_sb, tb->L[i]); reiserfs_restore_prepared_buffer(tb->tb_sb, tb->R[i]); reiserfs_restore_prepared_buffer(tb->tb_sb, tb->FL[i]); reiserfs_restore_prepared_buffer(tb->tb_sb, tb->FR[i]); reiserfs_restore_prepared_buffer(tb->tb_sb, tb-> CFL[i]); reiserfs_restore_prepared_buffer(tb->tb_sb, tb-> CFR[i]); } brelse(tb->L[i]); brelse(tb->R[i]); brelse(tb->FL[i]); brelse(tb->FR[i]); brelse(tb->CFL[i]); brelse(tb->CFR[i]); tb->L[i] = NULL; tb->R[i] = NULL; tb->FL[i] = NULL; tb->FR[i] = NULL; tb->CFL[i] = NULL; tb->CFR[i] = NULL; } if (wait_tb_buffers_run) { for (i = 0; i < MAX_FEB_SIZE; i++) { if (tb->FEB[i]) reiserfs_restore_prepared_buffer (tb->tb_sb, tb->FEB[i]); } } return ret; } } void unfix_nodes(struct tree_balance *tb) { int i; /* Release path buffers. */ pathrelse_and_restore(tb->tb_sb, tb->tb_path); /* brelse all resources collected for balancing */ for (i = 0; i < MAX_HEIGHT; i++) { reiserfs_restore_prepared_buffer(tb->tb_sb, tb->L[i]); reiserfs_restore_prepared_buffer(tb->tb_sb, tb->R[i]); reiserfs_restore_prepared_buffer(tb->tb_sb, tb->FL[i]); reiserfs_restore_prepared_buffer(tb->tb_sb, tb->FR[i]); reiserfs_restore_prepared_buffer(tb->tb_sb, tb->CFL[i]); reiserfs_restore_prepared_buffer(tb->tb_sb, tb->CFR[i]); brelse(tb->L[i]); brelse(tb->R[i]); brelse(tb->FL[i]); brelse(tb->FR[i]); brelse(tb->CFL[i]); brelse(tb->CFR[i]); } /* deal with list of allocated (used and unused) nodes */ for (i = 0; i < MAX_FEB_SIZE; i++) { if (tb->FEB[i]) { b_blocknr_t blocknr = tb->FEB[i]->b_blocknr; /* * de-allocated block which was not used by * balancing and bforget about buffer for it */ brelse(tb->FEB[i]); reiserfs_free_block(tb->transaction_handle, NULL, blocknr, 0); } if (tb->used[i]) { /* release used as new nodes including a new root */ brelse(tb->used[i]); } } kfree(tb->vn_buf); } |
| 11099 3419 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Landlock LSM - Filesystem management and hooks * * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI */ #ifndef _SECURITY_LANDLOCK_FS_H #define _SECURITY_LANDLOCK_FS_H #include <linux/fs.h> #include <linux/init.h> #include <linux/rcupdate.h> #include "ruleset.h" #include "setup.h" /** * struct landlock_inode_security - Inode security blob * * Enable to reference a &struct landlock_object tied to an inode (i.e. * underlying object). */ struct landlock_inode_security { /** * @object: Weak pointer to an allocated object. All assignments of a * new object are protected by the underlying inode->i_lock. However, * atomically disassociating @object from the inode is only protected * by @object->lock, from the time @object's usage refcount drops to * zero to the time this pointer is nulled out (cf. release_inode() and * hook_sb_delete()). Indeed, such disassociation doesn't require * inode->i_lock thanks to the careful rcu_access_pointer() check * performed by get_inode_object(). */ struct landlock_object __rcu *object; }; /** * struct landlock_file_security - File security blob * * This information is populated when opening a file in hook_file_open, and * tracks the relevant Landlock access rights that were available at the time * of opening the file. Other LSM hooks use these rights in order to authorize * operations on already opened files. */ struct landlock_file_security { /** * @allowed_access: Access rights that were available at the time of * opening the file. This is not necessarily the full set of access * rights available at that time, but it's the necessary subset as * needed to authorize later operations on the open file. */ access_mask_t allowed_access; }; /** * struct landlock_superblock_security - Superblock security blob * * Enable hook_sb_delete() to wait for concurrent calls to release_inode(). */ struct landlock_superblock_security { /** * @inode_refs: Number of pending inodes (from this superblock) that * are being released by release_inode(). * Cf. struct super_block->s_fsnotify_inode_refs . */ atomic_long_t inode_refs; }; static inline struct landlock_file_security * landlock_file(const struct file *const file) { return file->f_security + landlock_blob_sizes.lbs_file; } static inline struct landlock_inode_security * landlock_inode(const struct inode *const inode) { return inode->i_security + landlock_blob_sizes.lbs_inode; } static inline struct landlock_superblock_security * landlock_superblock(const struct super_block *const superblock) { return superblock->s_security + landlock_blob_sizes.lbs_superblock; } __init void landlock_add_fs_hooks(void); int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, const struct path *const path, access_mask_t access_hierarchy); #endif /* _SECURITY_LANDLOCK_FS_H */ |
| 22 22 21 22 21 2 22 22 9 20 22 21 20 21 21 22 22 22 22 22 1 22 22 22 22 22 22 22 21 21 21 22 2 2 21 6 5 1 1 1 1 1 1 1 1 1 1 1 1 1 115 115 2 115 2 6 6 6 6 6 6 7 3 3 3 3 3 46 46 46 44 21 25 2 2 2 2 2 2 1 7 1 1 1 57 1 8 2 6 8 22 22 22 14 14 4 14 14 22 22 9 8 1 9 9 9 9 9 9 8 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 22 8 8 8 8 21 19 22 9 9 9 8 8 3 22 21 22 20 1 1 1 1 1 2 2 2 2 2 2 2 1 2 1 2 1 2 14 56 22 22 22 22 2 22 22 22 22 22 22 22 22 22 20 20 22 20 22 22 22 1 1 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 21 2 22 22 22 46 46 40 46 46 46 46 46 46 46 47 51 52 7 58 58 57 58 37 31 58 58 58 58 56 56 17 55 56 29 29 29 56 58 2 12 7 21 59 59 41 21 59 59 1 27 6 1 6 7 7 7 7 7 7 7 45 45 7 7 7 7 7 1 7 7 1 21 21 1 21 21 5 5 5 5 5 5 5 6 6 6 6 6 5 2 2 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 2 2 3 4 4 11 41 18 18 18 54 13 54 56 56 56 56 56 27 27 52 6 6 6 55 56 26 35 30 30 55 51 51 56 51 1 51 27 27 50 51 50 1 21 21 21 21 21 25 25 25 25 9 9 9 9 9 9 9 9 1 39 39 39 39 39 39 33 33 33 33 33 33 41 41 39 33 33 33 21 21 21 21 21 21 21 20 83 83 83 80 21 21 21 1 21 21 21 21 21 21 21 21 21 21 21 21 21 21 21 21 21 20 21 21 1 21 21 1 21 21 22 2 2 2 22 45 45 44 45 45 44 45 45 45 45 45 45 45 45 41 41 33 26 26 26 26 20 6 26 25 25 25 25 25 25 25 19 6 25 25 25 25 25 25 25 23 23 23 23 23 23 23 24 24 23 22 23 23 23 23 23 130 1 15 15 15 15 15 15 14 46 46 44 46 46 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/segment.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ */ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/sched/mm.h> #include <linux/prefetch.h> #include <linux/kthread.h> #include <linux/swap.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/sched/signal.h> #include <linux/random.h> #include "f2fs.h" #include "segment.h" #include "node.h" #include "gc.h" #include "iostat.h" #include <trace/events/f2fs.h> #define __reverse_ffz(x) __reverse_ffs(~(x)) static struct kmem_cache *discard_entry_slab; static struct kmem_cache *discard_cmd_slab; static struct kmem_cache *sit_entry_set_slab; static struct kmem_cache *revoke_entry_slab; static unsigned long __reverse_ulong(unsigned char *str) { unsigned long tmp = 0; int shift = 24, idx = 0; #if BITS_PER_LONG == 64 shift = 56; #endif while (shift >= 0) { tmp |= (unsigned long)str[idx++] << shift; shift -= BITS_PER_BYTE; } return tmp; } /* * __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since * MSB and LSB are reversed in a byte by f2fs_set_bit. */ static inline unsigned long __reverse_ffs(unsigned long word) { int num = 0; #if BITS_PER_LONG == 64 if ((word & 0xffffffff00000000UL) == 0) num += 32; else word >>= 32; #endif if ((word & 0xffff0000) == 0) num += 16; else word >>= 16; if ((word & 0xff00) == 0) num += 8; else word >>= 8; if ((word & 0xf0) == 0) num += 4; else word >>= 4; if ((word & 0xc) == 0) num += 2; else word >>= 2; if ((word & 0x2) == 0) num += 1; return num; } /* * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because * f2fs_set_bit makes MSB and LSB reversed in a byte. * @size must be integral times of unsigned long. * Example: * MSB <--> LSB * f2fs_set_bit(0, bitmap) => 1000 0000 * f2fs_set_bit(7, bitmap) => 0000 0001 */ static unsigned long __find_rev_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { const unsigned long *p = addr + BIT_WORD(offset); unsigned long result = size; unsigned long tmp; if (offset >= size) return size; size -= (offset & ~(BITS_PER_LONG - 1)); offset %= BITS_PER_LONG; while (1) { if (*p == 0) goto pass; tmp = __reverse_ulong((unsigned char *)p); tmp &= ~0UL >> offset; if (size < BITS_PER_LONG) tmp &= (~0UL << (BITS_PER_LONG - size)); if (tmp) goto found; pass: if (size <= BITS_PER_LONG) break; size -= BITS_PER_LONG; offset = 0; p++; } return result; found: return result - size + __reverse_ffs(tmp); } static unsigned long __find_rev_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { const unsigned long *p = addr + BIT_WORD(offset); unsigned long result = size; unsigned long tmp; if (offset >= size) return size; size -= (offset & ~(BITS_PER_LONG - 1)); offset %= BITS_PER_LONG; while (1) { if (*p == ~0UL) goto pass; tmp = __reverse_ulong((unsigned char *)p); if (offset) tmp |= ~0UL << (BITS_PER_LONG - offset); if (size < BITS_PER_LONG) tmp |= ~0UL >> size; if (tmp != ~0UL) goto found; pass: if (size <= BITS_PER_LONG) break; size -= BITS_PER_LONG; offset = 0; p++; } return result; found: return result - size + __reverse_ffz(tmp); } bool f2fs_need_SSR(struct f2fs_sb_info *sbi) { int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA); if (f2fs_lfs_mode(sbi)) return false; if (sbi->gc_mode == GC_URGENT_HIGH) return true; if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return true; return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs + SM_I(sbi)->min_ssr_sections + reserved_sections(sbi)); } void f2fs_abort_atomic_write(struct inode *inode, bool clean) { struct f2fs_inode_info *fi = F2FS_I(inode); if (!f2fs_is_atomic_file(inode)) return; release_atomic_write_cnt(inode); clear_inode_flag(inode, FI_ATOMIC_COMMITTED); clear_inode_flag(inode, FI_ATOMIC_REPLACE); clear_inode_flag(inode, FI_ATOMIC_FILE); stat_dec_atomic_inode(inode); F2FS_I(inode)->atomic_write_task = NULL; if (clean) { truncate_inode_pages_final(inode->i_mapping); f2fs_i_size_write(inode, fi->original_i_size); fi->original_i_size = 0; } /* avoid stale dirty inode during eviction */ sync_inode_metadata(inode, 0); } static int __replace_atomic_write_block(struct inode *inode, pgoff_t index, block_t new_addr, block_t *old_addr, bool recover) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; struct node_info ni; int err; retry: set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE); if (err) { if (err == -ENOMEM) { f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); goto retry; } return err; } err = f2fs_get_node_info(sbi, dn.nid, &ni, false); if (err) { f2fs_put_dnode(&dn); return err; } if (recover) { /* dn.data_blkaddr is always valid */ if (!__is_valid_data_blkaddr(new_addr)) { if (new_addr == NULL_ADDR) dec_valid_block_count(sbi, inode, 1); f2fs_invalidate_blocks(sbi, dn.data_blkaddr); f2fs_update_data_blkaddr(&dn, new_addr); } else { f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr, ni.version, true, true); } } else { blkcnt_t count = 1; err = inc_valid_block_count(sbi, inode, &count); if (err) { f2fs_put_dnode(&dn); return err; } *old_addr = dn.data_blkaddr; f2fs_truncate_data_blocks_range(&dn, 1); dec_valid_block_count(sbi, F2FS_I(inode)->cow_inode, count); f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr, ni.version, true, false); } f2fs_put_dnode(&dn); trace_f2fs_replace_atomic_write_block(inode, F2FS_I(inode)->cow_inode, index, old_addr ? *old_addr : 0, new_addr, recover); return 0; } static void __complete_revoke_list(struct inode *inode, struct list_head *head, bool revoke) { struct revoke_entry *cur, *tmp; pgoff_t start_index = 0; bool truncate = is_inode_flag_set(inode, FI_ATOMIC_REPLACE); list_for_each_entry_safe(cur, tmp, head, list) { if (revoke) { __replace_atomic_write_block(inode, cur->index, cur->old_addr, NULL, true); } else if (truncate) { f2fs_truncate_hole(inode, start_index, cur->index); start_index = cur->index + 1; } list_del(&cur->list); kmem_cache_free(revoke_entry_slab, cur); } if (!revoke && truncate) f2fs_do_truncate_blocks(inode, start_index * PAGE_SIZE, false); } static int __f2fs_commit_atomic_write(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); struct inode *cow_inode = fi->cow_inode; struct revoke_entry *new; struct list_head revoke_list; block_t blkaddr; struct dnode_of_data dn; pgoff_t len = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); pgoff_t off = 0, blen, index; int ret = 0, i; INIT_LIST_HEAD(&revoke_list); while (len) { blen = min_t(pgoff_t, ADDRS_PER_BLOCK(cow_inode), len); set_new_dnode(&dn, cow_inode, NULL, NULL, 0); ret = f2fs_get_dnode_of_data(&dn, off, LOOKUP_NODE_RA); if (ret && ret != -ENOENT) { goto out; } else if (ret == -ENOENT) { ret = 0; if (dn.max_level == 0) goto out; goto next; } blen = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, cow_inode), len); index = off; for (i = 0; i < blen; i++, dn.ofs_in_node++, index++) { blkaddr = f2fs_data_blkaddr(&dn); if (!__is_valid_data_blkaddr(blkaddr)) { continue; } else if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) { f2fs_put_dnode(&dn); ret = -EFSCORRUPTED; f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); goto out; } new = f2fs_kmem_cache_alloc(revoke_entry_slab, GFP_NOFS, true, NULL); ret = __replace_atomic_write_block(inode, index, blkaddr, &new->old_addr, false); if (ret) { f2fs_put_dnode(&dn); kmem_cache_free(revoke_entry_slab, new); goto out; } f2fs_update_data_blkaddr(&dn, NULL_ADDR); new->index = index; list_add_tail(&new->list, &revoke_list); } f2fs_put_dnode(&dn); next: off += blen; len -= blen; } out: if (ret) { sbi->revoked_atomic_block += fi->atomic_write_cnt; } else { sbi->committed_atomic_block += fi->atomic_write_cnt; set_inode_flag(inode, FI_ATOMIC_COMMITTED); } __complete_revoke_list(inode, &revoke_list, ret ? true : false); return ret; } int f2fs_commit_atomic_write(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); int err; err = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); if (err) return err; f2fs_down_write(&fi->i_gc_rwsem[WRITE]); f2fs_lock_op(sbi); err = __f2fs_commit_atomic_write(inode); f2fs_unlock_op(sbi); f2fs_up_write(&fi->i_gc_rwsem[WRITE]); return err; } /* * This function balances dirty node and dentry pages. * In addition, it controls garbage collection. */ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) { if (time_to_inject(sbi, FAULT_CHECKPOINT)) f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_FAULT_INJECT); /* balance_fs_bg is able to be pending */ if (need && excess_cached_nats(sbi)) f2fs_balance_fs_bg(sbi, false); if (!f2fs_is_checkpoint_ready(sbi)) return; /* * We should do GC or end up with checkpoint, if there are so many dirty * dir/node pages without enough free segments. */ if (has_enough_free_secs(sbi, 0, 0)) return; if (test_opt(sbi, GC_MERGE) && sbi->gc_thread && sbi->gc_thread->f2fs_gc_task) { DEFINE_WAIT(wait); prepare_to_wait(&sbi->gc_thread->fggc_wq, &wait, TASK_UNINTERRUPTIBLE); wake_up(&sbi->gc_thread->gc_wait_queue_head); io_schedule(); finish_wait(&sbi->gc_thread->fggc_wq, &wait); } else { struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO, .init_gc_type = BG_GC, .no_bg_gc = true, .should_migrate_blocks = false, .err_gc_skipped = false, .nr_free_secs = 1 }; f2fs_down_write(&sbi->gc_lock); stat_inc_gc_call_count(sbi, FOREGROUND); f2fs_gc(sbi, &gc_control); } } static inline bool excess_dirty_threshold(struct f2fs_sb_info *sbi) { int factor = f2fs_rwsem_is_locked(&sbi->cp_rwsem) ? 3 : 2; unsigned int dents = get_pages(sbi, F2FS_DIRTY_DENTS); unsigned int qdata = get_pages(sbi, F2FS_DIRTY_QDATA); unsigned int nodes = get_pages(sbi, F2FS_DIRTY_NODES); unsigned int meta = get_pages(sbi, F2FS_DIRTY_META); unsigned int imeta = get_pages(sbi, F2FS_DIRTY_IMETA); unsigned int threshold = sbi->blocks_per_seg * factor * DEFAULT_DIRTY_THRESHOLD; unsigned int global_threshold = threshold * 3 / 2; if (dents >= threshold || qdata >= threshold || nodes >= threshold || meta >= threshold || imeta >= threshold) return true; return dents + qdata + nodes + meta + imeta > global_threshold; } void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg) { if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) return; /* try to shrink extent cache when there is no enough memory */ if (!f2fs_available_free_memory(sbi, READ_EXTENT_CACHE)) f2fs_shrink_read_extent_tree(sbi, READ_EXTENT_CACHE_SHRINK_NUMBER); /* try to shrink age extent cache when there is no enough memory */ if (!f2fs_available_free_memory(sbi, AGE_EXTENT_CACHE)) f2fs_shrink_age_extent_tree(sbi, AGE_EXTENT_CACHE_SHRINK_NUMBER); /* check the # of cached NAT entries */ if (!f2fs_available_free_memory(sbi, NAT_ENTRIES)) f2fs_try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK); if (!f2fs_available_free_memory(sbi, FREE_NIDS)) f2fs_try_to_free_nids(sbi, MAX_FREE_NIDS); else f2fs_build_free_nids(sbi, false, false); if (excess_dirty_nats(sbi) || excess_dirty_threshold(sbi) || excess_prefree_segs(sbi) || !f2fs_space_for_roll_forward(sbi)) goto do_sync; /* there is background inflight IO or foreground operation recently */ if (is_inflight_io(sbi, REQ_TIME) || (!f2fs_time_over(sbi, REQ_TIME) && f2fs_rwsem_is_locked(&sbi->cp_rwsem))) return; /* exceed periodical checkpoint timeout threshold */ if (f2fs_time_over(sbi, CP_TIME)) goto do_sync; /* checkpoint is the only way to shrink partial cached entries */ if (f2fs_available_free_memory(sbi, NAT_ENTRIES) && f2fs_available_free_memory(sbi, INO_ENTRIES)) return; do_sync: if (test_opt(sbi, DATA_FLUSH) && from_bg) { struct blk_plug plug; mutex_lock(&sbi->flush_lock); blk_start_plug(&plug); f2fs_sync_dirty_inodes(sbi, FILE_INODE, false); blk_finish_plug(&plug); mutex_unlock(&sbi->flush_lock); } stat_inc_cp_call_count(sbi, BACKGROUND); f2fs_sync_fs(sbi->sb, 1); } static int __submit_flush_wait(struct f2fs_sb_info *sbi, struct block_device *bdev) { int ret = blkdev_issue_flush(bdev); trace_f2fs_issue_flush(bdev, test_opt(sbi, NOBARRIER), test_opt(sbi, FLUSH_MERGE), ret); if (!ret) f2fs_update_iostat(sbi, NULL, FS_FLUSH_IO, 0); return ret; } static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino) { int ret = 0; int i; if (!f2fs_is_multi_device(sbi)) return __submit_flush_wait(sbi, sbi->sb->s_bdev); for (i = 0; i < sbi->s_ndevs; i++) { if (!f2fs_is_dirty_device(sbi, ino, i, FLUSH_INO)) continue; ret = __submit_flush_wait(sbi, FDEV(i).bdev); if (ret) break; } return ret; } static int issue_flush_thread(void *data) { struct f2fs_sb_info *sbi = data; struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info; wait_queue_head_t *q = &fcc->flush_wait_queue; repeat: if (kthread_should_stop()) return 0; if (!llist_empty(&fcc->issue_list)) { struct flush_cmd *cmd, *next; int ret; fcc->dispatch_list = llist_del_all(&fcc->issue_list); fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list); cmd = llist_entry(fcc->dispatch_list, struct flush_cmd, llnode); ret = submit_flush_wait(sbi, cmd->ino); atomic_inc(&fcc->issued_flush); llist_for_each_entry_safe(cmd, next, fcc->dispatch_list, llnode) { cmd->ret = ret; complete(&cmd->wait); } fcc->dispatch_list = NULL; } wait_event_interruptible(*q, kthread_should_stop() || !llist_empty(&fcc->issue_list)); goto repeat; } int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino) { struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info; struct flush_cmd cmd; int ret; if (test_opt(sbi, NOBARRIER)) return 0; if (!test_opt(sbi, FLUSH_MERGE)) { atomic_inc(&fcc->queued_flush); ret = submit_flush_wait(sbi, ino); atomic_dec(&fcc->queued_flush); atomic_inc(&fcc->issued_flush); return ret; } if (atomic_inc_return(&fcc->queued_flush) == 1 || f2fs_is_multi_device(sbi)) { ret = submit_flush_wait(sbi, ino); atomic_dec(&fcc->queued_flush); atomic_inc(&fcc->issued_flush); return ret; } cmd.ino = ino; init_completion(&cmd.wait); llist_add(&cmd.llnode, &fcc->issue_list); /* * update issue_list before we wake up issue_flush thread, this * smp_mb() pairs with another barrier in ___wait_event(), see * more details in comments of waitqueue_active(). */ smp_mb(); if (waitqueue_active(&fcc->flush_wait_queue)) wake_up(&fcc->flush_wait_queue); if (fcc->f2fs_issue_flush) { wait_for_completion(&cmd.wait); atomic_dec(&fcc->queued_flush); } else { struct llist_node *list; list = llist_del_all(&fcc->issue_list); if (!list) { wait_for_completion(&cmd.wait); atomic_dec(&fcc->queued_flush); } else { struct flush_cmd *tmp, *next; ret = submit_flush_wait(sbi, ino); llist_for_each_entry_safe(tmp, next, list, llnode) { if (tmp == &cmd) { cmd.ret = ret; atomic_dec(&fcc->queued_flush); continue; } tmp->ret = ret; complete(&tmp->wait); } } } return cmd.ret; } int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi) { dev_t dev = sbi->sb->s_bdev->bd_dev; struct flush_cmd_control *fcc; if (SM_I(sbi)->fcc_info) { fcc = SM_I(sbi)->fcc_info; if (fcc->f2fs_issue_flush) return 0; goto init_thread; } fcc = f2fs_kzalloc(sbi, sizeof(struct flush_cmd_control), GFP_KERNEL); if (!fcc) return -ENOMEM; atomic_set(&fcc->issued_flush, 0); atomic_set(&fcc->queued_flush, 0); init_waitqueue_head(&fcc->flush_wait_queue); init_llist_head(&fcc->issue_list); SM_I(sbi)->fcc_info = fcc; if (!test_opt(sbi, FLUSH_MERGE)) return 0; init_thread: fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi, "f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(fcc->f2fs_issue_flush)) { int err = PTR_ERR(fcc->f2fs_issue_flush); fcc->f2fs_issue_flush = NULL; return err; } return 0; } void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free) { struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info; if (fcc && fcc->f2fs_issue_flush) { struct task_struct *flush_thread = fcc->f2fs_issue_flush; fcc->f2fs_issue_flush = NULL; kthread_stop(flush_thread); } if (free) { kfree(fcc); SM_I(sbi)->fcc_info = NULL; } } int f2fs_flush_device_cache(struct f2fs_sb_info *sbi) { int ret = 0, i; if (!f2fs_is_multi_device(sbi)) return 0; if (test_opt(sbi, NOBARRIER)) return 0; for (i = 1; i < sbi->s_ndevs; i++) { int count = DEFAULT_RETRY_IO_COUNT; if (!f2fs_test_bit(i, (char *)&sbi->dirty_device)) continue; do { ret = __submit_flush_wait(sbi, FDEV(i).bdev); if (ret) f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); } while (ret && --count); if (ret) { f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_FLUSH_FAIL); break; } spin_lock(&sbi->dev_lock); f2fs_clear_bit(i, (char *)&sbi->dirty_device); spin_unlock(&sbi->dev_lock); } return ret; } static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, enum dirty_type dirty_type) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); /* need not be added */ if (IS_CURSEG(sbi, segno)) return; if (!test_and_set_bit(segno, dirty_i->dirty_segmap[dirty_type])) dirty_i->nr_dirty[dirty_type]++; if (dirty_type == DIRTY) { struct seg_entry *sentry = get_seg_entry(sbi, segno); enum dirty_type t = sentry->type; if (unlikely(t >= DIRTY)) { f2fs_bug_on(sbi, 1); return; } if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t])) dirty_i->nr_dirty[t]++; if (__is_large_section(sbi)) { unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); block_t valid_blocks = get_valid_blocks(sbi, segno, true); f2fs_bug_on(sbi, unlikely(!valid_blocks || valid_blocks == CAP_BLKS_PER_SEC(sbi))); if (!IS_CURSEC(sbi, secno)) set_bit(secno, dirty_i->dirty_secmap); } } } static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, enum dirty_type dirty_type) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); block_t valid_blocks; if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type])) dirty_i->nr_dirty[dirty_type]--; if (dirty_type == DIRTY) { struct seg_entry *sentry = get_seg_entry(sbi, segno); enum dirty_type t = sentry->type; if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t])) dirty_i->nr_dirty[t]--; valid_blocks = get_valid_blocks(sbi, segno, true); if (valid_blocks == 0) { clear_bit(GET_SEC_FROM_SEG(sbi, segno), dirty_i->victim_secmap); #ifdef CONFIG_F2FS_CHECK_FS clear_bit(segno, SIT_I(sbi)->invalid_segmap); #endif } if (__is_large_section(sbi)) { unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); if (!valid_blocks || valid_blocks == CAP_BLKS_PER_SEC(sbi)) { clear_bit(secno, dirty_i->dirty_secmap); return; } if (!IS_CURSEC(sbi, secno)) set_bit(secno, dirty_i->dirty_secmap); } } } /* * Should not occur error such as -ENOMEM. * Adding dirty entry into seglist is not critical operation. * If a given segment is one of current working segments, it won't be added. */ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned short valid_blocks, ckpt_valid_blocks; unsigned int usable_blocks; if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno)) return; usable_blocks = f2fs_usable_blks_in_seg(sbi, segno); mutex_lock(&dirty_i->seglist_lock); valid_blocks = get_valid_blocks(sbi, segno, false); ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno, false); if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) || ckpt_valid_blocks == usable_blocks)) { __locate_dirty_segment(sbi, segno, PRE); __remove_dirty_segment(sbi, segno, DIRTY); } else if (valid_blocks < usable_blocks) { __locate_dirty_segment(sbi, segno, DIRTY); } else { /* Recovery routine with SSR needs this */ __remove_dirty_segment(sbi, segno, DIRTY); } mutex_unlock(&dirty_i->seglist_lock); } /* This moves currently empty dirty blocks to prefree. Must hold seglist_lock */ void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned int segno; mutex_lock(&dirty_i->seglist_lock); for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { if (get_valid_blocks(sbi, segno, false)) continue; if (IS_CURSEG(sbi, segno)) continue; __locate_dirty_segment(sbi, segno, PRE); __remove_dirty_segment(sbi, segno, DIRTY); } mutex_unlock(&dirty_i->seglist_lock); } block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi) { int ovp_hole_segs = (overprovision_segments(sbi) - reserved_segments(sbi)); block_t ovp_holes = ovp_hole_segs << sbi->log_blocks_per_seg; struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); block_t holes[2] = {0, 0}; /* DATA and NODE */ block_t unusable; struct seg_entry *se; unsigned int segno; mutex_lock(&dirty_i->seglist_lock); for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { se = get_seg_entry(sbi, segno); if (IS_NODESEG(se->type)) holes[NODE] += f2fs_usable_blks_in_seg(sbi, segno) - se->valid_blocks; else holes[DATA] += f2fs_usable_blks_in_seg(sbi, segno) - se->valid_blocks; } mutex_unlock(&dirty_i->seglist_lock); unusable = max(holes[DATA], holes[NODE]); if (unusable > ovp_holes) return unusable - ovp_holes; return 0; } int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable) { int ovp_hole_segs = (overprovision_segments(sbi) - reserved_segments(sbi)); if (unusable > F2FS_OPTION(sbi).unusable_cap) return -EAGAIN; if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) && dirty_segments(sbi) > ovp_hole_segs) return -EAGAIN; return 0; } /* This is only used by SBI_CP_DISABLED */ static unsigned int get_free_segment(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned int segno = 0; mutex_lock(&dirty_i->seglist_lock); for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { if (get_valid_blocks(sbi, segno, false)) continue; if (get_ckpt_valid_blocks(sbi, segno, false)) continue; mutex_unlock(&dirty_i->seglist_lock); return segno; } mutex_unlock(&dirty_i->seglist_lock); return NULL_SEGNO; } static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *pend_list; struct discard_cmd *dc; f2fs_bug_on(sbi, !len); pend_list = &dcc->pend_list[plist_idx(len)]; dc = f2fs_kmem_cache_alloc(discard_cmd_slab, GFP_NOFS, true, NULL); INIT_LIST_HEAD(&dc->list); dc->bdev = bdev; dc->di.lstart = lstart; dc->di.start = start; dc->di.len = len; dc->ref = 0; dc->state = D_PREP; dc->queued = 0; dc->error = 0; init_completion(&dc->wait); list_add_tail(&dc->list, pend_list); spin_lock_init(&dc->lock); dc->bio_ref = 0; atomic_inc(&dcc->discard_cmd_cnt); dcc->undiscard_blks += len; return dc; } static bool f2fs_check_discard_tree(struct f2fs_sb_info *sbi) { #ifdef CONFIG_F2FS_CHECK_FS struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct rb_node *cur = rb_first_cached(&dcc->root), *next; struct discard_cmd *cur_dc, *next_dc; while (cur) { next = rb_next(cur); if (!next) return true; cur_dc = rb_entry(cur, struct discard_cmd, rb_node); next_dc = rb_entry(next, struct discard_cmd, rb_node); if (cur_dc->di.lstart + cur_dc->di.len > next_dc->di.lstart) { f2fs_info(sbi, "broken discard_rbtree, " "cur(%u, %u) next(%u, %u)", cur_dc->di.lstart, cur_dc->di.len, next_dc->di.lstart, next_dc->di.len); return false; } cur = next; } #endif return true; } static struct discard_cmd *__lookup_discard_cmd(struct f2fs_sb_info *sbi, block_t blkaddr) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct rb_node *node = dcc->root.rb_root.rb_node; struct discard_cmd *dc; while (node) { dc = rb_entry(node, struct discard_cmd, rb_node); if (blkaddr < dc->di.lstart) node = node->rb_left; else if (blkaddr >= dc->di.lstart + dc->di.len) node = node->rb_right; else return dc; } return NULL; } static struct discard_cmd *__lookup_discard_cmd_ret(struct rb_root_cached *root, block_t blkaddr, struct discard_cmd **prev_entry, struct discard_cmd **next_entry, struct rb_node ***insert_p, struct rb_node **insert_parent) { struct rb_node **pnode = &root->rb_root.rb_node; struct rb_node *parent = NULL, *tmp_node; struct discard_cmd *dc; *insert_p = NULL; *insert_parent = NULL; *prev_entry = NULL; *next_entry = NULL; if (RB_EMPTY_ROOT(&root->rb_root)) return NULL; while (*pnode) { parent = *pnode; dc = rb_entry(*pnode, struct discard_cmd, rb_node); if (blkaddr < dc->di.lstart) pnode = &(*pnode)->rb_left; else if (blkaddr >= dc->di.lstart + dc->di.len) pnode = &(*pnode)->rb_right; else goto lookup_neighbors; } *insert_p = pnode; *insert_parent = parent; dc = rb_entry(parent, struct discard_cmd, rb_node); tmp_node = parent; if (parent && blkaddr > dc->di.lstart) tmp_node = rb_next(parent); *next_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node); tmp_node = parent; if (parent && blkaddr < dc->di.lstart) tmp_node = rb_prev(parent); *prev_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node); return NULL; lookup_neighbors: /* lookup prev node for merging backward later */ tmp_node = rb_prev(&dc->rb_node); *prev_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node); /* lookup next node for merging frontward later */ tmp_node = rb_next(&dc->rb_node); *next_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node); return dc; } static void __detach_discard_cmd(struct discard_cmd_control *dcc, struct discard_cmd *dc) { if (dc->state == D_DONE) atomic_sub(dc->queued, &dcc->queued_discard); list_del(&dc->list); rb_erase_cached(&dc->rb_node, &dcc->root); dcc->undiscard_blks -= dc->di.len; kmem_cache_free(discard_cmd_slab, dc); atomic_dec(&dcc->discard_cmd_cnt); } static void __remove_discard_cmd(struct f2fs_sb_info *sbi, struct discard_cmd *dc) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; unsigned long flags; trace_f2fs_remove_discard(dc->bdev, dc->di.start, dc->di.len); spin_lock_irqsave(&dc->lock, flags); if (dc->bio_ref) { spin_unlock_irqrestore(&dc->lock, flags); return; } spin_unlock_irqrestore(&dc->lock, flags); f2fs_bug_on(sbi, dc->ref); if (dc->error == -EOPNOTSUPP) dc->error = 0; if (dc->error) printk_ratelimited( "%sF2FS-fs (%s): Issue discard(%u, %u, %u) failed, ret: %d", KERN_INFO, sbi->sb->s_id, dc->di.lstart, dc->di.start, dc->di.len, dc->error); __detach_discard_cmd(dcc, dc); } static void f2fs_submit_discard_endio(struct bio *bio) { struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private; unsigned long flags; spin_lock_irqsave(&dc->lock, flags); if (!dc->error) dc->error = blk_status_to_errno(bio->bi_status); dc->bio_ref--; if (!dc->bio_ref && dc->state == D_SUBMIT) { dc->state = D_DONE; complete_all(&dc->wait); } spin_unlock_irqrestore(&dc->lock, flags); bio_put(bio); } static void __check_sit_bitmap(struct f2fs_sb_info *sbi, block_t start, block_t end) { #ifdef CONFIG_F2FS_CHECK_FS struct seg_entry *sentry; unsigned int segno; block_t blk = start; unsigned long offset, size, max_blocks = sbi->blocks_per_seg; unsigned long *map; while (blk < end) { segno = GET_SEGNO(sbi, blk); sentry = get_seg_entry(sbi, segno); offset = GET_BLKOFF_FROM_SEG0(sbi, blk); if (end < START_BLOCK(sbi, segno + 1)) size = GET_BLKOFF_FROM_SEG0(sbi, end); else size = max_blocks; map = (unsigned long *)(sentry->cur_valid_map); offset = __find_rev_next_bit(map, size, offset); f2fs_bug_on(sbi, offset != size); blk = START_BLOCK(sbi, segno + 1); } #endif } static void __init_discard_policy(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy, int discard_type, unsigned int granularity) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; /* common policy */ dpolicy->type = discard_type; dpolicy->sync = true; dpolicy->ordered = false; dpolicy->granularity = granularity; dpolicy->max_requests = dcc->max_discard_request; dpolicy->io_aware_gran = dcc->discard_io_aware_gran; dpolicy->timeout = false; if (discard_type == DPOLICY_BG) { dpolicy->min_interval = dcc->min_discard_issue_time; dpolicy->mid_interval = dcc->mid_discard_issue_time; dpolicy->max_interval = dcc->max_discard_issue_time; dpolicy->io_aware = true; dpolicy->sync = false; dpolicy->ordered = true; if (utilization(sbi) > dcc->discard_urgent_util) { dpolicy->granularity = MIN_DISCARD_GRANULARITY; if (atomic_read(&dcc->discard_cmd_cnt)) dpolicy->max_interval = dcc->min_discard_issue_time; } } else if (discard_type == DPOLICY_FORCE) { dpolicy->min_interval = dcc->min_discard_issue_time; dpolicy->mid_interval = dcc->mid_discard_issue_time; dpolicy->max_interval = dcc->max_discard_issue_time; dpolicy->io_aware = false; } else if (discard_type == DPOLICY_FSTRIM) { dpolicy->io_aware = false; } else if (discard_type == DPOLICY_UMOUNT) { dpolicy->io_aware = false; /* we need to issue all to keep CP_TRIMMED_FLAG */ dpolicy->granularity = MIN_DISCARD_GRANULARITY; dpolicy->timeout = true; } } static void __update_discard_tree_range(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len); #ifdef CONFIG_BLK_DEV_ZONED static void __submit_zone_reset_cmd(struct f2fs_sb_info *sbi, struct discard_cmd *dc, blk_opf_t flag, struct list_head *wait_list, unsigned int *issued) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct block_device *bdev = dc->bdev; struct bio *bio = bio_alloc(bdev, 0, REQ_OP_ZONE_RESET | flag, GFP_NOFS); unsigned long flags; trace_f2fs_issue_reset_zone(bdev, dc->di.start); spin_lock_irqsave(&dc->lock, flags); dc->state = D_SUBMIT; dc->bio_ref++; spin_unlock_irqrestore(&dc->lock, flags); if (issued) (*issued)++; atomic_inc(&dcc->queued_discard); dc->queued++; list_move_tail(&dc->list, wait_list); /* sanity check on discard range */ __check_sit_bitmap(sbi, dc->di.lstart, dc->di.lstart + dc->di.len); bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(dc->di.start); bio->bi_private = dc; bio->bi_end_io = f2fs_submit_discard_endio; submit_bio(bio); atomic_inc(&dcc->issued_discard); f2fs_update_iostat(sbi, NULL, FS_ZONE_RESET_IO, dc->di.len * F2FS_BLKSIZE); } #endif /* this function is copied from blkdev_issue_discard from block/blk-lib.c */ static int __submit_discard_cmd(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy, struct discard_cmd *dc, int *issued) { struct block_device *bdev = dc->bdev; unsigned int max_discard_blocks = SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev)); struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ? &(dcc->fstrim_list) : &(dcc->wait_list); blk_opf_t flag = dpolicy->sync ? REQ_SYNC : 0; block_t lstart, start, len, total_len; int err = 0; if (dc->state != D_PREP) return 0; if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) return 0; #ifdef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(bdev)) { int devi = f2fs_bdev_index(sbi, bdev); if (devi < 0) return -EINVAL; if (f2fs_blkz_is_seq(sbi, devi, dc->di.start)) { __submit_zone_reset_cmd(sbi, dc, flag, wait_list, issued); return 0; } } #endif trace_f2fs_issue_discard(bdev, dc->di.start, dc->di.len); lstart = dc->di.lstart; start = dc->di.start; len = dc->di.len; total_len = len; dc->di.len = 0; while (total_len && *issued < dpolicy->max_requests && !err) { struct bio *bio = NULL; unsigned long flags; bool last = true; if (len > max_discard_blocks) { len = max_discard_blocks; last = false; } (*issued)++; if (*issued == dpolicy->max_requests) last = true; dc->di.len += len; if (time_to_inject(sbi, FAULT_DISCARD)) { err = -EIO; } else { err = __blkdev_issue_discard(bdev, SECTOR_FROM_BLOCK(start), SECTOR_FROM_BLOCK(len), GFP_NOFS, &bio); } if (err) { spin_lock_irqsave(&dc->lock, flags); if (dc->state == D_PARTIAL) dc->state = D_SUBMIT; spin_unlock_irqrestore(&dc->lock, flags); break; } f2fs_bug_on(sbi, !bio); /* * should keep before submission to avoid D_DONE * right away */ spin_lock_irqsave(&dc->lock, flags); if (last) dc->state = D_SUBMIT; else dc->state = D_PARTIAL; dc->bio_ref++; spin_unlock_irqrestore(&dc->lock, flags); atomic_inc(&dcc->queued_discard); dc->queued++; list_move_tail(&dc->list, wait_list); /* sanity check on discard range */ __check_sit_bitmap(sbi, lstart, lstart + len); bio->bi_private = dc; bio->bi_end_io = f2fs_submit_discard_endio; bio->bi_opf |= flag; submit_bio(bio); atomic_inc(&dcc->issued_discard); f2fs_update_iostat(sbi, NULL, FS_DISCARD_IO, len * F2FS_BLKSIZE); lstart += len; start += len; total_len -= len; len = total_len; } if (!err && len) { dcc->undiscard_blks -= len; __update_discard_tree_range(sbi, bdev, lstart, start, len); } return err; } static void __insert_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct rb_node **p = &dcc->root.rb_root.rb_node; struct rb_node *parent = NULL; struct discard_cmd *dc; bool leftmost = true; /* look up rb tree to find parent node */ while (*p) { parent = *p; dc = rb_entry(parent, struct discard_cmd, rb_node); if (lstart < dc->di.lstart) { p = &(*p)->rb_left; } else if (lstart >= dc->di.lstart + dc->di.len) { p = &(*p)->rb_right; leftmost = false; } else { f2fs_bug_on(sbi, 1); } } dc = __create_discard_cmd(sbi, bdev, lstart, start, len); rb_link_node(&dc->rb_node, parent, p); rb_insert_color_cached(&dc->rb_node, &dcc->root, leftmost); } static void __relocate_discard_cmd(struct discard_cmd_control *dcc, struct discard_cmd *dc) { list_move_tail(&dc->list, &dcc->pend_list[plist_idx(dc->di.len)]); } static void __punch_discard_cmd(struct f2fs_sb_info *sbi, struct discard_cmd *dc, block_t blkaddr) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_info di = dc->di; bool modified = false; if (dc->state == D_DONE || dc->di.len == 1) { __remove_discard_cmd(sbi, dc); return; } dcc->undiscard_blks -= di.len; if (blkaddr > di.lstart) { dc->di.len = blkaddr - dc->di.lstart; dcc->undiscard_blks += dc->di.len; __relocate_discard_cmd(dcc, dc); modified = true; } if (blkaddr < di.lstart + di.len - 1) { if (modified) { __insert_discard_cmd(sbi, dc->bdev, blkaddr + 1, di.start + blkaddr + 1 - di.lstart, di.lstart + di.len - 1 - blkaddr); } else { dc->di.lstart++; dc->di.len--; dc->di.start++; dcc->undiscard_blks += dc->di.len; __relocate_discard_cmd(dcc, dc); } } } static void __update_discard_tree_range(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_cmd *prev_dc = NULL, *next_dc = NULL; struct discard_cmd *dc; struct discard_info di = {0}; struct rb_node **insert_p = NULL, *insert_parent = NULL; unsigned int max_discard_blocks = SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev)); block_t end = lstart + len; dc = __lookup_discard_cmd_ret(&dcc->root, lstart, &prev_dc, &next_dc, &insert_p, &insert_parent); if (dc) prev_dc = dc; if (!prev_dc) { di.lstart = lstart; di.len = next_dc ? next_dc->di.lstart - lstart : len; di.len = min(di.len, len); di.start = start; } while (1) { struct rb_node *node; bool merged = false; struct discard_cmd *tdc = NULL; if (prev_dc) { di.lstart = prev_dc->di.lstart + prev_dc->di.len; if (di.lstart < lstart) di.lstart = lstart; if (di.lstart >= end) break; if (!next_dc || next_dc->di.lstart > end) di.len = end - di.lstart; else di.len = next_dc->di.lstart - di.lstart; di.start = start + di.lstart - lstart; } if (!di.len) goto next; if (prev_dc && prev_dc->state == D_PREP && prev_dc->bdev == bdev && __is_discard_back_mergeable(&di, &prev_dc->di, max_discard_blocks)) { prev_dc->di.len += di.len; dcc->undiscard_blks += di.len; __relocate_discard_cmd(dcc, prev_dc); di = prev_dc->di; tdc = prev_dc; merged = true; } if (next_dc && next_dc->state == D_PREP && next_dc->bdev == bdev && __is_discard_front_mergeable(&di, &next_dc->di, max_discard_blocks)) { next_dc->di.lstart = di.lstart; next_dc->di.len += di.len; next_dc->di.start = di.start; dcc->undiscard_blks += di.len; __relocate_discard_cmd(dcc, next_dc); if (tdc) __remove_discard_cmd(sbi, tdc); merged = true; } if (!merged) __insert_discard_cmd(sbi, bdev, di.lstart, di.start, di.len); next: prev_dc = next_dc; if (!prev_dc) break; node = rb_next(&prev_dc->rb_node); next_dc = rb_entry_safe(node, struct discard_cmd, rb_node); } } #ifdef CONFIG_BLK_DEV_ZONED static void __queue_zone_reset_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkstart, block_t lblkstart, block_t blklen) { trace_f2fs_queue_reset_zone(bdev, blkstart); mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock); __insert_discard_cmd(sbi, bdev, lblkstart, blkstart, blklen); mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock); } #endif static void __queue_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkstart, block_t blklen) { block_t lblkstart = blkstart; if (!f2fs_bdev_support_discard(bdev)) return; trace_f2fs_queue_discard(bdev, blkstart, blklen); if (f2fs_is_multi_device(sbi)) { int devi = f2fs_target_device_index(sbi, blkstart); blkstart -= FDEV(devi).start_blk; } mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock); __update_discard_tree_range(sbi, bdev, lblkstart, blkstart, blklen); mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock); } static void __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy, int *issued) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_cmd *prev_dc = NULL, *next_dc = NULL; struct rb_node **insert_p = NULL, *insert_parent = NULL; struct discard_cmd *dc; struct blk_plug plug; bool io_interrupted = false; mutex_lock(&dcc->cmd_lock); dc = __lookup_discard_cmd_ret(&dcc->root, dcc->next_pos, &prev_dc, &next_dc, &insert_p, &insert_parent); if (!dc) dc = next_dc; blk_start_plug(&plug); while (dc) { struct rb_node *node; int err = 0; if (dc->state != D_PREP) goto next; if (dpolicy->io_aware && !is_idle(sbi, DISCARD_TIME)) { io_interrupted = true; break; } dcc->next_pos = dc->di.lstart + dc->di.len; err = __submit_discard_cmd(sbi, dpolicy, dc, issued); if (*issued >= dpolicy->max_requests) break; next: node = rb_next(&dc->rb_node); if (err) __remove_discard_cmd(sbi, dc); dc = rb_entry_safe(node, struct discard_cmd, rb_node); } blk_finish_plug(&plug); if (!dc) dcc->next_pos = 0; mutex_unlock(&dcc->cmd_lock); if (!(*issued) && io_interrupted) *issued = -1; } static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy); static int __issue_discard_cmd(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *pend_list; struct discard_cmd *dc, *tmp; struct blk_plug plug; int i, issued; bool io_interrupted = false; if (dpolicy->timeout) f2fs_update_time(sbi, UMOUNT_DISCARD_TIMEOUT); retry: issued = 0; for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { if (dpolicy->timeout && f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT)) break; if (i + 1 < dpolicy->granularity) break; if (i + 1 < dcc->max_ordered_discard && dpolicy->ordered) { __issue_discard_cmd_orderly(sbi, dpolicy, &issued); return issued; } pend_list = &dcc->pend_list[i]; mutex_lock(&dcc->cmd_lock); if (list_empty(pend_list)) goto next; if (unlikely(dcc->rbtree_check)) f2fs_bug_on(sbi, !f2fs_check_discard_tree(sbi)); blk_start_plug(&plug); list_for_each_entry_safe(dc, tmp, pend_list, list) { f2fs_bug_on(sbi, dc->state != D_PREP); if (dpolicy->timeout && f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT)) break; if (dpolicy->io_aware && i < dpolicy->io_aware_gran && !is_idle(sbi, DISCARD_TIME)) { io_interrupted = true; break; } __submit_discard_cmd(sbi, dpolicy, dc, &issued); if (issued >= dpolicy->max_requests) break; } blk_finish_plug(&plug); next: mutex_unlock(&dcc->cmd_lock); if (issued >= dpolicy->max_requests || io_interrupted) break; } if (dpolicy->type == DPOLICY_UMOUNT && issued) { __wait_all_discard_cmd(sbi, dpolicy); goto retry; } if (!issued && io_interrupted) issued = -1; return issued; } static bool __drop_discard_cmd(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *pend_list; struct discard_cmd *dc, *tmp; int i; bool dropped = false; mutex_lock(&dcc->cmd_lock); for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { pend_list = &dcc->pend_list[i]; list_for_each_entry_safe(dc, tmp, pend_list, list) { f2fs_bug_on(sbi, dc->state != D_PREP); __remove_discard_cmd(sbi, dc); dropped = true; } } mutex_unlock(&dcc->cmd_lock); return dropped; } void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi) { __drop_discard_cmd(sbi); } static unsigned int __wait_one_discard_bio(struct f2fs_sb_info *sbi, struct discard_cmd *dc) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; unsigned int len = 0; wait_for_completion_io(&dc->wait); mutex_lock(&dcc->cmd_lock); f2fs_bug_on(sbi, dc->state != D_DONE); dc->ref--; if (!dc->ref) { if (!dc->error) len = dc->di.len; __remove_discard_cmd(sbi, dc); } mutex_unlock(&dcc->cmd_lock); return len; } static unsigned int __wait_discard_cmd_range(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy, block_t start, block_t end) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ? &(dcc->fstrim_list) : &(dcc->wait_list); struct discard_cmd *dc = NULL, *iter, *tmp; unsigned int trimmed = 0; next: dc = NULL; mutex_lock(&dcc->cmd_lock); list_for_each_entry_safe(iter, tmp, wait_list, list) { if (iter->di.lstart + iter->di.len <= start || end <= iter->di.lstart) continue; if (iter->di.len < dpolicy->granularity) continue; if (iter->state == D_DONE && !iter->ref) { wait_for_completion_io(&iter->wait); if (!iter->error) trimmed += iter->di.len; __remove_discard_cmd(sbi, iter); } else { iter->ref++; dc = iter; break; } } mutex_unlock(&dcc->cmd_lock); if (dc) { trimmed += __wait_one_discard_bio(sbi, dc); goto next; } return trimmed; } static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy) { struct discard_policy dp; unsigned int discard_blks; if (dpolicy) return __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX); /* wait all */ __init_discard_policy(sbi, &dp, DPOLICY_FSTRIM, MIN_DISCARD_GRANULARITY); discard_blks = __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX); __init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, MIN_DISCARD_GRANULARITY); discard_blks += __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX); return discard_blks; } /* This should be covered by global mutex, &sit_i->sentry_lock */ static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_cmd *dc; bool need_wait = false; mutex_lock(&dcc->cmd_lock); dc = __lookup_discard_cmd(sbi, blkaddr); #ifdef CONFIG_BLK_DEV_ZONED if (dc && f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(dc->bdev)) { int devi = f2fs_bdev_index(sbi, dc->bdev); if (devi < 0) { mutex_unlock(&dcc->cmd_lock); return; } if (f2fs_blkz_is_seq(sbi, devi, dc->di.start)) { /* force submit zone reset */ if (dc->state == D_PREP) __submit_zone_reset_cmd(sbi, dc, REQ_SYNC, &dcc->wait_list, NULL); dc->ref++; mutex_unlock(&dcc->cmd_lock); /* wait zone reset */ __wait_one_discard_bio(sbi, dc); return; } } #endif if (dc) { if (dc->state == D_PREP) { __punch_discard_cmd(sbi, dc, blkaddr); } else { dc->ref++; need_wait = true; } } mutex_unlock(&dcc->cmd_lock); if (need_wait) __wait_one_discard_bio(sbi, dc); } void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; if (dcc && dcc->f2fs_issue_discard) { struct task_struct *discard_thread = dcc->f2fs_issue_discard; dcc->f2fs_issue_discard = NULL; kthread_stop(discard_thread); } } /** * f2fs_issue_discard_timeout() - Issue all discard cmd within UMOUNT_DISCARD_TIMEOUT * @sbi: the f2fs_sb_info data for discard cmd to issue * * When UMOUNT_DISCARD_TIMEOUT is exceeded, all remaining discard commands will be dropped * * Return true if issued all discard cmd or no discard cmd need issue, otherwise return false. */ bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_policy dpolicy; bool dropped; if (!atomic_read(&dcc->discard_cmd_cnt)) return true; __init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT, dcc->discard_granularity); __issue_discard_cmd(sbi, &dpolicy); dropped = __drop_discard_cmd(sbi); /* just to make sure there is no pending discard commands */ __wait_all_discard_cmd(sbi, NULL); f2fs_bug_on(sbi, atomic_read(&dcc->discard_cmd_cnt)); return !dropped; } static int issue_discard_thread(void *data) { struct f2fs_sb_info *sbi = data; struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; wait_queue_head_t *q = &dcc->discard_wait_queue; struct discard_policy dpolicy; unsigned int wait_ms = dcc->min_discard_issue_time; int issued; set_freezable(); do { wait_event_interruptible_timeout(*q, kthread_should_stop() || freezing(current) || dcc->discard_wake, msecs_to_jiffies(wait_ms)); if (sbi->gc_mode == GC_URGENT_HIGH || !f2fs_available_free_memory(sbi, DISCARD_CACHE)) __init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, MIN_DISCARD_GRANULARITY); else __init_discard_policy(sbi, &dpolicy, DPOLICY_BG, dcc->discard_granularity); if (dcc->discard_wake) dcc->discard_wake = false; /* clean up pending candidates before going to sleep */ if (atomic_read(&dcc->queued_discard)) __wait_all_discard_cmd(sbi, NULL); if (try_to_freeze()) continue; if (f2fs_readonly(sbi->sb)) continue; if (kthread_should_stop()) return 0; if (is_sbi_flag_set(sbi, SBI_NEED_FSCK) || !atomic_read(&dcc->discard_cmd_cnt)) { wait_ms = dpolicy.max_interval; continue; } sb_start_intwrite(sbi->sb); issued = __issue_discard_cmd(sbi, &dpolicy); if (issued > 0) { __wait_all_discard_cmd(sbi, &dpolicy); wait_ms = dpolicy.min_interval; } else if (issued == -1) { wait_ms = f2fs_time_to_wait(sbi, DISCARD_TIME); if (!wait_ms) wait_ms = dpolicy.mid_interval; } else { wait_ms = dpolicy.max_interval; } if (!atomic_read(&dcc->discard_cmd_cnt)) wait_ms = dpolicy.max_interval; sb_end_intwrite(sbi->sb); } while (!kthread_should_stop()); return 0; } #ifdef CONFIG_BLK_DEV_ZONED static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkstart, block_t blklen) { sector_t sector, nr_sects; block_t lblkstart = blkstart; int devi = 0; u64 remainder = 0; if (f2fs_is_multi_device(sbi)) { devi = f2fs_target_device_index(sbi, blkstart); if (blkstart < FDEV(devi).start_blk || blkstart > FDEV(devi).end_blk) { f2fs_err(sbi, "Invalid block %x", blkstart); return -EIO; } blkstart -= FDEV(devi).start_blk; } /* For sequential zones, reset the zone write pointer */ if (f2fs_blkz_is_seq(sbi, devi, blkstart)) { sector = SECTOR_FROM_BLOCK(blkstart); nr_sects = SECTOR_FROM_BLOCK(blklen); div64_u64_rem(sector, bdev_zone_sectors(bdev), &remainder); if (remainder || nr_sects != bdev_zone_sectors(bdev)) { f2fs_err(sbi, "(%d) %s: Unaligned zone reset attempted (block %x + %x)", devi, sbi->s_ndevs ? FDEV(devi).path : "", blkstart, blklen); return -EIO; } if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) { trace_f2fs_issue_reset_zone(bdev, blkstart); return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, sector, nr_sects, GFP_NOFS); } __queue_zone_reset_cmd(sbi, bdev, blkstart, lblkstart, blklen); return 0; } /* For conventional zones, use regular discard if supported */ __queue_discard_cmd(sbi, bdev, lblkstart, blklen); return 0; } #endif static int __issue_discard_async(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkstart, block_t blklen) { #ifdef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(bdev)) return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen); #endif __queue_discard_cmd(sbi, bdev, blkstart, blklen); return 0; } static int f2fs_issue_discard(struct f2fs_sb_info *sbi, block_t blkstart, block_t blklen) { sector_t start = blkstart, len = 0; struct block_device *bdev; struct seg_entry *se; unsigned int offset; block_t i; int err = 0; bdev = f2fs_target_device(sbi, blkstart, NULL); for (i = blkstart; i < blkstart + blklen; i++, len++) { if (i != start) { struct block_device *bdev2 = f2fs_target_device(sbi, i, NULL); if (bdev2 != bdev) { err = __issue_discard_async(sbi, bdev, start, len); if (err) return err; bdev = bdev2; start = i; len = 0; } } se = get_seg_entry(sbi, GET_SEGNO(sbi, i)); offset = GET_BLKOFF_FROM_SEG0(sbi, i); if (f2fs_block_unit_discard(sbi) && !f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; } if (len) err = __issue_discard_async(sbi, bdev, start, len); return err; } static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, bool check_only) { int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long); int max_blocks = sbi->blocks_per_seg; struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start); unsigned long *cur_map = (unsigned long *)se->cur_valid_map; unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map; unsigned long *discard_map = (unsigned long *)se->discard_map; unsigned long *dmap = SIT_I(sbi)->tmp_map; unsigned int start = 0, end = -1; bool force = (cpc->reason & CP_DISCARD); struct discard_entry *de = NULL; struct list_head *head = &SM_I(sbi)->dcc_info->entry_list; int i; if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi) || !f2fs_block_unit_discard(sbi)) return false; if (!force) { if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks || SM_I(sbi)->dcc_info->nr_discards >= SM_I(sbi)->dcc_info->max_discards) return false; } /* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */ for (i = 0; i < entries; i++) dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] : (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i]; while (force || SM_I(sbi)->dcc_info->nr_discards <= SM_I(sbi)->dcc_info->max_discards) { start = __find_rev_next_bit(dmap, max_blocks, end + 1); if (start >= max_blocks) break; end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1); if (force && start && end != max_blocks && (end - start) < cpc->trim_minlen) continue; if (check_only) return true; if (!de) { de = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_F2FS_ZERO, true, NULL); de->start_blkaddr = START_BLOCK(sbi, cpc->trim_start); list_add_tail(&de->list, head); } for (i = start; i < end; i++) __set_bit_le(i, (void *)de->discard_map); SM_I(sbi)->dcc_info->nr_discards += end - start; } return false; } static void release_discard_addr(struct discard_entry *entry) { list_del(&entry->list); kmem_cache_free(discard_entry_slab, entry); } void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi) { struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list); struct discard_entry *entry, *this; /* drop caches */ list_for_each_entry_safe(entry, this, head, list) release_discard_addr(entry); } /* * Should call f2fs_clear_prefree_segments after checkpoint is done. */ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned int segno; mutex_lock(&dirty_i->seglist_lock); for_each_set_bit(segno, dirty_i->dirty_segmap[PRE], MAIN_SEGS(sbi)) __set_test_and_free(sbi, segno, false); mutex_unlock(&dirty_i->seglist_lock); } void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *head = &dcc->entry_list; struct discard_entry *entry, *this; struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned long *prefree_map = dirty_i->dirty_segmap[PRE]; unsigned int start = 0, end = -1; unsigned int secno, start_segno; bool force = (cpc->reason & CP_DISCARD); bool section_alignment = F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION; if (f2fs_lfs_mode(sbi) && __is_large_section(sbi)) section_alignment = true; mutex_lock(&dirty_i->seglist_lock); while (1) { int i; if (section_alignment && end != -1) end--; start = find_next_bit(prefree_map, MAIN_SEGS(sbi), end + 1); if (start >= MAIN_SEGS(sbi)) break; end = find_next_zero_bit(prefree_map, MAIN_SEGS(sbi), start + 1); if (section_alignment) { start = rounddown(start, sbi->segs_per_sec); end = roundup(end, sbi->segs_per_sec); } for (i = start; i < end; i++) { if (test_and_clear_bit(i, prefree_map)) dirty_i->nr_dirty[PRE]--; } if (!f2fs_realtime_discard_enable(sbi)) continue; if (force && start >= cpc->trim_start && (end - 1) <= cpc->trim_end) continue; /* Should cover 2MB zoned device for zone-based reset */ if (!f2fs_sb_has_blkzoned(sbi) && (!f2fs_lfs_mode(sbi) || !__is_large_section(sbi))) { f2fs_issue_discard(sbi, START_BLOCK(sbi, start), (end - start) << sbi->log_blocks_per_seg); continue; } next: secno = GET_SEC_FROM_SEG(sbi, start); start_segno = GET_SEG_FROM_SEC(sbi, secno); if (!IS_CURSEC(sbi, secno) && !get_valid_blocks(sbi, start, true)) f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno), sbi->segs_per_sec << sbi->log_blocks_per_seg); start = start_segno + sbi->segs_per_sec; if (start < end) goto next; else end = start - 1; } mutex_unlock(&dirty_i->seglist_lock); if (!f2fs_block_unit_discard(sbi)) goto wakeup; /* send small discards */ list_for_each_entry_safe(entry, this, head, list) { unsigned int cur_pos = 0, next_pos, len, total_len = 0; bool is_valid = test_bit_le(0, entry->discard_map); find_next: if (is_valid) { next_pos = find_next_zero_bit_le(entry->discard_map, sbi->blocks_per_seg, cur_pos); len = next_pos - cur_pos; if (f2fs_sb_has_blkzoned(sbi) || (force && len < cpc->trim_minlen)) goto skip; f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos, len); total_len += len; } else { next_pos = find_next_bit_le(entry->discard_map, sbi->blocks_per_seg, cur_pos); } skip: cur_pos = next_pos; is_valid = !is_valid; if (cur_pos < sbi->blocks_per_seg) goto find_next; release_discard_addr(entry); dcc->nr_discards -= total_len; } wakeup: wake_up_discard_thread(sbi, false); } int f2fs_start_discard_thread(struct f2fs_sb_info *sbi) { dev_t dev = sbi->sb->s_bdev->bd_dev; struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; int err = 0; if (!f2fs_realtime_discard_enable(sbi)) return 0; dcc->f2fs_issue_discard = kthread_run(issue_discard_thread, sbi, "f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(dcc->f2fs_issue_discard)) { err = PTR_ERR(dcc->f2fs_issue_discard); dcc->f2fs_issue_discard = NULL; } return err; } static int create_discard_cmd_control(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc; int err = 0, i; if (SM_I(sbi)->dcc_info) { dcc = SM_I(sbi)->dcc_info; goto init_thread; } dcc = f2fs_kzalloc(sbi, sizeof(struct discard_cmd_control), GFP_KERNEL); if (!dcc) return -ENOMEM; dcc->discard_io_aware_gran = MAX_PLIST_NUM; dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY; dcc->max_ordered_discard = DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY; if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT) dcc->discard_granularity = sbi->blocks_per_seg; else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION) dcc->discard_granularity = BLKS_PER_SEC(sbi); INIT_LIST_HEAD(&dcc->entry_list); for (i = 0; i < MAX_PLIST_NUM; i++) INIT_LIST_HEAD(&dcc->pend_list[i]); INIT_LIST_HEAD(&dcc->wait_list); INIT_LIST_HEAD(&dcc->fstrim_list); mutex_init(&dcc->cmd_lock); atomic_set(&dcc->issued_discard, 0); atomic_set(&dcc->queued_discard, 0); atomic_set(&dcc->discard_cmd_cnt, 0); dcc->nr_discards = 0; dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg; dcc->max_discard_request = DEF_MAX_DISCARD_REQUEST; dcc->min_discard_issue_time = DEF_MIN_DISCARD_ISSUE_TIME; dcc->mid_discard_issue_time = DEF_MID_DISCARD_ISSUE_TIME; dcc->max_discard_issue_time = DEF_MAX_DISCARD_ISSUE_TIME; dcc->discard_urgent_util = DEF_DISCARD_URGENT_UTIL; dcc->undiscard_blks = 0; dcc->next_pos = 0; dcc->root = RB_ROOT_CACHED; dcc->rbtree_check = false; init_waitqueue_head(&dcc->discard_wait_queue); SM_I(sbi)->dcc_info = dcc; init_thread: err = f2fs_start_discard_thread(sbi); if (err) { kfree(dcc); SM_I(sbi)->dcc_info = NULL; } return err; } static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; if (!dcc) return; f2fs_stop_discard_thread(sbi); /* * Recovery can cache discard commands, so in error path of * fill_super(), it needs to give a chance to handle them. */ f2fs_issue_discard_timeout(sbi); kfree(dcc); SM_I(sbi)->dcc_info = NULL; } static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno) { struct sit_info *sit_i = SIT_I(sbi); if (!__test_and_set_bit(segno, sit_i->dirty_sentries_bitmap)) { sit_i->dirty_sentries++; return false; } return true; } static void __set_sit_entry_type(struct f2fs_sb_info *sbi, int type, unsigned int segno, int modified) { struct seg_entry *se = get_seg_entry(sbi, segno); se->type = type; if (modified) __mark_sit_entry_dirty(sbi, segno); } static inline unsigned long long get_segment_mtime(struct f2fs_sb_info *sbi, block_t blkaddr) { unsigned int segno = GET_SEGNO(sbi, blkaddr); if (segno == NULL_SEGNO) return 0; return get_seg_entry(sbi, segno)->mtime; } static void update_segment_mtime(struct f2fs_sb_info *sbi, block_t blkaddr, unsigned long long old_mtime) { struct seg_entry *se; unsigned int segno = GET_SEGNO(sbi, blkaddr); unsigned long long ctime = get_mtime(sbi, false); unsigned long long mtime = old_mtime ? old_mtime : ctime; if (segno == NULL_SEGNO) return; se = get_seg_entry(sbi, segno); if (!se->mtime) se->mtime = mtime; else se->mtime = div_u64(se->mtime * se->valid_blocks + mtime, se->valid_blocks + 1); if (ctime > SIT_I(sbi)->max_mtime) SIT_I(sbi)->max_mtime = ctime; } static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) { struct seg_entry *se; unsigned int segno, offset; long int new_vblocks; bool exist; #ifdef CONFIG_F2FS_CHECK_FS bool mir_exist; #endif segno = GET_SEGNO(sbi, blkaddr); se = get_seg_entry(sbi, segno); new_vblocks = se->valid_blocks + del; offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); f2fs_bug_on(sbi, (new_vblocks < 0 || (new_vblocks > f2fs_usable_blks_in_seg(sbi, segno)))); se->valid_blocks = new_vblocks; /* Update valid block bitmap */ if (del > 0) { exist = f2fs_test_and_set_bit(offset, se->cur_valid_map); #ifdef CONFIG_F2FS_CHECK_FS mir_exist = f2fs_test_and_set_bit(offset, se->cur_valid_map_mir); if (unlikely(exist != mir_exist)) { f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d", blkaddr, exist); f2fs_bug_on(sbi, 1); } #endif if (unlikely(exist)) { f2fs_err(sbi, "Bitmap was wrongly set, blk:%u", blkaddr); f2fs_bug_on(sbi, 1); se->valid_blocks--; del = 0; } if (f2fs_block_unit_discard(sbi) && !f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; /* * SSR should never reuse block which is checkpointed * or newly invalidated. */ if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks++; } } else { exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map); #ifdef CONFIG_F2FS_CHECK_FS mir_exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map_mir); if (unlikely(exist != mir_exist)) { f2fs_err(sbi, "Inconsistent error when clearing bitmap, blk:%u, old bit:%d", blkaddr, exist); f2fs_bug_on(sbi, 1); } #endif if (unlikely(!exist)) { f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u", blkaddr); f2fs_bug_on(sbi, 1); se->valid_blocks++; del = 0; } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { /* * If checkpoints are off, we must not reuse data that * was used in the previous checkpoint. If it was used * before, we must track that to know how much space we * really have. */ if (f2fs_test_bit(offset, se->ckpt_valid_map)) { spin_lock(&sbi->stat_lock); sbi->unusable_block_count++; spin_unlock(&sbi->stat_lock); } } if (f2fs_block_unit_discard(sbi) && f2fs_test_and_clear_bit(offset, se->discard_map)) sbi->discard_blks++; } if (!f2fs_test_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks += del; __mark_sit_entry_dirty(sbi, segno); /* update total number of valid blocks to be written in ckpt area */ SIT_I(sbi)->written_valid_blocks += del; if (__is_large_section(sbi)) get_sec_entry(sbi, segno)->valid_blocks += del; } void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) { unsigned int segno = GET_SEGNO(sbi, addr); struct sit_info *sit_i = SIT_I(sbi); f2fs_bug_on(sbi, addr == NULL_ADDR); if (addr == NEW_ADDR || addr == COMPRESS_ADDR) return; invalidate_mapping_pages(META_MAPPING(sbi), addr, addr); f2fs_invalidate_compress_page(sbi, addr); /* add it into sit main buffer */ down_write(&sit_i->sentry_lock); update_segment_mtime(sbi, addr, 0); update_sit_entry(sbi, addr, -1); /* add it into dirty seglist */ locate_dirty_segment(sbi, segno); up_write(&sit_i->sentry_lock); } bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) { struct sit_info *sit_i = SIT_I(sbi); unsigned int segno, offset; struct seg_entry *se; bool is_cp = false; if (!__is_valid_data_blkaddr(blkaddr)) return true; down_read(&sit_i->sentry_lock); segno = GET_SEGNO(sbi, blkaddr); se = get_seg_entry(sbi, segno); offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); if (f2fs_test_bit(offset, se->ckpt_valid_map)) is_cp = true; up_read(&sit_i->sentry_lock); return is_cp; } static unsigned short f2fs_curseg_valid_blocks(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); if (sbi->ckpt->alloc_type[type] == SSR) return sbi->blocks_per_seg; return curseg->next_blkoff; } /* * Calculate the number of current summary pages for writing */ int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) { int valid_sum_count = 0; int i, sum_in_page; for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { if (sbi->ckpt->alloc_type[i] != SSR && for_ra) valid_sum_count += le16_to_cpu(F2FS_CKPT(sbi)->cur_data_blkoff[i]); else valid_sum_count += f2fs_curseg_valid_blocks(sbi, i); } sum_in_page = (PAGE_SIZE - 2 * SUM_JOURNAL_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE; if (valid_sum_count <= sum_in_page) return 1; else if ((valid_sum_count - sum_in_page) <= (PAGE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE) return 2; return 3; } /* * Caller should put this summary page */ struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) { if (unlikely(f2fs_cp_error(sbi))) return ERR_PTR(-EIO); return f2fs_get_meta_page_retry(sbi, GET_SUM_BLOCK(sbi, segno)); } void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) { struct page *page = f2fs_grab_meta_page(sbi, blk_addr); memcpy(page_address(page), src, PAGE_SIZE); set_page_dirty(page); f2fs_put_page(page, 1); } static void write_sum_page(struct f2fs_sb_info *sbi, struct f2fs_summary_block *sum_blk, block_t blk_addr) { f2fs_update_meta_page(sbi, (void *)sum_blk, blk_addr); } static void write_current_sum_page(struct f2fs_sb_info *sbi, int type, block_t blk_addr) { struct curseg_info *curseg = CURSEG_I(sbi, type); struct page *page = f2fs_grab_meta_page(sbi, blk_addr); struct f2fs_summary_block *src = curseg->sum_blk; struct f2fs_summary_block *dst; dst = (struct f2fs_summary_block *)page_address(page); memset(dst, 0, PAGE_SIZE); mutex_lock(&curseg->curseg_mutex); down_read(&curseg->journal_rwsem); memcpy(&dst->journal, curseg->journal, SUM_JOURNAL_SIZE); up_read(&curseg->journal_rwsem); memcpy(dst->entries, src->entries, SUM_ENTRY_SIZE); memcpy(&dst->footer, &src->footer, SUM_FOOTER_SIZE); mutex_unlock(&curseg->curseg_mutex); set_page_dirty(page); f2fs_put_page(page, 1); } static int is_next_segment_free(struct f2fs_sb_info *sbi, struct curseg_info *curseg, int type) { unsigned int segno = curseg->segno + 1; struct free_segmap_info *free_i = FREE_I(sbi); if (segno < MAIN_SEGS(sbi) && segno % sbi->segs_per_sec) return !test_bit(segno, free_i->free_segmap); return 0; } /* * Find a new segment from the free segments bitmap to right order * This function should be returned with success, otherwise BUG */ static void get_new_segment(struct f2fs_sb_info *sbi, unsigned int *newseg, bool new_sec, int dir) { struct free_segmap_info *free_i = FREE_I(sbi); unsigned int segno, secno, zoneno; unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone; unsigned int hint = GET_SEC_FROM_SEG(sbi, *newseg); unsigned int old_zoneno = GET_ZONE_FROM_SEG(sbi, *newseg); unsigned int left_start = hint; bool init = true; int go_left = 0; int i; spin_lock(&free_i->segmap_lock); if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) { segno = find_next_zero_bit(free_i->free_segmap, GET_SEG_FROM_SEC(sbi, hint + 1), *newseg + 1); if (segno < GET_SEG_FROM_SEC(sbi, hint + 1)) goto got_it; } find_other_zone: secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint); if (secno >= MAIN_SECS(sbi)) { if (dir == ALLOC_RIGHT) { secno = find_first_zero_bit(free_i->free_secmap, MAIN_SECS(sbi)); f2fs_bug_on(sbi, secno >= MAIN_SECS(sbi)); } else { go_left = 1; left_start = hint - 1; } } if (go_left == 0) goto skip_left; while (test_bit(left_start, free_i->free_secmap)) { if (left_start > 0) { left_start--; continue; } left_start = find_first_zero_bit(free_i->free_secmap, MAIN_SECS(sbi)); f2fs_bug_on(sbi, left_start >= MAIN_SECS(sbi)); break; } secno = left_start; skip_left: segno = GET_SEG_FROM_SEC(sbi, secno); zoneno = GET_ZONE_FROM_SEC(sbi, secno); /* give up on finding another zone */ if (!init) goto got_it; if (sbi->secs_per_zone == 1) goto got_it; if (zoneno == old_zoneno) goto got_it; if (dir == ALLOC_LEFT) { if (!go_left && zoneno + 1 >= total_zones) goto got_it; if (go_left && zoneno == 0) goto got_it; } for (i = 0; i < NR_CURSEG_TYPE; i++) if (CURSEG_I(sbi, i)->zone == zoneno) break; if (i < NR_CURSEG_TYPE) { /* zone is in user, try another */ if (go_left) hint = zoneno * sbi->secs_per_zone - 1; else if (zoneno + 1 >= total_zones) hint = 0; else hint = (zoneno + 1) * sbi->secs_per_zone; init = false; goto find_other_zone; } got_it: /* set it as dirty segment in free segmap */ f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap)); __set_inuse(sbi, segno); *newseg = segno; spin_unlock(&free_i->segmap_lock); } static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified) { struct curseg_info *curseg = CURSEG_I(sbi, type); struct summary_footer *sum_footer; unsigned short seg_type = curseg->seg_type; curseg->inited = true; curseg->segno = curseg->next_segno; curseg->zone = GET_ZONE_FROM_SEG(sbi, curseg->segno); curseg->next_blkoff = 0; curseg->next_segno = NULL_SEGNO; sum_footer = &(curseg->sum_blk->footer); memset(sum_footer, 0, sizeof(struct summary_footer)); sanity_check_seg_type(sbi, seg_type); if (IS_DATASEG(seg_type)) SET_SUM_TYPE(sum_footer, SUM_TYPE_DATA); if (IS_NODESEG(seg_type)) SET_SUM_TYPE(sum_footer, SUM_TYPE_NODE); __set_sit_entry_type(sbi, seg_type, curseg->segno, modified); } static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); unsigned short seg_type = curseg->seg_type; sanity_check_seg_type(sbi, seg_type); if (f2fs_need_rand_seg(sbi)) return get_random_u32_below(MAIN_SECS(sbi) * sbi->segs_per_sec); /* if segs_per_sec is large than 1, we need to keep original policy. */ if (__is_large_section(sbi)) return curseg->segno; /* inmem log may not locate on any segment after mount */ if (!curseg->inited) return 0; if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return 0; if (test_opt(sbi, NOHEAP) && (seg_type == CURSEG_HOT_DATA || IS_NODESEG(seg_type))) return 0; if (SIT_I(sbi)->last_victim[ALLOC_NEXT]) return SIT_I(sbi)->last_victim[ALLOC_NEXT]; /* find segments from 0 to reuse freed segments */ if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) return 0; return curseg->segno; } /* * Allocate a current working segment. * This function always allocates a free segment in LFS manner. */ static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec) { struct curseg_info *curseg = CURSEG_I(sbi, type); unsigned short seg_type = curseg->seg_type; unsigned int segno = curseg->segno; int dir = ALLOC_LEFT; if (curseg->inited) write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, segno)); if (seg_type == CURSEG_WARM_DATA || seg_type == CURSEG_COLD_DATA) dir = ALLOC_RIGHT; if (test_opt(sbi, NOHEAP)) dir = ALLOC_RIGHT; segno = __get_next_segno(sbi, type); get_new_segment(sbi, &segno, new_sec, dir); curseg->next_segno = segno; reset_curseg(sbi, type, 1); curseg->alloc_type = LFS; if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) curseg->fragment_remained_chunk = get_random_u32_inclusive(1, sbi->max_fragment_chunk); } static int __next_free_blkoff(struct f2fs_sb_info *sbi, int segno, block_t start) { struct seg_entry *se = get_seg_entry(sbi, segno); int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long); unsigned long *target_map = SIT_I(sbi)->tmp_map; unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map; unsigned long *cur_map = (unsigned long *)se->cur_valid_map; int i; for (i = 0; i < entries; i++) target_map[i] = ckpt_map[i] | cur_map[i]; return __find_rev_next_zero_bit(target_map, sbi->blocks_per_seg, start); } static int f2fs_find_next_ssr_block(struct f2fs_sb_info *sbi, struct curseg_info *seg) { return __next_free_blkoff(sbi, seg->segno, seg->next_blkoff + 1); } bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno) { return __next_free_blkoff(sbi, segno, 0) < sbi->blocks_per_seg; } /* * This function always allocates a used segment(from dirty seglist) by SSR * manner, so it should recover the existing segment information of valid blocks */ static void change_curseg(struct f2fs_sb_info *sbi, int type) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, type); unsigned int new_segno = curseg->next_segno; struct f2fs_summary_block *sum_node; struct page *sum_page; write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, curseg->segno)); __set_test_and_inuse(sbi, new_segno); mutex_lock(&dirty_i->seglist_lock); __remove_dirty_segment(sbi, new_segno, PRE); __remove_dirty_segment(sbi, new_segno, DIRTY); mutex_unlock(&dirty_i->seglist_lock); reset_curseg(sbi, type, 1); curseg->alloc_type = SSR; curseg->next_blkoff = __next_free_blkoff(sbi, curseg->segno, 0); sum_page = f2fs_get_sum_page(sbi, new_segno); if (IS_ERR(sum_page)) { /* GC won't be able to use stale summary pages by cp_error */ memset(curseg->sum_blk, 0, SUM_ENTRY_SIZE); return; } sum_node = (struct f2fs_summary_block *)page_address(sum_page); memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); f2fs_put_page(sum_page, 1); } static int get_ssr_segment(struct f2fs_sb_info *sbi, int type, int alloc_mode, unsigned long long age); static void get_atssr_segment(struct f2fs_sb_info *sbi, int type, int target_type, int alloc_mode, unsigned long long age) { struct curseg_info *curseg = CURSEG_I(sbi, type); curseg->seg_type = target_type; if (get_ssr_segment(sbi, type, alloc_mode, age)) { struct seg_entry *se = get_seg_entry(sbi, curseg->next_segno); curseg->seg_type = se->type; change_curseg(sbi, type); } else { /* allocate cold segment by default */ curseg->seg_type = CURSEG_COLD_DATA; new_curseg(sbi, type, true); } stat_inc_seg_type(sbi, curseg); } static void __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC); if (!sbi->am.atgc_enabled) return; f2fs_down_read(&SM_I(sbi)->curseg_lock); mutex_lock(&curseg->curseg_mutex); down_write(&SIT_I(sbi)->sentry_lock); get_atssr_segment(sbi, CURSEG_ALL_DATA_ATGC, CURSEG_COLD_DATA, SSR, 0); up_write(&SIT_I(sbi)->sentry_lock); mutex_unlock(&curseg->curseg_mutex); f2fs_up_read(&SM_I(sbi)->curseg_lock); } void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi) { __f2fs_init_atgc_curseg(sbi); } static void __f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); if (!curseg->inited) goto out; if (get_valid_blocks(sbi, curseg->segno, false)) { write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, curseg->segno)); } else { mutex_lock(&DIRTY_I(sbi)->seglist_lock); __set_test_and_free(sbi, curseg->segno, true); mutex_unlock(&DIRTY_I(sbi)->seglist_lock); } out: mutex_unlock(&curseg->curseg_mutex); } void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi) { __f2fs_save_inmem_curseg(sbi, CURSEG_COLD_DATA_PINNED); if (sbi->am.atgc_enabled) __f2fs_save_inmem_curseg(sbi, CURSEG_ALL_DATA_ATGC); } static void __f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); if (!curseg->inited) goto out; if (get_valid_blocks(sbi, curseg->segno, false)) goto out; mutex_lock(&DIRTY_I(sbi)->seglist_lock); __set_test_and_inuse(sbi, curseg->segno); mutex_unlock(&DIRTY_I(sbi)->seglist_lock); out: mutex_unlock(&curseg->curseg_mutex); } void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi) { __f2fs_restore_inmem_curseg(sbi, CURSEG_COLD_DATA_PINNED); if (sbi->am.atgc_enabled) __f2fs_restore_inmem_curseg(sbi, CURSEG_ALL_DATA_ATGC); } static int get_ssr_segment(struct f2fs_sb_info *sbi, int type, int alloc_mode, unsigned long long age) { struct curseg_info *curseg = CURSEG_I(sbi, type); unsigned segno = NULL_SEGNO; unsigned short seg_type = curseg->seg_type; int i, cnt; bool reversed = false; sanity_check_seg_type(sbi, seg_type); /* f2fs_need_SSR() already forces to do this */ if (!f2fs_get_victim(sbi, &segno, BG_GC, seg_type, alloc_mode, age)) { curseg->next_segno = segno; return 1; } /* For node segments, let's do SSR more intensively */ if (IS_NODESEG(seg_type)) { if (seg_type >= CURSEG_WARM_NODE) { reversed = true; i = CURSEG_COLD_NODE; } else { i = CURSEG_HOT_NODE; } cnt = NR_CURSEG_NODE_TYPE; } else { if (seg_type >= CURSEG_WARM_DATA) { reversed = true; i = CURSEG_COLD_DATA; } else { i = CURSEG_HOT_DATA; } cnt = NR_CURSEG_DATA_TYPE; } for (; cnt-- > 0; reversed ? i-- : i++) { if (i == seg_type) continue; if (!f2fs_get_victim(sbi, &segno, BG_GC, i, alloc_mode, age)) { curseg->next_segno = segno; return 1; } } /* find valid_blocks=0 in dirty list */ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { segno = get_free_segment(sbi); if (segno != NULL_SEGNO) { curseg->next_segno = segno; return 1; } } return 0; } static bool need_new_seg(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) && curseg->seg_type == CURSEG_WARM_NODE) return true; if (curseg->alloc_type == LFS && is_next_segment_free(sbi, curseg, type) && likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return true; if (!f2fs_need_SSR(sbi) || !get_ssr_segment(sbi, type, SSR, 0)) return true; return false; } void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, unsigned int start, unsigned int end) { struct curseg_info *curseg = CURSEG_I(sbi, type); unsigned int segno; f2fs_down_read(&SM_I(sbi)->curseg_lock); mutex_lock(&curseg->curseg_mutex); down_write(&SIT_I(sbi)->sentry_lock); segno = CURSEG_I(sbi, type)->segno; if (segno < start || segno > end) goto unlock; if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type, SSR, 0)) change_curseg(sbi, type); else new_curseg(sbi, type, true); stat_inc_seg_type(sbi, curseg); locate_dirty_segment(sbi, segno); unlock: up_write(&SIT_I(sbi)->sentry_lock); if (segno != curseg->segno) f2fs_notice(sbi, "For resize: curseg of type %d: %u ==> %u", type, segno, curseg->segno); mutex_unlock(&curseg->curseg_mutex); f2fs_up_read(&SM_I(sbi)->curseg_lock); } static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type, bool new_sec, bool force) { struct curseg_info *curseg = CURSEG_I(sbi, type); unsigned int old_segno; if (!force && curseg->inited && !curseg->next_blkoff && !get_valid_blocks(sbi, curseg->segno, new_sec) && !get_ckpt_valid_blocks(sbi, curseg->segno, new_sec)) return; old_segno = curseg->segno; new_curseg(sbi, type, true); stat_inc_seg_type(sbi, curseg); locate_dirty_segment(sbi, old_segno); } void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force) { f2fs_down_read(&SM_I(sbi)->curseg_lock); down_write(&SIT_I(sbi)->sentry_lock); __allocate_new_segment(sbi, type, true, force); up_write(&SIT_I(sbi)->sentry_lock); f2fs_up_read(&SM_I(sbi)->curseg_lock); } void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi) { int i; f2fs_down_read(&SM_I(sbi)->curseg_lock); down_write(&SIT_I(sbi)->sentry_lock); for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) __allocate_new_segment(sbi, i, false, false); up_write(&SIT_I(sbi)->sentry_lock); f2fs_up_read(&SM_I(sbi)->curseg_lock); } bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc) { __u64 trim_start = cpc->trim_start; bool has_candidate = false; down_write(&SIT_I(sbi)->sentry_lock); for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) { if (add_discard_addrs(sbi, cpc, true)) { has_candidate = true; break; } } up_write(&SIT_I(sbi)->sentry_lock); cpc->trim_start = trim_start; return has_candidate; } static unsigned int __issue_discard_cmd_range(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy, unsigned int start, unsigned int end) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_cmd *prev_dc = NULL, *next_dc = NULL; struct rb_node **insert_p = NULL, *insert_parent = NULL; struct discard_cmd *dc; struct blk_plug plug; int issued; unsigned int trimmed = 0; next: issued = 0; mutex_lock(&dcc->cmd_lock); if (unlikely(dcc->rbtree_check)) f2fs_bug_on(sbi, !f2fs_check_discard_tree(sbi)); dc = __lookup_discard_cmd_ret(&dcc->root, start, &prev_dc, &next_dc, &insert_p, &insert_parent); if (!dc) dc = next_dc; blk_start_plug(&plug); while (dc && dc->di.lstart <= end) { struct rb_node *node; int err = 0; if (dc->di.len < dpolicy->granularity) goto skip; if (dc->state != D_PREP) { list_move_tail(&dc->list, &dcc->fstrim_list); goto skip; } err = __submit_discard_cmd(sbi, dpolicy, dc, &issued); if (issued >= dpolicy->max_requests) { start = dc->di.lstart + dc->di.len; if (err) __remove_discard_cmd(sbi, dc); blk_finish_plug(&plug); mutex_unlock(&dcc->cmd_lock); trimmed += __wait_all_discard_cmd(sbi, NULL); f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); goto next; } skip: node = rb_next(&dc->rb_node); if (err) __remove_discard_cmd(sbi, dc); dc = rb_entry_safe(node, struct discard_cmd, rb_node); if (fatal_signal_pending(current)) break; } blk_finish_plug(&plug); mutex_unlock(&dcc->cmd_lock); return trimmed; } int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) { __u64 start = F2FS_BYTES_TO_BLK(range->start); __u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1; unsigned int start_segno, end_segno; block_t start_block, end_block; struct cp_control cpc; struct discard_policy dpolicy; unsigned long long trimmed = 0; int err = 0; bool need_align = f2fs_lfs_mode(sbi) && __is_large_section(sbi); if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize) return -EINVAL; if (end < MAIN_BLKADDR(sbi)) goto out; if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { f2fs_warn(sbi, "Found FS corruption, run fsck to fix."); return -EFSCORRUPTED; } /* start/end segment number in main_area */ start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start); end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 : GET_SEGNO(sbi, end); if (need_align) { start_segno = rounddown(start_segno, sbi->segs_per_sec); end_segno = roundup(end_segno + 1, sbi->segs_per_sec) - 1; } cpc.reason = CP_DISCARD; cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen)); cpc.trim_start = start_segno; cpc.trim_end = end_segno; if (sbi->discard_blks == 0) goto out; f2fs_down_write(&sbi->gc_lock); stat_inc_cp_call_count(sbi, TOTAL_CALL); err = f2fs_write_checkpoint(sbi, &cpc); f2fs_up_write(&sbi->gc_lock); if (err) goto out; /* * We filed discard candidates, but actually we don't need to wait for * all of them, since they'll be issued in idle time along with runtime * discard option. User configuration looks like using runtime discard * or periodic fstrim instead of it. */ if (f2fs_realtime_discard_enable(sbi)) goto out; start_block = START_BLOCK(sbi, start_segno); end_block = START_BLOCK(sbi, end_segno + 1); __init_discard_policy(sbi, &dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen); trimmed = __issue_discard_cmd_range(sbi, &dpolicy, start_block, end_block); trimmed += __wait_discard_cmd_range(sbi, &dpolicy, start_block, end_block); out: if (!err) range->len = F2FS_BLK_TO_BYTES(trimmed); return err; } int f2fs_rw_hint_to_seg_type(enum rw_hint hint) { switch (hint) { case WRITE_LIFE_SHORT: return CURSEG_HOT_DATA; case WRITE_LIFE_EXTREME: return CURSEG_COLD_DATA; default: return CURSEG_WARM_DATA; } } static int __get_segment_type_2(struct f2fs_io_info *fio) { if (fio->type == DATA) return CURSEG_HOT_DATA; else return CURSEG_HOT_NODE; } static int __get_segment_type_4(struct f2fs_io_info *fio) { if (fio->type == DATA) { struct inode *inode = fio->page->mapping->host; if (S_ISDIR(inode->i_mode)) return CURSEG_HOT_DATA; else return CURSEG_COLD_DATA; } else { if (IS_DNODE(fio->page) && is_cold_node(fio->page)) return CURSEG_WARM_NODE; else return CURSEG_COLD_NODE; } } static int __get_age_segment_type(struct inode *inode, pgoff_t pgofs) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_info ei = {}; if (f2fs_lookup_age_extent_cache(inode, pgofs, &ei)) { if (!ei.age) return NO_CHECK_TYPE; if (ei.age <= sbi->hot_data_age_threshold) return CURSEG_HOT_DATA; if (ei.age <= sbi->warm_data_age_threshold) return CURSEG_WARM_DATA; return CURSEG_COLD_DATA; } return NO_CHECK_TYPE; } static int __get_segment_type_6(struct f2fs_io_info *fio) { if (fio->type == DATA) { struct inode *inode = fio->page->mapping->host; int type; if (is_inode_flag_set(inode, FI_ALIGNED_WRITE)) return CURSEG_COLD_DATA_PINNED; if (page_private_gcing(fio->page)) { if (fio->sbi->am.atgc_enabled && (fio->io_type == FS_DATA_IO) && (fio->sbi->gc_mode != GC_URGENT_HIGH)) return CURSEG_ALL_DATA_ATGC; else return CURSEG_COLD_DATA; } if (file_is_cold(inode) || f2fs_need_compress_data(inode)) return CURSEG_COLD_DATA; type = __get_age_segment_type(inode, fio->page->index); if (type != NO_CHECK_TYPE) return type; if (file_is_hot(inode) || is_inode_flag_set(inode, FI_HOT_DATA) || f2fs_is_cow_file(inode)) return CURSEG_HOT_DATA; return f2fs_rw_hint_to_seg_type(inode->i_write_hint); } else { if (IS_DNODE(fio->page)) return is_cold_node(fio->page) ? CURSEG_WARM_NODE : CURSEG_HOT_NODE; return CURSEG_COLD_NODE; } } static int __get_segment_type(struct f2fs_io_info *fio) { int type = 0; switch (F2FS_OPTION(fio->sbi).active_logs) { case 2: type = __get_segment_type_2(fio); break; case 4: type = __get_segment_type_4(fio); break; case 6: type = __get_segment_type_6(fio); break; default: f2fs_bug_on(fio->sbi, true); } if (IS_HOT(type)) fio->temp = HOT; else if (IS_WARM(type)) fio->temp = WARM; else fio->temp = COLD; return type; } static void f2fs_randomize_chunk(struct f2fs_sb_info *sbi, struct curseg_info *seg) { /* To allocate block chunks in different sizes, use random number */ if (--seg->fragment_remained_chunk > 0) return; seg->fragment_remained_chunk = get_random_u32_inclusive(1, sbi->max_fragment_chunk); seg->next_blkoff += get_random_u32_inclusive(1, sbi->max_fragment_hole); } void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, struct f2fs_io_info *fio) { struct sit_info *sit_i = SIT_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, type); unsigned long long old_mtime; bool from_gc = (type == CURSEG_ALL_DATA_ATGC); struct seg_entry *se = NULL; bool segment_full = false; f2fs_down_read(&SM_I(sbi)->curseg_lock); mutex_lock(&curseg->curseg_mutex); down_write(&sit_i->sentry_lock); if (from_gc) { f2fs_bug_on(sbi, GET_SEGNO(sbi, old_blkaddr) == NULL_SEGNO); se = get_seg_entry(sbi, GET_SEGNO(sbi, old_blkaddr)); sanity_check_seg_type(sbi, se->type); f2fs_bug_on(sbi, IS_NODESEG(se->type)); } *new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); f2fs_bug_on(sbi, curseg->next_blkoff >= sbi->blocks_per_seg); f2fs_wait_discard_bio(sbi, *new_blkaddr); curseg->sum_blk->entries[curseg->next_blkoff] = *sum; if (curseg->alloc_type == SSR) { curseg->next_blkoff = f2fs_find_next_ssr_block(sbi, curseg); } else { curseg->next_blkoff++; if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) f2fs_randomize_chunk(sbi, curseg); } if (curseg->next_blkoff >= f2fs_usable_blks_in_seg(sbi, curseg->segno)) segment_full = true; stat_inc_block_count(sbi, curseg); if (from_gc) { old_mtime = get_segment_mtime(sbi, old_blkaddr); } else { update_segment_mtime(sbi, old_blkaddr, 0); old_mtime = 0; } update_segment_mtime(sbi, *new_blkaddr, old_mtime); /* * SIT information should be updated before segment allocation, * since SSR needs latest valid block information. */ update_sit_entry(sbi, *new_blkaddr, 1); if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) update_sit_entry(sbi, old_blkaddr, -1); /* * If the current segment is full, flush it out and replace it with a * new segment. */ if (segment_full) { if (from_gc) { get_atssr_segment(sbi, type, se->type, AT_SSR, se->mtime); } else { if (need_new_seg(sbi, type)) new_curseg(sbi, type, false); else change_curseg(sbi, type); stat_inc_seg_type(sbi, curseg); } } /* * segment dirty status should be updated after segment allocation, * so we just need to update status only one time after previous * segment being closed. */ locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr)); if (IS_DATASEG(type)) atomic64_inc(&sbi->allocated_data_blocks); up_write(&sit_i->sentry_lock); if (page && IS_NODESEG(type)) { fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg)); f2fs_inode_chksum_set(sbi, page); } if (fio) { struct f2fs_bio_info *io; if (F2FS_IO_ALIGNED(sbi)) fio->retry = 0; INIT_LIST_HEAD(&fio->list); fio->in_list = 1; io = sbi->write_io[fio->type] + fio->temp; spin_lock(&io->io_lock); list_add_tail(&fio->list, &io->io_list); spin_unlock(&io->io_lock); } mutex_unlock(&curseg->curseg_mutex); f2fs_up_read(&SM_I(sbi)->curseg_lock); } void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino, block_t blkaddr, unsigned int blkcnt) { if (!f2fs_is_multi_device(sbi)) return; while (1) { unsigned int devidx = f2fs_target_device_index(sbi, blkaddr); unsigned int blks = FDEV(devidx).end_blk - blkaddr + 1; /* update device state for fsync */ f2fs_set_dirty_device(sbi, ino, devidx, FLUSH_INO); /* update device state for checkpoint */ if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) { spin_lock(&sbi->dev_lock); f2fs_set_bit(devidx, (char *)&sbi->dirty_device); spin_unlock(&sbi->dev_lock); } if (blkcnt <= blks) break; blkcnt -= blks; blkaddr += blks; } } static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) { int type = __get_segment_type(fio); bool keep_order = (f2fs_lfs_mode(fio->sbi) && type == CURSEG_COLD_DATA); if (keep_order) f2fs_down_read(&fio->sbi->io_order_lock); reallocate: f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, &fio->new_blkaddr, sum, type, fio); if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) { invalidate_mapping_pages(META_MAPPING(fio->sbi), fio->old_blkaddr, fio->old_blkaddr); f2fs_invalidate_compress_page(fio->sbi, fio->old_blkaddr); } /* writeout dirty page into bdev */ f2fs_submit_page_write(fio); if (fio->retry) { fio->old_blkaddr = fio->new_blkaddr; goto reallocate; } f2fs_update_device_state(fio->sbi, fio->ino, fio->new_blkaddr, 1); if (keep_order) f2fs_up_read(&fio->sbi->io_order_lock); } void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, enum iostat_type io_type) { struct f2fs_io_info fio = { .sbi = sbi, .type = META, .temp = HOT, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC | REQ_META | REQ_PRIO, .old_blkaddr = page->index, .new_blkaddr = page->index, .page = page, .encrypted_page = NULL, .in_list = 0, }; if (unlikely(page->index >= MAIN_BLKADDR(sbi))) fio.op_flags &= ~REQ_META; set_page_writeback(page); f2fs_submit_page_write(&fio); stat_inc_meta_count(sbi, page->index); f2fs_update_iostat(sbi, NULL, io_type, F2FS_BLKSIZE); } void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio) { struct f2fs_summary sum; set_summary(&sum, nid, 0, 0); do_write_page(&sum, fio); f2fs_update_iostat(fio->sbi, NULL, fio->io_type, F2FS_BLKSIZE); } void f2fs_outplace_write_data(struct dnode_of_data *dn, struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; struct f2fs_summary sum; f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR); if (fio->io_type == FS_DATA_IO || fio->io_type == FS_CP_DATA_IO) f2fs_update_age_extent_cache(dn); set_summary(&sum, dn->nid, dn->ofs_in_node, fio->version); do_write_page(&sum, fio); f2fs_update_data_blkaddr(dn, fio->new_blkaddr); f2fs_update_iostat(sbi, dn->inode, fio->io_type, F2FS_BLKSIZE); } int f2fs_inplace_write_data(struct f2fs_io_info *fio) { int err; struct f2fs_sb_info *sbi = fio->sbi; unsigned int segno; fio->new_blkaddr = fio->old_blkaddr; /* i/o temperature is needed for passing down write hints */ __get_segment_type(fio); segno = GET_SEGNO(sbi, fio->new_blkaddr); if (!IS_DATASEG(get_seg_entry(sbi, segno)->type)) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_warn(sbi, "%s: incorrect segment(%u) type, run fsck to fix.", __func__, segno); err = -EFSCORRUPTED; f2fs_handle_error(sbi, ERROR_INCONSISTENT_SUM_TYPE); goto drop_bio; } if (f2fs_cp_error(sbi)) { err = -EIO; goto drop_bio; } if (fio->post_read) invalidate_mapping_pages(META_MAPPING(sbi), fio->new_blkaddr, fio->new_blkaddr); stat_inc_inplace_blocks(fio->sbi); if (fio->bio && !IS_F2FS_IPU_NOCACHE(sbi)) err = f2fs_merge_page_bio(fio); else err = f2fs_submit_page_bio(fio); if (!err) { f2fs_update_device_state(fio->sbi, fio->ino, fio->new_blkaddr, 1); f2fs_update_iostat(fio->sbi, fio->page->mapping->host, fio->io_type, F2FS_BLKSIZE); } return err; drop_bio: if (fio->bio && *(fio->bio)) { struct bio *bio = *(fio->bio); bio->bi_status = BLK_STS_IOERR; bio_endio(bio); *(fio->bio) = NULL; } return err; } static inline int __f2fs_get_curseg(struct f2fs_sb_info *sbi, unsigned int segno) { int i; for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) { if (CURSEG_I(sbi, i)->segno == segno) break; } return i; } void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t old_blkaddr, block_t new_blkaddr, bool recover_curseg, bool recover_newaddr, bool from_gc) { struct sit_info *sit_i = SIT_I(sbi); struct curseg_info *curseg; unsigned int segno, old_cursegno; struct seg_entry *se; int type; unsigned short old_blkoff; unsigned char old_alloc_type; segno = GET_SEGNO(sbi, new_blkaddr); se = get_seg_entry(sbi, segno); type = se->type; f2fs_down_write(&SM_I(sbi)->curseg_lock); if (!recover_curseg) { /* for recovery flow */ if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) { if (old_blkaddr == NULL_ADDR) type = CURSEG_COLD_DATA; else type = CURSEG_WARM_DATA; } } else { if (IS_CURSEG(sbi, segno)) { /* se->type is volatile as SSR allocation */ type = __f2fs_get_curseg(sbi, segno); f2fs_bug_on(sbi, type == NO_CHECK_TYPE); } else { type = CURSEG_WARM_DATA; } } f2fs_bug_on(sbi, !IS_DATASEG(type)); curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); down_write(&sit_i->sentry_lock); old_cursegno = curseg->segno; old_blkoff = curseg->next_blkoff; old_alloc_type = curseg->alloc_type; /* change the current segment */ if (segno != curseg->segno) { curseg->next_segno = segno; change_curseg(sbi, type); } curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr); curseg->sum_blk->entries[curseg->next_blkoff] = *sum; if (!recover_curseg || recover_newaddr) { if (!from_gc) update_segment_mtime(sbi, new_blkaddr, 0); update_sit_entry(sbi, new_blkaddr, 1); } if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) { invalidate_mapping_pages(META_MAPPING(sbi), old_blkaddr, old_blkaddr); f2fs_invalidate_compress_page(sbi, old_blkaddr); if (!from_gc) update_segment_mtime(sbi, old_blkaddr, 0); update_sit_entry(sbi, old_blkaddr, -1); } locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr)); locate_dirty_segment(sbi, old_cursegno); if (recover_curseg) { if (old_cursegno != curseg->segno) { curseg->next_segno = old_cursegno; change_curseg(sbi, type); } curseg->next_blkoff = old_blkoff; curseg->alloc_type = old_alloc_type; } up_write(&sit_i->sentry_lock); mutex_unlock(&curseg->curseg_mutex); f2fs_up_write(&SM_I(sbi)->curseg_lock); } void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, block_t old_addr, block_t new_addr, unsigned char version, bool recover_curseg, bool recover_newaddr) { struct f2fs_summary sum; set_summary(&sum, dn->nid, dn->ofs_in_node, version); f2fs_do_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg, recover_newaddr, false); f2fs_update_data_blkaddr(dn, new_addr); } void f2fs_wait_on_page_writeback(struct page *page, enum page_type type, bool ordered, bool locked) { if (PageWriteback(page)) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); /* submit cached LFS IO */ f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type); /* submit cached IPU IO */ f2fs_submit_merged_ipu_write(sbi, NULL, page); if (ordered) { wait_on_page_writeback(page); f2fs_bug_on(sbi, locked && PageWriteback(page)); } else { wait_for_stable_page(page); } } } void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *cpage; if (!f2fs_post_read_required(inode)) return; if (!__is_valid_data_blkaddr(blkaddr)) return; cpage = find_lock_page(META_MAPPING(sbi), blkaddr); if (cpage) { f2fs_wait_on_page_writeback(cpage, DATA, true, true); f2fs_put_page(cpage, 1); } } void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, block_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); block_t i; if (!f2fs_post_read_required(inode)) return; for (i = 0; i < len; i++) f2fs_wait_on_block_writeback(inode, blkaddr + i); invalidate_mapping_pages(META_MAPPING(sbi), blkaddr, blkaddr + len - 1); } static int read_compacted_summaries(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); struct curseg_info *seg_i; unsigned char *kaddr; struct page *page; block_t start; int i, j, offset; start = start_sum_block(sbi); page = f2fs_get_meta_page(sbi, start++); if (IS_ERR(page)) return PTR_ERR(page); kaddr = (unsigned char *)page_address(page); /* Step 1: restore nat cache */ seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); memcpy(seg_i->journal, kaddr, SUM_JOURNAL_SIZE); /* Step 2: restore sit cache */ seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA); memcpy(seg_i->journal, kaddr + SUM_JOURNAL_SIZE, SUM_JOURNAL_SIZE); offset = 2 * SUM_JOURNAL_SIZE; /* Step 3: restore summary entries */ for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { unsigned short blk_off; unsigned int segno; seg_i = CURSEG_I(sbi, i); segno = le32_to_cpu(ckpt->cur_data_segno[i]); blk_off = le16_to_cpu(ckpt->cur_data_blkoff[i]); seg_i->next_segno = segno; reset_curseg(sbi, i, 0); seg_i->alloc_type = ckpt->alloc_type[i]; seg_i->next_blkoff = blk_off; if (seg_i->alloc_type == SSR) blk_off = sbi->blocks_per_seg; for (j = 0; j < blk_off; j++) { struct f2fs_summary *s; s = (struct f2fs_summary *)(kaddr + offset); seg_i->sum_blk->entries[j] = *s; offset += SUMMARY_SIZE; if (offset + SUMMARY_SIZE <= PAGE_SIZE - SUM_FOOTER_SIZE) continue; f2fs_put_page(page, 1); page = NULL; page = f2fs_get_meta_page(sbi, start++); if (IS_ERR(page)) return PTR_ERR(page); kaddr = (unsigned char *)page_address(page); offset = 0; } } f2fs_put_page(page, 1); return 0; } static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); struct f2fs_summary_block *sum; struct curseg_info *curseg; struct page *new; unsigned short blk_off; unsigned int segno = 0; block_t blk_addr = 0; int err = 0; /* get segment number and block addr */ if (IS_DATASEG(type)) { segno = le32_to_cpu(ckpt->cur_data_segno[type]); blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type - CURSEG_HOT_DATA]); if (__exist_node_summaries(sbi)) blk_addr = sum_blk_addr(sbi, NR_CURSEG_PERSIST_TYPE, type); else blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type); } else { segno = le32_to_cpu(ckpt->cur_node_segno[type - CURSEG_HOT_NODE]); blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type - CURSEG_HOT_NODE]); if (__exist_node_summaries(sbi)) blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE, type - CURSEG_HOT_NODE); else blk_addr = GET_SUM_BLOCK(sbi, segno); } new = f2fs_get_meta_page(sbi, blk_addr); if (IS_ERR(new)) return PTR_ERR(new); sum = (struct f2fs_summary_block *)page_address(new); if (IS_NODESEG(type)) { if (__exist_node_summaries(sbi)) { struct f2fs_summary *ns = &sum->entries[0]; int i; for (i = 0; i < sbi->blocks_per_seg; i++, ns++) { ns->version = 0; ns->ofs_in_node = 0; } } else { err = f2fs_restore_node_summary(sbi, segno, sum); if (err) goto out; } } /* set uncompleted segment to curseg */ curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); /* update journal info */ down_write(&curseg->journal_rwsem); memcpy(curseg->journal, &sum->journal, SUM_JOURNAL_SIZE); up_write(&curseg->journal_rwsem); memcpy(curseg->sum_blk->entries, sum->entries, SUM_ENTRY_SIZE); memcpy(&curseg->sum_blk->footer, &sum->footer, SUM_FOOTER_SIZE); curseg->next_segno = segno; reset_curseg(sbi, type, 0); curseg->alloc_type = ckpt->alloc_type[type]; curseg->next_blkoff = blk_off; mutex_unlock(&curseg->curseg_mutex); out: f2fs_put_page(new, 1); return err; } static int restore_curseg_summaries(struct f2fs_sb_info *sbi) { struct f2fs_journal *sit_j = CURSEG_I(sbi, CURSEG_COLD_DATA)->journal; struct f2fs_journal *nat_j = CURSEG_I(sbi, CURSEG_HOT_DATA)->journal; int type = CURSEG_HOT_DATA; int err; if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) { int npages = f2fs_npages_for_summary_flush(sbi, true); if (npages >= 2) f2fs_ra_meta_pages(sbi, start_sum_block(sbi), npages, META_CP, true); /* restore for compacted data summary */ err = read_compacted_summaries(sbi); if (err) return err; type = CURSEG_HOT_NODE; } if (__exist_node_summaries(sbi)) f2fs_ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_PERSIST_TYPE, type), NR_CURSEG_PERSIST_TYPE - type, META_CP, true); for (; type <= CURSEG_COLD_NODE; type++) { err = read_normal_summaries(sbi, type); if (err) return err; } /* sanity check for summary blocks */ if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES || sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) { f2fs_err(sbi, "invalid journal entries nats %u sits %u", nats_in_cursum(nat_j), sits_in_cursum(sit_j)); return -EINVAL; } return 0; } static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) { struct page *page; unsigned char *kaddr; struct f2fs_summary *summary; struct curseg_info *seg_i; int written_size = 0; int i, j; page = f2fs_grab_meta_page(sbi, blkaddr++); kaddr = (unsigned char *)page_address(page); memset(kaddr, 0, PAGE_SIZE); /* Step 1: write nat cache */ seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); memcpy(kaddr, seg_i->journal, SUM_JOURNAL_SIZE); written_size += SUM_JOURNAL_SIZE; /* Step 2: write sit cache */ seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA); memcpy(kaddr + written_size, seg_i->journal, SUM_JOURNAL_SIZE); written_size += SUM_JOURNAL_SIZE; /* Step 3: write summary entries */ for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { seg_i = CURSEG_I(sbi, i); for (j = 0; j < f2fs_curseg_valid_blocks(sbi, i); j++) { if (!page) { page = f2fs_grab_meta_page(sbi, blkaddr++); kaddr = (unsigned char *)page_address(page); memset(kaddr, 0, PAGE_SIZE); written_size = 0; } summary = (struct f2fs_summary *)(kaddr + written_size); *summary = seg_i->sum_blk->entries[j]; written_size += SUMMARY_SIZE; if (written_size + SUMMARY_SIZE <= PAGE_SIZE - SUM_FOOTER_SIZE) continue; set_page_dirty(page); f2fs_put_page(page, 1); page = NULL; } } if (page) { set_page_dirty(page); f2fs_put_page(page, 1); } } static void write_normal_summaries(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { int i, end; if (IS_DATASEG(type)) end = type + NR_CURSEG_DATA_TYPE; else end = type + NR_CURSEG_NODE_TYPE; for (i = type; i < end; i++) write_current_sum_page(sbi, i, blkaddr + (i - type)); } void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) { if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) write_compacted_summaries(sbi, start_blk); else write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA); } void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) { write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE); } int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, unsigned int val, int alloc) { int i; if (type == NAT_JOURNAL) { for (i = 0; i < nats_in_cursum(journal); i++) { if (le32_to_cpu(nid_in_journal(journal, i)) == val) return i; } if (alloc && __has_cursum_space(journal, 1, NAT_JOURNAL)) return update_nats_in_cursum(journal, 1); } else if (type == SIT_JOURNAL) { for (i = 0; i < sits_in_cursum(journal); i++) if (le32_to_cpu(segno_in_journal(journal, i)) == val) return i; if (alloc && __has_cursum_space(journal, 1, SIT_JOURNAL)) return update_sits_in_cursum(journal, 1); } return -1; } static struct page *get_current_sit_page(struct f2fs_sb_info *sbi, unsigned int segno) { return f2fs_get_meta_page(sbi, current_sit_addr(sbi, segno)); } static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, unsigned int start) { struct sit_info *sit_i = SIT_I(sbi); struct page *page; pgoff_t src_off, dst_off; src_off = current_sit_addr(sbi, start); dst_off = next_sit_addr(sbi, src_off); page = f2fs_grab_meta_page(sbi, dst_off); seg_info_to_sit_page(sbi, page, start); set_page_dirty(page); set_to_next_sit(sit_i, start); return page; } static struct sit_entry_set *grab_sit_entry_set(void) { struct sit_entry_set *ses = f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_NOFS, true, NULL); ses->entry_cnt = 0; INIT_LIST_HEAD(&ses->set_list); return ses; } static void release_sit_entry_set(struct sit_entry_set *ses) { list_del(&ses->set_list); kmem_cache_free(sit_entry_set_slab, ses); } static void adjust_sit_entry_set(struct sit_entry_set *ses, struct list_head *head) { struct sit_entry_set *next = ses; if (list_is_last(&ses->set_list, head)) return; list_for_each_entry_continue(next, head, set_list) if (ses->entry_cnt <= next->entry_cnt) { list_move_tail(&ses->set_list, &next->set_list); return; } list_move_tail(&ses->set_list, head); } static void add_sit_entry(unsigned int segno, struct list_head *head) { struct sit_entry_set *ses; unsigned int start_segno = START_SEGNO(segno); list_for_each_entry(ses, head, set_list) { if (ses->start_segno == start_segno) { ses->entry_cnt++; adjust_sit_entry_set(ses, head); return; } } ses = grab_sit_entry_set(); ses->start_segno = start_segno; ses->entry_cnt++; list_add(&ses->set_list, head); } static void add_sits_in_set(struct f2fs_sb_info *sbi) { struct f2fs_sm_info *sm_info = SM_I(sbi); struct list_head *set_list = &sm_info->sit_entry_set; unsigned long *bitmap = SIT_I(sbi)->dirty_sentries_bitmap; unsigned int segno; for_each_set_bit(segno, bitmap, MAIN_SEGS(sbi)) add_sit_entry(segno, set_list); } static void remove_sits_in_journal(struct f2fs_sb_info *sbi) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA); struct f2fs_journal *journal = curseg->journal; int i; down_write(&curseg->journal_rwsem); for (i = 0; i < sits_in_cursum(journal); i++) { unsigned int segno; bool dirtied; segno = le32_to_cpu(segno_in_journal(journal, i)); dirtied = __mark_sit_entry_dirty(sbi, segno); if (!dirtied) add_sit_entry(segno, &SM_I(sbi)->sit_entry_set); } update_sits_in_cursum(journal, -i); up_write(&curseg->journal_rwsem); } /* * CP calls this function, which flushes SIT entries including sit_journal, * and moves prefree segs to free segs. */ void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct sit_info *sit_i = SIT_I(sbi); unsigned long *bitmap = sit_i->dirty_sentries_bitmap; struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA); struct f2fs_journal *journal = curseg->journal; struct sit_entry_set *ses, *tmp; struct list_head *head = &SM_I(sbi)->sit_entry_set; bool to_journal = !is_sbi_flag_set(sbi, SBI_IS_RESIZEFS); struct seg_entry *se; down_write(&sit_i->sentry_lock); if (!sit_i->dirty_sentries) goto out; /* * add and account sit entries of dirty bitmap in sit entry * set temporarily */ add_sits_in_set(sbi); /* * if there are no enough space in journal to store dirty sit * entries, remove all entries from journal and add and account * them in sit entry set. */ if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL) || !to_journal) remove_sits_in_journal(sbi); /* * there are two steps to flush sit entries: * #1, flush sit entries to journal in current cold data summary block. * #2, flush sit entries to sit page. */ list_for_each_entry_safe(ses, tmp, head, set_list) { struct page *page = NULL; struct f2fs_sit_block *raw_sit = NULL; unsigned int start_segno = ses->start_segno; unsigned int end = min(start_segno + SIT_ENTRY_PER_BLOCK, (unsigned long)MAIN_SEGS(sbi)); unsigned int segno = start_segno; if (to_journal && !__has_cursum_space(journal, ses->entry_cnt, SIT_JOURNAL)) to_journal = false; if (to_journal) { down_write(&curseg->journal_rwsem); } else { page = get_next_sit_page(sbi, start_segno); raw_sit = page_address(page); } /* flush dirty sit entries in region of current sit set */ for_each_set_bit_from(segno, bitmap, end) { int offset, sit_offset; se = get_seg_entry(sbi, segno); #ifdef CONFIG_F2FS_CHECK_FS if (memcmp(se->cur_valid_map, se->cur_valid_map_mir, SIT_VBLOCK_MAP_SIZE)) f2fs_bug_on(sbi, 1); #endif /* add discard candidates */ if (!(cpc->reason & CP_DISCARD)) { cpc->trim_start = segno; add_discard_addrs(sbi, cpc, false); } if (to_journal) { offset = f2fs_lookup_journal_in_cursum(journal, SIT_JOURNAL, segno, 1); f2fs_bug_on(sbi, offset < 0); segno_in_journal(journal, offset) = cpu_to_le32(segno); seg_info_to_raw_sit(se, &sit_in_journal(journal, offset)); check_block_count(sbi, segno, &sit_in_journal(journal, offset)); } else { sit_offset = SIT_ENTRY_OFFSET(sit_i, segno); seg_info_to_raw_sit(se, &raw_sit->entries[sit_offset]); check_block_count(sbi, segno, &raw_sit->entries[sit_offset]); } __clear_bit(segno, bitmap); sit_i->dirty_sentries--; ses->entry_cnt--; } if (to_journal) up_write(&curseg->journal_rwsem); else f2fs_put_page(page, 1); f2fs_bug_on(sbi, ses->entry_cnt); release_sit_entry_set(ses); } f2fs_bug_on(sbi, !list_empty(head)); f2fs_bug_on(sbi, sit_i->dirty_sentries); out: if (cpc->reason & CP_DISCARD) { __u64 trim_start = cpc->trim_start; for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) add_discard_addrs(sbi, cpc, false); cpc->trim_start = trim_start; } up_write(&sit_i->sentry_lock); set_prefree_as_free_segments(sbi); } static int build_sit_info(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct sit_info *sit_i; unsigned int sit_segs, start; char *src_bitmap, *bitmap; unsigned int bitmap_size, main_bitmap_size, sit_bitmap_size; unsigned int discard_map = f2fs_block_unit_discard(sbi) ? 1 : 0; /* allocate memory for SIT information */ sit_i = f2fs_kzalloc(sbi, sizeof(struct sit_info), GFP_KERNEL); if (!sit_i) return -ENOMEM; SM_I(sbi)->sit_info = sit_i; sit_i->sentries = f2fs_kvzalloc(sbi, array_size(sizeof(struct seg_entry), MAIN_SEGS(sbi)), GFP_KERNEL); if (!sit_i->sentries) return -ENOMEM; main_bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(sbi, main_bitmap_size, GFP_KERNEL); if (!sit_i->dirty_sentries_bitmap) return -ENOMEM; #ifdef CONFIG_F2FS_CHECK_FS bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * (3 + discard_map); #else bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * (2 + discard_map); #endif sit_i->bitmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); if (!sit_i->bitmap) return -ENOMEM; bitmap = sit_i->bitmap; for (start = 0; start < MAIN_SEGS(sbi); start++) { sit_i->sentries[start].cur_valid_map = bitmap; bitmap += SIT_VBLOCK_MAP_SIZE; sit_i->sentries[start].ckpt_valid_map = bitmap; bitmap += SIT_VBLOCK_MAP_SIZE; #ifdef CONFIG_F2FS_CHECK_FS sit_i->sentries[start].cur_valid_map_mir = bitmap; bitmap += SIT_VBLOCK_MAP_SIZE; #endif if (discard_map) { sit_i->sentries[start].discard_map = bitmap; bitmap += SIT_VBLOCK_MAP_SIZE; } } sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); if (!sit_i->tmp_map) return -ENOMEM; if (__is_large_section(sbi)) { sit_i->sec_entries = f2fs_kvzalloc(sbi, array_size(sizeof(struct sec_entry), MAIN_SECS(sbi)), GFP_KERNEL); if (!sit_i->sec_entries) return -ENOMEM; } /* get information related with SIT */ sit_segs = le32_to_cpu(raw_super->segment_count_sit) >> 1; /* setup SIT bitmap from ckeckpoint pack */ sit_bitmap_size = __bitmap_size(sbi, SIT_BITMAP); src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP); sit_i->sit_bitmap = kmemdup(src_bitmap, sit_bitmap_size, GFP_KERNEL); if (!sit_i->sit_bitmap) return -ENOMEM; #ifdef CONFIG_F2FS_CHECK_FS sit_i->sit_bitmap_mir = kmemdup(src_bitmap, sit_bitmap_size, GFP_KERNEL); if (!sit_i->sit_bitmap_mir) return -ENOMEM; sit_i->invalid_segmap = f2fs_kvzalloc(sbi, main_bitmap_size, GFP_KERNEL); if (!sit_i->invalid_segmap) return -ENOMEM; #endif sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr); sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg; sit_i->written_valid_blocks = 0; sit_i->bitmap_size = sit_bitmap_size; sit_i->dirty_sentries = 0; sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK; sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time); sit_i->mounted_time = ktime_get_boottime_seconds(); init_rwsem(&sit_i->sentry_lock); return 0; } static int build_free_segmap(struct f2fs_sb_info *sbi) { struct free_segmap_info *free_i; unsigned int bitmap_size, sec_bitmap_size; /* allocate memory for free segmap information */ free_i = f2fs_kzalloc(sbi, sizeof(struct free_segmap_info), GFP_KERNEL); if (!free_i) return -ENOMEM; SM_I(sbi)->free_info = free_i; bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); free_i->free_segmap = f2fs_kvmalloc(sbi, bitmap_size, GFP_KERNEL); if (!free_i->free_segmap) return -ENOMEM; sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); free_i->free_secmap = f2fs_kvmalloc(sbi, sec_bitmap_size, GFP_KERNEL); if (!free_i->free_secmap) return -ENOMEM; /* set all segments as dirty temporarily */ memset(free_i->free_segmap, 0xff, bitmap_size); memset(free_i->free_secmap, 0xff, sec_bitmap_size); /* init free segmap information */ free_i->start_segno = GET_SEGNO_FROM_SEG0(sbi, MAIN_BLKADDR(sbi)); free_i->free_segments = 0; free_i->free_sections = 0; spin_lock_init(&free_i->segmap_lock); return 0; } static int build_curseg(struct f2fs_sb_info *sbi) { struct curseg_info *array; int i; array = f2fs_kzalloc(sbi, array_size(NR_CURSEG_TYPE, sizeof(*array)), GFP_KERNEL); if (!array) return -ENOMEM; SM_I(sbi)->curseg_array = array; for (i = 0; i < NO_CHECK_TYPE; i++) { mutex_init(&array[i].curseg_mutex); array[i].sum_blk = f2fs_kzalloc(sbi, PAGE_SIZE, GFP_KERNEL); if (!array[i].sum_blk) return -ENOMEM; init_rwsem(&array[i].journal_rwsem); array[i].journal = f2fs_kzalloc(sbi, sizeof(struct f2fs_journal), GFP_KERNEL); if (!array[i].journal) return -ENOMEM; if (i < NR_PERSISTENT_LOG) array[i].seg_type = CURSEG_HOT_DATA + i; else if (i == CURSEG_COLD_DATA_PINNED) array[i].seg_type = CURSEG_COLD_DATA; else if (i == CURSEG_ALL_DATA_ATGC) array[i].seg_type = CURSEG_COLD_DATA; array[i].segno = NULL_SEGNO; array[i].next_blkoff = 0; array[i].inited = false; } return restore_curseg_summaries(sbi); } static int build_sit_entries(struct f2fs_sb_info *sbi) { struct sit_info *sit_i = SIT_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA); struct f2fs_journal *journal = curseg->journal; struct seg_entry *se; struct f2fs_sit_entry sit; int sit_blk_cnt = SIT_BLK_CNT(sbi); unsigned int i, start, end; unsigned int readed, start_blk = 0; int err = 0; block_t sit_valid_blocks[2] = {0, 0}; do { readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_VECS, META_SIT, true); start = start_blk * sit_i->sents_per_block; end = (start_blk + readed) * sit_i->sents_per_block; for (; start < end && start < MAIN_SEGS(sbi); start++) { struct f2fs_sit_block *sit_blk; struct page *page; se = &sit_i->sentries[start]; page = get_current_sit_page(sbi, start); if (IS_ERR(page)) return PTR_ERR(page); sit_blk = (struct f2fs_sit_block *)page_address(page); sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)]; f2fs_put_page(page, 1); err = check_block_count(sbi, start, &sit); if (err) return err; seg_info_from_raw_sit(se, &sit); if (se->type >= NR_PERSISTENT_LOG) { f2fs_err(sbi, "Invalid segment type: %u, segno: %u", se->type, start); f2fs_handle_error(sbi, ERROR_INCONSISTENT_SUM_TYPE); return -EFSCORRUPTED; } sit_valid_blocks[SE_PAGETYPE(se)] += se->valid_blocks; if (f2fs_block_unit_discard(sbi)) { /* build discard map only one time */ if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE); } else { memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE); sbi->discard_blks += sbi->blocks_per_seg - se->valid_blocks; } } if (__is_large_section(sbi)) get_sec_entry(sbi, start)->valid_blocks += se->valid_blocks; } start_blk += readed; } while (start_blk < sit_blk_cnt); down_read(&curseg->journal_rwsem); for (i = 0; i < sits_in_cursum(journal); i++) { unsigned int old_valid_blocks; start = le32_to_cpu(segno_in_journal(journal, i)); if (start >= MAIN_SEGS(sbi)) { f2fs_err(sbi, "Wrong journal entry on segno %u", start); err = -EFSCORRUPTED; f2fs_handle_error(sbi, ERROR_CORRUPTED_JOURNAL); break; } se = &sit_i->sentries[start]; sit = sit_in_journal(journal, i); old_valid_blocks = se->valid_blocks; sit_valid_blocks[SE_PAGETYPE(se)] -= old_valid_blocks; err = check_block_count(sbi, start, &sit); if (err) break; seg_info_from_raw_sit(se, &sit); if (se->type >= NR_PERSISTENT_LOG) { f2fs_err(sbi, "Invalid segment type: %u, segno: %u", se->type, start); err = -EFSCORRUPTED; f2fs_handle_error(sbi, ERROR_INCONSISTENT_SUM_TYPE); break; } sit_valid_blocks[SE_PAGETYPE(se)] += se->valid_blocks; if (f2fs_block_unit_discard(sbi)) { if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE); } else { memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE); sbi->discard_blks += old_valid_blocks; sbi->discard_blks -= se->valid_blocks; } } if (__is_large_section(sbi)) { get_sec_entry(sbi, start)->valid_blocks += se->valid_blocks; get_sec_entry(sbi, start)->valid_blocks -= old_valid_blocks; } } up_read(&curseg->journal_rwsem); if (err) return err; if (sit_valid_blocks[NODE] != valid_node_count(sbi)) { f2fs_err(sbi, "SIT is corrupted node# %u vs %u", sit_valid_blocks[NODE], valid_node_count(sbi)); f2fs_handle_error(sbi, ERROR_INCONSISTENT_NODE_COUNT); return -EFSCORRUPTED; } if (sit_valid_blocks[DATA] + sit_valid_blocks[NODE] > valid_user_blocks(sbi)) { f2fs_err(sbi, "SIT is corrupted data# %u %u vs %u", sit_valid_blocks[DATA], sit_valid_blocks[NODE], valid_user_blocks(sbi)); f2fs_handle_error(sbi, ERROR_INCONSISTENT_BLOCK_COUNT); return -EFSCORRUPTED; } return 0; } static void init_free_segmap(struct f2fs_sb_info *sbi) { unsigned int start; int type; struct seg_entry *sentry; for (start = 0; start < MAIN_SEGS(sbi); start++) { if (f2fs_usable_blks_in_seg(sbi, start) == 0) continue; sentry = get_seg_entry(sbi, start); if (!sentry->valid_blocks) __set_free(sbi, start); else SIT_I(sbi)->written_valid_blocks += sentry->valid_blocks; } /* set use the current segments */ for (type = CURSEG_HOT_DATA; type <= CURSEG_COLD_NODE; type++) { struct curseg_info *curseg_t = CURSEG_I(sbi, type); __set_test_and_inuse(sbi, curseg_t->segno); } } static void init_dirty_segmap(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); struct free_segmap_info *free_i = FREE_I(sbi); unsigned int segno = 0, offset = 0, secno; block_t valid_blocks, usable_blks_in_seg; while (1) { /* find dirty segment based on free segmap */ segno = find_next_inuse(free_i, MAIN_SEGS(sbi), offset); if (segno >= MAIN_SEGS(sbi)) break; offset = segno + 1; valid_blocks = get_valid_blocks(sbi, segno, false); usable_blks_in_seg = f2fs_usable_blks_in_seg(sbi, segno); if (valid_blocks == usable_blks_in_seg || !valid_blocks) continue; if (valid_blocks > usable_blks_in_seg) { f2fs_bug_on(sbi, 1); continue; } mutex_lock(&dirty_i->seglist_lock); __locate_dirty_segment(sbi, segno, DIRTY); mutex_unlock(&dirty_i->seglist_lock); } if (!__is_large_section(sbi)) return; mutex_lock(&dirty_i->seglist_lock); for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { valid_blocks = get_valid_blocks(sbi, segno, true); secno = GET_SEC_FROM_SEG(sbi, segno); if (!valid_blocks || valid_blocks == CAP_BLKS_PER_SEC(sbi)) continue; if (IS_CURSEC(sbi, secno)) continue; set_bit(secno, dirty_i->dirty_secmap); } mutex_unlock(&dirty_i->seglist_lock); } static int init_victim_secmap(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); dirty_i->victim_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); if (!dirty_i->victim_secmap) return -ENOMEM; dirty_i->pinned_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); if (!dirty_i->pinned_secmap) return -ENOMEM; dirty_i->pinned_secmap_cnt = 0; dirty_i->enable_pin_section = true; return 0; } static int build_dirty_segmap(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i; unsigned int bitmap_size, i; /* allocate memory for dirty segments list information */ dirty_i = f2fs_kzalloc(sbi, sizeof(struct dirty_seglist_info), GFP_KERNEL); if (!dirty_i) return -ENOMEM; SM_I(sbi)->dirty_info = dirty_i; mutex_init(&dirty_i->seglist_lock); bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); for (i = 0; i < NR_DIRTY_TYPE; i++) { dirty_i->dirty_segmap[i] = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); if (!dirty_i->dirty_segmap[i]) return -ENOMEM; } if (__is_large_section(sbi)) { bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); dirty_i->dirty_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); if (!dirty_i->dirty_secmap) return -ENOMEM; } init_dirty_segmap(sbi); return init_victim_secmap(sbi); } static int sanity_check_curseg(struct f2fs_sb_info *sbi) { int i; /* * In LFS/SSR curseg, .next_blkoff should point to an unused blkaddr; * In LFS curseg, all blkaddr after .next_blkoff should be unused. */ for (i = 0; i < NR_PERSISTENT_LOG; i++) { struct curseg_info *curseg = CURSEG_I(sbi, i); struct seg_entry *se = get_seg_entry(sbi, curseg->segno); unsigned int blkofs = curseg->next_blkoff; if (f2fs_sb_has_readonly(sbi) && i != CURSEG_HOT_DATA && i != CURSEG_HOT_NODE) continue; sanity_check_seg_type(sbi, curseg->seg_type); if (curseg->alloc_type != LFS && curseg->alloc_type != SSR) { f2fs_err(sbi, "Current segment has invalid alloc_type:%d", curseg->alloc_type); f2fs_handle_error(sbi, ERROR_INVALID_CURSEG); return -EFSCORRUPTED; } if (f2fs_test_bit(blkofs, se->cur_valid_map)) goto out; if (curseg->alloc_type == SSR) continue; for (blkofs += 1; blkofs < sbi->blocks_per_seg; blkofs++) { if (!f2fs_test_bit(blkofs, se->cur_valid_map)) continue; out: f2fs_err(sbi, "Current segment's next free block offset is inconsistent with bitmap, logtype:%u, segno:%u, type:%u, next_blkoff:%u, blkofs:%u", i, curseg->segno, curseg->alloc_type, curseg->next_blkoff, blkofs); f2fs_handle_error(sbi, ERROR_INVALID_CURSEG); return -EFSCORRUPTED; } } return 0; } #ifdef CONFIG_BLK_DEV_ZONED static int check_zone_write_pointer(struct f2fs_sb_info *sbi, struct f2fs_dev_info *fdev, struct blk_zone *zone) { unsigned int wp_segno, wp_blkoff, zone_secno, zone_segno, segno; block_t zone_block, wp_block, last_valid_block; unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT; int i, s, b, ret; struct seg_entry *se; if (zone->type != BLK_ZONE_TYPE_SEQWRITE_REQ) return 0; wp_block = fdev->start_blk + (zone->wp >> log_sectors_per_block); wp_segno = GET_SEGNO(sbi, wp_block); wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno); zone_block = fdev->start_blk + (zone->start >> log_sectors_per_block); zone_segno = GET_SEGNO(sbi, zone_block); zone_secno = GET_SEC_FROM_SEG(sbi, zone_segno); if (zone_segno >= MAIN_SEGS(sbi)) return 0; /* * Skip check of zones cursegs point to, since * fix_curseg_write_pointer() checks them. */ for (i = 0; i < NO_CHECK_TYPE; i++) if (zone_secno == GET_SEC_FROM_SEG(sbi, CURSEG_I(sbi, i)->segno)) return 0; /* * Get last valid block of the zone. */ last_valid_block = zone_block - 1; for (s = sbi->segs_per_sec - 1; s >= 0; s--) { segno = zone_segno + s; se = get_seg_entry(sbi, segno); for (b = sbi->blocks_per_seg - 1; b >= 0; b--) if (f2fs_test_bit(b, se->cur_valid_map)) { last_valid_block = START_BLOCK(sbi, segno) + b; break; } if (last_valid_block >= zone_block) break; } /* * When safely unmounted in the previous mount, we can trust write * pointers. Otherwise, finish zones. */ if (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { /* * The write pointer matches with the valid blocks or * already points to the end of the zone. */ if ((last_valid_block + 1 == wp_block) || (zone->wp == zone->start + zone->len)) return 0; } if (last_valid_block + 1 == zone_block) { if (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { /* * If there is no valid block in the zone and if write * pointer is not at zone start, reset the write * pointer. */ f2fs_notice(sbi, "Zone without valid block has non-zero write " "pointer. Reset the write pointer: wp[0x%x,0x%x]", wp_segno, wp_blkoff); } ret = __f2fs_issue_discard_zone(sbi, fdev->bdev, zone_block, zone->len >> log_sectors_per_block); if (ret) f2fs_err(sbi, "Discard zone failed: %s (errno=%d)", fdev->path, ret); return ret; } if (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { /* * If there are valid blocks and the write pointer doesn't match * with them, we need to report the inconsistency and fill * the zone till the end to close the zone. This inconsistency * does not cause write error because the zone will not be * selected for write operation until it get discarded. */ f2fs_notice(sbi, "Valid blocks are not aligned with write " "pointer: valid block[0x%x,0x%x] wp[0x%x,0x%x]", GET_SEGNO(sbi, last_valid_block), GET_BLKOFF_FROM_SEG0(sbi, last_valid_block), wp_segno, wp_blkoff); } ret = blkdev_zone_mgmt(fdev->bdev, REQ_OP_ZONE_FINISH, zone->start, zone->len, GFP_NOFS); if (ret == -EOPNOTSUPP) { ret = blkdev_issue_zeroout(fdev->bdev, zone->wp, zone->len - (zone->wp - zone->start), GFP_NOFS, 0); if (ret) f2fs_err(sbi, "Fill up zone failed: %s (errno=%d)", fdev->path, ret); } else if (ret) { f2fs_err(sbi, "Finishing zone failed: %s (errno=%d)", fdev->path, ret); } return ret; } static struct f2fs_dev_info *get_target_zoned_dev(struct f2fs_sb_info *sbi, block_t zone_blkaddr) { int i; for (i = 0; i < sbi->s_ndevs; i++) { if (!bdev_is_zoned(FDEV(i).bdev)) continue; if (sbi->s_ndevs == 1 || (FDEV(i).start_blk <= zone_blkaddr && zone_blkaddr <= FDEV(i).end_blk)) return &FDEV(i); } return NULL; } static int report_one_zone_cb(struct blk_zone *zone, unsigned int idx, void *data) { memcpy(data, zone, sizeof(struct blk_zone)); return 0; } static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type) { struct curseg_info *cs = CURSEG_I(sbi, type); struct f2fs_dev_info *zbd; struct blk_zone zone; unsigned int cs_section, wp_segno, wp_blkoff, wp_sector_off; block_t cs_zone_block, wp_block; unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT; sector_t zone_sector; int err; cs_section = GET_SEC_FROM_SEG(sbi, cs->segno); cs_zone_block = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, cs_section)); zbd = get_target_zoned_dev(sbi, cs_zone_block); if (!zbd) return 0; /* report zone for the sector the curseg points to */ zone_sector = (sector_t)(cs_zone_block - zbd->start_blk) << log_sectors_per_block; err = blkdev_report_zones(zbd->bdev, zone_sector, 1, report_one_zone_cb, &zone); if (err != 1) { f2fs_err(sbi, "Report zone failed: %s errno=(%d)", zbd->path, err); return err; } if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ) return 0; /* * When safely unmounted in the previous mount, we could use current * segments. Otherwise, allocate new sections. */ if (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { wp_block = zbd->start_blk + (zone.wp >> log_sectors_per_block); wp_segno = GET_SEGNO(sbi, wp_block); wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno); wp_sector_off = zone.wp & GENMASK(log_sectors_per_block - 1, 0); if (cs->segno == wp_segno && cs->next_blkoff == wp_blkoff && wp_sector_off == 0) return 0; f2fs_notice(sbi, "Unaligned curseg[%d] with write pointer: " "curseg[0x%x,0x%x] wp[0x%x,0x%x]", type, cs->segno, cs->next_blkoff, wp_segno, wp_blkoff); } else { f2fs_notice(sbi, "Not successfully unmounted in the previous " "mount"); } f2fs_notice(sbi, "Assign new section to curseg[%d]: " "curseg[0x%x,0x%x]", type, cs->segno, cs->next_blkoff); f2fs_allocate_new_section(sbi, type, true); /* check consistency of the zone curseg pointed to */ if (check_zone_write_pointer(sbi, zbd, &zone)) return -EIO; /* check newly assigned zone */ cs_section = GET_SEC_FROM_SEG(sbi, cs->segno); cs_zone_block = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, cs_section)); zbd = get_target_zoned_dev(sbi, cs_zone_block); if (!zbd) return 0; zone_sector = (sector_t)(cs_zone_block - zbd->start_blk) << log_sectors_per_block; err = blkdev_report_zones(zbd->bdev, zone_sector, 1, report_one_zone_cb, &zone); if (err != 1) { f2fs_err(sbi, "Report zone failed: %s errno=(%d)", zbd->path, err); return err; } if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ) return 0; if (zone.wp != zone.start) { f2fs_notice(sbi, "New zone for curseg[%d] is not yet discarded. " "Reset the zone: curseg[0x%x,0x%x]", type, cs->segno, cs->next_blkoff); err = __f2fs_issue_discard_zone(sbi, zbd->bdev, cs_zone_block, zone.len >> log_sectors_per_block); if (err) { f2fs_err(sbi, "Discard zone failed: %s (errno=%d)", zbd->path, err); return err; } } return 0; } int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi) { int i, ret; for (i = 0; i < NR_PERSISTENT_LOG; i++) { ret = fix_curseg_write_pointer(sbi, i); if (ret) return ret; } return 0; } struct check_zone_write_pointer_args { struct f2fs_sb_info *sbi; struct f2fs_dev_info *fdev; }; static int check_zone_write_pointer_cb(struct blk_zone *zone, unsigned int idx, void *data) { struct check_zone_write_pointer_args *args; args = (struct check_zone_write_pointer_args *)data; return check_zone_write_pointer(args->sbi, args->fdev, zone); } int f2fs_check_write_pointer(struct f2fs_sb_info *sbi) { int i, ret; struct check_zone_write_pointer_args args; for (i = 0; i < sbi->s_ndevs; i++) { if (!bdev_is_zoned(FDEV(i).bdev)) continue; args.sbi = sbi; args.fdev = &FDEV(i); ret = blkdev_report_zones(FDEV(i).bdev, 0, BLK_ALL_ZONES, check_zone_write_pointer_cb, &args); if (ret < 0) return ret; } return 0; } /* * Return the number of usable blocks in a segment. The number of blocks * returned is always equal to the number of blocks in a segment for * segments fully contained within a sequential zone capacity or a * conventional zone. For segments partially contained in a sequential * zone capacity, the number of usable blocks up to the zone capacity * is returned. 0 is returned in all other cases. */ static inline unsigned int f2fs_usable_zone_blks_in_seg( struct f2fs_sb_info *sbi, unsigned int segno) { block_t seg_start, sec_start_blkaddr, sec_cap_blkaddr; unsigned int secno; if (!sbi->unusable_blocks_per_sec) return sbi->blocks_per_seg; secno = GET_SEC_FROM_SEG(sbi, segno); seg_start = START_BLOCK(sbi, segno); sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno)); sec_cap_blkaddr = sec_start_blkaddr + CAP_BLKS_PER_SEC(sbi); /* * If segment starts before zone capacity and spans beyond * zone capacity, then usable blocks are from seg start to * zone capacity. If the segment starts after the zone capacity, * then there are no usable blocks. */ if (seg_start >= sec_cap_blkaddr) return 0; if (seg_start + sbi->blocks_per_seg > sec_cap_blkaddr) return sec_cap_blkaddr - seg_start; return sbi->blocks_per_seg; } #else int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi) { return 0; } int f2fs_check_write_pointer(struct f2fs_sb_info *sbi) { return 0; } static inline unsigned int f2fs_usable_zone_blks_in_seg(struct f2fs_sb_info *sbi, unsigned int segno) { return 0; } #endif unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi, unsigned int segno) { if (f2fs_sb_has_blkzoned(sbi)) return f2fs_usable_zone_blks_in_seg(sbi, segno); return sbi->blocks_per_seg; } unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi, unsigned int segno) { if (f2fs_sb_has_blkzoned(sbi)) return CAP_SEGS_PER_SEC(sbi); return sbi->segs_per_sec; } /* * Update min, max modified time for cost-benefit GC algorithm */ static void init_min_max_mtime(struct f2fs_sb_info *sbi) { struct sit_info *sit_i = SIT_I(sbi); unsigned int segno; down_write(&sit_i->sentry_lock); sit_i->min_mtime = ULLONG_MAX; for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { unsigned int i; unsigned long long mtime = 0; for (i = 0; i < sbi->segs_per_sec; i++) mtime += get_seg_entry(sbi, segno + i)->mtime; mtime = div_u64(mtime, sbi->segs_per_sec); if (sit_i->min_mtime > mtime) sit_i->min_mtime = mtime; } sit_i->max_mtime = get_mtime(sbi, false); sit_i->dirty_max_mtime = 0; up_write(&sit_i->sentry_lock); } int f2fs_build_segment_manager(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); struct f2fs_sm_info *sm_info; int err; sm_info = f2fs_kzalloc(sbi, sizeof(struct f2fs_sm_info), GFP_KERNEL); if (!sm_info) return -ENOMEM; /* init sm info */ sbi->sm_info = sm_info; sm_info->seg0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr); sm_info->main_blkaddr = le32_to_cpu(raw_super->main_blkaddr); sm_info->segment_count = le32_to_cpu(raw_super->segment_count); sm_info->reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count); sm_info->ovp_segments = le32_to_cpu(ckpt->overprov_segment_count); sm_info->main_segments = le32_to_cpu(raw_super->segment_count_main); sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr); sm_info->rec_prefree_segments = sm_info->main_segments * DEF_RECLAIM_PREFREE_SEGMENTS / 100; if (sm_info->rec_prefree_segments > DEF_MAX_RECLAIM_PREFREE_SEGMENTS) sm_info->rec_prefree_segments = DEF_MAX_RECLAIM_PREFREE_SEGMENTS; if (!f2fs_lfs_mode(sbi)) sm_info->ipu_policy = BIT(F2FS_IPU_FSYNC); sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS; sm_info->min_seq_blocks = sbi->blocks_per_seg; sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS; sm_info->min_ssr_sections = reserved_sections(sbi); INIT_LIST_HEAD(&sm_info->sit_entry_set); init_f2fs_rwsem(&sm_info->curseg_lock); err = f2fs_create_flush_cmd_control(sbi); if (err) return err; err = create_discard_cmd_control(sbi); if (err) return err; err = build_sit_info(sbi); if (err) return err; err = build_free_segmap(sbi); if (err) return err; err = build_curseg(sbi); if (err) return err; /* reinit free segmap based on SIT */ err = build_sit_entries(sbi); if (err) return err; init_free_segmap(sbi); err = build_dirty_segmap(sbi); if (err) return err; err = sanity_check_curseg(sbi); if (err) return err; init_min_max_mtime(sbi); return 0; } static void discard_dirty_segmap(struct f2fs_sb_info *sbi, enum dirty_type dirty_type) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); mutex_lock(&dirty_i->seglist_lock); kvfree(dirty_i->dirty_segmap[dirty_type]); dirty_i->nr_dirty[dirty_type] = 0; mutex_unlock(&dirty_i->seglist_lock); } static void destroy_victim_secmap(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); kvfree(dirty_i->pinned_secmap); kvfree(dirty_i->victim_secmap); } static void destroy_dirty_segmap(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); int i; if (!dirty_i) return; /* discard pre-free/dirty segments list */ for (i = 0; i < NR_DIRTY_TYPE; i++) discard_dirty_segmap(sbi, i); if (__is_large_section(sbi)) { mutex_lock(&dirty_i->seglist_lock); kvfree(dirty_i->dirty_secmap); mutex_unlock(&dirty_i->seglist_lock); } destroy_victim_secmap(sbi); SM_I(sbi)->dirty_info = NULL; kfree(dirty_i); } static void destroy_curseg(struct f2fs_sb_info *sbi) { struct curseg_info *array = SM_I(sbi)->curseg_array; int i; if (!array) return; SM_I(sbi)->curseg_array = NULL; for (i = 0; i < NR_CURSEG_TYPE; i++) { kfree(array[i].sum_blk); kfree(array[i].journal); } kfree(array); } static void destroy_free_segmap(struct f2fs_sb_info *sbi) { struct free_segmap_info *free_i = SM_I(sbi)->free_info; if (!free_i) return; SM_I(sbi)->free_info = NULL; kvfree(free_i->free_segmap); kvfree(free_i->free_secmap); kfree(free_i); } static void destroy_sit_info(struct f2fs_sb_info *sbi) { struct sit_info *sit_i = SIT_I(sbi); if (!sit_i) return; if (sit_i->sentries) kvfree(sit_i->bitmap); kfree(sit_i->tmp_map); kvfree(sit_i->sentries); kvfree(sit_i->sec_entries); kvfree(sit_i->dirty_sentries_bitmap); SM_I(sbi)->sit_info = NULL; kvfree(sit_i->sit_bitmap); #ifdef CONFIG_F2FS_CHECK_FS kvfree(sit_i->sit_bitmap_mir); kvfree(sit_i->invalid_segmap); #endif kfree(sit_i); } void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi) { struct f2fs_sm_info *sm_info = SM_I(sbi); if (!sm_info) return; f2fs_destroy_flush_cmd_control(sbi, true); destroy_discard_cmd_control(sbi); destroy_dirty_segmap(sbi); destroy_curseg(sbi); destroy_free_segmap(sbi); destroy_sit_info(sbi); sbi->sm_info = NULL; kfree(sm_info); } int __init f2fs_create_segment_manager_caches(void) { discard_entry_slab = f2fs_kmem_cache_create("f2fs_discard_entry", sizeof(struct discard_entry)); if (!discard_entry_slab) goto fail; discard_cmd_slab = f2fs_kmem_cache_create("f2fs_discard_cmd", sizeof(struct discard_cmd)); if (!discard_cmd_slab) goto destroy_discard_entry; sit_entry_set_slab = f2fs_kmem_cache_create("f2fs_sit_entry_set", sizeof(struct sit_entry_set)); if (!sit_entry_set_slab) goto destroy_discard_cmd; revoke_entry_slab = f2fs_kmem_cache_create("f2fs_revoke_entry", sizeof(struct revoke_entry)); if (!revoke_entry_slab) goto destroy_sit_entry_set; return 0; destroy_sit_entry_set: kmem_cache_destroy(sit_entry_set_slab); destroy_discard_cmd: kmem_cache_destroy(discard_cmd_slab); destroy_discard_entry: kmem_cache_destroy(discard_entry_slab); fail: return -ENOMEM; } void f2fs_destroy_segment_manager_caches(void) { kmem_cache_destroy(sit_entry_set_slab); kmem_cache_destroy(discard_cmd_slab); kmem_cache_destroy(discard_entry_slab); kmem_cache_destroy(revoke_entry_slab); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H /* * If more than 16 keys are ever supported, a thorough audit * will be necessary to ensure that the types that store key * numbers and masks have sufficient capacity. */ #define arch_max_pkey() (cpu_feature_enabled(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); static inline bool arch_pkeys_enabled(void) { return cpu_feature_enabled(X86_FEATURE_OSPKE); } /* * Try to dedicate one of the protection keys to be used as an * execute-only protection key. */ extern int __execute_only_pkey(struct mm_struct *mm); static inline int execute_only_pkey(struct mm_struct *mm) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return ARCH_DEFAULT_PKEY; return __execute_only_pkey(mm); } extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey); static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return 0; return __arch_override_mprotect_pkey(vma, prot, pkey); } #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3) #define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map) #define mm_set_pkey_allocated(mm, pkey) do { \ mm_pkey_allocation_map(mm) |= (1U << pkey); \ } while (0) #define mm_set_pkey_free(mm, pkey) do { \ mm_pkey_allocation_map(mm) &= ~(1U << pkey); \ } while (0) static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { /* * "Allocated" pkeys are those that have been returned * from pkey_alloc() or pkey 0 which is allocated * implicitly when the mm is created. */ if (pkey < 0) return false; if (pkey >= arch_max_pkey()) return false; /* * The exec-only pkey is set in the allocation map, but * is not available to any of the user interfaces like * mprotect_pkey(). */ if (pkey == mm->context.execute_only_pkey) return false; return mm_pkey_allocation_map(mm) & (1U << pkey); } /* * Returns a positive, 4-bit key on success, or -1 on failure. */ static inline int mm_pkey_alloc(struct mm_struct *mm) { /* * Note: this is the one and only place we make sure * that the pkey is valid as far as the hardware is * concerned. The rest of the kernel trusts that * only good, valid pkeys come out of here. */ u16 all_pkeys_mask = ((1U << arch_max_pkey()) - 1); int ret; /* * Are we out of pkeys? We must handle this specially * because ffz() behavior is undefined if there are no * zeros. */ if (mm_pkey_allocation_map(mm) == all_pkeys_mask) return -1; ret = ffz(mm_pkey_allocation_map(mm)); mm_set_pkey_allocated(mm, ret); return ret; } static inline int mm_pkey_free(struct mm_struct *mm, int pkey) { if (!mm_pkey_is_allocated(mm, pkey)) return -EINVAL; mm_set_pkey_free(mm, pkey); return 0; } static inline int vma_pkey(struct vm_area_struct *vma) { unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3; return (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT; } #endif /*_ASM_X86_PKEYS_H */ |
| 164 166 163 243 210 8 4 4 4 207 207 206 1 207 128 207 129 125 103 105 105 105 26 105 3 204 204 134 13 136 8 38 36 28 38 38 36 4 38 38 38 8 2 6 2 8 8 8 17 14 17 17 5 5 10 10 2 2 42 30 4 4 50 50 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 | // SPDX-License-Identifier: GPL-2.0-or-later /* * algif_hash: User-space interface for hash algorithms * * This file provides the user-space API for hash algorithms. * * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/hash.h> #include <crypto/if_alg.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/net.h> #include <net/sock.h> struct hash_ctx { struct af_alg_sgl sgl; u8 *result; struct crypto_wait wait; unsigned int len; bool more; struct ahash_request req; }; static int hash_alloc_result(struct sock *sk, struct hash_ctx *ctx) { unsigned ds; if (ctx->result) return 0; ds = crypto_ahash_digestsize(crypto_ahash_reqtfm(&ctx->req)); ctx->result = sock_kmalloc(sk, ds, GFP_KERNEL); if (!ctx->result) return -ENOMEM; memset(ctx->result, 0, ds); return 0; } static void hash_free_result(struct sock *sk, struct hash_ctx *ctx) { unsigned ds; if (!ctx->result) return; ds = crypto_ahash_digestsize(crypto_ahash_reqtfm(&ctx->req)); sock_kzfree_s(sk, ctx->result, ds); ctx->result = NULL; } static int hash_sendmsg(struct socket *sock, struct msghdr *msg, size_t ignored) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct hash_ctx *ctx = ask->private; ssize_t copied = 0; size_t len, max_pages, npages; bool continuing, need_init = false; int err; max_pages = min_t(size_t, ALG_MAX_PAGES, DIV_ROUND_UP(sk->sk_sndbuf, PAGE_SIZE)); lock_sock(sk); continuing = ctx->more; if (!continuing) { /* Discard a previous request that wasn't marked MSG_MORE. */ hash_free_result(sk, ctx); if (!msg_data_left(msg)) goto done; /* Zero-length; don't start new req */ need_init = true; } else if (!msg_data_left(msg)) { /* * No data - finalise the prev req if MSG_MORE so any error * comes out here. */ if (!(msg->msg_flags & MSG_MORE)) { err = hash_alloc_result(sk, ctx); if (err) goto unlock_free; ahash_request_set_crypt(&ctx->req, NULL, ctx->result, 0); err = crypto_wait_req(crypto_ahash_final(&ctx->req), &ctx->wait); if (err) goto unlock_free; } goto done_more; } while (msg_data_left(msg)) { ctx->sgl.sgt.sgl = ctx->sgl.sgl; ctx->sgl.sgt.nents = 0; ctx->sgl.sgt.orig_nents = 0; err = -EIO; npages = iov_iter_npages(&msg->msg_iter, max_pages); if (npages == 0) goto unlock_free; sg_init_table(ctx->sgl.sgl, npages); ctx->sgl.need_unpin = iov_iter_extract_will_pin(&msg->msg_iter); err = extract_iter_to_sg(&msg->msg_iter, LONG_MAX, &ctx->sgl.sgt, npages, 0); if (err < 0) goto unlock_free; len = err; sg_mark_end(ctx->sgl.sgt.sgl + ctx->sgl.sgt.nents - 1); if (!msg_data_left(msg)) { err = hash_alloc_result(sk, ctx); if (err) goto unlock_free; } ahash_request_set_crypt(&ctx->req, ctx->sgl.sgt.sgl, ctx->result, len); if (!msg_data_left(msg) && !continuing && !(msg->msg_flags & MSG_MORE)) { err = crypto_ahash_digest(&ctx->req); } else { if (need_init) { err = crypto_wait_req( crypto_ahash_init(&ctx->req), &ctx->wait); if (err) goto unlock_free; need_init = false; } if (msg_data_left(msg) || (msg->msg_flags & MSG_MORE)) err = crypto_ahash_update(&ctx->req); else err = crypto_ahash_finup(&ctx->req); continuing = true; } err = crypto_wait_req(err, &ctx->wait); if (err) goto unlock_free; copied += len; af_alg_free_sg(&ctx->sgl); } done_more: ctx->more = msg->msg_flags & MSG_MORE; done: err = 0; unlock: release_sock(sk); return copied ?: err; unlock_free: af_alg_free_sg(&ctx->sgl); hash_free_result(sk, ctx); ctx->more = false; goto unlock; } static int hash_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 hash_ctx *ctx = ask->private; unsigned ds = crypto_ahash_digestsize(crypto_ahash_reqtfm(&ctx->req)); bool result; int err; if (len > ds) len = ds; else if (len < ds) msg->msg_flags |= MSG_TRUNC; lock_sock(sk); result = ctx->result; err = hash_alloc_result(sk, ctx); if (err) goto unlock; ahash_request_set_crypt(&ctx->req, NULL, ctx->result, 0); if (!result && !ctx->more) { err = crypto_wait_req(crypto_ahash_init(&ctx->req), &ctx->wait); if (err) goto unlock; } if (!result || ctx->more) { ctx->more = false; err = crypto_wait_req(crypto_ahash_final(&ctx->req), &ctx->wait); if (err) goto unlock; } err = memcpy_to_msg(msg, ctx->result, len); unlock: hash_free_result(sk, ctx); release_sock(sk); return err ?: len; } static int hash_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct hash_ctx *ctx = ask->private; struct ahash_request *req = &ctx->req; struct crypto_ahash *tfm; struct sock *sk2; struct alg_sock *ask2; struct hash_ctx *ctx2; char *state; bool more; int err; tfm = crypto_ahash_reqtfm(req); state = kmalloc(crypto_ahash_statesize(tfm), GFP_KERNEL); err = -ENOMEM; if (!state) goto out; lock_sock(sk); more = ctx->more; err = more ? crypto_ahash_export(req, state) : 0; release_sock(sk); if (err) goto out_free_state; err = af_alg_accept(ask->parent, newsock, kern); if (err) goto out_free_state; sk2 = newsock->sk; ask2 = alg_sk(sk2); ctx2 = ask2->private; ctx2->more = more; if (!more) goto out_free_state; err = crypto_ahash_import(&ctx2->req, state); if (err) { sock_orphan(sk2); sock_put(sk2); } out_free_state: kfree_sensitive(state); out: return err; } static struct proto_ops algif_hash_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, .release = af_alg_release, .sendmsg = hash_sendmsg, .recvmsg = hash_recvmsg, .accept = hash_accept, }; static int hash_check_key(struct socket *sock) { int err = 0; struct sock *psk; struct alg_sock *pask; struct crypto_ahash *tfm; struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); lock_sock(sk); if (!atomic_read(&ask->nokey_refcnt)) goto unlock_child; psk = ask->parent; pask = alg_sk(ask->parent); tfm = pask->private; err = -ENOKEY; lock_sock_nested(psk, SINGLE_DEPTH_NESTING); if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) goto unlock; atomic_dec(&pask->nokey_refcnt); atomic_set(&ask->nokey_refcnt, 0); err = 0; unlock: release_sock(psk); unlock_child: release_sock(sk); return err; } static int hash_sendmsg_nokey(struct socket *sock, struct msghdr *msg, size_t size) { int err; err = hash_check_key(sock); if (err) return err; return hash_sendmsg(sock, msg, size); } static int hash_recvmsg_nokey(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { int err; err = hash_check_key(sock); if (err) return err; return hash_recvmsg(sock, msg, ignored, flags); } static int hash_accept_nokey(struct socket *sock, struct socket *newsock, int flags, bool kern) { int err; err = hash_check_key(sock); if (err) return err; return hash_accept(sock, newsock, flags, kern); } static struct proto_ops algif_hash_ops_nokey = { .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, .release = af_alg_release, .sendmsg = hash_sendmsg_nokey, .recvmsg = hash_recvmsg_nokey, .accept = hash_accept_nokey, }; static void *hash_bind(const char *name, u32 type, u32 mask) { return crypto_alloc_ahash(name, type, mask); } static void hash_release(void *private) { crypto_free_ahash(private); } static int hash_setkey(void *private, const u8 *key, unsigned int keylen) { return crypto_ahash_setkey(private, key, keylen); } static void hash_sock_destruct(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct hash_ctx *ctx = ask->private; hash_free_result(sk, ctx); sock_kfree_s(sk, ctx, ctx->len); af_alg_release_parent(sk); } static int hash_accept_parent_nokey(void *private, struct sock *sk) { struct crypto_ahash *tfm = private; struct alg_sock *ask = alg_sk(sk); struct hash_ctx *ctx; unsigned int len = sizeof(*ctx) + crypto_ahash_reqsize(tfm); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->result = NULL; ctx->len = len; ctx->more = false; crypto_init_wait(&ctx->wait); ask->private = ctx; ahash_request_set_tfm(&ctx->req, tfm); ahash_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &ctx->wait); sk->sk_destruct = hash_sock_destruct; return 0; } static int hash_accept_parent(void *private, struct sock *sk) { struct crypto_ahash *tfm = private; if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return hash_accept_parent_nokey(private, sk); } static const struct af_alg_type algif_type_hash = { .bind = hash_bind, .release = hash_release, .setkey = hash_setkey, .accept = hash_accept_parent, .accept_nokey = hash_accept_parent_nokey, .ops = &algif_hash_ops, .ops_nokey = &algif_hash_ops_nokey, .name = "hash", .owner = THIS_MODULE }; static int __init algif_hash_init(void) { return af_alg_register_type(&algif_type_hash); } static void __exit algif_hash_exit(void) { int err = af_alg_unregister_type(&algif_type_hash); BUG_ON(err); } module_init(algif_hash_init); module_exit(algif_hash_exit); MODULE_LICENSE("GPL"); |
| 1606 1606 902 352 346 345 345 352 55 55 66 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 | // SPDX-License-Identifier: GPL-2.0 /* * Disk events - monitor disk events like media change and eject request. */ #include <linux/export.h> #include <linux/moduleparam.h> #include <linux/blkdev.h> #include "blk.h" struct disk_events { struct list_head node; /* all disk_event's */ struct gendisk *disk; /* the associated disk */ spinlock_t lock; struct mutex block_mutex; /* protects blocking */ int block; /* event blocking depth */ unsigned int pending; /* events already sent out */ unsigned int clearing; /* events being cleared */ long poll_msecs; /* interval, -1 for default */ struct delayed_work dwork; }; static const char *disk_events_strs[] = { [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "media_change", [ilog2(DISK_EVENT_EJECT_REQUEST)] = "eject_request", }; static char *disk_uevents[] = { [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "DISK_MEDIA_CHANGE=1", [ilog2(DISK_EVENT_EJECT_REQUEST)] = "DISK_EJECT_REQUEST=1", }; /* list of all disk_events */ static DEFINE_MUTEX(disk_events_mutex); static LIST_HEAD(disk_events); /* disable in-kernel polling by default */ static unsigned long disk_events_dfl_poll_msecs; static unsigned long disk_events_poll_jiffies(struct gendisk *disk) { struct disk_events *ev = disk->ev; long intv_msecs = 0; /* * If device-specific poll interval is set, always use it. If * the default is being used, poll if the POLL flag is set. */ if (ev->poll_msecs >= 0) intv_msecs = ev->poll_msecs; else if (disk->event_flags & DISK_EVENT_FLAG_POLL) intv_msecs = disk_events_dfl_poll_msecs; return msecs_to_jiffies(intv_msecs); } /** * disk_block_events - block and flush disk event checking * @disk: disk to block events for * * On return from this function, it is guaranteed that event checking * isn't in progress and won't happen until unblocked by * disk_unblock_events(). Events blocking is counted and the actual * unblocking happens after the matching number of unblocks are done. * * Note that this intentionally does not block event checking from * disk_clear_events(). * * CONTEXT: * Might sleep. */ void disk_block_events(struct gendisk *disk) { struct disk_events *ev = disk->ev; unsigned long flags; bool cancel; if (!ev) return; /* * Outer mutex ensures that the first blocker completes canceling * the event work before further blockers are allowed to finish. */ mutex_lock(&ev->block_mutex); spin_lock_irqsave(&ev->lock, flags); cancel = !ev->block++; spin_unlock_irqrestore(&ev->lock, flags); if (cancel) cancel_delayed_work_sync(&disk->ev->dwork); mutex_unlock(&ev->block_mutex); } static void __disk_unblock_events(struct gendisk *disk, bool check_now) { struct disk_events *ev = disk->ev; unsigned long intv; unsigned long flags; spin_lock_irqsave(&ev->lock, flags); if (WARN_ON_ONCE(ev->block <= 0)) goto out_unlock; if (--ev->block) goto out_unlock; intv = disk_events_poll_jiffies(disk); if (check_now) queue_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, 0); else if (intv) queue_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, intv); out_unlock: spin_unlock_irqrestore(&ev->lock, flags); } /** * disk_unblock_events - unblock disk event checking * @disk: disk to unblock events for * * Undo disk_block_events(). When the block count reaches zero, it * starts events polling if configured. * * CONTEXT: * Don't care. Safe to call from irq context. */ void disk_unblock_events(struct gendisk *disk) { if (disk->ev) __disk_unblock_events(disk, false); } /** * disk_flush_events - schedule immediate event checking and flushing * @disk: disk to check and flush events for * @mask: events to flush * * Schedule immediate event checking on @disk if not blocked. Events in * @mask are scheduled to be cleared from the driver. Note that this * doesn't clear the events from @disk->ev. * * CONTEXT: * If @mask is non-zero must be called with disk->open_mutex held. */ void disk_flush_events(struct gendisk *disk, unsigned int mask) { struct disk_events *ev = disk->ev; if (!ev) return; spin_lock_irq(&ev->lock); ev->clearing |= mask; if (!ev->block) mod_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, 0); spin_unlock_irq(&ev->lock); } /* * Tell userland about new events. Only the events listed in @disk->events are * reported, and only if DISK_EVENT_FLAG_UEVENT is set. Otherwise, events are * processed internally but never get reported to userland. */ static void disk_event_uevent(struct gendisk *disk, unsigned int events) { char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; int nr_events = 0, i; for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) if (events & disk->events & (1 << i)) envp[nr_events++] = disk_uevents[i]; if (nr_events) kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); } static void disk_check_events(struct disk_events *ev, unsigned int *clearing_ptr) { struct gendisk *disk = ev->disk; unsigned int clearing = *clearing_ptr; unsigned int events; unsigned long intv; /* check events */ events = disk->fops->check_events(disk, clearing); /* accumulate pending events and schedule next poll if necessary */ spin_lock_irq(&ev->lock); events &= ~ev->pending; ev->pending |= events; *clearing_ptr &= ~clearing; intv = disk_events_poll_jiffies(disk); if (!ev->block && intv) queue_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, intv); spin_unlock_irq(&ev->lock); if (events & DISK_EVENT_MEDIA_CHANGE) inc_diskseq(disk); if (disk->event_flags & DISK_EVENT_FLAG_UEVENT) disk_event_uevent(disk, events); } /** * disk_clear_events - synchronously check, clear and return pending events * @disk: disk to fetch and clear events from * @mask: mask of events to be fetched and cleared * * Disk events are synchronously checked and pending events in @mask * are cleared and returned. This ignores the block count. * * CONTEXT: * Might sleep. */ static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) { struct disk_events *ev = disk->ev; unsigned int pending; unsigned int clearing = mask; if (!ev) return 0; disk_block_events(disk); /* * store the union of mask and ev->clearing on the stack so that the * race with disk_flush_events does not cause ambiguity (ev->clearing * can still be modified even if events are blocked). */ spin_lock_irq(&ev->lock); clearing |= ev->clearing; ev->clearing = 0; spin_unlock_irq(&ev->lock); disk_check_events(ev, &clearing); /* * if ev->clearing is not 0, the disk_flush_events got called in the * middle of this function, so we want to run the workfn without delay. */ __disk_unblock_events(disk, ev->clearing ? true : false); /* then, fetch and clear pending events */ spin_lock_irq(&ev->lock); pending = ev->pending & mask; ev->pending &= ~mask; spin_unlock_irq(&ev->lock); WARN_ON_ONCE(clearing & mask); return pending; } /** * disk_check_media_change - check if a removable media has been changed * @disk: gendisk to check * * Returns %true and marks the disk for a partition rescan whether a removable * media has been changed, and %false if the media did not change. */ bool disk_check_media_change(struct gendisk *disk) { unsigned int events; events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST); if (events & DISK_EVENT_MEDIA_CHANGE) { set_bit(GD_NEED_PART_SCAN, &disk->state); return true; } return false; } EXPORT_SYMBOL(disk_check_media_change); /** * disk_force_media_change - force a media change event * @disk: the disk which will raise the event * * Should be called when the media changes for @disk. Generates a uevent * and attempts to free all dentries and inodes and invalidates all block * device page cache entries in that case. */ void disk_force_media_change(struct gendisk *disk) { disk_event_uevent(disk, DISK_EVENT_MEDIA_CHANGE); inc_diskseq(disk); bdev_mark_dead(disk->part0, true); set_bit(GD_NEED_PART_SCAN, &disk->state); } EXPORT_SYMBOL_GPL(disk_force_media_change); /* * Separate this part out so that a different pointer for clearing_ptr can be * passed in for disk_clear_events. */ static void disk_events_workfn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct disk_events *ev = container_of(dwork, struct disk_events, dwork); disk_check_events(ev, &ev->clearing); } /* * A disk events enabled device has the following sysfs nodes under * its /sys/block/X/ directory. * * events : list of all supported events * events_async : list of events which can be detected w/o polling * (always empty, only for backwards compatibility) * events_poll_msecs : polling interval, 0: disable, -1: system default */ static ssize_t __disk_events_show(unsigned int events, char *buf) { const char *delim = ""; ssize_t pos = 0; int i; for (i = 0; i < ARRAY_SIZE(disk_events_strs); i++) if (events & (1 << i)) { pos += sprintf(buf + pos, "%s%s", delim, disk_events_strs[i]); delim = " "; } if (pos) pos += sprintf(buf + pos, "\n"); return pos; } static ssize_t disk_events_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); if (!(disk->event_flags & DISK_EVENT_FLAG_UEVENT)) return 0; return __disk_events_show(disk->events, buf); } static ssize_t disk_events_async_show(struct device *dev, struct device_attribute *attr, char *buf) { return 0; } static ssize_t disk_events_poll_msecs_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); if (!disk->ev) return sprintf(buf, "-1\n"); return sprintf(buf, "%ld\n", disk->ev->poll_msecs); } static ssize_t disk_events_poll_msecs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct gendisk *disk = dev_to_disk(dev); long intv; if (!count || !sscanf(buf, "%ld", &intv)) return -EINVAL; if (intv < 0 && intv != -1) return -EINVAL; if (!disk->ev) return -ENODEV; disk_block_events(disk); disk->ev->poll_msecs = intv; __disk_unblock_events(disk, true); return count; } DEVICE_ATTR(events, 0444, disk_events_show, NULL); DEVICE_ATTR(events_async, 0444, disk_events_async_show, NULL); DEVICE_ATTR(events_poll_msecs, 0644, disk_events_poll_msecs_show, disk_events_poll_msecs_store); /* * The default polling interval can be specified by the kernel * parameter block.events_dfl_poll_msecs which defaults to 0 * (disable). This can also be modified runtime by writing to * /sys/module/block/parameters/events_dfl_poll_msecs. */ static int disk_events_set_dfl_poll_msecs(const char *val, const struct kernel_param *kp) { struct disk_events *ev; int ret; ret = param_set_ulong(val, kp); if (ret < 0) return ret; mutex_lock(&disk_events_mutex); list_for_each_entry(ev, &disk_events, node) disk_flush_events(ev->disk, 0); mutex_unlock(&disk_events_mutex); return 0; } static const struct kernel_param_ops disk_events_dfl_poll_msecs_param_ops = { .set = disk_events_set_dfl_poll_msecs, .get = param_get_ulong, }; #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "block." module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops, &disk_events_dfl_poll_msecs, 0644); /* * disk_{alloc|add|del|release}_events - initialize and destroy disk_events. */ int disk_alloc_events(struct gendisk *disk) { struct disk_events *ev; if (!disk->fops->check_events || !disk->events) return 0; ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) { pr_warn("%s: failed to initialize events\n", disk->disk_name); return -ENOMEM; } INIT_LIST_HEAD(&ev->node); ev->disk = disk; spin_lock_init(&ev->lock); mutex_init(&ev->block_mutex); ev->block = 1; ev->poll_msecs = -1; INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); disk->ev = ev; return 0; } void disk_add_events(struct gendisk *disk) { if (!disk->ev) return; mutex_lock(&disk_events_mutex); list_add_tail(&disk->ev->node, &disk_events); mutex_unlock(&disk_events_mutex); /* * Block count is initialized to 1 and the following initial * unblock kicks it into action. */ __disk_unblock_events(disk, true); } void disk_del_events(struct gendisk *disk) { if (disk->ev) { disk_block_events(disk); mutex_lock(&disk_events_mutex); list_del_init(&disk->ev->node); mutex_unlock(&disk_events_mutex); } } void disk_release_events(struct gendisk *disk) { /* the block count should be 1 from disk_del_events() */ WARN_ON_ONCE(disk->ev && disk->ev->block != 1); kfree(disk->ev); } |
| 16 15 16 15 16 15 16 15 16 16 16 16 43 35 35 35 35 35 35 35 26 26 32 32 32 26 26 26 26 26 26 26 26 20 3 20 35 43 19 15 19 15 19 15 19 15 19 18 3 19 3 45 45 45 4 3 3 3 26 45 26 26 26 26 26 26 20 20 20 20 20 20 45 45 45 62 62 62 62 62 51 38 62 62 62 68 68 68 68 68 68 68 26 68 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dccp/options.c * * An implementation of the DCCP protocol * Copyright (c) 2005 Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org> * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net> * Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz> */ #include <linux/dccp.h> #include <linux/module.h> #include <linux/types.h> #include <asm/unaligned.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include "ackvec.h" #include "ccid.h" #include "dccp.h" #include "feat.h" u64 dccp_decode_value_var(const u8 *bf, const u8 len) { u64 value = 0; if (len >= DCCP_OPTVAL_MAXLEN) value += ((u64)*bf++) << 40; if (len > 4) value += ((u64)*bf++) << 32; if (len > 3) value += ((u64)*bf++) << 24; if (len > 2) value += ((u64)*bf++) << 16; if (len > 1) value += ((u64)*bf++) << 8; if (len > 0) value += *bf; return value; } /** * dccp_parse_options - Parse DCCP options present in @skb * @sk: client|server|listening dccp socket (when @dreq != NULL) * @dreq: request socket to use during connection setup, or NULL * @skb: frame to parse */ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); const struct dccp_hdr *dh = dccp_hdr(skb); const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type; unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb); unsigned char *opt_ptr = options; const unsigned char *opt_end = (unsigned char *)dh + (dh->dccph_doff * 4); struct dccp_options_received *opt_recv = &dp->dccps_options_received; unsigned char opt, len; unsigned char *value; u32 elapsed_time; __be32 opt_val; int rc; int mandatory = 0; memset(opt_recv, 0, sizeof(*opt_recv)); opt = len = 0; while (opt_ptr != opt_end) { opt = *opt_ptr++; len = 0; value = NULL; /* Check if this isn't a single byte option */ if (opt > DCCPO_MAX_RESERVED) { if (opt_ptr == opt_end) goto out_nonsensical_length; len = *opt_ptr++; if (len < 2) goto out_nonsensical_length; /* * Remove the type and len fields, leaving * just the value size */ len -= 2; value = opt_ptr; opt_ptr += len; if (opt_ptr > opt_end) goto out_nonsensical_length; } /* * CCID-specific options are ignored during connection setup, as * negotiation may still be in progress (see RFC 4340, 10.3). * The same applies to Ack Vectors, as these depend on the CCID. */ if (dreq != NULL && (opt >= DCCPO_MIN_RX_CCID_SPECIFIC || opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1)) goto ignore_option; switch (opt) { case DCCPO_PADDING: break; case DCCPO_MANDATORY: if (mandatory) goto out_invalid_option; if (pkt_type != DCCP_PKT_DATA) mandatory = 1; break; case DCCPO_NDP_COUNT: if (len > 6) goto out_invalid_option; opt_recv->dccpor_ndp = dccp_decode_value_var(value, len); dccp_pr_debug("%s opt: NDP count=%llu\n", dccp_role(sk), (unsigned long long)opt_recv->dccpor_ndp); break; case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R: if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */ break; if (len == 0) goto out_invalid_option; rc = dccp_feat_parse_options(sk, dreq, mandatory, opt, *value, value + 1, len - 1); if (rc) goto out_featneg_failed; break; case DCCPO_TIMESTAMP: if (len != 4) goto out_invalid_option; /* * RFC 4340 13.1: "The precise time corresponding to * Timestamp Value zero is not specified". We use * zero to indicate absence of a meaningful timestamp. */ opt_val = get_unaligned((__be32 *)value); if (unlikely(opt_val == 0)) { DCCP_WARN("Timestamp with zero value\n"); break; } if (dreq != NULL) { dreq->dreq_timestamp_echo = ntohl(opt_val); dreq->dreq_timestamp_time = dccp_timestamp(); } else { opt_recv->dccpor_timestamp = dp->dccps_timestamp_echo = ntohl(opt_val); dp->dccps_timestamp_time = dccp_timestamp(); } dccp_pr_debug("%s rx opt: TIMESTAMP=%u, ackno=%llu\n", dccp_role(sk), ntohl(opt_val), (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq); /* schedule an Ack in case this sender is quiescent */ inet_csk_schedule_ack(sk); break; case DCCPO_TIMESTAMP_ECHO: if (len != 4 && len != 6 && len != 8) goto out_invalid_option; opt_val = get_unaligned((__be32 *)value); opt_recv->dccpor_timestamp_echo = ntohl(opt_val); dccp_pr_debug("%s rx opt: TIMESTAMP_ECHO=%u, len=%d, " "ackno=%llu", dccp_role(sk), opt_recv->dccpor_timestamp_echo, len + 2, (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq); value += 4; if (len == 4) { /* no elapsed time included */ dccp_pr_debug_cat("\n"); break; } if (len == 6) { /* 2-byte elapsed time */ __be16 opt_val2 = get_unaligned((__be16 *)value); elapsed_time = ntohs(opt_val2); } else { /* 4-byte elapsed time */ opt_val = get_unaligned((__be32 *)value); elapsed_time = ntohl(opt_val); } dccp_pr_debug_cat(", ELAPSED_TIME=%u\n", elapsed_time); /* Give precedence to the biggest ELAPSED_TIME */ if (elapsed_time > opt_recv->dccpor_elapsed_time) opt_recv->dccpor_elapsed_time = elapsed_time; break; case DCCPO_ELAPSED_TIME: if (dccp_packet_without_ack(skb)) /* RFC 4340, 13.2 */ break; if (len == 2) { __be16 opt_val2 = get_unaligned((__be16 *)value); elapsed_time = ntohs(opt_val2); } else if (len == 4) { opt_val = get_unaligned((__be32 *)value); elapsed_time = ntohl(opt_val); } else { goto out_invalid_option; } if (elapsed_time > opt_recv->dccpor_elapsed_time) opt_recv->dccpor_elapsed_time = elapsed_time; dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n", dccp_role(sk), elapsed_time); break; case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC: if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk, pkt_type, opt, value, len)) goto out_invalid_option; break; case DCCPO_ACK_VECTOR_0: case DCCPO_ACK_VECTOR_1: if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */ break; /* * Ack vectors are processed by the TX CCID if it is * interested. The RX CCID need not parse Ack Vectors, * since it is only interested in clearing old state. */ fallthrough; case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, pkt_type, opt, value, len)) goto out_invalid_option; break; default: DCCP_CRIT("DCCP(%p): option %d(len=%d) not " "implemented, ignoring", sk, opt, len); break; } ignore_option: if (opt != DCCPO_MANDATORY) mandatory = 0; } /* mandatory was the last byte in option list -> reset connection */ if (mandatory) goto out_invalid_option; out_nonsensical_length: /* RFC 4340, 5.8: ignore option and all remaining option space */ return 0; out_invalid_option: DCCP_INC_STATS(DCCP_MIB_INVALIDOPT); rc = DCCP_RESET_CODE_OPTION_ERROR; out_featneg_failed: DCCP_WARN("DCCP(%p): Option %d (len=%d) error=%u\n", sk, opt, len, rc); DCCP_SKB_CB(skb)->dccpd_reset_code = rc; DCCP_SKB_CB(skb)->dccpd_reset_data[0] = opt; DCCP_SKB_CB(skb)->dccpd_reset_data[1] = len > 0 ? value[0] : 0; DCCP_SKB_CB(skb)->dccpd_reset_data[2] = len > 1 ? value[1] : 0; return -1; } EXPORT_SYMBOL_GPL(dccp_parse_options); void dccp_encode_value_var(const u64 value, u8 *to, const u8 len) { if (len >= DCCP_OPTVAL_MAXLEN) *to++ = (value & 0xFF0000000000ull) >> 40; if (len > 4) *to++ = (value & 0xFF00000000ull) >> 32; if (len > 3) *to++ = (value & 0xFF000000) >> 24; if (len > 2) *to++ = (value & 0xFF0000) >> 16; if (len > 1) *to++ = (value & 0xFF00) >> 8; if (len > 0) *to++ = (value & 0xFF); } static inline u8 dccp_ndp_len(const u64 ndp) { if (likely(ndp <= 0xFF)) return 1; return likely(ndp <= USHRT_MAX) ? 2 : (ndp <= UINT_MAX ? 4 : 6); } int dccp_insert_option(struct sk_buff *skb, const unsigned char option, const void *value, const unsigned char len) { unsigned char *to; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 2 > DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len + 2; to = skb_push(skb, len + 2); *to++ = option; *to++ = len + 2; memcpy(to, value, len); return 0; } EXPORT_SYMBOL_GPL(dccp_insert_option); static int dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); u64 ndp = dp->dccps_ndp_count; if (dccp_non_data_packet(skb)) ++dp->dccps_ndp_count; else dp->dccps_ndp_count = 0; if (ndp > 0) { unsigned char *ptr; const int ndp_len = dccp_ndp_len(ndp); const int len = ndp_len + 2; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; ptr = skb_push(skb, len); *ptr++ = DCCPO_NDP_COUNT; *ptr++ = len; dccp_encode_value_var(ndp, ptr, ndp_len); } return 0; } static inline int dccp_elapsed_time_len(const u32 elapsed_time) { return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4; } static int dccp_insert_option_timestamp(struct sk_buff *skb) { __be32 now = htonl(dccp_timestamp()); /* yes this will overflow but that is the point as we want a * 10 usec 32 bit timer which mean it wraps every 11.9 hours */ return dccp_insert_option(skb, DCCPO_TIMESTAMP, &now, sizeof(now)); } static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp, struct dccp_request_sock *dreq, struct sk_buff *skb) { __be32 tstamp_echo; unsigned char *to; u32 elapsed_time, elapsed_time_len, len; if (dreq != NULL) { elapsed_time = dccp_timestamp() - dreq->dreq_timestamp_time; tstamp_echo = htonl(dreq->dreq_timestamp_echo); dreq->dreq_timestamp_echo = 0; } else { elapsed_time = dccp_timestamp() - dp->dccps_timestamp_time; tstamp_echo = htonl(dp->dccps_timestamp_echo); dp->dccps_timestamp_echo = 0; } elapsed_time_len = dccp_elapsed_time_len(elapsed_time); len = 6 + elapsed_time_len; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; to = skb_push(skb, len); *to++ = DCCPO_TIMESTAMP_ECHO; *to++ = len; memcpy(to, &tstamp_echo, 4); to += 4; if (elapsed_time_len == 2) { const __be16 var16 = htons((u16)elapsed_time); memcpy(to, &var16, 2); } else if (elapsed_time_len == 4) { const __be32 var32 = htonl(elapsed_time); memcpy(to, &var32, 4); } return 0; } static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); const u16 buflen = dccp_ackvec_buflen(av); /* Figure out how many options do we need to represent the ackvec */ const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN); u16 len = buflen + 2 * nr_opts; u8 i, nonce = 0; const unsigned char *tail, *from; unsigned char *to; if (dcb->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) { DCCP_WARN("Lacking space for %u bytes on %s packet\n", len, dccp_packet_name(dcb->dccpd_type)); return -1; } /* * Since Ack Vectors are variable-length, we can not always predict * their size. To catch exception cases where the space is running out * on the skb, a separate Sync is scheduled to carry the Ack Vector. */ if (len > DCCPAV_MIN_OPTLEN && len + dcb->dccpd_opt_len + skb->len > dp->dccps_mss_cache) { DCCP_WARN("No space left for Ack Vector (%u) on skb (%u+%u), " "MPS=%u ==> reduce payload size?\n", len, skb->len, dcb->dccpd_opt_len, dp->dccps_mss_cache); dp->dccps_sync_scheduled = 1; return 0; } dcb->dccpd_opt_len += len; to = skb_push(skb, len); len = buflen; from = av->av_buf + av->av_buf_head; tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; for (i = 0; i < nr_opts; ++i) { int copylen = len; if (len > DCCP_SINGLE_OPT_MAXLEN) copylen = DCCP_SINGLE_OPT_MAXLEN; /* * RFC 4340, 12.2: Encode the Nonce Echo for this Ack Vector via * its type; ack_nonce is the sum of all individual buf_nonce's. */ nonce ^= av->av_buf_nonce[i]; *to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i]; *to++ = copylen + 2; /* Check if buf_head wraps */ if (from + copylen > tail) { const u16 tailsize = tail - from; memcpy(to, from, tailsize); to += tailsize; len -= tailsize; copylen -= tailsize; from = av->av_buf; } memcpy(to, from, copylen); from += copylen; to += copylen; len -= copylen; } /* * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340. */ if (dccp_ackvec_update_records(av, dcb->dccpd_seq, nonce)) return -ENOBUFS; return 0; } /** * dccp_insert_option_mandatory - Mandatory option (5.8.2) * @skb: frame into which to insert option * * Note that since we are using skb_push, this function needs to be called * _after_ inserting the option it is supposed to influence (stack order). */ int dccp_insert_option_mandatory(struct sk_buff *skb) { if (DCCP_SKB_CB(skb)->dccpd_opt_len >= DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len++; *(u8 *)skb_push(skb, 1) = DCCPO_MANDATORY; return 0; } /** * dccp_insert_fn_opt - Insert single Feature-Negotiation option into @skb * @skb: frame to insert feature negotiation option into * @type: %DCCPO_CHANGE_L, %DCCPO_CHANGE_R, %DCCPO_CONFIRM_L, %DCCPO_CONFIRM_R * @feat: one out of %dccp_feature_numbers * @val: NN value or SP array (preferred element first) to copy * @len: true length of @val in bytes (excluding first element repetition) * @repeat_first: whether to copy the first element of @val twice * * The last argument is used to construct Confirm options, where the preferred * value and the preference list appear separately (RFC 4340, 6.3.1). Preference * lists are kept such that the preferred entry is always first, so we only need * to copy twice, and avoid the overhead of cloning into a bigger array. */ int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat, u8 *val, u8 len, bool repeat_first) { u8 tot_len, *to; /* take the `Feature' field and possible repetition into account */ if (len > (DCCP_SINGLE_OPT_MAXLEN - 2)) { DCCP_WARN("length %u for feature %u too large\n", len, feat); return -1; } if (unlikely(val == NULL || len == 0)) len = repeat_first = false; tot_len = 3 + repeat_first + len; if (DCCP_SKB_CB(skb)->dccpd_opt_len + tot_len > DCCP_MAX_OPT_LEN) { DCCP_WARN("packet too small for feature %d option!\n", feat); return -1; } DCCP_SKB_CB(skb)->dccpd_opt_len += tot_len; to = skb_push(skb, tot_len); *to++ = type; *to++ = tot_len; *to++ = feat; if (repeat_first) *to++ = *val; if (len) memcpy(to, val, len); return 0; } /* The length of all options needs to be a multiple of 4 (5.8) */ static void dccp_insert_option_padding(struct sk_buff *skb) { int padding = DCCP_SKB_CB(skb)->dccpd_opt_len % 4; if (padding != 0) { padding = 4 - padding; memset(skb_push(skb, padding), 0, padding); DCCP_SKB_CB(skb)->dccpd_opt_len += padding; } } int dccp_insert_options(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); DCCP_SKB_CB(skb)->dccpd_opt_len = 0; if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb)) return -1; if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) { /* Feature Negotiation */ if (dccp_feat_insert_opts(dp, NULL, skb)) return -1; if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST) { /* * Obtain RTT sample from Request/Response exchange. * This is currently used for TFRC initialisation. */ if (dccp_insert_option_timestamp(skb)) return -1; } else if (dccp_ackvec_pending(sk) && dccp_insert_option_ackvec(sk, skb)) { return -1; } } if (dp->dccps_hc_rx_insert_options) { if (ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb)) return -1; dp->dccps_hc_rx_insert_options = 0; } if (dp->dccps_timestamp_echo != 0 && dccp_insert_option_timestamp_echo(dp, NULL, skb)) return -1; dccp_insert_option_padding(skb); return 0; } int dccp_insert_options_rsk(struct dccp_request_sock *dreq, struct sk_buff *skb) { DCCP_SKB_CB(skb)->dccpd_opt_len = 0; if (dccp_feat_insert_opts(NULL, dreq, skb)) return -1; /* Obtain RTT sample from Response/Ack exchange (used by TFRC). */ if (dccp_insert_option_timestamp(skb)) return -1; if (dreq->dreq_timestamp_echo != 0 && dccp_insert_option_timestamp_echo(NULL, dreq, skb)) return -1; dccp_insert_option_padding(skb); return 0; } |
| 6 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_KSM_H #define __LINUX_KSM_H /* * Memory merging support. * * This code enables dynamic sharing of identical pages found in different * memory areas, even if they are not shared by fork(). */ #include <linux/bitops.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/sched.h> #include <linux/sched/coredump.h> #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); void ksm_add_vma(struct vm_area_struct *vma); int ksm_enable_merge_any(struct mm_struct *mm); int ksm_disable_merge_any(struct mm_struct *mm); int ksm_disable(struct mm_struct *mm); int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); /* * To identify zeropages that were mapped by KSM, we reuse the dirty bit * in the PTE. If the PTE is dirty, the zeropage was mapped by KSM when * deduplicating memory. */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) extern unsigned long ksm_zero_pages; static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { ksm_zero_pages--; mm->ksm_zero_pages--; } } static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { int ret; if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) { ret = __ksm_enter(mm); if (ret) return ret; } if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags)) set_bit(MMF_VM_MERGE_ANY, &mm->flags); return 0; } static inline void ksm_exit(struct mm_struct *mm) { if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) __ksm_exit(mm); } /* * When do_swap_page() first faults in from swap what used to be a KSM page, * no problem, it will be assigned to this vma's anon_vma; but thereafter, * it might be faulted into a different anon_vma (or perhaps to a different * offset in the same anon_vma). do_swap_page() cannot do all the locking * needed to reconstitute a cross-anon_vma KSM page: for now it has to make * a copy, and leave remerging the pages to a later pass of ksmd. * * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #ifdef CONFIG_MEMORY_FAILURE void collect_procs_ksm(struct page *page, struct list_head *to_kill, int force_early); #endif #ifdef CONFIG_PROC_FS long ksm_process_profit(struct mm_struct *); #endif /* CONFIG_PROC_FS */ #else /* !CONFIG_KSM */ static inline void ksm_add_vma(struct vm_area_struct *vma) { } static inline int ksm_disable(struct mm_struct *mm) { return 0; } static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { return 0; } static inline void ksm_exit(struct mm_struct *mm) { } static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { } #ifdef CONFIG_MEMORY_FAILURE static inline void collect_procs_ksm(struct page *page, struct list_head *to_kill, int force_early) { } #endif #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) { return 0; } static inline struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { return page; } static inline void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { } static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old) { } #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ #endif /* __LINUX_KSM_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2008, 2009 open80211s Ltd. * Copyright (C) 2023 Intel Corporation * Authors: Luis Carlos Cobo <luisca@cozybit.com> * Javier Cardona <javier@cozybit.com> */ #ifndef IEEE80211S_H #define IEEE80211S_H #include <linux/types.h> #include <linux/jhash.h> #include "ieee80211_i.h" /* Data structures */ /** * enum mesh_path_flags - mac80211 mesh path flags * * @MESH_PATH_ACTIVE: the mesh path can be used for forwarding * @MESH_PATH_RESOLVING: the discovery process is running for this mesh path * @MESH_PATH_SN_VALID: the mesh path contains a valid destination sequence * number * @MESH_PATH_FIXED: the mesh path has been manually set and should not be * modified * @MESH_PATH_RESOLVED: the mesh path can has been resolved * @MESH_PATH_REQ_QUEUED: there is an unsent path request for this destination * already queued up, waiting for the discovery process to start. * @MESH_PATH_DELETED: the mesh path has been deleted and should no longer * be used * * MESH_PATH_RESOLVED is used by the mesh path timer to * decide when to stop or cancel the mesh path discovery. */ enum mesh_path_flags { MESH_PATH_ACTIVE = BIT(0), MESH_PATH_RESOLVING = BIT(1), MESH_PATH_SN_VALID = BIT(2), MESH_PATH_FIXED = BIT(3), MESH_PATH_RESOLVED = BIT(4), MESH_PATH_REQ_QUEUED = BIT(5), MESH_PATH_DELETED = BIT(6), }; /** * enum mesh_deferred_task_flags - mac80211 mesh deferred tasks * * * * @MESH_WORK_HOUSEKEEPING: run the periodic mesh housekeeping tasks * @MESH_WORK_ROOT: the mesh root station needs to send a frame * @MESH_WORK_DRIFT_ADJUST: time to compensate for clock drift relative to other * mesh nodes * @MESH_WORK_MBSS_CHANGED: rebuild beacon and notify driver of BSS changes */ enum mesh_deferred_task_flags { MESH_WORK_HOUSEKEEPING, MESH_WORK_ROOT, MESH_WORK_DRIFT_ADJUST, MESH_WORK_MBSS_CHANGED, }; /** * struct mesh_path - mac80211 mesh path structure * * @dst: mesh path destination mac address * @mpp: mesh proxy mac address * @rhash: rhashtable list pointer * @walk_list: linked list containing all mesh_path objects. * @gate_list: list pointer for known gates list * @sdata: mesh subif * @next_hop: mesh neighbor to which frames for this destination will be * forwarded * @timer: mesh path discovery timer * @frame_queue: pending queue for frames sent to this destination while the * path is unresolved * @rcu: rcu head for freeing mesh path * @sn: target sequence number * @metric: current metric to this destination * @hop_count: hops to destination * @exp_time: in jiffies, when the path will expire or when it expired * @discovery_timeout: timeout (lapse in jiffies) used for the last discovery * retry * @discovery_retries: number of discovery retries * @flags: mesh path flags, as specified on &enum mesh_path_flags * @state_lock: mesh path state lock used to protect changes to the * mpath itself. No need to take this lock when adding or removing * an mpath to a hash bucket on a path table. * @rann_snd_addr: the RANN sender address * @rann_metric: the aggregated path metric towards the root node * @last_preq_to_root: Timestamp of last PREQ sent to root * @is_root: the destination station of this path is a root node * @is_gate: the destination station of this path is a mesh gate * @path_change_count: the number of path changes to destination * * * The dst address is unique in the mesh path table. Since the mesh_path is * protected by RCU, deleting the next_hop STA must remove / substitute the * mesh_path structure and wait until that is no longer reachable before * destroying the STA completely. */ struct mesh_path { u8 dst[ETH_ALEN]; u8 mpp[ETH_ALEN]; /* used for MPP or MAP */ struct rhash_head rhash; struct hlist_node walk_list; struct hlist_node gate_list; struct ieee80211_sub_if_data *sdata; struct sta_info __rcu *next_hop; struct timer_list timer; struct sk_buff_head frame_queue; struct rcu_head rcu; u32 sn; u32 metric; u8 hop_count; unsigned long exp_time; u32 discovery_timeout; u8 discovery_retries; enum mesh_path_flags flags; spinlock_t state_lock; u8 rann_snd_addr[ETH_ALEN]; u32 rann_metric; unsigned long last_preq_to_root; unsigned long fast_tx_check; bool is_root; bool is_gate; u32 path_change_count; }; #define MESH_FAST_TX_CACHE_MAX_SIZE 512 #define MESH_FAST_TX_CACHE_THRESHOLD_SIZE 384 #define MESH_FAST_TX_CACHE_TIMEOUT 8000 /* msecs */ /** * struct ieee80211_mesh_fast_tx - cached mesh fast tx entry * @rhash: rhashtable pointer * @addr_key: The Ethernet DA which is the key for this entry * @fast_tx: base fast_tx data * @hdr: cached mesh and rfc1042 headers * @hdrlen: length of mesh + rfc1042 * @walk_list: list containing all the fast tx entries * @mpath: mesh path corresponding to the Mesh DA * @mppath: MPP entry corresponding to this DA * @timestamp: Last used time of this entry */ struct ieee80211_mesh_fast_tx { struct rhash_head rhash; u8 addr_key[ETH_ALEN] __aligned(2); struct ieee80211_fast_tx fast_tx; u8 hdr[sizeof(struct ieee80211s_hdr) + sizeof(rfc1042_header)]; u16 hdrlen; struct mesh_path *mpath, *mppath; struct hlist_node walk_list; unsigned long timestamp; }; /* Recent multicast cache */ /* RMC_BUCKETS must be a power of 2, maximum 256 */ #define RMC_BUCKETS 256 #define RMC_QUEUE_MAX_LEN 4 #define RMC_TIMEOUT (3 * HZ) /** * struct rmc_entry - entry in the Recent Multicast Cache * * @seqnum: mesh sequence number of the frame * @exp_time: expiration time of the entry, in jiffies * @sa: source address of the frame * @list: hashtable list pointer * * The Recent Multicast Cache keeps track of the latest multicast frames that * have been received by a mesh interface and discards received multicast frames * that are found in the cache. */ struct rmc_entry { struct hlist_node list; unsigned long exp_time; u32 seqnum; u8 sa[ETH_ALEN]; }; struct mesh_rmc { struct hlist_head bucket[RMC_BUCKETS]; u32 idx_mask; }; #define IEEE80211_MESH_HOUSEKEEPING_INTERVAL (60 * HZ) #define MESH_PATH_EXPIRE (600 * HZ) /* Default maximum number of plinks per interface */ #define MESH_MAX_PLINKS 256 /* Maximum number of paths per interface */ #define MESH_MAX_MPATHS 1024 /* Number of frames buffered per destination for unresolved destinations */ #define MESH_FRAME_QUEUE_LEN 10 /* Public interfaces */ /* Various */ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, const u8 *da, const u8 *sa); unsigned int ieee80211_new_mesh_header(struct ieee80211_sub_if_data *sdata, struct ieee80211s_hdr *meshhdr, const char *addr4or5, const char *addr6); int mesh_rmc_check(struct ieee80211_sub_if_data *sdata, const u8 *addr, struct ieee80211s_hdr *mesh_hdr); bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *ie); int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_meshid_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_rsn_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vendor_ies(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_ht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_ht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_he_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u8 ie_len); int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_he_6ghz_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_eht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u8 ie_len); int mesh_add_eht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); void ieee80211s_update_metric(struct ieee80211_local *local, struct sta_info *sta, struct ieee80211_tx_status *st); void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_teardown_sdata(struct ieee80211_sub_if_data *sdata); int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh); const struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method); /* wrapper for ieee80211_bss_info_change_notify() */ void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata, u64 changed); /* mesh power save */ u64 ieee80211_mps_local_status_update(struct ieee80211_sub_if_data *sdata); u64 ieee80211_mps_set_sta_local_pm(struct sta_info *sta, enum nl80211_mesh_power_mode pm); void ieee80211_mps_set_frame_flags(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_hdr *hdr); void ieee80211_mps_sta_status_update(struct sta_info *sta); void ieee80211_mps_rx_h_sta_process(struct sta_info *sta, struct ieee80211_hdr *hdr); void ieee80211_mpsp_trigger_process(u8 *qc, struct sta_info *sta, bool tx, bool acked); void ieee80211_mps_frame_release(struct sta_info *sta, struct ieee802_11_elems *elems); /* Mesh paths */ int mesh_nexthop_lookup(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata); struct mesh_path *mesh_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst); struct mesh_path *mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst); int mpp_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst, const u8 *mpp); struct mesh_path * mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx); struct mesh_path * mpp_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx); void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop); void mesh_path_expire(struct ieee80211_sub_if_data *sdata); void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len); struct mesh_path * mesh_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst); int mesh_path_add_gate(struct mesh_path *mpath); int mesh_path_send_to_gates(struct mesh_path *mpath); int mesh_gate_num(struct ieee80211_sub_if_data *sdata); u32 airtime_link_metric_get(struct ieee80211_local *local, struct sta_info *sta); /* Mesh plinks */ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, u8 *hw_addr, struct ieee802_11_elems *ie, struct ieee80211_rx_status *rx_status); bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie); u64 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata); void mesh_plink_timer(struct timer_list *t); void mesh_plink_broken(struct sta_info *sta); u64 mesh_plink_deactivate(struct sta_info *sta); u64 mesh_plink_open(struct sta_info *sta); u64 mesh_plink_block(struct sta_info *sta); void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status); void mesh_sta_cleanup(struct sta_info *sta); /* Private interfaces */ /* Mesh paths */ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, u8 ttl, const u8 *target, u32 target_sn, u16 target_rcode, const u8 *ra); void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta); void mesh_path_flush_pending(struct mesh_path *mpath); void mesh_path_tx_pending(struct mesh_path *mpath); void mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata); void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata); int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr); void mesh_path_timer(struct timer_list *t); void mesh_path_flush_by_nexthop(struct sta_info *sta); void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata); bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt); struct ieee80211_mesh_fast_tx * mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata, const u8 *addr); bool ieee80211_mesh_xmit_fast(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 ctrl_flags); void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, struct mesh_path *mpath); void mesh_fast_tx_gc(struct ieee80211_sub_if_data *sdata); void mesh_fast_tx_flush_addr(struct ieee80211_sub_if_data *sdata, const u8 *addr); void mesh_fast_tx_flush_mpath(struct mesh_path *mpath); void mesh_fast_tx_flush_sta(struct ieee80211_sub_if_data *sdata, struct sta_info *sta); void mesh_path_refresh(struct ieee80211_sub_if_data *sdata, struct mesh_path *mpath, const u8 *addr); #ifdef CONFIG_MAC80211_MESH static inline u64 mesh_plink_inc_estab_count(struct ieee80211_sub_if_data *sdata) { atomic_inc(&sdata->u.mesh.estab_plinks); return mesh_accept_plinks_update(sdata) | BSS_CHANGED_BEACON; } static inline u64 mesh_plink_dec_estab_count(struct ieee80211_sub_if_data *sdata) { atomic_dec(&sdata->u.mesh.estab_plinks); return mesh_accept_plinks_update(sdata) | BSS_CHANGED_BEACON; } static inline int mesh_plink_free_count(struct ieee80211_sub_if_data *sdata) { return sdata->u.mesh.mshcfg.dot11MeshMaxPeerLinks - atomic_read(&sdata->u.mesh.estab_plinks); } static inline bool mesh_plink_availables(struct ieee80211_sub_if_data *sdata) { return (min_t(long, mesh_plink_free_count(sdata), MESH_MAX_PLINKS - sdata->local->num_sta)) > 0; } static inline void mesh_path_activate(struct mesh_path *mpath) { mpath->flags |= MESH_PATH_ACTIVE | MESH_PATH_RESOLVED; } static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return sdata->u.mesh.mesh_pp_id == IEEE80211_PATH_PROTOCOL_HWMP; } void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); void mesh_sync_adjust_tsf(struct ieee80211_sub_if_data *sdata); void ieee80211s_stop(void); #else static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return false; } static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) {} static inline void ieee80211s_stop(void) {} #endif #endif /* IEEE80211S_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * SM4 Cipher Algorithm, AES-NI/AVX2 optimized. * as specified in * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html * * Copyright (c) 2021, Alibaba Group. * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com> */ #include <linux/module.h> #include <linux/crypto.h> #include <linux/kernel.h> #include <asm/simd.h> #include <crypto/internal/simd.h> #include <crypto/internal/skcipher.h> #include <crypto/sm4.h> #include "sm4-avx.h" #define SM4_CRYPT16_BLOCK_SIZE (SM4_BLOCK_SIZE * 16) asmlinkage void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst, const u8 *src, u8 *iv); asmlinkage void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst, const u8 *src, u8 *iv); asmlinkage void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst, const u8 *src, u8 *iv); static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int key_len) { struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); return sm4_expandkey(ctx, key, key_len); } static int cbc_decrypt(struct skcipher_request *req) { return sm4_avx_cbc_decrypt(req, SM4_CRYPT16_BLOCK_SIZE, sm4_aesni_avx2_cbc_dec_blk16); } static int cfb_decrypt(struct skcipher_request *req) { return sm4_avx_cfb_decrypt(req, SM4_CRYPT16_BLOCK_SIZE, sm4_aesni_avx2_cfb_dec_blk16); } static int ctr_crypt(struct skcipher_request *req) { return sm4_avx_ctr_crypt(req, SM4_CRYPT16_BLOCK_SIZE, sm4_aesni_avx2_ctr_enc_blk16); } static struct skcipher_alg sm4_aesni_avx2_skciphers[] = { { .base = { .cra_name = "__ecb(sm4)", .cra_driver_name = "__ecb-sm4-aesni-avx2", .cra_priority = 500, .cra_flags = CRYPTO_ALG_INTERNAL, .cra_blocksize = SM4_BLOCK_SIZE, .cra_ctxsize = sizeof(struct sm4_ctx), .cra_module = THIS_MODULE, }, .min_keysize = SM4_KEY_SIZE, .max_keysize = SM4_KEY_SIZE, .walksize = 16 * SM4_BLOCK_SIZE, .setkey = sm4_skcipher_setkey, .encrypt = sm4_avx_ecb_encrypt, .decrypt = sm4_avx_ecb_decrypt, }, { .base = { .cra_name = "__cbc(sm4)", .cra_driver_name = "__cbc-sm4-aesni-avx2", .cra_priority = 500, .cra_flags = CRYPTO_ALG_INTERNAL, .cra_blocksize = SM4_BLOCK_SIZE, .cra_ctxsize = sizeof(struct sm4_ctx), .cra_module = THIS_MODULE, }, .min_keysize = SM4_KEY_SIZE, .max_keysize = SM4_KEY_SIZE, .ivsize = SM4_BLOCK_SIZE, .walksize = 16 * SM4_BLOCK_SIZE, .setkey = sm4_skcipher_setkey, .encrypt = sm4_cbc_encrypt, .decrypt = cbc_decrypt, }, { .base = { .cra_name = "__cfb(sm4)", .cra_driver_name = "__cfb-sm4-aesni-avx2", .cra_priority = 500, .cra_flags = CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct sm4_ctx), .cra_module = THIS_MODULE, }, .min_keysize = SM4_KEY_SIZE, .max_keysize = SM4_KEY_SIZE, .ivsize = SM4_BLOCK_SIZE, .chunksize = SM4_BLOCK_SIZE, .walksize = 16 * SM4_BLOCK_SIZE, .setkey = sm4_skcipher_setkey, .encrypt = sm4_cfb_encrypt, .decrypt = cfb_decrypt, }, { .base = { .cra_name = "__ctr(sm4)", .cra_driver_name = "__ctr-sm4-aesni-avx2", .cra_priority = 500, .cra_flags = CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct sm4_ctx), .cra_module = THIS_MODULE, }, .min_keysize = SM4_KEY_SIZE, .max_keysize = SM4_KEY_SIZE, .ivsize = SM4_BLOCK_SIZE, .chunksize = SM4_BLOCK_SIZE, .walksize = 16 * SM4_BLOCK_SIZE, .setkey = sm4_skcipher_setkey, .encrypt = ctr_crypt, .decrypt = ctr_crypt, } }; static struct simd_skcipher_alg * simd_sm4_aesni_avx2_skciphers[ARRAY_SIZE(sm4_aesni_avx2_skciphers)]; static int __init sm4_init(void) { const char *feature_name; if (!boot_cpu_has(X86_FEATURE_AVX) || !boot_cpu_has(X86_FEATURE_AVX2) || !boot_cpu_has(X86_FEATURE_AES) || !boot_cpu_has(X86_FEATURE_OSXSAVE)) { pr_info("AVX2 or AES-NI instructions are not detected.\n"); return -ENODEV; } if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, &feature_name)) { pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } return simd_register_skciphers_compat(sm4_aesni_avx2_skciphers, ARRAY_SIZE(sm4_aesni_avx2_skciphers), simd_sm4_aesni_avx2_skciphers); } static void __exit sm4_exit(void) { simd_unregister_skciphers(sm4_aesni_avx2_skciphers, ARRAY_SIZE(sm4_aesni_avx2_skciphers), simd_sm4_aesni_avx2_skciphers); } module_init(sm4_init); module_exit(sm4_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Tianjia Zhang <tianjia.zhang@linux.alibaba.com>"); MODULE_DESCRIPTION("SM4 Cipher Algorithm, AES-NI/AVX2 optimized"); MODULE_ALIAS_CRYPTO("sm4"); MODULE_ALIAS_CRYPTO("sm4-aesni-avx2"); |
| 83 83 83 83 16 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cache.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/pid_namespace.h> #include "internal.h" /* * /proc/thread_self: */ static const char *proc_thread_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct pid_namespace *ns = proc_pid_ns(inode->i_sb); pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; if (!pid) return ERR_PTR(-ENOENT); name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); if (unlikely(!name)) return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%u/task/%u", tgid, pid); set_delayed_call(done, kfree_link, name); return name; } static const struct inode_operations proc_thread_self_inode_operations = { .get_link = proc_thread_self_get_link, }; static unsigned thread_self_inum __ro_after_init; int proc_setup_thread_self(struct super_block *s) { struct inode *root_inode = d_inode(s->s_root); struct proc_fs_info *fs_info = proc_sb_info(s); struct dentry *thread_self; int ret = -ENOMEM; inode_lock(root_inode); thread_self = d_alloc_name(s->s_root, "thread-self"); if (thread_self) { struct inode *inode = new_inode(s); if (inode) { inode->i_ino = thread_self_inum; simple_inode_init_ts(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_thread_self_inode_operations; d_add(thread_self, inode); ret = 0; } else { dput(thread_self); } } inode_unlock(root_inode); if (ret) pr_err("proc_fill_super: can't allocate /proc/thread-self\n"); else fs_info->proc_thread_self = thread_self; return ret; } void __init proc_thread_self_init(void) { proc_alloc_inum(&thread_self_inum); } |
| 29 29 123 121 121 121 38 38 38 38 38 37 38 38 37 38 38 38 46 46 46 60 60 60 27 38 14 4 10 10 10 10 29 38 23 3 3 3 3 3 3 23 23 4 1 4 9 23 23 23 3 3 3 3 3 3 3 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 | // SPDX-License-Identifier: GPL-2.0-or-later /* * inet fragments management * * Authors: Pavel Emelyanov <xemul@openvz.org> * Started as consolidation of ipv4/ip_fragment.c, * ipv6/reassembly. and ipv6 nf conntrack reassembly */ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/rhashtable.h> #include <net/sock.h> #include <net/inet_frag.h> #include <net/inet_ecn.h> #include <net/ip.h> #include <net/ipv6.h> /* Use skb->cb to track consecutive/adjacent fragments coming at * the end of the queue. Nodes in the rb-tree queue will * contain "runs" of one or more adjacent fragments. * * Invariants: * - next_frag is NULL at the tail of a "run"; * - the head of a "run" has the sum of all fragment lengths in frag_run_len. */ struct ipfrag_skb_cb { union { struct inet_skb_parm h4; struct inet6_skb_parm h6; }; struct sk_buff *next_frag; int frag_run_len; }; #define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) static void fragcb_clear(struct sk_buff *skb) { RB_CLEAR_NODE(&skb->rbnode); FRAG_CB(skb)->next_frag = NULL; FRAG_CB(skb)->frag_run_len = skb->len; } /* Append skb to the last "run". */ static void fragrun_append_to_last(struct inet_frag_queue *q, struct sk_buff *skb) { fragcb_clear(skb); FRAG_CB(q->last_run_head)->frag_run_len += skb->len; FRAG_CB(q->fragments_tail)->next_frag = skb; q->fragments_tail = skb; } /* Create a new "run" with the skb. */ static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); fragcb_clear(skb); if (q->last_run_head) rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, &q->last_run_head->rbnode.rb_right); else rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); rb_insert_color(&skb->rbnode, &q->rb_fragments); q->fragments_tail = skb; q->last_run_head = skb; } /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. * 0 or INET_ECN_CE value, to be ORed in to final iph->tos field */ const u8 ip_frag_ecn_table[16] = { /* at least one fragment had CE, and others ECT_0 or ECT_1 */ [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = INET_ECN_CE, [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = INET_ECN_CE, [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = INET_ECN_CE, /* invalid combinations : drop frame */ [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff, }; EXPORT_SYMBOL(ip_frag_ecn_table); int inet_frags_init(struct inet_frags *f) { f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0, NULL); if (!f->frags_cachep) return -ENOMEM; refcount_set(&f->refcnt, 1); init_completion(&f->completion); return 0; } EXPORT_SYMBOL(inet_frags_init); void inet_frags_fini(struct inet_frags *f) { if (refcount_dec_and_test(&f->refcnt)) complete(&f->completion); wait_for_completion(&f->completion); kmem_cache_destroy(f->frags_cachep); f->frags_cachep = NULL; } EXPORT_SYMBOL(inet_frags_fini); /* called from rhashtable_free_and_destroy() at netns_frags dismantle */ static void inet_frags_free_cb(void *ptr, void *arg) { struct inet_frag_queue *fq = ptr; int count; count = del_timer_sync(&fq->timer) ? 1 : 0; spin_lock_bh(&fq->lock); fq->flags |= INET_FRAG_DROP; if (!(fq->flags & INET_FRAG_COMPLETE)) { fq->flags |= INET_FRAG_COMPLETE; count++; } else if (fq->flags & INET_FRAG_HASH_DEAD) { count++; } spin_unlock_bh(&fq->lock); if (refcount_sub_and_test(count, &fq->refcnt)) inet_frag_destroy(fq); } static LLIST_HEAD(fqdir_free_list); static void fqdir_free_fn(struct work_struct *work) { struct llist_node *kill_list; struct fqdir *fqdir, *tmp; struct inet_frags *f; /* Atomically snapshot the list of fqdirs to free */ kill_list = llist_del_all(&fqdir_free_list); /* We need to make sure all ongoing call_rcu(..., inet_frag_destroy_rcu) * have completed, since they need to dereference fqdir. * Would it not be nice to have kfree_rcu_barrier() ? :) */ rcu_barrier(); llist_for_each_entry_safe(fqdir, tmp, kill_list, free_list) { f = fqdir->f; if (refcount_dec_and_test(&f->refcnt)) complete(&f->completion); kfree(fqdir); } } static DECLARE_WORK(fqdir_free_work, fqdir_free_fn); static void fqdir_work_fn(struct work_struct *work) { struct fqdir *fqdir = container_of(work, struct fqdir, destroy_work); rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL); if (llist_add(&fqdir->free_list, &fqdir_free_list)) queue_work(system_wq, &fqdir_free_work); } int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net) { struct fqdir *fqdir = kzalloc(sizeof(*fqdir), GFP_KERNEL); int res; if (!fqdir) return -ENOMEM; fqdir->f = f; fqdir->net = net; res = rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); if (res < 0) { kfree(fqdir); return res; } refcount_inc(&f->refcnt); *fqdirp = fqdir; return 0; } EXPORT_SYMBOL(fqdir_init); static struct workqueue_struct *inet_frag_wq; static int __init inet_frag_wq_init(void) { inet_frag_wq = create_workqueue("inet_frag_wq"); if (!inet_frag_wq) panic("Could not create inet frag workq"); return 0; } pure_initcall(inet_frag_wq_init); void fqdir_exit(struct fqdir *fqdir) { INIT_WORK(&fqdir->destroy_work, fqdir_work_fn); queue_work(inet_frag_wq, &fqdir->destroy_work); } EXPORT_SYMBOL(fqdir_exit); void inet_frag_kill(struct inet_frag_queue *fq) { if (del_timer(&fq->timer)) refcount_dec(&fq->refcnt); if (!(fq->flags & INET_FRAG_COMPLETE)) { struct fqdir *fqdir = fq->fqdir; fq->flags |= INET_FRAG_COMPLETE; rcu_read_lock(); /* The RCU read lock provides a memory barrier * guaranteeing that if fqdir->dead is false then * the hash table destruction will not start until * after we unlock. Paired with fqdir_pre_exit(). */ if (!READ_ONCE(fqdir->dead)) { rhashtable_remove_fast(&fqdir->rhashtable, &fq->node, fqdir->f->rhash_params); refcount_dec(&fq->refcnt); } else { fq->flags |= INET_FRAG_HASH_DEAD; } rcu_read_unlock(); } } EXPORT_SYMBOL(inet_frag_kill); static void inet_frag_destroy_rcu(struct rcu_head *head) { struct inet_frag_queue *q = container_of(head, struct inet_frag_queue, rcu); struct inet_frags *f = q->fqdir->f; if (f->destructor) f->destructor(q); kmem_cache_free(f->frags_cachep, q); } unsigned int inet_frag_rbtree_purge(struct rb_root *root, enum skb_drop_reason reason) { struct rb_node *p = rb_first(root); unsigned int sum = 0; while (p) { struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); p = rb_next(p); rb_erase(&skb->rbnode, root); while (skb) { struct sk_buff *next = FRAG_CB(skb)->next_frag; sum += skb->truesize; kfree_skb_reason(skb, reason); skb = next; } } return sum; } EXPORT_SYMBOL(inet_frag_rbtree_purge); void inet_frag_destroy(struct inet_frag_queue *q) { unsigned int sum, sum_truesize = 0; enum skb_drop_reason reason; struct inet_frags *f; struct fqdir *fqdir; WARN_ON(!(q->flags & INET_FRAG_COMPLETE)); reason = (q->flags & INET_FRAG_DROP) ? SKB_DROP_REASON_FRAG_REASM_TIMEOUT : SKB_CONSUMED; WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ fqdir = q->fqdir; f = fqdir->f; sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments, reason); sum = sum_truesize + f->qsize; call_rcu(&q->rcu, inet_frag_destroy_rcu); sub_frag_mem_limit(fqdir, sum); } EXPORT_SYMBOL(inet_frag_destroy); static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir, struct inet_frags *f, void *arg) { struct inet_frag_queue *q; q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (!q) return NULL; q->fqdir = fqdir; f->constructor(q, arg); add_frag_mem_limit(fqdir, f->qsize); timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); refcount_set(&q->refcnt, 3); return q; } static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, void *arg, struct inet_frag_queue **prev) { struct inet_frags *f = fqdir->f; struct inet_frag_queue *q; q = inet_frag_alloc(fqdir, f, arg); if (!q) { *prev = ERR_PTR(-ENOMEM); return NULL; } mod_timer(&q->timer, jiffies + fqdir->timeout); *prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key, &q->node, f->rhash_params); if (*prev) { q->flags |= INET_FRAG_COMPLETE; inet_frag_kill(q); inet_frag_destroy(q); return NULL; } return q; } /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) { /* This pairs with WRITE_ONCE() in fqdir_pre_exit(). */ long high_thresh = READ_ONCE(fqdir->high_thresh); struct inet_frag_queue *fq = NULL, *prev; if (!high_thresh || frag_mem_limit(fqdir) > high_thresh) return NULL; rcu_read_lock(); prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params); if (!prev) fq = inet_frag_create(fqdir, key, &prev); if (!IS_ERR_OR_NULL(prev)) { fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; } rcu_read_unlock(); return fq; } EXPORT_SYMBOL(inet_frag_find); int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, int offset, int end) { struct sk_buff *last = q->fragments_tail; /* RFC5722, Section 4, amended by Errata ID : 3089 * When reassembling an IPv6 datagram, if * one or more its constituent fragments is determined to be an * overlapping fragment, the entire datagram (and any constituent * fragments) MUST be silently discarded. * * Duplicates, however, should be ignored (i.e. skb dropped, but the * queue/fragments kept for later reassembly). */ if (!last) fragrun_create(q, skb); /* First fragment. */ else if (last->ip_defrag_offset + last->len < end) { /* This is the common case: skb goes to the end. */ /* Detect and discard overlaps. */ if (offset < last->ip_defrag_offset + last->len) return IPFRAG_OVERLAP; if (offset == last->ip_defrag_offset + last->len) fragrun_append_to_last(q, skb); else fragrun_create(q, skb); } else { /* Binary search. Note that skb can become the first fragment, * but not the last (covered above). */ struct rb_node **rbn, *parent; rbn = &q->rb_fragments.rb_node; do { struct sk_buff *curr; int curr_run_end; parent = *rbn; curr = rb_to_skb(parent); curr_run_end = curr->ip_defrag_offset + FRAG_CB(curr)->frag_run_len; if (end <= curr->ip_defrag_offset) rbn = &parent->rb_left; else if (offset >= curr_run_end) rbn = &parent->rb_right; else if (offset >= curr->ip_defrag_offset && end <= curr_run_end) return IPFRAG_DUP; else return IPFRAG_OVERLAP; } while (*rbn); /* Here we have parent properly set, and rbn pointing to * one of its NULL left/right children. Insert skb. */ fragcb_clear(skb); rb_link_node(&skb->rbnode, parent, rbn); rb_insert_color(&skb->rbnode, &q->rb_fragments); } skb->ip_defrag_offset = offset; return IPFRAG_OK; } EXPORT_SYMBOL(inet_frag_queue_insert); void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, struct sk_buff *parent) { struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); struct sk_buff **nextp; int delta; if (head != skb) { fp = skb_clone(skb, GFP_ATOMIC); if (!fp) return NULL; FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; if (RB_EMPTY_NODE(&skb->rbnode)) FRAG_CB(parent)->next_frag = fp; else rb_replace_node(&skb->rbnode, &fp->rbnode, &q->rb_fragments); if (q->fragments_tail == skb) q->fragments_tail = fp; skb_morph(skb, head); FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; rb_replace_node(&head->rbnode, &skb->rbnode, &q->rb_fragments); consume_skb(head); head = skb; } WARN_ON(head->ip_defrag_offset != 0); delta = -head->truesize; /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) return NULL; delta += head->truesize; if (delta) add_frag_mem_limit(q->fqdir, delta); /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ if (skb_has_frag_list(head)) { struct sk_buff *clone; int i, plen = 0; clone = alloc_skb(0, GFP_ATOMIC); if (!clone) return NULL; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); for (i = 0; i < skb_shinfo(head)->nr_frags; i++) plen += skb_frag_size(&skb_shinfo(head)->frags[i]); clone->data_len = head->data_len - plen; clone->len = clone->data_len; head->truesize += clone->truesize; clone->csum = 0; clone->ip_summed = head->ip_summed; add_frag_mem_limit(q->fqdir, clone->truesize); skb_shinfo(head)->frag_list = clone; nextp = &clone->next; } else { nextp = &skb_shinfo(head)->frag_list; } return nextp; } EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, void *reasm_data, bool try_coalesce) { struct sk_buff **nextp = reasm_data; struct rb_node *rbn; struct sk_buff *fp; int sum_truesize; skb_push(head, head->data - skb_network_header(head)); /* Traverse the tree in order, to build frag_list. */ fp = FRAG_CB(head)->next_frag; rbn = rb_next(&head->rbnode); rb_erase(&head->rbnode, &q->rb_fragments); sum_truesize = head->truesize; while (rbn || fp) { /* fp points to the next sk_buff in the current run; * rbn points to the next run. */ /* Go through the current run. */ while (fp) { struct sk_buff *next_frag = FRAG_CB(fp)->next_frag; bool stolen; int delta; sum_truesize += fp->truesize; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); if (try_coalesce && skb_try_coalesce(head, fp, &stolen, &delta)) { kfree_skb_partial(fp, stolen); } else { fp->prev = NULL; memset(&fp->rbnode, 0, sizeof(fp->rbnode)); fp->sk = NULL; head->data_len += fp->len; head->len += fp->len; head->truesize += fp->truesize; *nextp = fp; nextp = &fp->next; } fp = next_frag; } /* Move to the next run. */ if (rbn) { struct rb_node *rbnext = rb_next(rbn); fp = rb_to_skb(rbn); rb_erase(rbn, &q->rb_fragments); rbn = rbnext; } } sub_frag_mem_limit(q->fqdir, sum_truesize); *nextp = NULL; skb_mark_not_on_list(head); head->prev = NULL; head->tstamp = q->stamp; head->mono_delivery_time = q->mono_delivery_time; } EXPORT_SYMBOL(inet_frag_reasm_finish); struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) { struct sk_buff *head, *skb; head = skb_rb_first(&q->rb_fragments); if (!head) return NULL; skb = FRAG_CB(head)->next_frag; if (skb) rb_replace_node(&head->rbnode, &skb->rbnode, &q->rb_fragments); else rb_erase(&head->rbnode, &q->rb_fragments); memset(&head->rbnode, 0, sizeof(head->rbnode)); barrier(); if (head == q->fragments_tail) q->fragments_tail = NULL; sub_frag_mem_limit(q->fqdir, head->truesize); return head; } EXPORT_SYMBOL(inet_frag_pull_head); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_PAGE_IDLE_H #define _LINUX_MM_PAGE_IDLE_H #include <linux/bitops.h> #include <linux/page-flags.h> #include <linux/page_ext.h> #ifdef CONFIG_PAGE_IDLE_FLAG #ifndef CONFIG_64BIT /* * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ static inline bool folio_test_young(struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); bool page_young; if (unlikely(!page_ext)) return false; page_young = test_bit(PAGE_EXT_YOUNG, &page_ext->flags); page_ext_put(page_ext); return page_young; } static inline void folio_set_young(struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; set_bit(PAGE_EXT_YOUNG, &page_ext->flags); page_ext_put(page_ext); } static inline bool folio_test_clear_young(struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); bool page_young; if (unlikely(!page_ext)) return false; page_young = test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags); page_ext_put(page_ext); return page_young; } static inline bool folio_test_idle(struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); bool page_idle; if (unlikely(!page_ext)) return false; page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags); page_ext_put(page_ext); return page_idle; } static inline void folio_set_idle(struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; set_bit(PAGE_EXT_IDLE, &page_ext->flags); page_ext_put(page_ext); } static inline void folio_clear_idle(struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; clear_bit(PAGE_EXT_IDLE, &page_ext->flags); page_ext_put(page_ext); } #endif /* !CONFIG_64BIT */ #else /* !CONFIG_PAGE_IDLE_FLAG */ static inline bool folio_test_young(struct folio *folio) { return false; } static inline void folio_set_young(struct folio *folio) { } static inline bool folio_test_clear_young(struct folio *folio) { return false; } static inline bool folio_test_idle(struct folio *folio) { return false; } static inline void folio_set_idle(struct folio *folio) { } static inline void folio_clear_idle(struct folio *folio) { } #endif /* CONFIG_PAGE_IDLE_FLAG */ static inline bool page_is_young(struct page *page) { return folio_test_young(page_folio(page)); } static inline void set_page_young(struct page *page) { folio_set_young(page_folio(page)); } static inline bool test_and_clear_page_young(struct page *page) { return folio_test_clear_young(page_folio(page)); } static inline bool page_is_idle(struct page *page) { return folio_test_idle(page_folio(page)); } static inline void set_page_idle(struct page *page) { folio_set_idle(page_folio(page)); } #endif /* _LINUX_MM_PAGE_IDLE_H */ |
| 4 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us> */ #ifndef __NET_TC_VLAN_H #define __NET_TC_VLAN_H #include <net/act_api.h> #include <linux/tc_act/tc_vlan.h> struct tcf_vlan_params { int tcfv_action; unsigned char tcfv_push_dst[ETH_ALEN]; unsigned char tcfv_push_src[ETH_ALEN]; u16 tcfv_push_vid; __be16 tcfv_push_proto; u8 tcfv_push_prio; bool tcfv_push_prio_exists; struct rcu_head rcu; }; struct tcf_vlan { struct tc_action common; struct tcf_vlan_params __rcu *vlan_p; }; #define to_vlan(a) ((struct tcf_vlan *)a) static inline bool is_tcf_vlan(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->id == TCA_ID_VLAN) return true; #endif return false; } static inline u32 tcf_vlan_action(const struct tc_action *a) { u32 tcfv_action; rcu_read_lock(); tcfv_action = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_action; rcu_read_unlock(); return tcfv_action; } static inline u16 tcf_vlan_push_vid(const struct tc_action *a) { u16 tcfv_push_vid; rcu_read_lock(); tcfv_push_vid = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_vid; rcu_read_unlock(); return tcfv_push_vid; } static inline __be16 tcf_vlan_push_proto(const struct tc_action *a) { __be16 tcfv_push_proto; rcu_read_lock(); tcfv_push_proto = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_proto; rcu_read_unlock(); return tcfv_push_proto; } static inline u8 tcf_vlan_push_prio(const struct tc_action *a) { u8 tcfv_push_prio; rcu_read_lock(); tcfv_push_prio = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_prio; rcu_read_unlock(); return tcfv_push_prio; } static inline void tcf_vlan_push_eth(unsigned char *src, unsigned char *dest, const struct tc_action *a) { rcu_read_lock(); memcpy(dest, rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_dst, ETH_ALEN); memcpy(src, rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_src, ETH_ALEN); rcu_read_unlock(); } #endif /* __NET_TC_VLAN_H */ |
| 542 542 542 542 542 542 421 527 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/char/misc.c * * Generic misc open routine by Johan Myreen * * Based on code from Linus * * Teemu Rantanen's Microsoft Busmouse support and Derrick Cole's * changes incorporated into 0.97pl4 * by Peter Cervasio (pete%q106fm.uucp@wupost.wustl.edu) (08SEP92) * See busmouse.c for particulars. * * Made things a lot mode modular - easy to compile in just one or two * of the misc drivers, as they are now completely independent. Linus. * * Support for loadable modules. 8-Sep-95 Philip Blundell <pjb27@cam.ac.uk> * * Fixed a failing symbol register to free the device registration * Alan Cox <alan@lxorguk.ukuu.org.uk> 21-Jan-96 * * Dynamic minors and /proc/mice by Alessandro Rubini. 26-Mar-96 * * Renamed to misc and miscdevice to be more accurate. Alan Cox 26-Mar-96 * * Handling of mouse minor numbers for kerneld: * Idea by Jacques Gelinas <jack@solucorp.qc.ca>, * adapted by Bjorn Ekwall <bj0rn@blox.se> * corrected by Alan Cox <alan@lxorguk.ukuu.org.uk> * * Changes for kmod (from kerneld): * Cyrus Durgin <cider@speakeasy.org> * * Added devfs support. Richard Gooch <rgooch@atnf.csiro.au> 10-Jan-1998 */ #include <linux/module.h> #include <linux/fs.h> #include <linux/errno.h> #include <linux/miscdevice.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/device.h> #include <linux/tty.h> #include <linux/kmod.h> #include <linux/gfp.h> /* * Head entry for the doubly linked miscdevice list */ static LIST_HEAD(misc_list); static DEFINE_MUTEX(misc_mtx); /* * Assigned numbers, used for dynamic minors */ #define DYNAMIC_MINORS 128 /* like dynamic majors */ static DEFINE_IDA(misc_minors_ida); static int misc_minor_alloc(void) { int ret; ret = ida_alloc_max(&misc_minors_ida, DYNAMIC_MINORS - 1, GFP_KERNEL); if (ret >= 0) { ret = DYNAMIC_MINORS - ret - 1; } else { ret = ida_alloc_range(&misc_minors_ida, MISC_DYNAMIC_MINOR + 1, MINORMASK, GFP_KERNEL); } return ret; } static void misc_minor_free(int minor) { if (minor < DYNAMIC_MINORS) ida_free(&misc_minors_ida, DYNAMIC_MINORS - minor - 1); else if (minor > MISC_DYNAMIC_MINOR) ida_free(&misc_minors_ida, minor); } #ifdef CONFIG_PROC_FS static void *misc_seq_start(struct seq_file *seq, loff_t *pos) { mutex_lock(&misc_mtx); return seq_list_start(&misc_list, *pos); } static void *misc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &misc_list, pos); } static void misc_seq_stop(struct seq_file *seq, void *v) { mutex_unlock(&misc_mtx); } static int misc_seq_show(struct seq_file *seq, void *v) { const struct miscdevice *p = list_entry(v, struct miscdevice, list); seq_printf(seq, "%3i %s\n", p->minor, p->name ? p->name : ""); return 0; } static const struct seq_operations misc_seq_ops = { .start = misc_seq_start, .next = misc_seq_next, .stop = misc_seq_stop, .show = misc_seq_show, }; #endif static int misc_open(struct inode *inode, struct file *file) { int minor = iminor(inode); struct miscdevice *c = NULL, *iter; int err = -ENODEV; const struct file_operations *new_fops = NULL; mutex_lock(&misc_mtx); list_for_each_entry(iter, &misc_list, list) { if (iter->minor != minor) continue; c = iter; new_fops = fops_get(iter->fops); break; } if (!new_fops) { mutex_unlock(&misc_mtx); request_module("char-major-%d-%d", MISC_MAJOR, minor); mutex_lock(&misc_mtx); list_for_each_entry(iter, &misc_list, list) { if (iter->minor != minor) continue; c = iter; new_fops = fops_get(iter->fops); break; } if (!new_fops) goto fail; } /* * Place the miscdevice in the file's * private_data so it can be used by the * file operations, including f_op->open below */ file->private_data = c; err = 0; replace_fops(file, new_fops); if (file->f_op->open) err = file->f_op->open(inode, file); fail: mutex_unlock(&misc_mtx); return err; } static char *misc_devnode(const struct device *dev, umode_t *mode) { const struct miscdevice *c = dev_get_drvdata(dev); if (mode && c->mode) *mode = c->mode; if (c->nodename) return kstrdup(c->nodename, GFP_KERNEL); return NULL; } static const struct class misc_class = { .name = "misc", .devnode = misc_devnode, }; static const struct file_operations misc_fops = { .owner = THIS_MODULE, .open = misc_open, .llseek = noop_llseek, }; /** * misc_register - register a miscellaneous device * @misc: device structure * * Register a miscellaneous device with the kernel. If the minor * number is set to %MISC_DYNAMIC_MINOR a minor number is assigned * and placed in the minor field of the structure. For other cases * the minor number requested is used. * * The structure passed is linked into the kernel and may not be * destroyed until it has been unregistered. By default, an open() * syscall to the device sets file->private_data to point to the * structure. Drivers don't need open in fops for this. * * A zero is returned on success and a negative errno code for * failure. */ int misc_register(struct miscdevice *misc) { dev_t dev; int err = 0; bool is_dynamic = (misc->minor == MISC_DYNAMIC_MINOR); INIT_LIST_HEAD(&misc->list); mutex_lock(&misc_mtx); if (is_dynamic) { int i = misc_minor_alloc(); if (i < 0) { err = -EBUSY; goto out; } misc->minor = i; } else { struct miscdevice *c; list_for_each_entry(c, &misc_list, list) { if (c->minor == misc->minor) { err = -EBUSY; goto out; } } } dev = MKDEV(MISC_MAJOR, misc->minor); misc->this_device = device_create_with_groups(&misc_class, misc->parent, dev, misc, misc->groups, "%s", misc->name); if (IS_ERR(misc->this_device)) { if (is_dynamic) { misc_minor_free(misc->minor); misc->minor = MISC_DYNAMIC_MINOR; } err = PTR_ERR(misc->this_device); goto out; } /* * Add it to the front, so that later devices can "override" * earlier defaults */ list_add(&misc->list, &misc_list); out: mutex_unlock(&misc_mtx); return err; } EXPORT_SYMBOL(misc_register); /** * misc_deregister - unregister a miscellaneous device * @misc: device to unregister * * Unregister a miscellaneous device that was previously * successfully registered with misc_register(). */ void misc_deregister(struct miscdevice *misc) { if (WARN_ON(list_empty(&misc->list))) return; mutex_lock(&misc_mtx); list_del(&misc->list); device_destroy(&misc_class, MKDEV(MISC_MAJOR, misc->minor)); misc_minor_free(misc->minor); mutex_unlock(&misc_mtx); } EXPORT_SYMBOL(misc_deregister); static int __init misc_init(void) { int err; struct proc_dir_entry *ret; ret = proc_create_seq("misc", 0, NULL, &misc_seq_ops); err = class_register(&misc_class); if (err) goto fail_remove; err = -EIO; if (register_chrdev(MISC_MAJOR, "misc", &misc_fops)) goto fail_printk; return 0; fail_printk: pr_err("unable to get major %d for misc devices\n", MISC_MAJOR); class_unregister(&misc_class); fail_remove: if (ret) remove_proc_entry("misc", NULL); return err; } subsys_initcall(misc_init); |
| 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 | /* * 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"); 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; 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) { int ret = 1; mutex_lock(&file->mutex); 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); wake_up_interruptible(&file->recv_wait); ret = 0; break; } 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)) 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)) 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); 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); 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); |
| 7 7 1 1 3 2 3 4 2 2 2 4 2 2 2 1 1 1 4 3 4 17 16 16 15 15 14 14 16 9 8 7 7 1 6 6 2 1 16 15 10 9 9 6 1 6 16 2 1 1 1 1 3 2 2 2 2 1 3 2 2 3 2 2 75 5 5 5 3 2 6 6 5 5 5 1 2 2 2 1 8 8 7 7 3 7 3 1 6 5 4 3 2 2 2 2 2 2 2 74 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 | // SPDX-License-Identifier: GPL-2.0-only /* * VMware VMCI Driver * * Copyright (C) 2012 VMware, Inc. All rights reserved. */ #include <linux/vmw_vmci_defs.h> #include <linux/vmw_vmci_api.h> #include <linux/miscdevice.h> #include <linux/interrupt.h> #include <linux/highmem.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/pci.h> #include <linux/smp.h> #include <linux/fs.h> #include <linux/io.h> #include "vmci_handle_array.h" #include "vmci_queue_pair.h" #include "vmci_datagram.h" #include "vmci_doorbell.h" #include "vmci_resource.h" #include "vmci_context.h" #include "vmci_driver.h" #include "vmci_event.h" #define VMCI_UTIL_NUM_RESOURCES 1 enum { VMCI_NOTIFY_RESOURCE_QUEUE_PAIR = 0, VMCI_NOTIFY_RESOURCE_DOOR_BELL = 1, }; enum { VMCI_NOTIFY_RESOURCE_ACTION_NOTIFY = 0, VMCI_NOTIFY_RESOURCE_ACTION_CREATE = 1, VMCI_NOTIFY_RESOURCE_ACTION_DESTROY = 2, }; /* * VMCI driver initialization. This block can also be used to * pass initial group membership etc. */ struct vmci_init_blk { u32 cid; u32 flags; }; /* VMCIqueue_pairAllocInfo_VMToVM */ struct vmci_qp_alloc_info_vmvm { struct vmci_handle handle; u32 peer; u32 flags; u64 produce_size; u64 consume_size; u64 produce_page_file; /* User VA. */ u64 consume_page_file; /* User VA. */ u64 produce_page_file_size; /* Size of the file name array. */ u64 consume_page_file_size; /* Size of the file name array. */ s32 result; u32 _pad; }; /* VMCISetNotifyInfo: Used to pass notify flag's address to the host driver. */ struct vmci_set_notify_info { u64 notify_uva; s32 result; u32 _pad; }; /* * Per-instance host state */ struct vmci_host_dev { struct vmci_ctx *context; int user_version; enum vmci_obj_type ct_type; struct mutex lock; /* Mutex lock for vmci context access */ }; static struct vmci_ctx *host_context; static bool vmci_host_device_initialized; static atomic_t vmci_host_active_users = ATOMIC_INIT(0); /* * Determines whether the VMCI host personality is * available. Since the core functionality of the host driver is * always present, all guests could possibly use the host * personality. However, to minimize the deviation from the * pre-unified driver state of affairs, we only consider the host * device active if there is no active guest device or if there * are VMX'en with active VMCI contexts using the host device. */ bool vmci_host_code_active(void) { return vmci_host_device_initialized && (!vmci_guest_code_active() || atomic_read(&vmci_host_active_users) > 0); } int vmci_host_users(void) { return atomic_read(&vmci_host_active_users); } /* * Called on open of /dev/vmci. */ static int vmci_host_open(struct inode *inode, struct file *filp) { struct vmci_host_dev *vmci_host_dev; vmci_host_dev = kzalloc(sizeof(struct vmci_host_dev), GFP_KERNEL); if (vmci_host_dev == NULL) return -ENOMEM; vmci_host_dev->ct_type = VMCIOBJ_NOT_SET; mutex_init(&vmci_host_dev->lock); filp->private_data = vmci_host_dev; return 0; } /* * Called on close of /dev/vmci, most often when the process * exits. */ static int vmci_host_close(struct inode *inode, struct file *filp) { struct vmci_host_dev *vmci_host_dev = filp->private_data; if (vmci_host_dev->ct_type == VMCIOBJ_CONTEXT) { vmci_ctx_destroy(vmci_host_dev->context); vmci_host_dev->context = NULL; /* * The number of active contexts is used to track whether any * VMX'en are using the host personality. It is incremented when * a context is created through the IOCTL_VMCI_INIT_CONTEXT * ioctl. */ atomic_dec(&vmci_host_active_users); } vmci_host_dev->ct_type = VMCIOBJ_NOT_SET; kfree(vmci_host_dev); filp->private_data = NULL; return 0; } /* * This is used to wake up the VMX when a VMCI call arrives, or * to wake up select() or poll() at the next clock tick. */ static __poll_t vmci_host_poll(struct file *filp, poll_table *wait) { struct vmci_host_dev *vmci_host_dev = filp->private_data; struct vmci_ctx *context; __poll_t mask = 0; if (vmci_host_dev->ct_type == VMCIOBJ_CONTEXT) { /* * Read context only if ct_type == VMCIOBJ_CONTEXT to make * sure that context is initialized */ context = vmci_host_dev->context; /* Check for VMCI calls to this VM context. */ if (wait) poll_wait(filp, &context->host_context.wait_queue, wait); spin_lock(&context->lock); if (context->pending_datagrams > 0 || vmci_handle_arr_get_size( context->pending_doorbell_array) > 0) { mask = EPOLLIN; } spin_unlock(&context->lock); } return mask; } /* * Copies the handles of a handle array into a user buffer, and * returns the new length in userBufferSize. If the copy to the * user buffer fails, the functions still returns VMCI_SUCCESS, * but retval != 0. */ static int drv_cp_harray_to_user(void __user *user_buf_uva, u64 *user_buf_size, struct vmci_handle_arr *handle_array, int *retval) { u32 array_size = 0; struct vmci_handle *handles; if (handle_array) array_size = vmci_handle_arr_get_size(handle_array); if (array_size * sizeof(*handles) > *user_buf_size) return VMCI_ERROR_MORE_DATA; *user_buf_size = array_size * sizeof(*handles); if (*user_buf_size) *retval = copy_to_user(user_buf_uva, vmci_handle_arr_get_handles (handle_array), *user_buf_size); return VMCI_SUCCESS; } /* * Sets up a given context for notify to work. Maps the notify * boolean in user VA into kernel space. */ static int vmci_host_setup_notify(struct vmci_ctx *context, unsigned long uva) { int retval; if (context->notify_page) { pr_devel("%s: Notify mechanism is already set up\n", __func__); return VMCI_ERROR_DUPLICATE_ENTRY; } /* * We are using 'bool' internally, but let's make sure we explicit * about the size. */ BUILD_BUG_ON(sizeof(bool) != sizeof(u8)); /* * Lock physical page backing a given user VA. */ retval = get_user_pages_fast(uva, 1, FOLL_WRITE, &context->notify_page); if (retval != 1) { context->notify_page = NULL; return VMCI_ERROR_GENERIC; } if (context->notify_page == NULL) return VMCI_ERROR_UNAVAILABLE; /* * Map the locked page and set up notify pointer. */ context->notify = kmap(context->notify_page) + (uva & (PAGE_SIZE - 1)); vmci_ctx_check_signal_notify(context); return VMCI_SUCCESS; } static int vmci_host_get_version(struct vmci_host_dev *vmci_host_dev, unsigned int cmd, void __user *uptr) { if (cmd == IOCTL_VMCI_VERSION2) { int __user *vptr = uptr; if (get_user(vmci_host_dev->user_version, vptr)) return -EFAULT; } /* * The basic logic here is: * * If the user sends in a version of 0 tell it our version. * If the user didn't send in a version, tell it our version. * If the user sent in an old version, tell it -its- version. * If the user sent in an newer version, tell it our version. * * The rationale behind telling the caller its version is that * Workstation 6.5 required that VMX and VMCI kernel module were * version sync'd. All new VMX users will be programmed to * handle the VMCI kernel module version. */ if (vmci_host_dev->user_version > 0 && vmci_host_dev->user_version < VMCI_VERSION_HOSTQP) { return vmci_host_dev->user_version; } return VMCI_VERSION; } #define vmci_ioctl_err(fmt, ...) \ pr_devel("%s: " fmt, ioctl_name, ##__VA_ARGS__) static int vmci_host_do_init_context(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_init_blk init_block; const struct cred *cred; int retval; if (copy_from_user(&init_block, uptr, sizeof(init_block))) { vmci_ioctl_err("error reading init block\n"); return -EFAULT; } mutex_lock(&vmci_host_dev->lock); if (vmci_host_dev->ct_type != VMCIOBJ_NOT_SET) { vmci_ioctl_err("received VMCI init on initialized handle\n"); retval = -EINVAL; goto out; } if (init_block.flags & ~VMCI_PRIVILEGE_FLAG_RESTRICTED) { vmci_ioctl_err("unsupported VMCI restriction flag\n"); retval = -EINVAL; goto out; } cred = get_current_cred(); vmci_host_dev->context = vmci_ctx_create(init_block.cid, init_block.flags, 0, vmci_host_dev->user_version, cred); put_cred(cred); if (IS_ERR(vmci_host_dev->context)) { retval = PTR_ERR(vmci_host_dev->context); vmci_ioctl_err("error initializing context\n"); goto out; } /* * Copy cid to userlevel, we do this to allow the VMX * to enforce its policy on cid generation. */ init_block.cid = vmci_ctx_get_id(vmci_host_dev->context); if (copy_to_user(uptr, &init_block, sizeof(init_block))) { vmci_ctx_destroy(vmci_host_dev->context); vmci_host_dev->context = NULL; vmci_ioctl_err("error writing init block\n"); retval = -EFAULT; goto out; } vmci_host_dev->ct_type = VMCIOBJ_CONTEXT; atomic_inc(&vmci_host_active_users); vmci_call_vsock_callback(true); retval = 0; out: mutex_unlock(&vmci_host_dev->lock); return retval; } static int vmci_host_do_send_datagram(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_datagram_snd_rcv_info send_info; struct vmci_datagram *dg = NULL; u32 cid; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&send_info, uptr, sizeof(send_info))) return -EFAULT; if (send_info.len > VMCI_MAX_DG_SIZE) { vmci_ioctl_err("datagram is too big (size=%d)\n", send_info.len); return -EINVAL; } if (send_info.len < sizeof(*dg)) { vmci_ioctl_err("datagram is too small (size=%d)\n", send_info.len); return -EINVAL; } dg = memdup_user((void __user *)(uintptr_t)send_info.addr, send_info.len); if (IS_ERR(dg)) { vmci_ioctl_err( "cannot allocate memory to dispatch datagram\n"); return PTR_ERR(dg); } if (VMCI_DG_SIZE(dg) != send_info.len) { vmci_ioctl_err("datagram size mismatch\n"); kfree(dg); return -EINVAL; } pr_devel("Datagram dst (handle=0x%x:0x%x) src (handle=0x%x:0x%x), payload (size=%llu bytes)\n", dg->dst.context, dg->dst.resource, dg->src.context, dg->src.resource, (unsigned long long)dg->payload_size); /* Get source context id. */ cid = vmci_ctx_get_id(vmci_host_dev->context); send_info.result = vmci_datagram_dispatch(cid, dg, true); kfree(dg); return copy_to_user(uptr, &send_info, sizeof(send_info)) ? -EFAULT : 0; } static int vmci_host_do_receive_datagram(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_datagram_snd_rcv_info recv_info; struct vmci_datagram *dg = NULL; int retval; size_t size; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&recv_info, uptr, sizeof(recv_info))) return -EFAULT; size = recv_info.len; recv_info.result = vmci_ctx_dequeue_datagram(vmci_host_dev->context, &size, &dg); if (recv_info.result >= VMCI_SUCCESS) { void __user *ubuf = (void __user *)(uintptr_t)recv_info.addr; retval = copy_to_user(ubuf, dg, VMCI_DG_SIZE(dg)); kfree(dg); if (retval != 0) return -EFAULT; } return copy_to_user(uptr, &recv_info, sizeof(recv_info)) ? -EFAULT : 0; } static int vmci_host_do_alloc_queuepair(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_handle handle; int vmci_status; int __user *retptr; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (vmci_host_dev->user_version < VMCI_VERSION_NOVMVM) { struct vmci_qp_alloc_info_vmvm alloc_info; struct vmci_qp_alloc_info_vmvm __user *info = uptr; if (copy_from_user(&alloc_info, uptr, sizeof(alloc_info))) return -EFAULT; handle = alloc_info.handle; retptr = &info->result; vmci_status = vmci_qp_broker_alloc(alloc_info.handle, alloc_info.peer, alloc_info.flags, VMCI_NO_PRIVILEGE_FLAGS, alloc_info.produce_size, alloc_info.consume_size, NULL, vmci_host_dev->context); if (vmci_status == VMCI_SUCCESS) vmci_status = VMCI_SUCCESS_QUEUEPAIR_CREATE; } else { struct vmci_qp_alloc_info alloc_info; struct vmci_qp_alloc_info __user *info = uptr; struct vmci_qp_page_store page_store; if (copy_from_user(&alloc_info, uptr, sizeof(alloc_info))) return -EFAULT; handle = alloc_info.handle; retptr = &info->result; page_store.pages = alloc_info.ppn_va; page_store.len = alloc_info.num_ppns; vmci_status = vmci_qp_broker_alloc(alloc_info.handle, alloc_info.peer, alloc_info.flags, VMCI_NO_PRIVILEGE_FLAGS, alloc_info.produce_size, alloc_info.consume_size, &page_store, vmci_host_dev->context); } if (put_user(vmci_status, retptr)) { if (vmci_status >= VMCI_SUCCESS) { vmci_status = vmci_qp_broker_detach(handle, vmci_host_dev->context); } return -EFAULT; } return 0; } static int vmci_host_do_queuepair_setva(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_qp_set_va_info set_va_info; struct vmci_qp_set_va_info __user *info = uptr; s32 result; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (vmci_host_dev->user_version < VMCI_VERSION_NOVMVM) { vmci_ioctl_err("is not allowed\n"); return -EINVAL; } if (copy_from_user(&set_va_info, uptr, sizeof(set_va_info))) return -EFAULT; if (set_va_info.va) { /* * VMX is passing down a new VA for the queue * pair mapping. */ result = vmci_qp_broker_map(set_va_info.handle, vmci_host_dev->context, set_va_info.va); } else { /* * The queue pair is about to be unmapped by * the VMX. */ result = vmci_qp_broker_unmap(set_va_info.handle, vmci_host_dev->context, 0); } return put_user(result, &info->result) ? -EFAULT : 0; } static int vmci_host_do_queuepair_setpf(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_qp_page_file_info page_file_info; struct vmci_qp_page_file_info __user *info = uptr; s32 result; if (vmci_host_dev->user_version < VMCI_VERSION_HOSTQP || vmci_host_dev->user_version >= VMCI_VERSION_NOVMVM) { vmci_ioctl_err("not supported on this VMX (version=%d)\n", vmci_host_dev->user_version); return -EINVAL; } if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&page_file_info, uptr, sizeof(*info))) return -EFAULT; /* * Communicate success pre-emptively to the caller. Note that the * basic premise is that it is incumbent upon the caller not to look at * the info.result field until after the ioctl() returns. And then, * only if the ioctl() result indicates no error. We send up the * SUCCESS status before calling SetPageStore() store because failing * to copy up the result code means unwinding the SetPageStore(). * * It turns out the logic to unwind a SetPageStore() opens a can of * worms. For example, if a host had created the queue_pair and a * guest attaches and SetPageStore() is successful but writing success * fails, then ... the host has to be stopped from writing (anymore) * data into the queue_pair. That means an additional test in the * VMCI_Enqueue() code path. Ugh. */ if (put_user(VMCI_SUCCESS, &info->result)) { /* * In this case, we can't write a result field of the * caller's info block. So, we don't even try to * SetPageStore(). */ return -EFAULT; } result = vmci_qp_broker_set_page_store(page_file_info.handle, page_file_info.produce_va, page_file_info.consume_va, vmci_host_dev->context); if (result < VMCI_SUCCESS) { if (put_user(result, &info->result)) { /* * Note that in this case the SetPageStore() * call failed but we were unable to * communicate that to the caller (because the * copy_to_user() call failed). So, if we * simply return an error (in this case * -EFAULT) then the caller will know that the * SetPageStore failed even though we couldn't * put the result code in the result field and * indicate exactly why it failed. * * That says nothing about the issue where we * were once able to write to the caller's info * memory and now can't. Something more * serious is probably going on than the fact * that SetPageStore() didn't work. */ return -EFAULT; } } return 0; } static int vmci_host_do_qp_detach(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_qp_dtch_info detach_info; struct vmci_qp_dtch_info __user *info = uptr; s32 result; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&detach_info, uptr, sizeof(detach_info))) return -EFAULT; result = vmci_qp_broker_detach(detach_info.handle, vmci_host_dev->context); if (result == VMCI_SUCCESS && vmci_host_dev->user_version < VMCI_VERSION_NOVMVM) { result = VMCI_SUCCESS_LAST_DETACH; } return put_user(result, &info->result) ? -EFAULT : 0; } static int vmci_host_do_ctx_add_notify(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_ctx_info ar_info; struct vmci_ctx_info __user *info = uptr; s32 result; u32 cid; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&ar_info, uptr, sizeof(ar_info))) return -EFAULT; cid = vmci_ctx_get_id(vmci_host_dev->context); result = vmci_ctx_add_notification(cid, ar_info.remote_cid); return put_user(result, &info->result) ? -EFAULT : 0; } static int vmci_host_do_ctx_remove_notify(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_ctx_info ar_info; struct vmci_ctx_info __user *info = uptr; u32 cid; int result; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&ar_info, uptr, sizeof(ar_info))) return -EFAULT; cid = vmci_ctx_get_id(vmci_host_dev->context); result = vmci_ctx_remove_notification(cid, ar_info.remote_cid); return put_user(result, &info->result) ? -EFAULT : 0; } static int vmci_host_do_ctx_get_cpt_state(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_ctx_chkpt_buf_info get_info; u32 cid; void *cpt_buf; int retval; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&get_info, uptr, sizeof(get_info))) return -EFAULT; cid = vmci_ctx_get_id(vmci_host_dev->context); get_info.result = vmci_ctx_get_chkpt_state(cid, get_info.cpt_type, &get_info.buf_size, &cpt_buf); if (get_info.result == VMCI_SUCCESS && get_info.buf_size) { void __user *ubuf = (void __user *)(uintptr_t)get_info.cpt_buf; retval = copy_to_user(ubuf, cpt_buf, get_info.buf_size); kfree(cpt_buf); if (retval) return -EFAULT; } return copy_to_user(uptr, &get_info, sizeof(get_info)) ? -EFAULT : 0; } static int vmci_host_do_ctx_set_cpt_state(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_ctx_chkpt_buf_info set_info; u32 cid; void *cpt_buf; int retval; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&set_info, uptr, sizeof(set_info))) return -EFAULT; cpt_buf = memdup_user((void __user *)(uintptr_t)set_info.cpt_buf, set_info.buf_size); if (IS_ERR(cpt_buf)) return PTR_ERR(cpt_buf); cid = vmci_ctx_get_id(vmci_host_dev->context); set_info.result = vmci_ctx_set_chkpt_state(cid, set_info.cpt_type, set_info.buf_size, cpt_buf); retval = copy_to_user(uptr, &set_info, sizeof(set_info)) ? -EFAULT : 0; kfree(cpt_buf); return retval; } static int vmci_host_do_get_context_id(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { u32 __user *u32ptr = uptr; return put_user(VMCI_HOST_CONTEXT_ID, u32ptr) ? -EFAULT : 0; } static int vmci_host_do_set_notify(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_set_notify_info notify_info; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(¬ify_info, uptr, sizeof(notify_info))) return -EFAULT; if (notify_info.notify_uva) { notify_info.result = vmci_host_setup_notify(vmci_host_dev->context, notify_info.notify_uva); } else { vmci_ctx_unset_notify(vmci_host_dev->context); notify_info.result = VMCI_SUCCESS; } return copy_to_user(uptr, ¬ify_info, sizeof(notify_info)) ? -EFAULT : 0; } static int vmci_host_do_notify_resource(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_dbell_notify_resource_info info; u32 cid; if (vmci_host_dev->user_version < VMCI_VERSION_NOTIFY) { vmci_ioctl_err("invalid for current VMX versions\n"); return -EINVAL; } if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&info, uptr, sizeof(info))) return -EFAULT; cid = vmci_ctx_get_id(vmci_host_dev->context); switch (info.action) { case VMCI_NOTIFY_RESOURCE_ACTION_NOTIFY: if (info.resource == VMCI_NOTIFY_RESOURCE_DOOR_BELL) { u32 flags = VMCI_NO_PRIVILEGE_FLAGS; info.result = vmci_ctx_notify_dbell(cid, info.handle, flags); } else { info.result = VMCI_ERROR_UNAVAILABLE; } break; case VMCI_NOTIFY_RESOURCE_ACTION_CREATE: info.result = vmci_ctx_dbell_create(cid, info.handle); break; case VMCI_NOTIFY_RESOURCE_ACTION_DESTROY: info.result = vmci_ctx_dbell_destroy(cid, info.handle); break; default: vmci_ioctl_err("got unknown action (action=%d)\n", info.action); info.result = VMCI_ERROR_INVALID_ARGS; } return copy_to_user(uptr, &info, sizeof(info)) ? -EFAULT : 0; } static int vmci_host_do_recv_notifications(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_ctx_notify_recv_info info; struct vmci_handle_arr *db_handle_array; struct vmci_handle_arr *qp_handle_array; void __user *ubuf; u32 cid; int retval = 0; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (vmci_host_dev->user_version < VMCI_VERSION_NOTIFY) { vmci_ioctl_err("not supported for the current vmx version\n"); return -EINVAL; } if (copy_from_user(&info, uptr, sizeof(info))) return -EFAULT; if ((info.db_handle_buf_size && !info.db_handle_buf_uva) || (info.qp_handle_buf_size && !info.qp_handle_buf_uva)) { return -EINVAL; } cid = vmci_ctx_get_id(vmci_host_dev->context); info.result = vmci_ctx_rcv_notifications_get(cid, &db_handle_array, &qp_handle_array); if (info.result != VMCI_SUCCESS) return copy_to_user(uptr, &info, sizeof(info)) ? -EFAULT : 0; ubuf = (void __user *)(uintptr_t)info.db_handle_buf_uva; info.result = drv_cp_harray_to_user(ubuf, &info.db_handle_buf_size, db_handle_array, &retval); if (info.result == VMCI_SUCCESS && !retval) { ubuf = (void __user *)(uintptr_t)info.qp_handle_buf_uva; info.result = drv_cp_harray_to_user(ubuf, &info.qp_handle_buf_size, qp_handle_array, &retval); } if (!retval && copy_to_user(uptr, &info, sizeof(info))) retval = -EFAULT; vmci_ctx_rcv_notifications_release(cid, db_handle_array, qp_handle_array, info.result == VMCI_SUCCESS && !retval); return retval; } static long vmci_host_unlocked_ioctl(struct file *filp, unsigned int iocmd, unsigned long ioarg) { #define VMCI_DO_IOCTL(ioctl_name, ioctl_fn) do { \ char *name = "IOCTL_VMCI_" # ioctl_name; \ return vmci_host_do_ ## ioctl_fn( \ vmci_host_dev, name, uptr); \ } while (0) struct vmci_host_dev *vmci_host_dev = filp->private_data; void __user *uptr = (void __user *)ioarg; switch (iocmd) { case IOCTL_VMCI_INIT_CONTEXT: VMCI_DO_IOCTL(INIT_CONTEXT, init_context); case IOCTL_VMCI_DATAGRAM_SEND: VMCI_DO_IOCTL(DATAGRAM_SEND, send_datagram); case IOCTL_VMCI_DATAGRAM_RECEIVE: VMCI_DO_IOCTL(DATAGRAM_RECEIVE, receive_datagram); case IOCTL_VMCI_QUEUEPAIR_ALLOC: VMCI_DO_IOCTL(QUEUEPAIR_ALLOC, alloc_queuepair); case IOCTL_VMCI_QUEUEPAIR_SETVA: VMCI_DO_IOCTL(QUEUEPAIR_SETVA, queuepair_setva); case IOCTL_VMCI_QUEUEPAIR_SETPAGEFILE: VMCI_DO_IOCTL(QUEUEPAIR_SETPAGEFILE, queuepair_setpf); case IOCTL_VMCI_QUEUEPAIR_DETACH: VMCI_DO_IOCTL(QUEUEPAIR_DETACH, qp_detach); case IOCTL_VMCI_CTX_ADD_NOTIFICATION: VMCI_DO_IOCTL(CTX_ADD_NOTIFICATION, ctx_add_notify); case IOCTL_VMCI_CTX_REMOVE_NOTIFICATION: VMCI_DO_IOCTL(CTX_REMOVE_NOTIFICATION, ctx_remove_notify); case IOCTL_VMCI_CTX_GET_CPT_STATE: VMCI_DO_IOCTL(CTX_GET_CPT_STATE, ctx_get_cpt_state); case IOCTL_VMCI_CTX_SET_CPT_STATE: VMCI_DO_IOCTL(CTX_SET_CPT_STATE, ctx_set_cpt_state); case IOCTL_VMCI_GET_CONTEXT_ID: VMCI_DO_IOCTL(GET_CONTEXT_ID, get_context_id); case IOCTL_VMCI_SET_NOTIFY: VMCI_DO_IOCTL(SET_NOTIFY, set_notify); case IOCTL_VMCI_NOTIFY_RESOURCE: VMCI_DO_IOCTL(NOTIFY_RESOURCE, notify_resource); case IOCTL_VMCI_NOTIFICATIONS_RECEIVE: VMCI_DO_IOCTL(NOTIFICATIONS_RECEIVE, recv_notifications); case IOCTL_VMCI_VERSION: case IOCTL_VMCI_VERSION2: return vmci_host_get_version(vmci_host_dev, iocmd, uptr); default: pr_devel("%s: Unknown ioctl (iocmd=%d)\n", __func__, iocmd); return -EINVAL; } #undef VMCI_DO_IOCTL } static const struct file_operations vmuser_fops = { .owner = THIS_MODULE, .open = vmci_host_open, .release = vmci_host_close, .poll = vmci_host_poll, .unlocked_ioctl = vmci_host_unlocked_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static struct miscdevice vmci_host_miscdev = { .name = "vmci", .minor = MISC_DYNAMIC_MINOR, .fops = &vmuser_fops, }; int __init vmci_host_init(void) { int error; host_context = vmci_ctx_create(VMCI_HOST_CONTEXT_ID, VMCI_DEFAULT_PROC_PRIVILEGE_FLAGS, -1, VMCI_VERSION, NULL); if (IS_ERR(host_context)) { error = PTR_ERR(host_context); pr_warn("Failed to initialize VMCIContext (error%d)\n", error); return error; } error = misc_register(&vmci_host_miscdev); if (error) { pr_warn("Module registration error (name=%s, major=%d, minor=%d, err=%d)\n", vmci_host_miscdev.name, MISC_MAJOR, vmci_host_miscdev.minor, error); pr_warn("Unable to initialize host personality\n"); vmci_ctx_destroy(host_context); return error; } pr_info("VMCI host device registered (name=%s, major=%d, minor=%d)\n", vmci_host_miscdev.name, MISC_MAJOR, vmci_host_miscdev.minor); vmci_host_device_initialized = true; return 0; } void __exit vmci_host_exit(void) { vmci_host_device_initialized = false; misc_deregister(&vmci_host_miscdev); vmci_ctx_destroy(host_context); vmci_qp_broker_exit(); pr_debug("VMCI host driver module unloaded\n"); } |
| 376 376 171 171 3858 126 51 3970 3972 3973 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 | /* 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) __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 |
| 147 147 147 62 62 85 147 142 127 15 142 1 356 355 147 142 142 140 137 59 32 78 52 84 83 193 47 36 47 46 1 3 2 2 3 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 | // SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/pagemap.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/statfs.h> #include <linux/magic.h> #include <linux/fscache.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include "v9fs.h" #include "v9fs_vfs.h" #include "fid.h" #include "xattr.h" #include "acl.h" static const struct super_operations v9fs_super_ops, v9fs_super_ops_dotl; /** * v9fs_set_super - set the superblock * @s: super block * @data: file system specific data * */ static int v9fs_set_super(struct super_block *s, void *data) { s->s_fs_info = data; return set_anon_super(s, data); } /** * v9fs_fill_super - populate superblock with info * @sb: superblock * @v9ses: session information * @flags: flags propagated from v9fs_mount() * */ static int v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, int flags) { int ret; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize_bits = fls(v9ses->maxdata - 1); sb->s_blocksize = 1 << sb->s_blocksize_bits; sb->s_magic = V9FS_MAGIC; if (v9fs_proto_dotl(v9ses)) { sb->s_op = &v9fs_super_ops_dotl; if (!(v9ses->flags & V9FS_NO_XATTR)) sb->s_xattr = v9fs_xattr_handlers; } else { sb->s_op = &v9fs_super_ops; sb->s_time_max = U32_MAX; } sb->s_time_min = 0; ret = super_setup_bdi(sb); if (ret) return ret; if (!v9ses->cache) { sb->s_bdi->ra_pages = 0; sb->s_bdi->io_pages = 0; } else { sb->s_bdi->ra_pages = v9ses->maxdata >> PAGE_SHIFT; sb->s_bdi->io_pages = v9ses->maxdata >> PAGE_SHIFT; } sb->s_flags |= SB_ACTIVE; #ifdef CONFIG_9P_FS_POSIX_ACL if ((v9ses->flags & V9FS_ACL_MASK) == V9FS_POSIX_ACL) sb->s_flags |= SB_POSIXACL; #endif return 0; } /** * v9fs_mount - mount a superblock * @fs_type: file system type * @flags: mount flags * @dev_name: device name that was mounted * @data: mount options * */ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { struct super_block *sb = NULL; struct inode *inode = NULL; struct dentry *root = NULL; struct v9fs_session_info *v9ses = NULL; umode_t mode = 0777 | S_ISVTX; struct p9_fid *fid; int retval = 0; p9_debug(P9_DEBUG_VFS, "\n"); v9ses = kzalloc(sizeof(struct v9fs_session_info), GFP_KERNEL); if (!v9ses) return ERR_PTR(-ENOMEM); fid = v9fs_session_init(v9ses, dev_name, data); if (IS_ERR(fid)) { retval = PTR_ERR(fid); goto free_session; } sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses); if (IS_ERR(sb)) { retval = PTR_ERR(sb); goto clunk_fid; } retval = v9fs_fill_super(sb, v9ses, flags); if (retval) goto release_sb; if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) sb->s_d_op = &v9fs_cached_dentry_operations; else sb->s_d_op = &v9fs_dentry_operations; inode = v9fs_get_inode(sb, S_IFDIR | mode, 0); if (IS_ERR(inode)) { retval = PTR_ERR(inode); goto release_sb; } root = d_make_root(inode); if (!root) { retval = -ENOMEM; goto release_sb; } sb->s_root = root; if (v9fs_proto_dotl(v9ses)) { struct p9_stat_dotl *st = NULL; st = p9_client_getattr_dotl(fid, P9_STATS_BASIC); if (IS_ERR(st)) { retval = PTR_ERR(st); goto release_sb; } d_inode(root)->i_ino = v9fs_qid2ino(&st->qid); v9fs_stat2inode_dotl(st, d_inode(root), 0); kfree(st); } else { struct p9_wstat *st = NULL; st = p9_client_stat(fid); if (IS_ERR(st)) { retval = PTR_ERR(st); goto release_sb; } d_inode(root)->i_ino = v9fs_qid2ino(&st->qid); v9fs_stat2inode(st, d_inode(root), sb, 0); p9stat_free(st); kfree(st); } retval = v9fs_get_acl(inode, fid); if (retval) goto release_sb; v9fs_fid_add(root, &fid); p9_debug(P9_DEBUG_VFS, " simple set mount, return 0\n"); return dget(sb->s_root); clunk_fid: p9_fid_put(fid); v9fs_session_close(v9ses); free_session: kfree(v9ses); return ERR_PTR(retval); release_sb: /* * we will do the session_close and root dentry release * in the below call. But we need to clunk fid, because we haven't * attached the fid to dentry so it won't get clunked * automatically. */ p9_fid_put(fid); deactivate_locked_super(sb); return ERR_PTR(retval); } /** * v9fs_kill_super - Kill Superblock * @s: superblock * */ static void v9fs_kill_super(struct super_block *s) { struct v9fs_session_info *v9ses = s->s_fs_info; p9_debug(P9_DEBUG_VFS, " %p\n", s); kill_anon_super(s); v9fs_session_cancel(v9ses); v9fs_session_close(v9ses); kfree(v9ses); s->s_fs_info = NULL; p9_debug(P9_DEBUG_VFS, "exiting kill_super\n"); } static void v9fs_umount_begin(struct super_block *sb) { struct v9fs_session_info *v9ses; v9ses = sb->s_fs_info; v9fs_session_begin_cancel(v9ses); } static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct v9fs_session_info *v9ses; struct p9_fid *fid; struct p9_rstatfs rs; int res; fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) { res = PTR_ERR(fid); goto done; } v9ses = v9fs_dentry2v9ses(dentry); if (v9fs_proto_dotl(v9ses)) { res = p9_client_statfs(fid, &rs); if (res == 0) { buf->f_type = rs.type; buf->f_bsize = rs.bsize; buf->f_blocks = rs.blocks; buf->f_bfree = rs.bfree; buf->f_bavail = rs.bavail; buf->f_files = rs.files; buf->f_ffree = rs.ffree; buf->f_fsid = u64_to_fsid(rs.fsid); buf->f_namelen = rs.namelen; } if (res != -ENOSYS) goto done; } res = simple_statfs(dentry, buf); done: p9_fid_put(fid); return res; } static int v9fs_drop_inode(struct inode *inode) { struct v9fs_session_info *v9ses; v9ses = v9fs_inode2v9ses(inode); if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) return generic_drop_inode(inode); /* * in case of non cached mode always drop the * inode because we want the inode attribute * to always match that on the server. */ return 1; } static int v9fs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct v9fs_inode *v9inode; /* * send an fsync request to server irrespective of * wbc->sync_mode. */ p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode); v9inode = V9FS_I(inode); fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode)); return 0; } static int v9fs_write_inode_dotl(struct inode *inode, struct writeback_control *wbc) { struct v9fs_inode *v9inode; v9inode = V9FS_I(inode); p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode); fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode)); return 0; } static const struct super_operations v9fs_super_ops = { .alloc_inode = v9fs_alloc_inode, .free_inode = v9fs_free_inode, .statfs = simple_statfs, .evict_inode = v9fs_evict_inode, .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, .write_inode = v9fs_write_inode, }; static const struct super_operations v9fs_super_ops_dotl = { .alloc_inode = v9fs_alloc_inode, .free_inode = v9fs_free_inode, .statfs = v9fs_statfs, .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, .write_inode = v9fs_write_inode_dotl, }; struct file_system_type v9fs_fs_type = { .name = "9p", .mount = v9fs_mount, .kill_sb = v9fs_kill_super, .owner = THIS_MODULE, .fs_flags = FS_RENAME_DOES_D_MOVE, }; MODULE_ALIAS_FS("9p"); |
| 8 2 6 9 8 2 7 7 6 6 9 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 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999 Jérôme de Vivie <devivie@info.enserb.u-bordeaux.fr> * (C) 1999 Hervé Eychenne <eychenne@info.enserb.u-bordeaux.fr> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/slab.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/interrupt.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_limit.h> struct xt_limit_priv { unsigned long prev; u32 credit; }; MODULE_LICENSE("GPL"); MODULE_AUTHOR("Herve Eychenne <rv@wallfire.org>"); MODULE_DESCRIPTION("Xtables: rate-limit match"); MODULE_ALIAS("ipt_limit"); MODULE_ALIAS("ip6t_limit"); /* The algorithm used is the Simple Token Bucket Filter (TBF) * see net/sched/sch_tbf.c in the linux source tree */ /* Rusty: This is my (non-mathematically-inclined) understanding of this algorithm. The `average rate' in jiffies becomes your initial amount of credit `credit' and the most credit you can ever have `credit_cap'. The `peak rate' becomes the cost of passing the test, `cost'. `prev' tracks the last packet hit: you gain one credit per jiffy. If you get credit balance more than this, the extra credit is discarded. Every time the match passes, you lose `cost' credits; if you don't have that many, the test fails. See Alexey's formal explanation in net/sched/sch_tbf.c. To get the maximum range, we multiply by this factor (ie. you get N credits per jiffy). We want to allow a rate as low as 1 per day (slowest userspace tool allows), which means CREDITS_PER_JIFFY*HZ*60*60*24 < 2^32. ie. */ #define MAX_CPJ (0xFFFFFFFF / (HZ*60*60*24)) /* Repeated shift and or gives us all 1s, final shift and add 1 gives * us the power of 2 below the theoretical max, so GCC simply does a * shift. */ #define _POW2_BELOW2(x) ((x)|((x)>>1)) #define _POW2_BELOW4(x) (_POW2_BELOW2(x)|_POW2_BELOW2((x)>>2)) #define _POW2_BELOW8(x) (_POW2_BELOW4(x)|_POW2_BELOW4((x)>>4)) #define _POW2_BELOW16(x) (_POW2_BELOW8(x)|_POW2_BELOW8((x)>>8)) #define _POW2_BELOW32(x) (_POW2_BELOW16(x)|_POW2_BELOW16((x)>>16)) #define POW2_BELOW32(x) ((_POW2_BELOW32(x)>>1) + 1) #define CREDITS_PER_JIFFY POW2_BELOW32(MAX_CPJ) static bool limit_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rateinfo *r = par->matchinfo; struct xt_limit_priv *priv = r->master; unsigned long now; u32 old_credit, new_credit, credit_increase = 0; bool ret; /* fastpath if there is nothing to update */ if ((READ_ONCE(priv->credit) < r->cost) && (READ_ONCE(priv->prev) == jiffies)) return false; do { now = jiffies; credit_increase += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY; old_credit = READ_ONCE(priv->credit); new_credit = old_credit; new_credit += credit_increase; if (new_credit > r->credit_cap) new_credit = r->credit_cap; if (new_credit >= r->cost) { ret = true; new_credit -= r->cost; } else { ret = false; } } while (cmpxchg(&priv->credit, old_credit, new_credit) != old_credit); return ret; } /* Precision saver. */ static u32 user2credits(u32 user) { /* If multiplying would overflow... */ if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) /* Divide first. */ return (user / XT_LIMIT_SCALE) * HZ * CREDITS_PER_JIFFY; return (user * HZ * CREDITS_PER_JIFFY) / XT_LIMIT_SCALE; } static int limit_mt_check(const struct xt_mtchk_param *par) { struct xt_rateinfo *r = par->matchinfo; struct xt_limit_priv *priv; /* Check for overflow. */ if (r->burst == 0 || user2credits(r->avg * r->burst) < user2credits(r->avg)) { pr_info_ratelimited("Overflow, try lower: %u/%u\n", r->avg, r->burst); return -ERANGE; } priv = kmalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) return -ENOMEM; /* For SMP, we only want to use one set of state. */ r->master = priv; /* User avg in seconds * XT_LIMIT_SCALE: convert to jiffies * 128. */ priv->prev = jiffies; priv->credit = user2credits(r->avg * r->burst); /* Credits full. */ if (r->cost == 0) { r->credit_cap = priv->credit; /* Credits full. */ r->cost = user2credits(r->avg); } return 0; } static void limit_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_rateinfo *info = par->matchinfo; kfree(info->master); } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_xt_rateinfo { u_int32_t avg; u_int32_t burst; compat_ulong_t prev; u_int32_t credit; u_int32_t credit_cap, cost; u_int32_t master; }; /* To keep the full "prev" timestamp, the upper 32 bits are stored in the * master pointer, which does not need to be preserved. */ static void limit_mt_compat_from_user(void *dst, const void *src) { const struct compat_xt_rateinfo *cm = src; struct xt_rateinfo m = { .avg = cm->avg, .burst = cm->burst, .prev = cm->prev | (unsigned long)cm->master << 32, .credit = cm->credit, .credit_cap = cm->credit_cap, .cost = cm->cost, }; memcpy(dst, &m, sizeof(m)); } static int limit_mt_compat_to_user(void __user *dst, const void *src) { const struct xt_rateinfo *m = src; struct compat_xt_rateinfo cm = { .avg = m->avg, .burst = m->burst, .prev = m->prev, .credit = m->credit, .credit_cap = m->credit_cap, .cost = m->cost, .master = m->prev >> 32, }; return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; } #endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ static struct xt_match limit_mt_reg __read_mostly = { .name = "limit", .revision = 0, .family = NFPROTO_UNSPEC, .match = limit_mt, .checkentry = limit_mt_check, .destroy = limit_mt_destroy, .matchsize = sizeof(struct xt_rateinfo), #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(struct compat_xt_rateinfo), .compat_from_user = limit_mt_compat_from_user, .compat_to_user = limit_mt_compat_to_user, #endif .usersize = offsetof(struct xt_rateinfo, prev), .me = THIS_MODULE, }; static int __init limit_mt_init(void) { return xt_register_match(&limit_mt_reg); } static void __exit limit_mt_exit(void) { xt_unregister_match(&limit_mt_reg); } module_init(limit_mt_init); module_exit(limit_mt_exit); |
| 5 5 5 21 19 19 5 14 13 4 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 | // SPDX-License-Identifier: GPL-2.0 /* * Implement the manual drop-all-pagecache function */ #include <linux/pagemap.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/writeback.h> #include <linux/sysctl.h> #include <linux/gfp.h> #include <linux/swap.h> #include "internal.h" /* A global variable is a bit ugly, but it keeps the code simple */ int sysctl_drop_caches; static void drop_pagecache_sb(struct super_block *sb, void *unused) { struct inode *inode, *toput_inode = NULL; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); /* * We must skip inodes in unusual state. We may also skip * inodes without pages but we deliberately won't in case * we need to reschedule to avoid softlockups. */ if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || (mapping_empty(inode->i_mapping) && !need_resched())) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); iput(toput_inode); } int drop_caches_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (ret) return ret; if (write) { static int stfu; if (sysctl_drop_caches & 1) { lru_add_drain_all(); iterate_supers(drop_pagecache_sb, NULL); count_vm_event(DROP_PAGECACHE); } if (sysctl_drop_caches & 2) { drop_slab(); count_vm_event(DROP_SLAB); } if (!stfu) { pr_info("%s (%d): drop_caches: %d\n", current->comm, task_pid_nr(current), sysctl_drop_caches); } stfu |= sysctl_drop_caches & 4; } return 0; } |
| 23763 23734 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_PAGE_EXT_H #define __LINUX_PAGE_EXT_H #include <linux/types.h> #include <linux/stacktrace.h> #include <linux/stackdepot.h> struct pglist_data; #ifdef CONFIG_PAGE_EXTENSION /** * struct page_ext_operations - per page_ext client operations * @offset: Offset to the client's data within page_ext. Offset is returned to * the client by page_ext_init. * @size: The size of the client data within page_ext. * @need: Function that returns true if client requires page_ext. * @init: (optional) Called to initialize client once page_exts are allocated. * @need_shared_flags: True when client is using shared page_ext->flags * field. * * Each Page Extension client must define page_ext_operations in * page_ext_ops array. */ struct page_ext_operations { size_t offset; size_t size; bool (*need)(void); void (*init)(void); bool need_shared_flags; }; /* * The page_ext_flags users must set need_shared_flags to true. */ enum page_ext_flags { PAGE_EXT_OWNER, PAGE_EXT_OWNER_ALLOCATED, #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, PAGE_EXT_IDLE, #endif }; /* * Page Extension can be considered as an extended mem_map. * A page_ext page is associated with every page descriptor. The * page_ext helps us add more information about the page. * All page_ext are allocated at boot or memory hotplug event, * then the page_ext for pfn always exists. */ struct page_ext { unsigned long flags; }; extern bool early_page_ext; extern unsigned long page_ext_size; extern void pgdat_page_ext_init(struct pglist_data *pgdat); static inline bool early_page_ext_enabled(void) { return early_page_ext; } #ifdef CONFIG_SPARSEMEM static inline void page_ext_init_flatmem(void) { } extern void page_ext_init(void); static inline void page_ext_init_flatmem_late(void) { } #else extern void page_ext_init_flatmem(void); extern void page_ext_init_flatmem_late(void); static inline void page_ext_init(void) { } #endif extern struct page_ext *page_ext_get(struct page *page); extern void page_ext_put(struct page_ext *page_ext); static inline void *page_ext_data(struct page_ext *page_ext, struct page_ext_operations *ops) { return (void *)(page_ext) + ops->offset; } static inline struct page_ext *page_ext_next(struct page_ext *curr) { void *next = curr; next += page_ext_size; return next; } #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; static inline bool early_page_ext_enabled(void) { return false; } static inline void pgdat_page_ext_init(struct pglist_data *pgdat) { } static inline void page_ext_init(void) { } static inline void page_ext_init_flatmem_late(void) { } static inline void page_ext_init_flatmem(void) { } static inline struct page_ext *page_ext_get(struct page *page) { return NULL; } static inline void page_ext_put(struct page_ext *page_ext) { } #endif /* CONFIG_PAGE_EXTENSION */ #endif /* __LINUX_PAGE_EXT_H */ |
| 3 3 3 3 3 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 | /* * linux/fs/nls/nls_iso8859-13.c * * Charset iso8859-13 translation tables. * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, /* 0x90*/ 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, /* 0xa0*/ 0x00a0, 0x201d, 0x00a2, 0x00a3, 0x00a4, 0x201e, 0x00a6, 0x00a7, 0x00d8, 0x00a9, 0x0156, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00c6, /* 0xb0*/ 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x201c, 0x00b5, 0x00b6, 0x00b7, 0x00f8, 0x00b9, 0x0157, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00e6, /* 0xc0*/ 0x0104, 0x012e, 0x0100, 0x0106, 0x00c4, 0x00c5, 0x0118, 0x0112, 0x010c, 0x00c9, 0x0179, 0x0116, 0x0122, 0x0136, 0x012a, 0x013b, /* 0xd0*/ 0x0160, 0x0143, 0x0145, 0x00d3, 0x014c, 0x00d5, 0x00d6, 0x00d7, 0x0172, 0x0141, 0x015a, 0x016a, 0x00dc, 0x017b, 0x017d, 0x00df, /* 0xe0*/ 0x0105, 0x012f, 0x0101, 0x0107, 0x00e4, 0x00e5, 0x0119, 0x0113, 0x010d, 0x00e9, 0x017a, 0x0117, 0x0123, 0x0137, 0x012b, 0x013c, /* 0xf0*/ 0x0161, 0x0144, 0x0146, 0x00f3, 0x014d, 0x00f5, 0x00f6, 0x00f7, 0x0173, 0x0142, 0x015b, 0x016b, 0x00fc, 0x017c, 0x017e, 0x2019, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0x00, 0xa2, 0xa3, 0xa4, 0x00, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0x00, 0xa9, 0x00, 0xab, 0xac, 0xad, 0xae, 0x00, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0x00, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0x00, 0xb9, 0x00, 0xbb, 0xbc, 0xbd, 0xbe, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0xc4, 0xc5, 0xaf, 0x00, /* 0xc0-0xc7 */ 0x00, 0xc9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0xd3, 0x00, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xa8, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0xdf, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0xe4, 0xe5, 0xbf, 0x00, /* 0xe0-0xe7 */ 0x00, 0xe9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0xf3, 0x00, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xb8, 0x00, 0x00, 0x00, 0xfc, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0xc2, 0xe2, 0x00, 0x00, 0xc0, 0xe0, 0xc3, 0xe3, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xc8, 0xe8, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0xc7, 0xe7, 0x00, 0x00, 0xcb, 0xeb, /* 0x10-0x17 */ 0xc6, 0xe6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0xcc, 0xec, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0xce, 0xee, 0x00, 0x00, 0xc1, 0xe1, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xcd, 0xed, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0xcf, 0xef, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0xd9, 0xf9, 0xd1, 0xf1, 0xd2, 0xf2, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0xd4, 0xf4, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xaa, 0xba, /* 0x50-0x57 */ 0x00, 0x00, 0xda, 0xfa, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0xd0, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0xdb, 0xfb, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0xd8, 0xf8, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0xca, 0xea, 0xdd, 0xfd, 0xde, 0xfe, 0x00, /* 0x78-0x7f */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0xff, 0x00, 0x00, 0xb4, 0xa1, 0xa5, 0x00, /* 0x18-0x1f */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xb1, 0xa2, 0xb3, 0xa4, 0xb5, 0xb6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xb9, 0xba, 0xbb, 0xbc, 0xad, 0xbe, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbf, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xc0-0xc7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xc8-0xcf */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xd7, /* 0xd0-0xd7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xa1, 0xb2, 0xa3, 0xb4, 0xa5, 0xa6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xa9, 0xaa, 0xab, 0xac, 0xbd, 0xae, 0xbd, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xe0-0xe7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xe8-0xef */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xf7, /* 0xf0-0xf7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "iso8859-13", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_iso8859_13(void) { return register_nls(&table); } static void __exit exit_nls_iso8859_13(void) { unregister_nls(&table); } module_init(init_nls_iso8859_13) module_exit(exit_nls_iso8859_13) MODULE_LICENSE("Dual BSD/GPL"); |
| 56 56 56 56 56 56 56 56 48 48 48 48 48 48 65 65 65 64 64 64 63 64 2 65 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/base/map.c * * (C) Copyright Al Viro 2002,2003 * * NOTE: data structure needs to be changed. It works, but for large dev_t * it will be too slow. It is isolated, though, so these changes will be * local to that file. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/kdev_t.h> #include <linux/kobject.h> #include <linux/kobj_map.h> struct kobj_map { struct probe { struct probe *next; dev_t dev; unsigned long range; struct module *owner; kobj_probe_t *get; int (*lock)(dev_t, void *); void *data; } *probes[255]; struct mutex *lock; }; int kobj_map(struct kobj_map *domain, dev_t dev, unsigned long range, struct module *module, kobj_probe_t *probe, int (*lock)(dev_t, void *), void *data) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *p; if (n > 255) n = 255; p = kmalloc_array(n, sizeof(struct probe), GFP_KERNEL); if (p == NULL) return -ENOMEM; for (i = 0; i < n; i++, p++) { p->owner = module; p->get = probe; p->lock = lock; p->dev = dev; p->range = range; p->data = data; } mutex_lock(domain->lock); for (i = 0, p -= n; i < n; i++, p++, index++) { struct probe **s = &domain->probes[index % 255]; while (*s && (*s)->range < range) s = &(*s)->next; p->next = *s; *s = p; } mutex_unlock(domain->lock); return 0; } void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *found = NULL; if (n > 255) n = 255; mutex_lock(domain->lock); for (i = 0; i < n; i++, index++) { struct probe **s; for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) { struct probe *p = *s; if (p->dev == dev && p->range == range) { *s = p->next; if (!found) found = p; break; } } } mutex_unlock(domain->lock); kfree(found); } struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index) { struct kobject *kobj; struct probe *p; unsigned long best = ~0UL; retry: mutex_lock(domain->lock); for (p = domain->probes[MAJOR(dev) % 255]; p; p = p->next) { struct kobject *(*probe)(dev_t, int *, void *); struct module *owner; void *data; if (p->dev > dev || p->dev + p->range - 1 < dev) continue; if (p->range - 1 >= best) break; if (!try_module_get(p->owner)) continue; owner = p->owner; data = p->data; probe = p->get; best = p->range - 1; *index = dev - p->dev; if (p->lock && p->lock(dev, data) < 0) { module_put(owner); continue; } mutex_unlock(domain->lock); kobj = probe(dev, index, data); /* Currently ->owner protects _only_ ->probe() itself. */ module_put(owner); if (kobj) return kobj; goto retry; } mutex_unlock(domain->lock); return NULL; } struct kobj_map *kobj_map_init(kobj_probe_t *base_probe, struct mutex *lock) { struct kobj_map *p = kmalloc(sizeof(struct kobj_map), GFP_KERNEL); struct probe *base = kzalloc(sizeof(*base), GFP_KERNEL); int i; if ((p == NULL) || (base == NULL)) { kfree(p); kfree(base); return NULL; } base->dev = 1; base->range = ~0; base->get = base_probe; for (i = 0; i < 255; i++) p->probes[i] = base; p->lock = lock; return p; } |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FS_CEPH_SUPER_H #define _FS_CEPH_SUPER_H #include <linux/ceph/ceph_debug.h> #include <asm/unaligned.h> #include <linux/backing-dev.h> #include <linux/completion.h> #include <linux/exportfs.h> #include <linux/fs.h> #include <linux/mempool.h> #include <linux/pagemap.h> #include <linux/wait.h> #include <linux/writeback.h> #include <linux/slab.h> #include <linux/posix_acl.h> #include <linux/refcount.h> #include <linux/security.h> #include <linux/netfs.h> #include <linux/fscache.h> #include <linux/hashtable.h> #include <linux/ceph/libceph.h> #include "crypto.h" /* large granularity for statfs utilization stats to facilitate * large volume sizes on 32-bit machines. */ #define CEPH_BLOCK_SHIFT 22 /* 4 MB */ #define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT) #define CEPH_4K_BLOCK_SHIFT 12 /* 4 KB */ #define CEPH_MOUNT_OPT_CLEANRECOVER (1<<1) /* auto reonnect (clean mode) after blocklisted */ #define CEPH_MOUNT_OPT_DIRSTAT (1<<4) /* `cat dirname` for stats */ #define CEPH_MOUNT_OPT_RBYTES (1<<5) /* dir st_bytes = rbytes */ #define CEPH_MOUNT_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */ #define CEPH_MOUNT_OPT_INO32 (1<<8) /* 32 bit inos */ #define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */ #define CEPH_MOUNT_OPT_FSCACHE (1<<10) /* use fscache */ #define CEPH_MOUNT_OPT_NOPOOLPERM (1<<11) /* no pool permission check */ #define CEPH_MOUNT_OPT_MOUNTWAIT (1<<12) /* mount waits if no mds is up */ #define CEPH_MOUNT_OPT_NOQUOTADF (1<<13) /* no root dir quota in statfs */ #define CEPH_MOUNT_OPT_NOCOPYFROM (1<<14) /* don't use RADOS 'copy-from' op */ #define CEPH_MOUNT_OPT_ASYNC_DIROPS (1<<15) /* allow async directory ops */ #define CEPH_MOUNT_OPT_NOPAGECACHE (1<<16) /* bypass pagecache altogether */ #define CEPH_MOUNT_OPT_SPARSEREAD (1<<17) /* always do sparse reads */ #define CEPH_MOUNT_OPT_DEFAULT \ (CEPH_MOUNT_OPT_DCACHE | \ CEPH_MOUNT_OPT_NOCOPYFROM | \ CEPH_MOUNT_OPT_ASYNC_DIROPS) #define ceph_set_mount_opt(fsc, opt) \ (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt #define ceph_clear_mount_opt(fsc, opt) \ (fsc)->mount_options->flags &= ~CEPH_MOUNT_OPT_##opt #define ceph_test_mount_opt(fsc, opt) \ (!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt)) /* max size of osd read request, limited by libceph */ #define CEPH_MAX_READ_SIZE CEPH_MSG_MAX_DATA_LEN /* osd has a configurable limitaion of max write size. * CEPH_MSG_MAX_DATA_LEN should be small enough. */ #define CEPH_MAX_WRITE_SIZE CEPH_MSG_MAX_DATA_LEN #define CEPH_RASIZE_DEFAULT (8192*1024) /* max readahead */ #define CEPH_MAX_READDIR_DEFAULT 1024 #define CEPH_MAX_READDIR_BYTES_DEFAULT (512*1024) #define CEPH_SNAPDIRNAME_DEFAULT ".snap" /* * Delay telling the MDS we no longer want caps, in case we reopen * the file. Delay a minimum amount of time, even if we send a cap * message for some other reason. Otherwise, take the oppotunity to * update the mds to avoid sending another message later. */ #define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */ #define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */ struct ceph_mount_options { unsigned int flags; unsigned int wsize; /* max write size */ unsigned int rsize; /* max read size */ unsigned int rasize; /* max readahead */ unsigned int congestion_kb; /* max writeback in flight */ unsigned int caps_wanted_delay_min, caps_wanted_delay_max; int caps_max; unsigned int max_readdir; /* max readdir result (entries) */ unsigned int max_readdir_bytes; /* max readdir result (bytes) */ bool new_dev_syntax; /* * everything above this point can be memcmp'd; everything below * is handled in compare_mount_options() */ char *snapdir_name; /* default ".snap" */ char *mds_namespace; /* default NULL */ char *server_path; /* default NULL (means "/") */ char *fscache_uniq; /* default NULL */ char *mon_addr; struct fscrypt_dummy_policy dummy_enc_policy; }; /* mount state */ enum { CEPH_MOUNT_MOUNTING, CEPH_MOUNT_MOUNTED, CEPH_MOUNT_UNMOUNTING, CEPH_MOUNT_UNMOUNTED, CEPH_MOUNT_SHUTDOWN, CEPH_MOUNT_RECOVER, CEPH_MOUNT_FENCE_IO, }; #define CEPH_ASYNC_CREATE_CONFLICT_BITS 8 struct ceph_fs_client { struct super_block *sb; struct list_head metric_wakeup; struct ceph_mount_options *mount_options; struct ceph_client *client; int mount_state; bool blocklisted; bool have_copy_from2; u32 filp_gen; loff_t max_file_size; struct ceph_mds_client *mdsc; atomic_long_t writeback_count; bool write_congested; struct workqueue_struct *inode_wq; struct workqueue_struct *cap_wq; DECLARE_HASHTABLE(async_unlink_conflict, CEPH_ASYNC_CREATE_CONFLICT_BITS); spinlock_t async_unlink_conflict_lock; #ifdef CONFIG_DEBUG_FS struct dentry *debugfs_dentry_lru, *debugfs_caps; struct dentry *debugfs_congestion_kb; struct dentry *debugfs_bdi; struct dentry *debugfs_mdsc, *debugfs_mdsmap; struct dentry *debugfs_status; struct dentry *debugfs_mds_sessions; struct dentry *debugfs_metrics_dir; #endif #ifdef CONFIG_CEPH_FSCACHE struct fscache_volume *fscache; #endif #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_dummy_policy fsc_dummy_enc_policy; #endif }; /* * File i/o capability. This tracks shared state with the metadata * server that allows us to cache or writeback attributes or to read * and write data. For any given inode, we should have one or more * capabilities, one issued by each metadata server, and our * cumulative access is the OR of all issued capabilities. * * Each cap is referenced by the inode's i_caps rbtree and by per-mds * session capability lists. */ struct ceph_cap { struct ceph_inode_info *ci; struct rb_node ci_node; /* per-ci cap tree */ struct ceph_mds_session *session; struct list_head session_caps; /* per-session caplist */ u64 cap_id; /* unique cap id (mds provided) */ union { /* in-use caps */ struct { int issued; /* latest, from the mds */ int implemented; /* implemented superset of issued (for revocation) */ int mds; /* mds index for this cap */ int mds_wanted; /* caps wanted from this mds */ }; /* caps to release */ struct { u64 cap_ino; int queue_release; }; }; u32 seq, issue_seq, mseq; u32 cap_gen; /* active/stale cycle */ unsigned long last_used; struct list_head caps_item; }; #define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */ #define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */ #define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */ struct ceph_cap_flush { u64 tid; int caps; bool wake; /* wake up flush waiters when finish ? */ bool is_capsnap; /* true means capsnap */ struct list_head g_list; // global struct list_head i_list; // per inode }; /* * Snapped cap state that is pending flush to mds. When a snapshot occurs, * we first complete any in-process sync writes and writeback any dirty * data before flushing the snapped state (tracked here) back to the MDS. */ struct ceph_cap_snap { refcount_t nref; struct list_head ci_item; struct ceph_cap_flush cap_flush; u64 follows; int issued, dirty; struct ceph_snap_context *context; umode_t mode; kuid_t uid; kgid_t gid; struct ceph_buffer *xattr_blob; u64 xattr_version; u64 size; u64 change_attr; struct timespec64 mtime, atime, ctime, btime; u64 time_warp_seq; u64 truncate_size; u32 truncate_seq; int writing; /* a sync write is still in progress */ int dirty_pages; /* dirty pages awaiting writeback */ bool inline_data; bool need_flush; }; static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap) { if (refcount_dec_and_test(&capsnap->nref)) { if (capsnap->xattr_blob) ceph_buffer_put(capsnap->xattr_blob); kmem_cache_free(ceph_cap_snap_cachep, capsnap); } } /* * The frag tree describes how a directory is fragmented, potentially across * multiple metadata servers. It is also used to indicate points where * metadata authority is delegated, and whether/where metadata is replicated. * * A _leaf_ frag will be present in the i_fragtree IFF there is * delegation info. That is, if mds >= 0 || ndist > 0. */ #define CEPH_MAX_DIRFRAG_REP 4 struct ceph_inode_frag { struct rb_node node; /* fragtree state */ u32 frag; int split_by; /* i.e. 2^(split_by) children */ /* delegation and replication info */ int mds; /* -1 if same authority as parent */ int ndist; /* >0 if replicated */ int dist[CEPH_MAX_DIRFRAG_REP]; }; /* * We cache inode xattrs as an encoded blob until they are first used, * at which point we parse them into an rbtree. */ struct ceph_inode_xattr { struct rb_node node; const char *name; int name_len; const char *val; int val_len; int dirty; int should_free_name; int should_free_val; }; /* * Ceph dentry state */ struct ceph_dentry_info { struct dentry *dentry; struct ceph_mds_session *lease_session; struct list_head lease_list; struct hlist_node hnode; unsigned long flags; int lease_shared_gen; u32 lease_gen; u32 lease_seq; unsigned long lease_renew_after, lease_renew_from; unsigned long time; u64 offset; }; #define CEPH_DENTRY_REFERENCED (1 << 0) #define CEPH_DENTRY_LEASE_LIST (1 << 1) #define CEPH_DENTRY_SHRINK_LIST (1 << 2) #define CEPH_DENTRY_PRIMARY_LINK (1 << 3) #define CEPH_DENTRY_ASYNC_UNLINK_BIT (4) #define CEPH_DENTRY_ASYNC_UNLINK (1 << CEPH_DENTRY_ASYNC_UNLINK_BIT) #define CEPH_DENTRY_ASYNC_CREATE_BIT (5) #define CEPH_DENTRY_ASYNC_CREATE (1 << CEPH_DENTRY_ASYNC_CREATE_BIT) struct ceph_inode_xattrs_info { /* * (still encoded) xattr blob. we avoid the overhead of parsing * this until someone actually calls getxattr, etc. * * blob->vec.iov_len == 4 implies there are no xattrs; blob == * NULL means we don't know. */ struct ceph_buffer *blob, *prealloc_blob; struct rb_root index; bool dirty; int count; int names_size; int vals_size; u64 version, index_version; }; /* * Ceph inode. */ struct ceph_inode_info { struct netfs_inode netfs; /* Netfslib context and vfs inode */ struct ceph_vino i_vino; /* ceph ino + snap */ spinlock_t i_ceph_lock; u64 i_version; u64 i_inline_version; u32 i_time_warp_seq; unsigned long i_ceph_flags; atomic64_t i_release_count; atomic64_t i_ordered_count; atomic64_t i_complete_seq[2]; struct ceph_dir_layout i_dir_layout; struct ceph_file_layout i_layout; struct ceph_file_layout i_cached_layout; // for async creates char *i_symlink; /* for dirs */ struct timespec64 i_rctime; u64 i_rbytes, i_rfiles, i_rsubdirs, i_rsnaps; u64 i_files, i_subdirs; /* quotas */ u64 i_max_bytes, i_max_files; s32 i_dir_pin; struct rb_root i_fragtree; int i_fragtree_nsplits; struct mutex i_fragtree_mutex; struct ceph_inode_xattrs_info i_xattrs; /* capabilities. protected _both_ by i_ceph_lock and cap->session's * s_mutex. */ struct rb_root i_caps; /* cap list */ struct ceph_cap *i_auth_cap; /* authoritative cap, if any */ unsigned i_dirty_caps, i_flushing_caps; /* mask of dirtied fields */ /* * Link to the auth cap's session's s_cap_dirty list. s_cap_dirty * is protected by the mdsc->cap_dirty_lock, but each individual item * is also protected by the inode's i_ceph_lock. Walking s_cap_dirty * requires the mdsc->cap_dirty_lock. List presence for an item can * be tested under the i_ceph_lock. Changing anything requires both. */ struct list_head i_dirty_item; /* * Link to session's s_cap_flushing list. Protected in a similar * fashion to i_dirty_item, but also by the s_mutex for changes. The * s_cap_flushing list can be walked while holding either the s_mutex * or msdc->cap_dirty_lock. List presence can also be checked while * holding the i_ceph_lock for this inode. */ struct list_head i_flushing_item; /* we need to track cap writeback on a per-cap-bit basis, to allow * overlapping, pipelined cap flushes to the mds. we can probably * reduce the tid to 8 bits if we're concerned about inode size. */ struct ceph_cap_flush *i_prealloc_cap_flush; struct list_head i_cap_flush_list; wait_queue_head_t i_cap_wq; /* threads waiting on a capability */ unsigned long i_hold_caps_max; /* jiffies */ struct list_head i_cap_delay_list; /* for delayed cap release to mds */ struct ceph_cap_reservation i_cap_migration_resv; struct list_head i_cap_snaps; /* snapped state pending flush to mds */ struct ceph_snap_context *i_head_snapc; /* set if wr_buffer_head > 0 or dirty|flushing caps */ unsigned i_snap_caps; /* cap bits for snapped files */ unsigned long i_last_rd; unsigned long i_last_wr; int i_nr_by_mode[CEPH_FILE_MODE_BITS]; /* open file counts */ struct mutex i_truncate_mutex; u32 i_truncate_seq; /* last truncate to smaller size */ u64 i_truncate_size; /* and the size we last truncated down to */ int i_truncate_pending; /* still need to call vmtruncate */ /* * For none fscrypt case it equals to i_truncate_size or it will * equals to fscrypt_file_size */ u64 i_truncate_pagecache_size; u64 i_max_size; /* max file size authorized by mds */ u64 i_reported_size; /* (max_)size reported to or requested of mds */ u64 i_wanted_max_size; /* offset we'd like to write too */ u64 i_requested_max_size; /* max_size we've requested */ /* held references to caps */ int i_pin_ref; int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref, i_fx_ref; int i_wrbuffer_ref, i_wrbuffer_ref_head; atomic_t i_filelock_ref; atomic_t i_shared_gen; /* increment each time we get FILE_SHARED */ u32 i_rdcache_gen; /* incremented each time we get FILE_CACHE. */ u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */ struct list_head i_unsafe_dirops; /* uncommitted mds dir ops */ struct list_head i_unsafe_iops; /* uncommitted mds inode ops */ spinlock_t i_unsafe_lock; union { struct ceph_snap_realm *i_snap_realm; /* snap realm (if caps) */ struct ceph_snapid_map *i_snapid_map; /* snapid -> dev_t */ }; struct list_head i_snap_realm_item; struct list_head i_snap_flush_item; struct timespec64 i_btime; struct timespec64 i_snap_btime; struct work_struct i_work; unsigned long i_work_mask; #ifdef CONFIG_FS_ENCRYPTION u32 fscrypt_auth_len; u32 fscrypt_file_len; u8 *fscrypt_auth; u8 *fscrypt_file; #endif }; struct ceph_netfs_request_data { int caps; /* * Maximum size of a file readahead request. * The fadvise could update the bdi's default ra_pages. */ unsigned int file_ra_pages; /* Set it if fadvise disables file readahead entirely */ bool file_ra_disabled; }; static inline struct ceph_inode_info * ceph_inode(const struct inode *inode) { return container_of(inode, struct ceph_inode_info, netfs.inode); } static inline struct ceph_fs_client * ceph_inode_to_fs_client(const struct inode *inode) { return (struct ceph_fs_client *)inode->i_sb->s_fs_info; } static inline struct ceph_fs_client * ceph_sb_to_fs_client(const struct super_block *sb) { return (struct ceph_fs_client *)sb->s_fs_info; } static inline struct ceph_mds_client * ceph_sb_to_mdsc(const struct super_block *sb) { return (struct ceph_mds_client *)ceph_sb_to_fs_client(sb)->mdsc; } static inline struct ceph_client * ceph_inode_to_client(const struct inode *inode) { return (struct ceph_client *)ceph_inode_to_fs_client(inode)->client; } static inline struct ceph_vino ceph_vino(const struct inode *inode) { return ceph_inode(inode)->i_vino; } static inline u32 ceph_ino_to_ino32(u64 vino) { u32 ino = vino & 0xffffffff; ino ^= vino >> 32; if (!ino) ino = 2; return ino; } /* * Inode numbers in cephfs are 64 bits, but inode->i_ino is 32-bits on * some arches. We generally do not use this value inside the ceph driver, but * we do want to set it to something, so that generic vfs code has an * appropriate value for tracepoints and the like. */ static inline ino_t ceph_vino_to_ino_t(struct ceph_vino vino) { if (sizeof(ino_t) == sizeof(u32)) return ceph_ino_to_ino32(vino.ino); return (ino_t)vino.ino; } /* for printf-style formatting */ #define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap static inline u64 ceph_ino(struct inode *inode) { return ceph_inode(inode)->i_vino.ino; } static inline u64 ceph_snap(struct inode *inode) { return ceph_inode(inode)->i_vino.snap; } /** * ceph_present_ino - format an inode number for presentation to userland * @sb: superblock where the inode lives * @ino: inode number to (possibly) convert * * If the user mounted with the ino32 option, then the 64-bit value needs * to be converted to something that can fit inside 32 bits. Note that * internal kernel code never uses this value, so this is entirely for * userland consumption. */ static inline u64 ceph_present_ino(struct super_block *sb, u64 ino) { if (unlikely(ceph_test_mount_opt(ceph_sb_to_fs_client(sb), INO32))) return ceph_ino_to_ino32(ino); return ino; } static inline u64 ceph_present_inode(struct inode *inode) { return ceph_present_ino(inode->i_sb, ceph_ino(inode)); } static inline int ceph_ino_compare(struct inode *inode, void *data) { struct ceph_vino *pvino = (struct ceph_vino *)data; struct ceph_inode_info *ci = ceph_inode(inode); return ci->i_vino.ino == pvino->ino && ci->i_vino.snap == pvino->snap; } /* * The MDS reserves a set of inodes for its own usage. These should never * be accessible by clients, and so the MDS has no reason to ever hand these * out. The range is CEPH_MDS_INO_MDSDIR_OFFSET..CEPH_INO_SYSTEM_BASE. * * These come from src/mds/mdstypes.h in the ceph sources. */ #define CEPH_MAX_MDS 0x100 #define CEPH_NUM_STRAY 10 #define CEPH_MDS_INO_MDSDIR_OFFSET (1 * CEPH_MAX_MDS) #define CEPH_MDS_INO_LOG_OFFSET (2 * CEPH_MAX_MDS) #define CEPH_INO_SYSTEM_BASE ((6*CEPH_MAX_MDS) + (CEPH_MAX_MDS * CEPH_NUM_STRAY)) static inline bool ceph_vino_is_reserved(const struct ceph_vino vino) { if (vino.ino >= CEPH_INO_SYSTEM_BASE || vino.ino < CEPH_MDS_INO_MDSDIR_OFFSET) return false; /* Don't warn on mdsdirs */ WARN_RATELIMIT(vino.ino >= CEPH_MDS_INO_LOG_OFFSET, "Attempt to access reserved inode number 0x%llx", vino.ino); return true; } static inline struct inode *ceph_find_inode(struct super_block *sb, struct ceph_vino vino) { if (ceph_vino_is_reserved(vino)) return NULL; /* * NB: The hashval will be run through the fs/inode.c hash function * anyway, so there is no need to squash the inode number down to * 32-bits first. Just use low-order bits on arches with 32-bit long. */ return ilookup5(sb, (unsigned long)vino.ino, ceph_ino_compare, &vino); } /* * Ceph inode. */ #define CEPH_I_DIR_ORDERED (1 << 0) /* dentries in dir are ordered */ #define CEPH_I_FLUSH (1 << 2) /* do not delay flush of dirty metadata */ #define CEPH_I_POOL_PERM (1 << 3) /* pool rd/wr bits are valid */ #define CEPH_I_POOL_RD (1 << 4) /* can read from pool */ #define CEPH_I_POOL_WR (1 << 5) /* can write to pool */ #define CEPH_I_SEC_INITED (1 << 6) /* security initialized */ #define CEPH_I_KICK_FLUSH (1 << 7) /* kick flushing caps */ #define CEPH_I_FLUSH_SNAPS (1 << 8) /* need flush snapss */ #define CEPH_I_ERROR_WRITE (1 << 9) /* have seen write errors */ #define CEPH_I_ERROR_FILELOCK (1 << 10) /* have seen file lock errors */ #define CEPH_I_ODIRECT (1 << 11) /* inode in direct I/O mode */ #define CEPH_ASYNC_CREATE_BIT (12) /* async create in flight for this */ #define CEPH_I_ASYNC_CREATE (1 << CEPH_ASYNC_CREATE_BIT) #define CEPH_I_SHUTDOWN (1 << 13) /* inode is no longer usable */ #define CEPH_I_ASYNC_CHECK_CAPS (1 << 14) /* check caps immediately after async creating finishes */ /* * Masks of ceph inode work. */ #define CEPH_I_WORK_WRITEBACK 0 #define CEPH_I_WORK_INVALIDATE_PAGES 1 #define CEPH_I_WORK_VMTRUNCATE 2 #define CEPH_I_WORK_CHECK_CAPS 3 #define CEPH_I_WORK_FLUSH_SNAPS 4 /* * We set the ERROR_WRITE bit when we start seeing write errors on an inode * and then clear it when they start succeeding. Note that we do a lockless * check first, and only take the lock if it looks like it needs to be changed. * The write submission code just takes this as a hint, so we're not too * worried if a few slip through in either direction. */ static inline void ceph_set_error_write(struct ceph_inode_info *ci) { if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE)) { spin_lock(&ci->i_ceph_lock); ci->i_ceph_flags |= CEPH_I_ERROR_WRITE; spin_unlock(&ci->i_ceph_lock); } } static inline void ceph_clear_error_write(struct ceph_inode_info *ci) { if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE) { spin_lock(&ci->i_ceph_lock); ci->i_ceph_flags &= ~CEPH_I_ERROR_WRITE; spin_unlock(&ci->i_ceph_lock); } } static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci, long long release_count, long long ordered_count) { /* * Makes sure operations that setup readdir cache (update page * cache and i_size) are strongly ordered w.r.t. the following * atomic64_set() operations. */ smp_mb(); atomic64_set(&ci->i_complete_seq[0], release_count); atomic64_set(&ci->i_complete_seq[1], ordered_count); } static inline void __ceph_dir_clear_complete(struct ceph_inode_info *ci) { atomic64_inc(&ci->i_release_count); } static inline void __ceph_dir_clear_ordered(struct ceph_inode_info *ci) { atomic64_inc(&ci->i_ordered_count); } static inline bool __ceph_dir_is_complete(struct ceph_inode_info *ci) { return atomic64_read(&ci->i_complete_seq[0]) == atomic64_read(&ci->i_release_count); } static inline bool __ceph_dir_is_complete_ordered(struct ceph_inode_info *ci) { return atomic64_read(&ci->i_complete_seq[0]) == atomic64_read(&ci->i_release_count) && atomic64_read(&ci->i_complete_seq[1]) == atomic64_read(&ci->i_ordered_count); } static inline void ceph_dir_clear_complete(struct inode *inode) { __ceph_dir_clear_complete(ceph_inode(inode)); } static inline void ceph_dir_clear_ordered(struct inode *inode) { __ceph_dir_clear_ordered(ceph_inode(inode)); } static inline bool ceph_dir_is_complete_ordered(struct inode *inode) { bool ret = __ceph_dir_is_complete_ordered(ceph_inode(inode)); smp_rmb(); return ret; } /* find a specific frag @f */ extern struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f); /* * choose fragment for value @v. copy frag content to pfrag, if leaf * exists */ extern u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v, struct ceph_inode_frag *pfrag, int *found); static inline struct ceph_dentry_info *ceph_dentry(const struct dentry *dentry) { return (struct ceph_dentry_info *)dentry->d_fsdata; } /* * caps helpers */ static inline bool __ceph_is_any_real_caps(struct ceph_inode_info *ci) { return !RB_EMPTY_ROOT(&ci->i_caps); } extern int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented); extern int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int t); extern int __ceph_caps_issued_mask_metric(struct ceph_inode_info *ci, int mask, int t); extern int __ceph_caps_issued_other(struct ceph_inode_info *ci, struct ceph_cap *cap); static inline int ceph_caps_issued(struct ceph_inode_info *ci) { int issued; spin_lock(&ci->i_ceph_lock); issued = __ceph_caps_issued(ci, NULL); spin_unlock(&ci->i_ceph_lock); return issued; } static inline int ceph_caps_issued_mask_metric(struct ceph_inode_info *ci, int mask, int touch) { int r; spin_lock(&ci->i_ceph_lock); r = __ceph_caps_issued_mask_metric(ci, mask, touch); spin_unlock(&ci->i_ceph_lock); return r; } static inline int __ceph_caps_dirty(struct ceph_inode_info *ci) { return ci->i_dirty_caps | ci->i_flushing_caps; } extern struct ceph_cap_flush *ceph_alloc_cap_flush(void); extern void ceph_free_cap_flush(struct ceph_cap_flush *cf); extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask, struct ceph_cap_flush **pcf); extern int __ceph_caps_revoking_other(struct ceph_inode_info *ci, struct ceph_cap *ocap, int mask); extern int ceph_caps_revoking(struct ceph_inode_info *ci, int mask); extern int __ceph_caps_used(struct ceph_inode_info *ci); static inline bool __ceph_is_file_opened(struct ceph_inode_info *ci) { return ci->i_nr_by_mode[0]; } extern int __ceph_caps_file_wanted(struct ceph_inode_info *ci); extern int __ceph_caps_wanted(struct ceph_inode_info *ci); /* what the mds thinks we want */ extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check); extern void ceph_caps_init(struct ceph_mds_client *mdsc); extern void ceph_caps_finalize(struct ceph_mds_client *mdsc); extern void ceph_adjust_caps_max_min(struct ceph_mds_client *mdsc, struct ceph_mount_options *fsopt); extern int ceph_reserve_caps(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx, int need); extern void ceph_unreserve_caps(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx); extern void ceph_reservation_status(struct ceph_fs_client *client, int *total, int *avail, int *used, int *reserved, int *min); extern void change_auth_cap_ses(struct ceph_inode_info *ci, struct ceph_mds_session *session); /* * we keep buffered readdir results attached to file->private_data */ #define CEPH_F_SYNC 1 #define CEPH_F_ATEND 2 struct ceph_file_info { short fmode; /* initialized on open */ short flags; /* CEPH_F_* */ spinlock_t rw_contexts_lock; struct list_head rw_contexts; u32 filp_gen; }; struct ceph_dir_file_info { struct ceph_file_info file_info; /* readdir: position within the dir */ u32 frag; struct ceph_mds_request *last_readdir; /* readdir: position within a frag */ unsigned next_offset; /* offset of next chunk (last_name's + 1) */ char *last_name; /* last entry in previous chunk */ long long dir_release_count; long long dir_ordered_count; int readdir_cache_idx; /* used for -o dirstat read() on directory thing */ char *dir_info; int dir_info_len; }; struct ceph_rw_context { struct list_head list; struct task_struct *thread; int caps; }; #define CEPH_DEFINE_RW_CONTEXT(_name, _caps) \ struct ceph_rw_context _name = { \ .thread = current, \ .caps = _caps, \ } static inline void ceph_add_rw_context(struct ceph_file_info *cf, struct ceph_rw_context *ctx) { spin_lock(&cf->rw_contexts_lock); list_add(&ctx->list, &cf->rw_contexts); spin_unlock(&cf->rw_contexts_lock); } static inline void ceph_del_rw_context(struct ceph_file_info *cf, struct ceph_rw_context *ctx) { spin_lock(&cf->rw_contexts_lock); list_del(&ctx->list); spin_unlock(&cf->rw_contexts_lock); } static inline struct ceph_rw_context* ceph_find_rw_context(struct ceph_file_info *cf) { struct ceph_rw_context *ctx, *found = NULL; spin_lock(&cf->rw_contexts_lock); list_for_each_entry(ctx, &cf->rw_contexts, list) { if (ctx->thread == current) { found = ctx; break; } } spin_unlock(&cf->rw_contexts_lock); return found; } struct ceph_readdir_cache_control { struct page *page; struct dentry **dentries; int index; }; /* * A "snap realm" describes a subset of the file hierarchy sharing * the same set of snapshots that apply to it. The realms themselves * are organized into a hierarchy, such that children inherit (some of) * the snapshots of their parents. * * All inodes within the realm that have capabilities are linked into a * per-realm list. */ struct ceph_snap_realm { u64 ino; struct inode *inode; atomic_t nref; struct rb_node node; u64 created, seq; u64 parent_ino; u64 parent_since; /* snapid when our current parent became so */ u64 *prior_parent_snaps; /* snaps inherited from any parents we */ u32 num_prior_parent_snaps; /* had prior to parent_since */ u64 *snaps; /* snaps specific to this realm */ u32 num_snaps; struct ceph_snap_realm *parent; struct list_head children; /* list of child realms */ struct list_head child_item; struct list_head empty_item; /* if i have ref==0 */ struct list_head dirty_item; /* if realm needs new context */ struct list_head rebuild_item; /* rebuild snap realms _downward_ in hierarchy */ /* the current set of snaps for this realm */ struct ceph_snap_context *cached_context; struct list_head inodes_with_caps; spinlock_t inodes_with_caps_lock; }; static inline int default_congestion_kb(void) { int congestion_kb; /* * Copied from NFS * * congestion size, scale with available memory. * * 64MB: 8192k * 128MB: 11585k * 256MB: 16384k * 512MB: 23170k * 1GB: 32768k * 2GB: 46340k * 4GB: 65536k * 8GB: 92681k * 16GB: 131072k * * This allows larger machines to have larger/more transfers. * Limit the default to 256M */ congestion_kb = (16*int_sqrt(totalram_pages())) << (PAGE_SHIFT-10); if (congestion_kb > 256*1024) congestion_kb = 256*1024; return congestion_kb; } /* super.c */ extern int ceph_force_reconnect(struct super_block *sb); /* snap.c */ struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc, u64 ino); extern void ceph_get_snap_realm(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm); extern void ceph_put_snap_realm(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm); extern int ceph_update_snap_trace(struct ceph_mds_client *m, void *p, void *e, bool deletion, struct ceph_snap_realm **realm_ret); void ceph_change_snap_realm(struct inode *inode, struct ceph_snap_realm *realm); extern void ceph_handle_snap(struct ceph_mds_client *mdsc, struct ceph_mds_session *session, struct ceph_msg *msg); extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci, struct ceph_cap_snap *capsnap); extern void ceph_cleanup_global_and_empty_realms(struct ceph_mds_client *mdsc); extern struct ceph_snapid_map *ceph_get_snapid_map(struct ceph_mds_client *mdsc, u64 snap); extern void ceph_put_snapid_map(struct ceph_mds_client* mdsc, struct ceph_snapid_map *sm); extern void ceph_trim_snapid_map(struct ceph_mds_client *mdsc); extern void ceph_cleanup_snapid_map(struct ceph_mds_client *mdsc); void ceph_umount_begin(struct super_block *sb); /* * a cap_snap is "pending" if it is still awaiting an in-progress * sync write (that may/may not still update size, mtime, etc.). */ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci) { return !list_empty(&ci->i_cap_snaps) && list_last_entry(&ci->i_cap_snaps, struct ceph_cap_snap, ci_item)->writing; } /* inode.c */ struct ceph_mds_reply_info_in; struct ceph_mds_reply_dirfrag; struct ceph_acl_sec_ctx; extern const struct inode_operations ceph_file_iops; extern struct inode *ceph_alloc_inode(struct super_block *sb); extern void ceph_evict_inode(struct inode *inode); extern void ceph_free_inode(struct inode *inode); struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry, umode_t *mode, struct ceph_acl_sec_ctx *as_ctx); void ceph_as_ctx_to_req(struct ceph_mds_request *req, struct ceph_acl_sec_ctx *as_ctx); extern struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino, struct inode *newino); extern struct inode *ceph_get_snapdir(struct inode *parent); extern int ceph_fill_file_size(struct inode *inode, int issued, u32 truncate_seq, u64 truncate_size, u64 size); extern void ceph_fill_file_time(struct inode *inode, int issued, u64 time_warp_seq, struct timespec64 *ctime, struct timespec64 *mtime, struct timespec64 *atime); extern int ceph_fill_inode(struct inode *inode, struct page *locked_page, struct ceph_mds_reply_info_in *iinfo, struct ceph_mds_reply_dirfrag *dirinfo, struct ceph_mds_session *session, int cap_fmode, struct ceph_cap_reservation *caps_reservation); extern int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req); extern int ceph_readdir_prepopulate(struct ceph_mds_request *req, struct ceph_mds_session *session); extern int ceph_inode_holds_cap(struct inode *inode, int mask); extern bool ceph_inode_set_size(struct inode *inode, loff_t size); extern void __ceph_do_pending_vmtruncate(struct inode *inode); void ceph_queue_inode_work(struct inode *inode, int work_bit); static inline void ceph_queue_vmtruncate(struct inode *inode) { ceph_queue_inode_work(inode, CEPH_I_WORK_VMTRUNCATE); } static inline void ceph_queue_invalidate(struct inode *inode) { ceph_queue_inode_work(inode, CEPH_I_WORK_INVALIDATE_PAGES); } static inline void ceph_queue_writeback(struct inode *inode) { ceph_queue_inode_work(inode, CEPH_I_WORK_WRITEBACK); } static inline void ceph_queue_check_caps(struct inode *inode) { ceph_queue_inode_work(inode, CEPH_I_WORK_CHECK_CAPS); } static inline void ceph_queue_flush_snaps(struct inode *inode) { ceph_queue_inode_work(inode, CEPH_I_WORK_FLUSH_SNAPS); } extern int ceph_try_to_choose_auth_mds(struct inode *inode, int mask); extern int __ceph_do_getattr(struct inode *inode, struct page *locked_page, int mask, bool force); static inline int ceph_do_getattr(struct inode *inode, int mask, bool force) { return __ceph_do_getattr(inode, NULL, mask, force); } extern int ceph_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); struct ceph_iattr { struct ceph_fscrypt_auth *fscrypt_auth; }; extern int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode, struct iattr *attr, struct ceph_iattr *cia); extern int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); extern int ceph_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); void ceph_inode_shutdown(struct inode *inode); static inline bool ceph_inode_is_shutdown(struct inode *inode) { unsigned long flags = READ_ONCE(ceph_inode(inode)->i_ceph_flags); struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode); int state = READ_ONCE(fsc->mount_state); return (flags & CEPH_I_SHUTDOWN) || state >= CEPH_MOUNT_SHUTDOWN; } /* xattr.c */ int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int); int ceph_do_getvxattr(struct inode *inode, const char *name, void *value, size_t size); ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t); extern ssize_t ceph_listxattr(struct dentry *, char *, size_t); extern struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci); extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci); extern const struct xattr_handler * const ceph_xattr_handlers[]; struct ceph_acl_sec_ctx { #ifdef CONFIG_CEPH_FS_POSIX_ACL void *default_acl; void *acl; #endif #ifdef CONFIG_CEPH_FS_SECURITY_LABEL void *sec_ctx; u32 sec_ctxlen; #endif #ifdef CONFIG_FS_ENCRYPTION struct ceph_fscrypt_auth *fscrypt_auth; #endif struct ceph_pagelist *pagelist; }; #ifdef CONFIG_SECURITY extern bool ceph_security_xattr_deadlock(struct inode *in); extern bool ceph_security_xattr_wanted(struct inode *in); #else static inline bool ceph_security_xattr_deadlock(struct inode *in) { return false; } static inline bool ceph_security_xattr_wanted(struct inode *in) { return false; } #endif #ifdef CONFIG_CEPH_FS_SECURITY_LABEL extern int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, struct ceph_acl_sec_ctx *ctx); static inline void ceph_security_invalidate_secctx(struct inode *inode) { security_inode_invalidate_secctx(inode); } #else static inline int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, struct ceph_acl_sec_ctx *ctx) { return 0; } static inline void ceph_security_invalidate_secctx(struct inode *inode) { } #endif void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx); /* acl.c */ #ifdef CONFIG_CEPH_FS_POSIX_ACL struct posix_acl *ceph_get_acl(struct inode *, int, bool); int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int ceph_pre_init_acls(struct inode *dir, umode_t *mode, struct ceph_acl_sec_ctx *as_ctx); void ceph_init_inode_acls(struct inode *inode, struct ceph_acl_sec_ctx *as_ctx); static inline void ceph_forget_all_cached_acls(struct inode *inode) { forget_all_cached_acls(inode); } #else #define ceph_get_acl NULL #define ceph_set_acl NULL static inline int ceph_pre_init_acls(struct inode *dir, umode_t *mode, struct ceph_acl_sec_ctx *as_ctx) { return 0; } static inline void ceph_init_inode_acls(struct inode *inode, struct ceph_acl_sec_ctx *as_ctx) { } static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode) { return 0; } static inline void ceph_forget_all_cached_acls(struct inode *inode) { } #endif /* caps.c */ extern const char *ceph_cap_string(int c); extern void ceph_handle_caps(struct ceph_mds_session *session, struct ceph_msg *msg); extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx); extern void ceph_add_cap(struct inode *inode, struct ceph_mds_session *session, u64 cap_id, unsigned issued, unsigned wanted, unsigned cap, unsigned seq, u64 realmino, int flags, struct ceph_cap **new_cap); extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release); extern void ceph_remove_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, bool queue_release); extern void __ceph_remove_caps(struct ceph_inode_info *ci); extern void ceph_put_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap); extern int ceph_is_any_caps(struct inode *inode); extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc); extern int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync); extern void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); void ceph_kick_flushing_inode_caps(struct ceph_mds_session *session, struct ceph_inode_info *ci); extern struct ceph_cap *__get_cap_for_mds(struct ceph_inode_info *ci, int mds); extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci, int mds); extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps, bool snap_rwsem_locked); extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps); extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had); extern void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had); extern void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci, int had); extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, struct ceph_snap_context *snapc); extern void __ceph_remove_capsnap(struct inode *inode, struct ceph_cap_snap *capsnap, bool *wake_ci, bool *wake_mdsc); extern void ceph_remove_capsnap(struct inode *inode, struct ceph_cap_snap *capsnap, bool *wake_ci, bool *wake_mdsc); extern void ceph_flush_snaps(struct ceph_inode_info *ci, struct ceph_mds_session **psession); extern bool __ceph_should_report_size(struct ceph_inode_info *ci); extern void ceph_check_caps(struct ceph_inode_info *ci, int flags); extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc); extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc); extern int ceph_drop_caps_for_unlink(struct inode *inode); extern int ceph_encode_inode_release(void **p, struct inode *inode, int mds, int drop, int unless, int force); extern int ceph_encode_dentry_release(void **p, struct dentry *dn, struct inode *dir, int mds, int drop, int unless); extern int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need, int want, loff_t endoff, int *got); extern int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got); extern int ceph_try_get_caps(struct inode *inode, int need, int want, bool nonblock, int *got); /* for counting open files by mode */ extern void ceph_get_fmode(struct ceph_inode_info *ci, int mode, int count); extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode, int count); extern void __ceph_touch_fmode(struct ceph_inode_info *ci, struct ceph_mds_client *mdsc, int fmode); /* addr.c */ extern const struct address_space_operations ceph_aops; extern const struct netfs_request_ops ceph_netfs_ops; extern int ceph_mmap(struct file *file, struct vm_area_struct *vma); extern int ceph_uninline_data(struct file *file); extern int ceph_pool_perm_check(struct inode *inode, int need); extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc); int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate); static inline bool ceph_has_inline_data(struct ceph_inode_info *ci) { if (ci->i_inline_version == CEPH_INLINE_NONE || ci->i_inline_version == 1) /* initial version, no data */ return false; return true; } /* file.c */ extern const struct file_operations ceph_file_fops; extern int ceph_renew_caps(struct inode *inode, int fmode); extern int ceph_open(struct inode *inode, struct file *file); extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned flags, umode_t mode); extern ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, struct iov_iter *to, int *retry_op, u64 *last_objver); extern int ceph_release(struct inode *inode, struct file *filp); extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, char *data, size_t len); /* dir.c */ extern const struct file_operations ceph_dir_fops; extern const struct file_operations ceph_snapdir_fops; extern const struct inode_operations ceph_dir_iops; extern const struct inode_operations ceph_snapdir_iops; extern const struct dentry_operations ceph_dentry_ops; extern loff_t ceph_make_fpos(unsigned high, unsigned off, bool hash_order); extern int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry); extern struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req, struct dentry *dentry); extern struct dentry *ceph_finish_lookup(struct ceph_mds_request *req, struct dentry *dentry, int err); extern void __ceph_dentry_lease_touch(struct ceph_dentry_info *di); extern void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di); extern void ceph_invalidate_dentry_lease(struct dentry *dentry); extern int ceph_trim_dentries(struct ceph_mds_client *mdsc); extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn); extern void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl); /* ioctl.c */ extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg); /* export.c */ extern const struct export_operations ceph_export_ops; struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino); /* locks.c */ extern __init void ceph_flock_init(void); extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl); extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl); extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num); extern int ceph_encode_locks_to_buffer(struct inode *inode, struct ceph_filelock *flocks, int num_fcntl_locks, int num_flock_locks); extern int ceph_locks_to_pagelist(struct ceph_filelock *flocks, struct ceph_pagelist *pagelist, int num_fcntl_locks, int num_flock_locks); /* debugfs.c */ extern void ceph_fs_debugfs_init(struct ceph_fs_client *client); extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client); /* quota.c */ enum quota_get_realm { QUOTA_GET_MAX_FILES, QUOTA_GET_MAX_BYTES, QUOTA_GET_ANY }; static inline bool __ceph_has_quota(struct ceph_inode_info *ci, enum quota_get_realm which) { bool has_quota = false; switch (which) { case QUOTA_GET_MAX_BYTES: has_quota = !!ci->i_max_bytes; break; case QUOTA_GET_MAX_FILES: has_quota = !!ci->i_max_files; break; default: has_quota = !!(ci->i_max_files || ci->i_max_bytes); } return has_quota; } extern void ceph_adjust_quota_realms_count(struct inode *inode, bool inc); static inline void __ceph_update_quota(struct ceph_inode_info *ci, u64 max_bytes, u64 max_files) { bool had_quota, has_quota; had_quota = __ceph_has_quota(ci, QUOTA_GET_ANY); ci->i_max_bytes = max_bytes; ci->i_max_files = max_files; has_quota = __ceph_has_quota(ci, QUOTA_GET_ANY); if (had_quota != has_quota) ceph_adjust_quota_realms_count(&ci->netfs.inode, has_quota); } extern void ceph_handle_quota(struct ceph_mds_client *mdsc, struct ceph_mds_session *session, struct ceph_msg *msg); extern bool ceph_quota_is_max_files_exceeded(struct inode *inode); extern bool ceph_quota_is_same_realm(struct inode *old, struct inode *new); extern bool ceph_quota_is_max_bytes_exceeded(struct inode *inode, loff_t newlen); extern bool ceph_quota_is_max_bytes_approaching(struct inode *inode, loff_t newlen); extern bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf); extern void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc); bool ceph_inc_mds_stopping_blocker(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc); bool ceph_inc_osd_stopping_blocker(struct ceph_mds_client *mdsc); void ceph_dec_osd_stopping_blocker(struct ceph_mds_client *mdsc); #endif /* _FS_CEPH_SUPER_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 | // SPDX-License-Identifier: GPL-2.0-only /* * Architecture specific (i386/x86_64) functions for kexec based crash dumps. * * Created by: Hariprasad Nellitheertha (hari@in.ibm.com) * * Copyright (C) IBM Corporation, 2004. All rights reserved. * Copyright (C) Red Hat Inc., 2014. All rights reserved. * Authors: * Vivek Goyal <vgoyal@redhat.com> * */ #define pr_fmt(fmt) "kexec: " fmt #include <linux/types.h> #include <linux/kernel.h> #include <linux/smp.h> #include <linux/reboot.h> #include <linux/kexec.h> #include <linux/delay.h> #include <linux/elf.h> #include <linux/elfcore.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/memblock.h> #include <asm/processor.h> #include <asm/hardirq.h> #include <asm/nmi.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/e820/types.h> #include <asm/io_apic.h> #include <asm/hpet.h> #include <linux/kdebug.h> #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/intel_pt.h> #include <asm/crash.h> #include <asm/cmdline.h> /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { struct boot_params *params; /* Type of memory */ unsigned int type; }; #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) { crash_save_cpu(regs, cpu); /* * Disable Intel PT to stop its logging */ cpu_emergency_stop_pt(); disable_local_APIC(); } void kdump_nmi_shootdown_cpus(void) { nmi_shootdown_cpus(kdump_nmi_callback); disable_local_APIC(); } /* Override the weak function in kernel/panic.c */ void crash_smp_send_stop(void) { static int cpus_stopped; if (cpus_stopped) return; if (smp_ops.crash_stop_other_cpus) smp_ops.crash_stop_other_cpus(); else smp_send_stop(); cpus_stopped = 1; } #else void crash_smp_send_stop(void) { /* There are no cpus to shootdown */ } #endif void native_machine_crash_shutdown(struct pt_regs *regs) { /* This function is only called after the system * has panicked or is otherwise in a critical state. * The minimum amount of code to allow a kexec'd kernel * to run successfully needs to happen here. * * In practice this means shooting down the other cpus in * an SMP system. */ /* The kernel is broken so disable interrupts */ local_irq_disable(); crash_smp_send_stop(); cpu_emergency_disable_virtualization(); /* * Disable Intel PT to stop its logging */ cpu_emergency_stop_pt(); #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); clear_IO_APIC(); #endif lapic_shutdown(); restore_boot_irq_mode(); #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif crash_save_cpu(regs, safe_smp_processor_id()); } #if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_HOTPLUG) static int get_nr_ram_ranges_callback(struct resource *res, void *arg) { unsigned int *nr_ranges = arg; (*nr_ranges)++; return 0; } /* Gather all the required information to prepare elf headers for ram regions */ static struct crash_mem *fill_up_crash_elf_data(void) { unsigned int nr_ranges = 0; struct crash_mem *cmem; walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); if (!nr_ranges) return NULL; /* * Exclusion of crash region and/or crashk_low_res may cause * another range split. So add extra two slots here. */ nr_ranges += 2; cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); if (!cmem) return NULL; cmem->max_nr_ranges = nr_ranges; cmem->nr_ranges = 0; return cmem; } /* * Look for any unwanted ranges between mstart, mend and remove them. This * might lead to split and split ranges are put in cmem->ranges[] array */ static int elf_header_exclude_ranges(struct crash_mem *cmem) { int ret = 0; /* Exclude the low 1M because it is always reserved */ ret = crash_exclude_mem_range(cmem, 0, (1<<20)-1); if (ret) return ret; /* Exclude crashkernel region */ ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); if (ret) return ret; if (crashk_low_res.end) ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); return ret; } static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { struct crash_mem *cmem = arg; cmem->ranges[cmem->nr_ranges].start = res->start; cmem->ranges[cmem->nr_ranges].end = res->end; cmem->nr_ranges++; return 0; } /* Prepare elf headers. Return addr and size */ static int prepare_elf_headers(struct kimage *image, void **addr, unsigned long *sz, unsigned long *nr_mem_ranges) { struct crash_mem *cmem; int ret; cmem = fill_up_crash_elf_data(); if (!cmem) return -ENOMEM; ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); if (ret) goto out; /* Exclude unwanted mem ranges */ ret = elf_header_exclude_ranges(cmem); if (ret) goto out; /* Return the computed number of memory ranges, for hotplug usage */ *nr_mem_ranges = cmem->nr_ranges; /* By default prepare 64bit headers */ ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); out: vfree(cmem); return ret; } #endif #ifdef CONFIG_KEXEC_FILE static int add_e820_entry(struct boot_params *params, struct e820_entry *entry) { unsigned int nr_e820_entries; nr_e820_entries = params->e820_entries; if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE) return 1; memcpy(¶ms->e820_table[nr_e820_entries], entry, sizeof(struct e820_entry)); params->e820_entries++; return 0; } static int memmap_entry_callback(struct resource *res, void *arg) { struct crash_memmap_data *cmd = arg; struct boot_params *params = cmd->params; struct e820_entry ei; ei.addr = res->start; ei.size = resource_size(res); ei.type = cmd->type; add_e820_entry(params, &ei); return 0; } static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, unsigned long long mstart, unsigned long long mend) { unsigned long start, end; cmem->ranges[0].start = mstart; cmem->ranges[0].end = mend; cmem->nr_ranges = 1; /* Exclude elf header region */ start = image->elf_load_addr; end = start + image->elf_headers_sz - 1; return crash_exclude_mem_range(cmem, start, end); } /* Prepare memory map for crash dump kernel */ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) { int i, ret = 0; unsigned long flags; struct e820_entry ei; struct crash_memmap_data cmd; struct crash_mem *cmem; cmem = vzalloc(struct_size(cmem, ranges, 1)); if (!cmem) return -ENOMEM; memset(&cmd, 0, sizeof(struct crash_memmap_data)); cmd.params = params; /* Add the low 1M */ cmd.type = E820_TYPE_RAM; flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; walk_iomem_res_desc(IORES_DESC_NONE, flags, 0, (1<<20)-1, &cmd, memmap_entry_callback); /* Add ACPI tables */ cmd.type = E820_TYPE_ACPI; flags = IORESOURCE_MEM | IORESOURCE_BUSY; walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd, memmap_entry_callback); /* Add ACPI Non-volatile Storage */ cmd.type = E820_TYPE_NVS; walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd, memmap_entry_callback); /* Add e820 reserved ranges */ cmd.type = E820_TYPE_RESERVED; flags = IORESOURCE_MEM; walk_iomem_res_desc(IORES_DESC_RESERVED, flags, 0, -1, &cmd, memmap_entry_callback); /* Add crashk_low_res region */ if (crashk_low_res.end) { ei.addr = crashk_low_res.start; ei.size = resource_size(&crashk_low_res); ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } /* Exclude some ranges from crashk_res and add rest to memmap */ ret = memmap_exclude_ranges(image, cmem, crashk_res.start, crashk_res.end); if (ret) goto out; for (i = 0; i < cmem->nr_ranges; i++) { ei.size = cmem->ranges[i].end - cmem->ranges[i].start + 1; /* If entry is less than a page, skip it */ if (ei.size < PAGE_SIZE) continue; ei.addr = cmem->ranges[i].start; ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } out: vfree(cmem); return ret; } int crash_load_segments(struct kimage *image) { int ret; unsigned long pnum = 0; struct kexec_buf kbuf = { .image = image, .buf_min = 0, .buf_max = ULONG_MAX, .top_down = false }; /* Prepare elf headers and add a segment */ ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz, &pnum); if (ret) return ret; image->elf_headers = kbuf.buffer; image->elf_headers_sz = kbuf.bufsz; kbuf.memsz = kbuf.bufsz; #ifdef CONFIG_CRASH_HOTPLUG /* * The elfcorehdr segment size accounts for VMCOREINFO, kernel_map, * maximum CPUs and maximum memory ranges. */ if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) pnum = 2 + CONFIG_NR_CPUS_DEFAULT + CONFIG_CRASH_MAX_MEMORY_RANGES; else pnum += 2 + CONFIG_NR_CPUS_DEFAULT; if (pnum < (unsigned long)PN_XNUM) { kbuf.memsz = pnum * sizeof(Elf64_Phdr); kbuf.memsz += sizeof(Elf64_Ehdr); image->elfcorehdr_index = image->nr_segments; /* Mark as usable to crash kernel, else crash kernel fails on boot */ image->elf_headers_sz = kbuf.memsz; } else { pr_err("number of Phdrs %lu exceeds max\n", pnum); } #endif kbuf.buf_align = ELF_CORE_HEADER_ALIGN; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) return ret; image->elf_load_addr = kbuf.mem; pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", image->elf_load_addr, kbuf.bufsz, kbuf.memsz); return ret; } #endif /* CONFIG_KEXEC_FILE */ #ifdef CONFIG_CRASH_HOTPLUG #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt /* These functions provide the value for the sysfs crash_hotplug nodes */ #ifdef CONFIG_HOTPLUG_CPU int arch_crash_hotplug_cpu_support(void) { return crash_check_update_elfcorehdr(); } #endif #ifdef CONFIG_MEMORY_HOTPLUG int arch_crash_hotplug_memory_support(void) { return crash_check_update_elfcorehdr(); } #endif unsigned int arch_crash_get_elfcorehdr_size(void) { unsigned int sz; /* kernel_map, VMCOREINFO and maximum CPUs */ sz = 2 + CONFIG_NR_CPUS_DEFAULT; if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) sz += CONFIG_CRASH_MAX_MEMORY_RANGES; sz *= sizeof(Elf64_Phdr); return sz; } /** * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes * @image: a pointer to kexec_crash_image * * Prepare the new elfcorehdr and replace the existing elfcorehdr. */ void arch_crash_handle_hotplug_event(struct kimage *image) { void *elfbuf = NULL, *old_elfcorehdr; unsigned long nr_mem_ranges; unsigned long mem, memsz; unsigned long elfsz = 0; /* * As crash_prepare_elf64_headers() has already described all * possible CPUs, there is no need to update the elfcorehdr * for additional CPU changes. */ if ((image->file_mode || image->elfcorehdr_updated) && ((image->hp_action == KEXEC_CRASH_HP_ADD_CPU) || (image->hp_action == KEXEC_CRASH_HP_REMOVE_CPU))) return; /* * Create the new elfcorehdr reflecting the changes to CPU and/or * memory resources. */ if (prepare_elf_headers(image, &elfbuf, &elfsz, &nr_mem_ranges)) { pr_err("unable to create new elfcorehdr"); goto out; } /* * Obtain address and size of the elfcorehdr segment, and * check it against the new elfcorehdr buffer. */ mem = image->segment[image->elfcorehdr_index].mem; memsz = image->segment[image->elfcorehdr_index].memsz; if (elfsz > memsz) { pr_err("update elfcorehdr elfsz %lu > memsz %lu", elfsz, memsz); goto out; } /* * Copy new elfcorehdr over the old elfcorehdr at destination. */ old_elfcorehdr = kmap_local_page(pfn_to_page(mem >> PAGE_SHIFT)); if (!old_elfcorehdr) { pr_err("mapping elfcorehdr segment failed\n"); goto out; } /* * Temporarily invalidate the crash image while the * elfcorehdr is updated. */ xchg(&kexec_crash_image, NULL); memcpy_flushcache(old_elfcorehdr, elfbuf, elfsz); xchg(&kexec_crash_image, image); kunmap_local(old_elfcorehdr); pr_debug("updated elfcorehdr\n"); out: vfree(elfbuf); } #endif |
| 2 2 2 71 70 71 71 50 50 40 40 36 4 4 4 4 4 2 2 2 2 1 2 4 40 1 1 1 1 1 1 14 14 13 13 6 13 13 13 13 13 13 6 6 6 6 4 4 31 74 71 68 71 71 71 71 155 152 152 153 151 153 196 149 72 23 2 1 1 1 1 1 1 1 1 1 1 12 11 11 11 11 11 58 58 58 1 71 71 1 1 71 70 71 5 5 5 5 5 71 31 71 70 71 72 59 58 58 58 58 58 1 58 58 58 58 58 58 58 45 41 41 36 13 31 25 25 25 25 23 25 72 10 1 63 72 9 64 64 72 58 71 10 71 9 63 9 6 6 5 1 1 1 1 1 1 1 1 1 1 1 1 1 75 74 73 75 75 75 75 75 5 75 4 75 75 74 73 73 123 123 102 123 123 75 75 34 75 102 63 31 9 55 5 113 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (C) 2011 Novell Inc. */ #include <linux/module.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fileattr.h> #include <linux/splice.h> #include <linux/xattr.h> #include <linux/security.h> #include <linux/uaccess.h> #include <linux/sched/signal.h> #include <linux/cred.h> #include <linux/namei.h> #include <linux/fdtable.h> #include <linux/ratelimit.h> #include <linux/exportfs.h> #include "overlayfs.h" #define OVL_COPY_UP_CHUNK_SIZE (1 << 20) static int ovl_ccup_set(const char *buf, const struct kernel_param *param) { pr_warn("\"check_copy_up\" module option is obsolete\n"); return 0; } static int ovl_ccup_get(char *buf, const struct kernel_param *param) { return sprintf(buf, "N\n"); } module_param_call(check_copy_up, ovl_ccup_set, ovl_ccup_get, NULL, 0644); MODULE_PARM_DESC(check_copy_up, "Obsolete; does nothing"); static bool ovl_must_copy_xattr(const char *name) { return !strcmp(name, XATTR_POSIX_ACL_ACCESS) || !strcmp(name, XATTR_POSIX_ACL_DEFAULT) || !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); } static int ovl_copy_acl(struct ovl_fs *ofs, const struct path *path, struct dentry *dentry, const char *acl_name) { int err; struct posix_acl *clone, *real_acl = NULL; real_acl = ovl_get_acl_path(path, acl_name, false); if (!real_acl) return 0; if (IS_ERR(real_acl)) { err = PTR_ERR(real_acl); if (err == -ENODATA || err == -EOPNOTSUPP) return 0; return err; } clone = posix_acl_clone(real_acl, GFP_KERNEL); posix_acl_release(real_acl); /* release original acl */ if (!clone) return -ENOMEM; err = ovl_do_set_acl(ofs, dentry, acl_name, clone); /* release cloned acl */ posix_acl_release(clone); return err; } int ovl_copy_xattr(struct super_block *sb, const struct path *oldpath, struct dentry *new) { struct dentry *old = oldpath->dentry; ssize_t list_size, size, value_size = 0; char *buf, *name, *value = NULL; int error = 0; size_t slen; if (!old->d_inode->i_op->listxattr || !new->d_inode->i_op->listxattr) return 0; list_size = vfs_listxattr(old, NULL, 0); if (list_size <= 0) { if (list_size == -EOPNOTSUPP) return 0; return list_size; } buf = kvzalloc(list_size, GFP_KERNEL); if (!buf) return -ENOMEM; list_size = vfs_listxattr(old, buf, list_size); if (list_size <= 0) { error = list_size; goto out; } for (name = buf; list_size; name += slen) { slen = strnlen(name, list_size) + 1; /* underlying fs providing us with an broken xattr list? */ if (WARN_ON(slen > list_size)) { error = -EIO; break; } list_size -= slen; if (ovl_is_private_xattr(sb, name)) continue; error = security_inode_copy_up_xattr(name); if (error < 0 && error != -EOPNOTSUPP) break; if (error == 1) { error = 0; continue; /* Discard */ } if (is_posix_acl_xattr(name)) { error = ovl_copy_acl(OVL_FS(sb), oldpath, new, name); if (!error) continue; /* POSIX ACLs must be copied. */ break; } retry: size = ovl_do_getxattr(oldpath, name, value, value_size); if (size == -ERANGE) size = ovl_do_getxattr(oldpath, name, NULL, 0); if (size < 0) { error = size; break; } if (size > value_size) { void *new; new = kvmalloc(size, GFP_KERNEL); if (!new) { error = -ENOMEM; break; } kvfree(value); value = new; value_size = size; goto retry; } error = ovl_do_setxattr(OVL_FS(sb), new, name, value, size, 0); if (error) { if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name)) break; /* Ignore failure to copy unknown xattrs */ error = 0; } } kvfree(value); out: kvfree(buf); return error; } static int ovl_copy_fileattr(struct inode *inode, const struct path *old, const struct path *new) { struct fileattr oldfa = { .flags_valid = true }; struct fileattr newfa = { .flags_valid = true }; int err; err = ovl_real_fileattr_get(old, &oldfa); if (err) { /* Ntfs-3g returns -EINVAL for "no fileattr support" */ if (err == -ENOTTY || err == -EINVAL) return 0; pr_warn("failed to retrieve lower fileattr (%pd2, err=%i)\n", old->dentry, err); return err; } /* * We cannot set immutable and append-only flags on upper inode, * because we would not be able to link upper inode to upper dir * not set overlay private xattr on upper inode. * Store these flags in overlay.protattr xattr instead. */ if (oldfa.flags & OVL_PROT_FS_FLAGS_MASK) { err = ovl_set_protattr(inode, new->dentry, &oldfa); if (err == -EPERM) pr_warn_once("copying fileattr: no xattr on upper\n"); else if (err) return err; } /* Don't bother copying flags if none are set */ if (!(oldfa.flags & OVL_COPY_FS_FLAGS_MASK)) return 0; err = ovl_real_fileattr_get(new, &newfa); if (err) { /* * Returning an error if upper doesn't support fileattr will * result in a regression, so revert to the old behavior. */ if (err == -ENOTTY || err == -EINVAL) { pr_warn_once("copying fileattr: no support on upper\n"); return 0; } pr_warn("failed to retrieve upper fileattr (%pd2, err=%i)\n", new->dentry, err); return err; } BUILD_BUG_ON(OVL_COPY_FS_FLAGS_MASK & ~FS_COMMON_FL); newfa.flags &= ~OVL_COPY_FS_FLAGS_MASK; newfa.flags |= (oldfa.flags & OVL_COPY_FS_FLAGS_MASK); BUILD_BUG_ON(OVL_COPY_FSX_FLAGS_MASK & ~FS_XFLAG_COMMON); newfa.fsx_xflags &= ~OVL_COPY_FSX_FLAGS_MASK; newfa.fsx_xflags |= (oldfa.fsx_xflags & OVL_COPY_FSX_FLAGS_MASK); return ovl_real_fileattr_set(new, &newfa); } static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, struct file *new_file, loff_t len) { struct path datapath; struct file *old_file; loff_t old_pos = 0; loff_t new_pos = 0; loff_t cloned; loff_t data_pos = -1; loff_t hole_len; bool skip_hole = false; int error = 0; ovl_path_lowerdata(dentry, &datapath); if (WARN_ON(datapath.dentry == NULL)) return -EIO; old_file = ovl_path_open(&datapath, O_LARGEFILE | O_RDONLY); if (IS_ERR(old_file)) return PTR_ERR(old_file); /* Try to use clone_file_range to clone up within the same fs */ ovl_start_write(dentry); cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0); ovl_end_write(dentry); if (cloned == len) goto out_fput; /* Couldn't clone, so now we try to copy the data */ /* Check if lower fs supports seek operation */ if (old_file->f_mode & FMODE_LSEEK) skip_hole = true; while (len) { size_t this_len = OVL_COPY_UP_CHUNK_SIZE; long bytes; if (len < this_len) this_len = len; if (signal_pending_state(TASK_KILLABLE, current)) { error = -EINTR; break; } /* * Fill zero for hole will cost unnecessary disk space * and meanwhile slow down the copy-up speed, so we do * an optimization for hole during copy-up, it relies * on SEEK_DATA implementation in lower fs so if lower * fs does not support it, copy-up will behave as before. * * Detail logic of hole detection as below: * When we detect next data position is larger than current * position we will skip that hole, otherwise we copy * data in the size of OVL_COPY_UP_CHUNK_SIZE. Actually, * it may not recognize all kind of holes and sometimes * only skips partial of hole area. However, it will be * enough for most of the use cases. * * We do not hold upper sb_writers throughout the loop to avert * lockdep warning with llseek of lower file in nested overlay: * - upper sb_writers * -- lower ovl_inode_lock (ovl_llseek) */ if (skip_hole && data_pos < old_pos) { data_pos = vfs_llseek(old_file, old_pos, SEEK_DATA); if (data_pos > old_pos) { hole_len = data_pos - old_pos; len -= hole_len; old_pos = new_pos = data_pos; continue; } else if (data_pos == -ENXIO) { break; } else if (data_pos < 0) { skip_hole = false; } } ovl_start_write(dentry); bytes = do_splice_direct(old_file, &old_pos, new_file, &new_pos, this_len, SPLICE_F_MOVE); ovl_end_write(dentry); if (bytes <= 0) { error = bytes; break; } WARN_ON(old_pos != new_pos); len -= bytes; } if (!error && ovl_should_sync(ofs)) error = vfs_fsync(new_file, 0); out_fput: fput(old_file); return error; } static int ovl_set_size(struct ovl_fs *ofs, struct dentry *upperdentry, struct kstat *stat) { struct iattr attr = { .ia_valid = ATTR_SIZE, .ia_size = stat->size, }; return ovl_do_notify_change(ofs, upperdentry, &attr); } static int ovl_set_timestamps(struct ovl_fs *ofs, struct dentry *upperdentry, struct kstat *stat) { struct iattr attr = { .ia_valid = ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_CTIME, .ia_atime = stat->atime, .ia_mtime = stat->mtime, }; return ovl_do_notify_change(ofs, upperdentry, &attr); } int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upperdentry, struct kstat *stat) { int err = 0; if (!S_ISLNK(stat->mode)) { struct iattr attr = { .ia_valid = ATTR_MODE, .ia_mode = stat->mode, }; err = ovl_do_notify_change(ofs, upperdentry, &attr); } if (!err) { struct iattr attr = { .ia_valid = ATTR_UID | ATTR_GID, .ia_vfsuid = VFSUIDT_INIT(stat->uid), .ia_vfsgid = VFSGIDT_INIT(stat->gid), }; err = ovl_do_notify_change(ofs, upperdentry, &attr); } if (!err) ovl_set_timestamps(ofs, upperdentry, stat); return err; } struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, bool is_upper) { struct ovl_fh *fh; int fh_type, dwords; int buflen = MAX_HANDLE_SZ; uuid_t *uuid = &real->d_sb->s_uuid; int err; /* Make sure the real fid stays 32bit aligned */ BUILD_BUG_ON(OVL_FH_FID_OFFSET % 4); BUILD_BUG_ON(MAX_HANDLE_SZ + OVL_FH_FID_OFFSET > 255); fh = kzalloc(buflen + OVL_FH_FID_OFFSET, GFP_KERNEL); if (!fh) return ERR_PTR(-ENOMEM); /* * We encode a non-connectable file handle for non-dir, because we * only need to find the lower inode number and we don't want to pay * the price or reconnecting the dentry. */ dwords = buflen >> 2; fh_type = exportfs_encode_fh(real, (void *)fh->fb.fid, &dwords, 0); buflen = (dwords << 2); err = -EIO; if (WARN_ON(fh_type < 0) || WARN_ON(buflen > MAX_HANDLE_SZ) || WARN_ON(fh_type == FILEID_INVALID)) goto out_err; fh->fb.version = OVL_FH_VERSION; fh->fb.magic = OVL_FH_MAGIC; fh->fb.type = fh_type; fh->fb.flags = OVL_FH_FLAG_CPU_ENDIAN; /* * When we will want to decode an overlay dentry from this handle * and all layers are on the same fs, if we get a disconncted real * dentry when we decode fid, the only way to tell if we should assign * it to upperdentry or to lowerstack is by checking this flag. */ if (is_upper) fh->fb.flags |= OVL_FH_FLAG_PATH_UPPER; fh->fb.len = sizeof(fh->fb) + buflen; if (ovl_origin_uuid(ofs)) fh->fb.uuid = *uuid; return fh; out_err: kfree(fh); return ERR_PTR(err); } struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin) { /* * When lower layer doesn't support export operations store a 'null' fh, * so we can use the overlay.origin xattr to distignuish between a copy * up and a pure upper inode. */ if (!ovl_can_decode_fh(origin->d_sb)) return NULL; return ovl_encode_real_fh(ofs, origin, false); } int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, struct dentry *upper) { int err; /* * Do not fail when upper doesn't support xattrs. */ err = ovl_check_setxattr(ofs, upper, OVL_XATTR_ORIGIN, fh->buf, fh ? fh->fb.len : 0, 0); /* Ignore -EPERM from setting "user.*" on symlink/special */ return err == -EPERM ? 0 : err; } /* Store file handle of @upper dir in @index dir entry */ static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper, struct dentry *index) { const struct ovl_fh *fh; int err; fh = ovl_encode_real_fh(ofs, upper, true); if (IS_ERR(fh)) return PTR_ERR(fh); err = ovl_setxattr(ofs, index, OVL_XATTR_UPPER, fh->buf, fh->fb.len); kfree(fh); return err; } /* * Create and install index entry. * * Caller must hold i_mutex on indexdir. */ static int ovl_create_index(struct dentry *dentry, const struct ovl_fh *fh, struct dentry *upper) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *indexdir = ovl_indexdir(dentry->d_sb); struct inode *dir = d_inode(indexdir); struct dentry *index = NULL; struct dentry *temp = NULL; struct qstr name = { }; int err; /* * For now this is only used for creating index entry for directories, * because non-dir are copied up directly to index and then hardlinked * to upper dir. * * TODO: implement create index for non-dir, so we can call it when * encoding file handle for non-dir in case index does not exist. */ if (WARN_ON(!d_is_dir(dentry))) return -EIO; /* Directory not expected to be indexed before copy up */ if (WARN_ON(ovl_test_flag(OVL_INDEX, d_inode(dentry)))) return -EIO; err = ovl_get_index_name_fh(fh, &name); if (err) return err; temp = ovl_create_temp(ofs, indexdir, OVL_CATTR(S_IFDIR | 0)); err = PTR_ERR(temp); if (IS_ERR(temp)) goto free_name; err = ovl_set_upper_fh(ofs, upper, temp); if (err) goto out; index = ovl_lookup_upper(ofs, name.name, indexdir, name.len); if (IS_ERR(index)) { err = PTR_ERR(index); } else { err = ovl_do_rename(ofs, dir, temp, dir, index, 0); dput(index); } out: if (err) ovl_cleanup(ofs, dir, temp); dput(temp); free_name: kfree(name.name); return err; } struct ovl_copy_up_ctx { struct dentry *parent; struct dentry *dentry; struct path lowerpath; struct kstat stat; struct kstat pstat; const char *link; struct dentry *destdir; struct qstr destname; struct dentry *workdir; const struct ovl_fh *origin_fh; bool origin; bool indexed; bool metacopy; bool metacopy_digest; }; static int ovl_link_up(struct ovl_copy_up_ctx *c) { int err; struct dentry *upper; struct dentry *upperdir = ovl_dentry_upper(c->parent); struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb); struct inode *udir = d_inode(upperdir); ovl_start_write(c->dentry); /* Mark parent "impure" because it may now contain non-pure upper */ err = ovl_set_impure(c->parent, upperdir); if (err) goto out; err = ovl_set_nlink_lower(c->dentry); if (err) goto out; inode_lock_nested(udir, I_MUTEX_PARENT); upper = ovl_lookup_upper(ofs, c->dentry->d_name.name, upperdir, c->dentry->d_name.len); err = PTR_ERR(upper); if (!IS_ERR(upper)) { err = ovl_do_link(ofs, ovl_dentry_upper(c->dentry), udir, upper); dput(upper); if (!err) { /* Restore timestamps on parent (best effort) */ ovl_set_timestamps(ofs, upperdir, &c->pstat); ovl_dentry_set_upper_alias(c->dentry); ovl_dentry_update_reval(c->dentry, upper); } } inode_unlock(udir); if (err) goto out; err = ovl_set_nlink_upper(c->dentry); out: ovl_end_write(c->dentry); return err; } static int ovl_copy_up_data(struct ovl_copy_up_ctx *c, const struct path *temp) { struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb); struct file *new_file; int err; if (!S_ISREG(c->stat.mode) || c->metacopy || !c->stat.size) return 0; new_file = ovl_path_open(temp, O_LARGEFILE | O_WRONLY); if (IS_ERR(new_file)) return PTR_ERR(new_file); err = ovl_copy_up_file(ofs, c->dentry, new_file, c->stat.size); fput(new_file); return err; } static int ovl_copy_up_metadata(struct ovl_copy_up_ctx *c, struct dentry *temp) { struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb); struct inode *inode = d_inode(c->dentry); struct path upperpath = { .mnt = ovl_upper_mnt(ofs), .dentry = temp }; int err; err = ovl_copy_xattr(c->dentry->d_sb, &c->lowerpath, temp); if (err) return err; if (inode->i_flags & OVL_COPY_I_FLAGS_MASK && (S_ISREG(c->stat.mode) || S_ISDIR(c->stat.mode))) { /* * Copy the fileattr inode flags that are the source of already * copied i_flags */ err = ovl_copy_fileattr(inode, &c->lowerpath, &upperpath); if (err) return err; } /* * Store identifier of lower inode in upper inode xattr to * allow lookup of the copy up origin inode. * * Don't set origin when we are breaking the association with a lower * hard link. */ if (c->origin) { err = ovl_set_origin_fh(ofs, c->origin_fh, temp); if (err) return err; } if (c->metacopy) { struct path lowerdatapath; struct ovl_metacopy metacopy_data = OVL_METACOPY_INIT; ovl_path_lowerdata(c->dentry, &lowerdatapath); if (WARN_ON_ONCE(lowerdatapath.dentry == NULL)) return -EIO; err = ovl_get_verity_digest(ofs, &lowerdatapath, &metacopy_data); if (err) return err; if (metacopy_data.digest_algo) c->metacopy_digest = true; err = ovl_set_metacopy_xattr(ofs, temp, &metacopy_data); if (err) return err; } inode_lock(temp->d_inode); if (S_ISREG(c->stat.mode)) err = ovl_set_size(ofs, temp, &c->stat); if (!err) err = ovl_set_attr(ofs, temp, &c->stat); inode_unlock(temp->d_inode); return err; } struct ovl_cu_creds { const struct cred *old; struct cred *new; }; static int ovl_prep_cu_creds(struct dentry *dentry, struct ovl_cu_creds *cc) { int err; cc->old = cc->new = NULL; err = security_inode_copy_up(dentry, &cc->new); if (err < 0) return err; if (cc->new) cc->old = override_creds(cc->new); return 0; } static void ovl_revert_cu_creds(struct ovl_cu_creds *cc) { if (cc->new) { revert_creds(cc->old); put_cred(cc->new); } } /* * Copyup using workdir to prepare temp file. Used when copying up directories, * special files or when upper fs doesn't support O_TMPFILE. */ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c) { struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb); struct inode *inode; struct inode *udir = d_inode(c->destdir), *wdir = d_inode(c->workdir); struct path path = { .mnt = ovl_upper_mnt(ofs) }; struct dentry *temp, *upper; struct ovl_cu_creds cc; int err; struct ovl_cattr cattr = { /* Can't properly set mode on creation because of the umask */ .mode = c->stat.mode & S_IFMT, .rdev = c->stat.rdev, .link = c->link }; err = ovl_prep_cu_creds(c->dentry, &cc); if (err) return err; ovl_start_write(c->dentry); inode_lock(wdir); temp = ovl_create_temp(ofs, c->workdir, &cattr); inode_unlock(wdir); ovl_end_write(c->dentry); ovl_revert_cu_creds(&cc); if (IS_ERR(temp)) return PTR_ERR(temp); /* * Copy up data first and then xattrs. Writing data after * xattrs will remove security.capability xattr automatically. */ path.dentry = temp; err = ovl_copy_up_data(c, &path); /* * We cannot hold lock_rename() throughout this helper, because or * lock ordering with sb_writers, which shouldn't be held when calling * ovl_copy_up_data(), so lock workdir and destdir and make sure that * temp wasn't moved before copy up completion or cleanup. * If temp was moved, abort without the cleanup. */ ovl_start_write(c->dentry); if (lock_rename(c->workdir, c->destdir) != NULL || temp->d_parent != c->workdir) { err = -EIO; goto unlock; } else if (err) { goto cleanup; } err = ovl_copy_up_metadata(c, temp); if (err) goto cleanup; if (S_ISDIR(c->stat.mode) && c->indexed) { err = ovl_create_index(c->dentry, c->origin_fh, temp); if (err) goto cleanup; } upper = ovl_lookup_upper(ofs, c->destname.name, c->destdir, c->destname.len); err = PTR_ERR(upper); if (IS_ERR(upper)) goto cleanup; err = ovl_do_rename(ofs, wdir, temp, udir, upper, 0); dput(upper); if (err) goto cleanup; inode = d_inode(c->dentry); if (c->metacopy_digest) ovl_set_flag(OVL_HAS_DIGEST, inode); else ovl_clear_flag(OVL_HAS_DIGEST, inode); ovl_clear_flag(OVL_VERIFIED_DIGEST, inode); if (!c->metacopy) ovl_set_upperdata(inode); ovl_inode_update(inode, temp); if (S_ISDIR(inode->i_mode)) ovl_set_flag(OVL_WHITEOUTS, inode); unlock: unlock_rename(c->workdir, c->destdir); ovl_end_write(c->dentry); return err; cleanup: ovl_cleanup(ofs, wdir, temp); dput(temp); goto unlock; } /* Copyup using O_TMPFILE which does not require cross dir locking */ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c) { struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb); struct inode *udir = d_inode(c->destdir); struct dentry *temp, *upper; struct file *tmpfile; struct ovl_cu_creds cc; int err; err = ovl_prep_cu_creds(c->dentry, &cc); if (err) return err; ovl_start_write(c->dentry); tmpfile = ovl_do_tmpfile(ofs, c->workdir, c->stat.mode); ovl_end_write(c->dentry); ovl_revert_cu_creds(&cc); if (IS_ERR(tmpfile)) return PTR_ERR(tmpfile); temp = tmpfile->f_path.dentry; if (!c->metacopy && c->stat.size) { err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size); if (err) goto out_fput; } ovl_start_write(c->dentry); err = ovl_copy_up_metadata(c, temp); if (err) goto out; inode_lock_nested(udir, I_MUTEX_PARENT); upper = ovl_lookup_upper(ofs, c->destname.name, c->destdir, c->destname.len); err = PTR_ERR(upper); if (!IS_ERR(upper)) { err = ovl_do_link(ofs, temp, udir, upper); dput(upper); } inode_unlock(udir); if (err) goto out; if (c->metacopy_digest) ovl_set_flag(OVL_HAS_DIGEST, d_inode(c->dentry)); else ovl_clear_flag(OVL_HAS_DIGEST, d_inode(c->dentry)); ovl_clear_flag(OVL_VERIFIED_DIGEST, d_inode(c->dentry)); if (!c->metacopy) ovl_set_upperdata(d_inode(c->dentry)); ovl_inode_update(d_inode(c->dentry), dget(temp)); out: ovl_end_write(c->dentry); out_fput: fput(tmpfile); return err; } /* * Copy up a single dentry * * All renames start with copy up of source if necessary. The actual * rename will only proceed once the copy up was successful. Copy up uses * upper parent i_mutex for exclusion. Since rename can change d_parent it * is possible that the copy up will lock the old parent. At that point * the file will have already been copied up anyway. */ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) { int err; struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb); struct dentry *origin = c->lowerpath.dentry; struct ovl_fh *fh = NULL; bool to_index = false; /* * Indexed non-dir is copied up directly to the index entry and then * hardlinked to upper dir. Indexed dir is copied up to indexdir, * then index entry is created and then copied up dir installed. * Copying dir up to indexdir instead of workdir simplifies locking. */ if (ovl_need_index(c->dentry)) { c->indexed = true; if (S_ISDIR(c->stat.mode)) c->workdir = ovl_indexdir(c->dentry->d_sb); else to_index = true; } if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || to_index) { fh = ovl_get_origin_fh(ofs, origin); if (IS_ERR(fh)) return PTR_ERR(fh); /* origin_fh may be NULL */ c->origin_fh = fh; c->origin = true; } if (to_index) { c->destdir = ovl_indexdir(c->dentry->d_sb); err = ovl_get_index_name(ofs, origin, &c->destname); if (err) goto out_free_fh; } else if (WARN_ON(!c->parent)) { /* Disconnected dentry must be copied up to index dir */ err = -EIO; goto out_free_fh; } else { /* * Mark parent "impure" because it may now contain non-pure * upper */ ovl_start_write(c->dentry); err = ovl_set_impure(c->parent, c->destdir); ovl_end_write(c->dentry); if (err) goto out_free_fh; } /* Should we copyup with O_TMPFILE or with workdir? */ if (S_ISREG(c->stat.mode) && ofs->tmpfile) err = ovl_copy_up_tmpfile(c); else err = ovl_copy_up_workdir(c); if (err) goto out; if (c->indexed) ovl_set_flag(OVL_INDEX, d_inode(c->dentry)); ovl_start_write(c->dentry); if (to_index) { /* Initialize nlink for copy up of disconnected dentry */ err = ovl_set_nlink_upper(c->dentry); } else { struct inode *udir = d_inode(c->destdir); /* Restore timestamps on parent (best effort) */ inode_lock(udir); ovl_set_timestamps(ofs, c->destdir, &c->pstat); inode_unlock(udir); ovl_dentry_set_upper_alias(c->dentry); ovl_dentry_update_reval(c->dentry, ovl_dentry_upper(c->dentry)); } ovl_end_write(c->dentry); out: if (to_index) kfree(c->destname.name); out_free_fh: kfree(fh); return err; } static bool ovl_need_meta_copy_up(struct dentry *dentry, umode_t mode, int flags) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); if (!ofs->config.metacopy) return false; if (!S_ISREG(mode)) return false; if (flags && ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC))) return false; /* Fall back to full copy if no fsverity on source data and we require verity */ if (ofs->config.verity_mode == OVL_VERITY_REQUIRE) { struct path lowerdata; ovl_path_lowerdata(dentry, &lowerdata); if (WARN_ON_ONCE(lowerdata.dentry == NULL) || ovl_ensure_verity_loaded(&lowerdata) || !fsverity_active(d_inode(lowerdata.dentry))) { return false; } } return true; } static ssize_t ovl_getxattr_value(const struct path *path, char *name, char **value) { ssize_t res; char *buf; res = ovl_do_getxattr(path, name, NULL, 0); if (res == -ENODATA || res == -EOPNOTSUPP) res = 0; if (res > 0) { buf = kzalloc(res, GFP_KERNEL); if (!buf) return -ENOMEM; res = ovl_do_getxattr(path, name, buf, res); if (res < 0) kfree(buf); else *value = buf; } return res; } /* Copy up data of an inode which was copied up metadata only in the past. */ static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c) { struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb); struct path upperpath; int err; char *capability = NULL; ssize_t cap_size; ovl_path_upper(c->dentry, &upperpath); if (WARN_ON(upperpath.dentry == NULL)) return -EIO; if (c->stat.size) { err = cap_size = ovl_getxattr_value(&upperpath, XATTR_NAME_CAPS, &capability); if (cap_size < 0) goto out; } err = ovl_copy_up_data(c, &upperpath); if (err) goto out_free; /* * Writing to upper file will clear security.capability xattr. We * don't want that to happen for normal copy-up operation. */ ovl_start_write(c->dentry); if (capability) { err = ovl_do_setxattr(ofs, upperpath.dentry, XATTR_NAME_CAPS, capability, cap_size, 0); } if (!err) { err = ovl_removexattr(ofs, upperpath.dentry, OVL_XATTR_METACOPY); } ovl_end_write(c->dentry); if (err) goto out_free; ovl_clear_flag(OVL_HAS_DIGEST, d_inode(c->dentry)); ovl_clear_flag(OVL_VERIFIED_DIGEST, d_inode(c->dentry)); ovl_set_upperdata(d_inode(c->dentry)); out_free: kfree(capability); out: return err; } static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, int flags) { int err; DEFINE_DELAYED_CALL(done); struct path parentpath; struct ovl_copy_up_ctx ctx = { .parent = parent, .dentry = dentry, .workdir = ovl_workdir(dentry), }; if (WARN_ON(!ctx.workdir)) return -EROFS; ovl_path_lower(dentry, &ctx.lowerpath); err = vfs_getattr(&ctx.lowerpath, &ctx.stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); if (err) return err; if (!kuid_has_mapping(current_user_ns(), ctx.stat.uid) || !kgid_has_mapping(current_user_ns(), ctx.stat.gid)) return -EOVERFLOW; ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags); if (parent) { ovl_path_upper(parent, &parentpath); ctx.destdir = parentpath.dentry; ctx.destname = dentry->d_name; err = vfs_getattr(&parentpath, &ctx.pstat, STATX_ATIME | STATX_MTIME, AT_STATX_SYNC_AS_STAT); if (err) return err; } /* maybe truncate regular file. this has no effect on dirs */ if (flags & O_TRUNC) ctx.stat.size = 0; if (S_ISLNK(ctx.stat.mode)) { ctx.link = vfs_get_link(ctx.lowerpath.dentry, &done); if (IS_ERR(ctx.link)) return PTR_ERR(ctx.link); } err = ovl_copy_up_start(dentry, flags); /* err < 0: interrupted, err > 0: raced with another copy-up */ if (unlikely(err)) { if (err > 0) err = 0; } else { if (!ovl_dentry_upper(dentry)) err = ovl_do_copy_up(&ctx); if (!err && parent && !ovl_dentry_has_upper_alias(dentry)) err = ovl_link_up(&ctx); if (!err && ovl_dentry_needs_data_copy_up_locked(dentry, flags)) err = ovl_copy_up_meta_inode_data(&ctx); ovl_copy_up_end(dentry); } do_delayed_call(&done); return err; } static int ovl_copy_up_flags(struct dentry *dentry, int flags) { int err = 0; const struct cred *old_cred; bool disconnected = (dentry->d_flags & DCACHE_DISCONNECTED); /* * With NFS export, copy up can get called for a disconnected non-dir. * In this case, we will copy up lower inode to index dir without * linking it to upper dir. */ if (WARN_ON(disconnected && d_is_dir(dentry))) return -EIO; /* * We may not need lowerdata if we are only doing metacopy up, but it is * not very important to optimize this case, so do lazy lowerdata lookup * before any copy up, so we can do it before taking ovl_inode_lock(). */ err = ovl_verify_lowerdata(dentry); if (err) return err; old_cred = ovl_override_creds(dentry->d_sb); while (!err) { struct dentry *next; struct dentry *parent = NULL; if (ovl_already_copied_up(dentry, flags)) break; next = dget(dentry); /* find the topmost dentry not yet copied up */ for (; !disconnected;) { parent = dget_parent(next); if (ovl_dentry_upper(parent)) break; dput(next); next = parent; } err = ovl_copy_up_one(parent, next, flags); dput(parent); dput(next); } revert_creds(old_cred); return err; } static bool ovl_open_need_copy_up(struct dentry *dentry, int flags) { /* Copy up of disconnected dentry does not set upper alias */ if (ovl_already_copied_up(dentry, flags)) return false; if (special_file(d_inode(dentry)->i_mode)) return false; if (!ovl_open_flags_need_copy_up(flags)) return false; return true; } int ovl_maybe_copy_up(struct dentry *dentry, int flags) { if (!ovl_open_need_copy_up(dentry, flags)) return 0; return ovl_copy_up_flags(dentry, flags); } int ovl_copy_up_with_data(struct dentry *dentry) { return ovl_copy_up_flags(dentry, O_WRONLY); } int ovl_copy_up(struct dentry *dentry) { return ovl_copy_up_flags(dentry, 0); } |
| 2128 2064 2070 1 3 4 5 2123 2077 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 | /* * Cryptographic API. * * Glue code for the SHA256 Secure Hash Algorithm assembler * implementation using supplemental SSE3 / AVX / AVX2 instructions. * * This file is based on sha256_generic.c * * Copyright (C) 2013 Intel Corporation. * * Author: * Tim Chen <tim.c.chen@linux.intel.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free * Software Foundation; either version 2 of the License, or (at your option) * any later version. * * 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) KBUILD_MODNAME ": " fmt #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <crypto/sha2.h> #include <crypto/sha256_base.h> #include <linux/string.h> #include <asm/cpu_device_id.h> #include <asm/simd.h> asmlinkage void sha256_transform_ssse3(struct sha256_state *state, const u8 *data, int blocks); static const struct x86_cpu_id module_cpu_ids[] = { X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); static int _sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha256_block_fn *sha256_xform) { struct sha256_state *sctx = shash_desc_ctx(desc); if (!crypto_simd_usable() || (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE) return crypto_sha256_update(desc, data, len); /* * Make sure struct sha256_state begins directly with the SHA256 * 256-bit internal state, as this is what the asm functions expect. */ BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); kernel_fpu_begin(); sha256_base_do_update(desc, data, len, sha256_xform); kernel_fpu_end(); return 0; } static int sha256_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out, sha256_block_fn *sha256_xform) { if (!crypto_simd_usable()) return crypto_sha256_finup(desc, data, len, out); kernel_fpu_begin(); if (len) sha256_base_do_update(desc, data, len, sha256_xform); sha256_base_do_finalize(desc, sha256_xform); kernel_fpu_end(); return sha256_base_finish(desc, out); } static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_transform_ssse3); } static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_transform_ssse3); } /* Add padding and return the message digest. */ static int sha256_ssse3_final(struct shash_desc *desc, u8 *out) { return sha256_ssse3_finup(desc, NULL, 0, out); } static int sha256_ssse3_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_ssse3_finup(desc, data, len, out); } static struct shash_alg sha256_ssse3_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_ssse3_update, .final = sha256_ssse3_final, .finup = sha256_ssse3_finup, .digest = sha256_ssse3_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-ssse3", .cra_priority = 150, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_ssse3_update, .final = sha256_ssse3_final, .finup = sha256_ssse3_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-ssse3", .cra_priority = 150, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static int register_sha256_ssse3(void) { if (boot_cpu_has(X86_FEATURE_SSSE3)) return crypto_register_shashes(sha256_ssse3_algs, ARRAY_SIZE(sha256_ssse3_algs)); return 0; } static void unregister_sha256_ssse3(void) { if (boot_cpu_has(X86_FEATURE_SSSE3)) crypto_unregister_shashes(sha256_ssse3_algs, ARRAY_SIZE(sha256_ssse3_algs)); } asmlinkage void sha256_transform_avx(struct sha256_state *state, const u8 *data, int blocks); static int sha256_avx_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_transform_avx); } static int sha256_avx_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_transform_avx); } static int sha256_avx_final(struct shash_desc *desc, u8 *out) { return sha256_avx_finup(desc, NULL, 0, out); } static int sha256_avx_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_avx_finup(desc, data, len, out); } static struct shash_alg sha256_avx_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_avx_update, .final = sha256_avx_final, .finup = sha256_avx_finup, .digest = sha256_avx_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-avx", .cra_priority = 160, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_avx_update, .final = sha256_avx_final, .finup = sha256_avx_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-avx", .cra_priority = 160, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static bool avx_usable(void) { if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { if (boot_cpu_has(X86_FEATURE_AVX)) pr_info("AVX detected but unusable.\n"); return false; } return true; } static int register_sha256_avx(void) { if (avx_usable()) return crypto_register_shashes(sha256_avx_algs, ARRAY_SIZE(sha256_avx_algs)); return 0; } static void unregister_sha256_avx(void) { if (avx_usable()) crypto_unregister_shashes(sha256_avx_algs, ARRAY_SIZE(sha256_avx_algs)); } asmlinkage void sha256_transform_rorx(struct sha256_state *state, const u8 *data, int blocks); static int sha256_avx2_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_transform_rorx); } static int sha256_avx2_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_transform_rorx); } static int sha256_avx2_final(struct shash_desc *desc, u8 *out) { return sha256_avx2_finup(desc, NULL, 0, out); } static int sha256_avx2_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_avx2_finup(desc, data, len, out); } static struct shash_alg sha256_avx2_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_avx2_update, .final = sha256_avx2_final, .finup = sha256_avx2_finup, .digest = sha256_avx2_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-avx2", .cra_priority = 170, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_avx2_update, .final = sha256_avx2_final, .finup = sha256_avx2_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-avx2", .cra_priority = 170, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static bool avx2_usable(void) { if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI2)) return true; return false; } static int register_sha256_avx2(void) { if (avx2_usable()) return crypto_register_shashes(sha256_avx2_algs, ARRAY_SIZE(sha256_avx2_algs)); return 0; } static void unregister_sha256_avx2(void) { if (avx2_usable()) crypto_unregister_shashes(sha256_avx2_algs, ARRAY_SIZE(sha256_avx2_algs)); } #ifdef CONFIG_AS_SHA256_NI asmlinkage void sha256_ni_transform(struct sha256_state *digest, const u8 *data, int rounds); static int sha256_ni_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_ni_transform); } static int sha256_ni_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_ni_transform); } static int sha256_ni_final(struct shash_desc *desc, u8 *out) { return sha256_ni_finup(desc, NULL, 0, out); } static int sha256_ni_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_ni_finup(desc, data, len, out); } static struct shash_alg sha256_ni_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_ni_update, .final = sha256_ni_final, .finup = sha256_ni_finup, .digest = sha256_ni_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-ni", .cra_priority = 250, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_ni_update, .final = sha256_ni_final, .finup = sha256_ni_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-ni", .cra_priority = 250, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static int register_sha256_ni(void) { if (boot_cpu_has(X86_FEATURE_SHA_NI)) return crypto_register_shashes(sha256_ni_algs, ARRAY_SIZE(sha256_ni_algs)); return 0; } static void unregister_sha256_ni(void) { if (boot_cpu_has(X86_FEATURE_SHA_NI)) crypto_unregister_shashes(sha256_ni_algs, ARRAY_SIZE(sha256_ni_algs)); } #else static inline int register_sha256_ni(void) { return 0; } static inline void unregister_sha256_ni(void) { } #endif static int __init sha256_ssse3_mod_init(void) { if (!x86_match_cpu(module_cpu_ids)) return -ENODEV; if (register_sha256_ssse3()) goto fail; if (register_sha256_avx()) { unregister_sha256_ssse3(); goto fail; } if (register_sha256_avx2()) { unregister_sha256_avx(); unregister_sha256_ssse3(); goto fail; } if (register_sha256_ni()) { unregister_sha256_avx2(); unregister_sha256_avx(); unregister_sha256_ssse3(); goto fail; } return 0; fail: return -ENODEV; } static void __exit sha256_ssse3_mod_fini(void) { unregister_sha256_ni(); unregister_sha256_avx2(); unregister_sha256_avx(); unregister_sha256_ssse3(); } module_init(sha256_ssse3_mod_init); module_exit(sha256_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated"); MODULE_ALIAS_CRYPTO("sha256"); MODULE_ALIAS_CRYPTO("sha256-ssse3"); MODULE_ALIAS_CRYPTO("sha256-avx"); MODULE_ALIAS_CRYPTO("sha256-avx2"); MODULE_ALIAS_CRYPTO("sha224"); MODULE_ALIAS_CRYPTO("sha224-ssse3"); MODULE_ALIAS_CRYPTO("sha224-avx"); MODULE_ALIAS_CRYPTO("sha224-avx2"); #ifdef CONFIG_AS_SHA256_NI MODULE_ALIAS_CRYPTO("sha256-ni"); MODULE_ALIAS_CRYPTO("sha224-ni"); #endif |
| 56 54 543 9 669 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Hash algorithms. * * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_HASH_H #define _CRYPTO_INTERNAL_HASH_H #include <crypto/algapi.h> #include <crypto/hash.h> struct ahash_request; struct scatterlist; struct crypto_hash_walk { char *data; unsigned int offset; unsigned int flags; struct page *pg; unsigned int entrylen; unsigned int total; struct scatterlist *sg; }; struct ahash_instance { void (*free)(struct ahash_instance *inst); union { struct { char head[offsetof(struct ahash_alg, halg.base)]; struct crypto_instance base; } s; struct ahash_alg alg; }; }; struct shash_instance { void (*free)(struct shash_instance *inst); union { struct { char head[offsetof(struct shash_alg, base)]; struct crypto_instance base; } s; struct shash_alg alg; }; }; struct crypto_ahash_spawn { struct crypto_spawn base; }; struct crypto_shash_spawn { struct crypto_spawn base; }; int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err); int crypto_hash_walk_first(struct ahash_request *req, struct crypto_hash_walk *walk); static inline int crypto_hash_walk_last(struct crypto_hash_walk *walk) { return !(walk->entrylen | walk->total); } int crypto_register_ahash(struct ahash_alg *alg); void crypto_unregister_ahash(struct ahash_alg *alg); int crypto_register_ahashes(struct ahash_alg *algs, int count); void crypto_unregister_ahashes(struct ahash_alg *algs, int count); int ahash_register_instance(struct crypto_template *tmpl, struct ahash_instance *inst); int shash_no_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); static inline bool crypto_shash_alg_has_setkey(struct shash_alg *alg) { return alg->setkey != shash_no_setkey; } static inline bool crypto_shash_alg_needs_key(struct shash_alg *alg) { return crypto_shash_alg_has_setkey(alg) && !(alg->base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY); } bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg); int crypto_grab_ahash(struct crypto_ahash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_ahash(struct crypto_ahash_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct hash_alg_common *crypto_spawn_ahash_alg( struct crypto_ahash_spawn *spawn) { return __crypto_hash_alg_common(spawn->base.alg); } int crypto_register_shash(struct shash_alg *alg); void crypto_unregister_shash(struct shash_alg *alg); int crypto_register_shashes(struct shash_alg *algs, int count); void crypto_unregister_shashes(struct shash_alg *algs, int count); int shash_register_instance(struct crypto_template *tmpl, struct shash_instance *inst); void shash_free_singlespawn_instance(struct shash_instance *inst); int crypto_grab_shash(struct crypto_shash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_shash(struct crypto_shash_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct shash_alg *crypto_spawn_shash_alg( struct crypto_shash_spawn *spawn) { return __crypto_shash_alg(spawn->base.alg); } int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc); static inline void *crypto_ahash_ctx(struct crypto_ahash *tfm) { return crypto_tfm_ctx(crypto_ahash_tfm(tfm)); } static inline void *crypto_ahash_ctx_dma(struct crypto_ahash *tfm) { return crypto_tfm_ctx_dma(crypto_ahash_tfm(tfm)); } static inline struct ahash_alg *__crypto_ahash_alg(struct crypto_alg *alg) { return container_of(__crypto_hash_alg_common(alg), struct ahash_alg, halg); } static inline struct ahash_alg *crypto_ahash_alg(struct crypto_ahash *hash) { return container_of(crypto_hash_alg_common(hash), struct ahash_alg, halg); } static inline void crypto_ahash_set_statesize(struct crypto_ahash *tfm, unsigned int size) { tfm->statesize = size; } static inline void crypto_ahash_set_reqsize(struct crypto_ahash *tfm, unsigned int reqsize) { tfm->reqsize = reqsize; } static inline void crypto_ahash_set_reqsize_dma(struct crypto_ahash *ahash, unsigned int reqsize) { reqsize += crypto_dma_align() & ~(crypto_tfm_ctx_alignment() - 1); ahash->reqsize = reqsize; } static inline struct crypto_instance *ahash_crypto_instance( struct ahash_instance *inst) { return &inst->s.base; } static inline struct ahash_instance *ahash_instance( struct crypto_instance *inst) { return container_of(inst, struct ahash_instance, s.base); } static inline struct ahash_instance *ahash_alg_instance( struct crypto_ahash *ahash) { return ahash_instance(crypto_tfm_alg_instance(&ahash->base)); } static inline void *ahash_instance_ctx(struct ahash_instance *inst) { return crypto_instance_ctx(ahash_crypto_instance(inst)); } static inline void *ahash_request_ctx_dma(struct ahash_request *req) { unsigned int align = crypto_dma_align(); if (align <= crypto_tfm_ctx_alignment()) align = 1; return PTR_ALIGN(ahash_request_ctx(req), align); } static inline void ahash_request_complete(struct ahash_request *req, int err) { crypto_request_complete(&req->base, err); } static inline u32 ahash_request_flags(struct ahash_request *req) { return req->base.flags; } static inline struct crypto_ahash *crypto_spawn_ahash( struct crypto_ahash_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline int ahash_enqueue_request(struct crypto_queue *queue, struct ahash_request *request) { return crypto_enqueue_request(queue, &request->base); } static inline struct ahash_request *ahash_dequeue_request( struct crypto_queue *queue) { return ahash_request_cast(crypto_dequeue_request(queue)); } static inline void *crypto_shash_ctx(struct crypto_shash *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline struct crypto_instance *shash_crypto_instance( struct shash_instance *inst) { return &inst->s.base; } static inline struct shash_instance *shash_instance( struct crypto_instance *inst) { return container_of(inst, struct shash_instance, s.base); } static inline struct shash_instance *shash_alg_instance( struct crypto_shash *shash) { return shash_instance(crypto_tfm_alg_instance(&shash->base)); } static inline void *shash_instance_ctx(struct shash_instance *inst) { return crypto_instance_ctx(shash_crypto_instance(inst)); } static inline struct crypto_shash *crypto_spawn_shash( struct crypto_shash_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline struct crypto_shash *__crypto_shash_cast(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_shash, base); } #endif /* _CRYPTO_INTERNAL_HASH_H */ |
| 39 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2016 Facebook */ #ifndef __BPF_LRU_LIST_H_ #define __BPF_LRU_LIST_H_ #include <linux/cache.h> #include <linux/list.h> #include <linux/spinlock_types.h> #define NR_BPF_LRU_LIST_T (3) #define NR_BPF_LRU_LIST_COUNT (2) #define NR_BPF_LRU_LOCAL_LIST_T (2) #define BPF_LOCAL_LIST_T_OFFSET NR_BPF_LRU_LIST_T enum bpf_lru_list_type { BPF_LRU_LIST_T_ACTIVE, BPF_LRU_LIST_T_INACTIVE, BPF_LRU_LIST_T_FREE, BPF_LRU_LOCAL_LIST_T_FREE, BPF_LRU_LOCAL_LIST_T_PENDING, }; struct bpf_lru_node { struct list_head list; u16 cpu; u8 type; u8 ref; }; struct bpf_lru_list { struct list_head lists[NR_BPF_LRU_LIST_T]; unsigned int counts[NR_BPF_LRU_LIST_COUNT]; /* The next inactive list rotation starts from here */ struct list_head *next_inactive_rotation; raw_spinlock_t lock ____cacheline_aligned_in_smp; }; struct bpf_lru_locallist { struct list_head lists[NR_BPF_LRU_LOCAL_LIST_T]; u16 next_steal; raw_spinlock_t lock; }; struct bpf_common_lru { struct bpf_lru_list lru_list; struct bpf_lru_locallist __percpu *local_list; }; typedef bool (*del_from_htab_func)(void *arg, struct bpf_lru_node *node); struct bpf_lru { union { struct bpf_common_lru common_lru; struct bpf_lru_list __percpu *percpu_lru; }; del_from_htab_func del_from_htab; void *del_arg; unsigned int hash_offset; unsigned int nr_scans; bool percpu; }; static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node) { if (!READ_ONCE(node->ref)) WRITE_ONCE(node->ref, 1); } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, del_from_htab_func del_from_htab, void *delete_arg); void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, u32 elem_size, u32 nr_elems); void bpf_lru_destroy(struct bpf_lru *lru); struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash); void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node); #endif |
| 1 1 2 2 2 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * v4l2-dv-timings - dv-timings helper functions * * Copyright 2013 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/rational.h> #include <linux/videodev2.h> #include <linux/v4l2-dv-timings.h> #include <media/v4l2-dv-timings.h> #include <linux/math64.h> #include <linux/hdmi.h> #include <media/cec.h> MODULE_AUTHOR("Hans Verkuil"); MODULE_DESCRIPTION("V4L2 DV Timings Helper Functions"); MODULE_LICENSE("GPL"); const struct v4l2_dv_timings v4l2_dv_timings_presets[] = { V4L2_DV_BT_CEA_640X480P59_94, V4L2_DV_BT_CEA_720X480I59_94, V4L2_DV_BT_CEA_720X480P59_94, V4L2_DV_BT_CEA_720X576I50, V4L2_DV_BT_CEA_720X576P50, V4L2_DV_BT_CEA_1280X720P24, V4L2_DV_BT_CEA_1280X720P25, V4L2_DV_BT_CEA_1280X720P30, V4L2_DV_BT_CEA_1280X720P50, V4L2_DV_BT_CEA_1280X720P60, V4L2_DV_BT_CEA_1920X1080P24, V4L2_DV_BT_CEA_1920X1080P25, V4L2_DV_BT_CEA_1920X1080P30, V4L2_DV_BT_CEA_1920X1080I50, V4L2_DV_BT_CEA_1920X1080P50, V4L2_DV_BT_CEA_1920X1080I60, V4L2_DV_BT_CEA_1920X1080P60, V4L2_DV_BT_DMT_640X350P85, V4L2_DV_BT_DMT_640X400P85, V4L2_DV_BT_DMT_720X400P85, V4L2_DV_BT_DMT_640X480P72, V4L2_DV_BT_DMT_640X480P75, V4L2_DV_BT_DMT_640X480P85, V4L2_DV_BT_DMT_800X600P56, V4L2_DV_BT_DMT_800X600P60, V4L2_DV_BT_DMT_800X600P72, V4L2_DV_BT_DMT_800X600P75, V4L2_DV_BT_DMT_800X600P85, V4L2_DV_BT_DMT_800X600P120_RB, V4L2_DV_BT_DMT_848X480P60, V4L2_DV_BT_DMT_1024X768I43, V4L2_DV_BT_DMT_1024X768P60, V4L2_DV_BT_DMT_1024X768P70, V4L2_DV_BT_DMT_1024X768P75, V4L2_DV_BT_DMT_1024X768P85, V4L2_DV_BT_DMT_1024X768P120_RB, V4L2_DV_BT_DMT_1152X864P75, V4L2_DV_BT_DMT_1280X768P60_RB, V4L2_DV_BT_DMT_1280X768P60, V4L2_DV_BT_DMT_1280X768P75, V4L2_DV_BT_DMT_1280X768P85, V4L2_DV_BT_DMT_1280X768P120_RB, V4L2_DV_BT_DMT_1280X800P60_RB, V4L2_DV_BT_DMT_1280X800P60, V4L2_DV_BT_DMT_1280X800P75, V4L2_DV_BT_DMT_1280X800P85, V4L2_DV_BT_DMT_1280X800P120_RB, V4L2_DV_BT_DMT_1280X960P60, V4L2_DV_BT_DMT_1280X960P85, V4L2_DV_BT_DMT_1280X960P120_RB, V4L2_DV_BT_DMT_1280X1024P60, V4L2_DV_BT_DMT_1280X1024P75, V4L2_DV_BT_DMT_1280X1024P85, V4L2_DV_BT_DMT_1280X1024P120_RB, V4L2_DV_BT_DMT_1360X768P60, V4L2_DV_BT_DMT_1360X768P120_RB, V4L2_DV_BT_DMT_1366X768P60, V4L2_DV_BT_DMT_1366X768P60_RB, V4L2_DV_BT_DMT_1400X1050P60_RB, V4L2_DV_BT_DMT_1400X1050P60, V4L2_DV_BT_DMT_1400X1050P75, V4L2_DV_BT_DMT_1400X1050P85, V4L2_DV_BT_DMT_1400X1050P120_RB, V4L2_DV_BT_DMT_1440X900P60_RB, V4L2_DV_BT_DMT_1440X900P60, V4L2_DV_BT_DMT_1440X900P75, V4L2_DV_BT_DMT_1440X900P85, V4L2_DV_BT_DMT_1440X900P120_RB, V4L2_DV_BT_DMT_1600X900P60_RB, V4L2_DV_BT_DMT_1600X1200P60, V4L2_DV_BT_DMT_1600X1200P65, V4L2_DV_BT_DMT_1600X1200P70, V4L2_DV_BT_DMT_1600X1200P75, V4L2_DV_BT_DMT_1600X1200P85, V4L2_DV_BT_DMT_1600X1200P120_RB, V4L2_DV_BT_DMT_1680X1050P60_RB, V4L2_DV_BT_DMT_1680X1050P60, V4L2_DV_BT_DMT_1680X1050P75, V4L2_DV_BT_DMT_1680X1050P85, V4L2_DV_BT_DMT_1680X1050P120_RB, V4L2_DV_BT_DMT_1792X1344P60, V4L2_DV_BT_DMT_1792X1344P75, V4L2_DV_BT_DMT_1792X1344P120_RB, V4L2_DV_BT_DMT_1856X1392P60, V4L2_DV_BT_DMT_1856X1392P75, V4L2_DV_BT_DMT_1856X1392P120_RB, V4L2_DV_BT_DMT_1920X1200P60_RB, V4L2_DV_BT_DMT_1920X1200P60, V4L2_DV_BT_DMT_1920X1200P75, V4L2_DV_BT_DMT_1920X1200P85, V4L2_DV_BT_DMT_1920X1200P120_RB, V4L2_DV_BT_DMT_1920X1440P60, V4L2_DV_BT_DMT_1920X1440P75, V4L2_DV_BT_DMT_1920X1440P120_RB, V4L2_DV_BT_DMT_2048X1152P60_RB, V4L2_DV_BT_DMT_2560X1600P60_RB, V4L2_DV_BT_DMT_2560X1600P60, V4L2_DV_BT_DMT_2560X1600P75, V4L2_DV_BT_DMT_2560X1600P85, V4L2_DV_BT_DMT_2560X1600P120_RB, V4L2_DV_BT_CEA_3840X2160P24, V4L2_DV_BT_CEA_3840X2160P25, V4L2_DV_BT_CEA_3840X2160P30, V4L2_DV_BT_CEA_3840X2160P50, V4L2_DV_BT_CEA_3840X2160P60, V4L2_DV_BT_CEA_4096X2160P24, V4L2_DV_BT_CEA_4096X2160P25, V4L2_DV_BT_CEA_4096X2160P30, V4L2_DV_BT_CEA_4096X2160P50, V4L2_DV_BT_DMT_4096X2160P59_94_RB, V4L2_DV_BT_CEA_4096X2160P60, { } }; EXPORT_SYMBOL_GPL(v4l2_dv_timings_presets); bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t, const struct v4l2_dv_timings_cap *dvcap, v4l2_check_dv_timings_fnc fnc, void *fnc_handle) { const struct v4l2_bt_timings *bt = &t->bt; const struct v4l2_bt_timings_cap *cap = &dvcap->bt; u32 caps = cap->capabilities; const u32 max_vert = 10240; u32 max_hor = 3 * bt->width; if (t->type != V4L2_DV_BT_656_1120) return false; if (t->type != dvcap->type || bt->height < cap->min_height || bt->height > cap->max_height || bt->width < cap->min_width || bt->width > cap->max_width || bt->pixelclock < cap->min_pixelclock || bt->pixelclock > cap->max_pixelclock || (!(caps & V4L2_DV_BT_CAP_CUSTOM) && cap->standards && bt->standards && !(bt->standards & cap->standards)) || (bt->interlaced && !(caps & V4L2_DV_BT_CAP_INTERLACED)) || (!bt->interlaced && !(caps & V4L2_DV_BT_CAP_PROGRESSIVE))) return false; /* sanity checks for the blanking timings */ if (!bt->interlaced && (bt->il_vbackporch || bt->il_vsync || bt->il_vfrontporch)) return false; /* * Some video receivers cannot properly separate the frontporch, * backporch and sync values, and instead they only have the total * blanking. That can be assigned to any of these three fields. * So just check that none of these are way out of range. */ if (bt->hfrontporch > max_hor || bt->hsync > max_hor || bt->hbackporch > max_hor) return false; if (bt->vfrontporch > max_vert || bt->vsync > max_vert || bt->vbackporch > max_vert) return false; if (bt->interlaced && (bt->il_vfrontporch > max_vert || bt->il_vsync > max_vert || bt->il_vbackporch > max_vert)) return false; return fnc == NULL || fnc(t, fnc_handle); } EXPORT_SYMBOL_GPL(v4l2_valid_dv_timings); int v4l2_enum_dv_timings_cap(struct v4l2_enum_dv_timings *t, const struct v4l2_dv_timings_cap *cap, v4l2_check_dv_timings_fnc fnc, void *fnc_handle) { u32 i, idx; memset(t->reserved, 0, sizeof(t->reserved)); for (i = idx = 0; v4l2_dv_timings_presets[i].bt.width; i++) { if (v4l2_valid_dv_timings(v4l2_dv_timings_presets + i, cap, fnc, fnc_handle) && idx++ == t->index) { t->timings = v4l2_dv_timings_presets[i]; return 0; } } return -EINVAL; } EXPORT_SYMBOL_GPL(v4l2_enum_dv_timings_cap); bool v4l2_find_dv_timings_cap(struct v4l2_dv_timings *t, const struct v4l2_dv_timings_cap *cap, unsigned pclock_delta, v4l2_check_dv_timings_fnc fnc, void *fnc_handle) { int i; if (!v4l2_valid_dv_timings(t, cap, fnc, fnc_handle)) return false; for (i = 0; v4l2_dv_timings_presets[i].bt.width; i++) { if (v4l2_valid_dv_timings(v4l2_dv_timings_presets + i, cap, fnc, fnc_handle) && v4l2_match_dv_timings(t, v4l2_dv_timings_presets + i, pclock_delta, false)) { u32 flags = t->bt.flags & V4L2_DV_FL_REDUCED_FPS; *t = v4l2_dv_timings_presets[i]; if (can_reduce_fps(&t->bt)) t->bt.flags |= flags; return true; } } return false; } EXPORT_SYMBOL_GPL(v4l2_find_dv_timings_cap); bool v4l2_find_dv_timings_cea861_vic(struct v4l2_dv_timings *t, u8 vic) { unsigned int i; for (i = 0; v4l2_dv_timings_presets[i].bt.width; i++) { const struct v4l2_bt_timings *bt = &v4l2_dv_timings_presets[i].bt; if ((bt->flags & V4L2_DV_FL_HAS_CEA861_VIC) && bt->cea861_vic == vic) { *t = v4l2_dv_timings_presets[i]; return true; } } return false; } EXPORT_SYMBOL_GPL(v4l2_find_dv_timings_cea861_vic); /** * v4l2_match_dv_timings - check if two timings match * @t1: compare this v4l2_dv_timings struct... * @t2: with this struct. * @pclock_delta: the allowed pixelclock deviation. * @match_reduced_fps: if true, then fail if V4L2_DV_FL_REDUCED_FPS does not * match. * * Compare t1 with t2 with a given margin of error for the pixelclock. */ bool v4l2_match_dv_timings(const struct v4l2_dv_timings *t1, const struct v4l2_dv_timings *t2, unsigned pclock_delta, bool match_reduced_fps) { if (t1->type != t2->type || t1->type != V4L2_DV_BT_656_1120) return false; if (t1->bt.width == t2->bt.width && t1->bt.height == t2->bt.height && t1->bt.interlaced == t2->bt.interlaced && t1->bt.polarities == t2->bt.polarities && t1->bt.pixelclock >= t2->bt.pixelclock - pclock_delta && t1->bt.pixelclock <= t2->bt.pixelclock + pclock_delta && t1->bt.hfrontporch == t2->bt.hfrontporch && t1->bt.hsync == t2->bt.hsync && t1->bt.hbackporch == t2->bt.hbackporch && t1->bt.vfrontporch == t2->bt.vfrontporch && t1->bt.vsync == t2->bt.vsync && t1->bt.vbackporch == t2->bt.vbackporch && (!match_reduced_fps || (t1->bt.flags & V4L2_DV_FL_REDUCED_FPS) == (t2->bt.flags & V4L2_DV_FL_REDUCED_FPS)) && (!t1->bt.interlaced || (t1->bt.il_vfrontporch == t2->bt.il_vfrontporch && t1->bt.il_vsync == t2->bt.il_vsync && t1->bt.il_vbackporch == t2->bt.il_vbackporch))) return true; return false; } EXPORT_SYMBOL_GPL(v4l2_match_dv_timings); void v4l2_print_dv_timings(const char *dev_prefix, const char *prefix, const struct v4l2_dv_timings *t, bool detailed) { const struct v4l2_bt_timings *bt = &t->bt; u32 htot, vtot; u32 fps; if (t->type != V4L2_DV_BT_656_1120) return; htot = V4L2_DV_BT_FRAME_WIDTH(bt); vtot = V4L2_DV_BT_FRAME_HEIGHT(bt); if (bt->interlaced) vtot /= 2; fps = (htot * vtot) > 0 ? div_u64((100 * (u64)bt->pixelclock), (htot * vtot)) : 0; if (prefix == NULL) prefix = ""; pr_info("%s: %s%ux%u%s%u.%02u (%ux%u)\n", dev_prefix, prefix, bt->width, bt->height, bt->interlaced ? "i" : "p", fps / 100, fps % 100, htot, vtot); if (!detailed) return; pr_info("%s: horizontal: fp = %u, %ssync = %u, bp = %u\n", dev_prefix, bt->hfrontporch, (bt->polarities & V4L2_DV_HSYNC_POS_POL) ? "+" : "-", bt->hsync, bt->hbackporch); pr_info("%s: vertical: fp = %u, %ssync = %u, bp = %u\n", dev_prefix, bt->vfrontporch, (bt->polarities & V4L2_DV_VSYNC_POS_POL) ? "+" : "-", bt->vsync, bt->vbackporch); if (bt->interlaced) pr_info("%s: vertical bottom field: fp = %u, %ssync = %u, bp = %u\n", dev_prefix, bt->il_vfrontporch, (bt->polarities & V4L2_DV_VSYNC_POS_POL) ? "+" : "-", bt->il_vsync, bt->il_vbackporch); pr_info("%s: pixelclock: %llu\n", dev_prefix, bt->pixelclock); pr_info("%s: flags (0x%x):%s%s%s%s%s%s%s%s%s%s\n", dev_prefix, bt->flags, (bt->flags & V4L2_DV_FL_REDUCED_BLANKING) ? " REDUCED_BLANKING" : "", ((bt->flags & V4L2_DV_FL_REDUCED_BLANKING) && bt->vsync == 8) ? " (V2)" : "", (bt->flags & V4L2_DV_FL_CAN_REDUCE_FPS) ? " CAN_REDUCE_FPS" : "", (bt->flags & V4L2_DV_FL_REDUCED_FPS) ? " REDUCED_FPS" : "", (bt->flags & V4L2_DV_FL_HALF_LINE) ? " HALF_LINE" : "", (bt->flags & V4L2_DV_FL_IS_CE_VIDEO) ? " CE_VIDEO" : "", (bt->flags & V4L2_DV_FL_FIRST_FIELD_EXTRA_LINE) ? " FIRST_FIELD_EXTRA_LINE" : "", (bt->flags & V4L2_DV_FL_HAS_PICTURE_ASPECT) ? " HAS_PICTURE_ASPECT" : "", (bt->flags & V4L2_DV_FL_HAS_CEA861_VIC) ? " HAS_CEA861_VIC" : "", (bt->flags & V4L2_DV_FL_HAS_HDMI_VIC) ? " HAS_HDMI_VIC" : ""); pr_info("%s: standards (0x%x):%s%s%s%s%s\n", dev_prefix, bt->standards, (bt->standards & V4L2_DV_BT_STD_CEA861) ? " CEA" : "", (bt->standards & V4L2_DV_BT_STD_DMT) ? " DMT" : "", (bt->standards & V4L2_DV_BT_STD_CVT) ? " CVT" : "", (bt->standards & V4L2_DV_BT_STD_GTF) ? " GTF" : "", (bt->standards & V4L2_DV_BT_STD_SDI) ? " SDI" : ""); if (bt->flags & V4L2_DV_FL_HAS_PICTURE_ASPECT) pr_info("%s: picture aspect (hor:vert): %u:%u\n", dev_prefix, bt->picture_aspect.numerator, bt->picture_aspect.denominator); if (bt->flags & V4L2_DV_FL_HAS_CEA861_VIC) pr_info("%s: CEA-861 VIC: %u\n", dev_prefix, bt->cea861_vic); if (bt->flags & V4L2_DV_FL_HAS_HDMI_VIC) pr_info("%s: HDMI VIC: %u\n", dev_prefix, bt->hdmi_vic); } EXPORT_SYMBOL_GPL(v4l2_print_dv_timings); struct v4l2_fract v4l2_dv_timings_aspect_ratio(const struct v4l2_dv_timings *t) { struct v4l2_fract ratio = { 1, 1 }; unsigned long n, d; if (t->type != V4L2_DV_BT_656_1120) return ratio; if (!(t->bt.flags & V4L2_DV_FL_HAS_PICTURE_ASPECT)) return ratio; ratio.numerator = t->bt.width * t->bt.picture_aspect.denominator; ratio.denominator = t->bt.height * t->bt.picture_aspect.numerator; rational_best_approximation(ratio.numerator, ratio.denominator, ratio.numerator, ratio.denominator, &n, &d); ratio.numerator = n; ratio.denominator = d; return ratio; } EXPORT_SYMBOL_GPL(v4l2_dv_timings_aspect_ratio); /** v4l2_calc_timeperframe - helper function to calculate timeperframe based * v4l2_dv_timings fields. * @t - Timings for the video mode. * * Calculates the expected timeperframe using the pixel clock value and * horizontal/vertical measures. This means that v4l2_dv_timings structure * must be correctly and fully filled. */ struct v4l2_fract v4l2_calc_timeperframe(const struct v4l2_dv_timings *t) { const struct v4l2_bt_timings *bt = &t->bt; struct v4l2_fract fps_fract = { 1, 1 }; unsigned long n, d; u32 htot, vtot, fps; u64 pclk; if (t->type != V4L2_DV_BT_656_1120) return fps_fract; htot = V4L2_DV_BT_FRAME_WIDTH(bt); vtot = V4L2_DV_BT_FRAME_HEIGHT(bt); pclk = bt->pixelclock; if ((bt->flags & V4L2_DV_FL_CAN_DETECT_REDUCED_FPS) && (bt->flags & V4L2_DV_FL_REDUCED_FPS)) pclk = div_u64(pclk * 1000ULL, 1001); fps = (htot * vtot) > 0 ? div_u64((100 * pclk), (htot * vtot)) : 0; if (!fps) return fps_fract; rational_best_approximation(fps, 100, fps, 100, &n, &d); fps_fract.numerator = d; fps_fract.denominator = n; return fps_fract; } EXPORT_SYMBOL_GPL(v4l2_calc_timeperframe); /* * CVT defines * Based on Coordinated Video Timings Standard * version 1.1 September 10, 2003 */ #define CVT_PXL_CLK_GRAN 250000 /* pixel clock granularity */ #define CVT_PXL_CLK_GRAN_RB_V2 1000 /* granularity for reduced blanking v2*/ /* Normal blanking */ #define CVT_MIN_V_BPORCH 7 /* lines */ #define CVT_MIN_V_PORCH_RND 3 /* lines */ #define CVT_MIN_VSYNC_BP 550 /* min time of vsync + back porch (us) */ #define CVT_HSYNC_PERCENT 8 /* nominal hsync as percentage of line */ /* Normal blanking for CVT uses GTF to calculate horizontal blanking */ #define CVT_CELL_GRAN 8 /* character cell granularity */ #define CVT_M 600 /* blanking formula gradient */ #define CVT_C 40 /* blanking formula offset */ #define CVT_K 128 /* blanking formula scaling factor */ #define CVT_J 20 /* blanking formula scaling factor */ #define CVT_C_PRIME (((CVT_C - CVT_J) * CVT_K / 256) + CVT_J) #define CVT_M_PRIME (CVT_K * CVT_M / 256) /* Reduced Blanking */ #define CVT_RB_MIN_V_BPORCH 7 /* lines */ #define CVT_RB_V_FPORCH 3 /* lines */ #define CVT_RB_MIN_V_BLANK 460 /* us */ #define CVT_RB_H_SYNC 32 /* pixels */ #define CVT_RB_H_BLANK 160 /* pixels */ /* Reduce blanking Version 2 */ #define CVT_RB_V2_H_BLANK 80 /* pixels */ #define CVT_RB_MIN_V_FPORCH 3 /* lines */ #define CVT_RB_V2_MIN_V_FPORCH 1 /* lines */ #define CVT_RB_V_BPORCH 6 /* lines */ /** v4l2_detect_cvt - detect if the given timings follow the CVT standard * @frame_height - the total height of the frame (including blanking) in lines. * @hfreq - the horizontal frequency in Hz. * @vsync - the height of the vertical sync in lines. * @active_width - active width of image (does not include blanking). This * information is needed only in case of version 2 of reduced blanking. * In other cases, this parameter does not have any effect on timings. * @polarities - the horizontal and vertical polarities (same as struct * v4l2_bt_timings polarities). * @interlaced - if this flag is true, it indicates interlaced format * @fmt - the resulting timings. * * This function will attempt to detect if the given values correspond to a * valid CVT format. If so, then it will return true, and fmt will be filled * in with the found CVT timings. */ bool v4l2_detect_cvt(unsigned frame_height, unsigned hfreq, unsigned vsync, unsigned active_width, u32 polarities, bool interlaced, struct v4l2_dv_timings *fmt) { int v_fp, v_bp, h_fp, h_bp, hsync; int frame_width, image_height, image_width; bool reduced_blanking; bool rb_v2 = false; unsigned pix_clk; if (vsync < 4 || vsync > 8) return false; if (polarities == V4L2_DV_VSYNC_POS_POL) reduced_blanking = false; else if (polarities == V4L2_DV_HSYNC_POS_POL) reduced_blanking = true; else return false; if (reduced_blanking && vsync == 8) rb_v2 = true; if (rb_v2 && active_width == 0) return false; if (!rb_v2 && vsync > 7) return false; if (hfreq == 0) return false; /* Vertical */ if (reduced_blanking) { if (rb_v2) { v_bp = CVT_RB_V_BPORCH; v_fp = (CVT_RB_MIN_V_BLANK * hfreq) / 1000000 + 1; v_fp -= vsync + v_bp; if (v_fp < CVT_RB_V2_MIN_V_FPORCH) v_fp = CVT_RB_V2_MIN_V_FPORCH; } else { v_fp = CVT_RB_V_FPORCH; v_bp = (CVT_RB_MIN_V_BLANK * hfreq) / 1000000 + 1; v_bp -= vsync + v_fp; if (v_bp < CVT_RB_MIN_V_BPORCH) v_bp = CVT_RB_MIN_V_BPORCH; } } else { v_fp = CVT_MIN_V_PORCH_RND; v_bp = (CVT_MIN_VSYNC_BP * hfreq) / 1000000 + 1 - vsync; if (v_bp < CVT_MIN_V_BPORCH) v_bp = CVT_MIN_V_BPORCH; } if (interlaced) image_height = (frame_height - 2 * v_fp - 2 * vsync - 2 * v_bp) & ~0x1; else image_height = (frame_height - v_fp - vsync - v_bp + 1) & ~0x1; if (image_height < 0) return false; /* Aspect ratio based on vsync */ switch (vsync) { case 4: image_width = (image_height * 4) / 3; break; case 5: image_width = (image_height * 16) / 9; break; case 6: image_width = (image_height * 16) / 10; break; case 7: /* special case */ if (image_height == 1024) image_width = (image_height * 5) / 4; else if (image_height == 768) image_width = (image_height * 15) / 9; else return false; break; case 8: image_width = active_width; break; default: return false; } if (!rb_v2) image_width = image_width & ~7; /* Horizontal */ if (reduced_blanking) { int h_blank; int clk_gran; h_blank = rb_v2 ? CVT_RB_V2_H_BLANK : CVT_RB_H_BLANK; clk_gran = rb_v2 ? CVT_PXL_CLK_GRAN_RB_V2 : CVT_PXL_CLK_GRAN; pix_clk = (image_width + h_blank) * hfreq; pix_clk = (pix_clk / clk_gran) * clk_gran; h_bp = h_blank / 2; hsync = CVT_RB_H_SYNC; h_fp = h_blank - h_bp - hsync; frame_width = image_width + h_blank; } else { unsigned ideal_duty_cycle_per_myriad = 100 * CVT_C_PRIME - (CVT_M_PRIME * 100000) / hfreq; int h_blank; if (ideal_duty_cycle_per_myriad < 2000) ideal_duty_cycle_per_myriad = 2000; h_blank = image_width * ideal_duty_cycle_per_myriad / (10000 - ideal_duty_cycle_per_myriad); h_blank = (h_blank / (2 * CVT_CELL_GRAN)) * 2 * CVT_CELL_GRAN; pix_clk = (image_width + h_blank) * hfreq; pix_clk = (pix_clk / CVT_PXL_CLK_GRAN) * CVT_PXL_CLK_GRAN; h_bp = h_blank / 2; frame_width = image_width + h_blank; hsync = frame_width * CVT_HSYNC_PERCENT / 100; hsync = (hsync / CVT_CELL_GRAN) * CVT_CELL_GRAN; h_fp = h_blank - hsync - h_bp; } fmt->type = V4L2_DV_BT_656_1120; fmt->bt.polarities = polarities; fmt->bt.width = image_width; fmt->bt.height = image_height; fmt->bt.hfrontporch = h_fp; fmt->bt.vfrontporch = v_fp; fmt->bt.hsync = hsync; fmt->bt.vsync = vsync; fmt->bt.hbackporch = frame_width - image_width - h_fp - hsync; if (!interlaced) { fmt->bt.vbackporch = frame_height - image_height - v_fp - vsync; fmt->bt.interlaced = V4L2_DV_PROGRESSIVE; } else { fmt->bt.vbackporch = (frame_height - image_height - 2 * v_fp - 2 * vsync) / 2; fmt->bt.il_vbackporch = frame_height - image_height - 2 * v_fp - 2 * vsync - fmt->bt.vbackporch; fmt->bt.il_vfrontporch = v_fp; fmt->bt.il_vsync = vsync; fmt->bt.flags |= V4L2_DV_FL_HALF_LINE; fmt->bt.interlaced = V4L2_DV_INTERLACED; } fmt->bt.pixelclock = pix_clk; fmt->bt.standards = V4L2_DV_BT_STD_CVT; if (reduced_blanking) fmt->bt.flags |= V4L2_DV_FL_REDUCED_BLANKING; return true; } EXPORT_SYMBOL_GPL(v4l2_detect_cvt); /* * GTF defines * Based on Generalized Timing Formula Standard * Version 1.1 September 2, 1999 */ #define GTF_PXL_CLK_GRAN 250000 /* pixel clock granularity */ #define GTF_MIN_VSYNC_BP 550 /* min time of vsync + back porch (us) */ #define GTF_V_FP 1 /* vertical front porch (lines) */ #define GTF_CELL_GRAN 8 /* character cell granularity */ /* Default */ #define GTF_D_M 600 /* blanking formula gradient */ #define GTF_D_C 40 /* blanking formula offset */ #define GTF_D_K 128 /* blanking formula scaling factor */ #define GTF_D_J 20 /* blanking formula scaling factor */ #define GTF_D_C_PRIME ((((GTF_D_C - GTF_D_J) * GTF_D_K) / 256) + GTF_D_J) #define GTF_D_M_PRIME ((GTF_D_K * GTF_D_M) / 256) /* Secondary */ #define GTF_S_M 3600 /* blanking formula gradient */ #define GTF_S_C 40 /* blanking formula offset */ #define GTF_S_K 128 /* blanking formula scaling factor */ #define GTF_S_J 35 /* blanking formula scaling factor */ #define GTF_S_C_PRIME ((((GTF_S_C - GTF_S_J) * GTF_S_K) / 256) + GTF_S_J) #define GTF_S_M_PRIME ((GTF_S_K * GTF_S_M) / 256) /** v4l2_detect_gtf - detect if the given timings follow the GTF standard * @frame_height - the total height of the frame (including blanking) in lines. * @hfreq - the horizontal frequency in Hz. * @vsync - the height of the vertical sync in lines. * @polarities - the horizontal and vertical polarities (same as struct * v4l2_bt_timings polarities). * @interlaced - if this flag is true, it indicates interlaced format * @aspect - preferred aspect ratio. GTF has no method of determining the * aspect ratio in order to derive the image width from the * image height, so it has to be passed explicitly. Usually * the native screen aspect ratio is used for this. If it * is not filled in correctly, then 16:9 will be assumed. * @fmt - the resulting timings. * * This function will attempt to detect if the given values correspond to a * valid GTF format. If so, then it will return true, and fmt will be filled * in with the found GTF timings. */ bool v4l2_detect_gtf(unsigned frame_height, unsigned hfreq, unsigned vsync, u32 polarities, bool interlaced, struct v4l2_fract aspect, struct v4l2_dv_timings *fmt) { int pix_clk; int v_fp, v_bp, h_fp, hsync; int frame_width, image_height, image_width; bool default_gtf; int h_blank; if (vsync != 3) return false; if (polarities == V4L2_DV_VSYNC_POS_POL) default_gtf = true; else if (polarities == V4L2_DV_HSYNC_POS_POL) default_gtf = false; else return false; if (hfreq == 0) return false; /* Vertical */ v_fp = GTF_V_FP; v_bp = (GTF_MIN_VSYNC_BP * hfreq + 500000) / 1000000 - vsync; if (interlaced) image_height = (frame_height - 2 * v_fp - 2 * vsync - 2 * v_bp) & ~0x1; else image_height = (frame_height - v_fp - vsync - v_bp + 1) & ~0x1; if (image_height < 0) return false; if (aspect.numerator == 0 || aspect.denominator == 0) { aspect.numerator = 16; aspect.denominator = 9; } image_width = ((image_height * aspect.numerator) / aspect.denominator); image_width = (image_width + GTF_CELL_GRAN/2) & ~(GTF_CELL_GRAN - 1); /* Horizontal */ if (default_gtf) { u64 num; u32 den; num = ((image_width * GTF_D_C_PRIME * (u64)hfreq) - ((u64)image_width * GTF_D_M_PRIME * 1000)); den = (hfreq * (100 - GTF_D_C_PRIME) + GTF_D_M_PRIME * 1000) * (2 * GTF_CELL_GRAN); h_blank = div_u64((num + (den >> 1)), den); h_blank *= (2 * GTF_CELL_GRAN); } else { u64 num; u32 den; num = ((image_width * GTF_S_C_PRIME * (u64)hfreq) - ((u64)image_width * GTF_S_M_PRIME * 1000)); den = (hfreq * (100 - GTF_S_C_PRIME) + GTF_S_M_PRIME * 1000) * (2 * GTF_CELL_GRAN); h_blank = div_u64((num + (den >> 1)), den); h_blank *= (2 * GTF_CELL_GRAN); } frame_width = image_width + h_blank; pix_clk = (image_width + h_blank) * hfreq; pix_clk = pix_clk / GTF_PXL_CLK_GRAN * GTF_PXL_CLK_GRAN; hsync = (frame_width * 8 + 50) / 100; hsync = DIV_ROUND_CLOSEST(hsync, GTF_CELL_GRAN) * GTF_CELL_GRAN; h_fp = h_blank / 2 - hsync; fmt->type = V4L2_DV_BT_656_1120; fmt->bt.polarities = polarities; fmt->bt.width = image_width; fmt->bt.height = image_height; fmt->bt.hfrontporch = h_fp; fmt->bt.vfrontporch = v_fp; fmt->bt.hsync = hsync; fmt->bt.vsync = vsync; fmt->bt.hbackporch = frame_width - image_width - h_fp - hsync; if (!interlaced) { fmt->bt.vbackporch = frame_height - image_height - v_fp - vsync; fmt->bt.interlaced = V4L2_DV_PROGRESSIVE; } else { fmt->bt.vbackporch = (frame_height - image_height - 2 * v_fp - 2 * vsync) / 2; fmt->bt.il_vbackporch = frame_height - image_height - 2 * v_fp - 2 * vsync - fmt->bt.vbackporch; fmt->bt.il_vfrontporch = v_fp; fmt->bt.il_vsync = vsync; fmt->bt.flags |= V4L2_DV_FL_HALF_LINE; fmt->bt.interlaced = V4L2_DV_INTERLACED; } fmt->bt.pixelclock = pix_clk; fmt->bt.standards = V4L2_DV_BT_STD_GTF; if (!default_gtf) fmt->bt.flags |= V4L2_DV_FL_REDUCED_BLANKING; return true; } EXPORT_SYMBOL_GPL(v4l2_detect_gtf); /** v4l2_calc_aspect_ratio - calculate the aspect ratio based on bytes * 0x15 and 0x16 from the EDID. * @hor_landscape - byte 0x15 from the EDID. * @vert_portrait - byte 0x16 from the EDID. * * Determines the aspect ratio from the EDID. * See VESA Enhanced EDID standard, release A, rev 2, section 3.6.2: * "Horizontal and Vertical Screen Size or Aspect Ratio" */ struct v4l2_fract v4l2_calc_aspect_ratio(u8 hor_landscape, u8 vert_portrait) { struct v4l2_fract aspect = { 16, 9 }; u8 ratio; /* Nothing filled in, fallback to 16:9 */ if (!hor_landscape && !vert_portrait) return aspect; /* Both filled in, so they are interpreted as the screen size in cm */ if (hor_landscape && vert_portrait) { aspect.numerator = hor_landscape; aspect.denominator = vert_portrait; return aspect; } /* Only one is filled in, so interpret them as a ratio: (val + 99) / 100 */ ratio = hor_landscape | vert_portrait; /* Change some rounded values into the exact aspect ratio */ if (ratio == 79) { aspect.numerator = 16; aspect.denominator = 9; } else if (ratio == 34) { aspect.numerator = 4; aspect.denominator = 3; } else if (ratio == 68) { aspect.numerator = 15; aspect.denominator = 9; } else { aspect.numerator = hor_landscape + 99; aspect.denominator = 100; } if (hor_landscape) return aspect; /* The aspect ratio is for portrait, so swap numerator and denominator */ swap(aspect.denominator, aspect.numerator); return aspect; } EXPORT_SYMBOL_GPL(v4l2_calc_aspect_ratio); /** v4l2_hdmi_rx_colorimetry - determine HDMI colorimetry information * based on various InfoFrames. * @avi: the AVI InfoFrame * @hdmi: the HDMI Vendor InfoFrame, may be NULL * @height: the frame height * * Determines the HDMI colorimetry information, i.e. how the HDMI * pixel color data should be interpreted. * * Note that some of the newer features (DCI-P3, HDR) are not yet * implemented: the hdmi.h header needs to be updated to the HDMI 2.0 * and CTA-861-G standards. */ struct v4l2_hdmi_colorimetry v4l2_hdmi_rx_colorimetry(const struct hdmi_avi_infoframe *avi, const struct hdmi_vendor_infoframe *hdmi, unsigned int height) { struct v4l2_hdmi_colorimetry c = { V4L2_COLORSPACE_SRGB, V4L2_YCBCR_ENC_DEFAULT, V4L2_QUANTIZATION_FULL_RANGE, V4L2_XFER_FUNC_SRGB }; bool is_ce = avi->video_code || (hdmi && hdmi->vic); bool is_sdtv = height <= 576; bool default_is_lim_range_rgb = avi->video_code > 1; switch (avi->colorspace) { case HDMI_COLORSPACE_RGB: /* RGB pixel encoding */ switch (avi->colorimetry) { case HDMI_COLORIMETRY_EXTENDED: switch (avi->extended_colorimetry) { case HDMI_EXTENDED_COLORIMETRY_OPRGB: c.colorspace = V4L2_COLORSPACE_OPRGB; c.xfer_func = V4L2_XFER_FUNC_OPRGB; break; case HDMI_EXTENDED_COLORIMETRY_BT2020: c.colorspace = V4L2_COLORSPACE_BT2020; c.xfer_func = V4L2_XFER_FUNC_709; break; default: break; } break; default: break; } switch (avi->quantization_range) { case HDMI_QUANTIZATION_RANGE_LIMITED: c.quantization = V4L2_QUANTIZATION_LIM_RANGE; break; case HDMI_QUANTIZATION_RANGE_FULL: break; default: if (default_is_lim_range_rgb) c.quantization = V4L2_QUANTIZATION_LIM_RANGE; break; } break; default: /* YCbCr pixel encoding */ c.quantization = V4L2_QUANTIZATION_LIM_RANGE; switch (avi->colorimetry) { case HDMI_COLORIMETRY_NONE: if (!is_ce) break; if (is_sdtv) { c.colorspace = V4L2_COLORSPACE_SMPTE170M; c.ycbcr_enc = V4L2_YCBCR_ENC_601; } else { c.colorspace = V4L2_COLORSPACE_REC709; c.ycbcr_enc = V4L2_YCBCR_ENC_709; } c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_COLORIMETRY_ITU_601: c.colorspace = V4L2_COLORSPACE_SMPTE170M; c.ycbcr_enc = V4L2_YCBCR_ENC_601; c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_COLORIMETRY_ITU_709: c.colorspace = V4L2_COLORSPACE_REC709; c.ycbcr_enc = V4L2_YCBCR_ENC_709; c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_COLORIMETRY_EXTENDED: switch (avi->extended_colorimetry) { case HDMI_EXTENDED_COLORIMETRY_XV_YCC_601: c.colorspace = V4L2_COLORSPACE_REC709; c.ycbcr_enc = V4L2_YCBCR_ENC_XV709; c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_EXTENDED_COLORIMETRY_XV_YCC_709: c.colorspace = V4L2_COLORSPACE_REC709; c.ycbcr_enc = V4L2_YCBCR_ENC_XV601; c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_EXTENDED_COLORIMETRY_S_YCC_601: c.colorspace = V4L2_COLORSPACE_SRGB; c.ycbcr_enc = V4L2_YCBCR_ENC_601; c.xfer_func = V4L2_XFER_FUNC_SRGB; break; case HDMI_EXTENDED_COLORIMETRY_OPYCC_601: c.colorspace = V4L2_COLORSPACE_OPRGB; c.ycbcr_enc = V4L2_YCBCR_ENC_601; c.xfer_func = V4L2_XFER_FUNC_OPRGB; break; case HDMI_EXTENDED_COLORIMETRY_BT2020: c.colorspace = V4L2_COLORSPACE_BT2020; c.ycbcr_enc = V4L2_YCBCR_ENC_BT2020; c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM: c.colorspace = V4L2_COLORSPACE_BT2020; c.ycbcr_enc = V4L2_YCBCR_ENC_BT2020_CONST_LUM; c.xfer_func = V4L2_XFER_FUNC_709; break; default: /* fall back to ITU_709 */ c.colorspace = V4L2_COLORSPACE_REC709; c.ycbcr_enc = V4L2_YCBCR_ENC_709; c.xfer_func = V4L2_XFER_FUNC_709; break; } break; default: break; } /* * YCC Quantization Range signaling is more-or-less broken, * let's just ignore this. */ break; } return c; } EXPORT_SYMBOL_GPL(v4l2_hdmi_rx_colorimetry); /** * v4l2_get_edid_phys_addr() - find and return the physical address * * @edid: pointer to the EDID data * @size: size in bytes of the EDID data * @offset: If not %NULL then the location of the physical address * bytes in the EDID will be returned here. This is set to 0 * if there is no physical address found. * * Return: the physical address or CEC_PHYS_ADDR_INVALID if there is none. */ u16 v4l2_get_edid_phys_addr(const u8 *edid, unsigned int size, unsigned int *offset) { unsigned int loc = cec_get_edid_spa_location(edid, size); if (offset) *offset = loc; if (loc == 0) return CEC_PHYS_ADDR_INVALID; return (edid[loc] << 8) | edid[loc + 1]; } EXPORT_SYMBOL_GPL(v4l2_get_edid_phys_addr); /** * v4l2_set_edid_phys_addr() - find and set the physical address * * @edid: pointer to the EDID data * @size: size in bytes of the EDID data * @phys_addr: the new physical address * * This function finds the location of the physical address in the EDID * and fills in the given physical address and updates the checksum * at the end of the EDID block. It does nothing if the EDID doesn't * contain a physical address. */ void v4l2_set_edid_phys_addr(u8 *edid, unsigned int size, u16 phys_addr) { unsigned int loc = cec_get_edid_spa_location(edid, size); u8 sum = 0; unsigned int i; if (loc == 0) return; edid[loc] = phys_addr >> 8; edid[loc + 1] = phys_addr & 0xff; loc &= ~0x7f; /* update the checksum */ for (i = loc; i < loc + 127; i++) sum += edid[i]; edid[i] = 256 - sum; } EXPORT_SYMBOL_GPL(v4l2_set_edid_phys_addr); /** * v4l2_phys_addr_for_input() - calculate the PA for an input * * @phys_addr: the physical address of the parent * @input: the number of the input port, must be between 1 and 15 * * This function calculates a new physical address based on the input * port number. For example: * * PA = 0.0.0.0 and input = 2 becomes 2.0.0.0 * * PA = 3.0.0.0 and input = 1 becomes 3.1.0.0 * * PA = 3.2.1.0 and input = 5 becomes 3.2.1.5 * * PA = 3.2.1.3 and input = 5 becomes f.f.f.f since it maxed out the depth. * * Return: the new physical address or CEC_PHYS_ADDR_INVALID. */ u16 v4l2_phys_addr_for_input(u16 phys_addr, u8 input) { /* Check if input is sane */ if (WARN_ON(input == 0 || input > 0xf)) return CEC_PHYS_ADDR_INVALID; if (phys_addr == 0) return input << 12; if ((phys_addr & 0x0fff) == 0) return phys_addr | (input << 8); if ((phys_addr & 0x00ff) == 0) return phys_addr | (input << 4); if ((phys_addr & 0x000f) == 0) return phys_addr | input; /* * All nibbles are used so no valid physical addresses can be assigned * to the input. */ return CEC_PHYS_ADDR_INVALID; } EXPORT_SYMBOL_GPL(v4l2_phys_addr_for_input); /** * v4l2_phys_addr_validate() - validate a physical address from an EDID * * @phys_addr: the physical address to validate * @parent: if not %NULL, then this is filled with the parents PA. * @port: if not %NULL, then this is filled with the input port. * * This validates a physical address as read from an EDID. If the * PA is invalid (such as 1.0.1.0 since '0' is only allowed at the end), * then it will return -EINVAL. * * The parent PA is passed into %parent and the input port is passed into * %port. For example: * * PA = 0.0.0.0: has parent 0.0.0.0 and input port 0. * * PA = 1.0.0.0: has parent 0.0.0.0 and input port 1. * * PA = 3.2.0.0: has parent 3.0.0.0 and input port 2. * * PA = f.f.f.f: has parent f.f.f.f and input port 0. * * Return: 0 if the PA is valid, -EINVAL if not. */ int v4l2_phys_addr_validate(u16 phys_addr, u16 *parent, u16 *port) { int i; if (parent) *parent = phys_addr; if (port) *port = 0; if (phys_addr == CEC_PHYS_ADDR_INVALID) return 0; for (i = 0; i < 16; i += 4) if (phys_addr & (0xf << i)) break; if (i == 16) return 0; if (parent) *parent = phys_addr & (0xfff0 << i); if (port) *port = (phys_addr >> i) & 0xf; for (i += 4; i < 16; i += 4) if ((phys_addr & (0xf << i)) == 0) return -EINVAL; return 0; } EXPORT_SYMBOL_GPL(v4l2_phys_addr_validate); |
| 36 36 36 36 36 36 36 35 12 12 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 12 12 1 37 12 36 36 36 24 36 1 1 1 1 1 1 36 36 24 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2007 Alan Stern * Copyright (C) IBM Corporation, 2009 * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com> * * Thanks to Ingo Molnar for his many suggestions. * * Authors: Alan Stern <stern@rowland.harvard.edu> * K.Prasad <prasad@linux.vnet.ibm.com> * Frederic Weisbecker <fweisbec@gmail.com> */ /* * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility, * using the CPU's debug registers. * This file contains the arch-independent routines. */ #include <linux/hw_breakpoint.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/export.h> #include <linux/init.h> #include <linux/irqflags.h> #include <linux/kdebug.h> #include <linux/kernel.h> #include <linux/mutex.h> #include <linux/notifier.h> #include <linux/percpu-rwsem.h> #include <linux/percpu.h> #include <linux/rhashtable.h> #include <linux/sched.h> #include <linux/slab.h> /* * Datastructure to track the total uses of N slots across tasks or CPUs; * bp_slots_histogram::count[N] is the number of assigned N+1 breakpoint slots. */ struct bp_slots_histogram { #ifdef hw_breakpoint_slots atomic_t count[hw_breakpoint_slots(0)]; #else atomic_t *count; #endif }; /* * Per-CPU constraints data. */ struct bp_cpuinfo { /* Number of pinned CPU breakpoints in a CPU. */ unsigned int cpu_pinned; /* Histogram of pinned task breakpoints in a CPU. */ struct bp_slots_histogram tsk_pinned; }; static DEFINE_PER_CPU(struct bp_cpuinfo, bp_cpuinfo[TYPE_MAX]); static struct bp_cpuinfo *get_bp_info(int cpu, enum bp_type_idx type) { return per_cpu_ptr(bp_cpuinfo + type, cpu); } /* Number of pinned CPU breakpoints globally. */ static struct bp_slots_histogram cpu_pinned[TYPE_MAX]; /* Number of pinned CPU-independent task breakpoints. */ static struct bp_slots_histogram tsk_pinned_all[TYPE_MAX]; /* Keep track of the breakpoints attached to tasks */ static struct rhltable task_bps_ht; static const struct rhashtable_params task_bps_ht_params = { .head_offset = offsetof(struct hw_perf_event, bp_list), .key_offset = offsetof(struct hw_perf_event, target), .key_len = sizeof_field(struct hw_perf_event, target), .automatic_shrinking = true, }; static bool constraints_initialized __ro_after_init; /* * Synchronizes accesses to the per-CPU constraints; the locking rules are: * * 1. Atomic updates to bp_cpuinfo::tsk_pinned only require a held read-lock * (due to bp_slots_histogram::count being atomic, no update are lost). * * 2. Holding a write-lock is required for computations that require a * stable snapshot of all bp_cpuinfo::tsk_pinned. * * 3. In all other cases, non-atomic accesses require the appropriately held * lock (read-lock for read-only accesses; write-lock for reads/writes). */ DEFINE_STATIC_PERCPU_RWSEM(bp_cpuinfo_sem); /* * Return mutex to serialize accesses to per-task lists in task_bps_ht. Since * rhltable synchronizes concurrent insertions/deletions, independent tasks may * insert/delete concurrently; therefore, a mutex per task is sufficient. * * Uses task_struct::perf_event_mutex, to avoid extending task_struct with a * hw_breakpoint-only mutex, which may be infrequently used. The caveat here is * that hw_breakpoint may contend with per-task perf event list management. The * assumption is that perf usecases involving hw_breakpoints are very unlikely * to result in unnecessary contention. */ static inline struct mutex *get_task_bps_mutex(struct perf_event *bp) { struct task_struct *tsk = bp->hw.target; return tsk ? &tsk->perf_event_mutex : NULL; } static struct mutex *bp_constraints_lock(struct perf_event *bp) { struct mutex *tsk_mtx = get_task_bps_mutex(bp); if (tsk_mtx) { /* * Fully analogous to the perf_try_init_event() nesting * argument in the comment near perf_event_ctx_lock_nested(); * this child->perf_event_mutex cannot ever deadlock against * the parent->perf_event_mutex usage from * perf_event_task_{en,dis}able(). * * Specifically, inherited events will never occur on * ->perf_event_list. */ mutex_lock_nested(tsk_mtx, SINGLE_DEPTH_NESTING); percpu_down_read(&bp_cpuinfo_sem); } else { percpu_down_write(&bp_cpuinfo_sem); } return tsk_mtx; } static void bp_constraints_unlock(struct mutex *tsk_mtx) { if (tsk_mtx) { percpu_up_read(&bp_cpuinfo_sem); mutex_unlock(tsk_mtx); } else { percpu_up_write(&bp_cpuinfo_sem); } } static bool bp_constraints_is_locked(struct perf_event *bp) { struct mutex *tsk_mtx = get_task_bps_mutex(bp); return percpu_is_write_locked(&bp_cpuinfo_sem) || (tsk_mtx ? mutex_is_locked(tsk_mtx) : percpu_is_read_locked(&bp_cpuinfo_sem)); } static inline void assert_bp_constraints_lock_held(struct perf_event *bp) { struct mutex *tsk_mtx = get_task_bps_mutex(bp); if (tsk_mtx) lockdep_assert_held(tsk_mtx); lockdep_assert_held(&bp_cpuinfo_sem); } #ifdef hw_breakpoint_slots /* * Number of breakpoint slots is constant, and the same for all types. */ static_assert(hw_breakpoint_slots(TYPE_INST) == hw_breakpoint_slots(TYPE_DATA)); static inline int hw_breakpoint_slots_cached(int type) { return hw_breakpoint_slots(type); } static inline int init_breakpoint_slots(void) { return 0; } #else /* * Dynamic number of breakpoint slots. */ static int __nr_bp_slots[TYPE_MAX] __ro_after_init; static inline int hw_breakpoint_slots_cached(int type) { return __nr_bp_slots[type]; } static __init bool bp_slots_histogram_alloc(struct bp_slots_histogram *hist, enum bp_type_idx type) { hist->count = kcalloc(hw_breakpoint_slots_cached(type), sizeof(*hist->count), GFP_KERNEL); return hist->count; } static __init void bp_slots_histogram_free(struct bp_slots_histogram *hist) { kfree(hist->count); } static __init int init_breakpoint_slots(void) { int i, cpu, err_cpu; for (i = 0; i < TYPE_MAX; i++) __nr_bp_slots[i] = hw_breakpoint_slots(i); for_each_possible_cpu(cpu) { for (i = 0; i < TYPE_MAX; i++) { struct bp_cpuinfo *info = get_bp_info(cpu, i); if (!bp_slots_histogram_alloc(&info->tsk_pinned, i)) goto err; } } for (i = 0; i < TYPE_MAX; i++) { if (!bp_slots_histogram_alloc(&cpu_pinned[i], i)) goto err; if (!bp_slots_histogram_alloc(&tsk_pinned_all[i], i)) goto err; } return 0; err: for_each_possible_cpu(err_cpu) { for (i = 0; i < TYPE_MAX; i++) bp_slots_histogram_free(&get_bp_info(err_cpu, i)->tsk_pinned); if (err_cpu == cpu) break; } for (i = 0; i < TYPE_MAX; i++) { bp_slots_histogram_free(&cpu_pinned[i]); bp_slots_histogram_free(&tsk_pinned_all[i]); } return -ENOMEM; } #endif static inline void bp_slots_histogram_add(struct bp_slots_histogram *hist, int old, int val) { const int old_idx = old - 1; const int new_idx = old_idx + val; if (old_idx >= 0) WARN_ON(atomic_dec_return_relaxed(&hist->count[old_idx]) < 0); if (new_idx >= 0) WARN_ON(atomic_inc_return_relaxed(&hist->count[new_idx]) < 0); } static int bp_slots_histogram_max(struct bp_slots_histogram *hist, enum bp_type_idx type) { for (int i = hw_breakpoint_slots_cached(type) - 1; i >= 0; i--) { const int count = atomic_read(&hist->count[i]); /* Catch unexpected writers; we want a stable snapshot. */ ASSERT_EXCLUSIVE_WRITER(hist->count[i]); if (count > 0) return i + 1; WARN(count < 0, "inconsistent breakpoint slots histogram"); } return 0; } static int bp_slots_histogram_max_merge(struct bp_slots_histogram *hist1, struct bp_slots_histogram *hist2, enum bp_type_idx type) { for (int i = hw_breakpoint_slots_cached(type) - 1; i >= 0; i--) { const int count1 = atomic_read(&hist1->count[i]); const int count2 = atomic_read(&hist2->count[i]); /* Catch unexpected writers; we want a stable snapshot. */ ASSERT_EXCLUSIVE_WRITER(hist1->count[i]); ASSERT_EXCLUSIVE_WRITER(hist2->count[i]); if (count1 + count2 > 0) return i + 1; WARN(count1 < 0, "inconsistent breakpoint slots histogram"); WARN(count2 < 0, "inconsistent breakpoint slots histogram"); } return 0; } #ifndef hw_breakpoint_weight static inline int hw_breakpoint_weight(struct perf_event *bp) { return 1; } #endif static inline enum bp_type_idx find_slot_idx(u64 bp_type) { if (bp_type & HW_BREAKPOINT_RW) return TYPE_DATA; return TYPE_INST; } /* * Return the maximum number of pinned breakpoints a task has in this CPU. */ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type) { struct bp_slots_histogram *tsk_pinned = &get_bp_info(cpu, type)->tsk_pinned; /* * At this point we want to have acquired the bp_cpuinfo_sem as a * writer to ensure that there are no concurrent writers in * toggle_bp_task_slot() to tsk_pinned, and we get a stable snapshot. */ lockdep_assert_held_write(&bp_cpuinfo_sem); return bp_slots_histogram_max_merge(tsk_pinned, &tsk_pinned_all[type], type); } /* * Count the number of breakpoints of the same type and same task. * The given event must be not on the list. * * If @cpu is -1, but the result of task_bp_pinned() is not CPU-independent, * returns a negative value. */ static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type) { struct rhlist_head *head, *pos; struct perf_event *iter; int count = 0; /* * We need a stable snapshot of the per-task breakpoint list. */ assert_bp_constraints_lock_held(bp); rcu_read_lock(); head = rhltable_lookup(&task_bps_ht, &bp->hw.target, task_bps_ht_params); if (!head) goto out; rhl_for_each_entry_rcu(iter, pos, head, hw.bp_list) { if (find_slot_idx(iter->attr.bp_type) != type) continue; if (iter->cpu >= 0) { if (cpu == -1) { count = -1; goto out; } else if (cpu != iter->cpu) continue; } count += hw_breakpoint_weight(iter); } out: rcu_read_unlock(); return count; } static const struct cpumask *cpumask_of_bp(struct perf_event *bp) { if (bp->cpu >= 0) return cpumask_of(bp->cpu); return cpu_possible_mask; } /* * Returns the max pinned breakpoint slots in a given * CPU (cpu > -1) or across all of them (cpu = -1). */ static int max_bp_pinned_slots(struct perf_event *bp, enum bp_type_idx type) { const struct cpumask *cpumask = cpumask_of_bp(bp); int pinned_slots = 0; int cpu; if (bp->hw.target && bp->cpu < 0) { int max_pinned = task_bp_pinned(-1, bp, type); if (max_pinned >= 0) { /* * Fast path: task_bp_pinned() is CPU-independent and * returns the same value for any CPU. */ max_pinned += bp_slots_histogram_max(&cpu_pinned[type], type); return max_pinned; } } for_each_cpu(cpu, cpumask) { struct bp_cpuinfo *info = get_bp_info(cpu, type); int nr; nr = info->cpu_pinned; if (!bp->hw.target) nr += max_task_bp_pinned(cpu, type); else nr += task_bp_pinned(cpu, bp, type); pinned_slots = max(nr, pinned_slots); } return pinned_slots; } /* * Add/remove the given breakpoint in our constraint table */ static int toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, int weight) { int cpu, next_tsk_pinned; if (!enable) weight = -weight; if (!bp->hw.target) { /* * Update the pinned CPU slots, in per-CPU bp_cpuinfo and in the * global histogram. */ struct bp_cpuinfo *info = get_bp_info(bp->cpu, type); lockdep_assert_held_write(&bp_cpuinfo_sem); bp_slots_histogram_add(&cpu_pinned[type], info->cpu_pinned, weight); info->cpu_pinned += weight; return 0; } /* * If bp->hw.target, tsk_pinned is only modified, but not used * otherwise. We can permit concurrent updates as long as there are no * other uses: having acquired bp_cpuinfo_sem as a reader allows * concurrent updates here. Uses of tsk_pinned will require acquiring * bp_cpuinfo_sem as a writer to stabilize tsk_pinned's value. */ lockdep_assert_held_read(&bp_cpuinfo_sem); /* * Update the pinned task slots, in per-CPU bp_cpuinfo and in the global * histogram. We need to take care of 4 cases: * * 1. This breakpoint targets all CPUs (cpu < 0), and there may only * exist other task breakpoints targeting all CPUs. In this case we * can simply update the global slots histogram. * * 2. This breakpoint targets a specific CPU (cpu >= 0), but there may * only exist other task breakpoints targeting all CPUs. * * a. On enable: remove the existing breakpoints from the global * slots histogram and use the per-CPU histogram. * * b. On disable: re-insert the existing breakpoints into the global * slots histogram and remove from per-CPU histogram. * * 3. Some other existing task breakpoints target specific CPUs. Only * update the per-CPU slots histogram. */ if (!enable) { /* * Remove before updating histograms so we can determine if this * was the last task breakpoint for a specific CPU. */ int ret = rhltable_remove(&task_bps_ht, &bp->hw.bp_list, task_bps_ht_params); if (ret) return ret; } /* * Note: If !enable, next_tsk_pinned will not count the to-be-removed breakpoint. */ next_tsk_pinned = task_bp_pinned(-1, bp, type); if (next_tsk_pinned >= 0) { if (bp->cpu < 0) { /* Case 1: fast path */ if (!enable) next_tsk_pinned += hw_breakpoint_weight(bp); bp_slots_histogram_add(&tsk_pinned_all[type], next_tsk_pinned, weight); } else if (enable) { /* Case 2.a: slow path */ /* Add existing to per-CPU histograms. */ for_each_possible_cpu(cpu) { bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned, 0, next_tsk_pinned); } /* Add this first CPU-pinned task breakpoint. */ bp_slots_histogram_add(&get_bp_info(bp->cpu, type)->tsk_pinned, next_tsk_pinned, weight); /* Rebalance global task pinned histogram. */ bp_slots_histogram_add(&tsk_pinned_all[type], next_tsk_pinned, -next_tsk_pinned); } else { /* Case 2.b: slow path */ /* Remove this last CPU-pinned task breakpoint. */ bp_slots_histogram_add(&get_bp_info(bp->cpu, type)->tsk_pinned, next_tsk_pinned + hw_breakpoint_weight(bp), weight); /* Remove all from per-CPU histograms. */ for_each_possible_cpu(cpu) { bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned, next_tsk_pinned, -next_tsk_pinned); } /* Rebalance global task pinned histogram. */ bp_slots_histogram_add(&tsk_pinned_all[type], 0, next_tsk_pinned); } } else { /* Case 3: slow path */ const struct cpumask *cpumask = cpumask_of_bp(bp); for_each_cpu(cpu, cpumask) { next_tsk_pinned = task_bp_pinned(cpu, bp, type); if (!enable) next_tsk_pinned += hw_breakpoint_weight(bp); bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned, next_tsk_pinned, weight); } } /* * Readers want a stable snapshot of the per-task breakpoint list. */ assert_bp_constraints_lock_held(bp); if (enable) return rhltable_insert(&task_bps_ht, &bp->hw.bp_list, task_bps_ht_params); return 0; } /* * Constraints to check before allowing this new breakpoint counter. * * Note: Flexible breakpoints are currently unimplemented, but outlined in the * below algorithm for completeness. The implementation treats flexible as * pinned due to no guarantee that we currently always schedule flexible events * before a pinned event in a same CPU. * * == Non-pinned counter == (Considered as pinned for now) * * - If attached to a single cpu, check: * * (per_cpu(info->flexible, cpu) || (per_cpu(info->cpu_pinned, cpu) * + max(per_cpu(info->tsk_pinned, cpu)))) < HBP_NUM * * -> If there are already non-pinned counters in this cpu, it means * there is already a free slot for them. * Otherwise, we check that the maximum number of per task * breakpoints (for this cpu) plus the number of per cpu breakpoint * (for this cpu) doesn't cover every registers. * * - If attached to every cpus, check: * * (per_cpu(info->flexible, *) || (max(per_cpu(info->cpu_pinned, *)) * + max(per_cpu(info->tsk_pinned, *)))) < HBP_NUM * * -> This is roughly the same, except we check the number of per cpu * bp for every cpu and we keep the max one. Same for the per tasks * breakpoints. * * * == Pinned counter == * * - If attached to a single cpu, check: * * ((per_cpu(info->flexible, cpu) > 1) + per_cpu(info->cpu_pinned, cpu) * + max(per_cpu(info->tsk_pinned, cpu))) < HBP_NUM * * -> Same checks as before. But now the info->flexible, if any, must keep * one register at least (or they will never be fed). * * - If attached to every cpus, check: * * ((per_cpu(info->flexible, *) > 1) + max(per_cpu(info->cpu_pinned, *)) * + max(per_cpu(info->tsk_pinned, *))) < HBP_NUM */ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type) { enum bp_type_idx type; int max_pinned_slots; int weight; /* We couldn't initialize breakpoint constraints on boot */ if (!constraints_initialized) return -ENOMEM; /* Basic checks */ if (bp_type == HW_BREAKPOINT_EMPTY || bp_type == HW_BREAKPOINT_INVALID) return -EINVAL; type = find_slot_idx(bp_type); weight = hw_breakpoint_weight(bp); /* Check if this new breakpoint can be satisfied across all CPUs. */ max_pinned_slots = max_bp_pinned_slots(bp, type) + weight; if (max_pinned_slots > hw_breakpoint_slots_cached(type)) return -ENOSPC; return toggle_bp_slot(bp, true, type, weight); } int reserve_bp_slot(struct perf_event *bp) { struct mutex *mtx = bp_constraints_lock(bp); int ret = __reserve_bp_slot(bp, bp->attr.bp_type); bp_constraints_unlock(mtx); return ret; } static void __release_bp_slot(struct perf_event *bp, u64 bp_type) { enum bp_type_idx type; int weight; type = find_slot_idx(bp_type); weight = hw_breakpoint_weight(bp); WARN_ON(toggle_bp_slot(bp, false, type, weight)); } void release_bp_slot(struct perf_event *bp) { struct mutex *mtx = bp_constraints_lock(bp); __release_bp_slot(bp, bp->attr.bp_type); bp_constraints_unlock(mtx); } static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type) { int err; __release_bp_slot(bp, old_type); err = __reserve_bp_slot(bp, new_type); if (err) { /* * Reserve the old_type slot back in case * there's no space for the new type. * * This must succeed, because we just released * the old_type slot in the __release_bp_slot * call above. If not, something is broken. */ WARN_ON(__reserve_bp_slot(bp, old_type)); } return err; } static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type) { struct mutex *mtx = bp_constraints_lock(bp); int ret = __modify_bp_slot(bp, old_type, new_type); bp_constraints_unlock(mtx); return ret; } /* * Allow the kernel debugger to reserve breakpoint slots without * taking a lock using the dbg_* variant of for the reserve and * release breakpoint slots. */ int dbg_reserve_bp_slot(struct perf_event *bp) { int ret; if (bp_constraints_is_locked(bp)) return -1; /* Locks aren't held; disable lockdep assert checking. */ lockdep_off(); ret = __reserve_bp_slot(bp, bp->attr.bp_type); lockdep_on(); return ret; } int dbg_release_bp_slot(struct perf_event *bp) { if (bp_constraints_is_locked(bp)) return -1; /* Locks aren't held; disable lockdep assert checking. */ lockdep_off(); __release_bp_slot(bp, bp->attr.bp_type); lockdep_on(); return 0; } static int hw_breakpoint_parse(struct perf_event *bp, const struct perf_event_attr *attr, struct arch_hw_breakpoint *hw) { int err; err = hw_breakpoint_arch_parse(bp, attr, hw); if (err) return err; if (arch_check_bp_in_kernelspace(hw)) { if (attr->exclude_kernel) return -EINVAL; /* * Don't let unprivileged users set a breakpoint in the trap * path to avoid trap recursion attacks. */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; } return 0; } int register_perf_hw_breakpoint(struct perf_event *bp) { struct arch_hw_breakpoint hw = { }; int err; err = reserve_bp_slot(bp); if (err) return err; err = hw_breakpoint_parse(bp, &bp->attr, &hw); if (err) { release_bp_slot(bp); return err; } bp->hw.info = hw; return 0; } /** * register_user_hw_breakpoint - register a hardware breakpoint for user space * @attr: breakpoint attributes * @triggered: callback to trigger when we hit the breakpoint * @context: context data could be used in the triggered callback * @tsk: pointer to 'task_struct' of the process to which the address belongs */ struct perf_event * register_user_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered, void *context, struct task_struct *tsk) { return perf_event_create_kernel_counter(attr, -1, tsk, triggered, context); } EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); static void hw_breakpoint_copy_attr(struct perf_event_attr *to, struct perf_event_attr *from) { to->bp_addr = from->bp_addr; to->bp_type = from->bp_type; to->bp_len = from->bp_len; to->disabled = from->disabled; } int modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr, bool check) { struct arch_hw_breakpoint hw = { }; int err; err = hw_breakpoint_parse(bp, attr, &hw); if (err) return err; if (check) { struct perf_event_attr old_attr; old_attr = bp->attr; hw_breakpoint_copy_attr(&old_attr, attr); if (memcmp(&old_attr, attr, sizeof(*attr))) return -EINVAL; } if (bp->attr.bp_type != attr->bp_type) { err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type); if (err) return err; } hw_breakpoint_copy_attr(&bp->attr, attr); bp->hw.info = hw; return 0; } /** * modify_user_hw_breakpoint - modify a user-space hardware breakpoint * @bp: the breakpoint structure to modify * @attr: new breakpoint attributes */ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr) { int err; /* * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it * will not be possible to raise IPIs that invoke __perf_event_disable. * So call the function directly after making sure we are targeting the * current task. */ if (irqs_disabled() && bp->ctx && bp->ctx->task == current) perf_event_disable_local(bp); else perf_event_disable(bp); err = modify_user_hw_breakpoint_check(bp, attr, false); if (!bp->attr.disabled) perf_event_enable(bp); return err; } EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint); /** * unregister_hw_breakpoint - unregister a user-space hardware breakpoint * @bp: the breakpoint structure to unregister */ void unregister_hw_breakpoint(struct perf_event *bp) { if (!bp) return; perf_event_release_kernel(bp); } EXPORT_SYMBOL_GPL(unregister_hw_breakpoint); /** * register_wide_hw_breakpoint - register a wide breakpoint in the kernel * @attr: breakpoint attributes * @triggered: callback to trigger when we hit the breakpoint * @context: context data could be used in the triggered callback * * @return a set of per_cpu pointers to perf events */ struct perf_event * __percpu * register_wide_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered, void *context) { struct perf_event * __percpu *cpu_events, *bp; long err = 0; int cpu; cpu_events = alloc_percpu(typeof(*cpu_events)); if (!cpu_events) return (void __percpu __force *)ERR_PTR(-ENOMEM); cpus_read_lock(); for_each_online_cpu(cpu) { bp = perf_event_create_kernel_counter(attr, cpu, NULL, triggered, context); if (IS_ERR(bp)) { err = PTR_ERR(bp); break; } per_cpu(*cpu_events, cpu) = bp; } cpus_read_unlock(); if (likely(!err)) return cpu_events; unregister_wide_hw_breakpoint(cpu_events); return (void __percpu __force *)ERR_PTR(err); } EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint); /** * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel * @cpu_events: the per cpu set of events to unregister */ void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events) { int cpu; for_each_possible_cpu(cpu) unregister_hw_breakpoint(per_cpu(*cpu_events, cpu)); free_percpu(cpu_events); } EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint); /** * hw_breakpoint_is_used - check if breakpoints are currently used * * Returns: true if breakpoints are used, false otherwise. */ bool hw_breakpoint_is_used(void) { int cpu; if (!constraints_initialized) return false; for_each_possible_cpu(cpu) { for (int type = 0; type < TYPE_MAX; ++type) { struct bp_cpuinfo *info = get_bp_info(cpu, type); if (info->cpu_pinned) return true; for (int slot = 0; slot < hw_breakpoint_slots_cached(type); ++slot) { if (atomic_read(&info->tsk_pinned.count[slot])) return true; } } } for (int type = 0; type < TYPE_MAX; ++type) { for (int slot = 0; slot < hw_breakpoint_slots_cached(type); ++slot) { /* * Warn, because if there are CPU pinned counters, * should never get here; bp_cpuinfo::cpu_pinned should * be consistent with the global cpu_pinned histogram. */ if (WARN_ON(atomic_read(&cpu_pinned[type].count[slot]))) return true; if (atomic_read(&tsk_pinned_all[type].count[slot])) return true; } } return false; } static struct notifier_block hw_breakpoint_exceptions_nb = { .notifier_call = hw_breakpoint_exceptions_notify, /* we need to be notified first */ .priority = 0x7fffffff }; static void bp_perf_event_destroy(struct perf_event *event) { release_bp_slot(event); } static int hw_breakpoint_event_init(struct perf_event *bp) { int err; if (bp->attr.type != PERF_TYPE_BREAKPOINT) return -ENOENT; /* * no branch sampling for breakpoint events */ if (has_branch_stack(bp)) return -EOPNOTSUPP; err = register_perf_hw_breakpoint(bp); if (err) return err; bp->destroy = bp_perf_event_destroy; return 0; } static int hw_breakpoint_add(struct perf_event *bp, int flags) { if (!(flags & PERF_EF_START)) bp->hw.state = PERF_HES_STOPPED; if (is_sampling_event(bp)) { bp->hw.last_period = bp->hw.sample_period; perf_swevent_set_period(bp); } return arch_install_hw_breakpoint(bp); } static void hw_breakpoint_del(struct perf_event *bp, int flags) { arch_uninstall_hw_breakpoint(bp); } static void hw_breakpoint_start(struct perf_event *bp, int flags) { bp->hw.state = 0; } static void hw_breakpoint_stop(struct perf_event *bp, int flags) { bp->hw.state = PERF_HES_STOPPED; } static struct pmu perf_breakpoint = { .task_ctx_nr = perf_sw_context, /* could eventually get its own */ .event_init = hw_breakpoint_event_init, .add = hw_breakpoint_add, .del = hw_breakpoint_del, .start = hw_breakpoint_start, .stop = hw_breakpoint_stop, .read = hw_breakpoint_pmu_read, }; int __init init_hw_breakpoint(void) { int ret; ret = rhltable_init(&task_bps_ht, &task_bps_ht_params); if (ret) return ret; ret = init_breakpoint_slots(); if (ret) return ret; constraints_initialized = true; perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT); return register_die_notifier(&hw_breakpoint_exceptions_nb); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * (C) 2011 Pablo Neira Ayuso <pablo@netfilter.org> * (C) 2011 Intra2net AG <https://www.intra2net.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/nfnetlink_acct.h> #include <linux/netfilter/xt_nfacct.h> MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("Xtables: match for the extended accounting infrastructure"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_nfacct"); MODULE_ALIAS("ip6t_nfacct"); static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) { int overquota; const struct xt_nfacct_match_info *info = par->targinfo; nfnl_acct_update(skb, info->nfacct); overquota = nfnl_acct_overquota(xt_net(par), info->nfacct); return overquota != NFACCT_UNDERQUOTA; } static int nfacct_mt_checkentry(const struct xt_mtchk_param *par) { struct xt_nfacct_match_info *info = par->matchinfo; struct nf_acct *nfacct; nfacct = nfnl_acct_find_get(par->net, info->name); if (nfacct == NULL) { pr_info_ratelimited("accounting object `%s' does not exists\n", info->name); return -ENOENT; } info->nfacct = nfacct; return 0; } static void nfacct_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_nfacct_match_info *info = par->matchinfo; nfnl_acct_put(info->nfacct); } static struct xt_match nfacct_mt_reg[] __read_mostly = { { .name = "nfacct", .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = nfacct_mt_checkentry, .match = nfacct_mt, .destroy = nfacct_mt_destroy, .matchsize = sizeof(struct xt_nfacct_match_info), .usersize = offsetof(struct xt_nfacct_match_info, nfacct), .me = THIS_MODULE, }, { .name = "nfacct", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = nfacct_mt_checkentry, .match = nfacct_mt, .destroy = nfacct_mt_destroy, .matchsize = sizeof(struct xt_nfacct_match_info_v1), .usersize = offsetof(struct xt_nfacct_match_info_v1, nfacct), .me = THIS_MODULE, }, }; static int __init nfacct_mt_init(void) { return xt_register_matches(nfacct_mt_reg, ARRAY_SIZE(nfacct_mt_reg)); } static void __exit nfacct_mt_exit(void) { xt_unregister_matches(nfacct_mt_reg, ARRAY_SIZE(nfacct_mt_reg)); } module_init(nfacct_mt_init); module_exit(nfacct_mt_exit); |
| 10 4 1 69 75 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __DRM_GEM_SHMEM_HELPER_H__ #define __DRM_GEM_SHMEM_HELPER_H__ #include <linux/fs.h> #include <linux/mm.h> #include <linux/mutex.h> #include <drm/drm_file.h> #include <drm/drm_gem.h> #include <drm/drm_ioctl.h> #include <drm/drm_prime.h> struct dma_buf_attachment; struct drm_mode_create_dumb; struct drm_printer; struct sg_table; /** * struct drm_gem_shmem_object - GEM object backed by shmem */ struct drm_gem_shmem_object { /** * @base: Base GEM object */ struct drm_gem_object base; /** * @pages: Page table */ struct page **pages; /** * @pages_use_count: * * Reference count on the pages table. * The pages are put when the count reaches zero. */ unsigned int pages_use_count; /** * @madv: State for madvise * * 0 is active/inuse. * A negative value is the object is purged. * Positive values are driver specific and not used by the helpers. */ int madv; /** * @madv_list: List entry for madvise tracking * * Typically used by drivers to track purgeable objects */ struct list_head madv_list; /** * @sgt: Scatter/gather table for imported PRIME buffers */ struct sg_table *sgt; /** * @vaddr: Kernel virtual address of the backing memory */ void *vaddr; /** * @vmap_use_count: * * Reference count on the virtual address. * The address are un-mapped when the count reaches zero. */ unsigned int vmap_use_count; /** * @pages_mark_dirty_on_put: * * Mark pages as dirty when they are put. */ bool pages_mark_dirty_on_put : 1; /** * @pages_mark_accessed_on_put: * * Mark pages as accessed when they are put. */ bool pages_mark_accessed_on_put : 1; /** * @map_wc: map object write-combined (instead of using shmem defaults). */ bool map_wc : 1; }; #define to_drm_gem_shmem_obj(obj) \ container_of(obj, struct drm_gem_shmem_object, base) struct drm_gem_shmem_object *drm_gem_shmem_create(struct drm_device *dev, size_t size); void drm_gem_shmem_free(struct drm_gem_shmem_object *shmem); void drm_gem_shmem_put_pages(struct drm_gem_shmem_object *shmem); int drm_gem_shmem_pin(struct drm_gem_shmem_object *shmem); void drm_gem_shmem_unpin(struct drm_gem_shmem_object *shmem); int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map); void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map); int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct *vma); int drm_gem_shmem_madvise(struct drm_gem_shmem_object *shmem, int madv); static inline bool drm_gem_shmem_is_purgeable(struct drm_gem_shmem_object *shmem) { return (shmem->madv > 0) && !shmem->vmap_use_count && shmem->sgt && !shmem->base.dma_buf && !shmem->base.import_attach; } void drm_gem_shmem_purge(struct drm_gem_shmem_object *shmem); struct sg_table *drm_gem_shmem_get_sg_table(struct drm_gem_shmem_object *shmem); struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_shmem_object *shmem); void drm_gem_shmem_print_info(const struct drm_gem_shmem_object *shmem, struct drm_printer *p, unsigned int indent); extern const struct vm_operations_struct drm_gem_shmem_vm_ops; /* * GEM object functions */ /** * drm_gem_shmem_object_free - GEM object function for drm_gem_shmem_free() * @obj: GEM object to free * * This function wraps drm_gem_shmem_free(). Drivers that employ the shmem helpers * should use it as their &drm_gem_object_funcs.free handler. */ static inline void drm_gem_shmem_object_free(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); drm_gem_shmem_free(shmem); } /** * drm_gem_shmem_object_print_info() - Print &drm_gem_shmem_object info for debugfs * @p: DRM printer * @indent: Tab indentation level * @obj: GEM object * * This function wraps drm_gem_shmem_print_info(). Drivers that employ the shmem helpers should * use this function as their &drm_gem_object_funcs.print_info handler. */ static inline void drm_gem_shmem_object_print_info(struct drm_printer *p, unsigned int indent, const struct drm_gem_object *obj) { const struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); drm_gem_shmem_print_info(shmem, p, indent); } /** * drm_gem_shmem_object_pin - GEM object function for drm_gem_shmem_pin() * @obj: GEM object * * This function wraps drm_gem_shmem_pin(). Drivers that employ the shmem helpers should * use it as their &drm_gem_object_funcs.pin handler. */ static inline int drm_gem_shmem_object_pin(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); return drm_gem_shmem_pin(shmem); } /** * drm_gem_shmem_object_unpin - GEM object function for drm_gem_shmem_unpin() * @obj: GEM object * * This function wraps drm_gem_shmem_unpin(). Drivers that employ the shmem helpers should * use it as their &drm_gem_object_funcs.unpin handler. */ static inline void drm_gem_shmem_object_unpin(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); drm_gem_shmem_unpin(shmem); } /** * drm_gem_shmem_object_get_sg_table - GEM object function for drm_gem_shmem_get_sg_table() * @obj: GEM object * * This function wraps drm_gem_shmem_get_sg_table(). Drivers that employ the shmem helpers should * use it as their &drm_gem_object_funcs.get_sg_table handler. * * Returns: * A pointer to the scatter/gather table of pinned pages or error pointer on failure. */ static inline struct sg_table *drm_gem_shmem_object_get_sg_table(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); return drm_gem_shmem_get_sg_table(shmem); } /* * drm_gem_shmem_object_vmap - GEM object function for drm_gem_shmem_vmap() * @obj: GEM object * @map: Returns the kernel virtual address of the SHMEM GEM object's backing store. * * This function wraps drm_gem_shmem_vmap(). Drivers that employ the shmem helpers should * use it as their &drm_gem_object_funcs.vmap handler. * * Returns: * 0 on success or a negative error code on failure. */ static inline int drm_gem_shmem_object_vmap(struct drm_gem_object *obj, struct iosys_map *map) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); return drm_gem_shmem_vmap(shmem, map); } /* * drm_gem_shmem_object_vunmap - GEM object function for drm_gem_shmem_vunmap() * @obj: GEM object * @map: Kernel virtual address where the SHMEM GEM object was mapped * * This function wraps drm_gem_shmem_vunmap(). Drivers that employ the shmem helpers should * use it as their &drm_gem_object_funcs.vunmap handler. */ static inline void drm_gem_shmem_object_vunmap(struct drm_gem_object *obj, struct iosys_map *map) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); drm_gem_shmem_vunmap(shmem, map); } /** * drm_gem_shmem_object_mmap - GEM object function for drm_gem_shmem_mmap() * @obj: GEM object * @vma: VMA for the area to be mapped * * This function wraps drm_gem_shmem_mmap(). Drivers that employ the shmem helpers should * use it as their &drm_gem_object_funcs.mmap handler. * * Returns: * 0 on success or a negative error code on failure. */ static inline int drm_gem_shmem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); return drm_gem_shmem_mmap(shmem, vma); } /* * Driver ops */ struct drm_gem_object * drm_gem_shmem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sgt); int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev, struct drm_mode_create_dumb *args); /** * DRM_GEM_SHMEM_DRIVER_OPS - Default shmem GEM operations * * This macro provides a shortcut for setting the shmem GEM operations in * the &drm_driver structure. */ #define DRM_GEM_SHMEM_DRIVER_OPS \ .gem_prime_import_sg_table = drm_gem_shmem_prime_import_sg_table, \ .dumb_create = drm_gem_shmem_dumb_create #endif /* __DRM_GEM_SHMEM_HELPER_H__ */ |
| 3 351 4 350 1 351 67 350 5 351 284 351 9 350 70 351 351 379 379 379 379 379 25 25 25 351 351 350 334 15 2 14 6 6 18 18 14 15 13 14 6 6 5 6 3 4 4 4 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/statfs.h> #include <linux/security.h> #include <linux/uaccess.h> #include <linux/compat.h> #include "internal.h" static int flags_by_mnt(int mnt_flags) { int flags = 0; if (mnt_flags & MNT_READONLY) flags |= ST_RDONLY; if (mnt_flags & MNT_NOSUID) flags |= ST_NOSUID; if (mnt_flags & MNT_NODEV) flags |= ST_NODEV; if (mnt_flags & MNT_NOEXEC) flags |= ST_NOEXEC; if (mnt_flags & MNT_NOATIME) flags |= ST_NOATIME; if (mnt_flags & MNT_NODIRATIME) flags |= ST_NODIRATIME; if (mnt_flags & MNT_RELATIME) flags |= ST_RELATIME; if (mnt_flags & MNT_NOSYMFOLLOW) flags |= ST_NOSYMFOLLOW; return flags; } static int flags_by_sb(int s_flags) { int flags = 0; if (s_flags & SB_SYNCHRONOUS) flags |= ST_SYNCHRONOUS; if (s_flags & SB_MANDLOCK) flags |= ST_MANDLOCK; if (s_flags & SB_RDONLY) flags |= ST_RDONLY; return flags; } static int calculate_f_flags(struct vfsmount *mnt) { return ST_VALID | flags_by_mnt(mnt->mnt_flags) | flags_by_sb(mnt->mnt_sb->s_flags); } static int statfs_by_dentry(struct dentry *dentry, struct kstatfs *buf) { int retval; if (!dentry->d_sb->s_op->statfs) return -ENOSYS; memset(buf, 0, sizeof(*buf)); retval = security_sb_statfs(dentry); if (retval) return retval; retval = dentry->d_sb->s_op->statfs(dentry, buf); if (retval == 0 && buf->f_frsize == 0) buf->f_frsize = buf->f_bsize; return retval; } int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid) { struct kstatfs st; int error; error = statfs_by_dentry(dentry, &st); if (error) return error; *fsid = st.f_fsid; return 0; } EXPORT_SYMBOL(vfs_get_fsid); int vfs_statfs(const struct path *path, struct kstatfs *buf) { int error; error = statfs_by_dentry(path->dentry, buf); if (!error) buf->f_flags = calculate_f_flags(path->mnt); return error; } EXPORT_SYMBOL(vfs_statfs); int user_statfs(const char __user *pathname, struct kstatfs *st) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (!error) { error = vfs_statfs(&path, st); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } int fd_statfs(int fd, struct kstatfs *st) { struct fd f = fdget_raw(fd); int error = -EBADF; if (f.file) { error = vfs_statfs(&f.file->f_path, st); fdput(f); } return error; } static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) { struct statfs buf; if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { memset(&buf, 0, sizeof(buf)); if (sizeof buf.f_blocks == 4) { if ((st->f_blocks | st->f_bfree | st->f_bavail | st->f_bsize | st->f_frsize) & 0xffffffff00000000ULL) return -EOVERFLOW; /* * f_files and f_ffree may be -1; it's okay to stuff * that into 32 bits */ if (st->f_files != -1 && (st->f_files & 0xffffffff00000000ULL)) return -EOVERFLOW; if (st->f_ffree != -1 && (st->f_ffree & 0xffffffff00000000ULL)) return -EOVERFLOW; } buf.f_type = st->f_type; buf.f_bsize = st->f_bsize; buf.f_blocks = st->f_blocks; buf.f_bfree = st->f_bfree; buf.f_bavail = st->f_bavail; buf.f_files = st->f_files; buf.f_ffree = st->f_ffree; buf.f_fsid = st->f_fsid; buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; return 0; } static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) { struct statfs64 buf; if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { memset(&buf, 0, sizeof(buf)); buf.f_type = st->f_type; buf.f_bsize = st->f_bsize; buf.f_blocks = st->f_blocks; buf.f_bfree = st->f_bfree; buf.f_bavail = st->f_bavail; buf.f_files = st->f_files; buf.f_ffree = st->f_ffree; buf.f_fsid = st->f_fsid; buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; return 0; } SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct statfs __user *, buf) { struct kstatfs st; int error = user_statfs(pathname, &st); if (!error) error = do_statfs_native(&st, buf); return error; } SYSCALL_DEFINE3(statfs64, const char __user *, pathname, size_t, sz, struct statfs64 __user *, buf) { struct kstatfs st; int error; if (sz != sizeof(*buf)) return -EINVAL; error = user_statfs(pathname, &st); if (!error) error = do_statfs64(&st, buf); return error; } SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct statfs __user *, buf) { struct kstatfs st; int error = fd_statfs(fd, &st); if (!error) error = do_statfs_native(&st, buf); return error; } SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user *, buf) { struct kstatfs st; int error; if (sz != sizeof(*buf)) return -EINVAL; error = fd_statfs(fd, &st); if (!error) error = do_statfs64(&st, buf); return error; } static int vfs_ustat(dev_t dev, struct kstatfs *sbuf) { struct super_block *s = user_get_super(dev, false); int err; if (!s) return -EINVAL; err = statfs_by_dentry(s->s_root, sbuf); drop_super(s); return err; } SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf) { struct ustat tmp; struct kstatfs sbuf; int err = vfs_ustat(new_decode_dev(dev), &sbuf); if (err) return err; memset(&tmp,0,sizeof(struct ustat)); tmp.f_tfree = sbuf.f_bfree; if (IS_ENABLED(CONFIG_ARCH_32BIT_USTAT_F_TINODE)) tmp.f_tinode = min_t(u64, sbuf.f_ffree, UINT_MAX); else tmp.f_tinode = sbuf.f_ffree; return copy_to_user(ubuf, &tmp, sizeof(struct ustat)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf) { struct compat_statfs buf; if (sizeof ubuf->f_blocks == 4) { if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail | kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL) return -EOVERFLOW; /* f_files and f_ffree may be -1; it's okay * to stuff that into 32 bits */ if (kbuf->f_files != 0xffffffffffffffffULL && (kbuf->f_files & 0xffffffff00000000ULL)) return -EOVERFLOW; if (kbuf->f_ffree != 0xffffffffffffffffULL && (kbuf->f_ffree & 0xffffffff00000000ULL)) return -EOVERFLOW; } memset(&buf, 0, sizeof(struct compat_statfs)); buf.f_type = kbuf->f_type; buf.f_bsize = kbuf->f_bsize; buf.f_blocks = kbuf->f_blocks; buf.f_bfree = kbuf->f_bfree; buf.f_bavail = kbuf->f_bavail; buf.f_files = kbuf->f_files; buf.f_ffree = kbuf->f_ffree; buf.f_namelen = kbuf->f_namelen; buf.f_fsid.val[0] = kbuf->f_fsid.val[0]; buf.f_fsid.val[1] = kbuf->f_fsid.val[1]; buf.f_frsize = kbuf->f_frsize; buf.f_flags = kbuf->f_flags; if (copy_to_user(ubuf, &buf, sizeof(struct compat_statfs))) return -EFAULT; return 0; } /* * The following statfs calls are copies of code from fs/statfs.c and * should be checked against those from time to time */ COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf) { struct kstatfs tmp; int error = user_statfs(pathname, &tmp); if (!error) error = put_compat_statfs(buf, &tmp); return error; } COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf) { struct kstatfs tmp; int error = fd_statfs(fd, &tmp); if (!error) error = put_compat_statfs(buf, &tmp); return error; } static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf) { struct compat_statfs64 buf; if ((kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL) return -EOVERFLOW; memset(&buf, 0, sizeof(struct compat_statfs64)); buf.f_type = kbuf->f_type; buf.f_bsize = kbuf->f_bsize; buf.f_blocks = kbuf->f_blocks; buf.f_bfree = kbuf->f_bfree; buf.f_bavail = kbuf->f_bavail; buf.f_files = kbuf->f_files; buf.f_ffree = kbuf->f_ffree; buf.f_namelen = kbuf->f_namelen; buf.f_fsid.val[0] = kbuf->f_fsid.val[0]; buf.f_fsid.val[1] = kbuf->f_fsid.val[1]; buf.f_frsize = kbuf->f_frsize; buf.f_flags = kbuf->f_flags; if (copy_to_user(ubuf, &buf, sizeof(struct compat_statfs64))) return -EFAULT; return 0; } int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, struct compat_statfs64 __user * buf) { struct kstatfs tmp; int error; if (sz != sizeof(*buf)) return -EINVAL; error = user_statfs(pathname, &tmp); if (!error) error = put_compat_statfs64(buf, &tmp); return error; } COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf) { return kcompat_sys_statfs64(pathname, sz, buf); } int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user * buf) { struct kstatfs tmp; int error; if (sz != sizeof(*buf)) return -EINVAL; error = fd_statfs(fd, &tmp); if (!error) error = put_compat_statfs64(buf, &tmp); return error; } COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf) { return kcompat_sys_fstatfs64(fd, sz, buf); } /* * This is a copy of sys_ustat, just dealing with a structure layout. * Given how simple this syscall is that apporach is more maintainable * than the various conversion hacks. */ COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u) { struct compat_ustat tmp; struct kstatfs sbuf; int err = vfs_ustat(new_decode_dev(dev), &sbuf); if (err) return err; memset(&tmp, 0, sizeof(struct compat_ustat)); tmp.f_tfree = sbuf.f_bfree; tmp.f_tinode = sbuf.f_ffree; if (copy_to_user(u, &tmp, sizeof(struct compat_ustat))) return -EFAULT; return 0; } #endif |
| 8 1 5 8 8 5 6 6 5 5 5 5 1 4 5 5 4 5 1 1 5 5 5 5 5 5 5 5 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 5 1 6 6 6 2 14 1 1 1 1 1 9 9 2 8 9 1 2 2 2 2 10 10 2 9 7 4 1 1 4 1 4 1 5 3 3 3 5 6 1 2 1 1 2 2 1 2 8 8 8 4 8 6 8 33 6 5 5 6 33 11 1 9 1 1 15 6 9 15 3 13 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2009 Red Hat, Inc. * Author: Michael S. Tsirkin <mst@redhat.com> * * virtio-net server in host kernel. */ #include <linux/compat.h> #include <linux/eventfd.h> #include <linux/vhost.h> #include <linux/virtio_net.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/mutex.h> #include <linux/workqueue.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/sched/clock.h> #include <linux/sched/signal.h> #include <linux/vmalloc.h> #include <linux/net.h> #include <linux/if_packet.h> #include <linux/if_arp.h> #include <linux/if_tun.h> #include <linux/if_macvlan.h> #include <linux/if_tap.h> #include <linux/if_vlan.h> #include <linux/skb_array.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/xdp.h> #include "vhost.h" static int experimental_zcopytx = 0; module_param(experimental_zcopytx, int, 0444); MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" " 1 -Enable; 0 - Disable"); /* Max number of bytes transferred before requeueing the job. * Using this limit prevents one virtqueue from starving others. */ #define VHOST_NET_WEIGHT 0x80000 /* Max number of packets transferred before requeueing the job. * Using this limit prevents one virtqueue from starving others with small * pkts. */ #define VHOST_NET_PKT_WEIGHT 256 /* MAX number of TX used buffers for outstanding zerocopy */ #define VHOST_MAX_PEND 128 #define VHOST_GOODCOPY_LEN 256 /* * For transmit, used buffer len is unused; we override it to track buffer * status internally; used for zerocopy tx only. */ /* Lower device DMA failed */ #define VHOST_DMA_FAILED_LEN ((__force __virtio32)3) /* Lower device DMA done */ #define VHOST_DMA_DONE_LEN ((__force __virtio32)2) /* Lower device DMA in progress */ #define VHOST_DMA_IN_PROGRESS ((__force __virtio32)1) /* Buffer unused */ #define VHOST_DMA_CLEAR_LEN ((__force __virtio32)0) #define VHOST_DMA_IS_DONE(len) ((__force u32)(len) >= (__force u32)VHOST_DMA_DONE_LEN) enum { VHOST_NET_FEATURES = VHOST_FEATURES | (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) | (1ULL << VIRTIO_NET_F_MRG_RXBUF) | (1ULL << VIRTIO_F_ACCESS_PLATFORM) | (1ULL << VIRTIO_F_RING_RESET) }; enum { VHOST_NET_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) }; enum { VHOST_NET_VQ_RX = 0, VHOST_NET_VQ_TX = 1, VHOST_NET_VQ_MAX = 2, }; struct vhost_net_ubuf_ref { /* refcount follows semantics similar to kref: * 0: object is released * 1: no outstanding ubufs * >1: outstanding ubufs */ atomic_t refcount; wait_queue_head_t wait; struct vhost_virtqueue *vq; }; #define VHOST_NET_BATCH 64 struct vhost_net_buf { void **queue; int tail; int head; }; struct vhost_net_virtqueue { struct vhost_virtqueue vq; size_t vhost_hlen; size_t sock_hlen; /* vhost zerocopy support fields below: */ /* last used idx for outstanding DMA zerocopy buffers */ int upend_idx; /* For TX, first used idx for DMA done zerocopy buffers * For RX, number of batched heads */ int done_idx; /* Number of XDP frames batched */ int batched_xdp; /* an array of userspace buffers info */ struct ubuf_info_msgzc *ubuf_info; /* Reference counting for outstanding ubufs. * Protected by vq mutex. Writers must also take device mutex. */ struct vhost_net_ubuf_ref *ubufs; struct ptr_ring *rx_ring; struct vhost_net_buf rxq; /* Batched XDP buffs */ struct xdp_buff *xdp; }; struct vhost_net { struct vhost_dev dev; struct vhost_net_virtqueue vqs[VHOST_NET_VQ_MAX]; struct vhost_poll poll[VHOST_NET_VQ_MAX]; /* Number of TX recently submitted. * Protected by tx vq lock. */ unsigned tx_packets; /* Number of times zerocopy TX recently failed. * Protected by tx vq lock. */ unsigned tx_zcopy_err; /* Flush in progress. Protected by tx vq lock. */ bool tx_flush; /* Private page frag */ struct page_frag page_frag; /* Refcount bias of page frag */ int refcnt_bias; }; static unsigned vhost_net_zcopy_mask __read_mostly; static void *vhost_net_buf_get_ptr(struct vhost_net_buf *rxq) { if (rxq->tail != rxq->head) return rxq->queue[rxq->head]; else return NULL; } static int vhost_net_buf_get_size(struct vhost_net_buf *rxq) { return rxq->tail - rxq->head; } static int vhost_net_buf_is_empty(struct vhost_net_buf *rxq) { return rxq->tail == rxq->head; } static void *vhost_net_buf_consume(struct vhost_net_buf *rxq) { void *ret = vhost_net_buf_get_ptr(rxq); ++rxq->head; return ret; } static int vhost_net_buf_produce(struct vhost_net_virtqueue *nvq) { struct vhost_net_buf *rxq = &nvq->rxq; rxq->head = 0; rxq->tail = ptr_ring_consume_batched(nvq->rx_ring, rxq->queue, VHOST_NET_BATCH); return rxq->tail; } static void vhost_net_buf_unproduce(struct vhost_net_virtqueue *nvq) { struct vhost_net_buf *rxq = &nvq->rxq; if (nvq->rx_ring && !vhost_net_buf_is_empty(rxq)) { ptr_ring_unconsume(nvq->rx_ring, rxq->queue + rxq->head, vhost_net_buf_get_size(rxq), tun_ptr_free); rxq->head = rxq->tail = 0; } } static int vhost_net_buf_peek_len(void *ptr) { if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); return xdpf->len; } return __skb_array_len_with_tag(ptr); } static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq) { struct vhost_net_buf *rxq = &nvq->rxq; if (!vhost_net_buf_is_empty(rxq)) goto out; if (!vhost_net_buf_produce(nvq)) return 0; out: return vhost_net_buf_peek_len(vhost_net_buf_get_ptr(rxq)); } static void vhost_net_buf_init(struct vhost_net_buf *rxq) { rxq->head = rxq->tail = 0; } static void vhost_net_enable_zcopy(int vq) { vhost_net_zcopy_mask |= 0x1 << vq; } static struct vhost_net_ubuf_ref * vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy) { struct vhost_net_ubuf_ref *ubufs; /* No zero copy backend? Nothing to count. */ if (!zcopy) return NULL; ubufs = kmalloc(sizeof(*ubufs), GFP_KERNEL); if (!ubufs) return ERR_PTR(-ENOMEM); atomic_set(&ubufs->refcount, 1); init_waitqueue_head(&ubufs->wait); ubufs->vq = vq; return ubufs; } static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs) { int r = atomic_sub_return(1, &ubufs->refcount); if (unlikely(!r)) wake_up(&ubufs->wait); return r; } static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs) { vhost_net_ubuf_put(ubufs); wait_event(ubufs->wait, !atomic_read(&ubufs->refcount)); } static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs) { vhost_net_ubuf_put_and_wait(ubufs); kfree(ubufs); } static void vhost_net_clear_ubuf_info(struct vhost_net *n) { int i; for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { kfree(n->vqs[i].ubuf_info); n->vqs[i].ubuf_info = NULL; } } static int vhost_net_set_ubuf_info(struct vhost_net *n) { bool zcopy; int i; for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { zcopy = vhost_net_zcopy_mask & (0x1 << i); if (!zcopy) continue; n->vqs[i].ubuf_info = kmalloc_array(UIO_MAXIOV, sizeof(*n->vqs[i].ubuf_info), GFP_KERNEL); if (!n->vqs[i].ubuf_info) goto err; } return 0; err: vhost_net_clear_ubuf_info(n); return -ENOMEM; } static void vhost_net_vq_reset(struct vhost_net *n) { int i; vhost_net_clear_ubuf_info(n); for (i = 0; i < VHOST_NET_VQ_MAX; i++) { n->vqs[i].done_idx = 0; n->vqs[i].upend_idx = 0; n->vqs[i].ubufs = NULL; n->vqs[i].vhost_hlen = 0; n->vqs[i].sock_hlen = 0; vhost_net_buf_init(&n->vqs[i].rxq); } } static void vhost_net_tx_packet(struct vhost_net *net) { ++net->tx_packets; if (net->tx_packets < 1024) return; net->tx_packets = 0; net->tx_zcopy_err = 0; } static void vhost_net_tx_err(struct vhost_net *net) { ++net->tx_zcopy_err; } static bool vhost_net_tx_select_zcopy(struct vhost_net *net) { /* TX flush waits for outstanding DMAs to be done. * Don't start new DMAs. */ return !net->tx_flush && net->tx_packets / 64 >= net->tx_zcopy_err; } static bool vhost_sock_zcopy(struct socket *sock) { return unlikely(experimental_zcopytx) && sock_flag(sock->sk, SOCK_ZEROCOPY); } static bool vhost_sock_xdp(struct socket *sock) { return sock_flag(sock->sk, SOCK_XDP); } /* In case of DMA done not in order in lower device driver for some reason. * upend_idx is used to track end of used idx, done_idx is used to track head * of used idx. Once lower device DMA done contiguously, we will signal KVM * guest used idx. */ static void vhost_zerocopy_signal_used(struct vhost_net *net, struct vhost_virtqueue *vq) { struct vhost_net_virtqueue *nvq = container_of(vq, struct vhost_net_virtqueue, vq); int i, add; int j = 0; for (i = nvq->done_idx; i != nvq->upend_idx; i = (i + 1) % UIO_MAXIOV) { if (vq->heads[i].len == VHOST_DMA_FAILED_LEN) vhost_net_tx_err(net); if (VHOST_DMA_IS_DONE(vq->heads[i].len)) { vq->heads[i].len = VHOST_DMA_CLEAR_LEN; ++j; } else break; } while (j) { add = min(UIO_MAXIOV - nvq->done_idx, j); vhost_add_used_and_signal_n(vq->dev, vq, &vq->heads[nvq->done_idx], add); nvq->done_idx = (nvq->done_idx + add) % UIO_MAXIOV; j -= add; } } static void vhost_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf_base, bool success) { struct ubuf_info_msgzc *ubuf = uarg_to_msgzc(ubuf_base); struct vhost_net_ubuf_ref *ubufs = ubuf->ctx; struct vhost_virtqueue *vq = ubufs->vq; int cnt; rcu_read_lock_bh(); /* set len to mark this desc buffers done DMA */ vq->heads[ubuf->desc].len = success ? VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN; cnt = vhost_net_ubuf_put(ubufs); /* * Trigger polling thread if guest stopped submitting new buffers: * in this case, the refcount after decrement will eventually reach 1. * We also trigger polling periodically after each 16 packets * (the value 16 here is more or less arbitrary, it's tuned to trigger * less than 10% of times). */ if (cnt <= 1 || !(cnt % 16)) vhost_poll_queue(&vq->poll); rcu_read_unlock_bh(); } static inline unsigned long busy_clock(void) { return local_clock() >> 10; } static bool vhost_can_busy_poll(unsigned long endtime) { return likely(!need_resched() && !time_after(busy_clock(), endtime) && !signal_pending(current)); } static void vhost_net_disable_vq(struct vhost_net *n, struct vhost_virtqueue *vq) { struct vhost_net_virtqueue *nvq = container_of(vq, struct vhost_net_virtqueue, vq); struct vhost_poll *poll = n->poll + (nvq - n->vqs); if (!vhost_vq_get_backend(vq)) return; vhost_poll_stop(poll); } static int vhost_net_enable_vq(struct vhost_net *n, struct vhost_virtqueue *vq) { struct vhost_net_virtqueue *nvq = container_of(vq, struct vhost_net_virtqueue, vq); struct vhost_poll *poll = n->poll + (nvq - n->vqs); struct socket *sock; sock = vhost_vq_get_backend(vq); if (!sock) return 0; return vhost_poll_start(poll, sock->file); } static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq) { struct vhost_virtqueue *vq = &nvq->vq; struct vhost_dev *dev = vq->dev; if (!nvq->done_idx) return; vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx); nvq->done_idx = 0; } static void vhost_tx_batch(struct vhost_net *net, struct vhost_net_virtqueue *nvq, struct socket *sock, struct msghdr *msghdr) { struct tun_msg_ctl ctl = { .type = TUN_MSG_PTR, .num = nvq->batched_xdp, .ptr = nvq->xdp, }; int i, err; if (nvq->batched_xdp == 0) goto signal_used; msghdr->msg_control = &ctl; msghdr->msg_controllen = sizeof(ctl); err = sock->ops->sendmsg(sock, msghdr, 0); if (unlikely(err < 0)) { vq_err(&nvq->vq, "Fail to batch sending packets\n"); /* free pages owned by XDP; since this is an unlikely error path, * keep it simple and avoid more complex bulk update for the * used pages */ for (i = 0; i < nvq->batched_xdp; ++i) put_page(virt_to_head_page(nvq->xdp[i].data)); nvq->batched_xdp = 0; nvq->done_idx = 0; return; } signal_used: vhost_net_signal_used(nvq); nvq->batched_xdp = 0; } static int sock_has_rx_data(struct socket *sock) { if (unlikely(!sock)) return 0; if (sock->ops->peek_len) return sock->ops->peek_len(sock); return skb_queue_empty(&sock->sk->sk_receive_queue); } static void vhost_net_busy_poll_try_queue(struct vhost_net *net, struct vhost_virtqueue *vq) { if (!vhost_vq_avail_empty(&net->dev, vq)) { vhost_poll_queue(&vq->poll); } else if (unlikely(vhost_enable_notify(&net->dev, vq))) { vhost_disable_notify(&net->dev, vq); vhost_poll_queue(&vq->poll); } } static void vhost_net_busy_poll(struct vhost_net *net, struct vhost_virtqueue *rvq, struct vhost_virtqueue *tvq, bool *busyloop_intr, bool poll_rx) { unsigned long busyloop_timeout; unsigned long endtime; struct socket *sock; struct vhost_virtqueue *vq = poll_rx ? tvq : rvq; /* Try to hold the vq mutex of the paired virtqueue. We can't * use mutex_lock() here since we could not guarantee a * consistenet lock ordering. */ if (!mutex_trylock(&vq->mutex)) return; vhost_disable_notify(&net->dev, vq); sock = vhost_vq_get_backend(rvq); busyloop_timeout = poll_rx ? rvq->busyloop_timeout: tvq->busyloop_timeout; preempt_disable(); endtime = busy_clock() + busyloop_timeout; while (vhost_can_busy_poll(endtime)) { if (vhost_vq_has_work(vq)) { *busyloop_intr = true; break; } if ((sock_has_rx_data(sock) && !vhost_vq_avail_empty(&net->dev, rvq)) || !vhost_vq_avail_empty(&net->dev, tvq)) break; cpu_relax(); } preempt_enable(); if (poll_rx || sock_has_rx_data(sock)) vhost_net_busy_poll_try_queue(net, vq); else if (!poll_rx) /* On tx here, sock has no rx data. */ vhost_enable_notify(&net->dev, rvq); mutex_unlock(&vq->mutex); } static int vhost_net_tx_get_vq_desc(struct vhost_net *net, struct vhost_net_virtqueue *tnvq, unsigned int *out_num, unsigned int *in_num, struct msghdr *msghdr, bool *busyloop_intr) { struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX]; struct vhost_virtqueue *rvq = &rnvq->vq; struct vhost_virtqueue *tvq = &tnvq->vq; int r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), out_num, in_num, NULL, NULL); if (r == tvq->num && tvq->busyloop_timeout) { /* Flush batched packets first */ if (!vhost_sock_zcopy(vhost_vq_get_backend(tvq))) vhost_tx_batch(net, tnvq, vhost_vq_get_backend(tvq), msghdr); vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, false); r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), out_num, in_num, NULL, NULL); } return r; } static bool vhost_exceeds_maxpend(struct vhost_net *net) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; return (nvq->upend_idx + UIO_MAXIOV - nvq->done_idx) % UIO_MAXIOV > min_t(unsigned int, VHOST_MAX_PEND, vq->num >> 2); } static size_t init_iov_iter(struct vhost_virtqueue *vq, struct iov_iter *iter, size_t hdr_size, int out) { /* Skip header. TODO: support TSO. */ size_t len = iov_length(vq->iov, out); iov_iter_init(iter, ITER_SOURCE, vq->iov, out, len); iov_iter_advance(iter, hdr_size); return iov_iter_count(iter); } static int get_tx_bufs(struct vhost_net *net, struct vhost_net_virtqueue *nvq, struct msghdr *msg, unsigned int *out, unsigned int *in, size_t *len, bool *busyloop_intr) { struct vhost_virtqueue *vq = &nvq->vq; int ret; ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); if (ret < 0 || ret == vq->num) return ret; if (*in) { vq_err(vq, "Unexpected descriptor format for TX: out %d, int %d\n", *out, *in); return -EFAULT; } /* Sanity check */ *len = init_iov_iter(vq, &msg->msg_iter, nvq->vhost_hlen, *out); if (*len == 0) { vq_err(vq, "Unexpected header len for TX: %zd expected %zd\n", *len, nvq->vhost_hlen); return -EFAULT; } return ret; } static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len) { return total_len < VHOST_NET_WEIGHT && !vhost_vq_avail_empty(vq->dev, vq); } static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz, struct page_frag *pfrag, gfp_t gfp) { if (pfrag->page) { if (pfrag->offset + sz <= pfrag->size) return true; __page_frag_cache_drain(pfrag->page, net->refcnt_bias); } pfrag->offset = 0; net->refcnt_bias = 0; if (SKB_FRAG_PAGE_ORDER) { /* Avoid direct reclaim but allow kswapd to wake */ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; goto done; } } pfrag->page = alloc_page(gfp); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE; goto done; } return false; done: net->refcnt_bias = USHRT_MAX; page_ref_add(pfrag->page, USHRT_MAX - 1); return true; } #define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, struct iov_iter *from) { struct vhost_virtqueue *vq = &nvq->vq; struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); struct socket *sock = vhost_vq_get_backend(vq); struct page_frag *alloc_frag = &net->page_frag; struct virtio_net_hdr *gso; struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; struct tun_xdp_hdr *hdr; size_t len = iov_iter_count(from); int headroom = vhost_sock_xdp(sock) ? XDP_PACKET_HEADROOM : 0; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); int pad = SKB_DATA_ALIGN(VHOST_NET_RX_PAD + headroom + nvq->sock_hlen); int sock_hlen = nvq->sock_hlen; void *buf; int copied; if (unlikely(len < nvq->sock_hlen)) return -EFAULT; if (SKB_DATA_ALIGN(len + pad) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return -ENOSPC; buflen += SKB_DATA_ALIGN(len + pad); alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); if (unlikely(!vhost_net_page_frag_refill(net, buflen, alloc_frag, GFP_KERNEL))) return -ENOMEM; buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; copied = copy_page_from_iter(alloc_frag->page, alloc_frag->offset + offsetof(struct tun_xdp_hdr, gso), sock_hlen, from); if (copied != sock_hlen) return -EFAULT; hdr = buf; gso = &hdr->gso; if ((gso->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && vhost16_to_cpu(vq, gso->csum_start) + vhost16_to_cpu(vq, gso->csum_offset) + 2 > vhost16_to_cpu(vq, gso->hdr_len)) { gso->hdr_len = cpu_to_vhost16(vq, vhost16_to_cpu(vq, gso->csum_start) + vhost16_to_cpu(vq, gso->csum_offset) + 2); if (vhost16_to_cpu(vq, gso->hdr_len) > len) return -EINVAL; } len -= sock_hlen; copied = copy_page_from_iter(alloc_frag->page, alloc_frag->offset + pad, len, from); if (copied != len) return -EFAULT; xdp_init_buff(xdp, buflen, NULL); xdp_prepare_buff(xdp, buf, pad, len, true); hdr->buflen = buflen; --net->refcnt_bias; alloc_frag->offset += buflen; ++nvq->batched_xdp; return 0; } static void handle_tx_copy(struct vhost_net *net, struct socket *sock) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; unsigned out, in; int head; struct msghdr msg = { .msg_name = NULL, .msg_namelen = 0, .msg_control = NULL, .msg_controllen = 0, .msg_flags = MSG_DONTWAIT, }; size_t len, total_len = 0; int err; int sent_pkts = 0; bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX); do { bool busyloop_intr = false; if (nvq->done_idx == VHOST_NET_BATCH) vhost_tx_batch(net, nvq, sock, &msg); head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, &busyloop_intr); /* On error, stop handling until the next kick. */ if (unlikely(head < 0)) break; /* Nothing new? Wait for eventfd to tell us they refilled. */ if (head == vq->num) { if (unlikely(busyloop_intr)) { vhost_poll_queue(&vq->poll); } else if (unlikely(vhost_enable_notify(&net->dev, vq))) { vhost_disable_notify(&net->dev, vq); continue; } break; } total_len += len; /* For simplicity, TX batching is only enabled if * sndbuf is unlimited. */ if (sock_can_batch) { err = vhost_net_build_xdp(nvq, &msg.msg_iter); if (!err) { goto done; } else if (unlikely(err != -ENOSPC)) { vhost_tx_batch(net, nvq, sock, &msg); vhost_discard_vq_desc(vq, 1); vhost_net_enable_vq(net, vq); break; } /* We can't build XDP buff, go for single * packet path but let's flush batched * packets. */ vhost_tx_batch(net, nvq, sock, &msg); msg.msg_control = NULL; } else { if (tx_can_batch(vq, total_len)) msg.msg_flags |= MSG_MORE; else msg.msg_flags &= ~MSG_MORE; } err = sock->ops->sendmsg(sock, &msg, len); if (unlikely(err < 0)) { if (err == -EAGAIN || err == -ENOMEM || err == -ENOBUFS) { vhost_discard_vq_desc(vq, 1); vhost_net_enable_vq(net, vq); break; } pr_debug("Fail to send packet: err %d", err); } else if (unlikely(err != len)) pr_debug("Truncated TX packet: len %d != %zd\n", err, len); done: vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); vq->heads[nvq->done_idx].len = 0; ++nvq->done_idx; } while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len))); vhost_tx_batch(net, nvq, sock, &msg); } static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; unsigned out, in; int head; struct msghdr msg = { .msg_name = NULL, .msg_namelen = 0, .msg_control = NULL, .msg_controllen = 0, .msg_flags = MSG_DONTWAIT, }; struct tun_msg_ctl ctl; size_t len, total_len = 0; int err; struct vhost_net_ubuf_ref *ubufs; struct ubuf_info_msgzc *ubuf; bool zcopy_used; int sent_pkts = 0; do { bool busyloop_intr; /* Release DMAs done buffers first */ vhost_zerocopy_signal_used(net, vq); busyloop_intr = false; head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, &busyloop_intr); /* On error, stop handling until the next kick. */ if (unlikely(head < 0)) break; /* Nothing new? Wait for eventfd to tell us they refilled. */ if (head == vq->num) { if (unlikely(busyloop_intr)) { vhost_poll_queue(&vq->poll); } else if (unlikely(vhost_enable_notify(&net->dev, vq))) { vhost_disable_notify(&net->dev, vq); continue; } break; } zcopy_used = len >= VHOST_GOODCOPY_LEN && !vhost_exceeds_maxpend(net) && vhost_net_tx_select_zcopy(net); /* use msg_control to pass vhost zerocopy ubuf info to skb */ if (zcopy_used) { ubuf = nvq->ubuf_info + nvq->upend_idx; vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head); vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS; ubuf->ctx = nvq->ubufs; ubuf->desc = nvq->upend_idx; ubuf->ubuf.callback = vhost_zerocopy_callback; ubuf->ubuf.flags = SKBFL_ZEROCOPY_FRAG; refcount_set(&ubuf->ubuf.refcnt, 1); msg.msg_control = &ctl; ctl.type = TUN_MSG_UBUF; ctl.ptr = &ubuf->ubuf; msg.msg_controllen = sizeof(ctl); ubufs = nvq->ubufs; atomic_inc(&ubufs->refcount); nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV; } else { msg.msg_control = NULL; ubufs = NULL; } total_len += len; if (tx_can_batch(vq, total_len) && likely(!vhost_exceeds_maxpend(net))) { msg.msg_flags |= MSG_MORE; } else { msg.msg_flags &= ~MSG_MORE; } err = sock->ops->sendmsg(sock, &msg, len); if (unlikely(err < 0)) { bool retry = err == -EAGAIN || err == -ENOMEM || err == -ENOBUFS; if (zcopy_used) { if (vq->heads[ubuf->desc].len == VHOST_DMA_IN_PROGRESS) vhost_net_ubuf_put(ubufs); if (retry) nvq->upend_idx = ((unsigned)nvq->upend_idx - 1) % UIO_MAXIOV; else vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN; } if (retry) { vhost_discard_vq_desc(vq, 1); vhost_net_enable_vq(net, vq); break; } pr_debug("Fail to send packet: err %d", err); } else if (unlikely(err != len)) pr_debug("Truncated TX packet: " " len %d != %zd\n", err, len); if (!zcopy_used) vhost_add_used_and_signal(&net->dev, vq, head, 0); else vhost_zerocopy_signal_used(net, vq); vhost_net_tx_packet(net); } while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len))); } /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ static void handle_tx(struct vhost_net *net) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; struct socket *sock; mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_TX); sock = vhost_vq_get_backend(vq); if (!sock) goto out; if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(&net->dev, vq); vhost_net_disable_vq(net, vq); if (vhost_sock_zcopy(sock)) handle_tx_zerocopy(net, sock); else handle_tx_copy(net, sock); out: mutex_unlock(&vq->mutex); } static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk) { struct sk_buff *head; int len = 0; unsigned long flags; if (rvq->rx_ring) return vhost_net_buf_peek(rvq); spin_lock_irqsave(&sk->sk_receive_queue.lock, flags); head = skb_peek(&sk->sk_receive_queue); if (likely(head)) { len = head->len; if (skb_vlan_tag_present(head)) len += VLAN_HLEN; } spin_unlock_irqrestore(&sk->sk_receive_queue.lock, flags); return len; } static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk, bool *busyloop_intr) { struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX]; struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *rvq = &rnvq->vq; struct vhost_virtqueue *tvq = &tnvq->vq; int len = peek_head_len(rnvq, sk); if (!len && rvq->busyloop_timeout) { /* Flush batched heads first */ vhost_net_signal_used(rnvq); /* Both tx vq and rx socket were polled here */ vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, true); len = peek_head_len(rnvq, sk); } return len; } /* This is a multi-buffer version of vhost_get_desc, that works if * vq has read descriptors only. * @vq - the relevant virtqueue * @datalen - data length we'll be reading * @iovcount - returned count of io vectors we fill * @log - vhost log * @log_num - log offset * @quota - headcount quota, 1 for big buffer * returns number of buffer heads allocated, negative on error */ static int get_rx_bufs(struct vhost_virtqueue *vq, struct vring_used_elem *heads, int datalen, unsigned *iovcount, struct vhost_log *log, unsigned *log_num, unsigned int quota) { unsigned int out, in; int seg = 0; int headcount = 0; unsigned d; int r, nlogs = 0; /* len is always initialized before use since we are always called with * datalen > 0. */ u32 len; while (datalen > 0 && headcount < quota) { if (unlikely(seg >= UIO_MAXIOV)) { r = -ENOBUFS; goto err; } r = vhost_get_vq_desc(vq, vq->iov + seg, ARRAY_SIZE(vq->iov) - seg, &out, &in, log, log_num); if (unlikely(r < 0)) goto err; d = r; if (d == vq->num) { r = 0; goto err; } if (unlikely(out || in <= 0)) { vq_err(vq, "unexpected descriptor format for RX: " "out %d, in %d\n", out, in); r = -EINVAL; goto err; } if (unlikely(log)) { nlogs += *log_num; log += *log_num; } heads[headcount].id = cpu_to_vhost32(vq, d); len = iov_length(vq->iov + seg, in); heads[headcount].len = cpu_to_vhost32(vq, len); datalen -= len; ++headcount; seg += in; } heads[headcount - 1].len = cpu_to_vhost32(vq, len + datalen); *iovcount = seg; if (unlikely(log)) *log_num = nlogs; /* Detect overrun */ if (unlikely(datalen > 0)) { r = UIO_MAXIOV + 1; goto err; } return headcount; err: vhost_discard_vq_desc(vq, headcount); return r; } /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ static void handle_rx(struct vhost_net *net) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_RX]; struct vhost_virtqueue *vq = &nvq->vq; unsigned in, log; struct vhost_log *vq_log; struct msghdr msg = { .msg_name = NULL, .msg_namelen = 0, .msg_control = NULL, /* FIXME: get and handle RX aux data. */ .msg_controllen = 0, .msg_flags = MSG_DONTWAIT, }; struct virtio_net_hdr hdr = { .flags = 0, .gso_type = VIRTIO_NET_HDR_GSO_NONE }; size_t total_len = 0; int err, mergeable; s16 headcount; size_t vhost_hlen, sock_hlen; size_t vhost_len, sock_len; bool busyloop_intr = false; struct socket *sock; struct iov_iter fixup; __virtio16 num_buffers; int recv_pkts = 0; mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_RX); sock = vhost_vq_get_backend(vq); if (!sock) goto out; if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(&net->dev, vq); vhost_net_disable_vq(net, vq); vhost_hlen = nvq->vhost_hlen; sock_hlen = nvq->sock_hlen; vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ? vq->log : NULL; mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF); do { sock_len = vhost_net_rx_peek_head_len(net, sock->sk, &busyloop_intr); if (!sock_len) break; sock_len += sock_hlen; vhost_len = sock_len + vhost_hlen; headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx, vhost_len, &in, vq_log, &log, likely(mergeable) ? UIO_MAXIOV : 1); /* On error, stop handling until the next kick. */ if (unlikely(headcount < 0)) goto out; /* OK, now we need to know about added descriptors. */ if (!headcount) { if (unlikely(busyloop_intr)) { vhost_poll_queue(&vq->poll); } else if (unlikely(vhost_enable_notify(&net->dev, vq))) { /* They have slipped one in as we were * doing that: check again. */ vhost_disable_notify(&net->dev, vq); continue; } /* Nothing new? Wait for eventfd to tell us * they refilled. */ goto out; } busyloop_intr = false; if (nvq->rx_ring) msg.msg_control = vhost_net_buf_consume(&nvq->rxq); /* On overrun, truncate and discard */ if (unlikely(headcount > UIO_MAXIOV)) { iov_iter_init(&msg.msg_iter, ITER_DEST, vq->iov, 1, 1); err = sock->ops->recvmsg(sock, &msg, 1, MSG_DONTWAIT | MSG_TRUNC); pr_debug("Discarded rx packet: len %zd\n", sock_len); continue; } /* We don't need to be notified again. */ iov_iter_init(&msg.msg_iter, ITER_DEST, vq->iov, in, vhost_len); fixup = msg.msg_iter; if (unlikely((vhost_hlen))) { /* We will supply the header ourselves * TODO: support TSO. */ iov_iter_advance(&msg.msg_iter, vhost_hlen); } err = sock->ops->recvmsg(sock, &msg, sock_len, MSG_DONTWAIT | MSG_TRUNC); /* Userspace might have consumed the packet meanwhile: * it's not supposed to do this usually, but might be hard * to prevent. Discard data we got (if any) and keep going. */ if (unlikely(err != sock_len)) { pr_debug("Discarded rx packet: " " len %d, expected %zd\n", err, sock_len); vhost_discard_vq_desc(vq, headcount); continue; } /* Supply virtio_net_hdr if VHOST_NET_F_VIRTIO_NET_HDR */ if (unlikely(vhost_hlen)) { if (copy_to_iter(&hdr, sizeof(hdr), &fixup) != sizeof(hdr)) { vq_err(vq, "Unable to write vnet_hdr " "at addr %p\n", vq->iov->iov_base); goto out; } } else { /* Header came from socket; we'll need to patch * ->num_buffers over if VIRTIO_NET_F_MRG_RXBUF */ iov_iter_advance(&fixup, sizeof(hdr)); } /* TODO: Should check and handle checksum. */ num_buffers = cpu_to_vhost16(vq, headcount); if (likely(mergeable) && copy_to_iter(&num_buffers, sizeof num_buffers, &fixup) != sizeof num_buffers) { vq_err(vq, "Failed num_buffers write"); vhost_discard_vq_desc(vq, headcount); goto out; } nvq->done_idx += headcount; if (nvq->done_idx > VHOST_NET_BATCH) vhost_net_signal_used(nvq); if (unlikely(vq_log)) vhost_log_write(vq, vq_log, log, vhost_len, vq->iov, in); total_len += vhost_len; } while (likely(!vhost_exceeds_weight(vq, ++recv_pkts, total_len))); if (unlikely(busyloop_intr)) vhost_poll_queue(&vq->poll); else if (!sock_len) vhost_net_enable_vq(net, vq); out: vhost_net_signal_used(nvq); mutex_unlock(&vq->mutex); } static void handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); handle_tx(net); } static void handle_rx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); handle_rx(net); } static void handle_tx_net(struct vhost_work *work) { struct vhost_net *net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_TX].work); handle_tx(net); } static void handle_rx_net(struct vhost_work *work) { struct vhost_net *net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_RX].work); handle_rx(net); } static int vhost_net_open(struct inode *inode, struct file *f) { struct vhost_net *n; struct vhost_dev *dev; struct vhost_virtqueue **vqs; void **queue; struct xdp_buff *xdp; int i; n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!n) return -ENOMEM; vqs = kmalloc_array(VHOST_NET_VQ_MAX, sizeof(*vqs), GFP_KERNEL); if (!vqs) { kvfree(n); return -ENOMEM; } queue = kmalloc_array(VHOST_NET_BATCH, sizeof(void *), GFP_KERNEL); if (!queue) { kfree(vqs); kvfree(n); return -ENOMEM; } n->vqs[VHOST_NET_VQ_RX].rxq.queue = queue; xdp = kmalloc_array(VHOST_NET_BATCH, sizeof(*xdp), GFP_KERNEL); if (!xdp) { kfree(vqs); kvfree(n); kfree(queue); return -ENOMEM; } n->vqs[VHOST_NET_VQ_TX].xdp = xdp; dev = &n->dev; vqs[VHOST_NET_VQ_TX] = &n->vqs[VHOST_NET_VQ_TX].vq; vqs[VHOST_NET_VQ_RX] = &n->vqs[VHOST_NET_VQ_RX].vq; n->vqs[VHOST_NET_VQ_TX].vq.handle_kick = handle_tx_kick; n->vqs[VHOST_NET_VQ_RX].vq.handle_kick = handle_rx_kick; for (i = 0; i < VHOST_NET_VQ_MAX; i++) { n->vqs[i].ubufs = NULL; n->vqs[i].ubuf_info = NULL; n->vqs[i].upend_idx = 0; n->vqs[i].done_idx = 0; n->vqs[i].batched_xdp = 0; n->vqs[i].vhost_hlen = 0; n->vqs[i].sock_hlen = 0; n->vqs[i].rx_ring = NULL; vhost_net_buf_init(&n->vqs[i].rxq); } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX, UIO_MAXIOV + VHOST_NET_BATCH, VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT, true, NULL); vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev, vqs[VHOST_NET_VQ_TX]); vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev, vqs[VHOST_NET_VQ_RX]); f->private_data = n; n->page_frag.page = NULL; n->refcnt_bias = 0; return 0; } static struct socket *vhost_net_stop_vq(struct vhost_net *n, struct vhost_virtqueue *vq) { struct socket *sock; struct vhost_net_virtqueue *nvq = container_of(vq, struct vhost_net_virtqueue, vq); mutex_lock(&vq->mutex); sock = vhost_vq_get_backend(vq); vhost_net_disable_vq(n, vq); vhost_vq_set_backend(vq, NULL); vhost_net_buf_unproduce(nvq); nvq->rx_ring = NULL; mutex_unlock(&vq->mutex); return sock; } static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock, struct socket **rx_sock) { *tx_sock = vhost_net_stop_vq(n, &n->vqs[VHOST_NET_VQ_TX].vq); *rx_sock = vhost_net_stop_vq(n, &n->vqs[VHOST_NET_VQ_RX].vq); } static void vhost_net_flush(struct vhost_net *n) { vhost_dev_flush(&n->dev); if (n->vqs[VHOST_NET_VQ_TX].ubufs) { mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); n->tx_flush = true; mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); /* Wait for all lower device DMAs done. */ vhost_net_ubuf_put_and_wait(n->vqs[VHOST_NET_VQ_TX].ubufs); mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); n->tx_flush = false; atomic_set(&n->vqs[VHOST_NET_VQ_TX].ubufs->refcount, 1); mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); } } static int vhost_net_release(struct inode *inode, struct file *f) { struct vhost_net *n = f->private_data; struct socket *tx_sock; struct socket *rx_sock; vhost_net_stop(n, &tx_sock, &rx_sock); vhost_net_flush(n); vhost_dev_stop(&n->dev); vhost_dev_cleanup(&n->dev); vhost_net_vq_reset(n); if (tx_sock) sockfd_put(tx_sock); if (rx_sock) sockfd_put(rx_sock); /* Make sure no callbacks are outstanding */ synchronize_rcu(); /* We do an extra flush before freeing memory, * since jobs can re-queue themselves. */ vhost_net_flush(n); kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue); kfree(n->vqs[VHOST_NET_VQ_TX].xdp); kfree(n->dev.vqs); if (n->page_frag.page) __page_frag_cache_drain(n->page_frag.page, n->refcnt_bias); kvfree(n); return 0; } static struct socket *get_raw_socket(int fd) { int r; struct socket *sock = sockfd_lookup(fd, &r); if (!sock) return ERR_PTR(-ENOTSOCK); /* Parameter checking */ if (sock->sk->sk_type != SOCK_RAW) { r = -ESOCKTNOSUPPORT; goto err; } if (sock->sk->sk_family != AF_PACKET) { r = -EPFNOSUPPORT; goto err; } return sock; err: sockfd_put(sock); return ERR_PTR(r); } static struct ptr_ring *get_tap_ptr_ring(struct file *file) { struct ptr_ring *ring; ring = tun_get_tx_ring(file); if (!IS_ERR(ring)) goto out; ring = tap_get_ptr_ring(file); if (!IS_ERR(ring)) goto out; ring = NULL; out: return ring; } static struct socket *get_tap_socket(int fd) { struct file *file = fget(fd); struct socket *sock; if (!file) return ERR_PTR(-EBADF); sock = tun_get_socket(file); if (!IS_ERR(sock)) return sock; sock = tap_get_socket(file); if (IS_ERR(sock)) fput(file); return sock; } static struct socket *get_socket(int fd) { struct socket *sock; /* special case to disable backend */ if (fd == -1) return NULL; sock = get_raw_socket(fd); if (!IS_ERR(sock)) return sock; sock = get_tap_socket(fd); if (!IS_ERR(sock)) return sock; return ERR_PTR(-ENOTSOCK); } static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) { struct socket *sock, *oldsock; struct vhost_virtqueue *vq; struct vhost_net_virtqueue *nvq; struct vhost_net_ubuf_ref *ubufs, *oldubufs = NULL; int r; mutex_lock(&n->dev.mutex); r = vhost_dev_check_owner(&n->dev); if (r) goto err; if (index >= VHOST_NET_VQ_MAX) { r = -ENOBUFS; goto err; } vq = &n->vqs[index].vq; nvq = &n->vqs[index]; mutex_lock(&vq->mutex); if (fd == -1) vhost_clear_msg(&n->dev); /* Verify that ring has been setup correctly. */ if (!vhost_vq_access_ok(vq)) { r = -EFAULT; goto err_vq; } sock = get_socket(fd); if (IS_ERR(sock)) { r = PTR_ERR(sock); goto err_vq; } /* start polling new socket */ oldsock = vhost_vq_get_backend(vq); if (sock != oldsock) { ubufs = vhost_net_ubuf_alloc(vq, sock && vhost_sock_zcopy(sock)); if (IS_ERR(ubufs)) { r = PTR_ERR(ubufs); goto err_ubufs; } vhost_net_disable_vq(n, vq); vhost_vq_set_backend(vq, sock); vhost_net_buf_unproduce(nvq); r = vhost_vq_init_access(vq); if (r) goto err_used; r = vhost_net_enable_vq(n, vq); if (r) goto err_used; if (index == VHOST_NET_VQ_RX) { if (sock) nvq->rx_ring = get_tap_ptr_ring(sock->file); else nvq->rx_ring = NULL; } oldubufs = nvq->ubufs; nvq->ubufs = ubufs; n->tx_packets = 0; n->tx_zcopy_err = 0; n->tx_flush = false; } mutex_unlock(&vq->mutex); if (oldubufs) { vhost_net_ubuf_put_wait_and_free(oldubufs); mutex_lock(&vq->mutex); vhost_zerocopy_signal_used(n, vq); mutex_unlock(&vq->mutex); } if (oldsock) { vhost_dev_flush(&n->dev); sockfd_put(oldsock); } mutex_unlock(&n->dev.mutex); return 0; err_used: vhost_vq_set_backend(vq, oldsock); vhost_net_enable_vq(n, vq); if (ubufs) vhost_net_ubuf_put_wait_and_free(ubufs); err_ubufs: if (sock) sockfd_put(sock); err_vq: mutex_unlock(&vq->mutex); err: mutex_unlock(&n->dev.mutex); return r; } static long vhost_net_reset_owner(struct vhost_net *n) { struct socket *tx_sock = NULL; struct socket *rx_sock = NULL; long err; struct vhost_iotlb *umem; mutex_lock(&n->dev.mutex); err = vhost_dev_check_owner(&n->dev); if (err) goto done; umem = vhost_dev_reset_owner_prepare(); if (!umem) { err = -ENOMEM; goto done; } vhost_net_stop(n, &tx_sock, &rx_sock); vhost_net_flush(n); vhost_dev_stop(&n->dev); vhost_dev_reset_owner(&n->dev, umem); vhost_net_vq_reset(n); done: mutex_unlock(&n->dev.mutex); if (tx_sock) sockfd_put(tx_sock); if (rx_sock) sockfd_put(rx_sock); return err; } static int vhost_net_set_features(struct vhost_net *n, u64 features) { size_t vhost_hlen, sock_hlen, hdr_len; int i; hdr_len = (features & ((1ULL << VIRTIO_NET_F_MRG_RXBUF) | (1ULL << VIRTIO_F_VERSION_1))) ? sizeof(struct virtio_net_hdr_mrg_rxbuf) : sizeof(struct virtio_net_hdr); if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) { /* vhost provides vnet_hdr */ vhost_hlen = hdr_len; sock_hlen = 0; } else { /* socket provides vnet_hdr */ vhost_hlen = 0; sock_hlen = hdr_len; } mutex_lock(&n->dev.mutex); if ((features & (1 << VHOST_F_LOG_ALL)) && !vhost_log_access_ok(&n->dev)) goto out_unlock; if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) { if (vhost_init_device_iotlb(&n->dev)) goto out_unlock; } for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { mutex_lock(&n->vqs[i].vq.mutex); n->vqs[i].vq.acked_features = features; n->vqs[i].vhost_hlen = vhost_hlen; n->vqs[i].sock_hlen = sock_hlen; mutex_unlock(&n->vqs[i].vq.mutex); } mutex_unlock(&n->dev.mutex); return 0; out_unlock: mutex_unlock(&n->dev.mutex); return -EFAULT; } static long vhost_net_set_owner(struct vhost_net *n) { int r; mutex_lock(&n->dev.mutex); if (vhost_dev_has_owner(&n->dev)) { r = -EBUSY; goto out; } r = vhost_net_set_ubuf_info(n); if (r) goto out; r = vhost_dev_set_owner(&n->dev); if (r) vhost_net_clear_ubuf_info(n); vhost_net_flush(n); out: mutex_unlock(&n->dev.mutex); return r; } static long vhost_net_ioctl(struct file *f, unsigned int ioctl, unsigned long arg) { struct vhost_net *n = f->private_data; void __user *argp = (void __user *)arg; u64 __user *featurep = argp; struct vhost_vring_file backend; u64 features; int r; switch (ioctl) { case VHOST_NET_SET_BACKEND: if (copy_from_user(&backend, argp, sizeof backend)) return -EFAULT; return vhost_net_set_backend(n, backend.index, backend.fd); case VHOST_GET_FEATURES: features = VHOST_NET_FEATURES; if (copy_to_user(featurep, &features, sizeof features)) return -EFAULT; return 0; case VHOST_SET_FEATURES: if (copy_from_user(&features, featurep, sizeof features)) return -EFAULT; if (features & ~VHOST_NET_FEATURES) return -EOPNOTSUPP; return vhost_net_set_features(n, features); case VHOST_GET_BACKEND_FEATURES: features = VHOST_NET_BACKEND_FEATURES; if (copy_to_user(featurep, &features, sizeof(features))) return -EFAULT; return 0; case VHOST_SET_BACKEND_FEATURES: if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; if (features & ~VHOST_NET_BACKEND_FEATURES) return -EOPNOTSUPP; vhost_set_backend_features(&n->dev, features); return 0; case VHOST_RESET_OWNER: return vhost_net_reset_owner(n); case VHOST_SET_OWNER: return vhost_net_set_owner(n); default: mutex_lock(&n->dev.mutex); r = vhost_dev_ioctl(&n->dev, ioctl, argp); if (r == -ENOIOCTLCMD) r = vhost_vring_ioctl(&n->dev, ioctl, argp); else vhost_net_flush(n); mutex_unlock(&n->dev.mutex); return r; } } static ssize_t vhost_net_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct vhost_net *n = file->private_data; struct vhost_dev *dev = &n->dev; int noblock = file->f_flags & O_NONBLOCK; return vhost_chr_read_iter(dev, to, noblock); } static ssize_t vhost_net_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct vhost_net *n = file->private_data; struct vhost_dev *dev = &n->dev; return vhost_chr_write_iter(dev, from); } static __poll_t vhost_net_chr_poll(struct file *file, poll_table *wait) { struct vhost_net *n = file->private_data; struct vhost_dev *dev = &n->dev; return vhost_chr_poll(file, dev, wait); } static const struct file_operations vhost_net_fops = { .owner = THIS_MODULE, .release = vhost_net_release, .read_iter = vhost_net_chr_read_iter, .write_iter = vhost_net_chr_write_iter, .poll = vhost_net_chr_poll, .unlocked_ioctl = vhost_net_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = vhost_net_open, .llseek = noop_llseek, }; static struct miscdevice vhost_net_misc = { .minor = VHOST_NET_MINOR, .name = "vhost-net", .fops = &vhost_net_fops, }; static int __init vhost_net_init(void) { if (experimental_zcopytx) vhost_net_enable_zcopy(VHOST_NET_VQ_TX); return misc_register(&vhost_net_misc); } module_init(vhost_net_init); static void __exit vhost_net_exit(void) { misc_deregister(&vhost_net_misc); } module_exit(vhost_net_exit); MODULE_VERSION("0.0.1"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Michael S. Tsirkin"); MODULE_DESCRIPTION("Host kernel accelerator for virtio net"); MODULE_ALIAS_MISCDEV(VHOST_NET_MINOR); MODULE_ALIAS("devname:vhost-net"); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/em_ipt.c IPtables matches Ematch * * (c) 2018 Eyal Birger <eyal.birger@gmail.com> */ #include <linux/gfp.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/tc_ematch/tc_em_ipt.h> #include <linux/netfilter.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/pkt_cls.h> struct em_ipt_match { const struct xt_match *match; u32 hook; u8 nfproto; u8 match_data[] __aligned(8); }; struct em_ipt_xt_match { char *match_name; int (*validate_match_data)(struct nlattr **tb, u8 mrev); }; static const struct nla_policy em_ipt_policy[TCA_EM_IPT_MAX + 1] = { [TCA_EM_IPT_MATCH_NAME] = { .type = NLA_STRING, .len = XT_EXTENSION_MAXNAMELEN }, [TCA_EM_IPT_MATCH_REVISION] = { .type = NLA_U8 }, [TCA_EM_IPT_HOOK] = { .type = NLA_U32 }, [TCA_EM_IPT_NFPROTO] = { .type = NLA_U8 }, [TCA_EM_IPT_MATCH_DATA] = { .type = NLA_UNSPEC }, }; static int check_match(struct net *net, struct em_ipt_match *im, int mdata_len) { struct xt_mtchk_param mtpar = {}; union { struct ipt_entry e4; struct ip6t_entry e6; } e = {}; mtpar.net = net; mtpar.table = "filter"; mtpar.hook_mask = 1 << im->hook; mtpar.family = im->match->family; mtpar.match = im->match; mtpar.entryinfo = &e; mtpar.matchinfo = (void *)im->match_data; return xt_check_match(&mtpar, mdata_len, 0, 0); } static int policy_validate_match_data(struct nlattr **tb, u8 mrev) { if (mrev != 0) { pr_err("only policy match revision 0 supported"); return -EINVAL; } if (nla_get_u32(tb[TCA_EM_IPT_HOOK]) != NF_INET_PRE_ROUTING) { pr_err("policy can only be matched on NF_INET_PRE_ROUTING"); return -EINVAL; } return 0; } static int addrtype_validate_match_data(struct nlattr **tb, u8 mrev) { if (mrev != 1) { pr_err("only addrtype match revision 1 supported"); return -EINVAL; } return 0; } static const struct em_ipt_xt_match em_ipt_xt_matches[] = { { .match_name = "policy", .validate_match_data = policy_validate_match_data }, { .match_name = "addrtype", .validate_match_data = addrtype_validate_match_data }, {} }; static struct xt_match *get_xt_match(struct nlattr **tb) { const struct em_ipt_xt_match *m; struct nlattr *mname_attr; u8 nfproto, mrev = 0; int ret; mname_attr = tb[TCA_EM_IPT_MATCH_NAME]; for (m = em_ipt_xt_matches; m->match_name; m++) { if (!nla_strcmp(mname_attr, m->match_name)) break; } if (!m->match_name) { pr_err("Unsupported xt match"); return ERR_PTR(-EINVAL); } if (tb[TCA_EM_IPT_MATCH_REVISION]) mrev = nla_get_u8(tb[TCA_EM_IPT_MATCH_REVISION]); ret = m->validate_match_data(tb, mrev); if (ret < 0) return ERR_PTR(ret); nfproto = nla_get_u8(tb[TCA_EM_IPT_NFPROTO]); return xt_request_find_match(nfproto, m->match_name, mrev); } static int em_ipt_change(struct net *net, void *data, int data_len, struct tcf_ematch *em) { struct nlattr *tb[TCA_EM_IPT_MAX + 1]; struct em_ipt_match *im = NULL; struct xt_match *match; int mdata_len, ret; u8 nfproto; ret = nla_parse_deprecated(tb, TCA_EM_IPT_MAX, data, data_len, em_ipt_policy, NULL); if (ret < 0) return ret; if (!tb[TCA_EM_IPT_HOOK] || !tb[TCA_EM_IPT_MATCH_NAME] || !tb[TCA_EM_IPT_MATCH_DATA] || !tb[TCA_EM_IPT_NFPROTO]) return -EINVAL; nfproto = nla_get_u8(tb[TCA_EM_IPT_NFPROTO]); switch (nfproto) { case NFPROTO_IPV4: case NFPROTO_IPV6: break; default: return -EINVAL; } match = get_xt_match(tb); if (IS_ERR(match)) { pr_err("unable to load match\n"); return PTR_ERR(match); } mdata_len = XT_ALIGN(nla_len(tb[TCA_EM_IPT_MATCH_DATA])); im = kzalloc(sizeof(*im) + mdata_len, GFP_KERNEL); if (!im) { ret = -ENOMEM; goto err; } im->match = match; im->hook = nla_get_u32(tb[TCA_EM_IPT_HOOK]); im->nfproto = nfproto; nla_memcpy(im->match_data, tb[TCA_EM_IPT_MATCH_DATA], mdata_len); ret = check_match(net, im, mdata_len); if (ret) goto err; em->datalen = sizeof(*im) + mdata_len; em->data = (unsigned long)im; return 0; err: kfree(im); module_put(match->me); return ret; } static void em_ipt_destroy(struct tcf_ematch *em) { struct em_ipt_match *im = (void *)em->data; if (!im) return; if (im->match->destroy) { struct xt_mtdtor_param par = { .net = em->net, .match = im->match, .matchinfo = im->match_data, .family = im->match->family }; im->match->destroy(&par); } module_put(im->match->me); kfree(im); } static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em, struct tcf_pkt_info *info) { const struct em_ipt_match *im = (const void *)em->data; struct xt_action_param acpar = {}; struct net_device *indev = NULL; u8 nfproto = im->match->family; struct nf_hook_state state; int ret; switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) return 0; if (nfproto == NFPROTO_UNSPEC) nfproto = NFPROTO_IPV4; break; case htons(ETH_P_IPV6): if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) return 0; if (nfproto == NFPROTO_UNSPEC) nfproto = NFPROTO_IPV6; break; default: return 0; } rcu_read_lock(); if (skb->skb_iif) indev = dev_get_by_index_rcu(em->net, skb->skb_iif); nf_hook_state_init(&state, im->hook, nfproto, indev ?: skb->dev, skb->dev, NULL, em->net, NULL); acpar.match = im->match; acpar.matchinfo = im->match_data; acpar.state = &state; ret = im->match->match(skb, &acpar); rcu_read_unlock(); return ret; } static int em_ipt_dump(struct sk_buff *skb, struct tcf_ematch *em) { struct em_ipt_match *im = (void *)em->data; if (nla_put_string(skb, TCA_EM_IPT_MATCH_NAME, im->match->name) < 0) return -EMSGSIZE; if (nla_put_u32(skb, TCA_EM_IPT_HOOK, im->hook) < 0) return -EMSGSIZE; if (nla_put_u8(skb, TCA_EM_IPT_MATCH_REVISION, im->match->revision) < 0) return -EMSGSIZE; if (nla_put_u8(skb, TCA_EM_IPT_NFPROTO, im->nfproto) < 0) return -EMSGSIZE; if (nla_put(skb, TCA_EM_IPT_MATCH_DATA, im->match->usersize ?: im->match->matchsize, im->match_data) < 0) return -EMSGSIZE; return 0; } static struct tcf_ematch_ops em_ipt_ops = { .kind = TCF_EM_IPT, .change = em_ipt_change, .destroy = em_ipt_destroy, .match = em_ipt_match, .dump = em_ipt_dump, .owner = THIS_MODULE, .link = LIST_HEAD_INIT(em_ipt_ops.link) }; static int __init init_em_ipt(void) { return tcf_em_register(&em_ipt_ops); } static void __exit exit_em_ipt(void) { tcf_em_unregister(&em_ipt_ops); } MODULE_LICENSE("GPL"); MODULE_AUTHOR("Eyal Birger <eyal.birger@gmail.com>"); MODULE_DESCRIPTION("TC extended match for IPtables matches"); module_init(init_em_ipt); module_exit(exit_em_ipt); MODULE_ALIAS_TCF_EMATCH(TCF_EM_IPT); |
| 20 62 61 65 17 64 15 14 20 20 5 20 5 14 14 12 5 12 12 14 7 14 7 7 5 5 3 5 7 5 7 7 14 14 7 14 13 13 57 1 57 57 1 1 1 56 1 54 56 50 11 57 57 50 57 14 6 14 14 14 14 14 14 12 12 12 7 7 7 7 7 7 7 7 7 7 7 7 7 7 6 7 9 14 14 14 6 9 65 65 65 65 64 7 7 7 7 7 7 7 7 7 56 56 56 56 56 56 56 56 56 56 56 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 48 1 48 47 1 48 16 16 16 15 14 16 16 16 16 16 16 16 13 57 57 57 57 57 3 56 55 7 53 5 52 50 54 54 53 52 2 2 56 56 56 56 56 57 11 50 57 57 50 1 50 50 50 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 56 56 2 56 7 7 2 7 7 3 7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * * This code builds two trees of free clusters extents. * Trees are sorted by start of extent and by length of extent. * NTFS_MAX_WND_EXTENTS defines the maximum number of elements in trees. * In extreme case code reads on-disk bitmap to find free clusters. * */ #include <linux/buffer_head.h> #include <linux/fs.h> #include <linux/kernel.h> #include "ntfs.h" #include "ntfs_fs.h" /* * Maximum number of extents in tree. */ #define NTFS_MAX_WND_EXTENTS (32u * 1024u) struct rb_node_key { struct rb_node node; size_t key; }; struct e_node { struct rb_node_key start; /* Tree sorted by start. */ struct rb_node_key count; /* Tree sorted by len. */ }; static int wnd_rescan(struct wnd_bitmap *wnd); static struct buffer_head *wnd_map(struct wnd_bitmap *wnd, size_t iw); static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits); static struct kmem_cache *ntfs_enode_cachep; int __init ntfs3_init_bitmap(void) { ntfs_enode_cachep = kmem_cache_create("ntfs3_enode_cache", sizeof(struct e_node), 0, SLAB_RECLAIM_ACCOUNT, NULL); return ntfs_enode_cachep ? 0 : -ENOMEM; } void ntfs3_exit_bitmap(void) { kmem_cache_destroy(ntfs_enode_cachep); } /* * wnd_scan * * b_pos + b_len - biggest fragment. * Scan range [wpos wbits) window @buf. * * Return: -1 if not found. */ static size_t wnd_scan(const void *buf, size_t wbit, u32 wpos, u32 wend, size_t to_alloc, size_t *prev_tail, size_t *b_pos, size_t *b_len) { while (wpos < wend) { size_t free_len; u32 free_bits, end; u32 used = find_next_zero_bit_le(buf, wend, wpos); if (used >= wend) { if (*b_len < *prev_tail) { *b_pos = wbit - *prev_tail; *b_len = *prev_tail; } *prev_tail = 0; return -1; } if (used > wpos) { wpos = used; if (*b_len < *prev_tail) { *b_pos = wbit - *prev_tail; *b_len = *prev_tail; } *prev_tail = 0; } /* * Now we have a fragment [wpos, wend) staring with 0. */ end = wpos + to_alloc - *prev_tail; free_bits = find_next_bit_le(buf, min(end, wend), wpos); free_len = *prev_tail + free_bits - wpos; if (*b_len < free_len) { *b_pos = wbit + wpos - *prev_tail; *b_len = free_len; } if (free_len >= to_alloc) return wbit + wpos - *prev_tail; if (free_bits >= wend) { *prev_tail += free_bits - wpos; return -1; } wpos = free_bits + 1; *prev_tail = 0; } return -1; } /* * wnd_close - Frees all resources. */ void wnd_close(struct wnd_bitmap *wnd) { struct rb_node *node, *next; kfree(wnd->free_bits); wnd->free_bits = NULL; run_close(&wnd->run); node = rb_first(&wnd->start_tree); while (node) { next = rb_next(node); rb_erase(node, &wnd->start_tree); kmem_cache_free(ntfs_enode_cachep, rb_entry(node, struct e_node, start.node)); node = next; } } static struct rb_node *rb_lookup(struct rb_root *root, size_t v) { struct rb_node **p = &root->rb_node; struct rb_node *r = NULL; while (*p) { struct rb_node_key *k; k = rb_entry(*p, struct rb_node_key, node); if (v < k->key) { p = &(*p)->rb_left; } else if (v > k->key) { r = &k->node; p = &(*p)->rb_right; } else { return &k->node; } } return r; } /* * rb_insert_count - Helper function to insert special kind of 'count' tree. */ static inline bool rb_insert_count(struct rb_root *root, struct e_node *e) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; size_t e_ckey = e->count.key; size_t e_skey = e->start.key; while (*p) { struct e_node *k = rb_entry(parent = *p, struct e_node, count.node); if (e_ckey > k->count.key) { p = &(*p)->rb_left; } else if (e_ckey < k->count.key) { p = &(*p)->rb_right; } else if (e_skey < k->start.key) { p = &(*p)->rb_left; } else if (e_skey > k->start.key) { p = &(*p)->rb_right; } else { WARN_ON(1); return false; } } rb_link_node(&e->count.node, parent, p); rb_insert_color(&e->count.node, root); return true; } /* * rb_insert_start - Helper function to insert special kind of 'count' tree. */ static inline bool rb_insert_start(struct rb_root *root, struct e_node *e) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; size_t e_skey = e->start.key; while (*p) { struct e_node *k; parent = *p; k = rb_entry(parent, struct e_node, start.node); if (e_skey < k->start.key) { p = &(*p)->rb_left; } else if (e_skey > k->start.key) { p = &(*p)->rb_right; } else { WARN_ON(1); return false; } } rb_link_node(&e->start.node, parent, p); rb_insert_color(&e->start.node, root); return true; } /* * wnd_add_free_ext - Adds a new extent of free space. * @build: 1 when building tree. */ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len, bool build) { struct e_node *e, *e0 = NULL; size_t ib, end_in = bit + len; struct rb_node *n; if (build) { /* Use extent_min to filter too short extents. */ if (wnd->count >= NTFS_MAX_WND_EXTENTS && len <= wnd->extent_min) { wnd->uptodated = -1; return; } } else { /* Try to find extent before 'bit'. */ n = rb_lookup(&wnd->start_tree, bit); if (!n) { n = rb_first(&wnd->start_tree); } else { e = rb_entry(n, struct e_node, start.node); n = rb_next(n); if (e->start.key + e->count.key == bit) { /* Remove left. */ bit = e->start.key; len += e->count.key; rb_erase(&e->start.node, &wnd->start_tree); rb_erase(&e->count.node, &wnd->count_tree); wnd->count -= 1; e0 = e; } } while (n) { size_t next_end; e = rb_entry(n, struct e_node, start.node); next_end = e->start.key + e->count.key; if (e->start.key > end_in) break; /* Remove right. */ n = rb_next(n); len += next_end - end_in; end_in = next_end; rb_erase(&e->start.node, &wnd->start_tree); rb_erase(&e->count.node, &wnd->count_tree); wnd->count -= 1; if (!e0) e0 = e; else kmem_cache_free(ntfs_enode_cachep, e); } if (wnd->uptodated != 1) { /* Check bits before 'bit'. */ ib = wnd->zone_bit == wnd->zone_end || bit < wnd->zone_end ? 0 : wnd->zone_end; while (bit > ib && wnd_is_free_hlp(wnd, bit - 1, 1)) { bit -= 1; len += 1; } /* Check bits after 'end_in'. */ ib = wnd->zone_bit == wnd->zone_end || end_in > wnd->zone_bit ? wnd->nbits : wnd->zone_bit; while (end_in < ib && wnd_is_free_hlp(wnd, end_in, 1)) { end_in += 1; len += 1; } } } /* Insert new fragment. */ if (wnd->count >= NTFS_MAX_WND_EXTENTS) { if (e0) kmem_cache_free(ntfs_enode_cachep, e0); wnd->uptodated = -1; /* Compare with smallest fragment. */ n = rb_last(&wnd->count_tree); e = rb_entry(n, struct e_node, count.node); if (len <= e->count.key) goto out; /* Do not insert small fragments. */ if (build) { struct e_node *e2; n = rb_prev(n); e2 = rb_entry(n, struct e_node, count.node); /* Smallest fragment will be 'e2->count.key'. */ wnd->extent_min = e2->count.key; } /* Replace smallest fragment by new one. */ rb_erase(&e->start.node, &wnd->start_tree); rb_erase(&e->count.node, &wnd->count_tree); wnd->count -= 1; } else { e = e0 ? e0 : kmem_cache_alloc(ntfs_enode_cachep, GFP_ATOMIC); if (!e) { wnd->uptodated = -1; goto out; } if (build && len <= wnd->extent_min) wnd->extent_min = len; } e->start.key = bit; e->count.key = len; if (len > wnd->extent_max) wnd->extent_max = len; rb_insert_start(&wnd->start_tree, e); rb_insert_count(&wnd->count_tree, e); wnd->count += 1; out:; } /* * wnd_remove_free_ext - Remove a run from the cached free space. */ static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len) { struct rb_node *n, *n3; struct e_node *e, *e3; size_t end_in = bit + len; size_t end3, end, new_key, new_len, max_new_len; /* Try to find extent before 'bit'. */ n = rb_lookup(&wnd->start_tree, bit); if (!n) return; e = rb_entry(n, struct e_node, start.node); end = e->start.key + e->count.key; new_key = new_len = 0; len = e->count.key; /* Range [bit,end_in) must be inside 'e' or outside 'e' and 'n'. */ if (e->start.key > bit) ; else if (end_in <= end) { /* Range [bit,end_in) inside 'e'. */ new_key = end_in; new_len = end - end_in; len = bit - e->start.key; } else if (bit > end) { bool bmax = false; n3 = rb_next(n); while (n3) { e3 = rb_entry(n3, struct e_node, start.node); if (e3->start.key >= end_in) break; if (e3->count.key == wnd->extent_max) bmax = true; end3 = e3->start.key + e3->count.key; if (end3 > end_in) { e3->start.key = end_in; rb_erase(&e3->count.node, &wnd->count_tree); e3->count.key = end3 - end_in; rb_insert_count(&wnd->count_tree, e3); break; } n3 = rb_next(n3); rb_erase(&e3->start.node, &wnd->start_tree); rb_erase(&e3->count.node, &wnd->count_tree); wnd->count -= 1; kmem_cache_free(ntfs_enode_cachep, e3); } if (!bmax) return; n3 = rb_first(&wnd->count_tree); wnd->extent_max = n3 ? rb_entry(n3, struct e_node, count.node)->count.key : 0; return; } if (e->count.key != wnd->extent_max) { ; } else if (rb_prev(&e->count.node)) { ; } else { n3 = rb_next(&e->count.node); max_new_len = max(len, new_len); if (!n3) { wnd->extent_max = max_new_len; } else { e3 = rb_entry(n3, struct e_node, count.node); wnd->extent_max = max(e3->count.key, max_new_len); } } if (!len) { if (new_len) { e->start.key = new_key; rb_erase(&e->count.node, &wnd->count_tree); e->count.key = new_len; rb_insert_count(&wnd->count_tree, e); } else { rb_erase(&e->start.node, &wnd->start_tree); rb_erase(&e->count.node, &wnd->count_tree); wnd->count -= 1; kmem_cache_free(ntfs_enode_cachep, e); } goto out; } rb_erase(&e->count.node, &wnd->count_tree); e->count.key = len; rb_insert_count(&wnd->count_tree, e); if (!new_len) goto out; if (wnd->count >= NTFS_MAX_WND_EXTENTS) { wnd->uptodated = -1; /* Get minimal extent. */ e = rb_entry(rb_last(&wnd->count_tree), struct e_node, count.node); if (e->count.key > new_len) goto out; /* Replace minimum. */ rb_erase(&e->start.node, &wnd->start_tree); rb_erase(&e->count.node, &wnd->count_tree); wnd->count -= 1; } else { e = kmem_cache_alloc(ntfs_enode_cachep, GFP_ATOMIC); if (!e) wnd->uptodated = -1; } if (e) { e->start.key = new_key; e->count.key = new_len; rb_insert_start(&wnd->start_tree, e); rb_insert_count(&wnd->count_tree, e); wnd->count += 1; } out: if (!wnd->count && 1 != wnd->uptodated) wnd_rescan(wnd); } /* * wnd_rescan - Scan all bitmap. Used while initialization. */ static int wnd_rescan(struct wnd_bitmap *wnd) { int err = 0; size_t prev_tail = 0; struct super_block *sb = wnd->sb; struct ntfs_sb_info *sbi = sb->s_fs_info; u64 lbo, len = 0; u32 blocksize = sb->s_blocksize; u8 cluster_bits = sbi->cluster_bits; u32 wbits = 8 * sb->s_blocksize; u32 used, frb; size_t wpos, wbit, iw, vbo; struct buffer_head *bh = NULL; CLST lcn, clen; wnd->uptodated = 0; wnd->extent_max = 0; wnd->extent_min = MINUS_ONE_T; wnd->total_zeroes = 0; vbo = 0; for (iw = 0; iw < wnd->nwnd; iw++) { if (iw + 1 == wnd->nwnd) wbits = wnd->bits_last; if (wnd->inited) { if (!wnd->free_bits[iw]) { /* All ones. */ if (prev_tail) { wnd_add_free_ext(wnd, vbo * 8 - prev_tail, prev_tail, true); prev_tail = 0; } goto next_wnd; } if (wbits == wnd->free_bits[iw]) { /* All zeroes. */ prev_tail += wbits; wnd->total_zeroes += wbits; goto next_wnd; } } if (!len) { u32 off = vbo & sbi->cluster_mask; if (!run_lookup_entry(&wnd->run, vbo >> cluster_bits, &lcn, &clen, NULL)) { err = -ENOENT; goto out; } lbo = ((u64)lcn << cluster_bits) + off; len = ((u64)clen << cluster_bits) - off; } bh = ntfs_bread(sb, lbo >> sb->s_blocksize_bits); if (!bh) { err = -EIO; goto out; } used = ntfs_bitmap_weight_le(bh->b_data, wbits); if (used < wbits) { frb = wbits - used; wnd->free_bits[iw] = frb; wnd->total_zeroes += frb; } wpos = 0; wbit = vbo * 8; if (wbit + wbits > wnd->nbits) wbits = wnd->nbits - wbit; do { used = find_next_zero_bit_le(bh->b_data, wbits, wpos); if (used > wpos && prev_tail) { wnd_add_free_ext(wnd, wbit + wpos - prev_tail, prev_tail, true); prev_tail = 0; } wpos = used; if (wpos >= wbits) { /* No free blocks. */ prev_tail = 0; break; } frb = find_next_bit_le(bh->b_data, wbits, wpos); if (frb >= wbits) { /* Keep last free block. */ prev_tail += frb - wpos; break; } wnd_add_free_ext(wnd, wbit + wpos - prev_tail, frb + prev_tail - wpos, true); /* Skip free block and first '1'. */ wpos = frb + 1; /* Reset previous tail. */ prev_tail = 0; } while (wpos < wbits); next_wnd: if (bh) put_bh(bh); bh = NULL; vbo += blocksize; if (len) { len -= blocksize; lbo += blocksize; } } /* Add last block. */ if (prev_tail) wnd_add_free_ext(wnd, wnd->nbits - prev_tail, prev_tail, true); /* * Before init cycle wnd->uptodated was 0. * If any errors or limits occurs while initialization then * wnd->uptodated will be -1. * If 'uptodated' is still 0 then Tree is really updated. */ if (!wnd->uptodated) wnd->uptodated = 1; if (wnd->zone_bit != wnd->zone_end) { size_t zlen = wnd->zone_end - wnd->zone_bit; wnd->zone_end = wnd->zone_bit; wnd_zone_set(wnd, wnd->zone_bit, zlen); } out: return err; } int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits) { int err; u32 blocksize = sb->s_blocksize; u32 wbits = blocksize * 8; init_rwsem(&wnd->rw_lock); wnd->sb = sb; wnd->nbits = nbits; wnd->total_zeroes = nbits; wnd->extent_max = MINUS_ONE_T; wnd->zone_bit = wnd->zone_end = 0; wnd->nwnd = bytes_to_block(sb, bitmap_size(nbits)); wnd->bits_last = nbits & (wbits - 1); if (!wnd->bits_last) wnd->bits_last = wbits; wnd->free_bits = kvmalloc_array(wnd->nwnd, sizeof(u16), GFP_KERNEL | __GFP_ZERO); if (!wnd->free_bits) return -ENOMEM; err = wnd_rescan(wnd); if (err) return err; wnd->inited = true; return 0; } /* * wnd_map - Call sb_bread for requested window. */ static struct buffer_head *wnd_map(struct wnd_bitmap *wnd, size_t iw) { size_t vbo; CLST lcn, clen; struct super_block *sb = wnd->sb; struct ntfs_sb_info *sbi; struct buffer_head *bh; u64 lbo; sbi = sb->s_fs_info; vbo = (u64)iw << sb->s_blocksize_bits; if (!run_lookup_entry(&wnd->run, vbo >> sbi->cluster_bits, &lcn, &clen, NULL)) { return ERR_PTR(-ENOENT); } lbo = ((u64)lcn << sbi->cluster_bits) + (vbo & sbi->cluster_mask); bh = ntfs_bread(wnd->sb, lbo >> sb->s_blocksize_bits); if (!bh) return ERR_PTR(-EIO); return bh; } /* * wnd_set_free - Mark the bits range from bit to bit + bits as free. */ int wnd_set_free(struct wnd_bitmap *wnd, size_t bit, size_t bits) { int err = 0; struct super_block *sb = wnd->sb; size_t bits0 = bits; u32 wbits = 8 * sb->s_blocksize; size_t iw = bit >> (sb->s_blocksize_bits + 3); u32 wbit = bit & (wbits - 1); struct buffer_head *bh; while (iw < wnd->nwnd && bits) { u32 tail, op; if (iw + 1 == wnd->nwnd) wbits = wnd->bits_last; tail = wbits - wbit; op = min_t(u32, tail, bits); bh = wnd_map(wnd, iw); if (IS_ERR(bh)) { err = PTR_ERR(bh); break; } lock_buffer(bh); ntfs_bitmap_clear_le(bh->b_data, wbit, op); wnd->free_bits[iw] += op; set_buffer_uptodate(bh); mark_buffer_dirty(bh); unlock_buffer(bh); put_bh(bh); wnd->total_zeroes += op; bits -= op; wbit = 0; iw += 1; } wnd_add_free_ext(wnd, bit, bits0, false); return err; } /* * wnd_set_used - Mark the bits range from bit to bit + bits as used. */ int wnd_set_used(struct wnd_bitmap *wnd, size_t bit, size_t bits) { int err = 0; struct super_block *sb = wnd->sb; size_t bits0 = bits; size_t iw = bit >> (sb->s_blocksize_bits + 3); u32 wbits = 8 * sb->s_blocksize; u32 wbit = bit & (wbits - 1); struct buffer_head *bh; while (iw < wnd->nwnd && bits) { u32 tail, op; if (unlikely(iw + 1 == wnd->nwnd)) wbits = wnd->bits_last; tail = wbits - wbit; op = min_t(u32, tail, bits); bh = wnd_map(wnd, iw); if (IS_ERR(bh)) { err = PTR_ERR(bh); break; } lock_buffer(bh); ntfs_bitmap_set_le(bh->b_data, wbit, op); wnd->free_bits[iw] -= op; set_buffer_uptodate(bh); mark_buffer_dirty(bh); unlock_buffer(bh); put_bh(bh); wnd->total_zeroes -= op; bits -= op; wbit = 0; iw += 1; } if (!RB_EMPTY_ROOT(&wnd->start_tree)) wnd_remove_free_ext(wnd, bit, bits0); return err; } /* * wnd_set_used_safe - Mark the bits range from bit to bit + bits as used. * * Unlikely wnd_set_used/wnd_set_free this function is not full trusted. * It scans every bit in bitmap and marks free bit as used. * @done - how many bits were marked as used. * * NOTE: normally *done should be 0. */ int wnd_set_used_safe(struct wnd_bitmap *wnd, size_t bit, size_t bits, size_t *done) { size_t i, from = 0, len = 0; int err = 0; *done = 0; for (i = 0; i < bits; i++) { if (wnd_is_free(wnd, bit + i, 1)) { if (!len) from = bit + i; len += 1; } else if (len) { err = wnd_set_used(wnd, from, len); *done += len; len = 0; if (err) break; } } if (len) { /* last fragment. */ err = wnd_set_used(wnd, from, len); *done += len; } return err; } /* * wnd_is_free_hlp * * Return: True if all clusters [bit, bit+bits) are free (bitmap only). */ static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits) { struct super_block *sb = wnd->sb; size_t iw = bit >> (sb->s_blocksize_bits + 3); u32 wbits = 8 * sb->s_blocksize; u32 wbit = bit & (wbits - 1); while (iw < wnd->nwnd && bits) { u32 tail, op; if (unlikely(iw + 1 == wnd->nwnd)) wbits = wnd->bits_last; tail = wbits - wbit; op = min_t(u32, tail, bits); if (wbits != wnd->free_bits[iw]) { bool ret; struct buffer_head *bh = wnd_map(wnd, iw); if (IS_ERR(bh)) return false; ret = are_bits_clear(bh->b_data, wbit, op); put_bh(bh); if (!ret) return false; } bits -= op; wbit = 0; iw += 1; } return true; } /* * wnd_is_free * * Return: True if all clusters [bit, bit+bits) are free. */ bool wnd_is_free(struct wnd_bitmap *wnd, size_t bit, size_t bits) { bool ret; struct rb_node *n; size_t end; struct e_node *e; if (RB_EMPTY_ROOT(&wnd->start_tree)) goto use_wnd; n = rb_lookup(&wnd->start_tree, bit); if (!n) goto use_wnd; e = rb_entry(n, struct e_node, start.node); end = e->start.key + e->count.key; if (bit < end && bit + bits <= end) return true; use_wnd: ret = wnd_is_free_hlp(wnd, bit, bits); return ret; } /* * wnd_is_used * * Return: True if all clusters [bit, bit+bits) are used. */ bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits) { bool ret = false; struct super_block *sb = wnd->sb; size_t iw = bit >> (sb->s_blocksize_bits + 3); u32 wbits = 8 * sb->s_blocksize; u32 wbit = bit & (wbits - 1); size_t end; struct rb_node *n; struct e_node *e; if (RB_EMPTY_ROOT(&wnd->start_tree)) goto use_wnd; end = bit + bits; n = rb_lookup(&wnd->start_tree, end - 1); if (!n) goto use_wnd; e = rb_entry(n, struct e_node, start.node); if (e->start.key + e->count.key > bit) return false; use_wnd: while (iw < wnd->nwnd && bits) { u32 tail, op; if (unlikely(iw + 1 == wnd->nwnd)) wbits = wnd->bits_last; tail = wbits - wbit; op = min_t(u32, tail, bits); if (wnd->free_bits[iw]) { bool ret; struct buffer_head *bh = wnd_map(wnd, iw); if (IS_ERR(bh)) goto out; ret = are_bits_set(bh->b_data, wbit, op); put_bh(bh); if (!ret) goto out; } bits -= op; wbit = 0; iw += 1; } ret = true; out: return ret; } /* * wnd_find - Look for free space. * * - flags - BITMAP_FIND_XXX flags * * Return: 0 if not found. */ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint, size_t flags, size_t *allocated) { struct super_block *sb; u32 wbits, wpos, wzbit, wzend; size_t fnd, max_alloc, b_len, b_pos; size_t iw, prev_tail, nwnd, wbit, ebit, zbit, zend; size_t to_alloc0 = to_alloc; const struct e_node *e; const struct rb_node *pr, *cr; u8 log2_bits; bool fbits_valid; struct buffer_head *bh; /* Fast checking for available free space. */ if (flags & BITMAP_FIND_FULL) { size_t zeroes = wnd_zeroes(wnd); zeroes -= wnd->zone_end - wnd->zone_bit; if (zeroes < to_alloc0) goto no_space; if (to_alloc0 > wnd->extent_max) goto no_space; } else { if (to_alloc > wnd->extent_max) to_alloc = wnd->extent_max; } if (wnd->zone_bit <= hint && hint < wnd->zone_end) hint = wnd->zone_end; max_alloc = wnd->nbits; b_len = b_pos = 0; if (hint >= max_alloc) hint = 0; if (RB_EMPTY_ROOT(&wnd->start_tree)) { if (wnd->uptodated == 1) { /* Extents tree is updated -> No free space. */ goto no_space; } goto scan_bitmap; } e = NULL; if (!hint) goto allocate_biggest; /* Use hint: Enumerate extents by start >= hint. */ pr = NULL; cr = wnd->start_tree.rb_node; for (;;) { e = rb_entry(cr, struct e_node, start.node); if (e->start.key == hint) break; if (e->start.key < hint) { pr = cr; cr = cr->rb_right; if (!cr) break; continue; } cr = cr->rb_left; if (!cr) { e = pr ? rb_entry(pr, struct e_node, start.node) : NULL; break; } } if (!e) goto allocate_biggest; if (e->start.key + e->count.key > hint) { /* We have found extension with 'hint' inside. */ size_t len = e->start.key + e->count.key - hint; if (len >= to_alloc && hint + to_alloc <= max_alloc) { fnd = hint; goto found; } if (!(flags & BITMAP_FIND_FULL)) { if (len > to_alloc) len = to_alloc; if (hint + len <= max_alloc) { fnd = hint; to_alloc = len; goto found; } } } allocate_biggest: /* Allocate from biggest free extent. */ e = rb_entry(rb_first(&wnd->count_tree), struct e_node, count.node); if (e->count.key != wnd->extent_max) wnd->extent_max = e->count.key; if (e->count.key < max_alloc) { if (e->count.key >= to_alloc) { ; } else if (flags & BITMAP_FIND_FULL) { if (e->count.key < to_alloc0) { /* Biggest free block is less then requested. */ goto no_space; } to_alloc = e->count.key; } else if (-1 != wnd->uptodated) { to_alloc = e->count.key; } else { /* Check if we can use more bits. */ size_t op, max_check; struct rb_root start_tree; memcpy(&start_tree, &wnd->start_tree, sizeof(struct rb_root)); memset(&wnd->start_tree, 0, sizeof(struct rb_root)); max_check = e->start.key + to_alloc; if (max_check > max_alloc) max_check = max_alloc; for (op = e->start.key + e->count.key; op < max_check; op++) { if (!wnd_is_free(wnd, op, 1)) break; } memcpy(&wnd->start_tree, &start_tree, sizeof(struct rb_root)); to_alloc = op - e->start.key; } /* Prepare to return. */ fnd = e->start.key; if (e->start.key + to_alloc > max_alloc) to_alloc = max_alloc - e->start.key; goto found; } if (wnd->uptodated == 1) { /* Extents tree is updated -> no free space. */ goto no_space; } b_len = e->count.key; b_pos = e->start.key; scan_bitmap: sb = wnd->sb; log2_bits = sb->s_blocksize_bits + 3; /* At most two ranges [hint, max_alloc) + [0, hint). */ Again: /* TODO: Optimize request for case nbits > wbits. */ iw = hint >> log2_bits; wbits = sb->s_blocksize * 8; wpos = hint & (wbits - 1); prev_tail = 0; fbits_valid = true; if (max_alloc == wnd->nbits) { nwnd = wnd->nwnd; } else { size_t t = max_alloc + wbits - 1; nwnd = likely(t > max_alloc) ? (t >> log2_bits) : wnd->nwnd; } /* Enumerate all windows. */ for (; iw < nwnd; iw++) { wbit = iw << log2_bits; if (!wnd->free_bits[iw]) { if (prev_tail > b_len) { b_pos = wbit - prev_tail; b_len = prev_tail; } /* Skip full used window. */ prev_tail = 0; wpos = 0; continue; } if (unlikely(iw + 1 == nwnd)) { if (max_alloc == wnd->nbits) { wbits = wnd->bits_last; } else { size_t t = max_alloc & (wbits - 1); if (t) { wbits = t; fbits_valid = false; } } } if (wnd->zone_end > wnd->zone_bit) { ebit = wbit + wbits; zbit = max(wnd->zone_bit, wbit); zend = min(wnd->zone_end, ebit); /* Here we have a window [wbit, ebit) and zone [zbit, zend). */ if (zend <= zbit) { /* Zone does not overlap window. */ } else { wzbit = zbit - wbit; wzend = zend - wbit; /* Zone overlaps window. */ if (wnd->free_bits[iw] == wzend - wzbit) { prev_tail = 0; wpos = 0; continue; } /* Scan two ranges window: [wbit, zbit) and [zend, ebit). */ bh = wnd_map(wnd, iw); if (IS_ERR(bh)) { /* TODO: Error */ prev_tail = 0; wpos = 0; continue; } /* Scan range [wbit, zbit). */ if (wpos < wzbit) { /* Scan range [wpos, zbit). */ fnd = wnd_scan(bh->b_data, wbit, wpos, wzbit, to_alloc, &prev_tail, &b_pos, &b_len); if (fnd != MINUS_ONE_T) { put_bh(bh); goto found; } } prev_tail = 0; /* Scan range [zend, ebit). */ if (wzend < wbits) { fnd = wnd_scan(bh->b_data, wbit, max(wzend, wpos), wbits, to_alloc, &prev_tail, &b_pos, &b_len); if (fnd != MINUS_ONE_T) { put_bh(bh); goto found; } } wpos = 0; put_bh(bh); continue; } } /* Current window does not overlap zone. */ if (!wpos && fbits_valid && wnd->free_bits[iw] == wbits) { /* Window is empty. */ if (prev_tail + wbits >= to_alloc) { fnd = wbit + wpos - prev_tail; goto found; } /* Increase 'prev_tail' and process next window. */ prev_tail += wbits; wpos = 0; continue; } /* Read window. */ bh = wnd_map(wnd, iw); if (IS_ERR(bh)) { // TODO: Error. prev_tail = 0; wpos = 0; continue; } /* Scan range [wpos, eBits). */ fnd = wnd_scan(bh->b_data, wbit, wpos, wbits, to_alloc, &prev_tail, &b_pos, &b_len); put_bh(bh); if (fnd != MINUS_ONE_T) goto found; } if (b_len < prev_tail) { /* The last fragment. */ b_len = prev_tail; b_pos = max_alloc - prev_tail; } if (hint) { /* * We have scanned range [hint max_alloc). * Prepare to scan range [0 hint + to_alloc). */ size_t nextmax = hint + to_alloc; if (likely(nextmax >= hint) && nextmax < max_alloc) max_alloc = nextmax; hint = 0; goto Again; } if (!b_len) goto no_space; wnd->extent_max = b_len; if (flags & BITMAP_FIND_FULL) goto no_space; fnd = b_pos; to_alloc = b_len; found: if (flags & BITMAP_FIND_MARK_AS_USED) { /* TODO: Optimize remove extent (pass 'e'?). */ if (wnd_set_used(wnd, fnd, to_alloc)) goto no_space; } else if (wnd->extent_max != MINUS_ONE_T && to_alloc > wnd->extent_max) { wnd->extent_max = to_alloc; } *allocated = fnd; return to_alloc; no_space: return 0; } /* * wnd_extend - Extend bitmap ($MFT bitmap). */ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) { int err; struct super_block *sb = wnd->sb; struct ntfs_sb_info *sbi = sb->s_fs_info; u32 blocksize = sb->s_blocksize; u32 wbits = blocksize * 8; u32 b0, new_last; size_t bits, iw, new_wnd; size_t old_bits = wnd->nbits; u16 *new_free; if (new_bits <= old_bits) return -EINVAL; /* Align to 8 byte boundary. */ new_wnd = bytes_to_block(sb, bitmap_size(new_bits)); new_last = new_bits & (wbits - 1); if (!new_last) new_last = wbits; if (new_wnd != wnd->nwnd) { new_free = kmalloc_array(new_wnd, sizeof(u16), GFP_NOFS); if (!new_free) return -ENOMEM; memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short)); memset(new_free + wnd->nwnd, 0, (new_wnd - wnd->nwnd) * sizeof(short)); kfree(wnd->free_bits); wnd->free_bits = new_free; } /* Zero bits [old_bits,new_bits). */ bits = new_bits - old_bits; b0 = old_bits & (wbits - 1); for (iw = old_bits >> (sb->s_blocksize_bits + 3); bits; iw += 1) { u32 op; size_t frb; u64 vbo, lbo, bytes; struct buffer_head *bh; if (iw + 1 == new_wnd) wbits = new_last; op = b0 + bits > wbits ? wbits - b0 : bits; vbo = (u64)iw * blocksize; err = ntfs_vbo_to_lbo(sbi, &wnd->run, vbo, &lbo, &bytes); if (err) break; bh = ntfs_bread(sb, lbo >> sb->s_blocksize_bits); if (!bh) return -EIO; lock_buffer(bh); ntfs_bitmap_clear_le(bh->b_data, b0, blocksize * 8 - b0); frb = wbits - ntfs_bitmap_weight_le(bh->b_data, wbits); wnd->total_zeroes += frb - wnd->free_bits[iw]; wnd->free_bits[iw] = frb; set_buffer_uptodate(bh); mark_buffer_dirty(bh); unlock_buffer(bh); /* err = sync_dirty_buffer(bh); */ b0 = 0; bits -= op; } wnd->nbits = new_bits; wnd->nwnd = new_wnd; wnd->bits_last = new_last; wnd_add_free_ext(wnd, old_bits, new_bits - old_bits, false); return 0; } void wnd_zone_set(struct wnd_bitmap *wnd, size_t lcn, size_t len) { size_t zlen = wnd->zone_end - wnd->zone_bit; if (zlen) wnd_add_free_ext(wnd, wnd->zone_bit, zlen, false); if (!RB_EMPTY_ROOT(&wnd->start_tree) && len) wnd_remove_free_ext(wnd, lcn, len); wnd->zone_bit = lcn; wnd->zone_end = lcn + len; } int ntfs_trim_fs(struct ntfs_sb_info *sbi, struct fstrim_range *range) { int err = 0; struct super_block *sb = sbi->sb; struct wnd_bitmap *wnd = &sbi->used.bitmap; u32 wbits = 8 * sb->s_blocksize; CLST len = 0, lcn = 0, done = 0; CLST minlen = bytes_to_cluster(sbi, range->minlen); CLST lcn_from = bytes_to_cluster(sbi, range->start); size_t iw = lcn_from >> (sb->s_blocksize_bits + 3); u32 wbit = lcn_from & (wbits - 1); CLST lcn_to; if (!minlen) minlen = 1; if (range->len == (u64)-1) lcn_to = wnd->nbits; else lcn_to = bytes_to_cluster(sbi, range->start + range->len); down_read_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); for (; iw < wnd->nwnd; iw++, wbit = 0) { CLST lcn_wnd = iw * wbits; struct buffer_head *bh; if (lcn_wnd > lcn_to) break; if (!wnd->free_bits[iw]) continue; if (iw + 1 == wnd->nwnd) wbits = wnd->bits_last; if (lcn_wnd + wbits > lcn_to) wbits = lcn_to - lcn_wnd; bh = wnd_map(wnd, iw); if (IS_ERR(bh)) { err = PTR_ERR(bh); break; } for (; wbit < wbits; wbit++) { if (!test_bit_le(wbit, bh->b_data)) { if (!len) lcn = lcn_wnd + wbit; len += 1; continue; } if (len >= minlen) { err = ntfs_discard(sbi, lcn, len); if (err) goto out; done += len; } len = 0; } put_bh(bh); } /* Process the last fragment. */ if (len >= minlen) { err = ntfs_discard(sbi, lcn, len); if (err) goto out; done += len; } out: range->len = (u64)done << sbi->cluster_bits; up_read(&wnd->rw_lock); return err; } #if BITS_PER_LONG == 64 typedef __le64 bitmap_ulong; #define cpu_to_ul(x) cpu_to_le64(x) #define ul_to_cpu(x) le64_to_cpu(x) #else typedef __le32 bitmap_ulong; #define cpu_to_ul(x) cpu_to_le32(x) #define ul_to_cpu(x) le32_to_cpu(x) #endif void ntfs_bitmap_set_le(void *map, unsigned int start, int len) { bitmap_ulong *p = (bitmap_ulong *)map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); bitmap_ulong mask_to_set = cpu_to_ul(BITMAP_FIRST_WORD_MASK(start)); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_LONG; mask_to_set = cpu_to_ul(~0UL); p++; } if (len) { mask_to_set &= cpu_to_ul(BITMAP_LAST_WORD_MASK(size)); *p |= mask_to_set; } } void ntfs_bitmap_clear_le(void *map, unsigned int start, int len) { bitmap_ulong *p = (bitmap_ulong *)map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); bitmap_ulong mask_to_clear = cpu_to_ul(BITMAP_FIRST_WORD_MASK(start)); while (len - bits_to_clear >= 0) { *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_LONG; mask_to_clear = cpu_to_ul(~0UL); p++; } if (len) { mask_to_clear &= cpu_to_ul(BITMAP_LAST_WORD_MASK(size)); *p &= ~mask_to_clear; } } unsigned int ntfs_bitmap_weight_le(const void *bitmap, int bits) { const ulong *bmp = bitmap; unsigned int k, lim = bits / BITS_PER_LONG; unsigned int w = 0; for (k = 0; k < lim; k++) w += hweight_long(bmp[k]); if (bits % BITS_PER_LONG) { w += hweight_long(ul_to_cpu(((bitmap_ulong *)bitmap)[k]) & BITMAP_LAST_WORD_MASK(bits)); } return w; } |
| 56 48 34 7 4 1 57 34 5 57 34 34 55 55 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2020-2023 Intel Corporation */ #include <linux/kernel.h> #include <linux/device.h> #include <linux/if.h> #include <linux/if_ether.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/notifier.h> #include <net/mac80211.h> #include <net/cfg80211.h> #include "ieee80211_i.h" #include "rate.h" #include "debugfs.h" #include "debugfs_netdev.h" #include "driver-ops.h" static ssize_t ieee80211_if_read_sdata( struct ieee80211_sub_if_data *sdata, char __user *userbuf, size_t count, loff_t *ppos, ssize_t (*format)(const struct ieee80211_sub_if_data *sdata, char *, int)) { char buf[200]; ssize_t ret = -EINVAL; wiphy_lock(sdata->local->hw.wiphy); ret = (*format)(sdata, buf, sizeof(buf)); wiphy_unlock(sdata->local->hw.wiphy); if (ret >= 0) ret = simple_read_from_buffer(userbuf, count, ppos, buf, ret); return ret; } static ssize_t ieee80211_if_write_sdata( struct ieee80211_sub_if_data *sdata, const char __user *userbuf, size_t count, loff_t *ppos, ssize_t (*write)(struct ieee80211_sub_if_data *sdata, const char *, int)) { char buf[64]; ssize_t ret; if (count >= sizeof(buf)) return -E2BIG; if (copy_from_user(buf, userbuf, count)) return -EFAULT; buf[count] = '\0'; wiphy_lock(sdata->local->hw.wiphy); ret = (*write)(sdata, buf, count); wiphy_unlock(sdata->local->hw.wiphy); return ret; } static ssize_t ieee80211_if_read_link( struct ieee80211_link_data *link, char __user *userbuf, size_t count, loff_t *ppos, ssize_t (*format)(const struct ieee80211_link_data *link, char *, int)) { char buf[200]; ssize_t ret = -EINVAL; wiphy_lock(link->sdata->local->hw.wiphy); ret = (*format)(link, buf, sizeof(buf)); wiphy_unlock(link->sdata->local->hw.wiphy); if (ret >= 0) ret = simple_read_from_buffer(userbuf, count, ppos, buf, ret); return ret; } static ssize_t ieee80211_if_write_link( struct ieee80211_link_data *link, const char __user *userbuf, size_t count, loff_t *ppos, ssize_t (*write)(struct ieee80211_link_data *link, const char *, int)) { char buf[64]; ssize_t ret; if (count >= sizeof(buf)) return -E2BIG; if (copy_from_user(buf, userbuf, count)) return -EFAULT; buf[count] = '\0'; wiphy_lock(link->sdata->local->hw.wiphy); ret = (*write)(link, buf, count); wiphy_unlock(link->sdata->local->hw.wiphy); return ret; } #define IEEE80211_IF_FMT(name, type, field, format_string) \ static ssize_t ieee80211_if_fmt_##name( \ const type *data, char *buf, \ int buflen) \ { \ return scnprintf(buf, buflen, format_string, data->field); \ } #define IEEE80211_IF_FMT_DEC(name, type, field) \ IEEE80211_IF_FMT(name, type, field, "%d\n") #define IEEE80211_IF_FMT_HEX(name, type, field) \ IEEE80211_IF_FMT(name, type, field, "%#x\n") #define IEEE80211_IF_FMT_LHEX(name, type, field) \ IEEE80211_IF_FMT(name, type, field, "%#lx\n") #define IEEE80211_IF_FMT_HEXARRAY(name, type, field) \ static ssize_t ieee80211_if_fmt_##name( \ const type *data, \ char *buf, int buflen) \ { \ char *p = buf; \ int i; \ for (i = 0; i < sizeof(data->field); i++) { \ p += scnprintf(p, buflen + buf - p, "%.2x ", \ data->field[i]); \ } \ p += scnprintf(p, buflen + buf - p, "\n"); \ return p - buf; \ } #define IEEE80211_IF_FMT_ATOMIC(name, type, field) \ static ssize_t ieee80211_if_fmt_##name( \ const type *data, \ char *buf, int buflen) \ { \ return scnprintf(buf, buflen, "%d\n", atomic_read(&data->field));\ } #define IEEE80211_IF_FMT_MAC(name, type, field) \ static ssize_t ieee80211_if_fmt_##name( \ const type *data, char *buf, \ int buflen) \ { \ return scnprintf(buf, buflen, "%pM\n", data->field); \ } #define IEEE80211_IF_FMT_JIFFIES_TO_MS(name, type, field) \ static ssize_t ieee80211_if_fmt_##name( \ const type *data, \ char *buf, int buflen) \ { \ return scnprintf(buf, buflen, "%d\n", \ jiffies_to_msecs(data->field)); \ } #define _IEEE80211_IF_FILE_OPS(name, _read, _write) \ static const struct file_operations name##_ops = { \ .read = (_read), \ .write = (_write), \ .open = simple_open, \ .llseek = generic_file_llseek, \ } #define _IEEE80211_IF_FILE_R_FN(name) \ static ssize_t ieee80211_if_read_##name(struct file *file, \ char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ return ieee80211_if_read_sdata(file->private_data, \ userbuf, count, ppos, \ ieee80211_if_fmt_##name); \ } #define _IEEE80211_IF_FILE_W_FN(name) \ static ssize_t ieee80211_if_write_##name(struct file *file, \ const char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ return ieee80211_if_write_sdata(file->private_data, userbuf, \ count, ppos, \ ieee80211_if_parse_##name); \ } #define IEEE80211_IF_FILE_R(name) \ _IEEE80211_IF_FILE_R_FN(name) \ _IEEE80211_IF_FILE_OPS(name, ieee80211_if_read_##name, NULL) #define IEEE80211_IF_FILE_W(name) \ _IEEE80211_IF_FILE_W_FN(name) \ _IEEE80211_IF_FILE_OPS(name, NULL, ieee80211_if_write_##name) #define IEEE80211_IF_FILE_RW(name) \ _IEEE80211_IF_FILE_R_FN(name) \ _IEEE80211_IF_FILE_W_FN(name) \ _IEEE80211_IF_FILE_OPS(name, ieee80211_if_read_##name, \ ieee80211_if_write_##name) #define IEEE80211_IF_FILE(name, field, format) \ IEEE80211_IF_FMT_##format(name, struct ieee80211_sub_if_data, field) \ IEEE80211_IF_FILE_R(name) #define _IEEE80211_IF_LINK_R_FN(name) \ static ssize_t ieee80211_if_read_##name(struct file *file, \ char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ return ieee80211_if_read_link(file->private_data, \ userbuf, count, ppos, \ ieee80211_if_fmt_##name); \ } #define _IEEE80211_IF_LINK_W_FN(name) \ static ssize_t ieee80211_if_write_##name(struct file *file, \ const char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ return ieee80211_if_write_link(file->private_data, userbuf, \ count, ppos, \ ieee80211_if_parse_##name); \ } #define IEEE80211_IF_LINK_FILE_R(name) \ _IEEE80211_IF_LINK_R_FN(name) \ _IEEE80211_IF_FILE_OPS(link_##name, ieee80211_if_read_##name, NULL) #define IEEE80211_IF_LINK_FILE_W(name) \ _IEEE80211_IF_LINK_W_FN(name) \ _IEEE80211_IF_FILE_OPS(link_##name, NULL, ieee80211_if_write_##name) #define IEEE80211_IF_LINK_FILE_RW(name) \ _IEEE80211_IF_LINK_R_FN(name) \ _IEEE80211_IF_LINK_W_FN(name) \ _IEEE80211_IF_FILE_OPS(link_##name, ieee80211_if_read_##name, \ ieee80211_if_write_##name) #define IEEE80211_IF_LINK_FILE(name, field, format) \ IEEE80211_IF_FMT_##format(name, struct ieee80211_link_data, field) \ IEEE80211_IF_LINK_FILE_R(name) /* common attributes */ IEEE80211_IF_FILE(rc_rateidx_mask_2ghz, rc_rateidx_mask[NL80211_BAND_2GHZ], HEX); IEEE80211_IF_FILE(rc_rateidx_mask_5ghz, rc_rateidx_mask[NL80211_BAND_5GHZ], HEX); IEEE80211_IF_FILE(rc_rateidx_mcs_mask_2ghz, rc_rateidx_mcs_mask[NL80211_BAND_2GHZ], HEXARRAY); IEEE80211_IF_FILE(rc_rateidx_mcs_mask_5ghz, rc_rateidx_mcs_mask[NL80211_BAND_5GHZ], HEXARRAY); static ssize_t ieee80211_if_fmt_rc_rateidx_vht_mcs_mask_2ghz( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { int i, len = 0; const u16 *mask = sdata->rc_rateidx_vht_mcs_mask[NL80211_BAND_2GHZ]; for (i = 0; i < NL80211_VHT_NSS_MAX; i++) len += scnprintf(buf + len, buflen - len, "%04x ", mask[i]); len += scnprintf(buf + len, buflen - len, "\n"); return len; } IEEE80211_IF_FILE_R(rc_rateidx_vht_mcs_mask_2ghz); static ssize_t ieee80211_if_fmt_rc_rateidx_vht_mcs_mask_5ghz( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { int i, len = 0; const u16 *mask = sdata->rc_rateidx_vht_mcs_mask[NL80211_BAND_5GHZ]; for (i = 0; i < NL80211_VHT_NSS_MAX; i++) len += scnprintf(buf + len, buflen - len, "%04x ", mask[i]); len += scnprintf(buf + len, buflen - len, "\n"); return len; } IEEE80211_IF_FILE_R(rc_rateidx_vht_mcs_mask_5ghz); IEEE80211_IF_FILE(flags, flags, HEX); IEEE80211_IF_FILE(state, state, LHEX); IEEE80211_IF_LINK_FILE(txpower, conf->txpower, DEC); IEEE80211_IF_LINK_FILE(ap_power_level, ap_power_level, DEC); IEEE80211_IF_LINK_FILE(user_power_level, user_power_level, DEC); static ssize_t ieee80211_if_fmt_hw_queues(const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { int len; len = scnprintf(buf, buflen, "AC queues: VO:%d VI:%d BE:%d BK:%d\n", sdata->vif.hw_queue[IEEE80211_AC_VO], sdata->vif.hw_queue[IEEE80211_AC_VI], sdata->vif.hw_queue[IEEE80211_AC_BE], sdata->vif.hw_queue[IEEE80211_AC_BK]); if (sdata->vif.type == NL80211_IFTYPE_AP) len += scnprintf(buf + len, buflen - len, "cab queue: %d\n", sdata->vif.cab_queue); return len; } IEEE80211_IF_FILE_R(hw_queues); /* STA attributes */ IEEE80211_IF_FILE(bssid, deflink.u.mgd.bssid, MAC); IEEE80211_IF_FILE(aid, vif.cfg.aid, DEC); IEEE80211_IF_FILE(beacon_timeout, u.mgd.beacon_timeout, JIFFIES_TO_MS); static int ieee80211_set_smps(struct ieee80211_link_data *link, enum ieee80211_smps_mode smps_mode) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; /* The driver indicated that EML is enabled for the interface, thus do * not allow to override the SMPS state. */ if (sdata->vif.driver_flags & IEEE80211_VIF_EML_ACTIVE) return -EOPNOTSUPP; if (!(local->hw.wiphy->features & NL80211_FEATURE_STATIC_SMPS) && smps_mode == IEEE80211_SMPS_STATIC) return -EINVAL; /* auto should be dynamic if in PS mode */ if (!(local->hw.wiphy->features & NL80211_FEATURE_DYNAMIC_SMPS) && (smps_mode == IEEE80211_SMPS_DYNAMIC || smps_mode == IEEE80211_SMPS_AUTOMATIC)) return -EINVAL; if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; return __ieee80211_request_smps_mgd(link->sdata, link, smps_mode); } static const char *smps_modes[IEEE80211_SMPS_NUM_MODES] = { [IEEE80211_SMPS_AUTOMATIC] = "auto", [IEEE80211_SMPS_OFF] = "off", [IEEE80211_SMPS_STATIC] = "static", [IEEE80211_SMPS_DYNAMIC] = "dynamic", }; static ssize_t ieee80211_if_fmt_smps(const struct ieee80211_link_data *link, char *buf, int buflen) { if (link->sdata->vif.type == NL80211_IFTYPE_STATION) return snprintf(buf, buflen, "request: %s\nused: %s\n", smps_modes[link->u.mgd.req_smps], smps_modes[link->smps_mode]); return -EINVAL; } static ssize_t ieee80211_if_parse_smps(struct ieee80211_link_data *link, const char *buf, int buflen) { enum ieee80211_smps_mode mode; for (mode = 0; mode < IEEE80211_SMPS_NUM_MODES; mode++) { if (strncmp(buf, smps_modes[mode], buflen) == 0) { int err = ieee80211_set_smps(link, mode); if (!err) return buflen; return err; } } return -EINVAL; } IEEE80211_IF_LINK_FILE_RW(smps); static ssize_t ieee80211_if_parse_tkip_mic_test( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { struct ieee80211_local *local = sdata->local; u8 addr[ETH_ALEN]; struct sk_buff *skb; struct ieee80211_hdr *hdr; __le16 fc; if (!mac_pton(buf, addr)) return -EINVAL; if (!ieee80211_sdata_running(sdata)) return -ENOTCONN; skb = dev_alloc_skb(local->hw.extra_tx_headroom + 24 + 100); if (!skb) return -ENOMEM; skb_reserve(skb, local->hw.extra_tx_headroom); hdr = skb_put_zero(skb, 24); fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA); switch (sdata->vif.type) { case NL80211_IFTYPE_AP: fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); /* DA BSSID SA */ memcpy(hdr->addr1, addr, ETH_ALEN); memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); memcpy(hdr->addr3, sdata->vif.addr, ETH_ALEN); break; case NL80211_IFTYPE_STATION: fc |= cpu_to_le16(IEEE80211_FCTL_TODS); /* BSSID SA DA */ if (!sdata->u.mgd.associated) { dev_kfree_skb(skb); return -ENOTCONN; } memcpy(hdr->addr1, sdata->deflink.u.mgd.bssid, ETH_ALEN); memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); memcpy(hdr->addr3, addr, ETH_ALEN); break; default: dev_kfree_skb(skb); return -EOPNOTSUPP; } hdr->frame_control = fc; /* * Add some length to the test frame to make it look bit more valid. * The exact contents does not matter since the recipient is required * to drop this because of the Michael MIC failure. */ skb_put_zero(skb, 50); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_TKIP_MIC_FAILURE; ieee80211_tx_skb(sdata, skb); return buflen; } IEEE80211_IF_FILE_W(tkip_mic_test); static ssize_t ieee80211_if_parse_beacon_loss( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { if (!ieee80211_sdata_running(sdata) || !sdata->vif.cfg.assoc) return -ENOTCONN; ieee80211_beacon_loss(&sdata->vif); return buflen; } IEEE80211_IF_FILE_W(beacon_loss); static ssize_t ieee80211_if_fmt_uapsd_queues( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { const struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; return snprintf(buf, buflen, "0x%x\n", ifmgd->uapsd_queues); } static ssize_t ieee80211_if_parse_uapsd_queues( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 val; int ret; ret = kstrtou8(buf, 0, &val); if (ret) return ret; if (val & ~IEEE80211_WMM_IE_STA_QOSINFO_AC_MASK) return -ERANGE; ifmgd->uapsd_queues = val; return buflen; } IEEE80211_IF_FILE_RW(uapsd_queues); static ssize_t ieee80211_if_fmt_uapsd_max_sp_len( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { const struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; return snprintf(buf, buflen, "0x%x\n", ifmgd->uapsd_max_sp_len); } static ssize_t ieee80211_if_parse_uapsd_max_sp_len( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; unsigned long val; int ret; ret = kstrtoul(buf, 0, &val); if (ret) return -EINVAL; if (val & ~IEEE80211_WMM_IE_STA_QOSINFO_SP_MASK) return -ERANGE; ifmgd->uapsd_max_sp_len = val; return buflen; } IEEE80211_IF_FILE_RW(uapsd_max_sp_len); static ssize_t ieee80211_if_fmt_tdls_wider_bw( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { const struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; bool tdls_wider_bw; tdls_wider_bw = ieee80211_hw_check(&sdata->local->hw, TDLS_WIDER_BW) && !ifmgd->tdls_wider_bw_prohibited; return snprintf(buf, buflen, "%d\n", tdls_wider_bw); } static ssize_t ieee80211_if_parse_tdls_wider_bw( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 val; int ret; ret = kstrtou8(buf, 0, &val); if (ret) return ret; ifmgd->tdls_wider_bw_prohibited = !val; return buflen; } IEEE80211_IF_FILE_RW(tdls_wider_bw); /* AP attributes */ IEEE80211_IF_FILE(num_mcast_sta, u.ap.num_mcast_sta, ATOMIC); IEEE80211_IF_FILE(num_sta_ps, u.ap.ps.num_sta_ps, ATOMIC); IEEE80211_IF_FILE(dtim_count, u.ap.ps.dtim_count, DEC); IEEE80211_IF_FILE(num_mcast_sta_vlan, u.vlan.num_mcast_sta, ATOMIC); static ssize_t ieee80211_if_fmt_num_buffered_multicast( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { return scnprintf(buf, buflen, "%u\n", skb_queue_len(&sdata->u.ap.ps.bc_buf)); } IEEE80211_IF_FILE_R(num_buffered_multicast); static ssize_t ieee80211_if_fmt_aqm( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { struct ieee80211_local *local = sdata->local; struct txq_info *txqi; int len; if (!sdata->vif.txq) return 0; txqi = to_txq_info(sdata->vif.txq); spin_lock_bh(&local->fq.lock); rcu_read_lock(); len = scnprintf(buf, buflen, "ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets\n" "%u %u %u %u %u %u %u %u %u %u\n", txqi->txq.ac, txqi->tin.backlog_bytes, txqi->tin.backlog_packets, txqi->tin.flows, txqi->cstats.drop_count, txqi->cstats.ecn_mark, txqi->tin.overlimit, txqi->tin.collisions, txqi->tin.tx_bytes, txqi->tin.tx_packets); rcu_read_unlock(); spin_unlock_bh(&local->fq.lock); return len; } IEEE80211_IF_FILE_R(aqm); IEEE80211_IF_FILE(multicast_to_unicast, u.ap.multicast_to_unicast, HEX); /* IBSS attributes */ static ssize_t ieee80211_if_fmt_tsf( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { struct ieee80211_local *local = sdata->local; u64 tsf; tsf = drv_get_tsf(local, (struct ieee80211_sub_if_data *)sdata); return scnprintf(buf, buflen, "0x%016llx\n", (unsigned long long) tsf); } static ssize_t ieee80211_if_parse_tsf( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { struct ieee80211_local *local = sdata->local; unsigned long long tsf; int ret; int tsf_is_delta = 0; if (strncmp(buf, "reset", 5) == 0) { if (local->ops->reset_tsf) { drv_reset_tsf(local, sdata); wiphy_info(local->hw.wiphy, "debugfs reset TSF\n"); } } else { if (buflen > 10 && buf[1] == '=') { if (buf[0] == '+') tsf_is_delta = 1; else if (buf[0] == '-') tsf_is_delta = -1; else return -EINVAL; buf += 2; } ret = kstrtoull(buf, 10, &tsf); if (ret < 0) return ret; if (tsf_is_delta && local->ops->offset_tsf) { drv_offset_tsf(local, sdata, tsf_is_delta * tsf); wiphy_info(local->hw.wiphy, "debugfs offset TSF by %018lld\n", tsf_is_delta * tsf); } else if (local->ops->set_tsf) { if (tsf_is_delta) tsf = drv_get_tsf(local, sdata) + tsf_is_delta * tsf; drv_set_tsf(local, sdata, tsf); wiphy_info(local->hw.wiphy, "debugfs set TSF to %#018llx\n", tsf); } } ieee80211_recalc_dtim(local, sdata); return buflen; } IEEE80211_IF_FILE_RW(tsf); static ssize_t ieee80211_if_fmt_valid_links(const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { return snprintf(buf, buflen, "0x%x\n", sdata->vif.valid_links); } IEEE80211_IF_FILE_R(valid_links); static ssize_t ieee80211_if_fmt_active_links(const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { return snprintf(buf, buflen, "0x%x\n", sdata->vif.active_links); } static ssize_t ieee80211_if_parse_active_links(struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { u16 active_links; if (kstrtou16(buf, 0, &active_links)) return -EINVAL; return ieee80211_set_active_links(&sdata->vif, active_links) ?: buflen; } IEEE80211_IF_FILE_RW(active_links); IEEE80211_IF_LINK_FILE(addr, conf->addr, MAC); #ifdef CONFIG_MAC80211_MESH IEEE80211_IF_FILE(estab_plinks, u.mesh.estab_plinks, ATOMIC); /* Mesh stats attributes */ IEEE80211_IF_FILE(fwded_mcast, u.mesh.mshstats.fwded_mcast, DEC); IEEE80211_IF_FILE(fwded_unicast, u.mesh.mshstats.fwded_unicast, DEC); IEEE80211_IF_FILE(fwded_frames, u.mesh.mshstats.fwded_frames, DEC); IEEE80211_IF_FILE(dropped_frames_ttl, u.mesh.mshstats.dropped_frames_ttl, DEC); IEEE80211_IF_FILE(dropped_frames_no_route, u.mesh.mshstats.dropped_frames_no_route, DEC); /* Mesh parameters */ IEEE80211_IF_FILE(dot11MeshMaxRetries, u.mesh.mshcfg.dot11MeshMaxRetries, DEC); IEEE80211_IF_FILE(dot11MeshRetryTimeout, u.mesh.mshcfg.dot11MeshRetryTimeout, DEC); IEEE80211_IF_FILE(dot11MeshConfirmTimeout, u.mesh.mshcfg.dot11MeshConfirmTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHoldingTimeout, u.mesh.mshcfg.dot11MeshHoldingTimeout, DEC); IEEE80211_IF_FILE(dot11MeshTTL, u.mesh.mshcfg.dot11MeshTTL, DEC); IEEE80211_IF_FILE(element_ttl, u.mesh.mshcfg.element_ttl, DEC); IEEE80211_IF_FILE(auto_open_plinks, u.mesh.mshcfg.auto_open_plinks, DEC); IEEE80211_IF_FILE(dot11MeshMaxPeerLinks, u.mesh.mshcfg.dot11MeshMaxPeerLinks, DEC); IEEE80211_IF_FILE(dot11MeshHWMPactivePathTimeout, u.mesh.mshcfg.dot11MeshHWMPactivePathTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMPpreqMinInterval, u.mesh.mshcfg.dot11MeshHWMPpreqMinInterval, DEC); IEEE80211_IF_FILE(dot11MeshHWMPperrMinInterval, u.mesh.mshcfg.dot11MeshHWMPperrMinInterval, DEC); IEEE80211_IF_FILE(dot11MeshHWMPnetDiameterTraversalTime, u.mesh.mshcfg.dot11MeshHWMPnetDiameterTraversalTime, DEC); IEEE80211_IF_FILE(dot11MeshHWMPmaxPREQretries, u.mesh.mshcfg.dot11MeshHWMPmaxPREQretries, DEC); IEEE80211_IF_FILE(path_refresh_time, u.mesh.mshcfg.path_refresh_time, DEC); IEEE80211_IF_FILE(min_discovery_timeout, u.mesh.mshcfg.min_discovery_timeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMPRootMode, u.mesh.mshcfg.dot11MeshHWMPRootMode, DEC); IEEE80211_IF_FILE(dot11MeshGateAnnouncementProtocol, u.mesh.mshcfg.dot11MeshGateAnnouncementProtocol, DEC); IEEE80211_IF_FILE(dot11MeshHWMPRannInterval, u.mesh.mshcfg.dot11MeshHWMPRannInterval, DEC); IEEE80211_IF_FILE(dot11MeshForwarding, u.mesh.mshcfg.dot11MeshForwarding, DEC); IEEE80211_IF_FILE(rssi_threshold, u.mesh.mshcfg.rssi_threshold, DEC); IEEE80211_IF_FILE(ht_opmode, u.mesh.mshcfg.ht_opmode, DEC); IEEE80211_IF_FILE(dot11MeshHWMPactivePathToRootTimeout, u.mesh.mshcfg.dot11MeshHWMPactivePathToRootTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMProotInterval, u.mesh.mshcfg.dot11MeshHWMProotInterval, DEC); IEEE80211_IF_FILE(dot11MeshHWMPconfirmationInterval, u.mesh.mshcfg.dot11MeshHWMPconfirmationInterval, DEC); IEEE80211_IF_FILE(power_mode, u.mesh.mshcfg.power_mode, DEC); IEEE80211_IF_FILE(dot11MeshAwakeWindowDuration, u.mesh.mshcfg.dot11MeshAwakeWindowDuration, DEC); IEEE80211_IF_FILE(dot11MeshConnectedToMeshGate, u.mesh.mshcfg.dot11MeshConnectedToMeshGate, DEC); IEEE80211_IF_FILE(dot11MeshNolearn, u.mesh.mshcfg.dot11MeshNolearn, DEC); IEEE80211_IF_FILE(dot11MeshConnectedToAuthServer, u.mesh.mshcfg.dot11MeshConnectedToAuthServer, DEC); #endif #define DEBUGFS_ADD_MODE(name, mode) \ debugfs_create_file(#name, mode, sdata->vif.debugfs_dir, \ sdata, &name##_ops) #define DEBUGFS_ADD_X(_bits, _name, _mode) \ debugfs_create_x##_bits(#_name, _mode, sdata->vif.debugfs_dir, \ &sdata->vif._name) #define DEBUGFS_ADD_X8(_name, _mode) \ DEBUGFS_ADD_X(8, _name, _mode) #define DEBUGFS_ADD_X16(_name, _mode) \ DEBUGFS_ADD_X(16, _name, _mode) #define DEBUGFS_ADD_X32(_name, _mode) \ DEBUGFS_ADD_X(32, _name, _mode) #define DEBUGFS_ADD(name) DEBUGFS_ADD_MODE(name, 0400) static void add_common_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(rc_rateidx_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mask_5ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_5ghz); DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_2ghz); DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_5ghz); DEBUGFS_ADD(hw_queues); if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && sdata->vif.type != NL80211_IFTYPE_NAN) DEBUGFS_ADD(aqm); } static void add_sta_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(bssid); DEBUGFS_ADD(aid); DEBUGFS_ADD(beacon_timeout); DEBUGFS_ADD_MODE(tkip_mic_test, 0200); DEBUGFS_ADD_MODE(beacon_loss, 0200); DEBUGFS_ADD_MODE(uapsd_queues, 0600); DEBUGFS_ADD_MODE(uapsd_max_sp_len, 0600); DEBUGFS_ADD_MODE(tdls_wider_bw, 0600); DEBUGFS_ADD_MODE(valid_links, 0400); DEBUGFS_ADD_MODE(active_links, 0600); DEBUGFS_ADD_X16(dormant_links, 0400); } static void add_ap_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(num_mcast_sta); DEBUGFS_ADD(num_sta_ps); DEBUGFS_ADD(dtim_count); DEBUGFS_ADD(num_buffered_multicast); DEBUGFS_ADD_MODE(tkip_mic_test, 0200); DEBUGFS_ADD_MODE(multicast_to_unicast, 0600); } static void add_vlan_files(struct ieee80211_sub_if_data *sdata) { /* add num_mcast_sta_vlan using name num_mcast_sta */ debugfs_create_file("num_mcast_sta", 0400, sdata->vif.debugfs_dir, sdata, &num_mcast_sta_vlan_ops); } static void add_ibss_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD_MODE(tsf, 0600); } #ifdef CONFIG_MAC80211_MESH static void add_mesh_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD_MODE(tsf, 0600); DEBUGFS_ADD_MODE(estab_plinks, 0400); } static void add_mesh_stats(struct ieee80211_sub_if_data *sdata) { struct dentry *dir = debugfs_create_dir("mesh_stats", sdata->vif.debugfs_dir); #define MESHSTATS_ADD(name)\ debugfs_create_file(#name, 0400, dir, sdata, &name##_ops) MESHSTATS_ADD(fwded_mcast); MESHSTATS_ADD(fwded_unicast); MESHSTATS_ADD(fwded_frames); MESHSTATS_ADD(dropped_frames_ttl); MESHSTATS_ADD(dropped_frames_no_route); #undef MESHSTATS_ADD } static void add_mesh_config(struct ieee80211_sub_if_data *sdata) { struct dentry *dir = debugfs_create_dir("mesh_config", sdata->vif.debugfs_dir); #define MESHPARAMS_ADD(name) \ debugfs_create_file(#name, 0600, dir, sdata, &name##_ops) MESHPARAMS_ADD(dot11MeshMaxRetries); MESHPARAMS_ADD(dot11MeshRetryTimeout); MESHPARAMS_ADD(dot11MeshConfirmTimeout); MESHPARAMS_ADD(dot11MeshHoldingTimeout); MESHPARAMS_ADD(dot11MeshTTL); MESHPARAMS_ADD(element_ttl); MESHPARAMS_ADD(auto_open_plinks); MESHPARAMS_ADD(dot11MeshMaxPeerLinks); MESHPARAMS_ADD(dot11MeshHWMPactivePathTimeout); MESHPARAMS_ADD(dot11MeshHWMPpreqMinInterval); MESHPARAMS_ADD(dot11MeshHWMPperrMinInterval); MESHPARAMS_ADD(dot11MeshHWMPnetDiameterTraversalTime); MESHPARAMS_ADD(dot11MeshHWMPmaxPREQretries); MESHPARAMS_ADD(path_refresh_time); MESHPARAMS_ADD(min_discovery_timeout); MESHPARAMS_ADD(dot11MeshHWMPRootMode); MESHPARAMS_ADD(dot11MeshHWMPRannInterval); MESHPARAMS_ADD(dot11MeshForwarding); MESHPARAMS_ADD(dot11MeshGateAnnouncementProtocol); MESHPARAMS_ADD(rssi_threshold); MESHPARAMS_ADD(ht_opmode); MESHPARAMS_ADD(dot11MeshHWMPactivePathToRootTimeout); MESHPARAMS_ADD(dot11MeshHWMProotInterval); MESHPARAMS_ADD(dot11MeshHWMPconfirmationInterval); MESHPARAMS_ADD(power_mode); MESHPARAMS_ADD(dot11MeshAwakeWindowDuration); MESHPARAMS_ADD(dot11MeshConnectedToMeshGate); MESHPARAMS_ADD(dot11MeshNolearn); MESHPARAMS_ADD(dot11MeshConnectedToAuthServer); #undef MESHPARAMS_ADD } #endif static void add_files(struct ieee80211_sub_if_data *sdata) { if (!sdata->vif.debugfs_dir) return; DEBUGFS_ADD(flags); DEBUGFS_ADD(state); if (sdata->vif.type != NL80211_IFTYPE_MONITOR) add_common_files(sdata); switch (sdata->vif.type) { case NL80211_IFTYPE_MESH_POINT: #ifdef CONFIG_MAC80211_MESH add_mesh_files(sdata); add_mesh_stats(sdata); add_mesh_config(sdata); #endif break; case NL80211_IFTYPE_STATION: add_sta_files(sdata); break; case NL80211_IFTYPE_ADHOC: add_ibss_files(sdata); break; case NL80211_IFTYPE_AP: add_ap_files(sdata); break; case NL80211_IFTYPE_AP_VLAN: add_vlan_files(sdata); break; default: break; } } #undef DEBUGFS_ADD_MODE #undef DEBUGFS_ADD #define DEBUGFS_ADD_MODE(dentry, name, mode) \ debugfs_create_file(#name, mode, dentry, \ link, &link_##name##_ops) #define DEBUGFS_ADD(dentry, name) DEBUGFS_ADD_MODE(dentry, name, 0400) static void add_link_files(struct ieee80211_link_data *link, struct dentry *dentry) { DEBUGFS_ADD(dentry, txpower); DEBUGFS_ADD(dentry, user_power_level); DEBUGFS_ADD(dentry, ap_power_level); switch (link->sdata->vif.type) { case NL80211_IFTYPE_STATION: DEBUGFS_ADD_MODE(dentry, smps, 0600); break; default: break; } } void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata, bool mld_vif) { char buf[10+IFNAMSIZ]; sprintf(buf, "netdev:%s", sdata->name); sdata->vif.debugfs_dir = debugfs_create_dir(buf, sdata->local->hw.wiphy->debugfsdir); /* deflink also has this */ sdata->deflink.debugfs_dir = sdata->vif.debugfs_dir; sdata->debugfs.subdir_stations = debugfs_create_dir("stations", sdata->vif.debugfs_dir); add_files(sdata); if (!mld_vif) add_link_files(&sdata->deflink, sdata->vif.debugfs_dir); } void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata) { if (!sdata->vif.debugfs_dir) return; debugfs_remove_recursive(sdata->vif.debugfs_dir); sdata->vif.debugfs_dir = NULL; sdata->debugfs.subdir_stations = NULL; } void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata) { struct dentry *dir; char buf[10 + IFNAMSIZ]; dir = sdata->vif.debugfs_dir; if (IS_ERR_OR_NULL(dir)) return; sprintf(buf, "netdev:%s", sdata->name); debugfs_rename(dir->d_parent, dir, dir->d_parent, buf); } void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata, bool mld_vif) { ieee80211_debugfs_remove_netdev(sdata); ieee80211_debugfs_add_netdev(sdata, mld_vif); drv_vif_add_debugfs(sdata->local, sdata); if (!mld_vif) ieee80211_link_debugfs_drv_add(&sdata->deflink); } void ieee80211_link_debugfs_add(struct ieee80211_link_data *link) { char link_dir_name[10]; if (WARN_ON(!link->sdata->vif.debugfs_dir || link->debugfs_dir)) return; /* For now, this should not be called for non-MLO capable drivers */ if (WARN_ON(!(link->sdata->local->hw.wiphy->flags & WIPHY_FLAG_SUPPORTS_MLO))) return; snprintf(link_dir_name, sizeof(link_dir_name), "link-%d", link->link_id); link->debugfs_dir = debugfs_create_dir(link_dir_name, link->sdata->vif.debugfs_dir); DEBUGFS_ADD(link->debugfs_dir, addr); add_link_files(link, link->debugfs_dir); } void ieee80211_link_debugfs_remove(struct ieee80211_link_data *link) { if (!link->sdata->vif.debugfs_dir || !link->debugfs_dir) { link->debugfs_dir = NULL; return; } if (link->debugfs_dir == link->sdata->vif.debugfs_dir) { WARN_ON(link != &link->sdata->deflink); link->debugfs_dir = NULL; return; } debugfs_remove_recursive(link->debugfs_dir); link->debugfs_dir = NULL; } void ieee80211_link_debugfs_drv_add(struct ieee80211_link_data *link) { if (link->sdata->vif.type == NL80211_IFTYPE_MONITOR || WARN_ON(!link->debugfs_dir)) return; drv_link_add_debugfs(link->sdata->local, link->sdata, link->conf, link->debugfs_dir); } void ieee80211_link_debugfs_drv_remove(struct ieee80211_link_data *link) { if (!link || !link->debugfs_dir) return; if (WARN_ON(link->debugfs_dir == link->sdata->vif.debugfs_dir)) return; /* Recreate the directory excluding the driver data */ debugfs_remove_recursive(link->debugfs_dir); link->debugfs_dir = NULL; ieee80211_link_debugfs_add(link); } |
| 75 78 57 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_ACT_API_H #define __NET_ACT_API_H /* * Public action API for classifiers/qdiscs */ #include <linux/refcount.h> #include <net/flow_offload.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/net_namespace.h> #include <net/netns/generic.h> struct tcf_idrinfo { struct mutex lock; struct idr action_idr; struct net *net; }; struct tc_action_ops; struct tc_action { const struct tc_action_ops *ops; __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ struct tcf_idrinfo *idrinfo; u32 tcfa_index; refcount_t tcfa_refcnt; atomic_t tcfa_bindcnt; int tcfa_action; struct tcf_t tcfa_tm; struct gnet_stats_basic_sync tcfa_bstats; struct gnet_stats_basic_sync tcfa_bstats_hw; struct gnet_stats_queue tcfa_qstats; struct net_rate_estimator __rcu *tcfa_rate_est; spinlock_t tcfa_lock; struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_basic_sync __percpu *cpu_bstats_hw; struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie __rcu *user_cookie; struct tcf_chain __rcu *goto_chain; u32 tcfa_flags; u8 hw_stats; u8 used_hw_stats; bool used_hw_stats_valid; u32 in_hw_count; }; #define tcf_index common.tcfa_index #define tcf_refcnt common.tcfa_refcnt #define tcf_bindcnt common.tcfa_bindcnt #define tcf_action common.tcfa_action #define tcf_tm common.tcfa_tm #define tcf_bstats common.tcfa_bstats #define tcf_qstats common.tcfa_qstats #define tcf_rate_est common.tcfa_rate_est #define tcf_lock common.tcfa_lock #define TCA_ACT_HW_STATS_ANY (TCA_ACT_HW_STATS_IMMEDIATE | \ TCA_ACT_HW_STATS_DELAYED) /* Reserve 16 bits for user-space. See TCA_ACT_FLAGS_NO_PERCPU_STATS. */ #define TCA_ACT_FLAGS_USER_BITS 16 #define TCA_ACT_FLAGS_USER_MASK 0xffff #define TCA_ACT_FLAGS_POLICE (1U << TCA_ACT_FLAGS_USER_BITS) #define TCA_ACT_FLAGS_BIND (1U << (TCA_ACT_FLAGS_USER_BITS + 1)) #define TCA_ACT_FLAGS_REPLACE (1U << (TCA_ACT_FLAGS_USER_BITS + 2)) #define TCA_ACT_FLAGS_NO_RTNL (1U << (TCA_ACT_FLAGS_USER_BITS + 3)) #define TCA_ACT_FLAGS_AT_INGRESS (1U << (TCA_ACT_FLAGS_USER_BITS + 4)) /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. */ static inline void tcf_lastuse_update(struct tcf_t *tm) { unsigned long now = jiffies; if (tm->lastuse != now) tm->lastuse = now; if (unlikely(!tm->firstuse)) tm->firstuse = now; } static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm) { dtm->install = jiffies_to_clock_t(jiffies - stm->install); dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse); dtm->firstuse = stm->firstuse ? jiffies_to_clock_t(jiffies - stm->firstuse) : 0; dtm->expires = jiffies_to_clock_t(stm->expires); } static inline enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats) { if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY)) return FLOW_ACTION_HW_STATS_DONT_CARE; else if (!hw_stats) return FLOW_ACTION_HW_STATS_DISABLED; return hw_stats; } typedef void (*tc_action_priv_destructor)(void *priv); struct tc_action_ops { struct list_head head; char kind[IFNAMSIZ]; enum tca_id id; /* identifier should match kind */ unsigned int net_id; size_t size; struct module *owner; int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *); /* called under RCU BH lock*/ int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *); int (*lookup)(struct net *net, struct tc_action **a, u32 index); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack); int (*walk)(struct net *, struct sk_buff *, struct netlink_callback *, int, const struct tc_action_ops *, struct netlink_ext_ack *); void (*stats_update)(struct tc_action *, u64, u64, u64, u64, bool); size_t (*get_fill_size)(const struct tc_action *act); struct net_device *(*get_dev)(const struct tc_action *a, tc_action_priv_destructor *destructor); struct psample_group * (*get_psample_group)(const struct tc_action *a, tc_action_priv_destructor *destructor); int (*offload_act_setup)(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack); }; #ifdef CONFIG_NET_CLS_ACT #define ACT_P_CREATED 1 #define ACT_P_DELETED 1 struct tc_action_net { struct tcf_idrinfo *idrinfo; const struct tc_action_ops *ops; }; static inline int tc_action_net_init(struct net *net, struct tc_action_net *tn, const struct tc_action_ops *ops) { int err = 0; tn->idrinfo = kmalloc(sizeof(*tn->idrinfo), GFP_KERNEL); if (!tn->idrinfo) return -ENOMEM; tn->ops = ops; tn->idrinfo->net = net; mutex_init(&tn->idrinfo->lock); idr_init(&tn->idrinfo->action_idr); return err; } void tcf_idrinfo_destroy(const struct tc_action_ops *ops, struct tcf_idrinfo *idrinfo); static inline void tc_action_net_exit(struct list_head *net_list, unsigned int id) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { struct tc_action_net *tn = net_generic(net, id); tcf_idrinfo_destroy(tn->ops, tn->idrinfo); kfree(tn->idrinfo); } rtnl_unlock(); } int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops, struct netlink_ext_ack *extack); int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index); int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, bool cpustats, u32 flags); int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, u32 flags); void tcf_idr_insert_many(struct tc_action *actions[]); void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tc_action **a, int bind); int tcf_idr_release(struct tc_action *a, bool bind); int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_action_destroy(struct tc_action *actions[], int bind); int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, struct tc_action *actions[], int init_res[], size_t *attr_size, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack); struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police, bool rtnl_held, struct netlink_ext_ack *extack); struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, struct tc_action_ops *a_o, int *init_res, u32 flags, struct netlink_ext_ack *extack); int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, int ref, bool terse); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); static inline void tcf_action_update_bstats(struct tc_action *a, struct sk_buff *skb) { if (likely(a->cpu_bstats)) { bstats_update(this_cpu_ptr(a->cpu_bstats), skb); return; } spin_lock(&a->tcfa_lock); bstats_update(&a->tcfa_bstats, skb); spin_unlock(&a->tcfa_lock); } static inline void tcf_action_inc_drop_qstats(struct tc_action *a) { if (likely(a->cpu_qstats)) { qstats_drop_inc(this_cpu_ptr(a->cpu_qstats)); return; } spin_lock(&a->tcfa_lock); qstats_drop_inc(&a->tcfa_qstats); spin_unlock(&a->tcfa_lock); } static inline void tcf_action_inc_overlimit_qstats(struct tc_action *a) { if (likely(a->cpu_qstats)) { qstats_overlimit_inc(this_cpu_ptr(a->cpu_qstats)); return; } spin_lock(&a->tcfa_lock); qstats_overlimit_inc(&a->tcfa_qstats); spin_unlock(&a->tcfa_lock); } void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets, u64 drops, bool hw); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); int tcf_action_update_hw_stats(struct tc_action *action); int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb, void *cb_priv, bool add); int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, struct tcf_chain **handle, struct netlink_ext_ack *newchain); struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, struct tcf_chain *newchain); #ifdef CONFIG_INET DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count); #endif int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); #else /* !CONFIG_NET_CLS_ACT */ static inline int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb, void *cb_priv, bool add) { return 0; } #endif /* CONFIG_NET_CLS_ACT */ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { #ifdef CONFIG_NET_CLS_ACT if (!a->ops->stats_update) return; a->ops->stats_update(a, bytes, packets, drops, lastuse, hw); #endif } #endif |
| 13 12 155 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM vmscan #if !defined(_TRACE_VMSCAN_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_VMSCAN_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/memcontrol.h> #include <trace/events/mmflags.h> #define RECLAIM_WB_ANON 0x0001u #define RECLAIM_WB_FILE 0x0002u #define RECLAIM_WB_MIXED 0x0010u #define RECLAIM_WB_SYNC 0x0004u /* Unused, all reclaim async */ #define RECLAIM_WB_ASYNC 0x0008u #define RECLAIM_WB_LRU (RECLAIM_WB_ANON|RECLAIM_WB_FILE) #define show_reclaim_flags(flags) \ (flags) ? __print_flags(flags, "|", \ {RECLAIM_WB_ANON, "RECLAIM_WB_ANON"}, \ {RECLAIM_WB_FILE, "RECLAIM_WB_FILE"}, \ {RECLAIM_WB_MIXED, "RECLAIM_WB_MIXED"}, \ {RECLAIM_WB_SYNC, "RECLAIM_WB_SYNC"}, \ {RECLAIM_WB_ASYNC, "RECLAIM_WB_ASYNC"} \ ) : "RECLAIM_WB_NONE" #define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) #define _VMSCAN_THROTTLE_ISOLATED (1 << VMSCAN_THROTTLE_ISOLATED) #define _VMSCAN_THROTTLE_NOPROGRESS (1 << VMSCAN_THROTTLE_NOPROGRESS) #define _VMSCAN_THROTTLE_CONGESTED (1 << VMSCAN_THROTTLE_CONGESTED) #define show_throttle_flags(flags) \ (flags) ? __print_flags(flags, "|", \ {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"}, \ {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"}, \ {_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"}, \ {_VMSCAN_THROTTLE_CONGESTED, "VMSCAN_THROTTLE_CONGESTED"} \ ) : "VMSCAN_THROTTLE_NONE" #define trace_reclaim_flags(file) ( \ (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ (RECLAIM_WB_ASYNC) \ ) TRACE_EVENT(mm_vmscan_kswapd_sleep, TP_PROTO(int nid), TP_ARGS(nid), TP_STRUCT__entry( __field( int, nid ) ), TP_fast_assign( __entry->nid = nid; ), TP_printk("nid=%d", __entry->nid) ); TRACE_EVENT(mm_vmscan_kswapd_wake, TP_PROTO(int nid, int zid, int order), TP_ARGS(nid, zid, order), TP_STRUCT__entry( __field( int, nid ) __field( int, zid ) __field( int, order ) ), TP_fast_assign( __entry->nid = nid; __entry->zid = zid; __entry->order = order; ), TP_printk("nid=%d order=%d", __entry->nid, __entry->order) ); TRACE_EVENT(mm_vmscan_wakeup_kswapd, TP_PROTO(int nid, int zid, int order, gfp_t gfp_flags), TP_ARGS(nid, zid, order, gfp_flags), TP_STRUCT__entry( __field( int, nid ) __field( int, zid ) __field( int, order ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->nid = nid; __entry->zid = zid; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", __entry->nid, __entry->order, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template, TP_PROTO(int order, gfp_t gfp_flags), TP_ARGS(order, gfp_flags), TP_STRUCT__entry( __field( int, order ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("order=%d gfp_flags=%s", __entry->order, show_gfp_flags(__entry->gfp_flags)) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin, TP_PROTO(int order, gfp_t gfp_flags), TP_ARGS(order, gfp_flags) ); #ifdef CONFIG_MEMCG DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin, TP_PROTO(int order, gfp_t gfp_flags), TP_ARGS(order, gfp_flags) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin, TP_PROTO(int order, gfp_t gfp_flags), TP_ARGS(order, gfp_flags) ); #endif /* CONFIG_MEMCG */ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template, TP_PROTO(unsigned long nr_reclaimed), TP_ARGS(nr_reclaimed), TP_STRUCT__entry( __field( unsigned long, nr_reclaimed ) ), TP_fast_assign( __entry->nr_reclaimed = nr_reclaimed; ), TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end, TP_PROTO(unsigned long nr_reclaimed), TP_ARGS(nr_reclaimed) ); #ifdef CONFIG_MEMCG DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end, TP_PROTO(unsigned long nr_reclaimed), TP_ARGS(nr_reclaimed) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end, TP_PROTO(unsigned long nr_reclaimed), TP_ARGS(nr_reclaimed) ); #endif /* CONFIG_MEMCG */ TRACE_EVENT(mm_shrink_slab_start, TP_PROTO(struct shrinker *shr, struct shrink_control *sc, long nr_objects_to_shrink, unsigned long cache_items, unsigned long long delta, unsigned long total_scan, int priority), TP_ARGS(shr, sc, nr_objects_to_shrink, cache_items, delta, total_scan, priority), TP_STRUCT__entry( __field(struct shrinker *, shr) __field(void *, shrink) __field(int, nid) __field(long, nr_objects_to_shrink) __field(unsigned long, gfp_flags) __field(unsigned long, cache_items) __field(unsigned long long, delta) __field(unsigned long, total_scan) __field(int, priority) ), TP_fast_assign( __entry->shr = shr; __entry->shrink = shr->scan_objects; __entry->nid = sc->nid; __entry->nr_objects_to_shrink = nr_objects_to_shrink; __entry->gfp_flags = (__force unsigned long)sc->gfp_mask; __entry->cache_items = cache_items; __entry->delta = delta; __entry->total_scan = total_scan; __entry->priority = priority; ), TP_printk("%pS %p: nid: %d objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d", __entry->shrink, __entry->shr, __entry->nid, __entry->nr_objects_to_shrink, show_gfp_flags(__entry->gfp_flags), __entry->cache_items, __entry->delta, __entry->total_scan, __entry->priority) ); TRACE_EVENT(mm_shrink_slab_end, TP_PROTO(struct shrinker *shr, int nid, int shrinker_retval, long unused_scan_cnt, long new_scan_cnt, long total_scan), TP_ARGS(shr, nid, shrinker_retval, unused_scan_cnt, new_scan_cnt, total_scan), TP_STRUCT__entry( __field(struct shrinker *, shr) __field(int, nid) __field(void *, shrink) __field(long, unused_scan) __field(long, new_scan) __field(int, retval) __field(long, total_scan) ), TP_fast_assign( __entry->shr = shr; __entry->nid = nid; __entry->shrink = shr->scan_objects; __entry->unused_scan = unused_scan_cnt; __entry->new_scan = new_scan_cnt; __entry->retval = shrinker_retval; __entry->total_scan = total_scan; ), TP_printk("%pS %p: nid: %d unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d", __entry->shrink, __entry->shr, __entry->nid, __entry->unused_scan, __entry->new_scan, __entry->total_scan, __entry->retval) ); TRACE_EVENT(mm_vmscan_lru_isolate, TP_PROTO(int highest_zoneidx, int order, unsigned long nr_requested, unsigned long nr_scanned, unsigned long nr_skipped, unsigned long nr_taken, int lru), TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, lru), TP_STRUCT__entry( __field(int, highest_zoneidx) __field(int, order) __field(unsigned long, nr_requested) __field(unsigned long, nr_scanned) __field(unsigned long, nr_skipped) __field(unsigned long, nr_taken) __field(int, lru) ), TP_fast_assign( __entry->highest_zoneidx = highest_zoneidx; __entry->order = order; __entry->nr_requested = nr_requested; __entry->nr_scanned = nr_scanned; __entry->nr_skipped = nr_skipped; __entry->nr_taken = nr_taken; __entry->lru = lru; ), /* * classzone is previous name of the highest_zoneidx. * Reason not to change it is the ABI requirement of the tracepoint. */ TP_printk("classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s", __entry->highest_zoneidx, __entry->order, __entry->nr_requested, __entry->nr_scanned, __entry->nr_skipped, __entry->nr_taken, __print_symbolic(__entry->lru, LRU_NAMES)) ); TRACE_EVENT(mm_vmscan_write_folio, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(unsigned long, pfn) __field(int, reclaim_flags) ), TP_fast_assign( __entry->pfn = folio_pfn(folio); __entry->reclaim_flags = trace_reclaim_flags( folio_is_file_lru(folio)); ), TP_printk("page=%p pfn=0x%lx flags=%s", pfn_to_page(__entry->pfn), __entry->pfn, show_reclaim_flags(__entry->reclaim_flags)) ); TRACE_EVENT(mm_vmscan_lru_shrink_inactive, TP_PROTO(int nid, unsigned long nr_scanned, unsigned long nr_reclaimed, struct reclaim_stat *stat, int priority, int file), TP_ARGS(nid, nr_scanned, nr_reclaimed, stat, priority, file), TP_STRUCT__entry( __field(int, nid) __field(unsigned long, nr_scanned) __field(unsigned long, nr_reclaimed) __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, nr_congested) __field(unsigned long, nr_immediate) __field(unsigned int, nr_activate0) __field(unsigned int, nr_activate1) __field(unsigned long, nr_ref_keep) __field(unsigned long, nr_unmap_fail) __field(int, priority) __field(int, reclaim_flags) ), TP_fast_assign( __entry->nid = nid; __entry->nr_scanned = nr_scanned; __entry->nr_reclaimed = nr_reclaimed; __entry->nr_dirty = stat->nr_dirty; __entry->nr_writeback = stat->nr_writeback; __entry->nr_congested = stat->nr_congested; __entry->nr_immediate = stat->nr_immediate; __entry->nr_activate0 = stat->nr_activate[0]; __entry->nr_activate1 = stat->nr_activate[1]; __entry->nr_ref_keep = stat->nr_ref_keep; __entry->nr_unmap_fail = stat->nr_unmap_fail; __entry->priority = priority; __entry->reclaim_flags = trace_reclaim_flags(file); ), TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld nr_dirty=%ld nr_writeback=%ld nr_congested=%ld nr_immediate=%ld nr_activate_anon=%d nr_activate_file=%d nr_ref_keep=%ld nr_unmap_fail=%ld priority=%d flags=%s", __entry->nid, __entry->nr_scanned, __entry->nr_reclaimed, __entry->nr_dirty, __entry->nr_writeback, __entry->nr_congested, __entry->nr_immediate, __entry->nr_activate0, __entry->nr_activate1, __entry->nr_ref_keep, __entry->nr_unmap_fail, __entry->priority, show_reclaim_flags(__entry->reclaim_flags)) ); TRACE_EVENT(mm_vmscan_lru_shrink_active, TP_PROTO(int nid, unsigned long nr_taken, unsigned long nr_active, unsigned long nr_deactivated, unsigned long nr_referenced, int priority, int file), TP_ARGS(nid, nr_taken, nr_active, nr_deactivated, nr_referenced, priority, file), TP_STRUCT__entry( __field(int, nid) __field(unsigned long, nr_taken) __field(unsigned long, nr_active) __field(unsigned long, nr_deactivated) __field(unsigned long, nr_referenced) __field(int, priority) __field(int, reclaim_flags) ), TP_fast_assign( __entry->nid = nid; __entry->nr_taken = nr_taken; __entry->nr_active = nr_active; __entry->nr_deactivated = nr_deactivated; __entry->nr_referenced = nr_referenced; __entry->priority = priority; __entry->reclaim_flags = trace_reclaim_flags(file); ), TP_printk("nid=%d nr_taken=%ld nr_active=%ld nr_deactivated=%ld nr_referenced=%ld priority=%d flags=%s", __entry->nid, __entry->nr_taken, __entry->nr_active, __entry->nr_deactivated, __entry->nr_referenced, __entry->priority, show_reclaim_flags(__entry->reclaim_flags)) ); TRACE_EVENT(mm_vmscan_node_reclaim_begin, TP_PROTO(int nid, int order, gfp_t gfp_flags), TP_ARGS(nid, order, gfp_flags), TP_STRUCT__entry( __field(int, nid) __field(int, order) __field(unsigned long, gfp_flags) ), TP_fast_assign( __entry->nid = nid; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", __entry->nid, __entry->order, show_gfp_flags(__entry->gfp_flags)) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_node_reclaim_end, TP_PROTO(unsigned long nr_reclaimed), TP_ARGS(nr_reclaimed) ); TRACE_EVENT(mm_vmscan_throttled, TP_PROTO(int nid, int usec_timeout, int usec_delayed, int reason), TP_ARGS(nid, usec_timeout, usec_delayed, reason), TP_STRUCT__entry( __field(int, nid) __field(int, usec_timeout) __field(int, usec_delayed) __field(int, reason) ), TP_fast_assign( __entry->nid = nid; __entry->usec_timeout = usec_timeout; __entry->usec_delayed = usec_delayed; __entry->reason = 1U << reason; ), TP_printk("nid=%d usec_timeout=%d usect_delayed=%d reason=%s", __entry->nid, __entry->usec_timeout, __entry->usec_delayed, show_throttle_flags(__entry->reason)) ); #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 36 13 13 13 22 22 12 22 21 1 22 22 4453 1 1 1 1 1 1 1 1 1 22 22 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * NOHZ implementation for low and high resolution timers * * Started by: Thomas Gleixner and Ingo Molnar */ #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/percpu.h> #include <linux/nmi.h> #include <linux/profile.h> #include <linux/sched/signal.h> #include <linux/sched/clock.h> #include <linux/sched/stat.h> #include <linux/sched/nohz.h> #include <linux/sched/loadavg.h> #include <linux/module.h> #include <linux/irq_work.h> #include <linux/posix-timers.h> #include <linux/context_tracking.h> #include <linux/mm.h> #include <asm/irq_regs.h> #include "tick-internal.h" #include <trace/events/timer.h> /* * Per-CPU nohz control structure */ static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); struct tick_sched *tick_get_tick_sched(int cpu) { return &per_cpu(tick_cpu_sched, cpu); } #if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) /* * The time when the last jiffy update happened. Write access must hold * jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a * consistent view of jiffies and last_jiffies_update. */ static ktime_t last_jiffies_update; /* * Must be called with interrupts disabled ! */ static void tick_do_update_jiffies64(ktime_t now) { unsigned long ticks = 1; ktime_t delta, nextp; /* * 64-bit can do a quick check without holding the jiffies lock and * without looking at the sequence count. The smp_load_acquire() * pairs with the update done later in this function. * * 32-bit cannot do that because the store of 'tick_next_period' * consists of two 32-bit stores, and the first store could be * moved by the CPU to a random point in the future. */ if (IS_ENABLED(CONFIG_64BIT)) { if (ktime_before(now, smp_load_acquire(&tick_next_period))) return; } else { unsigned int seq; /* * Avoid contention on 'jiffies_lock' and protect the quick * check with the sequence count. */ do { seq = read_seqcount_begin(&jiffies_seq); nextp = tick_next_period; } while (read_seqcount_retry(&jiffies_seq, seq)); if (ktime_before(now, nextp)) return; } /* Quick check failed, i.e. update is required. */ raw_spin_lock(&jiffies_lock); /* * Re-evaluate with the lock held. Another CPU might have done the * update already. */ if (ktime_before(now, tick_next_period)) { raw_spin_unlock(&jiffies_lock); return; } write_seqcount_begin(&jiffies_seq); delta = ktime_sub(now, tick_next_period); if (unlikely(delta >= TICK_NSEC)) { /* Slow path for long idle sleep times */ s64 incr = TICK_NSEC; ticks += ktime_divns(delta, incr); last_jiffies_update = ktime_add_ns(last_jiffies_update, incr * ticks); } else { last_jiffies_update = ktime_add_ns(last_jiffies_update, TICK_NSEC); } /* Advance jiffies to complete the 'jiffies_seq' protected job */ jiffies_64 += ticks; /* Keep the tick_next_period variable up to date */ nextp = ktime_add_ns(last_jiffies_update, TICK_NSEC); if (IS_ENABLED(CONFIG_64BIT)) { /* * Pairs with smp_load_acquire() in the lockless quick * check above, and ensures that the update to 'jiffies_64' is * not reordered vs. the store to 'tick_next_period', neither * by the compiler nor by the CPU. */ smp_store_release(&tick_next_period, nextp); } else { /* * A plain store is good enough on 32-bit, as the quick check * above is protected by the sequence count. */ tick_next_period = nextp; } /* * Release the sequence count. calc_global_load() below is not * protected by it, but 'jiffies_lock' needs to be held to prevent * concurrent invocations. */ write_seqcount_end(&jiffies_seq); calc_global_load(); raw_spin_unlock(&jiffies_lock); update_wall_time(); } /* * Initialize and return retrieve the jiffies update. */ static ktime_t tick_init_jiffy_update(void) { ktime_t period; raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); /* Have we started the jiffies update yet ? */ if (last_jiffies_update == 0) { u32 rem; /* * Ensure that the tick is aligned to a multiple of * TICK_NSEC. */ div_u64_rem(tick_next_period, TICK_NSEC, &rem); if (rem) tick_next_period += TICK_NSEC - rem; last_jiffies_update = tick_next_period; } period = last_jiffies_update; write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); return period; } #define MAX_STALLED_JIFFIES 5 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { int cpu = smp_processor_id(); #ifdef CONFIG_NO_HZ_COMMON /* * Check if the do_timer duty was dropped. We don't care about * concurrency: This happens only when the CPU in charge went * into a long sleep. If two CPUs happen to assign themselves to * this duty, then the jiffies update is still serialized by * 'jiffies_lock'. * * If nohz_full is enabled, this should not happen because the * 'tick_do_timer_cpu' CPU never relinquishes. */ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL WARN_ON_ONCE(tick_nohz_full_running); #endif tick_do_timer_cpu = cpu; } #endif /* Check if jiffies need an update */ if (tick_do_timer_cpu == cpu) tick_do_update_jiffies64(now); /* * If the jiffies update stalled for too long (timekeeper in stop_machine() * or VMEXIT'ed for several msecs), force an update. */ if (ts->last_tick_jiffies != jiffies) { ts->stalled_jiffies = 0; ts->last_tick_jiffies = READ_ONCE(jiffies); } else { if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) { tick_do_update_jiffies64(now); ts->stalled_jiffies = 0; ts->last_tick_jiffies = READ_ONCE(jiffies); } } if (ts->inidle) ts->got_idle_tick = 1; } static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) { #ifdef CONFIG_NO_HZ_COMMON /* * When we are idle and the tick is stopped, we have to touch * the watchdog as we might not schedule for a really long * time. This happens on completely idle SMP systems while * waiting on the login prompt. We also increment the "start of * idle" jiffy stamp so the idle accounting adjustment we do * when we go busy again does not account too many ticks. */ if (ts->tick_stopped) { touch_softlockup_watchdog_sched(); if (is_idle_task(current)) ts->idle_jiffies++; /* * In case the current tick fired too early past its expected * expiration, make sure we don't bypass the next clock reprogramming * to the same deadline. */ ts->next_tick = 0; } #endif update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); } #endif #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; EXPORT_SYMBOL_GPL(tick_nohz_full_mask); bool tick_nohz_full_running; EXPORT_SYMBOL_GPL(tick_nohz_full_running); static atomic_t tick_dep_mask; static bool check_tick_dependency(atomic_t *dep) { int val = atomic_read(dep); if (val & TICK_DEP_MASK_POSIX_TIMER) { trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER); return true; } if (val & TICK_DEP_MASK_PERF_EVENTS) { trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS); return true; } if (val & TICK_DEP_MASK_SCHED) { trace_tick_stop(0, TICK_DEP_MASK_SCHED); return true; } if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) { trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE); return true; } if (val & TICK_DEP_MASK_RCU) { trace_tick_stop(0, TICK_DEP_MASK_RCU); return true; } if (val & TICK_DEP_MASK_RCU_EXP) { trace_tick_stop(0, TICK_DEP_MASK_RCU_EXP); return true; } return false; } static bool can_stop_full_tick(int cpu, struct tick_sched *ts) { lockdep_assert_irqs_disabled(); if (unlikely(!cpu_online(cpu))) return false; if (check_tick_dependency(&tick_dep_mask)) return false; if (check_tick_dependency(&ts->tick_dep_mask)) return false; if (check_tick_dependency(¤t->tick_dep_mask)) return false; if (check_tick_dependency(¤t->signal->tick_dep_mask)) return false; return true; } static void nohz_full_kick_func(struct irq_work *work) { /* Empty, the tick restart happens on tick_nohz_irq_exit() */ } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = IRQ_WORK_INIT_HARD(nohz_full_kick_func); /* * Kick this CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(), * is NMI safe. */ static void tick_nohz_full_kick(void) { if (!tick_nohz_full_cpu(smp_processor_id())) return; irq_work_queue(this_cpu_ptr(&nohz_full_kick_work)); } /* * Kick the CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. */ void tick_nohz_full_kick_cpu(int cpu) { if (!tick_nohz_full_cpu(cpu)) return; irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); } static void tick_nohz_kick_task(struct task_struct *tsk) { int cpu; /* * If the task is not running, run_posix_cpu_timers() * has nothing to elapse, and an IPI can then be optimized out. * * activate_task() STORE p->tick_dep_mask * STORE p->on_rq * __schedule() (switch to task 'p') smp_mb() (atomic_fetch_or()) * LOCK rq->lock LOAD p->on_rq * smp_mb__after_spin_lock() * tick_nohz_task_switch() * LOAD p->tick_dep_mask */ if (!sched_task_on_rq(tsk)) return; /* * If the task concurrently migrates to another CPU, * we guarantee it sees the new tick dependency upon * schedule. * * set_task_cpu(p, cpu); * STORE p->cpu = @cpu * __schedule() (switch to task 'p') * LOCK rq->lock * smp_mb__after_spin_lock() STORE p->tick_dep_mask * tick_nohz_task_switch() smp_mb() (atomic_fetch_or()) * LOAD p->tick_dep_mask LOAD p->cpu */ cpu = task_cpu(tsk); preempt_disable(); if (cpu_online(cpu)) tick_nohz_full_kick_cpu(cpu); preempt_enable(); } /* * Kick all full dynticks CPUs in order to force these to re-evaluate * their dependency on the tick and restart it if necessary. */ static void tick_nohz_full_kick_all(void) { int cpu; if (!tick_nohz_full_running) return; preempt_disable(); for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask) tick_nohz_full_kick_cpu(cpu); preempt_enable(); } static void tick_nohz_dep_set_all(atomic_t *dep, enum tick_dep_bits bit) { int prev; prev = atomic_fetch_or(BIT(bit), dep); if (!prev) tick_nohz_full_kick_all(); } /* * Set a global tick dependency. Used by perf events that rely on freq and * unstable clocks. */ void tick_nohz_dep_set(enum tick_dep_bits bit) { tick_nohz_dep_set_all(&tick_dep_mask, bit); } void tick_nohz_dep_clear(enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &tick_dep_mask); } /* * Set per-CPU tick dependency. Used by scheduler and perf events in order to * manage event-throttling. */ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { int prev; struct tick_sched *ts; ts = per_cpu_ptr(&tick_cpu_sched, cpu); prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask); if (!prev) { preempt_disable(); /* Perf needs local kick that is NMI safe */ if (cpu == smp_processor_id()) { tick_nohz_full_kick(); } else { /* Remote IRQ work not NMI-safe */ if (!WARN_ON_ONCE(in_nmi())) tick_nohz_full_kick_cpu(cpu); } preempt_enable(); } } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu); void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); atomic_andnot(BIT(bit), &ts->tick_dep_mask); } EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu); /* * Set a per-task tick dependency. RCU needs this. Also posix CPU timers * in order to elapse per task timers. */ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask)) tick_nohz_kick_task(tsk); } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task); void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &tsk->tick_dep_mask); } EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task); /* * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse * per process timers. */ void tick_nohz_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { int prev; struct signal_struct *sig = tsk->signal; prev = atomic_fetch_or(BIT(bit), &sig->tick_dep_mask); if (!prev) { struct task_struct *t; lockdep_assert_held(&tsk->sighand->siglock); __for_each_thread(sig, t) tick_nohz_kick_task(t); } } void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &sig->tick_dep_mask); } /* * Re-evaluate the need for the tick as we switch the current task. * It might need the tick due to per task/process properties: * perf events, posix CPU timers, ... */ void __tick_nohz_task_switch(void) { struct tick_sched *ts; if (!tick_nohz_full_cpu(smp_processor_id())) return; ts = this_cpu_ptr(&tick_cpu_sched); if (ts->tick_stopped) { if (atomic_read(¤t->tick_dep_mask) || atomic_read(¤t->signal->tick_dep_mask)) tick_nohz_full_kick(); } } /* Get the boot-time nohz CPU list from the kernel parameters. */ void __init tick_nohz_full_setup(cpumask_var_t cpumask) { alloc_bootmem_cpumask_var(&tick_nohz_full_mask); cpumask_copy(tick_nohz_full_mask, cpumask); tick_nohz_full_running = true; } bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { /* * The 'tick_do_timer_cpu' CPU handles housekeeping duty (unbound * timers, workqueues, timekeeping, ...) on behalf of full dynticks * CPUs. It must remain online when nohz full is enabled. */ if (tick_nohz_full_running && tick_do_timer_cpu == cpu) return false; return true; } static int tick_nohz_cpu_down(unsigned int cpu) { return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY; } void __init tick_nohz_init(void) { int cpu, ret; if (!tick_nohz_full_running) return; /* * Full dynticks uses IRQ work to drive the tick rescheduling on safe * locking contexts. But then we need IRQ work to raise its own * interrupts to avoid circular dependency on the tick. */ if (!arch_irq_work_has_interrupt()) { pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support IRQ work self-IPIs\n"); cpumask_clear(tick_nohz_full_mask); tick_nohz_full_running = false; return; } if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) && !IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) { cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { pr_warn("NO_HZ: Clearing %d from nohz_full range " "for timekeeping\n", cpu); cpumask_clear_cpu(cpu, tick_nohz_full_mask); } } for_each_cpu(cpu, tick_nohz_full_mask) ct_cpu_track_user(cpu); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "kernel/nohz:predown", NULL, tick_nohz_cpu_down); WARN_ON(ret < 0); pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", cpumask_pr_args(tick_nohz_full_mask)); } #endif /* * NOHZ - aka dynamic tick functionality */ #ifdef CONFIG_NO_HZ_COMMON /* * NO HZ enabled ? */ bool tick_nohz_enabled __read_mostly = true; unsigned long tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ static int __init setup_tick_nohz(char *str) { return (kstrtobool(str, &tick_nohz_enabled) == 0); } __setup("nohz=", setup_tick_nohz); bool tick_nohz_tick_stopped(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); return ts->tick_stopped; } bool tick_nohz_tick_stopped_cpu(int cpu) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); return ts->tick_stopped; } /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted * * Called from interrupt entry when the CPU was idle * * In case the sched_tick was stopped on this CPU, we have to check if jiffies * must be updated. Otherwise an interrupt handler could use a stale jiffy * value. We do this unconditionally on any CPU, as we don't know whether the * CPU, which has the update task assigned, is in a long sleep. */ static void tick_nohz_update_jiffies(ktime_t now) { unsigned long flags; __this_cpu_write(tick_cpu_sched.idle_waketime, now); local_irq_save(flags); tick_do_update_jiffies64(now); local_irq_restore(flags); touch_softlockup_watchdog_sched(); } static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) { ktime_t delta; if (WARN_ON_ONCE(!ts->idle_active)) return; delta = ktime_sub(now, ts->idle_entrytime); write_seqcount_begin(&ts->idle_sleeptime_seq); if (nr_iowait_cpu(smp_processor_id()) > 0) ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta); else ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); ts->idle_entrytime = now; ts->idle_active = 0; write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_wakeup_event(); } static void tick_nohz_start_idle(struct tick_sched *ts) { write_seqcount_begin(&ts->idle_sleeptime_seq); ts->idle_entrytime = ktime_get(); ts->idle_active = 1; write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_sleep_event(); } static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, bool compute_delta, u64 *last_update_time) { ktime_t now, idle; unsigned int seq; if (!tick_nohz_active) return -1; now = ktime_get(); if (last_update_time) *last_update_time = ktime_to_us(now); do { seq = read_seqcount_begin(&ts->idle_sleeptime_seq); if (ts->idle_active && compute_delta) { ktime_t delta = ktime_sub(now, ts->idle_entrytime); idle = ktime_add(*sleeptime, delta); } else { idle = *sleeptime; } } while (read_seqcount_retry(&ts->idle_sleeptime_seq, seq)); return ktime_to_us(idle); } /** * get_cpu_idle_time_us - get the total idle time of a CPU * @cpu: CPU number to query * @last_update_time: variable to store update time in. Do not update * counters if NULL. * * Return the cumulative idle time (since boot) for a given * CPU, in microseconds. Note that this is partially broken due to * the counter of iowait tasks that can be remotely updated without * any synchronization. Therefore it is possible to observe backward * values within two consecutive reads. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * * This function returns -1 if NOHZ is not enabled. */ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); return get_cpu_sleep_time_us(ts, &ts->idle_sleeptime, !nr_iowait_cpu(cpu), last_update_time); } EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); /** * get_cpu_iowait_time_us - get the total iowait time of a CPU * @cpu: CPU number to query * @last_update_time: variable to store update time in. Do not update * counters if NULL. * * Return the cumulative iowait time (since boot) for a given * CPU, in microseconds. Note this is partially broken due to * the counter of iowait tasks that can be remotely updated without * any synchronization. Therefore it is possible to observe backward * values within two consecutive reads. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * * This function returns -1 if NOHZ is not enabled. */ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); return get_cpu_sleep_time_us(ts, &ts->iowait_sleeptime, nr_iowait_cpu(cpu), last_update_time); } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) { hrtimer_cancel(&ts->sched_timer); hrtimer_set_expires(&ts->sched_timer, ts->last_tick); /* Forward the time to expire in the future */ hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); } else { tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } /* * Reset to make sure the next tick stop doesn't get fooled by past * cached clock deadline. */ ts->next_tick = 0; } static inline bool local_timer_softirq_pending(void) { return local_softirq_pending() & BIT(TIMER_SOFTIRQ); } static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { u64 basemono, next_tick, delta, expires; unsigned long basejiff; unsigned int seq; /* Read jiffies and the time when jiffies were updated last */ do { seq = read_seqcount_begin(&jiffies_seq); basemono = last_jiffies_update; basejiff = jiffies; } while (read_seqcount_retry(&jiffies_seq, seq)); ts->last_jiffies = basejiff; ts->timer_expires_base = basemono; /* * Keep the periodic tick, when RCU, architecture or irq_work * requests it. * Aside of that, check whether the local timer softirq is * pending. If so, its a bad idea to call get_next_timer_interrupt(), * because there is an already expired timer, so it will request * immediate expiry, which rearms the hardware timer with a * minimal delta, which brings us back to this place * immediately. Lather, rinse and repeat... */ if (rcu_needs_cpu() || arch_needs_cpu() || irq_work_needs_cpu() || local_timer_softirq_pending()) { next_tick = basemono + TICK_NSEC; } else { /* * Get the next pending timer. If high resolution * timers are enabled this only takes the timer wheel * timers into account. If high resolution timers are * disabled this also looks at the next expiring * hrtimer. */ next_tick = get_next_timer_interrupt(basejiff, basemono); ts->next_timer = next_tick; } /* * If the tick is due in the next period, keep it ticking or * force prod the timer. */ delta = next_tick - basemono; if (delta <= (u64)TICK_NSEC) { /* * Tell the timer code that the base is not idle, i.e. undo * the effect of get_next_timer_interrupt(): */ timer_clear_idle(); /* * We've not stopped the tick yet, and there's a timer in the * next period, so no point in stopping it either, bail. */ if (!ts->tick_stopped) { ts->timer_expires = 0; goto out; } } /* * If this CPU is the one which had the do_timer() duty last, we limit * the sleep time to the timekeeping 'max_deferment' value. * Otherwise we can sleep as long as we want. */ delta = timekeeping_max_deferment(); if (cpu != tick_do_timer_cpu && (tick_do_timer_cpu != TICK_DO_TIMER_NONE || !ts->do_timer_last)) delta = KTIME_MAX; /* Calculate the next expiry time */ if (delta < (KTIME_MAX - basemono)) expires = basemono + delta; else expires = KTIME_MAX; ts->timer_expires = min_t(u64, expires, next_tick); out: return ts->timer_expires; } static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); u64 basemono = ts->timer_expires_base; u64 expires = ts->timer_expires; ktime_t tick = expires; /* Make sure we won't be trying to stop it twice in a row. */ ts->timer_expires_base = 0; /* * If this CPU is the one which updates jiffies, then give up * the assignment and let it be taken by the CPU which runs * the tick timer next, which might be this CPU as well. If we * don't drop this here, the jiffies might be stale and * do_timer() never gets invoked. Keep track of the fact that it * was the one which had the do_timer() duty last. */ if (cpu == tick_do_timer_cpu) { tick_do_timer_cpu = TICK_DO_TIMER_NONE; ts->do_timer_last = 1; } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { ts->do_timer_last = 0; } /* Skip reprogram of event if it's not changed */ if (ts->tick_stopped && (expires == ts->next_tick)) { /* Sanity check: make sure clockevent is actually programmed */ if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) return; WARN_ON_ONCE(1); printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n", basemono, ts->next_tick, dev->next_event, hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer)); } /* * nohz_stop_sched_tick() can be called several times before * nohz_restart_sched_tick() is called. This happens when * interrupts arrive which do not cause a reschedule. In the * first call we save the current tick time, so we can restart * the scheduler tick in nohz_restart_sched_tick(). */ if (!ts->tick_stopped) { calc_load_nohz_start(); quiet_vmstat(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; trace_tick_stop(1, TICK_DEP_MASK_NONE); } ts->next_tick = tick; /* * If the expiration time == KTIME_MAX, then we simply stop * the tick timer. */ if (unlikely(expires == KTIME_MAX)) { if (ts->nohz_mode == NOHZ_MODE_HIGHRES) hrtimer_cancel(&ts->sched_timer); else tick_program_event(KTIME_MAX, 1); return; } if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED_HARD); } else { hrtimer_set_expires(&ts->sched_timer, tick); tick_program_event(tick, 1); } } static void tick_nohz_retain_tick(struct tick_sched *ts) { ts->timer_expires_base = 0; } #ifdef CONFIG_NO_HZ_FULL static void tick_nohz_stop_sched_tick(struct tick_sched *ts, int cpu) { if (tick_nohz_next_event(ts, cpu)) tick_nohz_stop_tick(ts, cpu); else tick_nohz_retain_tick(ts); } #endif /* CONFIG_NO_HZ_FULL */ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ tick_do_update_jiffies64(now); /* * Clear the timer idle flag, so we avoid IPIs on remote queueing and * the clock forward checks in the enqueue path: */ timer_clear_idle(); calc_load_nohz_stop(); touch_softlockup_watchdog_sched(); /* Cancel the scheduled timer and restore the tick: */ ts->tick_stopped = 0; tick_nohz_restart(ts, now); } static void __tick_nohz_full_update_tick(struct tick_sched *ts, ktime_t now) { #ifdef CONFIG_NO_HZ_FULL int cpu = smp_processor_id(); if (can_stop_full_tick(cpu, ts)) tick_nohz_stop_sched_tick(ts, cpu); else if (ts->tick_stopped) tick_nohz_restart_sched_tick(ts, now); #endif } static void tick_nohz_full_update_tick(struct tick_sched *ts) { if (!tick_nohz_full_cpu(smp_processor_id())) return; if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) return; __tick_nohz_full_update_tick(ts, ktime_get()); } /* * A pending softirq outside an IRQ (or softirq disabled section) context * should be waiting for ksoftirqd to handle it. Therefore we shouldn't * reach this code due to the need_resched() early check in can_stop_idle_tick(). * * However if we are between CPUHP_AP_SMPBOOT_THREADS and CPU_TEARDOWN_CPU on the * cpu_down() process, softirqs can still be raised while ksoftirqd is parked, * triggering the code below, since wakep_softirqd() is ignored. * */ static bool report_idle_softirq(void) { static int ratelimit; unsigned int pending = local_softirq_pending(); if (likely(!pending)) return false; /* Some softirqs claim to be safe against hotplug and ksoftirqd parking */ if (!cpu_active(smp_processor_id())) { pending &= ~SOFTIRQ_HOTPLUG_SAFE_MASK; if (!pending) return false; } if (ratelimit >= 10) return false; /* On RT, softirq handling may be waiting on some lock */ if (local_bh_blocked()) return false; pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n", pending); ratelimit++; return true; } static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) { /* * If this CPU is offline and it is the one which updates * jiffies, then give up the assignment and let it be taken by * the CPU which runs the tick timer next. If we don't drop * this here, the jiffies might be stale and do_timer() never * gets invoked. */ if (unlikely(!cpu_online(cpu))) { if (cpu == tick_do_timer_cpu) tick_do_timer_cpu = TICK_DO_TIMER_NONE; /* * Make sure the CPU doesn't get fooled by obsolete tick * deadline if it comes back online later. */ ts->next_tick = 0; return false; } if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) return false; if (need_resched()) return false; if (unlikely(report_idle_softirq())) return false; if (tick_nohz_full_enabled()) { /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around */ if (tick_do_timer_cpu == cpu) return false; /* Should not happen for nohz-full */ if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) return false; } return true; } /** * tick_nohz_idle_stop_tick - stop the idle tick from the idle task * * When the next event is more than a tick into the future, stop the idle tick */ void tick_nohz_idle_stop_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); int cpu = smp_processor_id(); ktime_t expires; /* * If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the * tick timer expiration time is known already. */ if (ts->timer_expires_base) expires = ts->timer_expires; else if (can_stop_idle_tick(cpu, ts)) expires = tick_nohz_next_event(ts, cpu); else return; ts->idle_calls++; if (expires > 0LL) { int was_stopped = ts->tick_stopped; tick_nohz_stop_tick(ts, cpu); ts->idle_sleeps++; ts->idle_expires = expires; if (!was_stopped && ts->tick_stopped) { ts->idle_jiffies = ts->last_jiffies; nohz_balance_enter_idle(cpu); } } else { tick_nohz_retain_tick(ts); } } void tick_nohz_idle_retain_tick(void) { tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched)); /* * Undo the effect of get_next_timer_interrupt() called from * tick_nohz_next_event(). */ timer_clear_idle(); } /** * tick_nohz_idle_enter - prepare for entering idle on the current CPU * * Called when we start the idle loop. */ void tick_nohz_idle_enter(void) { struct tick_sched *ts; lockdep_assert_irqs_enabled(); local_irq_disable(); ts = this_cpu_ptr(&tick_cpu_sched); WARN_ON_ONCE(ts->timer_expires_base); ts->inidle = 1; tick_nohz_start_idle(ts); local_irq_enable(); } /** * tick_nohz_irq_exit - Notify the tick about IRQ exit * * A timer may have been added/modified/deleted either by the current IRQ, * or by another place using this IRQ as a notification. This IRQ may have * also updated the RCU callback list. These events may require a * re-evaluation of the next tick. Depending on the context: * * 1) If the CPU is idle and no resched is pending, just proceed with idle * time accounting. The next tick will be re-evaluated on the next idle * loop iteration. * * 2) If the CPU is nohz_full: * * 2.1) If there is any tick dependency, restart the tick if stopped. * * 2.2) If there is no tick dependency, (re-)evaluate the next tick and * stop/update it accordingly. */ void tick_nohz_irq_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->inidle) tick_nohz_start_idle(ts); else tick_nohz_full_update_tick(ts); } /** * tick_nohz_idle_got_tick - Check whether or not the tick handler has run */ bool tick_nohz_idle_got_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->got_idle_tick) { ts->got_idle_tick = 0; return true; } return false; } /** * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer * or the tick, whichever expires first. Note that, if the tick has been * stopped, it returns the next hrtimer. * * Called from power state control code with interrupts disabled */ ktime_t tick_nohz_get_next_hrtimer(void) { return __this_cpu_read(tick_cpu_device.evtdev)->next_event; } /** * tick_nohz_get_sleep_length - return the expected length of the current sleep * @delta_next: duration until the next event if the tick cannot be stopped * * Called from power state control code with interrupts disabled. * * The return value of this function and/or the value returned by it through the * @delta_next pointer can be negative which must be taken into account by its * callers. */ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); int cpu = smp_processor_id(); /* * The idle entry time is expected to be a sufficient approximation of * the current time at this point. */ ktime_t now = ts->idle_entrytime; ktime_t next_event; WARN_ON_ONCE(!ts->inidle); *delta_next = ktime_sub(dev->next_event, now); if (!can_stop_idle_tick(cpu, ts)) return *delta_next; next_event = tick_nohz_next_event(ts, cpu); if (!next_event) return *delta_next; /* * If the next highres timer to expire is earlier than 'next_event', the * idle governor needs to know that. */ next_event = min_t(u64, next_event, hrtimer_next_event_without(&ts->sched_timer)); return ktime_sub(next_event, now); } /** * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value * for a particular CPU. * * Called from the schedutil frequency scaling governor in scheduler context. */ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) { struct tick_sched *ts = tick_get_tick_sched(cpu); return ts->idle_calls; } /** * tick_nohz_get_idle_calls - return the current idle calls counter value * * Called from the schedutil frequency scaling governor in scheduler context. */ unsigned long tick_nohz_get_idle_calls(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); return ts->idle_calls; } static void tick_nohz_account_idle_time(struct tick_sched *ts, ktime_t now) { unsigned long ticks; ts->idle_exittime = now; if (vtime_accounting_enabled_this_cpu()) return; /* * We stopped the tick in idle. update_process_times() would miss the * time we slept, as it does only a 1 tick accounting. * Enforce that this is accounted to idle ! */ ticks = jiffies - ts->idle_jiffies; /* * We might be one off. Do not randomly account a huge number of ticks! */ if (ticks && ticks < LONG_MAX) account_idle_ticks(ticks); } void tick_nohz_idle_restart_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->tick_stopped) { ktime_t now = ktime_get(); tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_time(ts, now); } } static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now) { if (tick_nohz_full_cpu(smp_processor_id())) __tick_nohz_full_update_tick(ts, now); else tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_time(ts, now); } /** * tick_nohz_idle_exit - Update the tick upon idle task exit * * When the idle task exits, update the tick depending on the * following situations: * * 1) If the CPU is not in nohz_full mode (most cases), then * restart the tick. * * 2) If the CPU is in nohz_full mode (corner case): * 2.1) If the tick can be kept stopped (no tick dependencies) * then re-evaluate the next tick and try to keep it stopped * as long as possible. * 2.2) If the tick has dependencies, restart the tick. * */ void tick_nohz_idle_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); bool idle_active, tick_stopped; ktime_t now; local_irq_disable(); WARN_ON_ONCE(!ts->inidle); WARN_ON_ONCE(ts->timer_expires_base); ts->inidle = 0; idle_active = ts->idle_active; tick_stopped = ts->tick_stopped; if (idle_active || tick_stopped) now = ktime_get(); if (idle_active) tick_nohz_stop_idle(ts, now); if (tick_stopped) tick_nohz_idle_update_tick(ts, now); local_irq_enable(); } /* * In low-resolution mode, the tick handler must be implemented directly * at the clockevent level. hrtimer can't be used instead, because its * infrastructure actually relies on the tick itself as a backend in * low-resolution mode (see hrtimer_run_queues()). * * This low-resolution handler still makes use of some hrtimer APIs meanwhile * for convenience with expiration calculation and forwarding. */ static void tick_nohz_lowres_handler(struct clock_event_device *dev) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); dev->next_event = KTIME_MAX; tick_sched_do_timer(ts, now); tick_sched_handle(ts, regs); /* * In dynticks mode, tick reprogram is deferred: * - to the idle task if in dynticks-idle * - to IRQ exit if in full-dynticks. */ if (likely(!ts->tick_stopped)) { hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } } static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { if (!tick_nohz_enabled) return; ts->nohz_mode = mode; /* One update is enough */ if (!test_and_set_bit(0, &tick_nohz_active)) timers_update_nohz(); } /** * tick_nohz_switch_to_nohz - switch to NOHZ mode */ static void tick_nohz_switch_to_nohz(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t next; if (!tick_nohz_enabled) return; if (tick_switch_to_oneshot(tick_nohz_lowres_handler)) return; /* * Recycle the hrtimer in 'ts', so we can share the * hrtimer_forward_now() function with the highres code. */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); /* Get the next period */ next = tick_init_jiffy_update(); hrtimer_set_expires(&ts->sched_timer, next); hrtimer_forward_now(&ts->sched_timer, TICK_NSEC); tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); tick_nohz_activate(ts, NOHZ_MODE_LOWRES); } static inline void tick_nohz_irq_enter(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t now; if (!ts->idle_active && !ts->tick_stopped) return; now = ktime_get(); if (ts->idle_active) tick_nohz_stop_idle(ts, now); /* * If all CPUs are idle we may need to update a stale jiffies value. * Note nohz_full is a special case: a timekeeper is guaranteed to stay * alive but it might be busy looping with interrupts disabled in some * rare case (typically stop machine). So we must make sure we have a * last resort. */ if (ts->tick_stopped) tick_nohz_update_jiffies(now); } #else static inline void tick_nohz_switch_to_nohz(void) { } static inline void tick_nohz_irq_enter(void) { } static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { } #endif /* CONFIG_NO_HZ_COMMON */ /* * Called from irq_enter() to notify about the possible interruption of idle() */ void tick_irq_enter(void) { tick_check_oneshot_broadcast_this_cpu(); tick_nohz_irq_enter(); } /* * High resolution timer specific code */ #ifdef CONFIG_HIGH_RES_TIMERS /* * We rearm the timer until we get disabled by the idle code. * Called with interrupts disabled. */ static enum hrtimer_restart tick_nohz_highres_handler(struct hrtimer *timer) { struct tick_sched *ts = container_of(timer, struct tick_sched, sched_timer); struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); tick_sched_do_timer(ts, now); /* * Do not call when we are not in IRQ context and have * no valid 'regs' pointer */ if (regs) tick_sched_handle(ts, regs); else ts->next_tick = 0; /* * In dynticks mode, tick reprogram is deferred: * - to the idle task if in dynticks-idle * - to IRQ exit if in full-dynticks. */ if (unlikely(ts->tick_stopped)) return HRTIMER_NORESTART; hrtimer_forward(timer, now, TICK_NSEC); return HRTIMER_RESTART; } static int sched_skew_tick; static int __init skew_tick(char *str) { get_option(&str, &sched_skew_tick); return 0; } early_param("skew_tick", skew_tick); /** * tick_setup_sched_timer - setup the tick emulation timer */ void tick_setup_sched_timer(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t now = ktime_get(); /* Emulate tick processing via per-CPU hrtimers: */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); ts->sched_timer.function = tick_nohz_highres_handler; /* Get the next period (per-CPU) */ hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); /* Offset the tick to avert 'jiffies_lock' contention. */ if (sched_skew_tick) { u64 offset = TICK_NSEC >> 1; do_div(offset, num_possible_cpus()); offset *= smp_processor_id(); hrtimer_add_expires_ns(&ts->sched_timer, offset); } hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); tick_nohz_activate(ts, NOHZ_MODE_HIGHRES); } #endif /* HIGH_RES_TIMERS */ #if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS void tick_cancel_sched_timer(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); # ifdef CONFIG_HIGH_RES_TIMERS if (ts->sched_timer.base) hrtimer_cancel(&ts->sched_timer); # endif memset(ts, 0, sizeof(*ts)); } #endif /* * Async notification about clocksource changes */ void tick_clock_notify(void) { int cpu; for_each_possible_cpu(cpu) set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks); } /* * Async notification about clock event changes */ void tick_oneshot_notify(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); set_bit(0, &ts->check_clocks); } /* * Check if a change happened, which makes oneshot possible. * * Called cyclically from the hrtimer softirq (driven by the timer * softirq). 'allow_nohz' signals that we can switch into low-res NOHZ * mode, because high resolution timers are disabled (either compile * or runtime). Called with interrupts disabled. */ int tick_check_oneshot_change(int allow_nohz) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (!test_and_clear_bit(0, &ts->check_clocks)) return 0; if (ts->nohz_mode != NOHZ_MODE_INACTIVE) return 0; if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available()) return 0; if (!allow_nohz) return 1; tick_nohz_switch_to_nohz(); return 0; } |
| 13 3 13 3 3 3 3 13 12 12 12 12 1 1 16 14 13 11 14 2 10 10 9 8 5 10 8 7 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ #include <linux/bitmap.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/jhash.h> #include <linux/random.h> #include <linux/btf_ids.h> #define BLOOM_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK) struct bpf_bloom_filter { struct bpf_map map; u32 bitset_mask; u32 hash_seed; u32 nr_hash_funcs; unsigned long bitset[]; }; static u32 hash(struct bpf_bloom_filter *bloom, void *value, u32 value_size, u32 index) { u32 h; if (likely(value_size % 4 == 0)) h = jhash2(value, value_size / 4, bloom->hash_seed + index); else h = jhash(value, value_size, bloom->hash_seed + index); return h & bloom->bitset_mask; } static long bloom_map_peek_elem(struct bpf_map *map, void *value) { struct bpf_bloom_filter *bloom = container_of(map, struct bpf_bloom_filter, map); u32 i, h; for (i = 0; i < bloom->nr_hash_funcs; i++) { h = hash(bloom, value, map->value_size, i); if (!test_bit(h, bloom->bitset)) return -ENOENT; } return 0; } static long bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags) { struct bpf_bloom_filter *bloom = container_of(map, struct bpf_bloom_filter, map); u32 i, h; if (flags != BPF_ANY) return -EINVAL; for (i = 0; i < bloom->nr_hash_funcs; i++) { h = hash(bloom, value, map->value_size, i); set_bit(h, bloom->bitset); } return 0; } static long bloom_map_pop_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } static long bloom_map_delete_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -EOPNOTSUPP; } static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; int numa_node = bpf_map_attr_numa_node(attr); struct bpf_bloom_filter *bloom; if (attr->key_size != 0 || attr->value_size == 0 || attr->max_entries == 0 || attr->map_flags & ~BLOOM_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags) || /* The lower 4 bits of map_extra (0xF) specify the number * of hash functions */ (attr->map_extra & ~0xF)) return ERR_PTR(-EINVAL); nr_hash_funcs = attr->map_extra; if (nr_hash_funcs == 0) /* Default to using 5 hash functions if unspecified */ nr_hash_funcs = 5; /* For the bloom filter, the optimal bit array size that minimizes the * false positive probability is n * k / ln(2) where n is the number of * expected entries in the bloom filter and k is the number of hash * functions. We use 7 / 5 to approximate 1 / ln(2). * * We round this up to the nearest power of two to enable more efficient * hashing using bitmasks. The bitmask will be the bit array size - 1. * * If this overflows a u32, the bit array size will have 2^32 (4 * GB) bits. */ if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) || check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) || nr_bits > (1UL << 31)) { /* The bit array size is 2^32 bits but to avoid overflowing the * u32, we use U32_MAX, which will round up to the equivalent * number of bytes */ bitset_bytes = BITS_TO_BYTES(U32_MAX); bitset_mask = U32_MAX; } else { if (nr_bits <= BITS_PER_LONG) nr_bits = BITS_PER_LONG; else nr_bits = roundup_pow_of_two(nr_bits); bitset_bytes = BITS_TO_BYTES(nr_bits); bitset_mask = nr_bits - 1; } bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node); if (!bloom) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&bloom->map, attr); bloom->nr_hash_funcs = nr_hash_funcs; bloom->bitset_mask = bitset_mask; if (!(attr->map_flags & BPF_F_ZERO_SEED)) bloom->hash_seed = get_random_u32(); return &bloom->map; } static void bloom_map_free(struct bpf_map *map) { struct bpf_bloom_filter *bloom = container_of(map, struct bpf_bloom_filter, map); bpf_map_area_free(bloom); } static void *bloom_map_lookup_elem(struct bpf_map *map, void *key) { /* The eBPF program should use map_peek_elem instead */ return ERR_PTR(-EINVAL); } static long bloom_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { /* The eBPF program should use map_push_elem instead */ return -EINVAL; } static int bloom_map_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { /* Bloom filter maps are keyless */ return btf_type_is_void(key_type) ? 0 : -EINVAL; } static u64 bloom_map_mem_usage(const struct bpf_map *map) { struct bpf_bloom_filter *bloom; u64 bitset_bytes; bloom = container_of(map, struct bpf_bloom_filter, map); bitset_bytes = BITS_TO_BYTES((u64)bloom->bitset_mask + 1); bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); return sizeof(*bloom) + bitset_bytes; } BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = bloom_map_alloc, .map_free = bloom_map_free, .map_get_next_key = bloom_map_get_next_key, .map_push_elem = bloom_map_push_elem, .map_peek_elem = bloom_map_peek_elem, .map_pop_elem = bloom_map_pop_elem, .map_lookup_elem = bloom_map_lookup_elem, .map_update_elem = bloom_map_update_elem, .map_delete_elem = bloom_map_delete_elem, .map_check_btf = bloom_map_check_btf, .map_mem_usage = bloom_map_mem_usage, .map_btf_id = &bpf_bloom_map_btf_ids[0], }; |
| 53 52 52 53 50 53 53 53 2 52 269 7 274 266 8 8 272 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 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/skbuff.h> #include <linux/sctp.h> #include <net/gso.h> #include <net/gro.h> /** * skb_eth_gso_segment - segmentation handler for ethernet protocols. * @skb: buffer to segment * @features: features for the output path (see dev->features) * @type: Ethernet Protocol ID */ struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, netdev_features_t features, __be16 type) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; rcu_read_lock(); list_for_each_entry_rcu(ptype, &offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; } } rcu_read_unlock(); return segs; } EXPORT_SYMBOL(skb_eth_gso_segment); /** * skb_mac_gso_segment - mac layer segmentation handler. * @skb: buffer to segment * @features: features for the output path (see dev->features) */ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; int vlan_depth = skb->mac_len; __be16 type = skb_network_protocol(skb, &vlan_depth); if (unlikely(!type)) return ERR_PTR(-EINVAL); __skb_pull(skb, vlan_depth); rcu_read_lock(); list_for_each_entry_rcu(ptype, &offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; } } rcu_read_unlock(); __skb_push(skb, skb->data - skb_mac_header(skb)); return segs; } EXPORT_SYMBOL(skb_mac_gso_segment); /* openvswitch calls this on rx path, so we need a different check. */ static bool skb_needs_check(const struct sk_buff *skb, bool tx_path) { if (tx_path) return skb->ip_summed != CHECKSUM_PARTIAL && skb->ip_summed != CHECKSUM_UNNECESSARY; return skb->ip_summed == CHECKSUM_NONE; } /** * __skb_gso_segment - Perform segmentation on skb. * @skb: buffer to segment * @features: features for the output path (see dev->features) * @tx_path: whether it is called in TX path * * This function segments the given skb and returns a list of segments. * * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. * * Segmentation preserves SKB_GSO_CB_OFFSET bytes of previous skb cb. */ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) { struct sk_buff *segs; if (unlikely(skb_needs_check(skb, tx_path))) { int err; /* We're going to init ->check field in TCP or UDP header */ err = skb_cow_head(skb, 0); if (err < 0) return ERR_PTR(err); } /* Only report GSO partial support if it will enable us to * support segmentation on this frame without needing additional * work. */ if (features & NETIF_F_GSO_PARTIAL) { netdev_features_t partial_features = NETIF_F_GSO_ROBUST; struct net_device *dev = skb->dev; partial_features |= dev->features & dev->gso_partial_features; if (!skb_gso_ok(skb, features | partial_features)) features &= ~NETIF_F_GSO_PARTIAL; } BUILD_BUG_ON(SKB_GSO_CB_OFFSET + sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb)); SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); SKB_GSO_CB(skb)->encap_level = 0; skb_reset_mac_header(skb); skb_reset_mac_len(skb); segs = skb_mac_gso_segment(skb, features); if (segs != skb && unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs))) skb_warn_bad_offload(skb); return segs; } EXPORT_SYMBOL(__skb_gso_segment); /** * skb_gso_transport_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_transport_seglen is used to determine the real size of the * individual segments, including Layer4 headers (TCP/UDP). * * The MAC/L2 or network (IP, IPv6) headers are not accounted for. */ static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int thlen = 0; if (skb->encapsulation) { thlen = skb_inner_transport_header(skb) - skb_transport_header(skb); if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) thlen += inner_tcp_hdrlen(skb); } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { thlen = tcp_hdrlen(skb); } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { thlen = sizeof(struct udphdr); } /* UFO sets gso_size to the size of the fragmentation * payload, i.e. the size of the L4 (UDP) header is already * accounted for. */ return thlen + shinfo->gso_size; } /** * skb_gso_network_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_network_seglen is used to determine the real size of the * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). * * The MAC/L2 header is not accounted for. */ static unsigned int skb_gso_network_seglen(const struct sk_buff *skb) { unsigned int hdr_len = skb_transport_header(skb) - skb_network_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } /** * skb_gso_mac_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_mac_seglen is used to determine the real size of the * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4 * headers (TCP/UDP). */ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) { unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } /** * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS * * There are a couple of instances where we have a GSO skb, and we * want to determine what size it would be after it is segmented. * * We might want to check: * - L3+L4+payload size (e.g. IP forwarding) * - L2+L3+L4+payload size (e.g. sanity check before passing to driver) * * This is a helper to do that correctly considering GSO_BY_FRAGS. * * @skb: GSO skb * * @seg_len: The segmented length (from skb_gso_*_seglen). In the * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS]. * * @max_len: The maximum permissible length. * * Returns true if the segmented length <= max length. */ static inline bool skb_gso_size_check(const struct sk_buff *skb, unsigned int seg_len, unsigned int max_len) { const struct skb_shared_info *shinfo = skb_shinfo(skb); const struct sk_buff *iter; if (shinfo->gso_size != GSO_BY_FRAGS) return seg_len <= max_len; /* Undo this so we can re-use header sizes */ seg_len -= GSO_BY_FRAGS; skb_walk_frags(skb, iter) { if (seg_len + skb_headlen(iter) > max_len) return false; } return true; } /** * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU? * * @skb: GSO skb * @mtu: MTU to validate against * * skb_gso_validate_network_len validates if a given skb will fit a * wanted MTU once split. It considers L3 headers, L4 headers, and the * payload. */ bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu) { return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu); } EXPORT_SYMBOL_GPL(skb_gso_validate_network_len); /** * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length? * * @skb: GSO skb * @len: length to validate against * * skb_gso_validate_mac_len validates if a given skb will fit a wanted * length once split, including L2, L3 and L4 headers and the payload. */ bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len) { return skb_gso_size_check(skb, skb_gso_mac_seglen(skb), len); } EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Declarations of X.25 Packet Layer type objects. * * History * nov/17/96 Jonathan Naylor Initial version. * mar/20/00 Daniela Squassoni Disabling/enabling of facilities * negotiation. */ #ifndef _X25_H #define _X25_H #include <linux/x25.h> #include <linux/slab.h> #include <linux/refcount.h> #include <net/sock.h> #define X25_ADDR_LEN 16 #define X25_MAX_L2_LEN 18 /* 802.2 LLC */ #define X25_STD_MIN_LEN 3 #define X25_EXT_MIN_LEN 4 #define X25_GFI_SEQ_MASK 0x30 #define X25_GFI_STDSEQ 0x10 #define X25_GFI_EXTSEQ 0x20 #define X25_Q_BIT 0x80 #define X25_D_BIT 0x40 #define X25_STD_M_BIT 0x10 #define X25_EXT_M_BIT 0x01 #define X25_CALL_REQUEST 0x0B #define X25_CALL_ACCEPTED 0x0F #define X25_CLEAR_REQUEST 0x13 #define X25_CLEAR_CONFIRMATION 0x17 #define X25_DATA 0x00 #define X25_INTERRUPT 0x23 #define X25_INTERRUPT_CONFIRMATION 0x27 #define X25_RR 0x01 #define X25_RNR 0x05 #define X25_REJ 0x09 #define X25_RESET_REQUEST 0x1B #define X25_RESET_CONFIRMATION 0x1F #define X25_REGISTRATION_REQUEST 0xF3 #define X25_REGISTRATION_CONFIRMATION 0xF7 #define X25_RESTART_REQUEST 0xFB #define X25_RESTART_CONFIRMATION 0xFF #define X25_DIAGNOSTIC 0xF1 #define X25_ILLEGAL 0xFD /* Define the various conditions that may exist */ #define X25_COND_ACK_PENDING 0x01 #define X25_COND_OWN_RX_BUSY 0x02 #define X25_COND_PEER_RX_BUSY 0x04 /* Define Link State constants. */ enum { X25_STATE_0, /* Ready */ X25_STATE_1, /* Awaiting Call Accepted */ X25_STATE_2, /* Awaiting Clear Confirmation */ X25_STATE_3, /* Data Transfer */ X25_STATE_4, /* Awaiting Reset Confirmation */ X25_STATE_5 /* Call Accepted / Call Connected pending */ }; enum { X25_LINK_STATE_0, X25_LINK_STATE_1, X25_LINK_STATE_2, X25_LINK_STATE_3 }; #define X25_DEFAULT_T20 (180 * HZ) /* Default T20 value */ #define X25_DEFAULT_T21 (200 * HZ) /* Default T21 value */ #define X25_DEFAULT_T22 (180 * HZ) /* Default T22 value */ #define X25_DEFAULT_T23 (180 * HZ) /* Default T23 value */ #define X25_DEFAULT_T2 (3 * HZ) /* Default ack holdback value */ #define X25_DEFAULT_WINDOW_SIZE 2 /* Default Window Size */ #define X25_DEFAULT_PACKET_SIZE X25_PS128 /* Default Packet Size */ #define X25_DEFAULT_THROUGHPUT 0x0A /* Deafult Throughput */ #define X25_DEFAULT_REVERSE 0x00 /* Default Reverse Charging */ #define X25_SMODULUS 8 #define X25_EMODULUS 128 /* * X.25 Facilities constants. */ #define X25_FAC_CLASS_MASK 0xC0 #define X25_FAC_CLASS_A 0x00 #define X25_FAC_CLASS_B 0x40 #define X25_FAC_CLASS_C 0x80 #define X25_FAC_CLASS_D 0xC0 #define X25_FAC_REVERSE 0x01 /* also fast select */ #define X25_FAC_THROUGHPUT 0x02 #define X25_FAC_PACKET_SIZE 0x42 #define X25_FAC_WINDOW_SIZE 0x43 #define X25_MAX_FAC_LEN 60 #define X25_MAX_CUD_LEN 128 #define X25_FAC_CALLING_AE 0xCB #define X25_FAC_CALLED_AE 0xC9 #define X25_MARKER 0x00 #define X25_DTE_SERVICES 0x0F #define X25_MAX_AE_LEN 40 /* Max num of semi-octets in AE - OSI Nw */ #define X25_MAX_DTE_FACIL_LEN 21 /* Max length of DTE facility params */ /* Bitset in x25_sock->flags for misc flags */ #define X25_Q_BIT_FLAG 0 #define X25_INTERRUPT_FLAG 1 #define X25_ACCPT_APPRV_FLAG 2 /** * struct x25_route - x25 routing entry * @node - entry in x25_list_lock * @address - Start of address range * @sigdigits - Number of sig digits * @dev - More than one for MLP * @refcnt - reference counter */ struct x25_route { struct list_head node; struct x25_address address; unsigned int sigdigits; struct net_device *dev; refcount_t refcnt; }; struct x25_neigh { struct list_head node; struct net_device *dev; unsigned int state; unsigned int extended; struct sk_buff_head queue; unsigned long t20; struct timer_list t20timer; unsigned long global_facil_mask; refcount_t refcnt; }; struct x25_sock { struct sock sk; struct x25_address source_addr, dest_addr; struct x25_neigh *neighbour; unsigned int lci, cudmatchlength; unsigned char state, condition; unsigned short vs, vr, va, vl; unsigned long t2, t21, t22, t23; unsigned short fraglen; unsigned long flags; struct sk_buff_head ack_queue; struct sk_buff_head fragment_queue; struct sk_buff_head interrupt_in_queue; struct sk_buff_head interrupt_out_queue; struct timer_list timer; struct x25_causediag causediag; struct x25_facilities facilities; struct x25_dte_facilities dte_facilities; struct x25_calluserdata calluserdata; unsigned long vc_facil_mask; /* inc_call facilities mask */ }; struct x25_forward { struct list_head node; unsigned int lci; struct net_device *dev1; struct net_device *dev2; atomic_t refcnt; }; #define x25_sk(ptr) container_of_const(ptr, struct x25_sock, sk) /* af_x25.c */ extern int sysctl_x25_restart_request_timeout; extern int sysctl_x25_call_request_timeout; extern int sysctl_x25_reset_request_timeout; extern int sysctl_x25_clear_request_timeout; extern int sysctl_x25_ack_holdback_timeout; extern int sysctl_x25_forward; int x25_parse_address_block(struct sk_buff *skb, struct x25_address *called_addr, struct x25_address *calling_addr); int x25_addr_ntoa(unsigned char *, struct x25_address *, struct x25_address *); int x25_addr_aton(unsigned char *, struct x25_address *, struct x25_address *); struct sock *x25_find_socket(unsigned int, struct x25_neigh *); void x25_destroy_socket_from_timer(struct sock *); int x25_rx_call_request(struct sk_buff *, struct x25_neigh *, unsigned int); void x25_kill_by_neigh(struct x25_neigh *); /* x25_dev.c */ void x25_send_frame(struct sk_buff *, struct x25_neigh *); int x25_lapb_receive_frame(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); void x25_establish_link(struct x25_neigh *); void x25_terminate_link(struct x25_neigh *); /* x25_facilities.c */ int x25_parse_facilities(struct sk_buff *, struct x25_facilities *, struct x25_dte_facilities *, unsigned long *); int x25_create_facilities(unsigned char *, struct x25_facilities *, struct x25_dte_facilities *, unsigned long); int x25_negotiate_facilities(struct sk_buff *, struct sock *, struct x25_facilities *, struct x25_dte_facilities *); void x25_limit_facilities(struct x25_facilities *, struct x25_neigh *); /* x25_forward.c */ void x25_clear_forward_by_lci(unsigned int lci); void x25_clear_forward_by_dev(struct net_device *); int x25_forward_data(int, struct x25_neigh *, struct sk_buff *); int x25_forward_call(struct x25_address *, struct x25_neigh *, struct sk_buff *, int); /* x25_in.c */ int x25_process_rx_frame(struct sock *, struct sk_buff *); int x25_backlog_rcv(struct sock *, struct sk_buff *); /* x25_link.c */ void x25_link_control(struct sk_buff *, struct x25_neigh *, unsigned short); void x25_link_device_up(struct net_device *); void x25_link_device_down(struct net_device *); void x25_link_established(struct x25_neigh *); void x25_link_terminated(struct x25_neigh *); void x25_transmit_clear_request(struct x25_neigh *, unsigned int, unsigned char); void x25_transmit_link(struct sk_buff *, struct x25_neigh *); int x25_subscr_ioctl(unsigned int, void __user *); struct x25_neigh *x25_get_neigh(struct net_device *); void x25_link_free(void); /* x25_neigh.c */ static __inline__ void x25_neigh_hold(struct x25_neigh *nb) { refcount_inc(&nb->refcnt); } static __inline__ void x25_neigh_put(struct x25_neigh *nb) { if (refcount_dec_and_test(&nb->refcnt)) kfree(nb); } /* x25_out.c */ int x25_output(struct sock *, struct sk_buff *); void x25_kick(struct sock *); void x25_enquiry_response(struct sock *); /* x25_route.c */ struct x25_route *x25_get_route(struct x25_address *addr); struct net_device *x25_dev_get(char *); void x25_route_device_down(struct net_device *dev); int x25_route_ioctl(unsigned int, void __user *); void x25_route_free(void); static __inline__ void x25_route_hold(struct x25_route *rt) { refcount_inc(&rt->refcnt); } static __inline__ void x25_route_put(struct x25_route *rt) { if (refcount_dec_and_test(&rt->refcnt)) kfree(rt); } /* x25_subr.c */ void x25_clear_queues(struct sock *); void x25_frames_acked(struct sock *, unsigned short); void x25_requeue_frames(struct sock *); int x25_validate_nr(struct sock *, unsigned short); void x25_write_internal(struct sock *, int); int x25_decode(struct sock *, struct sk_buff *, int *, int *, int *, int *, int *); void x25_disconnect(struct sock *, int, unsigned char, unsigned char); /* x25_timer.c */ void x25_init_timers(struct sock *sk); void x25_start_heartbeat(struct sock *); void x25_start_t2timer(struct sock *); void x25_start_t21timer(struct sock *); void x25_start_t22timer(struct sock *); void x25_start_t23timer(struct sock *); void x25_stop_heartbeat(struct sock *); void x25_stop_timer(struct sock *); unsigned long x25_display_timer(struct sock *); void x25_check_rbuf(struct sock *); /* sysctl_net_x25.c */ #ifdef CONFIG_SYSCTL int x25_register_sysctl(void); void x25_unregister_sysctl(void); #else static inline int x25_register_sysctl(void) { return 0; }; static inline void x25_unregister_sysctl(void) {}; #endif /* CONFIG_SYSCTL */ struct x25_skb_cb { unsigned int flags; }; #define X25_SKB_CB(s) ((struct x25_skb_cb *) ((s)->cb)) extern struct hlist_head x25_list; extern rwlock_t x25_list_lock; extern struct list_head x25_route_list; extern rwlock_t x25_route_list_lock; extern struct list_head x25_forward_list; extern rwlock_t x25_forward_list_lock; extern struct list_head x25_neigh_list; extern rwlock_t x25_neigh_list_lock; int x25_proc_init(void); void x25_proc_exit(void); #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * cgroups support for the BFQ I/O scheduler. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/cgroup.h> #include <linux/ktime.h> #include <linux/rbtree.h> #include <linux/ioprio.h> #include <linux/sbitmap.h> #include <linux/delay.h> #include "elevator.h" #include "bfq-iosched.h" #ifdef CONFIG_BFQ_CGROUP_DEBUG static int bfq_stat_init(struct bfq_stat *stat, gfp_t gfp) { int ret; ret = percpu_counter_init(&stat->cpu_cnt, 0, gfp); if (ret) return ret; atomic64_set(&stat->aux_cnt, 0); return 0; } static void bfq_stat_exit(struct bfq_stat *stat) { percpu_counter_destroy(&stat->cpu_cnt); } /** * bfq_stat_add - add a value to a bfq_stat * @stat: target bfq_stat * @val: value to add * * Add @val to @stat. The caller must ensure that IRQ on the same CPU * don't re-enter this function for the same counter. */ static inline void bfq_stat_add(struct bfq_stat *stat, uint64_t val) { percpu_counter_add_batch(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH); } /** * bfq_stat_read - read the current value of a bfq_stat * @stat: bfq_stat to read */ static inline uint64_t bfq_stat_read(struct bfq_stat *stat) { return percpu_counter_sum_positive(&stat->cpu_cnt); } /** * bfq_stat_reset - reset a bfq_stat * @stat: bfq_stat to reset */ static inline void bfq_stat_reset(struct bfq_stat *stat) { percpu_counter_set(&stat->cpu_cnt, 0); atomic64_set(&stat->aux_cnt, 0); } /** * bfq_stat_add_aux - add a bfq_stat into another's aux count * @to: the destination bfq_stat * @from: the source * * Add @from's count including the aux one to @to's aux count. */ static inline void bfq_stat_add_aux(struct bfq_stat *to, struct bfq_stat *from) { atomic64_add(bfq_stat_read(from) + atomic64_read(&from->aux_cnt), &to->aux_cnt); } /** * blkg_prfill_stat - prfill callback for bfq_stat * @sf: seq_file to print to * @pd: policy private data of interest * @off: offset to the bfq_stat in @pd * * prfill callback for printing a bfq_stat. */ static u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off) { return __blkg_prfill_u64(sf, pd, bfq_stat_read((void *)pd + off)); } /* bfqg stats flags */ enum bfqg_stats_flags { BFQG_stats_waiting = 0, BFQG_stats_idling, BFQG_stats_empty, }; #define BFQG_FLAG_FNS(name) \ static void bfqg_stats_mark_##name(struct bfqg_stats *stats) \ { \ stats->flags |= (1 << BFQG_stats_##name); \ } \ static void bfqg_stats_clear_##name(struct bfqg_stats *stats) \ { \ stats->flags &= ~(1 << BFQG_stats_##name); \ } \ static int bfqg_stats_##name(struct bfqg_stats *stats) \ { \ return (stats->flags & (1 << BFQG_stats_##name)) != 0; \ } \ BFQG_FLAG_FNS(waiting) BFQG_FLAG_FNS(idling) BFQG_FLAG_FNS(empty) #undef BFQG_FLAG_FNS /* This should be called with the scheduler lock held. */ static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats) { u64 now; if (!bfqg_stats_waiting(stats)) return; now = ktime_get_ns(); if (now > stats->start_group_wait_time) bfq_stat_add(&stats->group_wait_time, now - stats->start_group_wait_time); bfqg_stats_clear_waiting(stats); } /* This should be called with the scheduler lock held. */ static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg, struct bfq_group *curr_bfqg) { struct bfqg_stats *stats = &bfqg->stats; if (bfqg_stats_waiting(stats)) return; if (bfqg == curr_bfqg) return; stats->start_group_wait_time = ktime_get_ns(); bfqg_stats_mark_waiting(stats); } /* This should be called with the scheduler lock held. */ static void bfqg_stats_end_empty_time(struct bfqg_stats *stats) { u64 now; if (!bfqg_stats_empty(stats)) return; now = ktime_get_ns(); if (now > stats->start_empty_time) bfq_stat_add(&stats->empty_time, now - stats->start_empty_time); bfqg_stats_clear_empty(stats); } void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { bfq_stat_add(&bfqg->stats.dequeue, 1); } void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { struct bfqg_stats *stats = &bfqg->stats; if (blkg_rwstat_total(&stats->queued)) return; /* * group is already marked empty. This can happen if bfqq got new * request in parent group and moved to this group while being added * to service tree. Just ignore the event and move on. */ if (bfqg_stats_empty(stats)) return; stats->start_empty_time = ktime_get_ns(); bfqg_stats_mark_empty(stats); } void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { struct bfqg_stats *stats = &bfqg->stats; if (bfqg_stats_idling(stats)) { u64 now = ktime_get_ns(); if (now > stats->start_idle_time) bfq_stat_add(&stats->idle_time, now - stats->start_idle_time); bfqg_stats_clear_idling(stats); } } void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { struct bfqg_stats *stats = &bfqg->stats; stats->start_idle_time = ktime_get_ns(); bfqg_stats_mark_idling(stats); } void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { struct bfqg_stats *stats = &bfqg->stats; bfq_stat_add(&stats->avg_queue_size_sum, blkg_rwstat_total(&stats->queued)); bfq_stat_add(&stats->avg_queue_size_samples, 1); bfqg_stats_update_group_wait_time(stats); } void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, blk_opf_t opf) { blkg_rwstat_add(&bfqg->stats.queued, opf, 1); bfqg_stats_end_empty_time(&bfqg->stats); if (!(bfqq == bfqg->bfqd->in_service_queue)) bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq)); } void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf) { blkg_rwstat_add(&bfqg->stats.queued, opf, -1); } void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf) { blkg_rwstat_add(&bfqg->stats.merged, opf, 1); } void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, u64 io_start_time_ns, blk_opf_t opf) { struct bfqg_stats *stats = &bfqg->stats; u64 now = ktime_get_ns(); if (now > io_start_time_ns) blkg_rwstat_add(&stats->service_time, opf, now - io_start_time_ns); if (io_start_time_ns > start_time_ns) blkg_rwstat_add(&stats->wait_time, opf, io_start_time_ns - start_time_ns); } #else /* CONFIG_BFQ_CGROUP_DEBUG */ void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf) { } void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf) { } void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, u64 io_start_time_ns, blk_opf_t opf) { } void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { } void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { } #endif /* CONFIG_BFQ_CGROUP_DEBUG */ #ifdef CONFIG_BFQ_GROUP_IOSCHED /* * blk-cgroup policy-related handlers * The following functions help in converting between blk-cgroup * internal structures and BFQ-specific structures. */ static struct bfq_group *pd_to_bfqg(struct blkg_policy_data *pd) { return pd ? container_of(pd, struct bfq_group, pd) : NULL; } struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg) { return pd_to_blkg(&bfqg->pd); } static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg) { return pd_to_bfqg(blkg_to_pd(blkg, &blkcg_policy_bfq)); } /* * bfq_group handlers * The following functions help in navigating the bfq_group hierarchy * by allowing to find the parent of a bfq_group or the bfq_group * associated to a bfq_queue. */ static struct bfq_group *bfqg_parent(struct bfq_group *bfqg) { struct blkcg_gq *pblkg = bfqg_to_blkg(bfqg)->parent; return pblkg ? blkg_to_bfqg(pblkg) : NULL; } struct bfq_group *bfqq_group(struct bfq_queue *bfqq) { struct bfq_entity *group_entity = bfqq->entity.parent; return group_entity ? container_of(group_entity, struct bfq_group, entity) : bfqq->bfqd->root_group; } /* * The following two functions handle get and put of a bfq_group by * wrapping the related blk-cgroup hooks. */ static void bfqg_get(struct bfq_group *bfqg) { refcount_inc(&bfqg->ref); } static void bfqg_put(struct bfq_group *bfqg) { if (refcount_dec_and_test(&bfqg->ref)) kfree(bfqg); } static void bfqg_and_blkg_get(struct bfq_group *bfqg) { /* see comments in bfq_bic_update_cgroup for why refcounting bfqg */ bfqg_get(bfqg); blkg_get(bfqg_to_blkg(bfqg)); } void bfqg_and_blkg_put(struct bfq_group *bfqg) { blkg_put(bfqg_to_blkg(bfqg)); bfqg_put(bfqg); } void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq) { struct bfq_group *bfqg = blkg_to_bfqg(rq->bio->bi_blkg); if (!bfqg) return; blkg_rwstat_add(&bfqg->stats.bytes, rq->cmd_flags, blk_rq_bytes(rq)); blkg_rwstat_add(&bfqg->stats.ios, rq->cmd_flags, 1); } /* @stats = 0 */ static void bfqg_stats_reset(struct bfqg_stats *stats) { #ifdef CONFIG_BFQ_CGROUP_DEBUG /* queued stats shouldn't be cleared */ blkg_rwstat_reset(&stats->merged); blkg_rwstat_reset(&stats->service_time); blkg_rwstat_reset(&stats->wait_time); bfq_stat_reset(&stats->time); bfq_stat_reset(&stats->avg_queue_size_sum); bfq_stat_reset(&stats->avg_queue_size_samples); bfq_stat_reset(&stats->dequeue); bfq_stat_reset(&stats->group_wait_time); bfq_stat_reset(&stats->idle_time); bfq_stat_reset(&stats->empty_time); #endif } /* @to += @from */ static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from) { if (!to || !from) return; #ifdef CONFIG_BFQ_CGROUP_DEBUG /* queued stats shouldn't be cleared */ blkg_rwstat_add_aux(&to->merged, &from->merged); blkg_rwstat_add_aux(&to->service_time, &from->service_time); blkg_rwstat_add_aux(&to->wait_time, &from->wait_time); bfq_stat_add_aux(&from->time, &from->time); bfq_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum); bfq_stat_add_aux(&to->avg_queue_size_samples, &from->avg_queue_size_samples); bfq_stat_add_aux(&to->dequeue, &from->dequeue); bfq_stat_add_aux(&to->group_wait_time, &from->group_wait_time); bfq_stat_add_aux(&to->idle_time, &from->idle_time); bfq_stat_add_aux(&to->empty_time, &from->empty_time); #endif } /* * Transfer @bfqg's stats to its parent's aux counts so that the ancestors' * recursive stats can still account for the amount used by this bfqg after * it's gone. */ static void bfqg_stats_xfer_dead(struct bfq_group *bfqg) { struct bfq_group *parent; if (!bfqg) /* root_group */ return; parent = bfqg_parent(bfqg); lockdep_assert_held(&bfqg_to_blkg(bfqg)->q->queue_lock); if (unlikely(!parent)) return; bfqg_stats_add_aux(&parent->stats, &bfqg->stats); bfqg_stats_reset(&bfqg->stats); } void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg) { struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); entity->weight = entity->new_weight; entity->orig_weight = entity->new_weight; if (bfqq) { bfqq->ioprio = bfqq->new_ioprio; bfqq->ioprio_class = bfqq->new_ioprio_class; /* * Make sure that bfqg and its associated blkg do not * disappear before entity. */ bfqg_and_blkg_get(bfqg); } entity->parent = bfqg->my_entity; /* NULL for root group */ entity->sched_data = &bfqg->sched_data; } static void bfqg_stats_exit(struct bfqg_stats *stats) { blkg_rwstat_exit(&stats->bytes); blkg_rwstat_exit(&stats->ios); #ifdef CONFIG_BFQ_CGROUP_DEBUG blkg_rwstat_exit(&stats->merged); blkg_rwstat_exit(&stats->service_time); blkg_rwstat_exit(&stats->wait_time); blkg_rwstat_exit(&stats->queued); bfq_stat_exit(&stats->time); bfq_stat_exit(&stats->avg_queue_size_sum); bfq_stat_exit(&stats->avg_queue_size_samples); bfq_stat_exit(&stats->dequeue); bfq_stat_exit(&stats->group_wait_time); bfq_stat_exit(&stats->idle_time); bfq_stat_exit(&stats->empty_time); #endif } static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp) { if (blkg_rwstat_init(&stats->bytes, gfp) || blkg_rwstat_init(&stats->ios, gfp)) goto error; #ifdef CONFIG_BFQ_CGROUP_DEBUG if (blkg_rwstat_init(&stats->merged, gfp) || blkg_rwstat_init(&stats->service_time, gfp) || blkg_rwstat_init(&stats->wait_time, gfp) || blkg_rwstat_init(&stats->queued, gfp) || bfq_stat_init(&stats->time, gfp) || bfq_stat_init(&stats->avg_queue_size_sum, gfp) || bfq_stat_init(&stats->avg_queue_size_samples, gfp) || bfq_stat_init(&stats->dequeue, gfp) || bfq_stat_init(&stats->group_wait_time, gfp) || bfq_stat_init(&stats->idle_time, gfp) || bfq_stat_init(&stats->empty_time, gfp)) goto error; #endif return 0; error: bfqg_stats_exit(stats); return -ENOMEM; } static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd) { return cpd ? container_of(cpd, struct bfq_group_data, pd) : NULL; } static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg) { return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq)); } static struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp) { struct bfq_group_data *bgd; bgd = kzalloc(sizeof(*bgd), gfp); if (!bgd) return NULL; bgd->weight = CGROUP_WEIGHT_DFL; return &bgd->pd; } static void bfq_cpd_free(struct blkcg_policy_data *cpd) { kfree(cpd_to_bfqgd(cpd)); } static struct blkg_policy_data *bfq_pd_alloc(struct gendisk *disk, struct blkcg *blkcg, gfp_t gfp) { struct bfq_group *bfqg; bfqg = kzalloc_node(sizeof(*bfqg), gfp, disk->node_id); if (!bfqg) return NULL; if (bfqg_stats_init(&bfqg->stats, gfp)) { kfree(bfqg); return NULL; } /* see comments in bfq_bic_update_cgroup for why refcounting */ refcount_set(&bfqg->ref, 1); return &bfqg->pd; } static void bfq_pd_init(struct blkg_policy_data *pd) { struct blkcg_gq *blkg = pd_to_blkg(pd); struct bfq_group *bfqg = blkg_to_bfqg(blkg); struct bfq_data *bfqd = blkg->q->elevator->elevator_data; struct bfq_entity *entity = &bfqg->entity; struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg); entity->orig_weight = entity->weight = entity->new_weight = d->weight; entity->my_sched_data = &bfqg->sched_data; entity->last_bfqq_created = NULL; bfqg->my_entity = entity; /* * the root_group's will be set to NULL * in bfq_init_queue() */ bfqg->bfqd = bfqd; bfqg->active_entities = 0; bfqg->num_queues_with_pending_reqs = 0; bfqg->rq_pos_tree = RB_ROOT; } static void bfq_pd_free(struct blkg_policy_data *pd) { struct bfq_group *bfqg = pd_to_bfqg(pd); bfqg_stats_exit(&bfqg->stats); bfqg_put(bfqg); } static void bfq_pd_reset_stats(struct blkg_policy_data *pd) { struct bfq_group *bfqg = pd_to_bfqg(pd); bfqg_stats_reset(&bfqg->stats); } static void bfq_group_set_parent(struct bfq_group *bfqg, struct bfq_group *parent) { struct bfq_entity *entity; entity = &bfqg->entity; entity->parent = parent->my_entity; entity->sched_data = &parent->sched_data; } static void bfq_link_bfqg(struct bfq_data *bfqd, struct bfq_group *bfqg) { struct bfq_group *parent; struct bfq_entity *entity; /* * Update chain of bfq_groups as we might be handling a leaf group * which, along with some of its relatives, has not been hooked yet * to the private hierarchy of BFQ. */ entity = &bfqg->entity; for_each_entity(entity) { struct bfq_group *curr_bfqg = container_of(entity, struct bfq_group, entity); if (curr_bfqg != bfqd->root_group) { parent = bfqg_parent(curr_bfqg); if (!parent) parent = bfqd->root_group; bfq_group_set_parent(curr_bfqg, parent); } } } struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; struct bfq_group *bfqg; while (blkg) { if (!blkg->online) { blkg = blkg->parent; continue; } bfqg = blkg_to_bfqg(blkg); if (bfqg->pd.online) { bio_associate_blkg_from_css(bio, &blkg->blkcg->css); return bfqg; } blkg = blkg->parent; } bio_associate_blkg_from_css(bio, &bfqg_to_blkg(bfqd->root_group)->blkcg->css); return bfqd->root_group; } /** * bfq_bfqq_move - migrate @bfqq to @bfqg. * @bfqd: queue descriptor. * @bfqq: the queue to move. * @bfqg: the group to move to. * * Move @bfqq to @bfqg, deactivating it from its old group and reactivating * it on the new one. Avoid putting the entity on the old group idle tree. * * Must be called under the scheduler lock, to make sure that the blkg * owning @bfqg does not disappear (see comments in * bfq_bic_update_cgroup on guaranteeing the consistency of blkg * objects). */ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct bfq_group *bfqg) { struct bfq_entity *entity = &bfqq->entity; struct bfq_group *old_parent = bfqq_group(bfqq); bool has_pending_reqs = false; /* * No point to move bfqq to the same group, which can happen when * root group is offlined */ if (old_parent == bfqg) return; /* * oom_bfqq is not allowed to move, oom_bfqq will hold ref to root_group * until elevator exit. */ if (bfqq == &bfqd->oom_bfqq) return; /* * Get extra reference to prevent bfqq from being freed in * next possible expire or deactivate. */ bfqq->ref++; if (entity->in_groups_with_pending_reqs) { has_pending_reqs = true; bfq_del_bfqq_in_groups_with_pending_reqs(bfqq); } /* If bfqq is empty, then bfq_bfqq_expire also invokes * bfq_del_bfqq_busy, thereby removing bfqq and its entity * from data structures related to current group. Otherwise we * need to remove bfqq explicitly with bfq_deactivate_bfqq, as * we do below. */ if (bfqq == bfqd->in_service_queue) bfq_bfqq_expire(bfqd, bfqd->in_service_queue, false, BFQQE_PREEMPTED); if (bfq_bfqq_busy(bfqq)) bfq_deactivate_bfqq(bfqd, bfqq, false, false); else if (entity->on_st_or_in_serv) bfq_put_idle_entity(bfq_entity_service_tree(entity), entity); bfqg_and_blkg_put(old_parent); if (entity->parent && entity->parent->last_bfqq_created == bfqq) entity->parent->last_bfqq_created = NULL; else if (bfqd->last_bfqq_created == bfqq) bfqd->last_bfqq_created = NULL; entity->parent = bfqg->my_entity; entity->sched_data = &bfqg->sched_data; /* pin down bfqg and its associated blkg */ bfqg_and_blkg_get(bfqg); if (has_pending_reqs) bfq_add_bfqq_in_groups_with_pending_reqs(bfqq); if (bfq_bfqq_busy(bfqq)) { if (unlikely(!bfqd->nonrot_with_queueing)) bfq_pos_tree_add_move(bfqd, bfqq); bfq_activate_bfqq(bfqd, bfqq); } if (!bfqd->in_service_queue && !bfqd->tot_rq_in_driver) bfq_schedule_dispatch(bfqd); /* release extra ref taken above, bfqq may happen to be freed now */ bfq_put_queue(bfqq); } static void bfq_sync_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *sync_bfqq, struct bfq_io_cq *bic, struct bfq_group *bfqg, unsigned int act_idx) { struct bfq_queue *bfqq; if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) { /* We are the only user of this bfqq, just move it */ if (sync_bfqq->entity.sched_data != &bfqg->sched_data) bfq_bfqq_move(bfqd, sync_bfqq, bfqg); return; } /* * The queue was merged to a different queue. Check * that the merge chain still belongs to the same * cgroup. */ for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq) if (bfqq->entity.sched_data != &bfqg->sched_data) break; if (bfqq) { /* * Some queue changed cgroup so the merge is not valid * anymore. We cannot easily just cancel the merge (by * clearing new_bfqq) as there may be other processes * using this queue and holding refs to all queues * below sync_bfqq->new_bfqq. Similarly if the merge * already happened, we need to detach from bfqq now * so that we cannot merge bio to a request from the * old cgroup. */ bfq_put_cooperator(sync_bfqq); bic_set_bfqq(bic, NULL, true, act_idx); bfq_release_process_ref(bfqd, sync_bfqq); } } /** * __bfq_bic_change_cgroup - move @bic to @bfqg. * @bfqd: the queue descriptor. * @bic: the bic to move. * @bfqg: the group to move to. * * Move bic to blkcg, assuming that bfqd->lock is held; which makes * sure that the reference to cgroup is valid across the call (see * comments in bfq_bic_update_cgroup on this issue) */ static void __bfq_bic_change_cgroup(struct bfq_data *bfqd, struct bfq_io_cq *bic, struct bfq_group *bfqg) { unsigned int act_idx; for (act_idx = 0; act_idx < bfqd->num_actuators; act_idx++) { struct bfq_queue *async_bfqq = bic_to_bfqq(bic, false, act_idx); struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, true, act_idx); if (async_bfqq && async_bfqq->entity.sched_data != &bfqg->sched_data) { bic_set_bfqq(bic, NULL, false, act_idx); bfq_release_process_ref(bfqd, async_bfqq); } if (sync_bfqq) bfq_sync_bfqq_move(bfqd, sync_bfqq, bic, bfqg, act_idx); } } void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) { struct bfq_data *bfqd = bic_to_bfqd(bic); struct bfq_group *bfqg = bfq_bio_bfqg(bfqd, bio); uint64_t serial_nr; serial_nr = bfqg_to_blkg(bfqg)->blkcg->css.serial_nr; /* * Check whether blkcg has changed. The condition may trigger * spuriously on a newly created cic but there's no harm. */ if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr)) return; /* * New cgroup for this process. Make sure it is linked to bfq internal * cgroup hierarchy. */ bfq_link_bfqg(bfqd, bfqg); __bfq_bic_change_cgroup(bfqd, bic, bfqg); /* * Update blkg_path for bfq_log_* functions. We cache this * path, and update it here, for the following * reasons. Operations on blkg objects in blk-cgroup are * protected with the request_queue lock, and not with the * lock that protects the instances of this scheduler * (bfqd->lock). This exposes BFQ to the following sort of * race. * * The blkg_lookup performed in bfq_get_queue, protected * through rcu, may happen to return the address of a copy of * the original blkg. If this is the case, then the * bfqg_and_blkg_get performed in bfq_get_queue, to pin down * the blkg, is useless: it does not prevent blk-cgroup code * from destroying both the original blkg and all objects * directly or indirectly referred by the copy of the * blkg. * * On the bright side, destroy operations on a blkg invoke, as * a first step, hooks of the scheduler associated with the * blkg. And these hooks are executed with bfqd->lock held for * BFQ. As a consequence, for any blkg associated with the * request queue this instance of the scheduler is attached * to, we are guaranteed that such a blkg is not destroyed, and * that all the pointers it contains are consistent, while we * are holding bfqd->lock. A blkg_lookup performed with * bfqd->lock held then returns a fully consistent blkg, which * remains consistent until this lock is held. * * Thanks to the last fact, and to the fact that: (1) bfqg has * been obtained through a blkg_lookup in the above * assignment, and (2) bfqd->lock is being held, here we can * safely use the policy data for the involved blkg (i.e., the * field bfqg->pd) to get to the blkg associated with bfqg, * and then we can safely use any field of blkg. After we * release bfqd->lock, even just getting blkg through this * bfqg may cause dangling references to be traversed, as * bfqg->pd may not exist any more. * * In view of the above facts, here we cache, in the bfqg, any * blkg data we may need for this bic, and for its associated * bfq_queue. As of now, we need to cache only the path of the * blkg, which is used in the bfq_log_* functions. * * Finally, note that bfqg itself needs to be protected from * destruction on the blkg_free of the original blkg (which * invokes bfq_pd_free). We use an additional private * refcounter for bfqg, to let it disappear only after no * bfq_queue refers to it any longer. */ blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path)); bic->blkcg_serial_nr = serial_nr; } /** * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st. * @st: the service tree being flushed. */ static void bfq_flush_idle_tree(struct bfq_service_tree *st) { struct bfq_entity *entity = st->first_idle; for (; entity ; entity = st->first_idle) __bfq_deactivate_entity(entity, false); } /** * bfq_reparent_leaf_entity - move leaf entity to the root_group. * @bfqd: the device data structure with the root group. * @entity: the entity to move, if entity is a leaf; or the parent entity * of an active leaf entity to move, if entity is not a leaf. * @ioprio_class: I/O priority class to reparent. */ static void bfq_reparent_leaf_entity(struct bfq_data *bfqd, struct bfq_entity *entity, int ioprio_class) { struct bfq_queue *bfqq; struct bfq_entity *child_entity = entity; while (child_entity->my_sched_data) { /* leaf not reached yet */ struct bfq_sched_data *child_sd = child_entity->my_sched_data; struct bfq_service_tree *child_st = child_sd->service_tree + ioprio_class; struct rb_root *child_active = &child_st->active; child_entity = bfq_entity_of(rb_first(child_active)); if (!child_entity) child_entity = child_sd->in_service_entity; } bfqq = bfq_entity_to_bfqq(child_entity); bfq_bfqq_move(bfqd, bfqq, bfqd->root_group); } /** * bfq_reparent_active_queues - move to the root group all active queues. * @bfqd: the device data structure with the root group. * @bfqg: the group to move from. * @st: the service tree to start the search from. * @ioprio_class: I/O priority class to reparent. */ static void bfq_reparent_active_queues(struct bfq_data *bfqd, struct bfq_group *bfqg, struct bfq_service_tree *st, int ioprio_class) { struct rb_root *active = &st->active; struct bfq_entity *entity; while ((entity = bfq_entity_of(rb_first(active)))) bfq_reparent_leaf_entity(bfqd, entity, ioprio_class); if (bfqg->sched_data.in_service_entity) bfq_reparent_leaf_entity(bfqd, bfqg->sched_data.in_service_entity, ioprio_class); } /** * bfq_pd_offline - deactivate the entity associated with @pd, * and reparent its children entities. * @pd: descriptor of the policy going offline. * * blkio already grabs the queue_lock for us, so no need to use * RCU-based magic */ static void bfq_pd_offline(struct blkg_policy_data *pd) { struct bfq_service_tree *st; struct bfq_group *bfqg = pd_to_bfqg(pd); struct bfq_data *bfqd = bfqg->bfqd; struct bfq_entity *entity = bfqg->my_entity; unsigned long flags; int i; spin_lock_irqsave(&bfqd->lock, flags); if (!entity) /* root group */ goto put_async_queues; /* * Empty all service_trees belonging to this group before * deactivating the group itself. */ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) { st = bfqg->sched_data.service_tree + i; /* * It may happen that some queues are still active * (busy) upon group destruction (if the corresponding * processes have been forced to terminate). We move * all the leaf entities corresponding to these queues * to the root_group. * Also, it may happen that the group has an entity * in service, which is disconnected from the active * tree: it must be moved, too. * There is no need to put the sync queues, as the * scheduler has taken no reference. */ bfq_reparent_active_queues(bfqd, bfqg, st, i); /* * The idle tree may still contain bfq_queues * belonging to exited task because they never * migrated to a different cgroup from the one being * destroyed now. In addition, even * bfq_reparent_active_queues() may happen to add some * entities to the idle tree. It happens if, in some * of the calls to bfq_bfqq_move() performed by * bfq_reparent_active_queues(), the queue to move is * empty and gets expired. */ bfq_flush_idle_tree(st); } __bfq_deactivate_entity(entity, false); put_async_queues: bfq_put_async_queues(bfqd, bfqg); spin_unlock_irqrestore(&bfqd->lock, flags); /* * @blkg is going offline and will be ignored by * blkg_[rw]stat_recursive_sum(). Transfer stats to the parent so * that they don't get lost. If IOs complete after this point, the * stats for them will be lost. Oh well... */ bfqg_stats_xfer_dead(bfqg); } void bfq_end_wr_async(struct bfq_data *bfqd) { struct blkcg_gq *blkg; list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) { struct bfq_group *bfqg = blkg_to_bfqg(blkg); bfq_end_wr_async_queues(bfqd, bfqg); } bfq_end_wr_async_queues(bfqd, bfqd->root_group); } static int bfq_io_show_weight_legacy(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg); unsigned int val = 0; if (bfqgd) val = bfqgd->weight; seq_printf(sf, "%u\n", val); return 0; } static u64 bfqg_prfill_weight_device(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct bfq_group *bfqg = pd_to_bfqg(pd); if (!bfqg->entity.dev_weight) return 0; return __blkg_prfill_u64(sf, pd, bfqg->entity.dev_weight); } static int bfq_io_show_weight(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg); seq_printf(sf, "default %u\n", bfqgd->weight); blkcg_print_blkgs(sf, blkcg, bfqg_prfill_weight_device, &blkcg_policy_bfq, 0, false); return 0; } static void bfq_group_set_weight(struct bfq_group *bfqg, u64 weight, u64 dev_weight) { weight = dev_weight ?: weight; bfqg->entity.dev_weight = dev_weight; /* * Setting the prio_changed flag of the entity * to 1 with new_weight == weight would re-set * the value of the weight to its ioprio mapping. * Set the flag only if necessary. */ if ((unsigned short)weight != bfqg->entity.new_weight) { bfqg->entity.new_weight = (unsigned short)weight; /* * Make sure that the above new value has been * stored in bfqg->entity.new_weight before * setting the prio_changed flag. In fact, * this flag may be read asynchronously (in * critical sections protected by a different * lock than that held here), and finding this * flag set may cause the execution of the code * for updating parameters whose value may * depend also on bfqg->entity.new_weight (in * __bfq_entity_update_weight_prio). * This barrier makes sure that the new value * of bfqg->entity.new_weight is correctly * seen in that code. */ smp_wmb(); bfqg->entity.prio_changed = 1; } } static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg); struct blkcg_gq *blkg; int ret = -ERANGE; if (val < BFQ_MIN_WEIGHT || val > BFQ_MAX_WEIGHT) return ret; ret = 0; spin_lock_irq(&blkcg->lock); bfqgd->weight = (unsigned short)val; hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { struct bfq_group *bfqg = blkg_to_bfqg(blkg); if (bfqg) bfq_group_set_weight(bfqg, val, 0); } spin_unlock_irq(&blkcg->lock); return ret; } static ssize_t bfq_io_set_device_weight(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { int ret; struct blkg_conf_ctx ctx; struct blkcg *blkcg = css_to_blkcg(of_css(of)); struct bfq_group *bfqg; u64 v; blkg_conf_init(&ctx, buf); ret = blkg_conf_prep(blkcg, &blkcg_policy_bfq, &ctx); if (ret) goto out; if (sscanf(ctx.body, "%llu", &v) == 1) { /* require "default" on dfl */ ret = -ERANGE; if (!v) goto out; } else if (!strcmp(strim(ctx.body), "default")) { v = 0; } else { ret = -EINVAL; goto out; } bfqg = blkg_to_bfqg(ctx.blkg); ret = -ERANGE; if (!v || (v >= BFQ_MIN_WEIGHT && v <= BFQ_MAX_WEIGHT)) { bfq_group_set_weight(bfqg, bfqg->entity.weight, v); ret = 0; } out: blkg_conf_exit(&ctx); return ret ?: nbytes; } static ssize_t bfq_io_set_weight(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { char *endp; int ret; u64 v; buf = strim(buf); /* "WEIGHT" or "default WEIGHT" sets the default weight */ v = simple_strtoull(buf, &endp, 0); if (*endp == '\0' || sscanf(buf, "default %llu", &v) == 1) { ret = bfq_io_set_weight_legacy(of_css(of), NULL, v); return ret ?: nbytes; } return bfq_io_set_device_weight(of, buf, nbytes, off); } static int bfqg_print_rwstat(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat, &blkcg_policy_bfq, seq_cft(sf)->private, true); return 0; } static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct blkg_rwstat_sample sum; blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum); return __blkg_prfill_rwstat(sf, pd, &sum); } static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq, seq_cft(sf)->private, true); return 0; } #ifdef CONFIG_BFQ_CGROUP_DEBUG static int bfqg_print_stat(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat, &blkcg_policy_bfq, seq_cft(sf)->private, false); return 0; } static u64 bfqg_prfill_stat_recursive(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct blkcg_gq *blkg = pd_to_blkg(pd); struct blkcg_gq *pos_blkg; struct cgroup_subsys_state *pos_css; u64 sum = 0; lockdep_assert_held(&blkg->q->queue_lock); rcu_read_lock(); blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { struct bfq_stat *stat; if (!pos_blkg->online) continue; stat = (void *)blkg_to_pd(pos_blkg, &blkcg_policy_bfq) + off; sum += bfq_stat_read(stat) + atomic64_read(&stat->aux_cnt); } rcu_read_unlock(); return __blkg_prfill_u64(sf, pd, sum); } static int bfqg_print_stat_recursive(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), bfqg_prfill_stat_recursive, &blkcg_policy_bfq, seq_cft(sf)->private, false); return 0; } static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct bfq_group *bfqg = blkg_to_bfqg(pd->blkg); u64 sum = blkg_rwstat_total(&bfqg->stats.bytes); return __blkg_prfill_u64(sf, pd, sum >> 9); } static int bfqg_print_stat_sectors(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), bfqg_prfill_sectors, &blkcg_policy_bfq, 0, false); return 0; } static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct blkg_rwstat_sample tmp; blkg_rwstat_recursive_sum(pd->blkg, &blkcg_policy_bfq, offsetof(struct bfq_group, stats.bytes), &tmp); return __blkg_prfill_u64(sf, pd, (tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]) >> 9); } static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), bfqg_prfill_sectors_recursive, &blkcg_policy_bfq, 0, false); return 0; } static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct bfq_group *bfqg = pd_to_bfqg(pd); u64 samples = bfq_stat_read(&bfqg->stats.avg_queue_size_samples); u64 v = 0; if (samples) { v = bfq_stat_read(&bfqg->stats.avg_queue_size_sum); v = div64_u64(v, samples); } __blkg_prfill_u64(sf, pd, v); return 0; } /* print avg_queue_size */ static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), bfqg_prfill_avg_queue_size, &blkcg_policy_bfq, 0, false); return 0; } #endif /* CONFIG_BFQ_CGROUP_DEBUG */ struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) { int ret; ret = blkcg_activate_policy(bfqd->queue->disk, &blkcg_policy_bfq); if (ret) return NULL; return blkg_to_bfqg(bfqd->queue->root_blkg); } struct blkcg_policy blkcg_policy_bfq = { .dfl_cftypes = bfq_blkg_files, .legacy_cftypes = bfq_blkcg_legacy_files, .cpd_alloc_fn = bfq_cpd_alloc, .cpd_free_fn = bfq_cpd_free, .pd_alloc_fn = bfq_pd_alloc, .pd_init_fn = bfq_pd_init, .pd_offline_fn = bfq_pd_offline, .pd_free_fn = bfq_pd_free, .pd_reset_stats_fn = bfq_pd_reset_stats, }; struct cftype bfq_blkcg_legacy_files[] = { { .name = "bfq.weight", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = bfq_io_show_weight_legacy, .write_u64 = bfq_io_set_weight_legacy, }, { .name = "bfq.weight_device", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = bfq_io_show_weight, .write = bfq_io_set_weight, }, /* statistics, covers only the tasks in the bfqg */ { .name = "bfq.io_service_bytes", .private = offsetof(struct bfq_group, stats.bytes), .seq_show = bfqg_print_rwstat, }, { .name = "bfq.io_serviced", .private = offsetof(struct bfq_group, stats.ios), .seq_show = bfqg_print_rwstat, }, #ifdef CONFIG_BFQ_CGROUP_DEBUG { .name = "bfq.time", .private = offsetof(struct bfq_group, stats.time), .seq_show = bfqg_print_stat, }, { .name = "bfq.sectors", .seq_show = bfqg_print_stat_sectors, }, { .name = "bfq.io_service_time", .private = offsetof(struct bfq_group, stats.service_time), .seq_show = bfqg_print_rwstat, }, { .name = "bfq.io_wait_time", .private = offsetof(struct bfq_group, stats.wait_time), .seq_show = bfqg_print_rwstat, }, { .name = "bfq.io_merged", .private = offsetof(struct bfq_group, stats.merged), .seq_show = bfqg_print_rwstat, }, { .name = "bfq.io_queued", .private = offsetof(struct bfq_group, stats.queued), .seq_show = bfqg_print_rwstat, }, #endif /* CONFIG_BFQ_CGROUP_DEBUG */ /* the same statistics which cover the bfqg and its descendants */ { .name = "bfq.io_service_bytes_recursive", .private = offsetof(struct bfq_group, stats.bytes), .seq_show = bfqg_print_rwstat_recursive, }, { .name = "bfq.io_serviced_recursive", .private = offsetof(struct bfq_group, stats.ios), .seq_show = bfqg_print_rwstat_recursive, }, #ifdef CONFIG_BFQ_CGROUP_DEBUG { .name = "bfq.time_recursive", .private = offsetof(struct bfq_group, stats.time), .seq_show = bfqg_print_stat_recursive, }, { .name = "bfq.sectors_recursive", .seq_show = bfqg_print_stat_sectors_recursive, }, { .name = "bfq.io_service_time_recursive", .private = offsetof(struct bfq_group, stats.service_time), .seq_show = bfqg_print_rwstat_recursive, }, { .name = "bfq.io_wait_time_recursive", .private = offsetof(struct bfq_group, stats.wait_time), .seq_show = bfqg_print_rwstat_recursive, }, { .name = "bfq.io_merged_recursive", .private = offsetof(struct bfq_group, stats.merged), .seq_show = bfqg_print_rwstat_recursive, }, { .name = "bfq.io_queued_recursive", .private = offsetof(struct bfq_group, stats.queued), .seq_show = bfqg_print_rwstat_recursive, }, { .name = "bfq.avg_queue_size", .seq_show = bfqg_print_avg_queue_size, }, { .name = "bfq.group_wait_time", .private = offsetof(struct bfq_group, stats.group_wait_time), .seq_show = bfqg_print_stat, }, { .name = "bfq.idle_time", .private = offsetof(struct bfq_group, stats.idle_time), .seq_show = bfqg_print_stat, }, { .name = "bfq.empty_time", .private = offsetof(struct bfq_group, stats.empty_time), .seq_show = bfqg_print_stat, }, { .name = "bfq.dequeue", .private = offsetof(struct bfq_group, stats.dequeue), .seq_show = bfqg_print_stat, }, #endif /* CONFIG_BFQ_CGROUP_DEBUG */ { } /* terminate */ }; struct cftype bfq_blkg_files[] = { { .name = "bfq.weight", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = bfq_io_show_weight, .write = bfq_io_set_weight, }, {} /* terminate */ }; #else /* CONFIG_BFQ_GROUP_IOSCHED */ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct bfq_group *bfqg) {} void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg) { struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); entity->weight = entity->new_weight; entity->orig_weight = entity->new_weight; if (bfqq) { bfqq->ioprio = bfqq->new_ioprio; bfqq->ioprio_class = bfqq->new_ioprio_class; } entity->sched_data = &bfqg->sched_data; } void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) {} void bfq_end_wr_async(struct bfq_data *bfqd) { bfq_end_wr_async_queues(bfqd, bfqd->root_group); } struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio) { return bfqd->root_group; } struct bfq_group *bfqq_group(struct bfq_queue *bfqq) { return bfqq->bfqd->root_group; } void bfqg_and_blkg_put(struct bfq_group *bfqg) {} struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) { struct bfq_group *bfqg; int i; bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node); if (!bfqg) return NULL; for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT; return bfqg; } #endif /* CONFIG_BFQ_GROUP_IOSCHED */ |
| 9 25 13 16 16 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #ifndef _WG_QUEUEING_H #define _WG_QUEUEING_H #include "peer.h" #include <linux/types.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <net/ip_tunnels.h> struct wg_device; struct wg_peer; struct multicore_worker; struct crypt_queue; struct prev_queue; struct sk_buff; /* queueing.c APIs: */ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, unsigned int len); void wg_packet_queue_free(struct crypt_queue *queue, bool purge); struct multicore_worker __percpu * wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr); /* receive.c APIs: */ void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb); void wg_packet_handshake_receive_worker(struct work_struct *work); /* NAPI poll function: */ int wg_packet_rx_poll(struct napi_struct *napi, int budget); /* Workqueue worker: */ void wg_packet_decrypt_worker(struct work_struct *work); /* send.c APIs: */ void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer, bool is_retry); void wg_packet_send_handshake_response(struct wg_peer *peer); void wg_packet_send_handshake_cookie(struct wg_device *wg, struct sk_buff *initiating_skb, __le32 sender_index); void wg_packet_send_keepalive(struct wg_peer *peer); void wg_packet_purge_staged_packets(struct wg_peer *peer); void wg_packet_send_staged_packets(struct wg_peer *peer); /* Workqueue workers: */ void wg_packet_handshake_send_worker(struct work_struct *work); void wg_packet_tx_worker(struct work_struct *work); void wg_packet_encrypt_worker(struct work_struct *work); enum packet_state { PACKET_STATE_UNCRYPTED, PACKET_STATE_CRYPTED, PACKET_STATE_DEAD }; struct packet_cb { u64 nonce; struct noise_keypair *keypair; atomic_t state; u32 mtu; u8 ds; }; #define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb)) #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer) static inline bool wg_check_packet_protocol(struct sk_buff *skb) { __be16 real_protocol = ip_tunnel_parse_protocol(skb); return real_protocol && skb->protocol == real_protocol; } static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating) { u8 l4_hash = skb->l4_hash; u8 sw_hash = skb->sw_hash; u32 hash = skb->hash; skb_scrub_packet(skb, true); memset(&skb->headers, 0, sizeof(skb->headers)); if (encapsulating) { skb->l4_hash = l4_hash; skb->sw_hash = sw_hash; skb->hash = hash; } skb->queue_mapping = 0; skb->nohdr = 0; skb->peeked = 0; skb->mac_len = 0; skb->dev = NULL; #ifdef CONFIG_NET_SCHED skb->tc_index = 0; #endif skb_reset_redirect(skb); skb->hdr_len = skb_headroom(skb); skb_reset_mac_header(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb_probe_transport_header(skb); skb_reset_inner_headers(skb); } static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id) { unsigned int cpu = *stored_cpu, cpu_index, i; if (unlikely(cpu >= nr_cpu_ids || !cpumask_test_cpu(cpu, cpu_online_mask))) { cpu_index = id % cpumask_weight(cpu_online_mask); cpu = cpumask_first(cpu_online_mask); for (i = 0; i < cpu_index; ++i) cpu = cpumask_next(cpu, cpu_online_mask); *stored_cpu = cpu; } return cpu; } /* This function is racy, in the sense that it's called while last_cpu is * unlocked, so it could return the same CPU twice. Adding locking or using * atomic sequence numbers is slower though, and the consequences of racing are * harmless, so live with it. */ static inline int wg_cpumask_next_online(int *last_cpu) { int cpu = cpumask_next(*last_cpu, cpu_online_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(cpu_online_mask); *last_cpu = cpu; return cpu; } void wg_prev_queue_init(struct prev_queue *queue); /* Multi producer */ bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb); /* Single consumer */ struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue); /* Single consumer */ static inline struct sk_buff *wg_prev_queue_peek(struct prev_queue *queue) { if (queue->peeked) return queue->peeked; queue->peeked = wg_prev_queue_dequeue(queue); return queue->peeked; } /* Single consumer */ static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue) { queue->peeked = NULL; } static inline int wg_queue_enqueue_per_device_and_peer( struct crypt_queue *device_queue, struct prev_queue *peer_queue, struct sk_buff *skb, struct workqueue_struct *wq) { int cpu; atomic_set_release(&PACKET_CB(skb)->state, PACKET_STATE_UNCRYPTED); /* We first queue this up for the peer ingestion, but the consumer * will wait for the state to change to CRYPTED or DEAD before. */ if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb))) return -ENOSPC; /* Then we queue it up in the device queue, which consumes the * packet as soon as it can. */ cpu = wg_cpumask_next_online(&device_queue->last_cpu); if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb))) return -EPIPE; queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work); return 0; } static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state) { /* We take a reference, because as soon as we call atomic_set, the * peer can be freed from below us. */ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); atomic_set_release(&PACKET_CB(skb)->state, state); queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, peer->internal_id), peer->device->packet_crypt_wq, &peer->transmit_packet_work); wg_peer_put(peer); } static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state) { /* We take a reference, because as soon as we call atomic_set, the * peer can be freed from below us. */ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); atomic_set_release(&PACKET_CB(skb)->state, state); napi_schedule(&peer->napi); wg_peer_put(peer); } #ifdef DEBUG bool wg_packet_counter_selftest(void); #endif #endif /* _WG_QUEUEING_H */ |
| 145 169 2 2 2 2 2 2 2 2 2 67 67 67 67 63 63 1 1 1 1 1 1 1 32 5 5 5 5 5 5 5 5 5 5 5 5 67 67 63 63 83 68 82 82 82 82 82 82 80 67 67 83 1 63 63 63 63 57 63 62 62 63 63 63 62 63 63 59 59 1 1 1 1 73 73 3 73 73 68 68 68 4 4 12 12 12 12 12 12 5 12 4 12 2 12 2 12 2 12 12 12 12 4 4 4 4 4 3 3 3 3 3 3 3 3 3 3 3 1 1 61 61 2 4 1 1 1 1 1 1 1 352 4 7 1 32 1 49 49 4 4 4 4 4 68 68 73 73 72 72 73 73 73 73 12 73 72 73 73 2 2 71 71 72 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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) 2001-2002 Intel Corp. * Copyright (c) 2002 Nokia Corp. * * This is part of the SCTP Linux Kernel Implementation. * * These are the state functions for the 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> * Mathew Kotowsky <kotowsky@sctp.org> * Sridhar Samudrala <samudrala@us.ibm.com> * Jon Grimm <jgrimm@us.ibm.com> * Hui Huang <hui.huang@nokia.com> * Dajiang Zhang <dajiang.zhang@nokia.com> * Daisy Chang <daisyc@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> * Ryan Layer <rmlayer@us.ibm.com> * Kevin Gao <kevin.gao@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/kernel.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/slab.h> #include <net/sock.h> #include <net/inet_ecn.h> #include <linux/skbuff.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/structs.h> #define CREATE_TRACE_POINTS #include <trace/events/sctp.h> static struct sctp_packet *sctp_abort_pkt_new( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, const void *payload, size_t paylen); static int sctp_eat_data(const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_cmd_seq *commands); static struct sctp_packet *sctp_ootb_pkt_new( struct net *net, const struct sctp_association *asoc, const struct sctp_chunk *chunk); static void sctp_send_stale_cookie_err(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const struct sctp_chunk *chunk, struct sctp_cmd_seq *commands, struct sctp_chunk *err_chunk); static enum sctp_disposition sctp_sf_do_5_2_6_stale( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); static enum sctp_disposition sctp_sf_shut_8_4_5( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); static enum sctp_disposition sctp_sf_tabort_8_4_8( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); static enum sctp_disposition sctp_sf_new_encap_port( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk); static enum sctp_disposition sctp_stop_t1_and_abort( struct net *net, struct sctp_cmd_seq *commands, __be16 error, int sk_err, const struct sctp_association *asoc, struct sctp_transport *transport); static enum sctp_disposition sctp_sf_abort_violation( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, void *arg, struct sctp_cmd_seq *commands, const __u8 *payload, const size_t paylen); static enum sctp_disposition sctp_sf_violation_chunklen( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); static enum sctp_disposition sctp_sf_violation_paramlen( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, void *ext, struct sctp_cmd_seq *commands); static enum sctp_disposition sctp_sf_violation_ctsn( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); static enum sctp_disposition sctp_sf_violation_chunk( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); static enum sctp_ierror sctp_sf_authenticate( const struct sctp_association *asoc, struct sctp_chunk *chunk); static enum sctp_disposition __sctp_sf_do_9_1_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); static enum sctp_disposition __sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); /* Small helper function that checks if the chunk length * is of the appropriate length. The 'required_length' argument * is set to be the size of a specific chunk we are testing. * Return Values: true = Valid length * false = Invalid length * */ static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk, __u16 required_length) { __u16 chunk_length = ntohs(chunk->chunk_hdr->length); /* Previously already marked? */ if (unlikely(chunk->pdiscard)) return false; if (unlikely(chunk_length < required_length)) return false; return true; } /* Check for format error in an ABORT chunk */ static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk) { struct sctp_errhdr *err; sctp_walk_errors(err, chunk->chunk_hdr); return (void *)err == (void *)chunk->chunk_end; } /********************************************************** * These are the state functions for handling chunk events. **********************************************************/ /* * Process the final SHUTDOWN COMPLETE. * * Section: 4 (C) (diagram), 9.2 * Upon reception of the SHUTDOWN COMPLETE chunk the endpoint will verify * that it is in SHUTDOWN-ACK-SENT state, if it is not the chunk should be * discarded. If the endpoint is in the SHUTDOWN-ACK-SENT state the endpoint * should stop the T2-shutdown timer and remove all knowledge of the * association (and thus the association enters the CLOSED state). * * Verification Tag: 8.5.1(C), sctpimpguide 2.41. * C) Rules for packet carrying SHUTDOWN COMPLETE: * ... * - The receiver of a SHUTDOWN COMPLETE shall accept the packet * if the Verification Tag field of the packet matches its own tag and * the T bit is not set * OR * it is set to its peer's tag and the T bit is set in the Chunk * Flags. * Otherwise, the receiver MUST silently discard the packet * and take no further action. An endpoint MUST ignore the * SHUTDOWN COMPLETE if it is not in the SHUTDOWN-ACK-SENT state. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_4_C(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_ulpevent *ev; if (!sctp_vtag_verify_either(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* RFC 2960 6.10 Bundling * * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. */ if (!chunk->singleton) return sctp_sf_violation_chunk(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN_COMPLETE chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* RFC 2960 10.2 SCTP-to-ULP * * H) SHUTDOWN COMPLETE notification * * When SCTP completes the shutdown procedures (section 9.2) this * notification is passed to the upper layer. */ ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_SHUTDOWN_COMP, 0, 0, 0, NULL, GFP_ATOMIC); if (ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); /* Upon reception of the SHUTDOWN COMPLETE chunk the endpoint * will verify that it is in SHUTDOWN-ACK-SENT state, if it is * not the chunk should be discarded. If the endpoint is in * the SHUTDOWN-ACK-SENT state the endpoint should stop the * T2-shutdown timer and remove all knowledge of the * association (and thus the association enters the CLOSED * state). */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); SCTP_INC_STATS(net, SCTP_MIB_SHUTDOWNS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); return SCTP_DISPOSITION_DELETE_TCB; } /* * Respond to a normal INIT chunk. * We are the side that is being asked for an association. * * Section: 5.1 Normal Establishment of an Association, B * B) "Z" shall respond immediately with an INIT ACK chunk. The * destination IP address of the INIT ACK MUST be set to the source * IP address of the INIT to which this INIT ACK is responding. In * the response, besides filling in other parameters, "Z" must set the * Verification Tag field to Tag_A, and also provide its own * Verification Tag (Tag_Z) in the Initiate Tag field. * * Verification Tag: Must be 0. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg, *repl, *err_chunk; struct sctp_unrecognized_param *unk_param; struct sctp_association *new_asoc; struct sctp_packet *packet; int len; /* 6.10 Bundling * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. * * IG Section 2.11.2 * Furthermore, we require that the receiver of an INIT chunk MUST * enforce these rules by silently discarding an arriving packet * with an INIT chunk that is bundled with other chunks. */ if (!chunk->singleton) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the INIT chunk has a valid length. * Normally, this would cause an ABORT with a Protocol Violation * error, but since we don't have an association, we'll * just discard the packet. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* If the packet is an OOTB packet which is temporarily on the * control endpoint, respond with an ABORT. */ if (ep == sctp_sk(net->sctp.ctl_sock)->ep) { SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); } /* 3.1 A packet containing an INIT chunk MUST have a zero Verification * Tag. */ if (chunk->sctp_hdr->vtag != 0) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); /* If the INIT is coming toward a closing socket, we'll send back * and ABORT. Essentially, this catches the race of INIT being * backloged to the socket at the same time as the user issues close(). * Since the socket and all its associations are going away, we * can treat this OOTB */ if (sctp_sstate(ep->base.sk, CLOSING)) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (struct sctp_init_chunk *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. * Send an ABORT, with causes if there is any. */ if (err_chunk) { packet = sctp_abort_pkt_new(net, ep, asoc, arg, (__u8 *)(err_chunk->chunk_hdr) + sizeof(struct sctp_chunkhdr), ntohs(err_chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr)); sctp_chunk_free(err_chunk); if (packet) { sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); return SCTP_DISPOSITION_CONSUME; } else { return SCTP_DISPOSITION_NOMEM; } } else { return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); } } /* Grab the INIT header. */ chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data; /* Tag the variable length parameters. */ chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(struct sctp_inithdr)); new_asoc = sctp_make_temp_asoc(ep, chunk, GFP_ATOMIC); if (!new_asoc) goto nomem; /* Update socket peer label if first association. */ if (security_sctp_assoc_request(new_asoc, chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } if (sctp_assoc_set_bind_addr_from_ep(new_asoc, sctp_scope(sctp_source(chunk)), GFP_ATOMIC) < 0) goto nomem_init; /* The call, sctp_process_init(), can fail on memory allocation. */ if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), (struct sctp_init_chunk *)chunk->chunk_hdr, GFP_ATOMIC)) goto nomem_init; /* B) "Z" shall respond immediately with an INIT ACK chunk. */ /* If there are errors need to be reported for unknown parameters, * make sure to reserve enough room in the INIT ACK for them. */ len = 0; if (err_chunk) len = ntohs(err_chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr); repl = sctp_make_init_ack(new_asoc, chunk, GFP_ATOMIC, len); if (!repl) goto nomem_init; /* If there are errors need to be reported for unknown parameters, * include them in the outgoing INIT ACK as "Unrecognized parameter" * parameter. */ if (err_chunk) { /* Get the "Unrecognized parameter" parameter(s) out of the * ERROR chunk generated by sctp_verify_init(). Since the * error cause code for "unknown parameter" and the * "Unrecognized parameter" type is the same, we can * construct the parameters in INIT ACK by copying the * ERROR causes over. */ unk_param = (struct sctp_unrecognized_param *) ((__u8 *)(err_chunk->chunk_hdr) + sizeof(struct sctp_chunkhdr)); /* Replace the cause code with the "Unrecognized parameter" * parameter type. */ sctp_addto_chunk(repl, len, unk_param); sctp_chunk_free(err_chunk); } sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); /* * Note: After sending out INIT ACK with the State Cookie parameter, * "Z" MUST NOT allocate any resources, nor keep any states for the * new association. Otherwise, "Z" will be vulnerable to resource * attacks. */ sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); return SCTP_DISPOSITION_DELETE_TCB; nomem_init: sctp_association_free(new_asoc); nomem: if (err_chunk) sctp_chunk_free(err_chunk); return SCTP_DISPOSITION_NOMEM; } /* * Respond to a normal INIT ACK chunk. * We are the side that is initiating the association. * * Section: 5.1 Normal Establishment of an Association, C * C) Upon reception of the INIT ACK from "Z", "A" shall stop the T1-init * timer and leave COOKIE-WAIT state. "A" shall then send the State * Cookie received in the INIT ACK chunk in a COOKIE ECHO chunk, start * the T1-cookie timer, and enter the COOKIE-ECHOED state. * * Note: The COOKIE ECHO chunk can be bundled with any pending outbound * DATA chunks, but it MUST be the first chunk in the packet and * until the COOKIE ACK is returned the sender MUST NOT send any * other packets to the peer. * * Verification Tag: 3.3.3 * If the value of the Initiate Tag in a received INIT ACK chunk is * found to be 0, the receiver MUST treat it as an error and close the * association by transmitting an ABORT. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_init_chunk *initchunk; struct sctp_chunk *chunk = arg; struct sctp_chunk *err_chunk; struct sctp_packet *packet; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* 6.10 Bundling * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. */ if (!chunk->singleton) return sctp_sf_violation_chunk(net, ep, asoc, type, arg, commands); /* Make sure that the INIT-ACK chunk has a valid length */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_initack_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Grab the INIT header. */ chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data; /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (struct sctp_init_chunk *)chunk->chunk_hdr, chunk, &err_chunk)) { enum sctp_error error = SCTP_ERROR_NO_RESOURCE; /* This chunk contains fatal error. It is to be discarded. * Send an ABORT, with causes. If there are no causes, * then there wasn't enough memory. Just terminate * the association. */ if (err_chunk) { packet = sctp_abort_pkt_new(net, ep, asoc, arg, (__u8 *)(err_chunk->chunk_hdr) + sizeof(struct sctp_chunkhdr), ntohs(err_chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr)); sctp_chunk_free(err_chunk); if (packet) { sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); error = SCTP_ERROR_INV_PARAM; } } /* SCTP-AUTH, Section 6.3: * It should be noted that if the receiver wants to tear * down an association in an authenticated way only, the * handling of malformed packets should not result in * tearing down the association. * * This means that if we only want to abort associations * in an authenticated way (i.e AUTH+ABORT), then we * can't destroy this association just because the packet * was malformed. */ if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); return sctp_stop_t1_and_abort(net, commands, error, ECONNREFUSED, asoc, chunk->transport); } /* Tag the variable length parameters. Note that we never * convert the parameters in an INIT chunk. */ chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(struct sctp_inithdr)); initchunk = (struct sctp_init_chunk *)chunk->chunk_hdr; sctp_add_cmd_sf(commands, SCTP_CMD_PEER_INIT, SCTP_PEER_INIT(initchunk)); /* Reset init error count upon receipt of INIT-ACK. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_RESET, SCTP_NULL()); /* 5.1 C) "A" shall stop the T1-init timer and leave * COOKIE-WAIT state. "A" shall then ... start the T1-cookie * timer, and enter the COOKIE-ECHOED state. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_COOKIE)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_COOKIE_ECHOED)); /* SCTP-AUTH: generate the association shared keys so that * we can potentially sign the COOKIE-ECHO. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL()); /* 5.1 C) "A" shall then send the State Cookie received in the * INIT ACK chunk in a COOKIE ECHO chunk, ... */ /* If there is any errors to report, send the ERROR chunk generated * for unknown parameters as well. */ sctp_add_cmd_sf(commands, SCTP_CMD_GEN_COOKIE_ECHO, SCTP_CHUNK(err_chunk)); return SCTP_DISPOSITION_CONSUME; } static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk, const struct sctp_association *asoc) { struct sctp_chunk auth; if (!chunk->auth_chunk) return true; /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo * is supposed to be authenticated and we have to do delayed * authentication. We've just recreated the association using * the information in the cookie and now it's much easier to * do the authentication. */ /* Make sure that we and the peer are AUTH capable */ if (!net->sctp.auth_enable || !asoc->peer.auth_capable) return false; /* set-up our fake chunk so that we can process it */ auth.skb = chunk->auth_chunk; auth.asoc = chunk->asoc; auth.sctp_hdr = chunk->sctp_hdr; auth.chunk_hdr = (struct sctp_chunkhdr *) skb_push(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); auth.transport = chunk->transport; return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR; } /* * Respond to a normal COOKIE ECHO chunk. * We are the side that is being asked for an association. * * Section: 5.1 Normal Establishment of an Association, D * D) Upon reception of the COOKIE ECHO chunk, Endpoint "Z" will reply * with a COOKIE ACK chunk after building a TCB and moving to * the ESTABLISHED state. A COOKIE ACK chunk may be bundled with * any pending DATA chunks (and/or SACK chunks), but the COOKIE ACK * chunk MUST be the first chunk in the packet. * * IMPLEMENTATION NOTE: An implementation may choose to send the * Communication Up notification to the SCTP user upon reception * of a valid COOKIE ECHO chunk. * * Verification Tag: 8.5.1 Exceptions in Verification Tag Rules * D) Rules for packet carrying a COOKIE ECHO * * - When sending a COOKIE ECHO, the endpoint MUST use the value of the * Initial Tag received in the INIT ACK. * * - The receiver of a COOKIE ECHO follows the procedures in Section 5. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_ulpevent *ev, *ai_ev = NULL, *auth_ev = NULL; struct sctp_association *new_asoc; struct sctp_init_chunk *peer_init; struct sctp_chunk *chunk = arg; struct sctp_chunk *err_chk_p; struct sctp_chunk *repl; struct sock *sk; int error = 0; if (asoc && !sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* If the packet is an OOTB packet which is temporarily on the * control endpoint, respond with an ABORT. */ if (ep == sctp_sk(net->sctp.ctl_sock)->ep) { SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); } /* Make sure that the COOKIE_ECHO chunk has a valid length. * In this case, we check that we have enough for at least a * chunk header. More detailed verification is done * in sctp_unpack_cookie(). */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* If the endpoint is not listening or if the number of associations * on the TCP-style socket exceed the max backlog, respond with an * ABORT. */ sk = ep->base.sk; if (!sctp_sstate(sk, LISTENING) || (sctp_style(sk, TCP) && sk_acceptq_is_full(sk))) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); /* "Decode" the chunk. We have no optional parameters so we * are in good shape. */ chunk->subh.cookie_hdr = (struct sctp_signed_cookie *)chunk->skb->data; if (!pskb_pull(chunk->skb, ntohs(chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr))) goto nomem; /* 5.1 D) Upon reception of the COOKIE ECHO chunk, Endpoint * "Z" will reply with a COOKIE ACK chunk after building a TCB * and moving to the ESTABLISHED state. */ new_asoc = sctp_unpack_cookie(ep, asoc, chunk, GFP_ATOMIC, &error, &err_chk_p); /* FIXME: * If the re-build failed, what is the proper error path * from here? * * [We should abort the association. --piggy] */ if (!new_asoc) { /* FIXME: Several errors are possible. A bad cookie should * be silently discarded, but think about logging it too. */ switch (error) { case -SCTP_IERROR_NOMEM: goto nomem; case -SCTP_IERROR_STALE_COOKIE: sctp_send_stale_cookie_err(net, ep, asoc, chunk, commands, err_chk_p); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); case -SCTP_IERROR_BAD_SIG: default: return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } } if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } /* Delay state machine commands until later. * * Re-build the bind address for the association is done in * the sctp_unpack_cookie() already. */ /* This is a brand-new association, so these are not yet side * effects--it is safe to run them here. */ peer_init = (struct sctp_init_chunk *)(chunk->subh.cookie_hdr + 1); if (!sctp_process_init(new_asoc, chunk, &chunk->subh.cookie_hdr->c.peer_addr, peer_init, GFP_ATOMIC)) goto nomem_init; /* SCTP-AUTH: Now that we've populate required fields in * sctp_process_init, set up the association shared keys as * necessary so that we can potentially authenticate the ACK */ error = sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC); if (error) goto nomem_init; if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } repl = sctp_make_cookie_ack(new_asoc, chunk); if (!repl) goto nomem_init; /* RFC 2960 5.1 Normal Establishment of an Association * * D) IMPLEMENTATION NOTE: An implementation may choose to * send the Communication Up notification to the SCTP user * upon reception of a valid COOKIE ECHO chunk. */ ev = sctp_ulpevent_make_assoc_change(new_asoc, 0, SCTP_COMM_UP, 0, new_asoc->c.sinit_num_ostreams, new_asoc->c.sinit_max_instreams, NULL, GFP_ATOMIC); if (!ev) goto nomem_ev; /* Sockets API Draft Section 5.3.1.6 * When a peer sends a Adaptation Layer Indication parameter , SCTP * delivers this notification to inform the application that of the * peers requested adaptation layer. */ if (new_asoc->peer.adaptation_ind) { ai_ev = sctp_ulpevent_make_adaptation_indication(new_asoc, GFP_ATOMIC); if (!ai_ev) goto nomem_aiev; } if (!new_asoc->peer.auth_capable) { auth_ev = sctp_ulpevent_make_authkey(new_asoc, 0, SCTP_AUTH_NO_AUTH, GFP_ATOMIC); if (!auth_ev) goto nomem_authev; } /* Add all the state machine commands now since we've created * everything. This way we don't introduce memory corruptions * during side-effect processing and correctly count established * associations. */ sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_ESTABLISHED)); SCTP_INC_STATS(net, SCTP_MIB_CURRESTAB); SCTP_INC_STATS(net, SCTP_MIB_PASSIVEESTABS); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL()); if (new_asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); /* This will send the COOKIE ACK */ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); /* Queue the ASSOC_CHANGE event */ sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); /* Send up the Adaptation Layer Indication event */ if (ai_ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ai_ev)); if (auth_ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(auth_ev)); return SCTP_DISPOSITION_CONSUME; nomem_authev: sctp_ulpevent_free(ai_ev); nomem_aiev: sctp_ulpevent_free(ev); nomem_ev: sctp_chunk_free(repl); nomem_init: sctp_association_free(new_asoc); nomem: return SCTP_DISPOSITION_NOMEM; } /* * Respond to a normal COOKIE ACK chunk. * We are the side that is asking for an association. * * RFC 2960 5.1 Normal Establishment of an Association * * E) Upon reception of the COOKIE ACK, endpoint "A" will move from the * COOKIE-ECHOED state to the ESTABLISHED state, stopping the T1-cookie * timer. It may also notify its ULP about the successful * establishment of the association with a Communication Up * notification (see Section 10). * * Verification Tag: * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_ulpevent *ev; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Set peer label for connection. */ if (security_sctp_assoc_established((struct sctp_association *)asoc, chunk->head_skb ?: chunk->skb)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Verify that the chunk length for the COOKIE-ACK is OK. * If we don't do this, any bundled chunks may be junked. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Reset init error count upon receipt of COOKIE-ACK, * to avoid problems with the management of this * counter in stale cookie situations when a transition back * from the COOKIE-ECHOED state to the COOKIE-WAIT * state is performed. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_RESET, SCTP_NULL()); /* RFC 2960 5.1 Normal Establishment of an Association * * E) Upon reception of the COOKIE ACK, endpoint "A" will move * from the COOKIE-ECHOED state to the ESTABLISHED state, * stopping the T1-cookie timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_COOKIE)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_ESTABLISHED)); SCTP_INC_STATS(net, SCTP_MIB_CURRESTAB); SCTP_INC_STATS(net, SCTP_MIB_ACTIVEESTABS); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL()); if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); /* It may also notify its ULP about the successful * establishment of the association with a Communication Up * notification (see Section 10). */ ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_COMM_UP, 0, asoc->c.sinit_num_ostreams, asoc->c.sinit_max_instreams, NULL, GFP_ATOMIC); if (!ev) goto nomem; sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); /* Sockets API Draft Section 5.3.1.6 * When a peer sends a Adaptation Layer Indication parameter , SCTP * delivers this notification to inform the application that of the * peers requested adaptation layer. */ if (asoc->peer.adaptation_ind) { ev = sctp_ulpevent_make_adaptation_indication(asoc, GFP_ATOMIC); if (!ev) goto nomem; sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); } if (!asoc->peer.auth_capable) { ev = sctp_ulpevent_make_authkey(asoc, 0, SCTP_AUTH_NO_AUTH, GFP_ATOMIC); if (!ev) goto nomem; sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); } return SCTP_DISPOSITION_CONSUME; nomem: return SCTP_DISPOSITION_NOMEM; } /* Generate and sendout a heartbeat packet. */ static enum sctp_disposition sctp_sf_heartbeat( const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_transport *transport = (struct sctp_transport *) arg; struct sctp_chunk *reply; /* Send a heartbeat to our peer. */ reply = sctp_make_heartbeat(asoc, transport, 0); if (!reply) return SCTP_DISPOSITION_NOMEM; /* Set rto_pending indicating that an RTT measurement * is started with this heartbeat chunk. */ sctp_add_cmd_sf(commands, SCTP_CMD_RTO_PENDING, SCTP_TRANSPORT(transport)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); return SCTP_DISPOSITION_CONSUME; } /* Generate a HEARTBEAT packet on the given transport. */ enum sctp_disposition sctp_sf_sendbeat_8_3(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_transport *transport = (struct sctp_transport *) arg; if (asoc->overall_error_count >= asoc->max_retrans) { sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_NO_ERROR)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_DISPOSITION_DELETE_TCB; } /* Section 3.3.5. * The Sender-specific Heartbeat Info field should normally include * information about the sender's current time when this HEARTBEAT * chunk is sent and the destination transport address to which this * HEARTBEAT is sent (see Section 8.3). */ if (transport->param_flags & SPP_HB_ENABLE) { if (SCTP_DISPOSITION_NOMEM == sctp_sf_heartbeat(ep, asoc, type, arg, commands)) return SCTP_DISPOSITION_NOMEM; /* Set transport error counter and association error counter * when sending heartbeat. */ sctp_add_cmd_sf(commands, SCTP_CMD_TRANSPORT_HB_SENT, SCTP_TRANSPORT(transport)); } sctp_add_cmd_sf(commands, SCTP_CMD_TRANSPORT_IDLE, SCTP_TRANSPORT(transport)); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMER_UPDATE, SCTP_TRANSPORT(transport)); return SCTP_DISPOSITION_CONSUME; } /* resend asoc strreset_chunk. */ enum sctp_disposition sctp_sf_send_reconf(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_transport *transport = arg; if (asoc->overall_error_count >= asoc->max_retrans) { sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_NO_ERROR)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_DISPOSITION_DELETE_TCB; } sctp_chunk_hold(asoc->strreset_chunk); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(asoc->strreset_chunk)); sctp_add_cmd_sf(commands, SCTP_CMD_STRIKE, SCTP_TRANSPORT(transport)); return SCTP_DISPOSITION_CONSUME; } /* send hb chunk with padding for PLPMUTD. */ enum sctp_disposition sctp_sf_send_probe(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_transport *transport = (struct sctp_transport *)arg; struct sctp_chunk *reply; if (!sctp_transport_pl_enabled(transport)) return SCTP_DISPOSITION_CONSUME; sctp_transport_pl_send(transport); reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); if (!reply) return SCTP_DISPOSITION_NOMEM; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE, SCTP_TRANSPORT(transport)); return SCTP_DISPOSITION_CONSUME; } /* * Process an heartbeat request. * * Section: 8.3 Path Heartbeat * The receiver of the HEARTBEAT should immediately respond with a * HEARTBEAT ACK that contains the Heartbeat Information field copied * from the received HEARTBEAT chunk. * * Verification Tag: 8.5 Verification Tag [Normal verification] * When receiving an SCTP packet, the endpoint MUST ensure that the * value in the Verification Tag field of the received SCTP packet * matches its own Tag. If the received Verification Tag value does not * match the receiver's own tag value, the receiver shall silently * discard the packet and shall not process it any further except for * those cases listed in Section 8.5.1 below. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_beat_8_3(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_paramhdr *param_hdr; struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; size_t paylen = 0; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the HEARTBEAT chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_heartbeat_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* 8.3 The receiver of the HEARTBEAT should immediately * respond with a HEARTBEAT ACK that contains the Heartbeat * Information field copied from the received HEARTBEAT chunk. */ chunk->subh.hb_hdr = (struct sctp_heartbeathdr *)chunk->skb->data; param_hdr = (struct sctp_paramhdr *)chunk->subh.hb_hdr; paylen = ntohs(chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr); if (ntohs(param_hdr->length) > paylen) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, param_hdr, commands); if (!pskb_pull(chunk->skb, paylen)) goto nomem; reply = sctp_make_heartbeat_ack(asoc, chunk, param_hdr, paylen); if (!reply) goto nomem; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); return SCTP_DISPOSITION_CONSUME; nomem: return SCTP_DISPOSITION_NOMEM; } /* * Process the returning HEARTBEAT ACK. * * Section: 8.3 Path Heartbeat * Upon the receipt of the HEARTBEAT ACK, the sender of the HEARTBEAT * should clear the error counter of the destination transport * address to which the HEARTBEAT was sent, and mark the destination * transport address as active if it is not so marked. The endpoint may * optionally report to the upper layer when an inactive destination * address is marked as active due to the reception of the latest * HEARTBEAT ACK. The receiver of the HEARTBEAT ACK must also * clear the association overall error count as well (as defined * in section 8.1). * * The receiver of the HEARTBEAT ACK should also perform an RTT * measurement for that destination transport address using the time * value carried in the HEARTBEAT ACK chunk. * * Verification Tag: 8.5 Verification Tag [Normal verification] * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_sender_hb_info *hbinfo; struct sctp_chunk *chunk = arg; struct sctp_transport *link; unsigned long max_interval; union sctp_addr from_addr; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the HEARTBEAT-ACK chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr) + sizeof(*hbinfo))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); hbinfo = (struct sctp_sender_hb_info *)chunk->skb->data; /* Make sure that the length of the parameter is what we expect */ if (ntohs(hbinfo->param_hdr.length) != sizeof(*hbinfo)) return SCTP_DISPOSITION_DISCARD; from_addr = hbinfo->daddr; link = sctp_assoc_lookup_paddr(asoc, &from_addr); /* This should never happen, but lets log it if so. */ if (unlikely(!link)) { if (from_addr.sa.sa_family == AF_INET6) { net_warn_ratelimited("%s association %p could not find address %pI6\n", __func__, asoc, &from_addr.v6.sin6_addr); } else { net_warn_ratelimited("%s association %p could not find address %pI4\n", __func__, asoc, &from_addr.v4.sin_addr.s_addr); } return SCTP_DISPOSITION_DISCARD; } /* Validate the 64-bit random nonce. */ if (hbinfo->hb_nonce != link->hb_nonce) return SCTP_DISPOSITION_DISCARD; if (hbinfo->probe_size) { if (hbinfo->probe_size != link->pl.probe_size || !sctp_transport_pl_enabled(link)) return SCTP_DISPOSITION_DISCARD; if (sctp_transport_pl_recv(link)) return SCTP_DISPOSITION_CONSUME; return sctp_sf_send_probe(net, ep, asoc, type, link, commands); } max_interval = link->hbinterval + link->rto; /* Check if the timestamp looks valid. */ if (time_after(hbinfo->sent_at, jiffies) || time_after(jiffies, hbinfo->sent_at + max_interval)) { pr_debug("%s: HEARTBEAT ACK with invalid timestamp received " "for transport:%p\n", __func__, link); return SCTP_DISPOSITION_DISCARD; } /* 8.3 Upon the receipt of the HEARTBEAT ACK, the sender of * the HEARTBEAT should clear the error counter of the * destination transport address to which the HEARTBEAT was * sent and mark the destination transport address as active if * it is not so marked. */ sctp_add_cmd_sf(commands, SCTP_CMD_TRANSPORT_ON, SCTP_TRANSPORT(link)); return SCTP_DISPOSITION_CONSUME; } /* Helper function to send out an abort for the restart * condition. */ static int sctp_sf_send_restart_abort(struct net *net, union sctp_addr *ssa, struct sctp_chunk *init, struct sctp_cmd_seq *commands) { struct sctp_af *af = sctp_get_af_specific(ssa->v4.sin_family); union sctp_addr_param *addrparm; struct sctp_errhdr *errhdr; char buffer[sizeof(*errhdr) + sizeof(*addrparm)]; struct sctp_endpoint *ep; struct sctp_packet *pkt; int len; /* Build the error on the stack. We are way to malloc crazy * throughout the code today. */ errhdr = (struct sctp_errhdr *)buffer; addrparm = (union sctp_addr_param *)(errhdr + 1); /* Copy into a parm format. */ len = af->to_addr_param(ssa, addrparm); len += sizeof(*errhdr); errhdr->cause = SCTP_ERROR_RESTART; errhdr->length = htons(len); /* Assign to the control socket. */ ep = sctp_sk(net->sctp.ctl_sock)->ep; /* Association is NULL since this may be a restart attack and we * want to send back the attacker's vtag. */ pkt = sctp_abort_pkt_new(net, ep, NULL, init, errhdr, len); if (!pkt) goto out; sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(pkt)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); /* Discard the rest of the inbound packet. */ sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); out: /* Even if there is no memory, treat as a failure so * the packet will get dropped. */ return 0; } static bool list_has_sctp_addr(const struct list_head *list, union sctp_addr *ipaddr) { struct sctp_transport *addr; list_for_each_entry(addr, list, transports) { if (sctp_cmp_addr_exact(ipaddr, &addr->ipaddr)) return true; } return false; } /* A restart is occurring, check to make sure no new addresses * are being added as we may be under a takeover attack. */ static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc, const struct sctp_association *asoc, struct sctp_chunk *init, struct sctp_cmd_seq *commands) { struct net *net = new_asoc->base.net; struct sctp_transport *new_addr; int ret = 1; /* Implementor's Guide - Section 5.2.2 * ... * Before responding the endpoint MUST check to see if the * unexpected INIT adds new addresses to the association. If new * addresses are added to the association, the endpoint MUST respond * with an ABORT.. */ /* Search through all current addresses and make sure * we aren't adding any new ones. */ list_for_each_entry(new_addr, &new_asoc->peer.transport_addr_list, transports) { if (!list_has_sctp_addr(&asoc->peer.transport_addr_list, &new_addr->ipaddr)) { sctp_sf_send_restart_abort(net, &new_addr->ipaddr, init, commands); ret = 0; break; } } /* Return success if all addresses were found. */ return ret; } /* Populate the verification/tie tags based on overlapping INIT * scenario. * * Note: Do not use in CLOSED or SHUTDOWN-ACK-SENT state. */ static void sctp_tietags_populate(struct sctp_association *new_asoc, const struct sctp_association *asoc) { switch (asoc->state) { /* 5.2.1 INIT received in COOKIE-WAIT or COOKIE-ECHOED State */ case SCTP_STATE_COOKIE_WAIT: new_asoc->c.my_vtag = asoc->c.my_vtag; new_asoc->c.my_ttag = asoc->c.my_vtag; new_asoc->c.peer_ttag = 0; break; case SCTP_STATE_COOKIE_ECHOED: new_asoc->c.my_vtag = asoc->c.my_vtag; new_asoc->c.my_ttag = asoc->c.my_vtag; new_asoc->c.peer_ttag = asoc->c.peer_vtag; break; /* 5.2.2 Unexpected INIT in States Other than CLOSED, COOKIE-ECHOED, * COOKIE-WAIT and SHUTDOWN-ACK-SENT */ default: new_asoc->c.my_ttag = asoc->c.my_vtag; new_asoc->c.peer_ttag = asoc->c.peer_vtag; break; } /* Other parameters for the endpoint SHOULD be copied from the * existing parameters of the association (e.g. number of * outbound streams) into the INIT ACK and cookie. */ new_asoc->rwnd = asoc->rwnd; new_asoc->c.sinit_num_ostreams = asoc->c.sinit_num_ostreams; new_asoc->c.sinit_max_instreams = asoc->c.sinit_max_instreams; new_asoc->c.initial_tsn = asoc->c.initial_tsn; } /* * Compare vtag/tietag values to determine unexpected COOKIE-ECHO * handling action. * * RFC 2960 5.2.4 Handle a COOKIE ECHO when a TCB exists. * * Returns value representing action to be taken. These action values * correspond to Action/Description values in RFC 2960, Table 2. */ static char sctp_tietags_compare(struct sctp_association *new_asoc, const struct sctp_association *asoc) { /* In this case, the peer may have restarted. */ if ((asoc->c.my_vtag != new_asoc->c.my_vtag) && (asoc->c.peer_vtag != new_asoc->c.peer_vtag) && (asoc->c.my_vtag == new_asoc->c.my_ttag) && (asoc->c.peer_vtag == new_asoc->c.peer_ttag)) return 'A'; /* Collision case B. */ if ((asoc->c.my_vtag == new_asoc->c.my_vtag) && ((asoc->c.peer_vtag != new_asoc->c.peer_vtag) || (0 == asoc->c.peer_vtag))) { return 'B'; } /* Collision case D. */ if ((asoc->c.my_vtag == new_asoc->c.my_vtag) && (asoc->c.peer_vtag == new_asoc->c.peer_vtag)) return 'D'; /* Collision case C. */ if ((asoc->c.my_vtag != new_asoc->c.my_vtag) && (asoc->c.peer_vtag == new_asoc->c.peer_vtag) && (0 == new_asoc->c.my_ttag) && (0 == new_asoc->c.peer_ttag)) return 'C'; /* No match to any of the special cases; discard this packet. */ return 'E'; } /* Common helper routine for both duplicate and simultaneous INIT * chunk handling. */ static enum sctp_disposition sctp_sf_do_unexpected_init( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg, *repl, *err_chunk; struct sctp_unrecognized_param *unk_param; struct sctp_association *new_asoc; enum sctp_disposition retval; struct sctp_packet *packet; int len; /* 6.10 Bundling * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. * * IG Section 2.11.2 * Furthermore, we require that the receiver of an INIT chunk MUST * enforce these rules by silently discarding an arriving packet * with an INIT chunk that is bundled with other chunks. */ if (!chunk->singleton) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the INIT chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* 3.1 A packet containing an INIT chunk MUST have a zero Verification * Tag. */ if (chunk->sctp_hdr->vtag != 0) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); if (SCTP_INPUT_CB(chunk->skb)->encap_port != chunk->transport->encap_port) return sctp_sf_new_encap_port(net, ep, asoc, type, arg, commands); /* Grab the INIT header. */ chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data; /* Tag the variable length parameters. */ chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(struct sctp_inithdr)); /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (struct sctp_init_chunk *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. * Send an ABORT, with causes if there is any. */ if (err_chunk) { packet = sctp_abort_pkt_new(net, ep, asoc, arg, (__u8 *)(err_chunk->chunk_hdr) + sizeof(struct sctp_chunkhdr), ntohs(err_chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr)); if (packet) { sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); retval = SCTP_DISPOSITION_CONSUME; } else { retval = SCTP_DISPOSITION_NOMEM; } goto cleanup; } else { return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); } } /* * Other parameters for the endpoint SHOULD be copied from the * existing parameters of the association (e.g. number of * outbound streams) into the INIT ACK and cookie. * FIXME: We are copying parameters from the endpoint not the * association. */ new_asoc = sctp_make_temp_asoc(ep, chunk, GFP_ATOMIC); if (!new_asoc) goto nomem; /* Update socket peer label if first association. */ if (security_sctp_assoc_request(new_asoc, chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } if (sctp_assoc_set_bind_addr_from_ep(new_asoc, sctp_scope(sctp_source(chunk)), GFP_ATOMIC) < 0) goto nomem; /* In the outbound INIT ACK the endpoint MUST copy its current * Verification Tag and Peers Verification tag into a reserved * place (local tie-tag and per tie-tag) within the state cookie. */ if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), (struct sctp_init_chunk *)chunk->chunk_hdr, GFP_ATOMIC)) goto nomem; /* Make sure no new addresses are being added during the * restart. Do not do this check for COOKIE-WAIT state, * since there are no peer addresses to check against. * Upon return an ABORT will have been sent if needed. */ if (!sctp_state(asoc, COOKIE_WAIT)) { if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) { retval = SCTP_DISPOSITION_CONSUME; goto nomem_retval; } } sctp_tietags_populate(new_asoc, asoc); /* B) "Z" shall respond immediately with an INIT ACK chunk. */ /* If there are errors need to be reported for unknown parameters, * make sure to reserve enough room in the INIT ACK for them. */ len = 0; if (err_chunk) { len = ntohs(err_chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr); } repl = sctp_make_init_ack(new_asoc, chunk, GFP_ATOMIC, len); if (!repl) goto nomem; /* If there are errors need to be reported for unknown parameters, * include them in the outgoing INIT ACK as "Unrecognized parameter" * parameter. */ if (err_chunk) { /* Get the "Unrecognized parameter" parameter(s) out of the * ERROR chunk generated by sctp_verify_init(). Since the * error cause code for "unknown parameter" and the * "Unrecognized parameter" type is the same, we can * construct the parameters in INIT ACK by copying the * ERROR causes over. */ unk_param = (struct sctp_unrecognized_param *) ((__u8 *)(err_chunk->chunk_hdr) + sizeof(struct sctp_chunkhdr)); /* Replace the cause code with the "Unrecognized parameter" * parameter type. */ sctp_addto_chunk(repl, len, unk_param); } sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); /* * Note: After sending out INIT ACK with the State Cookie parameter, * "Z" MUST NOT allocate any resources for this new association. * Otherwise, "Z" will be vulnerable to resource attacks. */ sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); retval = SCTP_DISPOSITION_CONSUME; return retval; nomem: retval = SCTP_DISPOSITION_NOMEM; nomem_retval: if (new_asoc) sctp_association_free(new_asoc); cleanup: if (err_chunk) sctp_chunk_free(err_chunk); return retval; } /* * Handle simultaneous INIT. * This means we started an INIT and then we got an INIT request from * our peer. * * Section: 5.2.1 INIT received in COOKIE-WAIT or COOKIE-ECHOED State (Item B) * This usually indicates an initialization collision, i.e., each * endpoint is attempting, at about the same time, to establish an * association with the other endpoint. * * Upon receipt of an INIT in the COOKIE-WAIT or COOKIE-ECHOED state, an * endpoint MUST respond with an INIT ACK using the same parameters it * sent in its original INIT chunk (including its Verification Tag, * unchanged). These original parameters are combined with those from the * newly received INIT chunk. The endpoint shall also generate a State * Cookie with the INIT ACK. The endpoint uses the parameters sent in its * INIT to calculate the State Cookie. * * After that, the endpoint MUST NOT change its state, the T1-init * timer shall be left running and the corresponding TCB MUST NOT be * destroyed. The normal procedures for handling State Cookies when * a TCB exists will resolve the duplicate INITs to a single association. * * For an endpoint that is in the COOKIE-ECHOED state it MUST populate * its Tie-Tags with the Tag information of itself and its peer (see * section 5.2.2 for a description of the Tie-Tags). * * Verification Tag: Not explicit, but an INIT can not have a valid * verification tag, so we skip the check. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_5_2_1_siminit( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* Call helper to do the real work for both simultaneous and * duplicate INIT chunk handling. */ return sctp_sf_do_unexpected_init(net, ep, asoc, type, arg, commands); } /* * Handle duplicated INIT messages. These are usually delayed * restransmissions. * * Section: 5.2.2 Unexpected INIT in States Other than CLOSED, * COOKIE-ECHOED and COOKIE-WAIT * * Unless otherwise stated, upon reception of an unexpected INIT for * this association, the endpoint shall generate an INIT ACK with a * State Cookie. In the outbound INIT ACK the endpoint MUST copy its * current Verification Tag and peer's Verification Tag into a reserved * place within the state cookie. We shall refer to these locations as * the Peer's-Tie-Tag and the Local-Tie-Tag. The outbound SCTP packet * containing this INIT ACK MUST carry a Verification Tag value equal to * the Initiation Tag found in the unexpected INIT. And the INIT ACK * MUST contain a new Initiation Tag (randomly generated see Section * 5.3.1). Other parameters for the endpoint SHOULD be copied from the * existing parameters of the association (e.g. number of outbound * streams) into the INIT ACK and cookie. * * After sending out the INIT ACK, the endpoint shall take no further * actions, i.e., the existing association, including its current state, * and the corresponding TCB MUST NOT be changed. * * Note: Only when a TCB exists and the association is not in a COOKIE- * WAIT state are the Tie-Tags populated. For a normal association INIT * (i.e. the endpoint is in a COOKIE-WAIT state), the Tie-Tags MUST be * set to 0 (indicating that no previous TCB existed). The INIT ACK and * State Cookie are populated as specified in section 5.2.1. * * Verification Tag: Not specified, but an INIT has no way of knowing * what the verification tag could be, so we ignore it. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_5_2_2_dupinit( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* Call helper to do the real work for both simultaneous and * duplicate INIT chunk handling. */ return sctp_sf_do_unexpected_init(net, ep, asoc, type, arg, commands); } /* * Unexpected INIT-ACK handler. * * Section 5.2.3 * If an INIT ACK received by an endpoint in any state other than the * COOKIE-WAIT state, the endpoint should discard the INIT ACK chunk. * An unexpected INIT ACK usually indicates the processing of an old or * duplicated INIT chunk. */ enum sctp_disposition sctp_sf_do_5_2_3_initack( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* Per the above section, we'll discard the chunk if we have an * endpoint. If this is an OOTB INIT-ACK, treat it as such. */ if (ep == sctp_sk(net->sctp.ctl_sock)->ep) return sctp_sf_ootb(net, ep, asoc, type, arg, commands); else return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); } static int sctp_sf_do_assoc_update(struct sctp_association *asoc, struct sctp_association *new, struct sctp_cmd_seq *cmds) { struct net *net = asoc->base.net; struct sctp_chunk *abort; if (!sctp_assoc_update(asoc, new)) return 0; abort = sctp_make_abort(asoc, NULL, sizeof(struct sctp_errhdr)); if (abort) { sctp_init_cause(abort, SCTP_ERROR_RSRC_LOW, 0); sctp_add_cmd_sf(cmds, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); } sctp_add_cmd_sf(cmds, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); sctp_add_cmd_sf(cmds, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_RSRC_LOW)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return -ENOMEM; } /* Unexpected COOKIE-ECHO handler for peer restart (Table 2, action 'A') * * Section 5.2.4 * A) In this case, the peer may have restarted. */ static enum sctp_disposition sctp_sf_do_dupcook_a( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_cmd_seq *commands, struct sctp_association *new_asoc) { struct sctp_init_chunk *peer_init; enum sctp_disposition disposition; struct sctp_ulpevent *ev; struct sctp_chunk *repl; struct sctp_chunk *err; /* new_asoc is a brand-new association, so these are not yet * side effects--it is safe to run them here. */ peer_init = (struct sctp_init_chunk *)(chunk->subh.cookie_hdr + 1); if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), peer_init, GFP_ATOMIC)) goto nomem; if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC)) goto nomem; if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) return SCTP_DISPOSITION_DISCARD; /* Make sure no new addresses are being added during the * restart. Though this is a pretty complicated attack * since you'd have to get inside the cookie. */ if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) return SCTP_DISPOSITION_CONSUME; /* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes * the peer has restarted (Action A), it MUST NOT setup a new * association but instead resend the SHUTDOWN ACK and send an ERROR * chunk with a "Cookie Received while Shutting Down" error cause to * its peer. */ if (sctp_state(asoc, SHUTDOWN_ACK_SENT)) { disposition = __sctp_sf_do_9_2_reshutack(net, ep, asoc, SCTP_ST_CHUNK(chunk->chunk_hdr->type), chunk, commands); if (SCTP_DISPOSITION_NOMEM == disposition) goto nomem; err = sctp_make_op_error(asoc, chunk, SCTP_ERROR_COOKIE_IN_SHUTDOWN, NULL, 0, 0); if (err) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err)); return SCTP_DISPOSITION_CONSUME; } /* For now, stop pending T3-rtx and SACK timers, fail any unsent/unacked * data. Consider the optional choice of resending of this data. */ sctp_add_cmd_sf(commands, SCTP_CMD_T3_RTX_TIMERS_STOP, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_SACK)); sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_OUTQUEUE, SCTP_NULL()); /* Stop pending T4-rto timer, teardown ASCONF queue, ASCONF-ACK queue * and ASCONF-ACK cache. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_ASCONF_QUEUE, SCTP_NULL()); /* Update the content of current association. */ if (sctp_sf_do_assoc_update((struct sctp_association *)asoc, new_asoc, commands)) goto nomem; repl = sctp_make_cookie_ack(asoc, chunk); if (!repl) goto nomem; /* Report association restart to upper layer. */ ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_RESTART, 0, asoc->c.sinit_num_ostreams, asoc->c.sinit_max_instreams, NULL, GFP_ATOMIC); if (!ev) goto nomem_ev; sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); if ((sctp_state(asoc, SHUTDOWN_PENDING) || sctp_state(asoc, SHUTDOWN_SENT)) && (sctp_sstate(asoc->base.sk, CLOSING) || sock_flag(asoc->base.sk, SOCK_DEAD))) { /* If the socket has been closed by user, don't * transition to ESTABLISHED. Instead trigger SHUTDOWN * bundled with COOKIE_ACK. */ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); return sctp_sf_do_9_2_start_shutdown(net, ep, asoc, SCTP_ST_CHUNK(0), repl, commands); } else { sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_ESTABLISHED)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); } return SCTP_DISPOSITION_CONSUME; nomem_ev: sctp_chunk_free(repl); nomem: return SCTP_DISPOSITION_NOMEM; } /* Unexpected COOKIE-ECHO handler for setup collision (Table 2, action 'B') * * Section 5.2.4 * B) In this case, both sides may be attempting to start an association * at about the same time but the peer endpoint started its INIT * after responding to the local endpoint's INIT */ /* This case represents an initialization collision. */ static enum sctp_disposition sctp_sf_do_dupcook_b( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_cmd_seq *commands, struct sctp_association *new_asoc) { struct sctp_init_chunk *peer_init; struct sctp_chunk *repl; /* new_asoc is a brand-new association, so these are not yet * side effects--it is safe to run them here. */ peer_init = (struct sctp_init_chunk *)(chunk->subh.cookie_hdr + 1); if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), peer_init, GFP_ATOMIC)) goto nomem; if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC)) goto nomem; if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) return SCTP_DISPOSITION_DISCARD; sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_ESTABLISHED)); if (asoc->state < SCTP_STATE_ESTABLISHED) SCTP_INC_STATS(net, SCTP_MIB_CURRESTAB); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL()); /* Update the content of current association. */ if (sctp_sf_do_assoc_update((struct sctp_association *)asoc, new_asoc, commands)) goto nomem; repl = sctp_make_cookie_ack(asoc, chunk); if (!repl) goto nomem; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); /* RFC 2960 5.1 Normal Establishment of an Association * * D) IMPLEMENTATION NOTE: An implementation may choose to * send the Communication Up notification to the SCTP user * upon reception of a valid COOKIE ECHO chunk. * * Sadly, this needs to be implemented as a side-effect, because * we are not guaranteed to have set the association id of the real * association and so these notifications need to be delayed until * the association id is allocated. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_CHANGE, SCTP_U8(SCTP_COMM_UP)); /* Sockets API Draft Section 5.3.1.6 * When a peer sends a Adaptation Layer Indication parameter , SCTP * delivers this notification to inform the application that of the * peers requested adaptation layer. * * This also needs to be done as a side effect for the same reason as * above. */ if (asoc->peer.adaptation_ind) sctp_add_cmd_sf(commands, SCTP_CMD_ADAPTATION_IND, SCTP_NULL()); if (!asoc->peer.auth_capable) sctp_add_cmd_sf(commands, SCTP_CMD_PEER_NO_AUTH, SCTP_NULL()); return SCTP_DISPOSITION_CONSUME; nomem: return SCTP_DISPOSITION_NOMEM; } /* Unexpected COOKIE-ECHO handler for setup collision (Table 2, action 'C') * * Section 5.2.4 * C) In this case, the local endpoint's cookie has arrived late. * Before it arrived, the local endpoint sent an INIT and received an * INIT-ACK and finally sent a COOKIE ECHO with the peer's same tag * but a new tag of its own. */ /* This case represents an initialization collision. */ static enum sctp_disposition sctp_sf_do_dupcook_c( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_cmd_seq *commands, struct sctp_association *new_asoc) { /* The cookie should be silently discarded. * The endpoint SHOULD NOT change states and should leave * any timers running. */ return SCTP_DISPOSITION_DISCARD; } /* Unexpected COOKIE-ECHO handler lost chunk (Table 2, action 'D') * * Section 5.2.4 * * D) When both local and remote tags match the endpoint should always * enter the ESTABLISHED state, if it has not already done so. */ /* This case represents an initialization collision. */ static enum sctp_disposition sctp_sf_do_dupcook_d( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_cmd_seq *commands, struct sctp_association *new_asoc) { struct sctp_ulpevent *ev = NULL, *ai_ev = NULL, *auth_ev = NULL; struct sctp_chunk *repl; /* Clarification from Implementor's Guide: * D) When both local and remote tags match the endpoint should * enter the ESTABLISHED state, if it is in the COOKIE-ECHOED state. * It should stop any cookie timer that may be running and send * a COOKIE ACK. */ if (!sctp_auth_chunk_verify(net, chunk, asoc)) return SCTP_DISPOSITION_DISCARD; /* Don't accidentally move back into established state. */ if (asoc->state < SCTP_STATE_ESTABLISHED) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_COOKIE)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_ESTABLISHED)); SCTP_INC_STATS(net, SCTP_MIB_CURRESTAB); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL()); /* RFC 2960 5.1 Normal Establishment of an Association * * D) IMPLEMENTATION NOTE: An implementation may choose * to send the Communication Up notification to the * SCTP user upon reception of a valid COOKIE * ECHO chunk. */ ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_COMM_UP, 0, asoc->c.sinit_num_ostreams, asoc->c.sinit_max_instreams, NULL, GFP_ATOMIC); if (!ev) goto nomem; /* Sockets API Draft Section 5.3.1.6 * When a peer sends a Adaptation Layer Indication parameter, * SCTP delivers this notification to inform the application * that of the peers requested adaptation layer. */ if (asoc->peer.adaptation_ind) { ai_ev = sctp_ulpevent_make_adaptation_indication(asoc, GFP_ATOMIC); if (!ai_ev) goto nomem; } if (!asoc->peer.auth_capable) { auth_ev = sctp_ulpevent_make_authkey(asoc, 0, SCTP_AUTH_NO_AUTH, GFP_ATOMIC); if (!auth_ev) goto nomem; } } repl = sctp_make_cookie_ack(asoc, chunk); if (!repl) goto nomem; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); if (ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); if (ai_ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ai_ev)); if (auth_ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(auth_ev)); return SCTP_DISPOSITION_CONSUME; nomem: if (auth_ev) sctp_ulpevent_free(auth_ev); if (ai_ev) sctp_ulpevent_free(ai_ev); if (ev) sctp_ulpevent_free(ev); return SCTP_DISPOSITION_NOMEM; } /* * Handle a duplicate COOKIE-ECHO. This usually means a cookie-carrying * chunk was retransmitted and then delayed in the network. * * Section: 5.2.4 Handle a COOKIE ECHO when a TCB exists * * Verification Tag: None. Do cookie validation. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_association *new_asoc; struct sctp_chunk *chunk = arg; enum sctp_disposition retval; struct sctp_chunk *err_chk_p; int error = 0; char action; /* Make sure that the chunk has a valid length from the protocol * perspective. In this case check to make sure we have at least * enough for the chunk header. Cookie length verification is * done later. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) { if (!sctp_vtag_verify(chunk, asoc)) asoc = NULL; return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); } /* "Decode" the chunk. We have no optional parameters so we * are in good shape. */ chunk->subh.cookie_hdr = (struct sctp_signed_cookie *)chunk->skb->data; if (!pskb_pull(chunk->skb, ntohs(chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr))) goto nomem; /* In RFC 2960 5.2.4 3, if both Verification Tags in the State Cookie * of a duplicate COOKIE ECHO match the Verification Tags of the * current association, consider the State Cookie valid even if * the lifespan is exceeded. */ new_asoc = sctp_unpack_cookie(ep, asoc, chunk, GFP_ATOMIC, &error, &err_chk_p); /* FIXME: * If the re-build failed, what is the proper error path * from here? * * [We should abort the association. --piggy] */ if (!new_asoc) { /* FIXME: Several errors are possible. A bad cookie should * be silently discarded, but think about logging it too. */ switch (error) { case -SCTP_IERROR_NOMEM: goto nomem; case -SCTP_IERROR_STALE_COOKIE: sctp_send_stale_cookie_err(net, ep, asoc, chunk, commands, err_chk_p); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); case -SCTP_IERROR_BAD_SIG: default: return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } } /* Update socket peer label if first association. */ if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } /* Set temp so that it won't be added into hashtable */ new_asoc->temp = 1; /* Compare the tie_tag in cookie with the verification tag of * current association. */ action = sctp_tietags_compare(new_asoc, asoc); switch (action) { case 'A': /* Association restart. */ retval = sctp_sf_do_dupcook_a(net, ep, asoc, chunk, commands, new_asoc); break; case 'B': /* Collision case B. */ retval = sctp_sf_do_dupcook_b(net, ep, asoc, chunk, commands, new_asoc); break; case 'C': /* Collision case C. */ retval = sctp_sf_do_dupcook_c(net, ep, asoc, chunk, commands, new_asoc); break; case 'D': /* Collision case D. */ retval = sctp_sf_do_dupcook_d(net, ep, asoc, chunk, commands, new_asoc); break; default: /* Discard packet for all others. */ retval = sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); break; } /* Delete the temporary new association. */ sctp_add_cmd_sf(commands, SCTP_CMD_SET_ASOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); /* Restore association pointer to provide SCTP command interpreter * with a valid context in case it needs to manipulate * the queues */ sctp_add_cmd_sf(commands, SCTP_CMD_SET_ASOC, SCTP_ASOC((struct sctp_association *)asoc)); return retval; nomem: return SCTP_DISPOSITION_NOMEM; } /* * Process an ABORT. (SHUTDOWN-PENDING state) * * See sctp_sf_do_9_1_abort(). */ enum sctp_disposition sctp_sf_shutdown_pending_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; if (!sctp_vtag_verify_either(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the ABORT chunk has a valid length. * Since this is an ABORT chunk, we have to discard it * because of the following text: * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_abort_chunk))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* ADD-IP: Special case for ABORT chunks * F4) One special consideration is that ABORT Chunks arriving * destined to the IP address being deleted MUST be * ignored (see Section 5.3.1 for further details). */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } /* * Process an ABORT. (SHUTDOWN-SENT state) * * See sctp_sf_do_9_1_abort(). */ enum sctp_disposition sctp_sf_shutdown_sent_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; if (!sctp_vtag_verify_either(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the ABORT chunk has a valid length. * Since this is an ABORT chunk, we have to discard it * because of the following text: * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_abort_chunk))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* ADD-IP: Special case for ABORT chunks * F4) One special consideration is that ABORT Chunks arriving * destined to the IP address being deleted MUST be * ignored (see Section 5.3.1 for further details). */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Stop the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); /* Stop the T5-shutdown guard timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } /* * Process an ABORT. (SHUTDOWN-ACK-SENT state) * * See sctp_sf_do_9_1_abort(). */ enum sctp_disposition sctp_sf_shutdown_ack_sent_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* The same T2 timer, so we should be able to use * common function with the SHUTDOWN-SENT state. */ return sctp_sf_shutdown_sent_abort(net, ep, asoc, type, arg, commands); } /* * Handle an Error received in COOKIE_ECHOED state. * * Only handle the error type of stale COOKIE Error, the other errors will * be ignored. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_cookie_echoed_err( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_errhdr *err; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the ERROR chunk has a valid length. * The parameter walking depends on this as well. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_operr_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Process the error here */ /* FUTURE FIXME: When PR-SCTP related and other optional * parms are emitted, this will have to change to handle multiple * errors. */ sctp_walk_errors(err, chunk->chunk_hdr) { if (SCTP_ERROR_STALE_COOKIE == err->cause) return sctp_sf_do_5_2_6_stale(net, ep, asoc, type, arg, commands); } /* It is possible to have malformed error causes, and that * will cause us to end the walk early. However, since * we are discarding the packet, there should be no adverse * affects. */ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } /* * Handle a Stale COOKIE Error * * Section: 5.2.6 Handle Stale COOKIE Error * If the association is in the COOKIE-ECHOED state, the endpoint may elect * one of the following three alternatives. * ... * 3) Send a new INIT chunk to the endpoint, adding a Cookie * Preservative parameter requesting an extension to the lifetime of * the State Cookie. When calculating the time extension, an * implementation SHOULD use the RTT information measured based on the * previous COOKIE ECHO / ERROR exchange, and should add no more * than 1 second beyond the measured RTT, due to long State Cookie * lifetimes making the endpoint more subject to a replay attack. * * Verification Tag: Not explicit, but safe to ignore. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ static enum sctp_disposition sctp_sf_do_5_2_6_stale( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { int attempts = asoc->init_err_counter + 1; struct sctp_chunk *chunk = arg, *reply; struct sctp_cookie_preserve_param bht; struct sctp_bind_addr *bp; struct sctp_errhdr *err; u32 stale; if (attempts > asoc->max_init_attempts) { sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, SCTP_PERR(SCTP_ERROR_STALE_COOKIE)); return SCTP_DISPOSITION_DELETE_TCB; } err = (struct sctp_errhdr *)(chunk->skb->data); /* When calculating the time extension, an implementation * SHOULD use the RTT information measured based on the * previous COOKIE ECHO / ERROR exchange, and should add no * more than 1 second beyond the measured RTT, due to long * State Cookie lifetimes making the endpoint more subject to * a replay attack. * Measure of Staleness's unit is usec. (1/1000000 sec) * Suggested Cookie Life-span Increment's unit is msec. * (1/1000 sec) * In general, if you use the suggested cookie life, the value * found in the field of measure of staleness should be doubled * to give ample time to retransmit the new cookie and thus * yield a higher probability of success on the reattempt. */ stale = ntohl(*(__be32 *)((u8 *)err + sizeof(*err))); stale = (stale * 2) / 1000; bht.param_hdr.type = SCTP_PARAM_COOKIE_PRESERVATIVE; bht.param_hdr.length = htons(sizeof(bht)); bht.lifespan_increment = htonl(stale); /* Build that new INIT chunk. */ bp = (struct sctp_bind_addr *) &asoc->base.bind_addr; reply = sctp_make_init(asoc, bp, GFP_ATOMIC, sizeof(bht)); if (!reply) goto nomem; sctp_addto_chunk(reply, sizeof(bht), &bht); /* Clear peer's init_tag cached in assoc as we are sending a new INIT */ sctp_add_cmd_sf(commands, SCTP_CMD_CLEAR_INIT_TAG, SCTP_NULL()); /* Stop pending T3-rtx and heartbeat timers */ sctp_add_cmd_sf(commands, SCTP_CMD_T3_RTX_TIMERS_STOP, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_STOP, SCTP_NULL()); /* Delete non-primary peer ip addresses since we are transitioning * back to the COOKIE-WAIT state */ sctp_add_cmd_sf(commands, SCTP_CMD_DEL_NON_PRIMARY, SCTP_NULL()); /* If we've sent any data bundled with COOKIE-ECHO we will need to * resend */ sctp_add_cmd_sf(commands, SCTP_CMD_T1_RETRAN, SCTP_TRANSPORT(asoc->peer.primary_path)); /* Cast away the const modifier, as we want to just * rerun it through as a sideffect. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_INC, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_COOKIE)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_COOKIE_WAIT)); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); return SCTP_DISPOSITION_CONSUME; nomem: return SCTP_DISPOSITION_NOMEM; } /* * Process an ABORT. * * Section: 9.1 * After checking the Verification Tag, the receiving endpoint shall * remove the association from its record, and shall report the * termination to its upper layer. * * Verification Tag: 8.5.1 Exceptions in Verification Tag Rules * B) Rules for packet carrying ABORT: * * - The endpoint shall always fill in the Verification Tag field of the * outbound packet with the destination endpoint's tag value if it * is known. * * - If the ABORT is sent in response to an OOTB packet, the endpoint * MUST follow the procedure described in Section 8.4. * * - The receiver MUST accept the packet if the Verification Tag * matches either its own tag, OR the tag of its peer. Otherwise, the * receiver MUST silently discard the packet and take no further * action. * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_9_1_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; if (!sctp_vtag_verify_either(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the ABORT chunk has a valid length. * Since this is an ABORT chunk, we have to discard it * because of the following text: * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_abort_chunk))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* ADD-IP: Special case for ABORT chunks * F4) One special consideration is that ABORT Chunks arriving * destined to the IP address being deleted MUST be * ignored (see Section 5.3.1 for further details). */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } static enum sctp_disposition __sctp_sf_do_9_1_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { __be16 error = SCTP_ERROR_NO_ERROR; struct sctp_chunk *chunk = arg; unsigned int len; /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) error = ((struct sctp_errhdr *)chunk->skb->data)->cause; sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET)); /* ASSOC_FAILED will DELETE_TCB. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(error)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_DISPOSITION_ABORT; } /* * Process an ABORT. (COOKIE-WAIT state) * * See sctp_sf_do_9_1_abort() above. */ enum sctp_disposition sctp_sf_cookie_wait_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { __be16 error = SCTP_ERROR_NO_ERROR; struct sctp_chunk *chunk = arg; unsigned int len; if (!sctp_vtag_verify_either(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the ABORT chunk has a valid length. * Since this is an ABORT chunk, we have to discard it * because of the following text: * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_abort_chunk))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) error = ((struct sctp_errhdr *)chunk->skb->data)->cause; return sctp_stop_t1_and_abort(net, commands, error, ECONNREFUSED, asoc, chunk->transport); } /* * Process an incoming ICMP as an ABORT. (COOKIE-WAIT state) */ enum sctp_disposition sctp_sf_cookie_wait_icmp_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { return sctp_stop_t1_and_abort(net, commands, SCTP_ERROR_NO_ERROR, ENOPROTOOPT, asoc, (struct sctp_transport *)arg); } /* * Process an ABORT. (COOKIE-ECHOED state) */ enum sctp_disposition sctp_sf_cookie_echoed_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* There is a single T1 timer, so we should be able to use * common function with the COOKIE-WAIT state. */ return sctp_sf_cookie_wait_abort(net, ep, asoc, type, arg, commands); } /* * Stop T1 timer and abort association with "INIT failed". * * This is common code called by several sctp_sf_*_abort() functions above. */ static enum sctp_disposition sctp_stop_t1_and_abort( struct net *net, struct sctp_cmd_seq *commands, __be16 error, int sk_err, const struct sctp_association *asoc, struct sctp_transport *transport) { pr_debug("%s: ABORT received (INIT)\n", __func__); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(sk_err)); /* CMD_INIT_FAILED will DELETE_TCB. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, SCTP_PERR(error)); return SCTP_DISPOSITION_ABORT; } /* * sctp_sf_do_9_2_shut * * Section: 9.2 * Upon the reception of the SHUTDOWN, the peer endpoint shall * - enter the SHUTDOWN-RECEIVED state, * * - stop accepting new data from its SCTP user * * - verify, by checking the Cumulative TSN Ack field of the chunk, * that all its outstanding DATA chunks have been received by the * SHUTDOWN sender. * * Once an endpoint as reached the SHUTDOWN-RECEIVED state it MUST NOT * send a SHUTDOWN in response to a ULP request. And should discard * subsequent SHUTDOWN chunks. * * If there are still outstanding DATA chunks left, the SHUTDOWN * receiver shall continue to follow normal data transmission * procedures defined in Section 6 until all outstanding DATA chunks * are acknowledged; however, the SHUTDOWN receiver MUST NOT accept * new data from its SCTP user. * * Verification Tag: 8.5 Verification Tag [Normal verification] * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_9_2_shutdown( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { enum sctp_disposition disposition; struct sctp_chunk *chunk = arg; struct sctp_shutdownhdr *sdh; struct sctp_ulpevent *ev; __u32 ctsn; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_shutdown_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Convert the elaborate header. */ sdh = (struct sctp_shutdownhdr *)chunk->skb->data; skb_pull(chunk->skb, sizeof(*sdh)); chunk->subh.shutdown_hdr = sdh; ctsn = ntohl(sdh->cum_tsn_ack); if (TSN_lt(ctsn, asoc->ctsn_ack_point)) { pr_debug("%s: ctsn:%x, ctsn_ack_point:%x\n", __func__, ctsn, asoc->ctsn_ack_point); return SCTP_DISPOSITION_DISCARD; } /* If Cumulative TSN Ack beyond the max tsn currently * send, terminating the association and respond to the * sender with an ABORT. */ if (!TSN_lt(ctsn, asoc->next_tsn)) return sctp_sf_violation_ctsn(net, ep, asoc, type, arg, commands); /* API 5.3.1.5 SCTP_SHUTDOWN_EVENT * When a peer sends a SHUTDOWN, SCTP delivers this notification to * inform the application that it should cease sending data. */ ev = sctp_ulpevent_make_shutdown_event(asoc, 0, GFP_ATOMIC); if (!ev) { disposition = SCTP_DISPOSITION_NOMEM; goto out; } sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); /* Upon the reception of the SHUTDOWN, the peer endpoint shall * - enter the SHUTDOWN-RECEIVED state, * - stop accepting new data from its SCTP user * * [This is implicit in the new state.] */ sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_SHUTDOWN_RECEIVED)); disposition = SCTP_DISPOSITION_CONSUME; if (sctp_outq_is_empty(&asoc->outqueue)) { disposition = sctp_sf_do_9_2_shutdown_ack(net, ep, asoc, type, arg, commands); } if (SCTP_DISPOSITION_NOMEM == disposition) goto out; /* - verify, by checking the Cumulative TSN Ack field of the * chunk, that all its outstanding DATA chunks have been * received by the SHUTDOWN sender. */ sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_CTSN, SCTP_BE32(chunk->subh.shutdown_hdr->cum_tsn_ack)); out: return disposition; } /* * sctp_sf_do_9_2_shut_ctsn * * Once an endpoint has reached the SHUTDOWN-RECEIVED state, * it MUST NOT send a SHUTDOWN in response to a ULP request. * The Cumulative TSN Ack of the received SHUTDOWN chunk * MUST be processed. */ enum sctp_disposition sctp_sf_do_9_2_shut_ctsn( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_shutdownhdr *sdh; __u32 ctsn; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_shutdown_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); sdh = (struct sctp_shutdownhdr *)chunk->skb->data; ctsn = ntohl(sdh->cum_tsn_ack); if (TSN_lt(ctsn, asoc->ctsn_ack_point)) { pr_debug("%s: ctsn:%x, ctsn_ack_point:%x\n", __func__, ctsn, asoc->ctsn_ack_point); return SCTP_DISPOSITION_DISCARD; } /* If Cumulative TSN Ack beyond the max tsn currently * send, terminating the association and respond to the * sender with an ABORT. */ if (!TSN_lt(ctsn, asoc->next_tsn)) return sctp_sf_violation_ctsn(net, ep, asoc, type, arg, commands); /* verify, by checking the Cumulative TSN Ack field of the * chunk, that all its outstanding DATA chunks have been * received by the SHUTDOWN sender. */ sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_CTSN, SCTP_BE32(sdh->cum_tsn_ack)); return SCTP_DISPOSITION_CONSUME; } /* RFC 2960 9.2 * If an endpoint is in SHUTDOWN-ACK-SENT state and receives an INIT chunk * (e.g., if the SHUTDOWN COMPLETE was lost) with source and destination * transport addresses (either in the IP addresses or in the INIT chunk) * that belong to this association, it should discard the INIT chunk and * retransmit the SHUTDOWN ACK chunk. */ static enum sctp_disposition __sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; /* Make sure that the chunk has a valid length */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Since we are not going to really process this INIT, there * is no point in verifying chunk boundaries. Just generate * the SHUTDOWN ACK. */ reply = sctp_make_shutdown_ack(asoc, chunk); if (NULL == reply) goto nomem; /* Set the transport for the SHUTDOWN ACK chunk and the timeout for * the T2-SHUTDOWN timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_SETUP_T2, SCTP_CHUNK(reply)); /* and restart the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); return SCTP_DISPOSITION_CONSUME; nomem: return SCTP_DISPOSITION_NOMEM; } enum sctp_disposition sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; if (!chunk->singleton) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (chunk->sctp_hdr->vtag != 0) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); return __sctp_sf_do_9_2_reshutack(net, ep, asoc, type, arg, commands); } /* * sctp_sf_do_ecn_cwr * * Section: Appendix A: Explicit Congestion Notification * * CWR: * * RFC 2481 details a specific bit for a sender to send in the header of * its next outbound TCP segment to indicate to its peer that it has * reduced its congestion window. This is termed the CWR bit. For * SCTP the same indication is made by including the CWR chunk. * This chunk contains one data element, i.e. the TSN number that * was sent in the ECNE chunk. This element represents the lowest * TSN number in the datagram that was originally marked with the * CE bit. * * Verification Tag: 8.5 Verification Tag [Normal verification] * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_ecn_cwr(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_cwrhdr *cwr; u32 lowest_tsn; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_ecne_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); cwr = (struct sctp_cwrhdr *)chunk->skb->data; skb_pull(chunk->skb, sizeof(*cwr)); lowest_tsn = ntohl(cwr->lowest_tsn); /* Does this CWR ack the last sent congestion notification? */ if (TSN_lte(asoc->last_ecne_tsn, lowest_tsn)) { /* Stop sending ECNE. */ sctp_add_cmd_sf(commands, SCTP_CMD_ECN_CWR, SCTP_U32(lowest_tsn)); } return SCTP_DISPOSITION_CONSUME; } /* * sctp_sf_do_ecne * * Section: Appendix A: Explicit Congestion Notification * * ECN-Echo * * RFC 2481 details a specific bit for a receiver to send back in its * TCP acknowledgements to notify the sender of the Congestion * Experienced (CE) bit having arrived from the network. For SCTP this * same indication is made by including the ECNE chunk. This chunk * contains one data element, i.e. the lowest TSN associated with the IP * datagram marked with the CE bit..... * * Verification Tag: 8.5 Verification Tag [Normal verification] * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_ecne(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_ecnehdr *ecne; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_ecne_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); ecne = (struct sctp_ecnehdr *)chunk->skb->data; skb_pull(chunk->skb, sizeof(*ecne)); /* If this is a newer ECNE than the last CWR packet we sent out */ sctp_add_cmd_sf(commands, SCTP_CMD_ECN_ECNE, SCTP_U32(ntohl(ecne->lowest_tsn))); return SCTP_DISPOSITION_CONSUME; } /* * Section: 6.2 Acknowledgement on Reception of DATA Chunks * * The SCTP endpoint MUST always acknowledge the reception of each valid * DATA chunk. * * The guidelines on delayed acknowledgement algorithm specified in * Section 4.2 of [RFC2581] SHOULD be followed. Specifically, an * acknowledgement SHOULD be generated for at least every second packet * (not every second DATA chunk) received, and SHOULD be generated within * 200 ms of the arrival of any unacknowledged DATA chunk. In some * situations it may be beneficial for an SCTP transmitter to be more * conservative than the algorithms detailed in this document allow. * However, an SCTP transmitter MUST NOT be more aggressive than the * following algorithms allow. * * A SCTP receiver MUST NOT generate more than one SACK for every * incoming packet, other than to update the offered window as the * receiving application consumes new data. * * Verification Tag: 8.5 Verification Tag [Normal verification] * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_eat_data_6_2(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { union sctp_arg force = SCTP_NOFORCE(); struct sctp_chunk *chunk = arg; int error; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, SCTP_NULL()); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } if (!sctp_chunk_length_valid(chunk, sctp_datachk_len(&asoc->stream))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); error = sctp_eat_data(asoc, chunk, commands); switch (error) { case SCTP_IERROR_NO_ERROR: break; case SCTP_IERROR_HIGH_TSN: case SCTP_IERROR_BAD_STREAM: SCTP_INC_STATS(net, SCTP_MIB_IN_DATA_CHUNK_DISCARDS); goto discard_noforce; case SCTP_IERROR_DUP_TSN: case SCTP_IERROR_IGNORE_TSN: SCTP_INC_STATS(net, SCTP_MIB_IN_DATA_CHUNK_DISCARDS); goto discard_force; case SCTP_IERROR_NO_DATA: return SCTP_DISPOSITION_ABORT; case SCTP_IERROR_PROTO_VIOLATION: return sctp_sf_abort_violation(net, ep, asoc, chunk, commands, (u8 *)chunk->subh.data_hdr, sctp_datahdr_len(&asoc->stream)); default: BUG(); } if (chunk->chunk_hdr->flags & SCTP_DATA_SACK_IMM) force = SCTP_FORCE(); if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); } /* If this is the last chunk in a packet, we need to count it * toward sack generation. Note that we need to SACK every * OTHER packet containing data chunks, EVEN IF WE DISCARD * THEM. We elect to NOT generate SACK's if the chunk fails * the verification tag test. * * RFC 2960 6.2 Acknowledgement on Reception of DATA Chunks * * The SCTP endpoint MUST always acknowledge the reception of * each valid DATA chunk. * * The guidelines on delayed acknowledgement algorithm * specified in Section 4.2 of [RFC2581] SHOULD be followed. * Specifically, an acknowledgement SHOULD be generated for at * least every second packet (not every second DATA chunk) * received, and SHOULD be generated within 200 ms of the * arrival of any unacknowledged DATA chunk. In some * situations it may be beneficial for an SCTP transmitter to * be more conservative than the algorithms detailed in this * document allow. However, an SCTP transmitter MUST NOT be * more aggressive than the following algorithms allow. */ if (chunk->end_of_packet) sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, force); return SCTP_DISPOSITION_CONSUME; discard_force: /* RFC 2960 6.2 Acknowledgement on Reception of DATA Chunks * * When a packet arrives with duplicate DATA chunk(s) and with * no new DATA chunk(s), the endpoint MUST immediately send a * SACK with no delay. If a packet arrives with duplicate * DATA chunk(s) bundled with new DATA chunks, the endpoint * MAY immediately send a SACK. Normally receipt of duplicate * DATA chunks will occur when the original SACK chunk was lost * and the peer's RTO has expired. The duplicate TSN number(s) * SHOULD be reported in the SACK as duplicate. */ /* In our case, we split the MAY SACK advice up whether or not * the last chunk is a duplicate.' */ if (chunk->end_of_packet) sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_FORCE()); return SCTP_DISPOSITION_DISCARD; discard_noforce: if (chunk->end_of_packet) sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, force); return SCTP_DISPOSITION_DISCARD; } /* * sctp_sf_eat_data_fast_4_4 * * Section: 4 (4) * (4) In SHUTDOWN-SENT state the endpoint MUST acknowledge any received * DATA chunks without delay. * * Verification Tag: 8.5 Verification Tag [Normal verification] * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_eat_data_fast_4_4( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; int error; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, SCTP_NULL()); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } if (!sctp_chunk_length_valid(chunk, sctp_datachk_len(&asoc->stream))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); error = sctp_eat_data(asoc, chunk, commands); switch (error) { case SCTP_IERROR_NO_ERROR: case SCTP_IERROR_HIGH_TSN: case SCTP_IERROR_DUP_TSN: case SCTP_IERROR_IGNORE_TSN: case SCTP_IERROR_BAD_STREAM: break; case SCTP_IERROR_NO_DATA: return SCTP_DISPOSITION_ABORT; case SCTP_IERROR_PROTO_VIOLATION: return sctp_sf_abort_violation(net, ep, asoc, chunk, commands, (u8 *)chunk->subh.data_hdr, sctp_datahdr_len(&asoc->stream)); default: BUG(); } /* Go a head and force a SACK, since we are shutting down. */ /* Implementor's Guide. * * While in SHUTDOWN-SENT state, the SHUTDOWN sender MUST immediately * respond to each received packet containing one or more DATA chunk(s) * with a SACK, a SHUTDOWN chunk, and restart the T2-shutdown timer */ if (chunk->end_of_packet) { /* We must delay the chunk creation since the cumulative * TSN has not been updated yet. */ sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SHUTDOWN, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_FORCE()); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); } return SCTP_DISPOSITION_CONSUME; } /* * Section: 6.2 Processing a Received SACK * D) Any time a SACK arrives, the endpoint performs the following: * * i) If Cumulative TSN Ack is less than the Cumulative TSN Ack Point, * then drop the SACK. Since Cumulative TSN Ack is monotonically * increasing, a SACK whose Cumulative TSN Ack is less than the * Cumulative TSN Ack Point indicates an out-of-order SACK. * * ii) Set rwnd equal to the newly received a_rwnd minus the number * of bytes still outstanding after processing the Cumulative TSN Ack * and the Gap Ack Blocks. * * iii) If the SACK is missing a TSN that was previously * acknowledged via a Gap Ack Block (e.g., the data receiver * reneged on the data), then mark the corresponding DATA chunk * as available for retransmit: Mark it as missing for fast * retransmit as described in Section 7.2.4 and if no retransmit * timer is running for the destination address to which the DATA * chunk was originally transmitted, then T3-rtx is started for * that destination address. * * Verification Tag: 8.5 Verification Tag [Normal verification] * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_eat_sack_6_2(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_sackhdr *sackh; __u32 ctsn; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the SACK chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_sack_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Pull the SACK chunk from the data buffer */ sackh = sctp_sm_pull_sack(chunk); /* Was this a bogus SACK? */ if (!sackh) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); chunk->subh.sack_hdr = sackh; ctsn = ntohl(sackh->cum_tsn_ack); /* If Cumulative TSN Ack beyond the max tsn currently * send, terminating the association and respond to the * sender with an ABORT. */ if (TSN_lte(asoc->next_tsn, ctsn)) return sctp_sf_violation_ctsn(net, ep, asoc, type, arg, commands); trace_sctp_probe(ep, asoc, chunk); /* i) If Cumulative TSN Ack is less than the Cumulative TSN * Ack Point, then drop the SACK. Since Cumulative TSN * Ack is monotonically increasing, a SACK whose * Cumulative TSN Ack is less than the Cumulative TSN Ack * Point indicates an out-of-order SACK. */ if (TSN_lt(ctsn, asoc->ctsn_ack_point)) { pr_debug("%s: ctsn:%x, ctsn_ack_point:%x\n", __func__, ctsn, asoc->ctsn_ack_point); return SCTP_DISPOSITION_DISCARD; } /* Return this SACK for further processing. */ sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_SACK, SCTP_CHUNK(chunk)); /* Note: We do the rest of the work on the PROCESS_SACK * sideeffect. */ return SCTP_DISPOSITION_CONSUME; } /* * Generate an ABORT in response to a packet. * * Section: 8.4 Handle "Out of the blue" Packets, sctpimpguide 2.41 * * 8) The receiver should respond to the sender of the OOTB packet with * an ABORT. When sending the ABORT, the receiver of the OOTB packet * MUST fill in the Verification Tag field of the outbound packet * with the value found in the Verification Tag field of the OOTB * packet and set the T-bit in the Chunk Flags to indicate that the * Verification Tag is reflected. After sending this ABORT, the * receiver of the OOTB packet shall discard the OOTB packet and take * no further action. * * Verification Tag: * * The return value is the disposition of the chunk. */ static enum sctp_disposition sctp_sf_tabort_8_4_8( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_packet *packet = NULL; struct sctp_chunk *chunk = arg; struct sctp_chunk *abort; packet = sctp_ootb_pkt_new(net, asoc, chunk); if (!packet) return SCTP_DISPOSITION_NOMEM; /* Make an ABORT. The T bit will be set if the asoc * is NULL. */ abort = sctp_make_abort(asoc, chunk, 0); if (!abort) { sctp_ootb_pkt_free(packet); return SCTP_DISPOSITION_NOMEM; } /* Reflect vtag if T-Bit is set */ if (sctp_test_T_bit(abort)) packet->vtag = ntohl(chunk->sctp_hdr->vtag); /* Set the skb to the belonging sock for accounting. */ abort->skb->sk = ep->base.sk; sctp_packet_append_chunk(packet, abort); sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); return SCTP_DISPOSITION_CONSUME; } /* Handling of SCTP Packets Containing an INIT Chunk Matching an * Existing Associations when the UDP encap port is incorrect. * * From Section 4 at draft-tuexen-tsvwg-sctp-udp-encaps-cons-03. */ static enum sctp_disposition sctp_sf_new_encap_port( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_packet *packet = NULL; struct sctp_chunk *chunk = arg; struct sctp_chunk *abort; packet = sctp_ootb_pkt_new(net, asoc, chunk); if (!packet) return SCTP_DISPOSITION_NOMEM; abort = sctp_make_new_encap_port(asoc, chunk); if (!abort) { sctp_ootb_pkt_free(packet); return SCTP_DISPOSITION_NOMEM; } abort->skb->sk = ep->base.sk; sctp_packet_append_chunk(packet, abort); sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); return SCTP_DISPOSITION_CONSUME; } /* * Received an ERROR chunk from peer. Generate SCTP_REMOTE_ERROR * event as ULP notification for each cause included in the chunk. * * API 5.3.1.3 - SCTP_REMOTE_ERROR * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_operr_notify(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_errhdr *err; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the ERROR chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_operr_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); sctp_walk_errors(err, chunk->chunk_hdr); if ((void *)err != (void *)chunk->chunk_end) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err, commands); sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_OPERR, SCTP_CHUNK(chunk)); return SCTP_DISPOSITION_CONSUME; } /* * Process an inbound SHUTDOWN ACK. * * From Section 9.2: * Upon the receipt of the SHUTDOWN ACK, the SHUTDOWN sender shall * stop the T2-shutdown timer, send a SHUTDOWN COMPLETE chunk to its * peer, and remove all record of the association. * * The return value is the disposition. */ enum sctp_disposition sctp_sf_do_9_2_final(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; struct sctp_ulpevent *ev; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN_ACK chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* 10.2 H) SHUTDOWN COMPLETE notification * * When SCTP completes the shutdown procedures (section 9.2) this * notification is passed to the upper layer. */ ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_SHUTDOWN_COMP, 0, 0, 0, NULL, GFP_ATOMIC); if (!ev) goto nomem; /* ...send a SHUTDOWN COMPLETE chunk to its peer, */ reply = sctp_make_shutdown_complete(asoc, chunk); if (!reply) goto nomem_chunk; /* Do all the commands now (after allocation), so that we * have consistent state if memory allocation fails */ sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); /* Upon the receipt of the SHUTDOWN ACK, the SHUTDOWN sender shall * stop the T2-shutdown timer, */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); SCTP_INC_STATS(net, SCTP_MIB_SHUTDOWNS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); /* ...and remove all record of the association. */ sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); return SCTP_DISPOSITION_DELETE_TCB; nomem_chunk: sctp_ulpevent_free(ev); nomem: return SCTP_DISPOSITION_NOMEM; } /* * RFC 2960, 8.4 - Handle "Out of the blue" Packets, sctpimpguide 2.41. * * 5) If the packet contains a SHUTDOWN ACK chunk, the receiver should * respond to the sender of the OOTB packet with a SHUTDOWN COMPLETE. * When sending the SHUTDOWN COMPLETE, the receiver of the OOTB * packet must fill in the Verification Tag field of the outbound * packet with the Verification Tag received in the SHUTDOWN ACK and * set the T-bit in the Chunk Flags to indicate that the Verification * Tag is reflected. * * 8) The receiver should respond to the sender of the OOTB packet with * an ABORT. When sending the ABORT, the receiver of the OOTB packet * MUST fill in the Verification Tag field of the outbound packet * with the value found in the Verification Tag field of the OOTB * packet and set the T-bit in the Chunk Flags to indicate that the * Verification Tag is reflected. After sending this ABORT, the * receiver of the OOTB packet shall discard the OOTB packet and take * no further action. */ enum sctp_disposition sctp_sf_ootb(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sk_buff *skb = chunk->skb; struct sctp_chunkhdr *ch; struct sctp_errhdr *err; int ootb_cookie_ack = 0; int ootb_shut_ack = 0; __u8 *ch_end; SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); if (asoc && !sctp_vtag_verify(chunk, asoc)) asoc = NULL; ch = (struct sctp_chunkhdr *)chunk->chunk_hdr; do { /* Report violation if the chunk is less then minimal */ if (ntohs(ch->length) < sizeof(*ch)) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Report violation if chunk len overflows */ ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); if (ch_end > skb_tail_pointer(skb)) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Now that we know we at least have a chunk header, * do things that are type appropriate. */ if (SCTP_CID_SHUTDOWN_ACK == ch->type) ootb_shut_ack = 1; /* RFC 2960, Section 3.3.7 * Moreover, under any circumstances, an endpoint that * receives an ABORT MUST NOT respond to that ABORT by * sending an ABORT of its own. */ if (SCTP_CID_ABORT == ch->type) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* RFC 8.4, 7) If the packet contains a "Stale cookie" ERROR * or a COOKIE ACK the SCTP Packet should be silently * discarded. */ if (SCTP_CID_COOKIE_ACK == ch->type) ootb_cookie_ack = 1; if (SCTP_CID_ERROR == ch->type) { sctp_walk_errors(err, ch) { if (SCTP_ERROR_STALE_COOKIE == err->cause) { ootb_cookie_ack = 1; break; } } } ch = (struct sctp_chunkhdr *)ch_end; } while (ch_end < skb_tail_pointer(skb)); if (ootb_shut_ack) return sctp_sf_shut_8_4_5(net, ep, asoc, type, arg, commands); else if (ootb_cookie_ack) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); else return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); } /* * Handle an "Out of the blue" SHUTDOWN ACK. * * Section: 8.4 5, sctpimpguide 2.41. * * 5) If the packet contains a SHUTDOWN ACK chunk, the receiver should * respond to the sender of the OOTB packet with a SHUTDOWN COMPLETE. * When sending the SHUTDOWN COMPLETE, the receiver of the OOTB * packet must fill in the Verification Tag field of the outbound * packet with the Verification Tag received in the SHUTDOWN ACK and * set the T-bit in the Chunk Flags to indicate that the Verification * Tag is reflected. * * Inputs * (endpoint, asoc, type, arg, commands) * * Outputs * (enum sctp_disposition) * * The return value is the disposition of the chunk. */ static enum sctp_disposition sctp_sf_shut_8_4_5( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_packet *packet = NULL; struct sctp_chunk *chunk = arg; struct sctp_chunk *shut; packet = sctp_ootb_pkt_new(net, asoc, chunk); if (!packet) return SCTP_DISPOSITION_NOMEM; /* Make an SHUTDOWN_COMPLETE. * The T bit will be set if the asoc is NULL. */ shut = sctp_make_shutdown_complete(asoc, chunk); if (!shut) { sctp_ootb_pkt_free(packet); return SCTP_DISPOSITION_NOMEM; } /* Reflect vtag if T-Bit is set */ if (sctp_test_T_bit(shut)) packet->vtag = ntohl(chunk->sctp_hdr->vtag); /* Set the skb to the belonging sock for accounting. */ shut->skb->sk = ep->base.sk; sctp_packet_append_chunk(packet, shut); sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); /* We need to discard the rest of the packet to prevent * potential boomming attacks from additional bundled chunks. * This is documented in SCTP Threats ID. */ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } /* * Handle SHUTDOWN ACK in COOKIE_ECHOED or COOKIE_WAIT state. * * Verification Tag: 8.5.1 E) Rules for packet carrying a SHUTDOWN ACK * If the receiver is in COOKIE-ECHOED or COOKIE-WAIT state the * procedures in section 8.4 SHOULD be followed, in other words it * should be treated as an Out Of The Blue packet. * [This means that we do NOT check the Verification Tag on these * chunks. --piggy ] * */ enum sctp_disposition sctp_sf_do_8_5_1_E_sa(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; if (!sctp_vtag_verify(chunk, asoc)) asoc = NULL; /* Make sure that the SHUTDOWN_ACK chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Although we do have an association in this case, it corresponds * to a restarted association. So the packet is treated as an OOTB * packet and the state function that handles OOTB SHUTDOWN_ACK is * called with a NULL association. */ SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); return sctp_sf_shut_8_4_5(net, ep, NULL, type, arg, commands); } /* ADDIP Section 4.2 Upon reception of an ASCONF Chunk. */ enum sctp_disposition sctp_sf_do_asconf(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_paramhdr *err_param = NULL; struct sctp_chunk *asconf_ack = NULL; struct sctp_chunk *chunk = arg; struct sctp_addiphdr *hdr; __u32 serial; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, SCTP_NULL()); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } /* Make sure that the ASCONF ADDIP chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* ADD-IP: Section 4.1.1 * This chunk MUST be sent in an authenticated way by using * the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk * is received unauthenticated it MUST be silently discarded as * described in [I-D.ietf-tsvwg-sctp-auth]. */ if (!asoc->peer.asconf_capable || (!net->sctp.addip_noauth && !chunk->auth)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); hdr = (struct sctp_addiphdr *)chunk->skb->data; serial = ntohl(hdr->serial); /* Verify the ASCONF chunk before processing it. */ if (!sctp_verify_asconf(asoc, chunk, true, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); /* ADDIP 5.2 E1) Compare the value of the serial number to the value * the endpoint stored in a new association variable * 'Peer-Serial-Number'. */ if (serial == asoc->peer.addip_serial + 1) { /* If this is the first instance of ASCONF in the packet, * we can clean our old ASCONF-ACKs. */ if (!chunk->has_asconf) sctp_assoc_clean_asconf_ack_cache(asoc); /* ADDIP 5.2 E4) When the Sequence Number matches the next one * expected, process the ASCONF as described below and after * processing the ASCONF Chunk, append an ASCONF-ACK Chunk to * the response packet and cache a copy of it (in the event it * later needs to be retransmitted). * * Essentially, do V1-V5. */ asconf_ack = sctp_process_asconf((struct sctp_association *) asoc, chunk); if (!asconf_ack) return SCTP_DISPOSITION_NOMEM; } else if (serial < asoc->peer.addip_serial + 1) { /* ADDIP 5.2 E2) * If the value found in the Sequence Number is less than the * ('Peer- Sequence-Number' + 1), simply skip to the next * ASCONF, and include in the outbound response packet * any previously cached ASCONF-ACK response that was * sent and saved that matches the Sequence Number of the * ASCONF. Note: It is possible that no cached ASCONF-ACK * Chunk exists. This will occur when an older ASCONF * arrives out of order. In such a case, the receiver * should skip the ASCONF Chunk and not include ASCONF-ACK * Chunk for that chunk. */ asconf_ack = sctp_assoc_lookup_asconf_ack(asoc, hdr->serial); if (!asconf_ack) return SCTP_DISPOSITION_DISCARD; /* Reset the transport so that we select the correct one * this time around. This is to make sure that we don't * accidentally use a stale transport that's been removed. */ asconf_ack->transport = NULL; } else { /* ADDIP 5.2 E5) Otherwise, the ASCONF Chunk is discarded since * it must be either a stale packet or from an attacker. */ return SCTP_DISPOSITION_DISCARD; } /* ADDIP 5.2 E6) The destination address of the SCTP packet * containing the ASCONF-ACK Chunks MUST be the source address of * the SCTP packet that held the ASCONF Chunks. * * To do this properly, we'll set the destination address of the chunk * and at the transmit time, will try look up the transport to use. * Since ASCONFs may be bundled, the correct transport may not be * created until we process the entire packet, thus this workaround. */ asconf_ack->dest = chunk->source; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(asconf_ack)); if (asoc->new_transport) { sctp_sf_heartbeat(ep, asoc, type, asoc->new_transport, commands); ((struct sctp_association *)asoc)->new_transport = NULL; } return SCTP_DISPOSITION_CONSUME; } static enum sctp_disposition sctp_send_next_asconf( struct net *net, const struct sctp_endpoint *ep, struct sctp_association *asoc, const union sctp_subtype type, struct sctp_cmd_seq *commands) { struct sctp_chunk *asconf; struct list_head *entry; if (list_empty(&asoc->addip_chunk_list)) return SCTP_DISPOSITION_CONSUME; entry = asoc->addip_chunk_list.next; asconf = list_entry(entry, struct sctp_chunk, list); list_del_init(entry); sctp_chunk_hold(asconf); asoc->addip_last_asconf = asconf; return sctp_sf_do_prm_asconf(net, ep, asoc, type, asconf, commands); } /* * ADDIP Section 4.3 General rules for address manipulation * When building TLV parameters for the ASCONF Chunk that will add or * delete IP addresses the D0 to D13 rules should be applied: */ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *last_asconf = asoc->addip_last_asconf; struct sctp_paramhdr *err_param = NULL; struct sctp_chunk *asconf_ack = arg; struct sctp_addiphdr *addip_hdr; __u32 sent_serial, rcvd_serial; struct sctp_chunk *abort; if (!sctp_vtag_verify(asconf_ack, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, SCTP_NULL()); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } /* Make sure that the ADDIP chunk has a valid length. */ if (!sctp_chunk_length_valid(asconf_ack, sizeof(struct sctp_addip_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* ADD-IP, Section 4.1.2: * This chunk MUST be sent in an authenticated way by using * the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk * is received unauthenticated it MUST be silently discarded as * described in [I-D.ietf-tsvwg-sctp-auth]. */ if (!asoc->peer.asconf_capable || (!net->sctp.addip_noauth && !asconf_ack->auth)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); addip_hdr = (struct sctp_addiphdr *)asconf_ack->skb->data; rcvd_serial = ntohl(addip_hdr->serial); /* Verify the ASCONF-ACK chunk before processing it. */ if (!sctp_verify_asconf(asoc, asconf_ack, false, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); if (last_asconf) { addip_hdr = last_asconf->subh.addip_hdr; sent_serial = ntohl(addip_hdr->serial); } else { sent_serial = asoc->addip_serial - 1; } /* D0) If an endpoint receives an ASCONF-ACK that is greater than or * equal to the next serial number to be used but no ASCONF chunk is * outstanding the endpoint MUST ABORT the association. Note that a * sequence number is greater than if it is no more than 2^^31-1 * larger than the current sequence number (using serial arithmetic). */ if (ADDIP_SERIAL_gte(rcvd_serial, sent_serial + 1) && !(asoc->addip_last_asconf)) { abort = sctp_make_abort(asoc, asconf_ack, sizeof(struct sctp_errhdr)); if (abort) { sctp_init_cause(abort, SCTP_ERROR_ASCONF_ACK, 0); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); } /* We are going to ABORT, so we might as well stop * processing the rest of the chunks in the packet. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_ASCONF_ACK)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_DISPOSITION_ABORT; } if ((rcvd_serial == sent_serial) && asoc->addip_last_asconf) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); if (!sctp_process_asconf_ack((struct sctp_association *)asoc, asconf_ack)) return sctp_send_next_asconf(net, ep, (struct sctp_association *)asoc, type, commands); abort = sctp_make_abort(asoc, asconf_ack, sizeof(struct sctp_errhdr)); if (abort) { sctp_init_cause(abort, SCTP_ERROR_RSRC_LOW, 0); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); } /* We are going to ABORT, so we might as well stop * processing the rest of the chunks in the packet. */ sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_ASCONF_ACK)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_DISPOSITION_ABORT; } return SCTP_DISPOSITION_DISCARD; } /* RE-CONFIG Section 5.2 Upon reception of an RECONF Chunk. */ enum sctp_disposition sctp_sf_do_reconf(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_paramhdr *err_param = NULL; struct sctp_chunk *chunk = arg; struct sctp_reconf_chunk *hdr; union sctp_params param; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, SCTP_NULL()); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } /* Make sure that the RECONF chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(*hdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); if (!sctp_verify_reconf(asoc, chunk, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr; sctp_walk_params(param, hdr) { struct sctp_chunk *reply = NULL; struct sctp_ulpevent *ev = NULL; if (param.p->type == SCTP_PARAM_RESET_OUT_REQUEST) reply = sctp_process_strreset_outreq( (struct sctp_association *)asoc, param, &ev); else if (param.p->type == SCTP_PARAM_RESET_IN_REQUEST) reply = sctp_process_strreset_inreq( (struct sctp_association *)asoc, param, &ev); else if (param.p->type == SCTP_PARAM_RESET_TSN_REQUEST) reply = sctp_process_strreset_tsnreq( (struct sctp_association *)asoc, param, &ev); else if (param.p->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) reply = sctp_process_strreset_addstrm_out( (struct sctp_association *)asoc, param, &ev); else if (param.p->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) reply = sctp_process_strreset_addstrm_in( (struct sctp_association *)asoc, param, &ev); else if (param.p->type == SCTP_PARAM_RESET_RESPONSE) reply = sctp_process_strreset_resp( (struct sctp_association *)asoc, param, &ev); if (ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); if (reply) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); } return SCTP_DISPOSITION_CONSUME; } /* * PR-SCTP Section 3.6 Receiver Side Implementation of PR-SCTP * * When a FORWARD TSN chunk arrives, the data receiver MUST first update * its cumulative TSN point to the value carried in the FORWARD TSN * chunk, and then MUST further advance its cumulative TSN point locally * if possible. * After the above processing, the data receiver MUST stop reporting any * missing TSNs earlier than or equal to the new cumulative TSN point. * * Verification Tag: 8.5 Verification Tag [Normal verification] * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_eat_fwd_tsn(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_fwdtsn_hdr *fwdtsn_hdr; struct sctp_chunk *chunk = arg; __u16 len; __u32 tsn; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, SCTP_NULL()); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } if (!asoc->peer.prsctp_capable) return sctp_sf_unk_chunk(net, ep, asoc, type, arg, commands); /* Make sure that the FORWARD_TSN chunk has valid length. */ if (!sctp_chunk_length_valid(chunk, sctp_ftsnchk_len(&asoc->stream))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); fwdtsn_hdr = (struct sctp_fwdtsn_hdr *)chunk->skb->data; chunk->subh.fwdtsn_hdr = fwdtsn_hdr; len = ntohs(chunk->chunk_hdr->length); len -= sizeof(struct sctp_chunkhdr); skb_pull(chunk->skb, len); tsn = ntohl(fwdtsn_hdr->new_cum_tsn); pr_debug("%s: TSN 0x%x\n", __func__, tsn); /* The TSN is too high--silently discard the chunk and count on it * getting retransmitted later. */ if (sctp_tsnmap_check(&asoc->peer.tsn_map, tsn) < 0) goto discard_noforce; if (!asoc->stream.si->validate_ftsn(chunk)) goto discard_noforce; sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_FWDTSN, SCTP_U32(tsn)); if (len > sctp_ftsnhdr_len(&asoc->stream)) sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_FWDTSN, SCTP_CHUNK(chunk)); /* Count this as receiving DATA. */ if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); } /* FIXME: For now send a SACK, but DATA processing may * send another. */ sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_NOFORCE()); return SCTP_DISPOSITION_CONSUME; discard_noforce: return SCTP_DISPOSITION_DISCARD; } enum sctp_disposition sctp_sf_eat_fwd_tsn_fast( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_fwdtsn_hdr *fwdtsn_hdr; struct sctp_chunk *chunk = arg; __u16 len; __u32 tsn; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, SCTP_NULL()); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } if (!asoc->peer.prsctp_capable) return sctp_sf_unk_chunk(net, ep, asoc, type, arg, commands); /* Make sure that the FORWARD_TSN chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sctp_ftsnchk_len(&asoc->stream))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); fwdtsn_hdr = (struct sctp_fwdtsn_hdr *)chunk->skb->data; chunk->subh.fwdtsn_hdr = fwdtsn_hdr; len = ntohs(chunk->chunk_hdr->length); len -= sizeof(struct sctp_chunkhdr); skb_pull(chunk->skb, len); tsn = ntohl(fwdtsn_hdr->new_cum_tsn); pr_debug("%s: TSN 0x%x\n", __func__, tsn); /* The TSN is too high--silently discard the chunk and count on it * getting retransmitted later. */ if (sctp_tsnmap_check(&asoc->peer.tsn_map, tsn) < 0) goto gen_shutdown; if (!asoc->stream.si->validate_ftsn(chunk)) goto gen_shutdown; sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_FWDTSN, SCTP_U32(tsn)); if (len > sctp_ftsnhdr_len(&asoc->stream)) sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_FWDTSN, SCTP_CHUNK(chunk)); /* Go a head and force a SACK, since we are shutting down. */ gen_shutdown: /* Implementor's Guide. * * While in SHUTDOWN-SENT state, the SHUTDOWN sender MUST immediately * respond to each received packet containing one or more DATA chunk(s) * with a SACK, a SHUTDOWN chunk, and restart the T2-shutdown timer */ sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SHUTDOWN, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_FORCE()); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); return SCTP_DISPOSITION_CONSUME; } /* * SCTP-AUTH Section 6.3 Receiving authenticated chunks * * The receiver MUST use the HMAC algorithm indicated in the HMAC * Identifier field. If this algorithm was not specified by the * receiver in the HMAC-ALGO parameter in the INIT or INIT-ACK chunk * during association setup, the AUTH chunk and all chunks after it MUST * be discarded and an ERROR chunk SHOULD be sent with the error cause * defined in Section 4.1. * * If an endpoint with no shared key receives a Shared Key Identifier * other than 0, it MUST silently discard all authenticated chunks. If * the endpoint has at least one endpoint pair shared key for the peer, * it MUST use the key specified by the Shared Key Identifier if a * key has been configured for that Shared Key Identifier. If no * endpoint pair shared key has been configured for that Shared Key * Identifier, all authenticated chunks MUST be silently discarded. * * Verification Tag: 8.5 Verification Tag [Normal verification] * * The return value is the disposition of the chunk. */ static enum sctp_ierror sctp_sf_authenticate( const struct sctp_association *asoc, struct sctp_chunk *chunk) { struct sctp_shared_key *sh_key = NULL; struct sctp_authhdr *auth_hdr; __u8 *save_digest, *digest; struct sctp_hmac *hmac; unsigned int sig_len; __u16 key_id; /* Pull in the auth header, so we can do some more verification */ auth_hdr = (struct sctp_authhdr *)chunk->skb->data; chunk->subh.auth_hdr = auth_hdr; skb_pull(chunk->skb, sizeof(*auth_hdr)); /* Make sure that we support the HMAC algorithm from the auth * chunk. */ if (!sctp_auth_asoc_verify_hmac_id(asoc, auth_hdr->hmac_id)) return SCTP_IERROR_AUTH_BAD_HMAC; /* Make sure that the provided shared key identifier has been * configured */ key_id = ntohs(auth_hdr->shkey_id); if (key_id != asoc->active_key_id) { sh_key = sctp_auth_get_shkey(asoc, key_id); if (!sh_key) return SCTP_IERROR_AUTH_BAD_KEYID; } /* Make sure that the length of the signature matches what * we expect. */ sig_len = ntohs(chunk->chunk_hdr->length) - sizeof(struct sctp_auth_chunk); hmac = sctp_auth_get_hmac(ntohs(auth_hdr->hmac_id)); if (sig_len != hmac->hmac_len) return SCTP_IERROR_PROTO_VIOLATION; /* Now that we've done validation checks, we can compute and * verify the hmac. The steps involved are: * 1. Save the digest from the chunk. * 2. Zero out the digest in the chunk. * 3. Compute the new digest * 4. Compare saved and new digests. */ digest = (u8 *)(auth_hdr + 1); skb_pull(chunk->skb, sig_len); save_digest = kmemdup(digest, sig_len, GFP_ATOMIC); if (!save_digest) goto nomem; memset(digest, 0, sig_len); sctp_auth_calculate_hmac(asoc, chunk->skb, (struct sctp_auth_chunk *)chunk->chunk_hdr, sh_key, GFP_ATOMIC); /* Discard the packet if the digests do not match */ if (memcmp(save_digest, digest, sig_len)) { kfree(save_digest); return SCTP_IERROR_BAD_SIG; } kfree(save_digest); chunk->auth = 1; return SCTP_IERROR_NO_ERROR; nomem: return SCTP_IERROR_NOMEM; } enum sctp_disposition sctp_sf_eat_auth(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_authhdr *auth_hdr; struct sctp_chunk *err_chunk; enum sctp_ierror error; /* Make sure that the peer has AUTH capable */ if (!asoc->peer.auth_capable) return sctp_sf_unk_chunk(net, ep, asoc, type, arg, commands); if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, SCTP_NULL()); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } /* Make sure that the AUTH chunk has valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_auth_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); auth_hdr = (struct sctp_authhdr *)chunk->skb->data; error = sctp_sf_authenticate(asoc, chunk); switch (error) { case SCTP_IERROR_AUTH_BAD_HMAC: /* Generate the ERROR chunk and discard the rest * of the packet */ err_chunk = sctp_make_op_error(asoc, chunk, SCTP_ERROR_UNSUP_HMAC, &auth_hdr->hmac_id, sizeof(__u16), 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err_chunk)); } fallthrough; case SCTP_IERROR_AUTH_BAD_KEYID: case SCTP_IERROR_BAD_SIG: return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); case SCTP_IERROR_PROTO_VIOLATION: return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); case SCTP_IERROR_NOMEM: return SCTP_DISPOSITION_NOMEM; default: /* Prevent gcc warnings */ break; } if (asoc->active_key_id != ntohs(auth_hdr->shkey_id)) { struct sctp_ulpevent *ev; ev = sctp_ulpevent_make_authkey(asoc, ntohs(auth_hdr->shkey_id), SCTP_AUTH_NEW_KEY, GFP_ATOMIC); if (!ev) return SCTP_DISPOSITION_NOMEM; sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); } return SCTP_DISPOSITION_CONSUME; } /* * Process an unknown chunk. * * Section: 3.2. Also, 2.1 in the implementor's guide. * * Chunk Types are encoded such that the highest-order two bits specify * the action that must be taken if the processing endpoint does not * recognize the Chunk Type. * * 00 - Stop processing this SCTP packet and discard it, do not process * any further chunks within it. * * 01 - Stop processing this SCTP packet and discard it, do not process * any further chunks within it, and report the unrecognized * chunk in an 'Unrecognized Chunk Type'. * * 10 - Skip this chunk and continue processing. * * 11 - Skip this chunk and continue processing, but report in an ERROR * Chunk using the 'Unrecognized Chunk Type' cause of error. * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_unk_chunk(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *unk_chunk = arg; struct sctp_chunk *err_chunk; struct sctp_chunkhdr *hdr; pr_debug("%s: processing unknown chunk id:%d\n", __func__, type.chunk); if (!sctp_vtag_verify(unk_chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the chunk has a valid length. * Since we don't know the chunk type, we use a general * chunkhdr structure to make a comparison. */ if (!sctp_chunk_length_valid(unk_chunk, sizeof(*hdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); switch (type.chunk & SCTP_CID_ACTION_MASK) { case SCTP_CID_ACTION_DISCARD: /* Discard the packet. */ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); case SCTP_CID_ACTION_DISCARD_ERR: /* Generate an ERROR chunk as response. */ hdr = unk_chunk->chunk_hdr; err_chunk = sctp_make_op_error(asoc, unk_chunk, SCTP_ERROR_UNKNOWN_CHUNK, hdr, SCTP_PAD4(ntohs(hdr->length)), 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err_chunk)); } /* Discard the packet. */ sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); return SCTP_DISPOSITION_CONSUME; case SCTP_CID_ACTION_SKIP: /* Skip the chunk. */ return SCTP_DISPOSITION_DISCARD; case SCTP_CID_ACTION_SKIP_ERR: /* Generate an ERROR chunk as response. */ hdr = unk_chunk->chunk_hdr; err_chunk = sctp_make_op_error(asoc, unk_chunk, SCTP_ERROR_UNKNOWN_CHUNK, hdr, SCTP_PAD4(ntohs(hdr->length)), 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err_chunk)); } /* Skip the chunk. */ return SCTP_DISPOSITION_CONSUME; default: break; } return SCTP_DISPOSITION_DISCARD; } /* * Discard the chunk. * * Section: 0.2, 5.2.3, 5.2.5, 5.2.6, 6.0, 8.4.6, 8.5.1c, 9.2 * [Too numerous to mention...] * Verification Tag: No verification needed. * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_discard_chunk(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; if (asoc && !sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the chunk has a valid length. * Since we don't know the chunk type, we use a general * chunkhdr structure to make a comparison. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); pr_debug("%s: chunk:%d is discarded\n", __func__, type.chunk); return SCTP_DISPOSITION_DISCARD; } /* * Discard the whole packet. * * Section: 8.4 2) * * 2) If the OOTB packet contains an ABORT chunk, the receiver MUST * silently discard the OOTB packet and take no further action. * * Verification Tag: No verification necessary * * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_pdiscard(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_DISCARDS); sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); return SCTP_DISPOSITION_CONSUME; } /* * The other end is violating protocol. * * Section: Not specified * Verification Tag: Not specified * Inputs * (endpoint, asoc, chunk) * * Outputs * (asoc, reply_msg, msg_up, timers, counters) * * We simply tag the chunk as a violation. The state machine will log * the violation and continue. */ enum sctp_disposition sctp_sf_violation(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); return SCTP_DISPOSITION_VIOLATION; } /* * Common function to handle a protocol violation. */ static enum sctp_disposition sctp_sf_abort_violation( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, void *arg, struct sctp_cmd_seq *commands, const __u8 *payload, const size_t paylen) { struct sctp_packet *packet = NULL; struct sctp_chunk *chunk = arg; struct sctp_chunk *abort = NULL; /* SCTP-AUTH, Section 6.3: * It should be noted that if the receiver wants to tear * down an association in an authenticated way only, the * handling of malformed packets should not result in * tearing down the association. * * This means that if we only want to abort associations * in an authenticated way (i.e AUTH+ABORT), then we * can't destroy this association just because the packet * was malformed. */ if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)) goto discard; /* Make the abort chunk. */ abort = sctp_make_abort_violation(asoc, chunk, payload, paylen); if (!abort) goto nomem; if (asoc) { /* Treat INIT-ACK as a special case during COOKIE-WAIT. */ if (chunk->chunk_hdr->type == SCTP_CID_INIT_ACK && !asoc->peer.i.init_tag) { struct sctp_initack_chunk *initack; initack = (struct sctp_initack_chunk *)chunk->chunk_hdr; if (!sctp_chunk_length_valid(chunk, sizeof(*initack))) abort->chunk_hdr->flags |= SCTP_CHUNK_FLAG_T; else { unsigned int inittag; inittag = ntohl(initack->init_hdr.init_tag); sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_INITTAG, SCTP_U32(inittag)); } } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); if (asoc->state <= SCTP_STATE_COOKIE_ECHOED) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNREFUSED)); sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, SCTP_PERR(SCTP_ERROR_PROTO_VIOLATION)); } else { sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_PROTO_VIOLATION)); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); } } else { packet = sctp_ootb_pkt_new(net, asoc, chunk); if (!packet) goto nomem_pkt; if (sctp_test_T_bit(abort)) packet->vtag = ntohl(chunk->sctp_hdr->vtag); abort->skb->sk = ep->base.sk; sctp_packet_append_chunk(packet, abort); sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); } SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); discard: sctp_sf_pdiscard(net, ep, asoc, SCTP_ST_CHUNK(0), arg, commands); return SCTP_DISPOSITION_ABORT; nomem_pkt: sctp_chunk_free(abort); nomem: return SCTP_DISPOSITION_NOMEM; } /* * Handle a protocol violation when the chunk length is invalid. * "Invalid" length is identified as smaller than the minimal length a * given chunk can be. For example, a SACK chunk has invalid length * if its length is set to be smaller than the size of struct sctp_sack_chunk. * * We inform the other end by sending an ABORT with a Protocol Violation * error code. * * Section: Not specified * Verification Tag: Nothing to do * Inputs * (endpoint, asoc, chunk) * * Outputs * (reply_msg, msg_up, counters) * * Generate an ABORT chunk and terminate the association. */ static enum sctp_disposition sctp_sf_violation_chunklen( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { static const char err_str[] = "The following chunk had invalid length:"; return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str, sizeof(err_str)); } /* * Handle a protocol violation when the parameter length is invalid. * If the length is smaller than the minimum length of a given parameter, * or accumulated length in multi parameters exceeds the end of the chunk, * the length is considered as invalid. */ static enum sctp_disposition sctp_sf_violation_paramlen( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, void *ext, struct sctp_cmd_seq *commands) { struct sctp_paramhdr *param = ext; struct sctp_chunk *abort = NULL; struct sctp_chunk *chunk = arg; if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)) goto discard; /* Make the abort chunk. */ abort = sctp_make_violation_paramlen(asoc, chunk, param); if (!abort) goto nomem; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_PROTO_VIOLATION)); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); discard: sctp_sf_pdiscard(net, ep, asoc, SCTP_ST_CHUNK(0), arg, commands); return SCTP_DISPOSITION_ABORT; nomem: return SCTP_DISPOSITION_NOMEM; } /* Handle a protocol violation when the peer trying to advance the * cumulative tsn ack to a point beyond the max tsn currently sent. * * We inform the other end by sending an ABORT with a Protocol Violation * error code. */ static enum sctp_disposition sctp_sf_violation_ctsn( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { static const char err_str[] = "The cumulative tsn ack beyond the max tsn currently sent:"; return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str, sizeof(err_str)); } /* Handle protocol violation of an invalid chunk bundling. For example, * when we have an association and we receive bundled INIT-ACK, or * SHUTDOWN-COMPLETE, our peer is clearly violating the "MUST NOT bundle" * statement from the specs. Additionally, there might be an attacker * on the path and we may not want to continue this communication. */ static enum sctp_disposition sctp_sf_violation_chunk( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { static const char err_str[] = "The following chunk violates protocol:"; return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str, sizeof(err_str)); } /*************************************************************************** * These are the state functions for handling primitive (Section 10) events. ***************************************************************************/ /* * sctp_sf_do_prm_asoc * * Section: 10.1 ULP-to-SCTP * B) Associate * * Format: ASSOCIATE(local SCTP instance name, destination transport addr, * outbound stream count) * -> association id [,destination transport addr list] [,outbound stream * count] * * This primitive allows the upper layer to initiate an association to a * specific peer endpoint. * * The peer endpoint shall be specified by one of the transport addresses * which defines the endpoint (see Section 1.4). If the local SCTP * instance has not been initialized, the ASSOCIATE is considered an * error. * [This is not relevant for the kernel implementation since we do all * initialization at boot time. It we hadn't initialized we wouldn't * get anywhere near this code.] * * An association id, which is a local handle to the SCTP association, * will be returned on successful establishment of the association. If * SCTP is not able to open an SCTP association with the peer endpoint, * an error is returned. * [In the kernel implementation, the struct sctp_association needs to * be created BEFORE causing this primitive to run.] * * Other association parameters may be returned, including the * complete destination transport addresses of the peer as well as the * outbound stream count of the local endpoint. One of the transport * address from the returned destination addresses will be selected by * the local endpoint as default primary path for sending SCTP packets * to this peer. The returned "destination transport addr list" can * be used by the ULP to change the default primary path or to force * sending a packet to a specific transport address. [All of this * stuff happens when the INIT ACK arrives. This is a NON-BLOCKING * function.] * * Mandatory attributes: * * o local SCTP instance name - obtained from the INITIALIZE operation. * [This is the argument asoc.] * o destination transport addr - specified as one of the transport * addresses of the peer endpoint with which the association is to be * established. * [This is asoc->peer.active_path.] * o outbound stream count - the number of outbound streams the ULP * would like to open towards this peer endpoint. * [BUG: This is not currently implemented.] * Optional attributes: * * None. * * The return value is a disposition. */ enum sctp_disposition sctp_sf_do_prm_asoc(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_association *my_asoc; struct sctp_chunk *repl; /* The comment below says that we enter COOKIE-WAIT AFTER * sending the INIT, but that doesn't actually work in our * implementation... */ sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_COOKIE_WAIT)); /* RFC 2960 5.1 Normal Establishment of an Association * * A) "A" first sends an INIT chunk to "Z". In the INIT, "A" * must provide its Verification Tag (Tag_A) in the Initiate * Tag field. Tag_A SHOULD be a random number in the range of * 1 to 4294967295 (see 5.3.1 for Tag value selection). ... */ repl = sctp_make_init(asoc, &asoc->base.bind_addr, GFP_ATOMIC, 0); if (!repl) goto nomem; /* Choose transport for INIT. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_CHOOSE_TRANSPORT, SCTP_CHUNK(repl)); /* Cast away the const modifier, as we want to just * rerun it through as a sideffect. */ my_asoc = (struct sctp_association *)asoc; sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(my_asoc)); /* After sending the INIT, "A" starts the T1-init timer and * enters the COOKIE-WAIT state. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); return SCTP_DISPOSITION_CONSUME; nomem: return SCTP_DISPOSITION_NOMEM; } /* * Process the SEND primitive. * * Section: 10.1 ULP-to-SCTP * E) Send * * Format: SEND(association id, buffer address, byte count [,context] * [,stream id] [,life time] [,destination transport address] * [,unorder flag] [,no-bundle flag] [,payload protocol-id] ) * -> result * * This is the main method to send user data via SCTP. * * Mandatory attributes: * * o association id - local handle to the SCTP association * * o buffer address - the location where the user message to be * transmitted is stored; * * o byte count - The size of the user data in number of bytes; * * Optional attributes: * * o context - an optional 32 bit integer that will be carried in the * sending failure notification to the ULP if the transportation of * this User Message fails. * * o stream id - to indicate which stream to send the data on. If not * specified, stream 0 will be used. * * o life time - specifies the life time of the user data. The user data * will not be sent by SCTP after the life time expires. This * parameter can be used to avoid efforts to transmit stale * user messages. SCTP notifies the ULP if the data cannot be * initiated to transport (i.e. sent to the destination via SCTP's * send primitive) within the life time variable. However, the * user data will be transmitted if SCTP has attempted to transmit a * chunk before the life time expired. * * o destination transport address - specified as one of the destination * transport addresses of the peer endpoint to which this packet * should be sent. Whenever possible, SCTP should use this destination * transport address for sending the packets, instead of the current * primary path. * * o unorder flag - this flag, if present, indicates that the user * would like the data delivered in an unordered fashion to the peer * (i.e., the U flag is set to 1 on all DATA chunks carrying this * message). * * o no-bundle flag - instructs SCTP not to bundle this user data with * other outbound DATA chunks. SCTP MAY still bundle even when * this flag is present, when faced with network congestion. * * o payload protocol-id - A 32 bit unsigned integer that is to be * passed to the peer indicating the type of payload protocol data * being transmitted. This value is passed as opaque data by SCTP. * * The return value is the disposition. */ enum sctp_disposition sctp_sf_do_prm_send(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_datamsg *msg = arg; sctp_add_cmd_sf(commands, SCTP_CMD_SEND_MSG, SCTP_DATAMSG(msg)); return SCTP_DISPOSITION_CONSUME; } /* * Process the SHUTDOWN primitive. * * Section: 10.1: * C) Shutdown * * Format: SHUTDOWN(association id) * -> result * * Gracefully closes an association. Any locally queued user data * will be delivered to the peer. The association will be terminated only * after the peer acknowledges all the SCTP packets sent. A success code * will be returned on successful termination of the association. If * attempting to terminate the association results in a failure, an error * code shall be returned. * * Mandatory attributes: * * o association id - local handle to the SCTP association * * Optional attributes: * * None. * * The return value is the disposition. */ enum sctp_disposition sctp_sf_do_9_2_prm_shutdown( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { enum sctp_disposition disposition; /* From 9.2 Shutdown of an Association * Upon receipt of the SHUTDOWN primitive from its upper * layer, the endpoint enters SHUTDOWN-PENDING state and * remains there until all outstanding data has been * acknowledged by its peer. The endpoint accepts no new data * from its upper layer, but retransmits data to the far end * if necessary to fill gaps. */ sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_SHUTDOWN_PENDING)); disposition = SCTP_DISPOSITION_CONSUME; if (sctp_outq_is_empty(&asoc->outqueue)) { disposition = sctp_sf_do_9_2_start_shutdown(net, ep, asoc, type, arg, commands); } return disposition; } /* * Process the ABORT primitive. * * Section: 10.1: * C) Abort * * Format: Abort(association id [, cause code]) * -> result * * Ungracefully closes an association. Any locally queued user data * will be discarded and an ABORT chunk is sent to the peer. A success code * will be returned on successful abortion of the association. If * attempting to abort the association results in a failure, an error * code shall be returned. * * Mandatory attributes: * * o association id - local handle to the SCTP association * * Optional attributes: * * o cause code - reason of the abort to be passed to the peer * * None. * * The return value is the disposition. */ enum sctp_disposition sctp_sf_do_9_1_prm_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* From 9.1 Abort of an Association * Upon receipt of the ABORT primitive from its upper * layer, the endpoint enters CLOSED state and * discard all outstanding data has been * acknowledged by its peer. The endpoint accepts no new data * from its upper layer, but retransmits data to the far end * if necessary to fill gaps. */ struct sctp_chunk *abort = arg; if (abort) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); /* Even if we can't send the ABORT due to low memory delete the * TCB. This is a departure from our typical NOMEM handling. */ sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); /* Delete the established association. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_USER_ABORT)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_DISPOSITION_ABORT; } /* We tried an illegal operation on an association which is closed. */ enum sctp_disposition sctp_sf_error_closed(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_ERROR, SCTP_ERROR(-EINVAL)); return SCTP_DISPOSITION_CONSUME; } /* We tried an illegal operation on an association which is shutting * down. */ enum sctp_disposition sctp_sf_error_shutdown( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_ERROR, SCTP_ERROR(-ESHUTDOWN)); return SCTP_DISPOSITION_CONSUME; } /* * sctp_cookie_wait_prm_shutdown * * Section: 4 Note: 2 * Verification Tag: * Inputs * (endpoint, asoc) * * The RFC does not explicitly address this issue, but is the route through the * state table when someone issues a shutdown while in COOKIE_WAIT state. * * Outputs * (timers) */ enum sctp_disposition sctp_sf_cookie_wait_prm_shutdown( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); SCTP_INC_STATS(net, SCTP_MIB_SHUTDOWNS); sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); return SCTP_DISPOSITION_DELETE_TCB; } /* * sctp_cookie_echoed_prm_shutdown * * Section: 4 Note: 2 * Verification Tag: * Inputs * (endpoint, asoc) * * The RFC does not explicitly address this issue, but is the route through the * state table when someone issues a shutdown while in COOKIE_ECHOED state. * * Outputs * (timers) */ enum sctp_disposition sctp_sf_cookie_echoed_prm_shutdown( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* There is a single T1 timer, so we should be able to use * common function with the COOKIE-WAIT state. */ return sctp_sf_cookie_wait_prm_shutdown(net, ep, asoc, type, arg, commands); } /* * sctp_sf_cookie_wait_prm_abort * * Section: 4 Note: 2 * Verification Tag: * Inputs * (endpoint, asoc) * * The RFC does not explicitly address this issue, but is the route through the * state table when someone issues an abort while in COOKIE_WAIT state. * * Outputs * (timers) */ enum sctp_disposition sctp_sf_cookie_wait_prm_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *abort = arg; /* Stop T1-init timer */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); if (abort) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); /* Even if we can't send the ABORT due to low memory delete the * TCB. This is a departure from our typical NOMEM handling. */ sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNREFUSED)); /* Delete the established association. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, SCTP_PERR(SCTP_ERROR_USER_ABORT)); return SCTP_DISPOSITION_ABORT; } /* * sctp_sf_cookie_echoed_prm_abort * * Section: 4 Note: 3 * Verification Tag: * Inputs * (endpoint, asoc) * * The RFC does not explcitly address this issue, but is the route through the * state table when someone issues an abort while in COOKIE_ECHOED state. * * Outputs * (timers) */ enum sctp_disposition sctp_sf_cookie_echoed_prm_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* There is a single T1 timer, so we should be able to use * common function with the COOKIE-WAIT state. */ return sctp_sf_cookie_wait_prm_abort(net, ep, asoc, type, arg, commands); } /* * sctp_sf_shutdown_pending_prm_abort * * Inputs * (endpoint, asoc) * * The RFC does not explicitly address this issue, but is the route through the * state table when someone issues an abort while in SHUTDOWN-PENDING state. * * Outputs * (timers) */ enum sctp_disposition sctp_sf_shutdown_pending_prm_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* Stop the T5-shutdown guard timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); return sctp_sf_do_9_1_prm_abort(net, ep, asoc, type, arg, commands); } /* * sctp_sf_shutdown_sent_prm_abort * * Inputs * (endpoint, asoc) * * The RFC does not explicitly address this issue, but is the route through the * state table when someone issues an abort while in SHUTDOWN-SENT state. * * Outputs * (timers) */ enum sctp_disposition sctp_sf_shutdown_sent_prm_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* Stop the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); /* Stop the T5-shutdown guard timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); return sctp_sf_do_9_1_prm_abort(net, ep, asoc, type, arg, commands); } /* * sctp_sf_cookie_echoed_prm_abort * * Inputs * (endpoint, asoc) * * The RFC does not explcitly address this issue, but is the route through the * state table when someone issues an abort while in COOKIE_ECHOED state. * * Outputs * (timers) */ enum sctp_disposition sctp_sf_shutdown_ack_sent_prm_abort( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { /* The same T2 timer, so we should be able to use * common function with the SHUTDOWN-SENT state. */ return sctp_sf_shutdown_sent_prm_abort(net, ep, asoc, type, arg, commands); } /* * Process the REQUESTHEARTBEAT primitive * * 10.1 ULP-to-SCTP * J) Request Heartbeat * * Format: REQUESTHEARTBEAT(association id, destination transport address) * * -> result * * Instructs the local endpoint to perform a HeartBeat on the specified * destination transport address of the given association. The returned * result should indicate whether the transmission of the HEARTBEAT * chunk to the destination address is successful. * * Mandatory attributes: * * o association id - local handle to the SCTP association * * o destination transport address - the transport address of the * association on which a heartbeat should be issued. */ enum sctp_disposition sctp_sf_do_prm_requestheartbeat( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { if (SCTP_DISPOSITION_NOMEM == sctp_sf_heartbeat(ep, asoc, type, (struct sctp_transport *)arg, commands)) return SCTP_DISPOSITION_NOMEM; /* * RFC 2960 (bis), section 8.3 * * D) Request an on-demand HEARTBEAT on a specific destination * transport address of a given association. * * The endpoint should increment the respective error counter of * the destination transport address each time a HEARTBEAT is sent * to that address and not acknowledged within one RTO. * */ sctp_add_cmd_sf(commands, SCTP_CMD_TRANSPORT_HB_SENT, SCTP_TRANSPORT(arg)); return SCTP_DISPOSITION_CONSUME; } /* * ADDIP Section 4.1 ASCONF Chunk Procedures * When an endpoint has an ASCONF signaled change to be sent to the * remote endpoint it should do A1 to A9 */ enum sctp_disposition sctp_sf_do_prm_asconf(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; sctp_add_cmd_sf(commands, SCTP_CMD_SETUP_T4, SCTP_CHUNK(chunk)); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(chunk)); return SCTP_DISPOSITION_CONSUME; } /* RE-CONFIG Section 5.1 RECONF Chunk Procedures */ enum sctp_disposition sctp_sf_do_prm_reconf(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(chunk)); return SCTP_DISPOSITION_CONSUME; } /* * Ignore the primitive event * * The return value is the disposition of the primitive. */ enum sctp_disposition sctp_sf_ignore_primitive( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { pr_debug("%s: primitive type:%d is ignored\n", __func__, type.primitive); return SCTP_DISPOSITION_DISCARD; } /*************************************************************************** * These are the state functions for the OTHER events. ***************************************************************************/ /* * When the SCTP stack has no more user data to send or retransmit, this * notification is given to the user. Also, at the time when a user app * subscribes to this event, if there is no data to be sent or * retransmit, the stack will immediately send up this notification. */ enum sctp_disposition sctp_sf_do_no_pending_tsn( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_ulpevent *event; event = sctp_ulpevent_make_sender_dry_event(asoc, GFP_ATOMIC); if (!event) return SCTP_DISPOSITION_NOMEM; sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(event)); return SCTP_DISPOSITION_CONSUME; } /* * Start the shutdown negotiation. * * From Section 9.2: * Once all its outstanding data has been acknowledged, the endpoint * shall send a SHUTDOWN chunk to its peer including in the Cumulative * TSN Ack field the last sequential TSN it has received from the peer. * It shall then start the T2-shutdown timer and enter the SHUTDOWN-SENT * state. If the timer expires, the endpoint must re-send the SHUTDOWN * with the updated last sequential TSN received from its peer. * * The return value is the disposition. */ enum sctp_disposition sctp_sf_do_9_2_start_shutdown( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *reply; /* Once all its outstanding data has been acknowledged, the * endpoint shall send a SHUTDOWN chunk to its peer including * in the Cumulative TSN Ack field the last sequential TSN it * has received from the peer. */ reply = sctp_make_shutdown(asoc, arg); if (!reply) goto nomem; /* Set the transport for the SHUTDOWN chunk and the timeout for the * T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_SETUP_T2, SCTP_CHUNK(reply)); /* It shall then start the T2-shutdown timer */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); /* RFC 4960 Section 9.2 * The sender of the SHUTDOWN MAY also start an overall guard timer * 'T5-shutdown-guard' to bound the overall time for shutdown sequence. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); /* and enter the SHUTDOWN-SENT state. */ sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_SHUTDOWN_SENT)); /* sctp-implguide 2.10 Issues with Heartbeating and failover * * HEARTBEAT ... is discontinued after sending either SHUTDOWN * or SHUTDOWN-ACK. */ sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_STOP, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); return SCTP_DISPOSITION_CONSUME; nomem: return SCTP_DISPOSITION_NOMEM; } /* * Generate a SHUTDOWN ACK now that everything is SACK'd. * * From Section 9.2: * * If it has no more outstanding DATA chunks, the SHUTDOWN receiver * shall send a SHUTDOWN ACK and start a T2-shutdown timer of its own, * entering the SHUTDOWN-ACK-SENT state. If the timer expires, the * endpoint must re-send the SHUTDOWN ACK. * * The return value is the disposition. */ enum sctp_disposition sctp_sf_do_9_2_shutdown_ack( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; /* There are 2 ways of getting here: * 1) called in response to a SHUTDOWN chunk * 2) called when SCTP_EVENT_NO_PENDING_TSN event is issued. * * For the case (2), the arg parameter is set to NULL. We need * to check that we have a chunk before accessing it's fields. */ if (chunk) { if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN chunk has a valid length. */ if (!sctp_chunk_length_valid( chunk, sizeof(struct sctp_shutdown_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); } /* If it has no more outstanding DATA chunks, the SHUTDOWN receiver * shall send a SHUTDOWN ACK ... */ reply = sctp_make_shutdown_ack(asoc, chunk); if (!reply) goto nomem; /* Set the transport for the SHUTDOWN ACK chunk and the timeout for * the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_SETUP_T2, SCTP_CHUNK(reply)); /* and start/restart a T2-shutdown timer of its own, */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); /* Enter the SHUTDOWN-ACK-SENT state. */ sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_SHUTDOWN_ACK_SENT)); /* sctp-implguide 2.10 Issues with Heartbeating and failover * * HEARTBEAT ... is discontinued after sending either SHUTDOWN * or SHUTDOWN-ACK. */ sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_STOP, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); return SCTP_DISPOSITION_CONSUME; nomem: return SCTP_DISPOSITION_NOMEM; } /* * Ignore the event defined as other * * The return value is the disposition of the event. */ enum sctp_disposition sctp_sf_ignore_other(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { pr_debug("%s: the event other type:%d is ignored\n", __func__, type.other); return SCTP_DISPOSITION_DISCARD; } /************************************************************ * These are the state functions for handling timeout events. ************************************************************/ /* * RTX Timeout * * Section: 6.3.3 Handle T3-rtx Expiration * * Whenever the retransmission timer T3-rtx expires for a destination * address, do the following: * [See below] * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_do_6_3_3_rtx(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_transport *transport = arg; SCTP_INC_STATS(net, SCTP_MIB_T3_RTX_EXPIREDS); if (asoc->overall_error_count >= asoc->max_retrans) { if (asoc->peer.zero_window_announced && asoc->state == SCTP_STATE_SHUTDOWN_PENDING) { /* * We are here likely because the receiver had its rwnd * closed for a while and we have not been able to * transmit the locally queued data within the maximum * retransmission attempts limit. Start the T5 * shutdown guard timer to give the receiver one last * chance and some additional time to recover before * aborting. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START_ONCE, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); } else { sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_NO_ERROR)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_DISPOSITION_DELETE_TCB; } } /* E1) For the destination address for which the timer * expires, adjust its ssthresh with rules defined in Section * 7.2.3 and set the cwnd <- MTU. */ /* E2) For the destination address for which the timer * expires, set RTO <- RTO * 2 ("back off the timer"). The * maximum value discussed in rule C7 above (RTO.max) may be * used to provide an upper bound to this doubling operation. */ /* E3) Determine how many of the earliest (i.e., lowest TSN) * outstanding DATA chunks for the address for which the * T3-rtx has expired will fit into a single packet, subject * to the MTU constraint for the path corresponding to the * destination transport address to which the retransmission * is being sent (this may be different from the address for * which the timer expires [see Section 6.4]). Call this * value K. Bundle and retransmit those K DATA chunks in a * single packet to the destination endpoint. * * Note: Any DATA chunks that were sent to the address for * which the T3-rtx timer expired but did not fit in one MTU * (rule E3 above), should be marked for retransmission and * sent as soon as cwnd allows (normally when a SACK arrives). */ /* Do some failure management (Section 8.2). */ sctp_add_cmd_sf(commands, SCTP_CMD_STRIKE, SCTP_TRANSPORT(transport)); /* NB: Rules E4 and F1 are implicit in R1. */ sctp_add_cmd_sf(commands, SCTP_CMD_RETRAN, SCTP_TRANSPORT(transport)); return SCTP_DISPOSITION_CONSUME; } /* * Generate delayed SACK on timeout * * Section: 6.2 Acknowledgement on Reception of DATA Chunks * * The guidelines on delayed acknowledgement algorithm specified in * Section 4.2 of [RFC2581] SHOULD be followed. Specifically, an * acknowledgement SHOULD be generated for at least every second packet * (not every second DATA chunk) received, and SHOULD be generated * within 200 ms of the arrival of any unacknowledged DATA chunk. In * some situations it may be beneficial for an SCTP transmitter to be * more conservative than the algorithms detailed in this document * allow. However, an SCTP transmitter MUST NOT be more aggressive than * the following algorithms allow. */ enum sctp_disposition sctp_sf_do_6_2_sack(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { SCTP_INC_STATS(net, SCTP_MIB_DELAY_SACK_EXPIREDS); sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_FORCE()); return SCTP_DISPOSITION_CONSUME; } /* * sctp_sf_t1_init_timer_expire * * Section: 4 Note: 2 * Verification Tag: * Inputs * (endpoint, asoc) * * RFC 2960 Section 4 Notes * 2) If the T1-init timer expires, the endpoint MUST retransmit INIT * and re-start the T1-init timer without changing state. This MUST * be repeated up to 'Max.Init.Retransmits' times. After that, the * endpoint MUST abort the initialization process and report the * error to SCTP user. * * Outputs * (timers, events) * */ enum sctp_disposition sctp_sf_t1_init_timer_expire( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { int attempts = asoc->init_err_counter + 1; struct sctp_chunk *repl = NULL; struct sctp_bind_addr *bp; pr_debug("%s: timer T1 expired (INIT)\n", __func__); SCTP_INC_STATS(net, SCTP_MIB_T1_INIT_EXPIREDS); if (attempts <= asoc->max_init_attempts) { bp = (struct sctp_bind_addr *) &asoc->base.bind_addr; repl = sctp_make_init(asoc, bp, GFP_ATOMIC, 0); if (!repl) return SCTP_DISPOSITION_NOMEM; /* Choose transport for INIT. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_CHOOSE_TRANSPORT, SCTP_CHUNK(repl)); /* Issue a sideeffect to do the needed accounting. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); } else { pr_debug("%s: giving up on INIT, attempts:%d " "max_init_attempts:%d\n", __func__, attempts, asoc->max_init_attempts); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, SCTP_PERR(SCTP_ERROR_NO_ERROR)); return SCTP_DISPOSITION_DELETE_TCB; } return SCTP_DISPOSITION_CONSUME; } /* * sctp_sf_t1_cookie_timer_expire * * Section: 4 Note: 2 * Verification Tag: * Inputs * (endpoint, asoc) * * RFC 2960 Section 4 Notes * 3) If the T1-cookie timer expires, the endpoint MUST retransmit * COOKIE ECHO and re-start the T1-cookie timer without changing * state. This MUST be repeated up to 'Max.Init.Retransmits' times. * After that, the endpoint MUST abort the initialization process and * report the error to SCTP user. * * Outputs * (timers, events) * */ enum sctp_disposition sctp_sf_t1_cookie_timer_expire( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { int attempts = asoc->init_err_counter + 1; struct sctp_chunk *repl = NULL; pr_debug("%s: timer T1 expired (COOKIE-ECHO)\n", __func__); SCTP_INC_STATS(net, SCTP_MIB_T1_COOKIE_EXPIREDS); if (attempts <= asoc->max_init_attempts) { repl = sctp_make_cookie_echo(asoc, NULL); if (!repl) return SCTP_DISPOSITION_NOMEM; sctp_add_cmd_sf(commands, SCTP_CMD_INIT_CHOOSE_TRANSPORT, SCTP_CHUNK(repl)); /* Issue a sideeffect to do the needed accounting. */ sctp_add_cmd_sf(commands, SCTP_CMD_COOKIEECHO_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_COOKIE)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); } else { sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, SCTP_PERR(SCTP_ERROR_NO_ERROR)); return SCTP_DISPOSITION_DELETE_TCB; } return SCTP_DISPOSITION_CONSUME; } /* RFC2960 9.2 If the timer expires, the endpoint must re-send the SHUTDOWN * with the updated last sequential TSN received from its peer. * * An endpoint should limit the number of retransmission of the * SHUTDOWN chunk to the protocol parameter 'Association.Max.Retrans'. * If this threshold is exceeded the endpoint should destroy the TCB and * MUST report the peer endpoint unreachable to the upper layer (and * thus the association enters the CLOSED state). The reception of any * packet from its peer (i.e. as the peer sends all of its queued DATA * chunks) should clear the endpoint's retransmission count and restart * the T2-Shutdown timer, giving its peer ample opportunity to transmit * all of its queued DATA chunks that have not yet been sent. */ enum sctp_disposition sctp_sf_t2_timer_expire( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *reply = NULL; pr_debug("%s: timer T2 expired\n", __func__); SCTP_INC_STATS(net, SCTP_MIB_T2_SHUTDOWN_EXPIREDS); ((struct sctp_association *)asoc)->shutdown_retries++; if (asoc->overall_error_count >= asoc->max_retrans) { sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); /* Note: CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_NO_ERROR)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_DISPOSITION_DELETE_TCB; } switch (asoc->state) { case SCTP_STATE_SHUTDOWN_SENT: reply = sctp_make_shutdown(asoc, NULL); break; case SCTP_STATE_SHUTDOWN_ACK_SENT: reply = sctp_make_shutdown_ack(asoc, NULL); break; default: BUG(); break; } if (!reply) goto nomem; /* Do some failure management (Section 8.2). * If we remove the transport an SHUTDOWN was last sent to, don't * do failure management. */ if (asoc->shutdown_last_sent_to) sctp_add_cmd_sf(commands, SCTP_CMD_STRIKE, SCTP_TRANSPORT(asoc->shutdown_last_sent_to)); /* Set the transport for the SHUTDOWN/ACK chunk and the timeout for * the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_SETUP_T2, SCTP_CHUNK(reply)); /* Restart the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); return SCTP_DISPOSITION_CONSUME; nomem: return SCTP_DISPOSITION_NOMEM; } /* * ADDIP Section 4.1 ASCONF Chunk Procedures * If the T4 RTO timer expires the endpoint should do B1 to B5 */ enum sctp_disposition sctp_sf_t4_timer_expire( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = asoc->addip_last_asconf; struct sctp_transport *transport = chunk->transport; SCTP_INC_STATS(net, SCTP_MIB_T4_RTO_EXPIREDS); /* ADDIP 4.1 B1) Increment the error counters and perform path failure * detection on the appropriate destination address as defined in * RFC2960 [5] section 8.1 and 8.2. */ if (transport) sctp_add_cmd_sf(commands, SCTP_CMD_STRIKE, SCTP_TRANSPORT(transport)); /* Reconfig T4 timer and transport. */ sctp_add_cmd_sf(commands, SCTP_CMD_SETUP_T4, SCTP_CHUNK(chunk)); /* ADDIP 4.1 B2) Increment the association error counters and perform * endpoint failure detection on the association as defined in * RFC2960 [5] section 8.1 and 8.2. * association error counter is incremented in SCTP_CMD_STRIKE. */ if (asoc->overall_error_count >= asoc->max_retrans) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_NO_ERROR)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_DISPOSITION_ABORT; } /* ADDIP 4.1 B3) Back-off the destination address RTO value to which * the ASCONF chunk was sent by doubling the RTO timer value. * This is done in SCTP_CMD_STRIKE. */ /* ADDIP 4.1 B4) Re-transmit the ASCONF Chunk last sent and if possible * choose an alternate destination address (please refer to RFC2960 * [5] section 6.4.1). An endpoint MUST NOT add new parameters to this * chunk, it MUST be the same (including its serial number) as the last * ASCONF sent. */ sctp_chunk_hold(asoc->addip_last_asconf); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(asoc->addip_last_asconf)); /* ADDIP 4.1 B5) Restart the T-4 RTO timer. Note that if a different * destination is selected, then the RTO used will be that of the new * destination address. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); return SCTP_DISPOSITION_CONSUME; } /* sctpimpguide-05 Section 2.12.2 * The sender of the SHUTDOWN MAY also start an overall guard timer * 'T5-shutdown-guard' to bound the overall time for shutdown sequence. * At the expiration of this timer the sender SHOULD abort the association * by sending an ABORT chunk. */ enum sctp_disposition sctp_sf_t5_timer_expire( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *reply = NULL; pr_debug("%s: timer T5 expired\n", __func__); SCTP_INC_STATS(net, SCTP_MIB_T5_SHUTDOWN_GUARD_EXPIREDS); reply = sctp_make_abort(asoc, NULL, 0); if (!reply) goto nomem; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_NO_ERROR)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_DISPOSITION_DELETE_TCB; nomem: return SCTP_DISPOSITION_NOMEM; } /* Handle expiration of AUTOCLOSE timer. When the autoclose timer expires, * the association is automatically closed by starting the shutdown process. * The work that needs to be done is same as when SHUTDOWN is initiated by * the user. So this routine looks same as sctp_sf_do_9_2_prm_shutdown(). */ enum sctp_disposition sctp_sf_autoclose_timer_expire( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { enum sctp_disposition disposition; SCTP_INC_STATS(net, SCTP_MIB_AUTOCLOSE_EXPIREDS); /* From 9.2 Shutdown of an Association * Upon receipt of the SHUTDOWN primitive from its upper * layer, the endpoint enters SHUTDOWN-PENDING state and * remains there until all outstanding data has been * acknowledged by its peer. The endpoint accepts no new data * from its upper layer, but retransmits data to the far end * if necessary to fill gaps. */ sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_SHUTDOWN_PENDING)); disposition = SCTP_DISPOSITION_CONSUME; if (sctp_outq_is_empty(&asoc->outqueue)) { disposition = sctp_sf_do_9_2_start_shutdown(net, ep, asoc, type, NULL, commands); } return disposition; } /***************************************************************************** * These are sa state functions which could apply to all types of events. ****************************************************************************/ /* * This table entry is not implemented. * * Inputs * (endpoint, asoc, chunk) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_not_impl(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { return SCTP_DISPOSITION_NOT_IMPL; } /* * This table entry represents a bug. * * Inputs * (endpoint, asoc, chunk) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_bug(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { return SCTP_DISPOSITION_BUG; } /* * This table entry represents the firing of a timer in the wrong state. * Since timer deletion cannot be guaranteed a timer 'may' end up firing * when the association is in the wrong state. This event should * be ignored, so as to prevent any rearming of the timer. * * Inputs * (endpoint, asoc, chunk) * * The return value is the disposition of the chunk. */ enum sctp_disposition sctp_sf_timer_ignore(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands) { pr_debug("%s: timer %d ignored\n", __func__, type.chunk); return SCTP_DISPOSITION_CONSUME; } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ /* Pull the SACK chunk based on the SACK header. */ static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk) { struct sctp_sackhdr *sack; __u16 num_dup_tsns; unsigned int len; __u16 num_blocks; /* Protect ourselves from reading too far into * the skb from a bogus sender. */ sack = (struct sctp_sackhdr *) chunk->skb->data; num_blocks = ntohs(sack->num_gap_ack_blocks); num_dup_tsns = ntohs(sack->num_dup_tsns); len = sizeof(struct sctp_sackhdr); len += (num_blocks + num_dup_tsns) * sizeof(__u32); if (len > chunk->skb->len) return NULL; skb_pull(chunk->skb, len); return sack; } /* Create an ABORT packet to be sent as a response, with the specified * error causes. */ static struct sctp_packet *sctp_abort_pkt_new( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, const void *payload, size_t paylen) { struct sctp_packet *packet; struct sctp_chunk *abort; packet = sctp_ootb_pkt_new(net, asoc, chunk); if (packet) { /* Make an ABORT. * The T bit will be set if the asoc is NULL. */ abort = sctp_make_abort(asoc, chunk, paylen); if (!abort) { sctp_ootb_pkt_free(packet); return NULL; } /* Reflect vtag if T-Bit is set */ if (sctp_test_T_bit(abort)) packet->vtag = ntohl(chunk->sctp_hdr->vtag); /* Add specified error causes, i.e., payload, to the * end of the chunk. */ sctp_addto_chunk(abort, paylen, payload); /* Set the skb to the belonging sock for accounting. */ abort->skb->sk = ep->base.sk; sctp_packet_append_chunk(packet, abort); } return packet; } /* Allocate a packet for responding in the OOTB conditions. */ static struct sctp_packet *sctp_ootb_pkt_new( struct net *net, const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_transport *transport; struct sctp_packet *packet; __u16 sport, dport; __u32 vtag; /* Get the source and destination port from the inbound packet. */ sport = ntohs(chunk->sctp_hdr->dest); dport = ntohs(chunk->sctp_hdr->source); /* The V-tag is going to be the same as the inbound packet if no * association exists, otherwise, use the peer's vtag. */ if (asoc) { /* Special case the INIT-ACK as there is no peer's vtag * yet. */ switch (chunk->chunk_hdr->type) { case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: { struct sctp_initack_chunk *initack; initack = (struct sctp_initack_chunk *)chunk->chunk_hdr; vtag = ntohl(initack->init_hdr.init_tag); break; } default: vtag = asoc->peer.i.init_tag; break; } } else { /* Special case the INIT and stale COOKIE_ECHO as there is no * vtag yet. */ switch (chunk->chunk_hdr->type) { case SCTP_CID_INIT: { struct sctp_init_chunk *init; init = (struct sctp_init_chunk *)chunk->chunk_hdr; vtag = ntohl(init->init_hdr.init_tag); break; } default: vtag = ntohl(chunk->sctp_hdr->vtag); break; } } /* Make a transport for the bucket, Eliza... */ transport = sctp_transport_new(net, sctp_source(chunk), GFP_ATOMIC); if (!transport) goto nomem; transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; /* Cache a route for the transport with the chunk's destination as * the source address. */ sctp_transport_route(transport, (union sctp_addr *)&chunk->dest, sctp_sk(net->sctp.ctl_sock)); packet = &transport->packet; sctp_packet_init(packet, transport, sport, dport); sctp_packet_config(packet, vtag, 0); return packet; nomem: return NULL; } /* Free the packet allocated earlier for responding in the OOTB condition. */ void sctp_ootb_pkt_free(struct sctp_packet *packet) { sctp_transport_free(packet->transport); } /* Send a stale cookie error when a invalid COOKIE ECHO chunk is found */ static void sctp_send_stale_cookie_err(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const struct sctp_chunk *chunk, struct sctp_cmd_seq *commands, struct sctp_chunk *err_chunk) { struct sctp_packet *packet; if (err_chunk) { packet = sctp_ootb_pkt_new(net, asoc, chunk); if (packet) { struct sctp_signed_cookie *cookie; /* Override the OOTB vtag from the cookie. */ cookie = chunk->subh.cookie_hdr; packet->vtag = cookie->c.peer_vtag; /* Set the skb to the belonging sock for accounting. */ err_chunk->skb->sk = ep->base.sk; sctp_packet_append_chunk(packet, err_chunk); sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet)); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); } else sctp_chunk_free (err_chunk); } } /* Process a data chunk */ static int sctp_eat_data(const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_cmd_seq *commands) { struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); struct sctp_datahdr *data_hdr; struct sctp_chunk *err; enum sctp_verb deliver; size_t datalen; __u32 tsn; int tmp; data_hdr = (struct sctp_datahdr *)chunk->skb->data; chunk->subh.data_hdr = data_hdr; skb_pull(chunk->skb, sctp_datahdr_len(&asoc->stream)); tsn = ntohl(data_hdr->tsn); pr_debug("%s: TSN 0x%x\n", __func__, tsn); /* ASSERT: Now skb->data is really the user data. */ /* Process ECN based congestion. * * Since the chunk structure is reused for all chunks within * a packet, we use ecn_ce_done to track if we've already * done CE processing for this packet. * * We need to do ECN processing even if we plan to discard the * chunk later. */ if (asoc->peer.ecn_capable && !chunk->ecn_ce_done) { struct sctp_af *af = SCTP_INPUT_CB(chunk->skb)->af; chunk->ecn_ce_done = 1; if (af->is_ce(sctp_gso_headskb(chunk->skb))) { /* Do real work as side effect. */ sctp_add_cmd_sf(commands, SCTP_CMD_ECN_CE, SCTP_U32(tsn)); } } tmp = sctp_tsnmap_check(&asoc->peer.tsn_map, tsn); if (tmp < 0) { /* The TSN is too high--silently discard the chunk and * count on it getting retransmitted later. */ if (chunk->asoc) chunk->asoc->stats.outofseqtsns++; return SCTP_IERROR_HIGH_TSN; } else if (tmp > 0) { /* This is a duplicate. Record it. */ sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_DUP, SCTP_U32(tsn)); return SCTP_IERROR_DUP_TSN; } /* This is a new TSN. */ /* Discard if there is no room in the receive window. * Actually, allow a little bit of overflow (up to a MTU). */ datalen = ntohs(chunk->chunk_hdr->length); datalen -= sctp_datachk_len(&asoc->stream); deliver = SCTP_CMD_CHUNK_ULP; /* Think about partial delivery. */ if ((datalen >= asoc->rwnd) && (!asoc->ulpq.pd_mode)) { /* Even if we don't accept this chunk there is * memory pressure. */ sctp_add_cmd_sf(commands, SCTP_CMD_PART_DELIVER, SCTP_NULL()); } /* Spill over rwnd a little bit. Note: While allowed, this spill over * seems a bit troublesome in that frag_point varies based on * PMTU. In cases, such as loopback, this might be a rather * large spill over. */ if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over || (datalen > asoc->rwnd + asoc->frag_point))) { /* If this is the next TSN, consider reneging to make * room. Note: Playing nice with a confused sender. A * malicious sender can still eat up all our buffer * space and in the future we may want to detect and * do more drastic reneging. */ if (sctp_tsnmap_has_gap(map) && (sctp_tsnmap_get_ctsn(map) + 1) == tsn) { pr_debug("%s: reneging for tsn:%u\n", __func__, tsn); deliver = SCTP_CMD_RENEGE; } else { pr_debug("%s: discard tsn:%u len:%zu, rwnd:%d\n", __func__, tsn, datalen, asoc->rwnd); return SCTP_IERROR_IGNORE_TSN; } } /* * Also try to renege to limit our memory usage in the event that * we are under memory pressure * If we can't renege, don't worry about it, the sk_rmem_schedule * in sctp_ulpevent_make_rcvmsg will drop the frame if we grow our * memory usage too much */ if (sk_under_memory_pressure(sk)) { if (sctp_tsnmap_has_gap(map) && (sctp_tsnmap_get_ctsn(map) + 1) == tsn) { pr_debug("%s: under pressure, reneging for tsn:%u\n", __func__, tsn); deliver = SCTP_CMD_RENEGE; } } /* * Section 3.3.10.9 No User Data (9) * * Cause of error * --------------- * No User Data: This error cause is returned to the originator of a * DATA chunk if a received DATA chunk has no user data. */ if (unlikely(0 == datalen)) { err = sctp_make_abort_no_data(asoc, chunk, tsn); if (err) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err)); } /* We are going to ABORT, so we might as well stop * processing the rest of the chunks in the packet. */ sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_PERR(SCTP_ERROR_NO_DATA)); SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); return SCTP_IERROR_NO_DATA; } chunk->data_accepted = 1; /* Note: Some chunks may get overcounted (if we drop) or overcounted * if we renege and the chunk arrives again. */ if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) { SCTP_INC_STATS(net, SCTP_MIB_INUNORDERCHUNKS); if (chunk->asoc) chunk->asoc->stats.iuodchunks++; } else { SCTP_INC_STATS(net, SCTP_MIB_INORDERCHUNKS); if (chunk->asoc) chunk->asoc->stats.iodchunks++; } /* RFC 2960 6.5 Stream Identifier and Stream Sequence Number * * If an endpoint receive a DATA chunk with an invalid stream * identifier, it shall acknowledge the reception of the DATA chunk * following the normal procedure, immediately send an ERROR chunk * with cause set to "Invalid Stream Identifier" (See Section 3.3.10) * and discard the DATA chunk. */ if (ntohs(data_hdr->stream) >= asoc->stream.incnt) { /* Mark tsn as received even though we drop it */ sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn)); err = sctp_make_op_error(asoc, chunk, SCTP_ERROR_INV_STRM, &data_hdr->stream, sizeof(data_hdr->stream), sizeof(u16)); if (err) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err)); return SCTP_IERROR_BAD_STREAM; } /* Check to see if the SSN is possible for this TSN. * The biggest gap we can record is 4K wide. Since SSNs wrap * at an unsigned short, there is no way that an SSN can * wrap and for a valid TSN. We can simply check if the current * SSN is smaller then the next expected one. If it is, it wrapped * and is invalid. */ if (!asoc->stream.si->validate_data(chunk)) return SCTP_IERROR_PROTO_VIOLATION; /* Send the data up to the user. Note: Schedule the * SCTP_CMD_CHUNK_ULP cmd before the SCTP_CMD_GEN_SACK, as the SACK * chunk needs the updated rwnd. */ sctp_add_cmd_sf(commands, deliver, SCTP_CHUNK(chunk)); return SCTP_IERROR_NO_ERROR; } |
| 2 6 4 5 9 68 68 8 8 1 14 7 4 4 4 4 4 4 4 2 4 4 2 1 3 3 4 38 38 37 38 3 35 1 1 34 34 34 35 35 35 3 3 1 1 1 1 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 9 9 5 5 1 9 15 15 1 15 3 16 16 5 16 3 2 14 4 3 13 4 14 2 16 4 4 4 1 3 1 2 2 4 19 20 20 20 3 2 2 3 1 1 1 7 5 5 6 6 4 6 6 6 5 9 2 2 2 2 2 2 3 1 3 3 2 2 2 2 4 5 5 5 3 3 3 3 3 3 3 2 2 2 2 5 5 32 32 32 27 27 27 69 70 69 1 56 1 57 1 20 20 20 20 5 15 10 74 1 74 1 74 35 35 35 35 34 35 35 35 35 35 35 35 35 35 35 35 34 35 20 20 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mac80211 configuration hooks for cfg80211 * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH * Copyright (C) 2018-2022 Intel Corporation */ #include <linux/ieee80211.h> #include <linux/nl80211.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <linux/rcupdate.h> #include <linux/fips.h> #include <linux/if_ether.h> #include <net/cfg80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" #include "mesh.h" #include "wme.h" static struct ieee80211_link_data * ieee80211_link_or_deflink(struct ieee80211_sub_if_data *sdata, int link_id, bool require_valid) { struct ieee80211_link_data *link; if (link_id < 0) { /* * For keys, if sdata is not an MLD, we might not use * the return value at all (if it's not a pairwise key), * so in that case (require_valid==false) don't error. */ if (require_valid && ieee80211_vif_is_mld(&sdata->vif)) return ERR_PTR(-EINVAL); return &sdata->deflink; } link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return ERR_PTR(-ENOLINK); return link; } static void ieee80211_set_mu_mimo_follow(struct ieee80211_sub_if_data *sdata, struct vif_params *params) { bool mu_mimo_groups = false; bool mu_mimo_follow = false; if (params->vht_mumimo_groups) { u64 membership; BUILD_BUG_ON(sizeof(membership) != WLAN_MEMBERSHIP_LEN); memcpy(sdata->vif.bss_conf.mu_group.membership, params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN); memcpy(sdata->vif.bss_conf.mu_group.position, params->vht_mumimo_groups + WLAN_MEMBERSHIP_LEN, WLAN_USER_POSITION_LEN); ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_MU_GROUPS); /* don't care about endianness - just check for 0 */ memcpy(&membership, params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN); mu_mimo_groups = membership != 0; } if (params->vht_mumimo_follow_addr) { mu_mimo_follow = is_valid_ether_addr(params->vht_mumimo_follow_addr); ether_addr_copy(sdata->u.mntr.mu_follow_addr, params->vht_mumimo_follow_addr); } sdata->vif.bss_conf.mu_mimo_owner = mu_mimo_groups || mu_mimo_follow; } static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, struct vif_params *params) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *monitor_sdata; /* check flags first */ if (params->flags && ieee80211_sdata_running(sdata)) { u32 mask = MONITOR_FLAG_COOK_FRAMES | MONITOR_FLAG_ACTIVE; /* * Prohibit MONITOR_FLAG_COOK_FRAMES and * MONITOR_FLAG_ACTIVE to be changed while the * interface is up. * Else we would need to add a lot of cruft * to update everything: * cooked_mntrs, monitor and all fif_* counters * reconfigure hardware */ if ((params->flags & mask) != (sdata->u.mntr.flags & mask)) return -EBUSY; } /* also validate MU-MIMO change */ monitor_sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!monitor_sdata && (params->vht_mumimo_groups || params->vht_mumimo_follow_addr)) return -EOPNOTSUPP; /* apply all changes now - no failures allowed */ if (monitor_sdata) ieee80211_set_mu_mimo_follow(monitor_sdata, params); if (params->flags) { if (ieee80211_sdata_running(sdata)) { ieee80211_adjust_monitor_flags(sdata, -1); sdata->u.mntr.flags = params->flags; ieee80211_adjust_monitor_flags(sdata, 1); ieee80211_configure_filter(local); } else { /* * Because the interface is down, ieee80211_do_stop * and ieee80211_do_open take care of "everything" * mentioned in the comment above. */ sdata->u.mntr.flags = params->flags; } } return 0; } static int ieee80211_set_ap_mbssid_options(struct ieee80211_sub_if_data *sdata, struct cfg80211_mbssid_config params, struct ieee80211_bss_conf *link_conf) { struct ieee80211_sub_if_data *tx_sdata; sdata->vif.mbssid_tx_vif = NULL; link_conf->bssid_index = 0; link_conf->nontransmitted = false; link_conf->ema_ap = false; link_conf->bssid_indicator = 0; if (sdata->vif.type != NL80211_IFTYPE_AP || !params.tx_wdev) return -EINVAL; tx_sdata = IEEE80211_WDEV_TO_SUB_IF(params.tx_wdev); if (!tx_sdata) return -EINVAL; if (tx_sdata == sdata) { sdata->vif.mbssid_tx_vif = &sdata->vif; } else { sdata->vif.mbssid_tx_vif = &tx_sdata->vif; link_conf->nontransmitted = true; link_conf->bssid_index = params.index; } if (params.ema) link_conf->ema_ap = true; return 0; } static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy, const char *name, unsigned char name_assign_type, enum nl80211_iftype type, struct vif_params *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct wireless_dev *wdev; struct ieee80211_sub_if_data *sdata; int err; err = ieee80211_if_add(local, name, name_assign_type, &wdev, type, params); if (err) return ERR_PTR(err); sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (type == NL80211_IFTYPE_MONITOR) { err = ieee80211_set_mon_options(sdata, params); if (err) { ieee80211_if_remove(sdata); return NULL; } } return wdev; } static int ieee80211_del_iface(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_if_remove(IEEE80211_WDEV_TO_SUB_IF(wdev)); return 0; } static int ieee80211_change_iface(struct wiphy *wiphy, struct net_device *dev, enum nl80211_iftype type, struct vif_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret; lockdep_assert_wiphy(local->hw.wiphy); ret = ieee80211_if_change_type(sdata, type); if (ret) return ret; if (type == NL80211_IFTYPE_AP_VLAN && params->use_4addr == 0) { RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); ieee80211_check_fast_rx_iface(sdata); } else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; if (params->use_4addr == ifmgd->use_4addr) return 0; /* FIXME: no support for 4-addr MLO yet */ if (ieee80211_vif_is_mld(&sdata->vif)) return -EOPNOTSUPP; sdata->u.mgd.use_4addr = params->use_4addr; if (!ifmgd->associated) return 0; sta = sta_info_get(sdata, sdata->deflink.u.mgd.bssid); if (sta) drv_sta_set_4addr(local, sdata, &sta->sta, params->use_4addr); if (params->use_4addr) ieee80211_send_4addr_nullfunc(local, sdata); } if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { ret = ieee80211_set_mon_options(sdata, params); if (ret) return ret; } return 0; } static int ieee80211_start_p2p_device(struct wiphy *wiphy, struct wireless_dev *wdev) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; lockdep_assert_wiphy(sdata->local->hw.wiphy); ret = ieee80211_check_combinations(sdata, NULL, 0, 0); if (ret < 0) return ret; return ieee80211_do_open(wdev, true); } static void ieee80211_stop_p2p_device(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_sdata_stop(IEEE80211_WDEV_TO_SUB_IF(wdev)); } static int ieee80211_start_nan(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; lockdep_assert_wiphy(sdata->local->hw.wiphy); ret = ieee80211_check_combinations(sdata, NULL, 0, 0); if (ret < 0) return ret; ret = ieee80211_do_open(wdev, true); if (ret) return ret; ret = drv_start_nan(sdata->local, sdata, conf); if (ret) ieee80211_sdata_stop(sdata); sdata->u.nan.conf = *conf; return ret; } static void ieee80211_stop_nan(struct wiphy *wiphy, struct wireless_dev *wdev) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); drv_stop_nan(sdata->local, sdata); ieee80211_sdata_stop(sdata); } static int ieee80211_nan_change_conf(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf, u32 changes) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct cfg80211_nan_conf new_conf; int ret = 0; if (sdata->vif.type != NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; new_conf = sdata->u.nan.conf; if (changes & CFG80211_NAN_CONF_CHANGED_PREF) new_conf.master_pref = conf->master_pref; if (changes & CFG80211_NAN_CONF_CHANGED_BANDS) new_conf.bands = conf->bands; ret = drv_nan_change_conf(sdata->local, sdata, &new_conf, changes); if (!ret) sdata->u.nan.conf = new_conf; return ret; } static int ieee80211_add_nan_func(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_func *nan_func) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; if (sdata->vif.type != NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; spin_lock_bh(&sdata->u.nan.func_lock); ret = idr_alloc(&sdata->u.nan.function_inst_ids, nan_func, 1, sdata->local->hw.max_nan_de_entries + 1, GFP_ATOMIC); spin_unlock_bh(&sdata->u.nan.func_lock); if (ret < 0) return ret; nan_func->instance_id = ret; WARN_ON(nan_func->instance_id == 0); ret = drv_add_nan_func(sdata->local, sdata, nan_func); if (ret) { spin_lock_bh(&sdata->u.nan.func_lock); idr_remove(&sdata->u.nan.function_inst_ids, nan_func->instance_id); spin_unlock_bh(&sdata->u.nan.func_lock); } return ret; } static struct cfg80211_nan_func * ieee80211_find_nan_func_by_cookie(struct ieee80211_sub_if_data *sdata, u64 cookie) { struct cfg80211_nan_func *func; int id; lockdep_assert_held(&sdata->u.nan.func_lock); idr_for_each_entry(&sdata->u.nan.function_inst_ids, func, id) { if (func->cookie == cookie) return func; } return NULL; } static void ieee80211_del_nan_func(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct cfg80211_nan_func *func; u8 instance_id = 0; if (sdata->vif.type != NL80211_IFTYPE_NAN || !ieee80211_sdata_running(sdata)) return; spin_lock_bh(&sdata->u.nan.func_lock); func = ieee80211_find_nan_func_by_cookie(sdata, cookie); if (func) instance_id = func->instance_id; spin_unlock_bh(&sdata->u.nan.func_lock); if (instance_id) drv_del_nan_func(sdata->local, sdata, instance_id); } static int ieee80211_set_noack_map(struct wiphy *wiphy, struct net_device *dev, u16 noack_map) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); sdata->noack_map = noack_map; ieee80211_check_fast_xmit_iface(sdata); return 0; } static int ieee80211_set_tx(struct ieee80211_sub_if_data *sdata, const u8 *mac_addr, u8 key_idx) { struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; struct sta_info *sta; int ret = -EINVAL; if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_EXT_KEY_ID)) return -EINVAL; sta = sta_info_get_bss(sdata, mac_addr); if (!sta) return -EINVAL; if (sta->ptk_idx == key_idx) return 0; key = wiphy_dereference(local->hw.wiphy, sta->ptk[key_idx]); if (key && key->conf.flags & IEEE80211_KEY_FLAG_NO_AUTO_TX) ret = ieee80211_set_tx_key(key); return ret; } static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr, struct key_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, false); struct ieee80211_local *local = sdata->local; struct sta_info *sta = NULL; struct ieee80211_key *key; int err; lockdep_assert_wiphy(local->hw.wiphy); if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; if (IS_ERR(link)) return PTR_ERR(link); if (pairwise && params->mode == NL80211_KEY_SET_TX) return ieee80211_set_tx(sdata, mac_addr, key_idx); /* reject WEP and TKIP keys if WEP failed to initialize */ switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_WEP104: if (link_id >= 0) return -EINVAL; if (WARN_ON_ONCE(fips_enabled)) return -EINVAL; break; default: break; } key = ieee80211_key_alloc(params->cipher, key_idx, params->key_len, params->key, params->seq_len, params->seq); if (IS_ERR(key)) return PTR_ERR(key); key->conf.link_id = link_id; if (pairwise) key->conf.flags |= IEEE80211_KEY_FLAG_PAIRWISE; if (params->mode == NL80211_KEY_NO_TX) key->conf.flags |= IEEE80211_KEY_FLAG_NO_AUTO_TX; if (mac_addr) { sta = sta_info_get_bss(sdata, mac_addr); /* * The ASSOC test makes sure the driver is ready to * receive the key. When wpa_supplicant has roamed * using FT, it attempts to set the key before * association has completed, this rejects that attempt * so it will set the key again after association. * * TODO: accept the key if we have a station entry and * add it to the device after the station. */ if (!sta || !test_sta_flag(sta, WLAN_STA_ASSOC)) { ieee80211_key_free_unused(key); return -ENOENT; } } switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: if (sdata->u.mgd.mfp != IEEE80211_MFP_DISABLED) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* Keys without a station are used for TX only */ if (sta && test_sta_flag(sta, WLAN_STA_MFP)) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_ADHOC: /* no MFP (yet) */ break; case NL80211_IFTYPE_MESH_POINT: #ifdef CONFIG_MAC80211_MESH if (sdata->u.mesh.security != IEEE80211_MESH_SEC_NONE) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; #endif case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_OCB: /* shouldn't happen */ WARN_ON_ONCE(1); break; } err = ieee80211_key_link(key, link, sta); /* KRACK protection, shouldn't happen but just silently accept key */ if (err == -EALREADY) err = 0; return err; } static struct ieee80211_key * ieee80211_lookup_key(struct ieee80211_sub_if_data *sdata, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr) { struct ieee80211_local *local __maybe_unused = sdata->local; struct ieee80211_link_data *link = &sdata->deflink; struct ieee80211_key *key; if (link_id >= 0) { link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return NULL; } if (mac_addr) { struct sta_info *sta; struct link_sta_info *link_sta; sta = sta_info_get_bss(sdata, mac_addr); if (!sta) return NULL; if (link_id >= 0) { link_sta = rcu_dereference_check(sta->link[link_id], lockdep_is_held(&local->hw.wiphy->mtx)); if (!link_sta) return NULL; } else { link_sta = &sta->deflink; } if (pairwise && key_idx < NUM_DEFAULT_KEYS) return wiphy_dereference(local->hw.wiphy, sta->ptk[key_idx]); if (!pairwise && key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + NUM_DEFAULT_BEACON_KEYS) return wiphy_dereference(local->hw.wiphy, link_sta->gtk[key_idx]); return NULL; } if (pairwise && key_idx < NUM_DEFAULT_KEYS) return wiphy_dereference(local->hw.wiphy, sdata->keys[key_idx]); key = wiphy_dereference(local->hw.wiphy, link->gtk[key_idx]); if (key) return key; /* or maybe it was a WEP key */ if (key_idx < NUM_DEFAULT_KEYS) return wiphy_dereference(local->hw.wiphy, sdata->keys[key_idx]); return NULL; } static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; lockdep_assert_wiphy(local->hw.wiphy); key = ieee80211_lookup_key(sdata, link_id, key_idx, pairwise, mac_addr); if (!key) return -ENOENT; ieee80211_key_free(key, sdata->vif.type == NL80211_IFTYPE_STATION); return 0; } static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr, void *cookie, void (*callback)(void *cookie, struct key_params *params)) { struct ieee80211_sub_if_data *sdata; u8 seq[6] = {0}; struct key_params params; struct ieee80211_key *key; u64 pn64; u32 iv32; u16 iv16; int err = -ENOENT; struct ieee80211_key_seq kseq = {}; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); key = ieee80211_lookup_key(sdata, link_id, key_idx, pairwise, mac_addr); if (!key) goto out; memset(¶ms, 0, sizeof(params)); params.cipher = key->conf.cipher; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: pn64 = atomic64_read(&key->conf.tx_pn); iv32 = TKIP_PN_TO_IV32(pn64); iv16 = TKIP_PN_TO_IV16(pn64); if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { drv_get_key_seq(sdata->local, key, &kseq); iv32 = kseq.tkip.iv32; iv16 = kseq.tkip.iv16; } seq[0] = iv16 & 0xff; seq[1] = (iv16 >> 8) & 0xff; seq[2] = iv32 & 0xff; seq[3] = (iv32 >> 8) & 0xff; seq[4] = (iv32 >> 16) & 0xff; seq[5] = (iv32 >> 24) & 0xff; params.seq = seq; params.seq_len = 6; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), aes_cmac)); fallthrough; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), aes_gmac)); fallthrough; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), gcmp)); if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { drv_get_key_seq(sdata->local, key, &kseq); memcpy(seq, kseq.ccmp.pn, 6); } else { pn64 = atomic64_read(&key->conf.tx_pn); seq[0] = pn64; seq[1] = pn64 >> 8; seq[2] = pn64 >> 16; seq[3] = pn64 >> 24; seq[4] = pn64 >> 32; seq[5] = pn64 >> 40; } params.seq = seq; params.seq_len = 6; break; default: if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) break; if (WARN_ON(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) break; drv_get_key_seq(sdata->local, key, &kseq); params.seq = kseq.hw.seq; params.seq_len = kseq.hw.seq_len; break; } params.key = key->conf.key; params.key_len = key->conf.keylen; callback(cookie, ¶ms); err = 0; out: rcu_read_unlock(); return err; } static int ieee80211_config_default_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool uni, bool multi) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, false); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_key(link, key_idx, uni, multi); return 0; } static int ieee80211_config_default_mgmt_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, true); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_mgmt_key(link, key_idx); return 0; } static int ieee80211_config_default_beacon_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, true); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_beacon_key(link, key_idx); return |