| 953 951 952 953 1 1 947 953 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ /* * fsnotify inode mark locking/lifetime/and refcnting * * REFCNT: * The group->recnt and mark->refcnt tell how many "things" in the kernel * currently are referencing the objects. Both kind of objects typically will * live inside the kernel with a refcnt of 2, one for its creation and one for * the reference a group and a mark hold to each other. * If you are holding the appropriate locks, you can take a reference and the * object itself is guaranteed to survive until the reference is dropped. * * LOCKING: * There are 3 locks involved with fsnotify inode marks and they MUST be taken * in order as follows: * * group->mark_mutex * mark->lock * mark->connector->lock * * group->mark_mutex protects the marks_list anchored inside a given group and * each mark is hooked via the g_list. It also protects the groups private * data (i.e group limits). * mark->lock protects the marks attributes like its masks and flags. * Furthermore it protects the access to a reference of the group that the mark * is assigned to as well as the access to a reference of the inode/vfsmount * that is being watched by the mark. * * mark->connector->lock protects the list of marks anchored inside an * inode / vfsmount and each mark is hooked via the i_list. * * A list of notification marks relating to inode / mnt is contained in * fsnotify_mark_connector. That structure is alive as long as there are any * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets * detached from fsnotify_mark_connector when last reference to the mark is * dropped. Thus having mark reference is enough to protect mark->connector * pointer and to make sure fsnotify_mark_connector cannot disappear. Also * because we remove mark from g_list before dropping mark reference associated * with that, any mark found through g_list is guaranteed to have * mark->connector set until we drop group->mark_mutex. * * LIFETIME: * Inode marks survive between when they are added to an inode and when their * refcnt==0. Marks are also protected by fsnotify_mark_srcu. * * The inode mark can be cleared for a number of different reasons including: * - The inode is unlinked for the last time. (fsnotify_inode_remove) * - The inode is being evicted from cache. (fsnotify_inode_delete) * - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes) * - Something explicitly requests that it be removed. (fsnotify_destroy_mark) * - The fsnotify_group associated with the mark is going away and all such marks * need to be cleaned up. (fsnotify_clear_marks_by_group) * * This has the very interesting property of being able to run concurrently with * any (or all) other directions. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <linux/ratelimit.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" #define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */ struct srcu_struct fsnotify_mark_srcu; struct kmem_cache *fsnotify_mark_connector_cachep; static DEFINE_SPINLOCK(destroy_lock); static LIST_HEAD(destroy_list); static struct fsnotify_mark_connector *connector_destroy_list; static void fsnotify_mark_destroy_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn); static void fsnotify_connector_destroy_workfn(struct work_struct *work); static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn); void fsnotify_get_mark(struct fsnotify_mark *mark) { WARN_ON_ONCE(!refcount_read(&mark->refcnt)); refcount_inc(&mark->refcnt); } static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn) { if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) return &fsnotify_conn_inode(conn)->i_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) return &fsnotify_conn_sb(conn)->s_fsnotify_mask; return NULL; } __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) { if (WARN_ON(!fsnotify_valid_obj_type(conn->type))) return 0; return *fsnotify_conn_mask_p(conn); } static void fsnotify_get_inode_ref(struct inode *inode) { ihold(inode); atomic_long_inc(&inode->i_sb->s_fsnotify_connectors); } /* * Grab or drop inode reference for the connector if needed. * * When it's time to drop the reference, we only clear the HAS_IREF flag and * return the inode object. fsnotify_drop_object() will be resonsible for doing * iput() outside of spinlocks. This happens when last mark that wanted iref is * detached. */ static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, bool want_iref) { bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF; struct inode *inode = NULL; if (conn->type != FSNOTIFY_OBJ_TYPE_INODE || want_iref == has_iref) return NULL; if (want_iref) { /* Pin inode if any mark wants inode refcount held */ fsnotify_get_inode_ref(fsnotify_conn_inode(conn)); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF; } else { /* Unpin inode after detach of last mark that wanted iref */ inode = fsnotify_conn_inode(conn); conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF; } return inode; } static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { u32 new_mask = 0; bool want_iref = false; struct fsnotify_mark *mark; assert_spin_locked(&conn->lock); /* We can get detached connector here when inode is getting unlinked. */ if (!fsnotify_valid_obj_type(conn->type)) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) continue; new_mask |= fsnotify_calc_mask(mark); if (conn->type == FSNOTIFY_OBJ_TYPE_INODE && !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) want_iref = true; } *fsnotify_conn_mask_p(conn) = new_mask; return fsnotify_update_iref(conn, want_iref); } static bool fsnotify_conn_watches_children( struct fsnotify_mark_connector *conn) { if (conn->type != FSNOTIFY_OBJ_TYPE_INODE) return false; return fsnotify_inode_watches_children(fsnotify_conn_inode(conn)); } static void fsnotify_conn_set_children_dentry_flags( struct fsnotify_mark_connector *conn) { if (conn->type != FSNOTIFY_OBJ_TYPE_INODE) return; fsnotify_set_children_dentry_flags(fsnotify_conn_inode(conn)); } /* * Calculate mask of events for a list of marks. The caller must make sure * connector and connector->obj cannot disappear under us. Callers achieve * this by holding a mark->lock or mark->group->mark_mutex for a mark on this * list. */ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { bool update_children; if (!conn) return; spin_lock(&conn->lock); update_children = !fsnotify_conn_watches_children(conn); __fsnotify_recalc_mask(conn); update_children &= fsnotify_conn_watches_children(conn); spin_unlock(&conn->lock); /* * Set children's PARENT_WATCHED flags only if parent started watching. * When parent stops watching, we clear false positive PARENT_WATCHED * flags lazily in __fsnotify_parent(). */ if (update_children) fsnotify_conn_set_children_dentry_flags(conn); } /* Free all connectors queued for freeing once SRCU period ends */ static void fsnotify_connector_destroy_workfn(struct work_struct *work) { struct fsnotify_mark_connector *conn, *free; spin_lock(&destroy_lock); conn = connector_destroy_list; connector_destroy_list = NULL; spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); while (conn) { free = conn; conn = conn->destroy_next; kmem_cache_free(fsnotify_mark_connector_cachep, free); } } static void fsnotify_put_inode_ref(struct inode *inode) { struct super_block *sb = inode->i_sb; iput(inode); if (atomic_long_dec_and_test(&sb->s_fsnotify_connectors)) wake_up_var(&sb->s_fsnotify_connectors); } static void fsnotify_get_sb_connectors(struct fsnotify_mark_connector *conn) { struct super_block *sb = fsnotify_connector_sb(conn); if (sb) atomic_long_inc(&sb->s_fsnotify_connectors); } static void fsnotify_put_sb_connectors(struct fsnotify_mark_connector *conn) { struct super_block *sb = fsnotify_connector_sb(conn); if (sb && atomic_long_dec_and_test(&sb->s_fsnotify_connectors)) wake_up_var(&sb->s_fsnotify_connectors); } static void *fsnotify_detach_connector_from_object( struct fsnotify_mark_connector *conn, unsigned int *type) { struct inode *inode = NULL; *type = conn->type; if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) return NULL; if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) { inode = fsnotify_conn_inode(conn); inode->i_fsnotify_mask = 0; /* Unpin inode when detaching from connector */ if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF)) inode = NULL; } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { fsnotify_conn_sb(conn)->s_fsnotify_mask = 0; } fsnotify_put_sb_connectors(conn); rcu_assign_pointer(*(conn->obj), NULL); conn->obj = NULL; conn->type = FSNOTIFY_OBJ_TYPE_DETACHED; return inode; } static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; if (WARN_ON_ONCE(!group)) return; group->ops->free_mark(mark); fsnotify_put_group(group); } /* Drop object reference originally held by a connector */ static void fsnotify_drop_object(unsigned int type, void *objp) { if (!objp) return; /* Currently only inode references are passed to be dropped */ if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE)) return; fsnotify_put_inode_ref(objp); } void fsnotify_put_mark(struct fsnotify_mark *mark) { struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector); void *objp = NULL; unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ if (!conn) { if (refcount_dec_and_test(&mark->refcnt)) fsnotify_final_mark_destroy(mark); return; } /* * We have to be careful so that traversals of obj_list under lock can * safely grab mark reference. */ if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock)) return; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { objp = fsnotify_detach_connector_from_object(conn, &type); free_conn = true; } else { objp = __fsnotify_recalc_mask(conn); type = conn->type; } WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); fsnotify_drop_object(type, objp); if (free_conn) { spin_lock(&destroy_lock); conn->destroy_next = connector_destroy_list; connector_destroy_list = conn; spin_unlock(&destroy_lock); queue_work(system_unbound_wq, &connector_reaper_work); } /* * Note that we didn't update flags telling whether inode cares about * what's happening with children. We update these flags from * __fsnotify_parent() lazily when next event happens on one of our * children. */ spin_lock(&destroy_lock); list_add(&mark->g_list, &destroy_list); spin_unlock(&destroy_lock); queue_delayed_work(system_unbound_wq, &reaper_work, FSNOTIFY_REAPER_DELAY); } EXPORT_SYMBOL_GPL(fsnotify_put_mark); /* * Get mark reference when we found the mark via lockless traversal of object * list. Mark can be already removed from the list by now and on its way to be * destroyed once SRCU period ends. * * Also pin the group so it doesn't disappear under us. */ static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark) { if (!mark) return true; if (refcount_inc_not_zero(&mark->refcnt)) { spin_lock(&mark->lock); if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) { /* mark is attached, group is still alive then */ atomic_inc(&mark->group->user_waits); spin_unlock(&mark->lock); return true; } spin_unlock(&mark->lock); fsnotify_put_mark(mark); } return false; } /* * Puts marks and wakes up group destruction if necessary. * * Pairs with fsnotify_get_mark_safe() */ static void fsnotify_put_mark_wake(struct fsnotify_mark *mark) { if (mark) { struct fsnotify_group *group = mark->group; fsnotify_put_mark(mark); /* * We abuse notification_waitq on group shutdown for waiting for * all marks pinned when waiting for userspace. */ if (atomic_dec_and_test(&group->user_waits) && group->shutdown) wake_up(&group->notification_waitq); } } bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) __releases(&fsnotify_mark_srcu) { int type; fsnotify_foreach_iter_type(type) { /* This can fail if mark is being removed */ if (!fsnotify_get_mark_safe(iter_info->marks[type])) { __release(&fsnotify_mark_srcu); goto fail; } } /* * Now that both marks are pinned by refcount in the inode / vfsmount * lists, we can drop SRCU lock, and safely resume the list iteration * once userspace returns. */ srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx); return true; fail: for (type--; type >= 0; type--) fsnotify_put_mark_wake(iter_info->marks[type]); return false; } void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) __acquires(&fsnotify_mark_srcu) { int type; iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); fsnotify_foreach_iter_type(type) fsnotify_put_mark_wake(iter_info->marks[type]); } /* * Mark mark as detached, remove it from group list. Mark still stays in object * list until its last reference is dropped. Note that we rely on mark being * removed from group list before corresponding reference to it is dropped. In * particular we rely on mark->connector being valid while we hold * group->mark_mutex if we found the mark through g_list. * * Must be called with group->mark_mutex held. The caller must either hold * reference to the mark or be protected by fsnotify_mark_srcu. */ void fsnotify_detach_mark(struct fsnotify_mark *mark) { fsnotify_group_assert_locked(mark->group); WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) && refcount_read(&mark->refcnt) < 1 + !!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)); spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED; list_del_init(&mark->g_list); spin_unlock(&mark->lock); /* Drop mark reference acquired in fsnotify_add_mark_locked() */ fsnotify_put_mark(mark); } /* * Free fsnotify mark. The mark is actually only marked as being freed. The * freeing is actually happening only once last reference to the mark is * dropped from a workqueue which first waits for srcu period end. * * Caller must have a reference to the mark or be protected by * fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); /* * Some groups like to know that marks are being freed. This is a * callback to the group function to let it know that this mark * is being freed. */ if (group->ops->freeing_mark) group->ops->freeing_mark(mark, group); } void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { fsnotify_group_lock(group); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); } EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); /* * Sorting function for lists of fsnotify marks. * * Fanotify supports different notification classes (reflected as priority of * notification group). Events shall be passed to notification groups in * decreasing priority order. To achieve this marks in notification lists for * inodes and vfsmounts are sorted so that priorities of corresponding groups * are descending. * * Furthermore correct handling of the ignore mask requires processing inode * and vfsmount marks of each group together. Using the group address as * further sort criterion provides a unique sorting order and thus we can * merge inode and vfsmount lists of marks in linear time and find groups * present in both lists. * * A return value of 1 signifies that b has priority over a. * A return value of 0 signifies that the two marks have to be handled together. * A return value of -1 signifies that a has priority over b. */ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) { if (a == b) return 0; if (!a) return 1; if (!b) return -1; if (a->priority < b->priority) return 1; if (a->priority > b->priority) return -1; if (a < b) return 1; return -1; } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, unsigned int obj_type, __kernel_fsid_t *fsid) { struct fsnotify_mark_connector *conn; conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL); if (!conn) return -ENOMEM; spin_lock_init(&conn->lock); INIT_HLIST_HEAD(&conn->list); conn->flags = 0; conn->type = obj_type; conn->obj = connp; /* Cache fsid of filesystem containing the object */ if (fsid) { conn->fsid = *fsid; conn->flags = FSNOTIFY_CONN_FLAG_HAS_FSID; } else { conn->fsid.val[0] = conn->fsid.val[1] = 0; conn->flags = 0; } fsnotify_get_sb_connectors(conn); /* * cmpxchg() provides the barrier so that readers of *connp can see * only initialized structure */ if (cmpxchg(connp, NULL, conn)) { /* Someone else created list structure for us */ fsnotify_put_sb_connectors(conn); kmem_cache_free(fsnotify_mark_connector_cachep, conn); } return 0; } /* * Get mark connector, make sure it is alive and return with its lock held. * This is for users that get connector pointer from inode or mount. Users that * hold reference to a mark on the list may directly lock connector->lock as * they are sure list cannot go away under them. */ static struct fsnotify_mark_connector *fsnotify_grab_connector( fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; int idx; idx = srcu_read_lock(&fsnotify_mark_srcu); conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (!conn) goto out; spin_lock(&conn->lock); if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) { spin_unlock(&conn->lock); srcu_read_unlock(&fsnotify_mark_srcu, idx); return NULL; } out: srcu_read_unlock(&fsnotify_mark_srcu, idx); return conn; } /* * Add mark into proper place in given list of marks. These marks may be used * for the fsnotify backend to determine which event types should be delivered * to which group and for which inodes. These marks are ordered according to * priority, highest number first, and then by the group's location in memory. */ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { struct fsnotify_mark *lmark, *last = NULL; struct fsnotify_mark_connector *conn; int cmp; int err = 0; if (WARN_ON(!fsnotify_valid_obj_type(obj_type))) return -EINVAL; /* Backend is expected to check for zero fsid (e.g. tmpfs) */ if (fsid && WARN_ON_ONCE(!fsid->val[0] && !fsid->val[1])) return -ENODEV; restart: spin_lock(&mark->lock); conn = fsnotify_grab_connector(connp); if (!conn) { spin_unlock(&mark->lock); err = fsnotify_attach_connector_to_object(connp, obj_type, fsid); if (err) return err; goto restart; } else if (fsid && !(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID)) { conn->fsid = *fsid; /* Pairs with smp_rmb() in fanotify_get_fsid() */ smp_wmb(); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_FSID; } else if (fsid && (conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID) && (fsid->val[0] != conn->fsid.val[0] || fsid->val[1] != conn->fsid.val[1])) { /* * Backend is expected to check for non uniform fsid * (e.g. btrfs), but maybe we missed something? * Only allow setting conn->fsid once to non zero fsid. * inotify and non-fid fanotify groups do not set nor test * conn->fsid. */ pr_warn_ratelimited("%s: fsid mismatch on object of type %u: " "%x.%x != %x.%x\n", __func__, conn->type, fsid->val[0], fsid->val[1], conn->fsid.val[0], conn->fsid.val[1]); err = -EXDEV; goto out_err; } /* is mark the first mark? */ if (hlist_empty(&conn->list)) { hlist_add_head_rcu(&mark->obj_list, &conn->list); goto added; } /* should mark be in the middle of the current list? */ hlist_for_each_entry(lmark, &conn->list, obj_list) { last = lmark; if ((lmark->group == mark->group) && (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) && !(mark->group->flags & FSNOTIFY_GROUP_DUPS)) { err = -EEXIST; goto out_err; } cmp = fsnotify_compare_groups(lmark->group, mark->group); if (cmp >= 0) { hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list); goto added; } } BUG_ON(last == NULL); /* mark should be the last entry. last is the current last entry */ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list); added: /* * Since connector is attached to object using cmpxchg() we are * guaranteed that connector initialization is fully visible by anyone * seeing mark->connector set. */ WRITE_ONCE(mark->connector, conn); out_err: spin_unlock(&conn->lock); spin_unlock(&mark->lock); return err; } /* * Attach an initialized mark to a given group and fs object. * These marks may be used for the fsnotify backend to determine which * event types should be delivered to which group. */ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { struct fsnotify_group *group = mark->group; int ret = 0; fsnotify_group_assert_locked(group); /* * LOCKING ORDER!!!! * group->mark_mutex * mark->lock * mark->connector->lock */ spin_lock(&mark->lock); mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED; list_add(&mark->g_list, &group->marks_list); fsnotify_get_mark(mark); /* for g_list */ spin_unlock(&mark->lock); ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags, fsid); if (ret) goto err; fsnotify_recalc_mask(mark->connector); return ret; err: spin_lock(&mark->lock); mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED); list_del_init(&mark->g_list); spin_unlock(&mark->lock); fsnotify_put_mark(mark); return ret; } int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { int ret; struct fsnotify_group *group = mark->group; fsnotify_group_lock(group); ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags, fsid); fsnotify_group_unlock(group); return ret; } EXPORT_SYMBOL_GPL(fsnotify_add_mark); /* * Given a list of marks, find the mark associated with given group. If found * take a reference to that mark and return it, else return NULL. */ struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, struct fsnotify_group *group) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark; conn = fsnotify_grab_connector(connp); if (!conn) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (mark->group == group && (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); return mark; } } spin_unlock(&conn->lock); return NULL; } EXPORT_SYMBOL_GPL(fsnotify_find_mark); /* Clear any marks in a group with given type mask */ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type) { struct fsnotify_mark *lmark, *mark; LIST_HEAD(to_free); struct list_head *head = &to_free; /* Skip selection step if we want to clear all marks. */ if (obj_type == FSNOTIFY_OBJ_TYPE_ANY) { head = &group->marks_list; goto clear; } /* * We have to be really careful here. Anytime we drop mark_mutex, e.g. * fsnotify_clear_marks_by_inode() can come and free marks. Even in our * to_free list so we have to use mark_mutex even when accessing that * list. And freeing mark requires us to drop mark_mutex. So we can * reliably free only the first mark in the list. That's why we first * move marks to free to to_free list in one go and then free marks in * to_free list one by one. */ fsnotify_group_lock(group); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { if (mark->connector->type == obj_type) list_move(&mark->g_list, &to_free); } fsnotify_group_unlock(group); clear: while (1) { fsnotify_group_lock(group); if (list_empty(head)) { fsnotify_group_unlock(group); break; } mark = list_first_entry(head, struct fsnotify_mark, g_list); fsnotify_get_mark(mark); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); fsnotify_put_mark(mark); } } /* Destroy all marks attached to an object via connector */ void fsnotify_destroy_marks(fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark, *old_mark = NULL; void *objp; unsigned int type; conn = fsnotify_grab_connector(connp); if (!conn) return; /* * We have to be careful since we can race with e.g. * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the * list can get modified. However we are holding mark reference and * thus our mark cannot be removed from obj_list so we can continue * iteration after regaining conn->lock. */ hlist_for_each_entry(mark, &conn->list, obj_list) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); old_mark = mark; fsnotify_destroy_mark(mark, mark->group); spin_lock(&conn->lock); } /* * Detach list from object now so that we don't pin inode until all * mark references get dropped. It would lead to strange results such * as delaying inode deletion or blocking unmount. */ objp = fsnotify_detach_connector_from_object(conn, &type); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); fsnotify_drop_object(type, objp); } /* * Nothing fancy, just initialize lists and locks and counters. */ void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { memset(mark, 0, sizeof(*mark)); spin_lock_init(&mark->lock); refcount_set(&mark->refcnt, 1); fsnotify_get_group(group); mark->group = group; WRITE_ONCE(mark->connector, NULL); } EXPORT_SYMBOL_GPL(fsnotify_init_mark); /* * Destroy all marks in destroy_list, waits for SRCU period to finish before * actually freeing marks. */ static void fsnotify_mark_destroy_workfn(struct work_struct *work) { struct fsnotify_mark *mark, *next; struct list_head private_destroy_list; spin_lock(&destroy_lock); /* exchange the list head */ list_replace_init(&destroy_list, &private_destroy_list); spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { list_del_init(&mark->g_list); fsnotify_final_mark_destroy(mark); } } /* Wait for all marks queued for destruction to be actually destroyed */ void fsnotify_wait_marks_destroyed(void) { flush_delayed_work(&reaper_work); } EXPORT_SYMBOL_GPL(fsnotify_wait_marks_destroyed); |
| 967 965 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/if.h> #include <linux/if_vlan.h> #include <net/udp_tunnel.h> #include <net/sch_generic.h> #include <linux/netfilter.h> #include <rdma/ib_addr.h> #include "rxe.h" #include "rxe_net.h" #include "rxe_loc.h" static struct rxe_recv_sockets recv_sockets; int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid) { int err; unsigned char ll_addr[ETH_ALEN]; ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr); err = dev_mc_add(rxe->ndev, ll_addr); return err; } int rxe_mcast_delete(struct rxe_dev *rxe, union ib_gid *mgid) { int err; unsigned char ll_addr[ETH_ALEN]; ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr); err = dev_mc_del(rxe->ndev, ll_addr); return err; } static struct dst_entry *rxe_find_route4(struct net_device *ndev, struct in_addr *saddr, struct in_addr *daddr) { struct rtable *rt; struct flowi4 fl = { { 0 } }; memset(&fl, 0, sizeof(fl)); fl.flowi4_oif = ndev->ifindex; memcpy(&fl.saddr, saddr, sizeof(*saddr)); memcpy(&fl.daddr, daddr, sizeof(*daddr)); fl.flowi4_proto = IPPROTO_UDP; rt = ip_route_output_key(&init_net, &fl); if (IS_ERR(rt)) { pr_err_ratelimited("no route to %pI4\n", &daddr->s_addr); return NULL; } return &rt->dst; } #if IS_ENABLED(CONFIG_IPV6) static struct dst_entry *rxe_find_route6(struct net_device *ndev, struct in6_addr *saddr, struct in6_addr *daddr) { struct dst_entry *ndst; struct flowi6 fl6 = { { 0 } }; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = ndev->ifindex; memcpy(&fl6.saddr, saddr, sizeof(*saddr)); memcpy(&fl6.daddr, daddr, sizeof(*daddr)); fl6.flowi6_proto = IPPROTO_UDP; ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk), recv_sockets.sk6->sk, &fl6, NULL); if (IS_ERR(ndst)) { pr_err_ratelimited("no route to %pI6\n", daddr); return NULL; } if (unlikely(ndst->error)) { pr_err("no route to %pI6\n", daddr); goto put; } return ndst; put: dst_release(ndst); return NULL; } #else static struct dst_entry *rxe_find_route6(struct net_device *ndev, struct in6_addr *saddr, struct in6_addr *daddr) { return NULL; } #endif static struct dst_entry *rxe_find_route(struct net_device *ndev, struct rxe_qp *qp, struct rxe_av *av) { struct dst_entry *dst = NULL; if (qp_type(qp) == IB_QPT_RC) dst = sk_dst_get(qp->sk->sk); if (!dst || !dst_check(dst, qp->dst_cookie)) { if (dst) dst_release(dst); if (av->network_type == RXE_NETWORK_TYPE_IPV4) { struct in_addr *saddr; struct in_addr *daddr; saddr = &av->sgid_addr._sockaddr_in.sin_addr; daddr = &av->dgid_addr._sockaddr_in.sin_addr; dst = rxe_find_route4(ndev, saddr, daddr); } else if (av->network_type == RXE_NETWORK_TYPE_IPV6) { struct in6_addr *saddr6; struct in6_addr *daddr6; saddr6 = &av->sgid_addr._sockaddr_in6.sin6_addr; daddr6 = &av->dgid_addr._sockaddr_in6.sin6_addr; dst = rxe_find_route6(ndev, saddr6, daddr6); #if IS_ENABLED(CONFIG_IPV6) if (dst) qp->dst_cookie = rt6_get_cookie((struct rt6_info *)dst); #endif } if (dst && (qp_type(qp) == IB_QPT_RC)) { dst_hold(dst); sk_dst_set(qp->sk->sk, dst); } } return dst; } static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct udphdr *udph; struct rxe_dev *rxe; struct net_device *ndev = skb->dev; struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); /* takes a reference on rxe->ib_dev * drop when skb is freed */ rxe = rxe_get_dev_from_net(ndev); if (!rxe && is_vlan_dev(ndev)) rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev)); if (!rxe) goto drop; if (skb_linearize(skb)) { pr_err("skb_linearize failed\n"); ib_device_put(&rxe->ib_dev); goto drop; } udph = udp_hdr(skb); pkt->rxe = rxe; pkt->port_num = 1; pkt->hdr = (u8 *)(udph + 1); pkt->mask = RXE_GRH_MASK; pkt->paylen = be16_to_cpu(udph->len) - sizeof(*udph); /* remove udp header */ skb_pull(skb, sizeof(struct udphdr)); rxe_rcv(skb); return 0; drop: kfree_skb(skb); return 0; } static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port, bool ipv6) { int err; struct socket *sock; struct udp_port_cfg udp_cfg = { }; struct udp_tunnel_sock_cfg tnl_cfg = { }; if (ipv6) { udp_cfg.family = AF_INET6; udp_cfg.ipv6_v6only = 1; } else { udp_cfg.family = AF_INET; } udp_cfg.local_udp_port = port; /* Create UDP socket */ err = udp_sock_create(net, &udp_cfg, &sock); if (err < 0) return ERR_PTR(err); tnl_cfg.encap_type = 1; tnl_cfg.encap_rcv = rxe_udp_encap_recv; /* Setup UDP tunnel */ setup_udp_tunnel_sock(net, sock, &tnl_cfg); return sock; } static void rxe_release_udp_tunnel(struct socket *sk) { if (sk) udp_tunnel_sock_release(sk); } static void prepare_udp_hdr(struct sk_buff *skb, __be16 src_port, __be16 dst_port) { struct udphdr *udph; __skb_push(skb, sizeof(*udph)); skb_reset_transport_header(skb); udph = udp_hdr(skb); udph->dest = dst_port; udph->source = src_port; udph->len = htons(skb->len); udph->check = 0; } static void prepare_ipv4_hdr(struct dst_entry *dst, struct sk_buff *skb, __be32 saddr, __be32 daddr, __u8 proto, __u8 tos, __u8 ttl, __be16 df, bool xnet) { struct iphdr *iph; skb_scrub_packet(skb, xnet); skb_clear_hash(skb); skb_dst_set(skb, dst_clone(dst)); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = IPVERSION; iph->ihl = sizeof(struct iphdr) >> 2; iph->tot_len = htons(skb->len); iph->frag_off = df; iph->protocol = proto; iph->tos = tos; iph->daddr = daddr; iph->saddr = saddr; iph->ttl = ttl; __ip_select_ident(dev_net(dst->dev), iph, skb_shinfo(skb)->gso_segs ?: 1); } static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb, struct in6_addr *saddr, struct in6_addr *daddr, __u8 proto, __u8 prio, __u8 ttl) { struct ipv6hdr *ip6h; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_set(skb, dst_clone(dst)); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, htonl(0)); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = proto; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6h->payload_len = htons(skb->len - sizeof(*ip6h)); } static int prepare4(struct rxe_pkt_info *pkt, struct sk_buff *skb) { struct rxe_qp *qp = pkt->qp; struct dst_entry *dst; bool xnet = false; __be16 df = htons(IP_DF); struct rxe_av *av = rxe_get_av(pkt); struct in_addr *saddr = &av->sgid_addr._sockaddr_in.sin_addr; struct in_addr *daddr = &av->dgid_addr._sockaddr_in.sin_addr; dst = rxe_find_route(skb->dev, qp, av); if (!dst) { pr_err("Host not reachable\n"); return -EHOSTUNREACH; } prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), cpu_to_be16(ROCE_V2_UDP_DPORT)); prepare_ipv4_hdr(dst, skb, saddr->s_addr, daddr->s_addr, IPPROTO_UDP, av->grh.traffic_class, av->grh.hop_limit, df, xnet); dst_release(dst); return 0; } static int prepare6(struct rxe_pkt_info *pkt, struct sk_buff *skb) { struct rxe_qp *qp = pkt->qp; struct dst_entry *dst; struct rxe_av *av = rxe_get_av(pkt); struct in6_addr *saddr = &av->sgid_addr._sockaddr_in6.sin6_addr; struct in6_addr *daddr = &av->dgid_addr._sockaddr_in6.sin6_addr; dst = rxe_find_route(skb->dev, qp, av); if (!dst) { pr_err("Host not reachable\n"); return -EHOSTUNREACH; } prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), cpu_to_be16(ROCE_V2_UDP_DPORT)); prepare_ipv6_hdr(dst, skb, saddr, daddr, IPPROTO_UDP, av->grh.traffic_class, av->grh.hop_limit); dst_release(dst); return 0; } int rxe_prepare(struct rxe_pkt_info *pkt, struct sk_buff *skb) { int err = 0; if (skb->protocol == htons(ETH_P_IP)) err = prepare4(pkt, skb); else if (skb->protocol == htons(ETH_P_IPV6)) err = prepare6(pkt, skb); if (ether_addr_equal(skb->dev->dev_addr, rxe_get_av(pkt)->dmac)) pkt->mask |= RXE_LOOPBACK_MASK; return err; } static void rxe_skb_tx_dtor(struct sk_buff *skb) { struct sock *sk = skb->sk; struct rxe_qp *qp = sk->sk_user_data; int skb_out = atomic_dec_return(&qp->skb_out); if (unlikely(qp->need_req_skb && skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW)) rxe_run_task(&qp->req.task, 1); rxe_drop_ref(qp); } static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt) { int err; skb->destructor = rxe_skb_tx_dtor; skb->sk = pkt->qp->sk->sk; rxe_add_ref(pkt->qp); atomic_inc(&pkt->qp->skb_out); if (skb->protocol == htons(ETH_P_IP)) { err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } else if (skb->protocol == htons(ETH_P_IPV6)) { err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } else { pr_err("Unknown layer 3 protocol: %d\n", skb->protocol); atomic_dec(&pkt->qp->skb_out); rxe_drop_ref(pkt->qp); kfree_skb(skb); return -EINVAL; } if (unlikely(net_xmit_eval(err))) { pr_debug("error sending packet: %d\n", err); return -EAGAIN; } return 0; } /* fix up a send packet to match the packets * received from UDP before looping them back */ static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt) { memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt)); if (skb->protocol == htons(ETH_P_IP)) skb_pull(skb, sizeof(struct iphdr)); else skb_pull(skb, sizeof(struct ipv6hdr)); if (WARN_ON(!ib_device_try_get(&pkt->rxe->ib_dev))) { kfree_skb(skb); return -EIO; } /* remove udp header */ skb_pull(skb, sizeof(struct udphdr)); rxe_rcv(skb); return 0; } int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, struct sk_buff *skb) { int err; int is_request = pkt->mask & RXE_REQ_MASK; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); if ((is_request && (qp->req.state != QP_STATE_READY)) || (!is_request && (qp->resp.state != QP_STATE_READY))) { pr_info("Packet dropped. QP is not in ready state\n"); goto drop; } rxe_icrc_generate(skb, pkt); if (pkt->mask & RXE_LOOPBACK_MASK) err = rxe_loopback(skb, pkt); else err = rxe_send(skb, pkt); if (err) { rxe->xmit_errors++; rxe_counter_inc(rxe, RXE_CNT_SEND_ERR); return err; } if ((qp_type(qp) != IB_QPT_RC) && (pkt->mask & RXE_END_MASK)) { pkt->wqe->state = wqe_state_done; rxe_run_task(&qp->comp.task, 1); } rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS); goto done; drop: kfree_skb(skb); err = 0; done: return err; } struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av, int paylen, struct rxe_pkt_info *pkt) { unsigned int hdr_len; struct sk_buff *skb = NULL; struct net_device *ndev; const struct ib_gid_attr *attr; const int port_num = 1; attr = rdma_get_gid_attr(&rxe->ib_dev, port_num, av->grh.sgid_index); if (IS_ERR(attr)) return NULL; if (av->network_type == RXE_NETWORK_TYPE_IPV4) hdr_len = ETH_HLEN + sizeof(struct udphdr) + sizeof(struct iphdr); else hdr_len = ETH_HLEN + sizeof(struct udphdr) + sizeof(struct ipv6hdr); rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(attr); if (IS_ERR(ndev)) { rcu_read_unlock(); goto out; } skb = alloc_skb(paylen + hdr_len + LL_RESERVED_SPACE(ndev), GFP_ATOMIC); if (unlikely(!skb)) { rcu_read_unlock(); goto out; } skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev)); /* FIXME: hold reference to this netdev until life of this skb. */ skb->dev = ndev; rcu_read_unlock(); if (av->network_type == RXE_NETWORK_TYPE_IPV4) skb->protocol = htons(ETH_P_IP); else skb->protocol = htons(ETH_P_IPV6); pkt->rxe = rxe; pkt->port_num = port_num; pkt->hdr = skb_put(skb, paylen); pkt->mask |= RXE_GRH_MASK; out: rdma_put_gid_attr(attr); return skb; } /* * this is required by rxe_cfg to match rxe devices in * /sys/class/infiniband up with their underlying ethernet devices */ const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num) { return rxe->ndev->name; } int rxe_net_add(const char *ibdev_name, struct net_device *ndev) { int err; struct rxe_dev *rxe = NULL; rxe = ib_alloc_device(rxe_dev, ib_dev); if (!rxe) return -ENOMEM; rxe->ndev = ndev; err = rxe_add(rxe, ndev->mtu, ibdev_name); if (err) { ib_dealloc_device(&rxe->ib_dev); return err; } return 0; } static void rxe_port_event(struct rxe_dev *rxe, enum ib_event_type event) { struct ib_event ev; ev.device = &rxe->ib_dev; ev.element.port_num = 1; ev.event = event; ib_dispatch_event(&ev); } /* Caller must hold net_info_lock */ void rxe_port_up(struct rxe_dev *rxe) { struct rxe_port *port; port = &rxe->port; port->attr.state = IB_PORT_ACTIVE; rxe_port_event(rxe, IB_EVENT_PORT_ACTIVE); dev_info(&rxe->ib_dev.dev, "set active\n"); } /* Caller must hold net_info_lock */ void rxe_port_down(struct rxe_dev *rxe) { struct rxe_port *port; port = &rxe->port; port->attr.state = IB_PORT_DOWN; rxe_port_event(rxe, IB_EVENT_PORT_ERR); rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED); dev_info(&rxe->ib_dev.dev, "set down\n"); } void rxe_set_port_state(struct rxe_dev *rxe) { if (netif_running(rxe->ndev) && netif_carrier_ok(rxe->ndev)) rxe_port_up(rxe); else rxe_port_down(rxe); } static int rxe_notify(struct notifier_block *not_blk, unsigned long event, void *arg) { struct net_device *ndev = netdev_notifier_info_to_dev(arg); struct rxe_dev *rxe = rxe_get_dev_from_net(ndev); if (!rxe) return NOTIFY_OK; switch (event) { case NETDEV_UNREGISTER: ib_unregister_device_queued(&rxe->ib_dev); break; case NETDEV_UP: rxe_port_up(rxe); break; case NETDEV_DOWN: rxe_port_down(rxe); break; case NETDEV_CHANGEMTU: pr_info("%s changed mtu to %d\n", ndev->name, ndev->mtu); rxe_set_mtu(rxe, ndev->mtu); break; case NETDEV_CHANGE: rxe_set_port_state(rxe); break; case NETDEV_REBOOT: case NETDEV_GOING_DOWN: case NETDEV_CHANGEADDR: case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: default: pr_info("ignoring netdev event = %ld for %s\n", event, ndev->name); break; } ib_device_put(&rxe->ib_dev); return NOTIFY_OK; } static struct notifier_block rxe_net_notifier = { .notifier_call = rxe_notify, }; static int rxe_net_ipv4_init(void) { recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), false); if (IS_ERR(recv_sockets.sk4)) { recv_sockets.sk4 = NULL; pr_err("Failed to create IPv4 UDP tunnel\n"); return -1; } return 0; } static int rxe_net_ipv6_init(void) { #if IS_ENABLED(CONFIG_IPV6) recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), true); if (PTR_ERR(recv_sockets.sk6) == -EAFNOSUPPORT) { recv_sockets.sk6 = NULL; pr_warn("IPv6 is not supported, can not create a UDPv6 socket\n"); return 0; } if (IS_ERR(recv_sockets.sk6)) { recv_sockets.sk6 = NULL; pr_err("Failed to create IPv6 UDP tunnel\n"); return -1; } #endif return 0; } void rxe_net_exit(void) { rxe_release_udp_tunnel(recv_sockets.sk6); rxe_release_udp_tunnel(recv_sockets.sk4); unregister_netdevice_notifier(&rxe_net_notifier); } int rxe_net_init(void) { int err; recv_sockets.sk6 = NULL; err = rxe_net_ipv4_init(); if (err) return err; err = rxe_net_ipv6_init(); if (err) goto err_out; err = register_netdevice_notifier(&rxe_net_notifier); if (err) { pr_err("Failed to register netdev notifier\n"); goto err_out; } return 0; err_out: rxe_net_exit(); return err; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright 2019 Google LLC */ #ifndef __LINUX_BLK_CRYPTO_INTERNAL_H #define __LINUX_BLK_CRYPTO_INTERNAL_H #include <linux/bio.h> #include <linux/blkdev.h> /* Represents a crypto mode supported by blk-crypto */ struct blk_crypto_mode { const char *cipher_str; /* crypto API name (for fallback case) */ unsigned int keysize; /* key size in bytes */ unsigned int ivsize; /* iv size in bytes */ }; extern const struct blk_crypto_mode blk_crypto_modes[]; #ifdef CONFIG_BLK_INLINE_ENCRYPTION void bio_crypt_dun_increment(u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], unsigned int inc); bool bio_crypt_rq_ctx_compatible(struct request *rq, struct bio *bio); bool bio_crypt_ctx_mergeable(struct bio_crypt_ctx *bc1, unsigned int bc1_bytes, struct bio_crypt_ctx *bc2); static inline bool bio_crypt_ctx_back_mergeable(struct request *req, struct bio *bio) { return bio_crypt_ctx_mergeable(req->crypt_ctx, blk_rq_bytes(req), bio->bi_crypt_context); } static inline bool bio_crypt_ctx_front_mergeable(struct request *req, struct bio *bio) { return bio_crypt_ctx_mergeable(bio->bi_crypt_context, bio->bi_iter.bi_size, req->crypt_ctx); } static inline bool bio_crypt_ctx_merge_rq(struct request *req, struct request *next) { return bio_crypt_ctx_mergeable(req->crypt_ctx, blk_rq_bytes(req), next->crypt_ctx); } static inline void blk_crypto_rq_set_defaults(struct request *rq) { rq->crypt_ctx = NULL; rq->crypt_keyslot = NULL; } static inline bool blk_crypto_rq_is_encrypted(struct request *rq) { return rq->crypt_ctx; } static inline bool blk_crypto_rq_has_keyslot(struct request *rq) { return rq->crypt_keyslot; } #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool bio_crypt_rq_ctx_compatible(struct request *rq, struct bio *bio) { return true; } static inline bool bio_crypt_ctx_front_mergeable(struct request *req, struct bio *bio) { return true; } static inline bool bio_crypt_ctx_back_mergeable(struct request *req, struct bio *bio) { return true; } static inline bool bio_crypt_ctx_merge_rq(struct request *req, struct request *next) { return true; } static inline void blk_crypto_rq_set_defaults(struct request *rq) { } static inline bool blk_crypto_rq_is_encrypted(struct request *rq) { return false; } static inline bool blk_crypto_rq_has_keyslot(struct request *rq) { return false; } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ void __bio_crypt_advance(struct bio *bio, unsigned int bytes); static inline void bio_crypt_advance(struct bio *bio, unsigned int bytes) { if (bio_has_crypt_ctx(bio)) __bio_crypt_advance(bio, bytes); } void __bio_crypt_free_ctx(struct bio *bio); static inline void bio_crypt_free_ctx(struct bio *bio) { if (bio_has_crypt_ctx(bio)) __bio_crypt_free_ctx(bio); } static inline void bio_crypt_do_front_merge(struct request *rq, struct bio *bio) { #ifdef CONFIG_BLK_INLINE_ENCRYPTION if (bio_has_crypt_ctx(bio)) memcpy(rq->crypt_ctx->bc_dun, bio->bi_crypt_context->bc_dun, sizeof(rq->crypt_ctx->bc_dun)); #endif } bool __blk_crypto_bio_prep(struct bio **bio_ptr); static inline bool blk_crypto_bio_prep(struct bio **bio_ptr) { if (bio_has_crypt_ctx(*bio_ptr)) return __blk_crypto_bio_prep(bio_ptr); return true; } blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq); static inline blk_status_t blk_crypto_rq_get_keyslot(struct request *rq) { if (blk_crypto_rq_is_encrypted(rq)) return __blk_crypto_rq_get_keyslot(rq); return BLK_STS_OK; } void __blk_crypto_rq_put_keyslot(struct request *rq); static inline void blk_crypto_rq_put_keyslot(struct request *rq) { if (blk_crypto_rq_has_keyslot(rq)) __blk_crypto_rq_put_keyslot(rq); } void __blk_crypto_free_request(struct request *rq); static inline void blk_crypto_free_request(struct request *rq) { if (blk_crypto_rq_is_encrypted(rq)) __blk_crypto_free_request(rq); } int __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, gfp_t gfp_mask); /** * blk_crypto_rq_bio_prep - Prepare a request's crypt_ctx when its first bio * is inserted * @rq: The request to prepare * @bio: The first bio being inserted into the request * @gfp_mask: Memory allocation flags * * Return: 0 on success, -ENOMEM if out of memory. -ENOMEM is only possible if * @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM. */ static inline int blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, gfp_t gfp_mask) { if (bio_has_crypt_ctx(bio)) return __blk_crypto_rq_bio_prep(rq, bio, gfp_mask); return 0; } /** * blk_crypto_insert_cloned_request - Prepare a cloned request to be inserted * into a request queue. * @rq: the request being queued * * Return: BLK_STS_OK on success, nonzero on error. */ static inline blk_status_t blk_crypto_insert_cloned_request(struct request *rq) { if (blk_crypto_rq_is_encrypted(rq)) return blk_crypto_rq_get_keyslot(rq); return BLK_STS_OK; } #ifdef CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num); bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr); int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key); #else /* CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK */ static inline int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num) { pr_warn_once("crypto API fallback is disabled\n"); return -ENOPKG; } static inline bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr) { pr_warn_once("crypto API fallback disabled; failing request.\n"); (*bio_ptr)->bi_status = BLK_STS_NOTSUPP; return false; } static inline int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key) { return 0; } #endif /* CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK */ #endif /* __LINUX_BLK_CRYPTO_INTERNAL_H */ |
| 45 45 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 | /* * Copyright (c) 2006, 2018 Oracle and/or its affiliates. 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. * */ #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/in.h> #include <net/tcp.h> #include "rds.h" #include "tcp.h" void rds_tcp_keepalive(struct socket *sock) { /* values below based on xs_udp_default_timeout */ int keepidle = 5; /* send a probe 'keepidle' secs after last data */ int keepcnt = 5; /* number of unack'ed probes before declaring dead */ sock_set_keepalive(sock->sk); tcp_sock_set_keepcnt(sock->sk, keepcnt); tcp_sock_set_keepidle(sock->sk, keepidle); /* KEEPINTVL is the interval between successive probes. We follow * the model in xs_tcp_finish_connecting() and re-use keepidle. */ tcp_sock_set_keepintvl(sock->sk, keepidle); } /* rds_tcp_accept_one_path(): if accepting on cp_index > 0, make sure the * client's ipaddr < server's ipaddr. Otherwise, close the accepted * socket and force a reconneect from smaller -> larger ip addr. The reason * we special case cp_index 0 is to allow the rds probe ping itself to itself * get through efficiently. * Since reconnects are only initiated from the node with the numerically * smaller ip address, we recycle conns in RDS_CONN_ERROR on the passive side * by moving them to CONNECTING in this function. */ static struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn) { int i; int npaths = max_t(int, 1, conn->c_npaths); /* for mprds, all paths MUST be initiated by the peer * with the smaller address. */ if (rds_addr_cmp(&conn->c_faddr, &conn->c_laddr) >= 0) { /* Make sure we initiate at least one path if this * has not already been done; rds_start_mprds() will * take care of additional paths, if necessary. */ if (npaths == 1) rds_conn_path_connect_if_down(&conn->c_path[0]); return NULL; } for (i = 0; i < npaths; i++) { struct rds_conn_path *cp = &conn->c_path[i]; if (rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING) || rds_conn_path_transition(cp, RDS_CONN_ERROR, RDS_CONN_CONNECTING)) { return cp->cp_transport_data; } } return NULL; } int rds_tcp_accept_one(struct socket *sock) { struct socket *new_sock = NULL; struct rds_connection *conn; int ret; struct inet_sock *inet; struct rds_tcp_connection *rs_tcp = NULL; int conn_state; struct rds_conn_path *cp; struct in6_addr *my_addr, *peer_addr; #if !IS_ENABLED(CONFIG_IPV6) struct in6_addr saddr, daddr; #endif int dev_if = 0; if (!sock) /* module unload or netns delete in progress */ return -ENETUNREACH; ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type, sock->sk->sk_protocol, &new_sock); if (ret) goto out; ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true); if (ret < 0) goto out; /* sock_create_lite() does not get a hold on the owner module so we * need to do it here. Note that sock_release() uses sock->ops to * determine if it needs to decrement the reference count. So set * sock->ops after calling accept() in case that fails. And there's * no need to do try_module_get() as the listener should have a hold * already. */ new_sock->ops = sock->ops; __module_get(new_sock->ops->owner); rds_tcp_keepalive(new_sock); rds_tcp_tune(new_sock); inet = inet_sk(new_sock->sk); #if IS_ENABLED(CONFIG_IPV6) my_addr = &new_sock->sk->sk_v6_rcv_saddr; peer_addr = &new_sock->sk->sk_v6_daddr; #else ipv6_addr_set_v4mapped(inet->inet_saddr, &saddr); ipv6_addr_set_v4mapped(inet->inet_daddr, &daddr); my_addr = &saddr; peer_addr = &daddr; #endif rdsdebug("accepted family %d tcp %pI6c:%u -> %pI6c:%u\n", sock->sk->sk_family, my_addr, ntohs(inet->inet_sport), peer_addr, ntohs(inet->inet_dport)); #if IS_ENABLED(CONFIG_IPV6) /* sk_bound_dev_if is not set if the peer address is not link local * address. In this case, it happens that mcast_oif is set. So * just use it. */ if ((ipv6_addr_type(my_addr) & IPV6_ADDR_LINKLOCAL) && !(ipv6_addr_type(peer_addr) & IPV6_ADDR_LINKLOCAL)) { struct ipv6_pinfo *inet6; inet6 = inet6_sk(new_sock->sk); dev_if = inet6->mcast_oif; } else { dev_if = new_sock->sk->sk_bound_dev_if; } #endif if (!rds_tcp_laddr_check(sock_net(sock->sk), peer_addr, dev_if)) { /* local address connection is only allowed via loopback */ ret = -EOPNOTSUPP; goto out; } conn = rds_conn_create(sock_net(sock->sk), my_addr, peer_addr, &rds_tcp_transport, 0, GFP_KERNEL, dev_if); if (IS_ERR(conn)) { ret = PTR_ERR(conn); goto out; } /* An incoming SYN request came in, and TCP just accepted it. * * If the client reboots, this conn will need to be cleaned up. * rds_tcp_state_change() will do that cleanup */ rs_tcp = rds_tcp_accept_one_path(conn); if (!rs_tcp) goto rst_nsk; mutex_lock(&rs_tcp->t_conn_path_lock); cp = rs_tcp->t_cpath; conn_state = rds_conn_path_state(cp); WARN_ON(conn_state == RDS_CONN_UP); if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_ERROR) goto rst_nsk; if (rs_tcp->t_sock) { /* Duelling SYN has been handled in rds_tcp_accept_one() */ rds_tcp_reset_callbacks(new_sock, cp); /* rds_connect_path_complete() marks RDS_CONN_UP */ rds_connect_path_complete(cp, RDS_CONN_RESETTING); } else { rds_tcp_set_callbacks(new_sock, cp); rds_connect_path_complete(cp, RDS_CONN_CONNECTING); } new_sock = NULL; ret = 0; if (conn->c_npaths == 0) rds_send_ping(cp->cp_conn, cp->cp_index); goto out; rst_nsk: /* reset the newly returned accept sock and bail. * It is safe to set linger on new_sock because the RDS connection * has not been brought up on new_sock, so no RDS-level data could * be pending on it. By setting linger, we achieve the side-effect * of avoiding TIME_WAIT state on new_sock. */ sock_no_linger(new_sock->sk); kernel_sock_shutdown(new_sock, SHUT_RDWR); ret = 0; out: if (rs_tcp) mutex_unlock(&rs_tcp->t_conn_path_lock); if (new_sock) sock_release(new_sock); return ret; } void rds_tcp_listen_data_ready(struct sock *sk) { void (*ready)(struct sock *sk); rdsdebug("listen data ready sk %p\n", sk); read_lock_bh(&sk->sk_callback_lock); ready = sk->sk_user_data; if (!ready) { /* check for teardown race */ ready = sk->sk_data_ready; goto out; } /* * ->sk_data_ready is also called for a newly established child socket * before it has been accepted and the accepter has set up their * data_ready.. we only want to queue listen work for our listening * socket * * (*ready)() may be null if we are racing with netns delete, and * the listen socket is being torn down. */ if (sk->sk_state == TCP_LISTEN) rds_tcp_accept_work(sk); else ready = rds_tcp_listen_sock_def_readable(sock_net(sk)); out: read_unlock_bh(&sk->sk_callback_lock); if (ready) ready(sk); } struct socket *rds_tcp_listen_init(struct net *net, bool isv6) { struct socket *sock = NULL; struct sockaddr_storage ss; struct sockaddr_in6 *sin6; struct sockaddr_in *sin; int addr_len; int ret; ret = sock_create_kern(net, isv6 ? PF_INET6 : PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); if (ret < 0) { rdsdebug("could not create %s listener socket: %d\n", isv6 ? "IPv6" : "IPv4", ret); goto out; } sock->sk->sk_reuse = SK_CAN_REUSE; tcp_sock_set_nodelay(sock->sk); write_lock_bh(&sock->sk->sk_callback_lock); sock->sk->sk_user_data = sock->sk->sk_data_ready; sock->sk->sk_data_ready = rds_tcp_listen_data_ready; write_unlock_bh(&sock->sk->sk_callback_lock); if (isv6) { sin6 = (struct sockaddr_in6 *)&ss; sin6->sin6_family = PF_INET6; sin6->sin6_addr = in6addr_any; sin6->sin6_port = (__force u16)htons(RDS_TCP_PORT); sin6->sin6_scope_id = 0; sin6->sin6_flowinfo = 0; addr_len = sizeof(*sin6); } else { sin = (struct sockaddr_in *)&ss; sin->sin_family = PF_INET; sin->sin_addr.s_addr = INADDR_ANY; sin->sin_port = (__force u16)htons(RDS_TCP_PORT); addr_len = sizeof(*sin); } ret = kernel_bind(sock, (struct sockaddr *)&ss, addr_len); if (ret < 0) { rdsdebug("could not bind %s listener socket: %d\n", isv6 ? "IPv6" : "IPv4", ret); goto out; } ret = sock->ops->listen(sock, 64); if (ret < 0) goto out; return sock; out: if (sock) sock_release(sock); return NULL; } void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor) { struct sock *sk; if (!sock) return; sk = sock->sk; /* serialize with and prevent further callbacks */ lock_sock(sk); write_lock_bh(&sk->sk_callback_lock); if (sk->sk_user_data) { sk->sk_data_ready = sk->sk_user_data; sk->sk_user_data = NULL; } write_unlock_bh(&sk->sk_callback_lock); release_sock(sk); /* wait for accepts to stop and close the socket */ flush_workqueue(rds_wq); flush_work(acceptor); sock_release(sock); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ebtable_nat * * Authors: * Bart De Schuymer <bdschuym@pandora.be> * * April, 2002 * */ #include <linux/netfilter_bridge/ebtables.h> #include <uapi/linux/netfilter_bridge.h> #include <linux/module.h> #define NAT_VALID_HOOKS ((1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_OUT) | \ (1 << NF_BR_POST_ROUTING)) static struct ebt_entries initial_chains[] = { { .name = "PREROUTING", .policy = EBT_ACCEPT, }, { .name = "OUTPUT", .policy = EBT_ACCEPT, }, { .name = "POSTROUTING", .policy = EBT_ACCEPT, } }; static struct ebt_replace_kernel initial_table = { .name = "nat", .valid_hooks = NAT_VALID_HOOKS, .entries_size = 3 * sizeof(struct ebt_entries), .hook_entry = { [NF_BR_PRE_ROUTING] = &initial_chains[0], [NF_BR_LOCAL_OUT] = &initial_chains[1], [NF_BR_POST_ROUTING] = &initial_chains[2], }, .entries = (char *)initial_chains, }; static const struct ebt_table frame_nat = { .name = "nat", .table = &initial_table, .valid_hooks = NAT_VALID_HOOKS, .me = THIS_MODULE, }; static unsigned int ebt_nat_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ebt_do_table(skb, state, priv); } static const struct nf_hook_ops ebt_ops_nat[] = { { .hook = ebt_nat_hook, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_NAT_DST_OTHER, }, { .hook = ebt_nat_hook, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, .priority = NF_BR_PRI_NAT_SRC, }, { .hook = ebt_nat_hook, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_NAT_DST_BRIDGED, }, }; static int frame_nat_table_init(struct net *net) { return ebt_register_table(net, &frame_nat, ebt_ops_nat); } static void __net_exit frame_nat_net_pre_exit(struct net *net) { ebt_unregister_table_pre_exit(net, "nat"); } static void __net_exit frame_nat_net_exit(struct net *net) { ebt_unregister_table(net, "nat"); } static struct pernet_operations frame_nat_net_ops = { .exit = frame_nat_net_exit, .pre_exit = frame_nat_net_pre_exit, }; static int __init ebtable_nat_init(void) { int ret = ebt_register_template(&frame_nat, frame_nat_table_init); if (ret) return ret; ret = register_pernet_subsys(&frame_nat_net_ops); if (ret) { ebt_unregister_template(&frame_nat); return ret; } return ret; } static void __exit ebtable_nat_fini(void) { unregister_pernet_subsys(&frame_nat_net_ops); ebt_unregister_template(&frame_nat); } module_init(ebtable_nat_init); module_exit(ebtable_nat_fini); MODULE_LICENSE("GPL"); |
| 59 59 59 58 59 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 | // 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 DECLARE_BITMAP(misc_minors, DYNAMIC_MINORS); #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; int err = -ENODEV; const struct file_operations *new_fops = NULL; mutex_lock(&misc_mtx); list_for_each_entry(c, &misc_list, list) { if (c->minor == minor) { new_fops = fops_get(c->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(c, &misc_list, list) { if (c->minor == minor) { new_fops = fops_get(c->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 struct class *misc_class; 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 = find_first_zero_bit(misc_minors, DYNAMIC_MINORS); if (i >= DYNAMIC_MINORS) { err = -EBUSY; goto out; } misc->minor = DYNAMIC_MINORS - i - 1; set_bit(i, misc_minors); } 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) { int i = DYNAMIC_MINORS - misc->minor - 1; if (i < DYNAMIC_MINORS && i >= 0) clear_bit(i, misc_minors); 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) { int i = DYNAMIC_MINORS - misc->minor - 1; 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)); if (i < DYNAMIC_MINORS && i >= 0) clear_bit(i, misc_minors); mutex_unlock(&misc_mtx); } EXPORT_SYMBOL(misc_deregister); static char *misc_devnode(struct device *dev, umode_t *mode) { 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 int __init misc_init(void) { int err; struct proc_dir_entry *ret; ret = proc_create_seq("misc", 0, NULL, &misc_seq_ops); misc_class = class_create(THIS_MODULE, "misc"); err = PTR_ERR(misc_class); if (IS_ERR(misc_class)) goto fail_remove; err = -EIO; if (register_chrdev(MISC_MAJOR, "misc", &misc_fops)) goto fail_printk; misc_class->devnode = misc_devnode; return 0; fail_printk: pr_err("unable to get major %d for misc devices\n", MISC_MAJOR); class_destroy(misc_class); fail_remove: if (ret) remove_proc_entry("misc", NULL); return err; } subsys_initcall(misc_init); |
| 120 27 4 4 4 4 4 20 59 57 57 318 429 428 2 103 387 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the IP router. * * Version: @(#)route.h 1.0.4 05/27/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Fixes: * Alan Cox : Reformatted. Added ip_rt_local() * Alan Cox : Support for TCP parameters. * Alexey Kuznetsov: Major changes for new routing code. * Mike McLagan : Routing by source * Robert Olsson : Added rt_cache statistics */ #ifndef _ROUTE_H #define _ROUTE_H #include <net/dst.h> #include <net/inetpeer.h> #include <net/flow.h> #include <net/inet_sock.h> #include <net/ip_fib.h> #include <net/arp.h> #include <net/ndisc.h> #include <linux/in_route.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> #include <linux/route.h> #include <linux/ip.h> #include <linux/cache.h> #include <linux/security.h> /* IPv4 datagram length is stored into 16bit field (tot_len) */ #define IP_MAX_MTU 0xFFFFU #define RTO_ONLINK 0x01 #define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE)) #define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE)) struct fib_nh; struct fib_info; struct uncached_list; struct rtable { struct dst_entry dst; int rt_genid; unsigned int rt_flags; __u16 rt_type; __u8 rt_is_input; __u8 rt_uses_gateway; int rt_iif; u8 rt_gw_family; /* Info on neighbour */ union { __be32 rt_gw4; struct in6_addr rt_gw6; }; /* Miscellaneous cached information */ u32 rt_mtu_locked:1, rt_pmtu:31; struct list_head rt_uncached; struct uncached_list *rt_uncached_list; }; static inline bool rt_is_input_route(const struct rtable *rt) { return rt->rt_is_input != 0; } static inline bool rt_is_output_route(const struct rtable *rt) { return rt->rt_is_input == 0; } static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr) { if (rt->rt_gw_family == AF_INET) return rt->rt_gw4; return daddr; } struct ip_rt_acct { __u32 o_bytes; __u32 o_packets; __u32 i_bytes; __u32 i_packets; }; struct rt_cache_stat { unsigned int in_slow_tot; unsigned int in_slow_mc; unsigned int in_no_route; unsigned int in_brd; unsigned int in_martian_dst; unsigned int in_martian_src; unsigned int out_slow_tot; unsigned int out_slow_mc; }; extern struct ip_rt_acct __percpu *ip_rt_acct; struct in_device; int ip_rt_init(void); void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp, const struct sk_buff *skb); struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp, struct fib_result *res, const struct sk_buff *skb); static inline struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp) { return ip_route_output_key_hash(net, flp, NULL); } struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, const struct sock *sk); struct rtable *ip_route_output_tunnel(struct sk_buff *skb, struct net_device *dev, struct net *net, __be32 *saddr, const struct ip_tunnel_info *info, u8 protocol, bool use_cache); struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig); static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 *flp) { return ip_route_output_flow(net, flp, NULL); } static inline struct rtable *ip_route_output(struct net *net, __be32 daddr, __be32 saddr, u8 tos, int oif) { struct flowi4 fl4 = { .flowi4_oif = oif, .flowi4_tos = tos, .daddr = daddr, .saddr = saddr, }; return ip_route_output_key(net, &fl4); } static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi4 *fl4, struct sock *sk, __be32 daddr, __be32 saddr, __be16 dport, __be16 sport, __u8 proto, __u8 tos, int oif) { flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos, RT_SCOPE_UNIVERSE, proto, sk ? inet_sk_flowi_flags(sk) : 0, daddr, saddr, dport, sport, sock_net_uid(net, sk)); if (sk) security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); } static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 *fl4, __be32 daddr, __be32 saddr, __be32 gre_key, __u8 tos, int oif) { memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_oif = oif; fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = tos; fl4->flowi4_proto = IPPROTO_GRE; fl4->fl4_gre_key = gre_key; return ip_route_output_key(net, fl4); } int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct in_device *in_dev, u32 *itag); int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin); int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin, struct fib_result *res); int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin, const struct sk_buff *hint); static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin) { int err; rcu_read_lock(); err = ip_route_input_noref(skb, dst, src, tos, devin); if (!err) { skb_dst_force(skb); if (!skb_dst(skb)) err = -EINVAL; } rcu_read_unlock(); return err; } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol); void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk); void ip_rt_send_redirect(struct sk_buff *skb); unsigned int inet_addr_type(struct net *net, __be32 addr); unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr); unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr); void ip_rt_multicast_event(struct in_device *); int ip_rt_ioctl(struct net *, unsigned int cmd, struct rtentry *rt); void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt); struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, bool nopolicy, bool noxfrm); struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt); struct in_ifaddr; void fib_add_ifaddr(struct in_ifaddr *); void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *); void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric); void rt_add_uncached_list(struct rtable *rt); void rt_del_uncached_list(struct rtable *rt); int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, int *fa_index, int fa_start, unsigned int flags); static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. * We rely on dst being first structure in struct rtable */ BUILD_BUG_ON(offsetof(struct rtable, dst) != 0); dst_release(&rt->dst); } #define IPTOS_RT_MASK (IPTOS_TOS_MASK & ~3) extern const __u8 ip_tos2prio[16]; static inline char rt_tos2priority(u8 tos) { return ip_tos2prio[IPTOS_TOS(tos)>>1]; } /* ip_route_connect() and ip_route_newports() work in tandem whilst * binding a socket for a new outgoing connection. * * In order to use IPSEC properly, we must, in the end, have a * route that was looked up using all available keys including source * and destination ports. * * However, if a source port needs to be allocated (the user specified * a wildcard source port) we need to obtain addressing information * in order to perform that allocation. * * So ip_route_connect() looks up a route using wildcarded source and * destination ports in the key, simply so that we can get a pair of * addresses to use for port allocation. * * Later, once the ports are allocated, ip_route_newports() will make * another route lookup if needed to make sure we catch any IPSEC * rules keyed on the port information. * * The callers allocate the flow key on their stack, and must pass in * the same flowi4 object to both the ip_route_connect() and the * ip_route_newports() calls. */ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 src, u32 tos, int oif, u8 protocol, __be16 sport, __be16 dport, struct sock *sk) { __u8 flow_flags = 0; if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, protocol, flow_flags, dst, src, dport, sport, sk->sk_uid); } static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst, __be32 src, u32 tos, int oif, u8 protocol, __be16 sport, __be16 dport, struct sock *sk) { struct net *net = sock_net(sk); struct rtable *rt; ip_route_connect_init(fl4, dst, src, tos, oif, protocol, sport, dport, sk); if (!dst || !src) { rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) return rt; ip_rt_put(rt); flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr); } security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); } static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable *rt, __be16 orig_sport, __be16 orig_dport, __be16 sport, __be16 dport, struct sock *sk) { if (sport != orig_sport || dport != orig_dport) { fl4->fl4_dport = dport; fl4->fl4_sport = sport; ip_rt_put(rt); flowi4_update_output(fl4, sk->sk_bound_dev_if, RT_CONN_FLAGS(sk), fl4->daddr, fl4->saddr); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(sock_net(sk), fl4, sk); } return rt; } static inline int inet_iif(const struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); if (rt && rt->rt_iif) return rt->rt_iif; return skb->skb_iif; } static inline int ip4_dst_hoplimit(const struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); struct net *net = dev_net(dst->dev); if (hoplimit == 0) hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl); return hoplimit; } static inline struct neighbour *ip_neigh_gw4(struct net_device *dev, __be32 daddr) { struct neighbour *neigh; neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)daddr); if (unlikely(!neigh)) neigh = __neigh_create(&arp_tbl, &daddr, dev, false); return neigh; } static inline struct neighbour *ip_neigh_for_gw(struct rtable *rt, struct sk_buff *skb, bool *is_v6gw) { struct net_device *dev = rt->dst.dev; struct neighbour *neigh; if (likely(rt->rt_gw_family == AF_INET)) { neigh = ip_neigh_gw4(dev, rt->rt_gw4); } else if (rt->rt_gw_family == AF_INET6) { neigh = ip_neigh_gw6(dev, &rt->rt_gw6); *is_v6gw = true; } else { neigh = ip_neigh_gw4(dev, ip_hdr(skb)->daddr); } return neigh; } #endif /* _ROUTE_H */ |
| 5 1 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 | // SPDX-License-Identifier: GPL-2.0 /* XDP user-space packet buffer * Copyright(c) 2018 Intel Corporation. */ #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/bpf.h> #include <linux/mm.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/idr.h> #include <linux/vmalloc.h> #include "xdp_umem.h" #include "xsk_queue.h" #define XDP_UMEM_MIN_CHUNK_SIZE 2048 static DEFINE_IDA(umem_ida); static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); kvfree(umem->pgs); umem->pgs = NULL; } static void xdp_umem_unaccount_pages(struct xdp_umem *umem) { if (umem->user) { atomic_long_sub(umem->npgs, &umem->user->locked_vm); free_uid(umem->user); } } static void xdp_umem_addr_unmap(struct xdp_umem *umem) { vunmap(umem->addrs); umem->addrs = NULL; } static int xdp_umem_addr_map(struct xdp_umem *umem, struct page **pages, u32 nr_pages) { umem->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); if (!umem->addrs) return -ENOMEM; return 0; } static void xdp_umem_release(struct xdp_umem *umem) { umem->zc = false; ida_simple_remove(&umem_ida, umem->id); xdp_umem_addr_unmap(umem); xdp_umem_unpin_pages(umem); xdp_umem_unaccount_pages(umem); kfree(umem); } static void xdp_umem_release_deferred(struct work_struct *work) { struct xdp_umem *umem = container_of(work, struct xdp_umem, work); xdp_umem_release(umem); } void xdp_get_umem(struct xdp_umem *umem) { refcount_inc(&umem->users); } void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup) { if (!umem) return; if (refcount_dec_and_test(&umem->users)) { if (defer_cleanup) { INIT_WORK(&umem->work, xdp_umem_release_deferred); schedule_work(&umem->work); } else { xdp_umem_release(umem); } } } static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) { unsigned int gup_flags = FOLL_WRITE; long npgs; int err; umem->pgs = kvcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL | __GFP_NOWARN); if (!umem->pgs) return -ENOMEM; mmap_read_lock(current->mm); npgs = pin_user_pages(address, umem->npgs, gup_flags | FOLL_LONGTERM, &umem->pgs[0], NULL); mmap_read_unlock(current->mm); if (npgs != umem->npgs) { if (npgs >= 0) { umem->npgs = npgs; err = -ENOMEM; goto out_pin; } err = npgs; goto out_pgs; } return 0; out_pin: xdp_umem_unpin_pages(umem); out_pgs: kvfree(umem->pgs); umem->pgs = NULL; return err; } static int xdp_umem_account_pages(struct xdp_umem *umem) { unsigned long lock_limit, new_npgs, old_npgs; if (capable(CAP_IPC_LOCK)) return 0; lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; umem->user = get_uid(current_user()); do { old_npgs = atomic_long_read(&umem->user->locked_vm); new_npgs = old_npgs + umem->npgs; if (new_npgs > lock_limit) { free_uid(umem->user); umem->user = NULL; return -ENOBUFS; } } while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs, new_npgs) != old_npgs); return 0; } static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; u32 chunk_size = mr->chunk_size, headroom = mr->headroom; u64 addr = mr->addr, size = mr->len; u32 chunks_rem, npgs_rem; u64 chunks, npgs; int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { /* Strictly speaking we could support this, if: * - huge pages, or* * - using an IOMMU, or * - making sure the memory area is consecutive * but for now, we simply say "computer says no". */ return -EINVAL; } if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG) return -EINVAL; if (!unaligned_chunks && !is_power_of_2(chunk_size)) return -EINVAL; if (!PAGE_ALIGNED(addr)) { /* Memory area has to be page size aligned. For * simplicity, this might change. */ return -EINVAL; } if ((addr + size) < addr) return -EINVAL; npgs = div_u64_rem(size, PAGE_SIZE, &npgs_rem); if (npgs_rem) npgs++; if (npgs > U32_MAX) return -EINVAL; chunks = div_u64_rem(size, chunk_size, &chunks_rem); if (!chunks || chunks > U32_MAX) return -EINVAL; if (!unaligned_chunks && chunks_rem) return -EINVAL; if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; umem->size = size; umem->headroom = headroom; umem->chunk_size = chunk_size; umem->chunks = chunks; umem->npgs = npgs; umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); err = xdp_umem_account_pages(umem); if (err) return err; err = xdp_umem_pin_pages(umem, (unsigned long)addr); if (err) goto out_account; err = xdp_umem_addr_map(umem, umem->pgs, umem->npgs); if (err) goto out_unpin; return 0; out_unpin: xdp_umem_unpin_pages(umem); out_account: xdp_umem_unaccount_pages(umem); return err; } struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) { struct xdp_umem *umem; int err; umem = kzalloc(sizeof(*umem), GFP_KERNEL); if (!umem) return ERR_PTR(-ENOMEM); err = ida_simple_get(&umem_ida, 0, 0, GFP_KERNEL); if (err < 0) { kfree(umem); return ERR_PTR(err); } umem->id = err; err = xdp_umem_reg(umem, mr); if (err) { ida_simple_remove(&umem_ida, umem->id); kfree(umem); return ERR_PTR(err); } return umem; } |
| 126 11 226 86 89 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | #undef TRACE_SYSTEM #define TRACE_SYSTEM qdisc #if !defined(_TRACE_QDISC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_QDISC_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> #include <linux/pkt_sched.h> #include <net/sch_generic.h> TRACE_EVENT(qdisc_dequeue, TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, int packets, struct sk_buff *skb), TP_ARGS(qdisc, txq, packets, skb), TP_STRUCT__entry( __field( struct Qdisc *, qdisc ) __field(const struct netdev_queue *, txq ) __field( int, packets ) __field( void *, skbaddr ) __field( int, ifindex ) __field( u32, handle ) __field( u32, parent ) __field( unsigned long, txq_state) ), /* skb==NULL indicate packets dequeued was 0, even when packets==1 */ TP_fast_assign( __entry->qdisc = qdisc; __entry->txq = txq; __entry->packets = skb ? packets : 0; __entry->skbaddr = skb; __entry->ifindex = txq->dev ? txq->dev->ifindex : 0; __entry->handle = qdisc->handle; __entry->parent = qdisc->parent; __entry->txq_state = txq->state; ), TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%px", __entry->ifindex, __entry->handle, __entry->parent, __entry->txq_state, __entry->packets, __entry->skbaddr ) ); TRACE_EVENT(qdisc_enqueue, TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, struct sk_buff *skb), TP_ARGS(qdisc, txq, skb), TP_STRUCT__entry( __field(struct Qdisc *, qdisc) __field(const struct netdev_queue *, txq) __field(void *, skbaddr) __field(int, ifindex) __field(u32, handle) __field(u32, parent) ), TP_fast_assign( __entry->qdisc = qdisc; __entry->txq = txq; __entry->skbaddr = skb; __entry->ifindex = txq->dev ? txq->dev->ifindex : 0; __entry->handle = qdisc->handle; __entry->parent = qdisc->parent; ), TP_printk("enqueue ifindex=%d qdisc handle=0x%X parent=0x%X skbaddr=%px", __entry->ifindex, __entry->handle, __entry->parent, __entry->skbaddr) ); TRACE_EVENT(qdisc_reset, TP_PROTO(struct Qdisc *q), TP_ARGS(q), TP_STRUCT__entry( __string( dev, qdisc_dev(q) ? qdisc_dev(q)->name : "(null)" ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) ), TP_fast_assign( __assign_str(dev, qdisc_dev(q) ? qdisc_dev(q)->name : "(null)"); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; ), TP_printk("dev=%s kind=%s parent=%x:%x handle=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent), TC_H_MAJ(__entry->handle) >> 16, TC_H_MIN(__entry->handle)) ); TRACE_EVENT(qdisc_destroy, TP_PROTO(struct Qdisc *q), TP_ARGS(q), TP_STRUCT__entry( __string( dev, qdisc_dev(q)->name ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) ), TP_fast_assign( __assign_str(dev, qdisc_dev(q)->name); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; ), TP_printk("dev=%s kind=%s parent=%x:%x handle=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent), TC_H_MAJ(__entry->handle) >> 16, TC_H_MIN(__entry->handle)) ); TRACE_EVENT(qdisc_create, TP_PROTO(const struct Qdisc_ops *ops, struct net_device *dev, u32 parent), TP_ARGS(ops, dev, parent), TP_STRUCT__entry( __string( dev, dev->name ) __string( kind, ops->id ) __field( u32, parent ) ), TP_fast_assign( __assign_str(dev, dev->name); __assign_str(kind, ops->id); __entry->parent = parent; ), TP_printk("dev=%s kind=%s parent=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent)) ); #endif /* _TRACE_QDISC_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 4 341 13 10 322 40 5 300 79 340 339 285 129 325 72 338 49 341 13 346 348 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 | // SPDX-License-Identifier: GPL-2.0 /* * arch/x86_64/lib/csum-partial.c * * This file contains network checksum routines that are better done * in an architecture-specific manner due to speed. */ #include <linux/compiler.h> #include <linux/export.h> #include <asm/checksum.h> static inline unsigned short from32to16(unsigned a) { unsigned short b = a >> 16; asm("addw %w2,%w0\n\t" "adcw $0,%w0\n" : "=r" (b) : "0" (b), "r" (a)); return b; } /* * Do a 64-bit checksum on an arbitrary memory area. * Returns a 32bit checksum. * * This isn't as time critical as it used to be because many NICs * do hardware checksumming these days. * * Things tried and found to not make it faster: * Manual Prefetching * Unrolling to an 128 bytes inner loop. * Using interleaving with more registers to break the carry chains. */ static unsigned do_csum(const unsigned char *buff, unsigned len) { unsigned odd, count; unsigned long result = 0; if (unlikely(len == 0)) return result; odd = 1 & (unsigned long) buff; if (unlikely(odd)) { result = *buff << 8; len--; buff++; } count = len >> 1; /* nr of 16-bit words.. */ if (count) { if (2 & (unsigned long) buff) { result += *(unsigned short *)buff; count--; len -= 2; buff += 2; } count >>= 1; /* nr of 32-bit words.. */ if (count) { unsigned long zero; unsigned count64; if (4 & (unsigned long) buff) { result += *(unsigned int *) buff; count--; len -= 4; buff += 4; } count >>= 1; /* nr of 64-bit words.. */ /* main loop using 64byte blocks */ zero = 0; count64 = count >> 3; while (count64) { asm("addq 0*8(%[src]),%[res]\n\t" "adcq 1*8(%[src]),%[res]\n\t" "adcq 2*8(%[src]),%[res]\n\t" "adcq 3*8(%[src]),%[res]\n\t" "adcq 4*8(%[src]),%[res]\n\t" "adcq 5*8(%[src]),%[res]\n\t" "adcq 6*8(%[src]),%[res]\n\t" "adcq 7*8(%[src]),%[res]\n\t" "adcq %[zero],%[res]" : [res] "=r" (result) : [src] "r" (buff), [zero] "r" (zero), "[res]" (result)); buff += 64; count64--; } /* last up to 7 8byte blocks */ count %= 8; while (count) { asm("addq %1,%0\n\t" "adcq %2,%0\n" : "=r" (result) : "m" (*(unsigned long *)buff), "r" (zero), "0" (result)); --count; buff += 8; } result = add32_with_carry(result>>32, result&0xffffffff); if (len & 4) { result += *(unsigned int *) buff; buff += 4; } } if (len & 2) { result += *(unsigned short *) buff; buff += 2; } } if (len & 1) result += *buff; result = add32_with_carry(result>>32, result & 0xffffffff); if (unlikely(odd)) { result = from32to16(result); result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); } return result; } /* * computes the checksum of a memory block at buff, length len, * and adds in "sum" (32-bit) * * returns a 32-bit number suitable for feeding into itself * or csum_tcpudp_magic * * this function must be called with even lengths, except * for the last fragment, which may be odd * * it's best to have buff aligned on a 64-bit boundary */ __wsum csum_partial(const void *buff, int len, __wsum sum) { return (__force __wsum)add32_with_carry(do_csum(buff, len), (__force u32)sum); } EXPORT_SYMBOL(csum_partial); /* * this routine is used for miscellaneous IP-like checksums, mainly * in icmp.c */ __sum16 ip_compute_csum(const void *buff, int len) { return csum_fold(csum_partial(buff,len,0)); } EXPORT_SYMBOL(ip_compute_csum); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* net/atm/svc.c - ATM SVC sockets */ /* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__ #include <linux/string.h> #include <linux/net.h> /* struct socket, struct proto_ops */ #include <linux/errno.h> /* error codes */ #include <linux/kernel.h> /* printk */ #include <linux/skbuff.h> #include <linux/wait.h> #include <linux/sched/signal.h> #include <linux/fcntl.h> /* O_NONBLOCK */ #include <linux/init.h> #include <linux/atm.h> /* ATM stuff */ #include <linux/atmsap.h> #include <linux/atmsvc.h> #include <linux/atmdev.h> #include <linux/bitops.h> #include <net/sock.h> /* for sock_no_* */ #include <linux/uaccess.h> #include <linux/export.h> #include "resources.h" #include "common.h" /* common for PVCs and SVCs */ #include "signaling.h" #include "addr.h" static int svc_create(struct net *net, struct socket *sock, int protocol, int kern); /* * Note: since all this is still nicely synchronized with the signaling demon, * there's no need to protect sleep loops with clis. If signaling is * moved into the kernel, that would change. */ static int svc_shutdown(struct socket *sock, int how) { return 0; } static void svc_disconnect(struct atm_vcc *vcc) { DEFINE_WAIT(wait); struct sk_buff *skb; struct sock *sk = sk_atm(vcc); pr_debug("%p\n", vcc); if (test_bit(ATM_VF_REGIS, &vcc->flags)) { sigd_enq(vcc, as_close, NULL, NULL, NULL); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (test_bit(ATM_VF_RELEASED, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); } /* beware - socket is still in use by atmsigd until the last as_indicate has been answered */ while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { atm_return(vcc, skb->truesize); pr_debug("LISTEN REL\n"); sigd_enq2(NULL, as_reject, vcc, NULL, NULL, &vcc->qos, 0); dev_kfree_skb(skb); } clear_bit(ATM_VF_REGIS, &vcc->flags); /* ... may retry later */ } static int svc_release(struct socket *sock) { struct sock *sk = sock->sk; struct atm_vcc *vcc; if (sk) { vcc = ATM_SD(sock); pr_debug("%p\n", vcc); clear_bit(ATM_VF_READY, &vcc->flags); /* * VCC pointer is used as a reference, * so we must not free it (thereby subjecting it to re-use) * before all pending connections are closed */ svc_disconnect(vcc); vcc_release(sock); } return 0; } static int svc_bind(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct sockaddr_atmsvc *addr; struct atm_vcc *vcc; int error; if (sockaddr_len != sizeof(struct sockaddr_atmsvc)) return -EINVAL; lock_sock(sk); if (sock->state == SS_CONNECTED) { error = -EISCONN; goto out; } if (sock->state != SS_UNCONNECTED) { error = -EINVAL; goto out; } vcc = ATM_SD(sock); addr = (struct sockaddr_atmsvc *) sockaddr; if (addr->sas_family != AF_ATMSVC) { error = -EAFNOSUPPORT; goto out; } clear_bit(ATM_VF_BOUND, &vcc->flags); /* failing rebind will kill old binding */ /* @@@ check memory (de)allocation on rebind */ if (!test_bit(ATM_VF_HASQOS, &vcc->flags)) { error = -EBADFD; goto out; } vcc->local = *addr; set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_bind, NULL, NULL, &vcc->local); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); clear_bit(ATM_VF_REGIS, &vcc->flags); /* doesn't count */ if (!sigd) { error = -EUNATCH; goto out; } if (!sk->sk_err) set_bit(ATM_VF_BOUND, &vcc->flags); error = -sk->sk_err; out: release_sock(sk); return error; } static int svc_connect(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len, int flags) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct sockaddr_atmsvc *addr; struct atm_vcc *vcc = ATM_SD(sock); int error; pr_debug("%p\n", vcc); lock_sock(sk); if (sockaddr_len != sizeof(struct sockaddr_atmsvc)) { error = -EINVAL; goto out; } switch (sock->state) { default: error = -EINVAL; goto out; case SS_CONNECTED: error = -EISCONN; goto out; case SS_CONNECTING: if (test_bit(ATM_VF_WAITING, &vcc->flags)) { error = -EALREADY; goto out; } sock->state = SS_UNCONNECTED; if (sk->sk_err) { error = -sk->sk_err; goto out; } break; case SS_UNCONNECTED: addr = (struct sockaddr_atmsvc *) sockaddr; if (addr->sas_family != AF_ATMSVC) { error = -EAFNOSUPPORT; goto out; } if (!test_bit(ATM_VF_HASQOS, &vcc->flags)) { error = -EBADFD; goto out; } if (vcc->qos.txtp.traffic_class == ATM_ANYCLASS || vcc->qos.rxtp.traffic_class == ATM_ANYCLASS) { error = -EINVAL; goto out; } if (!vcc->qos.txtp.traffic_class && !vcc->qos.rxtp.traffic_class) { error = -EINVAL; goto out; } vcc->remote = *addr; set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_connect, NULL, NULL, &vcc->remote); if (flags & O_NONBLOCK) { sock->state = SS_CONNECTING; error = -EINPROGRESS; goto out; } error = 0; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { schedule(); if (!signal_pending(current)) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); continue; } pr_debug("*ABORT*\n"); /* * This is tricky: * Kernel ---close--> Demon * Kernel <--close--- Demon * or * Kernel ---close--> Demon * Kernel <--error--- Demon * or * Kernel ---close--> Demon * Kernel <--okay---- Demon * Kernel <--close--- Demon */ sigd_enq(vcc, as_close, NULL, NULL, NULL); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); schedule(); } if (!sk->sk_err) while (!test_bit(ATM_VF_RELEASED, &vcc->flags) && sigd) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); schedule(); } clear_bit(ATM_VF_REGIS, &vcc->flags); clear_bit(ATM_VF_RELEASED, &vcc->flags); clear_bit(ATM_VF_CLOSE, &vcc->flags); /* we're gone now but may connect later */ error = -EINTR; break; } finish_wait(sk_sleep(sk), &wait); if (error) goto out; if (!sigd) { error = -EUNATCH; goto out; } if (sk->sk_err) { error = -sk->sk_err; goto out; } } vcc->qos.txtp.max_pcr = SELECT_TOP_PCR(vcc->qos.txtp); vcc->qos.txtp.pcr = 0; vcc->qos.txtp.min_pcr = 0; error = vcc_connect(sock, vcc->itf, vcc->vpi, vcc->vci); if (!error) sock->state = SS_CONNECTED; else (void)svc_disconnect(vcc); out: release_sock(sk); return error; } static int svc_listen(struct socket *sock, int backlog) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int error; pr_debug("%p\n", vcc); lock_sock(sk); /* let server handle listen on unbound sockets */ if (test_bit(ATM_VF_SESSION, &vcc->flags)) { error = -EINVAL; goto out; } if (test_bit(ATM_VF_LISTEN, &vcc->flags)) { error = -EADDRINUSE; goto out; } set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_listen, NULL, NULL, &vcc->local); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); if (!sigd) { error = -EUNATCH; goto out; } set_bit(ATM_VF_LISTEN, &vcc->flags); vcc_insert_socket(sk); sk->sk_max_ack_backlog = backlog > 0 ? backlog : ATM_BACKLOG_DEFAULT; error = -sk->sk_err; out: release_sock(sk); return error; } static int svc_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct sock *sk = sock->sk; struct sk_buff *skb; struct atmsvc_msg *msg; struct atm_vcc *old_vcc = ATM_SD(sock); struct atm_vcc *new_vcc; int error; lock_sock(sk); error = svc_create(sock_net(sk), newsock, 0, kern); if (error) goto out; new_vcc = ATM_SD(newsock); pr_debug("%p -> %p\n", old_vcc, new_vcc); while (1) { DEFINE_WAIT(wait); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (!(skb = skb_dequeue(&sk->sk_receive_queue)) && sigd) { if (test_bit(ATM_VF_RELEASED, &old_vcc->flags)) break; if (test_bit(ATM_VF_CLOSE, &old_vcc->flags)) { error = -sk->sk_err; break; } if (flags & O_NONBLOCK) { error = -EAGAIN; break; } release_sock(sk); schedule(); lock_sock(sk); if (signal_pending(current)) { error = -ERESTARTSYS; break; } prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } finish_wait(sk_sleep(sk), &wait); if (error) goto out; if (!skb) { error = -EUNATCH; goto out; } msg = (struct atmsvc_msg *)skb->data; new_vcc->qos = msg->qos; set_bit(ATM_VF_HASQOS, &new_vcc->flags); new_vcc->remote = msg->svc; new_vcc->local = msg->local; new_vcc->sap = msg->sap; error = vcc_connect(newsock, msg->pvc.sap_addr.itf, msg->pvc.sap_addr.vpi, msg->pvc.sap_addr.vci); dev_kfree_skb(skb); sk_acceptq_removed(sk); if (error) { sigd_enq2(NULL, as_reject, old_vcc, NULL, NULL, &old_vcc->qos, error); error = error == -EAGAIN ? -EBUSY : error; goto out; } /* wait should be short, so we ignore the non-blocking flag */ set_bit(ATM_VF_WAITING, &new_vcc->flags); sigd_enq(new_vcc, as_accept, old_vcc, NULL, NULL); for (;;) { prepare_to_wait(sk_sleep(sk_atm(new_vcc)), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &new_vcc->flags) || !sigd) break; release_sock(sk); schedule(); lock_sock(sk); } finish_wait(sk_sleep(sk_atm(new_vcc)), &wait); if (!sigd) { error = -EUNATCH; goto out; } if (!sk_atm(new_vcc)->sk_err) break; if (sk_atm(new_vcc)->sk_err != ERESTARTSYS) { error = -sk_atm(new_vcc)->sk_err; goto out; } } newsock->state = SS_CONNECTED; out: release_sock(sk); return error; } static int svc_getname(struct socket *sock, struct sockaddr *sockaddr, int peer) { struct sockaddr_atmsvc *addr; addr = (struct sockaddr_atmsvc *) sockaddr; memcpy(addr, peer ? &ATM_SD(sock)->remote : &ATM_SD(sock)->local, sizeof(struct sockaddr_atmsvc)); return sizeof(struct sockaddr_atmsvc); } int svc_change_qos(struct atm_vcc *vcc, struct atm_qos *qos) { struct sock *sk = sk_atm(vcc); DEFINE_WAIT(wait); set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq2(vcc, as_modify, NULL, NULL, &vcc->local, qos, 0); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || test_bit(ATM_VF_RELEASED, &vcc->flags) || !sigd) { break; } schedule(); } finish_wait(sk_sleep(sk), &wait); if (!sigd) return -EUNATCH; return -sk->sk_err; } static int svc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int value, error = 0; lock_sock(sk); switch (optname) { case SO_ATMSAP: if (level != SOL_ATM || optlen != sizeof(struct atm_sap)) { error = -EINVAL; goto out; } if (copy_from_sockptr(&vcc->sap, optval, optlen)) { error = -EFAULT; goto out; } set_bit(ATM_VF_HASSAP, &vcc->flags); break; case SO_MULTIPOINT: if (level != SOL_ATM || optlen != sizeof(int)) { error = -EINVAL; goto out; } if (copy_from_sockptr(&value, optval, sizeof(int))) { error = -EFAULT; goto out; } if (value == 1) set_bit(ATM_VF_SESSION, &vcc->flags); else if (value == 0) clear_bit(ATM_VF_SESSION, &vcc->flags); else error = -EINVAL; break; default: error = vcc_setsockopt(sock, level, optname, optval, optlen); } out: release_sock(sk); return error; } static int svc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int error = 0, len; lock_sock(sk); if (!__SO_LEVEL_MATCH(optname, level) || optname != SO_ATMSAP) { error = vcc_getsockopt(sock, level, optname, optval, optlen); goto out; } if (get_user(len, optlen)) { error = -EFAULT; goto out; } if (len != sizeof(struct atm_sap)) { error = -EINVAL; goto out; } if (copy_to_user(optval, &ATM_SD(sock)->sap, sizeof(struct atm_sap))) { error = -EFAULT; goto out; } out: release_sock(sk); return error; } static int svc_addparty(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len, int flags) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int error; lock_sock(sk); set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_addparty, NULL, NULL, (struct sockaddr_atmsvc *) sockaddr); if (flags & O_NONBLOCK) { error = -EINPROGRESS; goto out; } pr_debug("added wait queue\n"); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); error = -xchg(&sk->sk_err_soft, 0); out: release_sock(sk); return error; } static int svc_dropparty(struct socket *sock, int ep_ref) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int error; lock_sock(sk); set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq2(vcc, as_dropparty, NULL, NULL, NULL, NULL, ep_ref); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); if (!sigd) { error = -EUNATCH; goto out; } error = -xchg(&sk->sk_err_soft, 0); out: release_sock(sk); return error; } static int svc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int error, ep_ref; struct sockaddr_atmsvc sa; struct atm_vcc *vcc = ATM_SD(sock); switch (cmd) { case ATM_ADDPARTY: if (!test_bit(ATM_VF_SESSION, &vcc->flags)) return -EINVAL; if (copy_from_user(&sa, (void __user *) arg, sizeof(sa))) return -EFAULT; error = svc_addparty(sock, (struct sockaddr *)&sa, sizeof(sa), 0); break; case ATM_DROPPARTY: if (!test_bit(ATM_VF_SESSION, &vcc->flags)) return -EINVAL; if (copy_from_user(&ep_ref, (void __user *) arg, sizeof(int))) return -EFAULT; error = svc_dropparty(sock, ep_ref); break; default: error = vcc_ioctl(sock, cmd, arg); } return error; } #ifdef CONFIG_COMPAT static int svc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { /* The definition of ATM_ADDPARTY uses the size of struct atm_iobuf. But actually it takes a struct sockaddr_atmsvc, which doesn't need compat handling. So all we have to do is fix up cmd... */ if (cmd == COMPAT_ATM_ADDPARTY) cmd = ATM_ADDPARTY; if (cmd == ATM_ADDPARTY || cmd == ATM_DROPPARTY) return svc_ioctl(sock, cmd, arg); else return vcc_compat_ioctl(sock, cmd, arg); } #endif /* CONFIG_COMPAT */ static const struct proto_ops svc_proto_ops = { .family = PF_ATMSVC, .owner = THIS_MODULE, .release = svc_release, .bind = svc_bind, .connect = svc_connect, .socketpair = sock_no_socketpair, .accept = svc_accept, .getname = svc_getname, .poll = vcc_poll, .ioctl = svc_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = svc_compat_ioctl, #endif .gettstamp = sock_gettstamp, .listen = svc_listen, .shutdown = svc_shutdown, .setsockopt = svc_setsockopt, .getsockopt = svc_getsockopt, .sendmsg = vcc_sendmsg, .recvmsg = vcc_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; static int svc_create(struct net *net, struct socket *sock, int protocol, int kern) { int error; if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; sock->ops = &svc_proto_ops; error = vcc_create(net, sock, protocol, AF_ATMSVC, kern); if (error) return error; ATM_SD(sock)->local.sas_family = AF_ATMSVC; ATM_SD(sock)->remote.sas_family = AF_ATMSVC; return 0; } static const struct net_proto_family svc_family_ops = { .family = PF_ATMSVC, .create = svc_create, .owner = THIS_MODULE, }; /* * Initialize the ATM SVC protocol family */ int __init atmsvc_init(void) { return sock_register(&svc_family_ops); } void atmsvc_exit(void) { sock_unregister(PF_ATMSVC); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MLD_H #define LINUX_MLD_H #include <linux/in6.h> #include <linux/icmpv6.h> /* MLDv1 Query/Report/Done */ struct mld_msg { struct icmp6hdr mld_hdr; struct in6_addr mld_mca; }; #define mld_type mld_hdr.icmp6_type #define mld_code mld_hdr.icmp6_code #define mld_cksum mld_hdr.icmp6_cksum #define mld_maxdelay mld_hdr.icmp6_maxdelay #define mld_reserved mld_hdr.icmp6_dataun.un_data16[1] /* Multicast Listener Discovery version 2 headers */ /* MLDv2 Report */ struct mld2_grec { __u8 grec_type; __u8 grec_auxwords; __be16 grec_nsrcs; struct in6_addr grec_mca; struct in6_addr grec_src[]; }; struct mld2_report { struct icmp6hdr mld2r_hdr; struct mld2_grec mld2r_grec[]; }; #define mld2r_type mld2r_hdr.icmp6_type #define mld2r_resv1 mld2r_hdr.icmp6_code #define mld2r_cksum mld2r_hdr.icmp6_cksum #define mld2r_resv2 mld2r_hdr.icmp6_dataun.un_data16[0] #define mld2r_ngrec mld2r_hdr.icmp6_dataun.un_data16[1] /* MLDv2 Query */ struct mld2_query { struct icmp6hdr mld2q_hdr; struct in6_addr mld2q_mca; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 mld2q_qrv:3, mld2q_suppress:1, mld2q_resv2:4; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 mld2q_resv2:4, mld2q_suppress:1, mld2q_qrv:3; #else #error "Please fix <asm/byteorder.h>" #endif __u8 mld2q_qqic; __be16 mld2q_nsrcs; struct in6_addr mld2q_srcs[]; }; #define mld2q_type mld2q_hdr.icmp6_type #define mld2q_code mld2q_hdr.icmp6_code #define mld2q_cksum mld2q_hdr.icmp6_cksum #define mld2q_mrc mld2q_hdr.icmp6_maxdelay #define mld2q_resv1 mld2q_hdr.icmp6_dataun.un_data16[1] /* RFC3810, 5.1.3. Maximum Response Code: * * If Maximum Response Code >= 32768, Maximum Response Code represents a * floating-point value as follows: * * 0 1 2 3 4 5 6 7 8 9 A B C D E F * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |1| exp | mant | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ #define MLDV2_MRC_EXP(value) (((value) >> 12) & 0x0007) #define MLDV2_MRC_MAN(value) ((value) & 0x0fff) /* RFC3810, 5.1.9. QQIC (Querier's Query Interval Code): * * If QQIC >= 128, QQIC represents a floating-point value as follows: * * 0 1 2 3 4 5 6 7 * +-+-+-+-+-+-+-+-+ * |1| exp | mant | * +-+-+-+-+-+-+-+-+ */ #define MLDV2_QQIC_EXP(value) (((value) >> 4) & 0x07) #define MLDV2_QQIC_MAN(value) ((value) & 0x0f) #define MLD_EXP_MIN_LIMIT 32768UL #define MLDV1_MRD_MAX_COMPAT (MLD_EXP_MIN_LIMIT - 1) #define MLD_MAX_QUEUE 8 #define MLD_MAX_SKBS 32 static inline unsigned long mldv2_mrc(const struct mld2_query *mlh2) { /* RFC3810, 5.1.3. Maximum Response Code */ unsigned long ret, mc_mrc = ntohs(mlh2->mld2q_mrc); if (mc_mrc < MLD_EXP_MIN_LIMIT) { ret = mc_mrc; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_MRC_EXP(mc_mrc); mc_man = MLDV2_MRC_MAN(mc_mrc); ret = (mc_man | 0x1000) << (mc_exp + 3); } return ret; } #endif |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/include/linux/jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com> * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved * * Definitions for transaction data structures for the buffer cache * filesystem journaling support. */ #ifndef _LINUX_JBD2_H #define _LINUX_JBD2_H /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ #include "jfs_compat.h" #define JBD2_DEBUG #else #include <linux/types.h> #include <linux/buffer_head.h> #include <linux/journal-head.h> #include <linux/stddef.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> #include <linux/bit_spinlock.h> #include <linux/blkdev.h> #include <crypto/hash.h> #endif #define journal_oom_retry 1 /* * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext4 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on * known-good hardware we may want to trap these errors. */ #undef JBD2_PARANOID_IOFAIL /* * The default maximum commit age, in seconds. */ #define JBD2_DEFAULT_MAX_COMMIT_AGE 5 #ifdef CONFIG_JBD2_DEBUG /* * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING extern ushort jbd2_journal_enable_debug; void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); #define jbd2_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else #define jbd2_debug(n, fmt, a...) no_printk(fmt, ##a) #endif extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 #define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256 #ifdef __KERNEL__ /** * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. * * All filesystem modifications made by the process go * through this handle. Recursive operations (such as quota operations) * are gathered into a single update. * * The buffer credits field is used to account for journaled buffers * being modified by the running process. To ensure that there is * enough log space for all outstanding operations, we need to limit the * number of outstanding buffers possible at any time. When the * operation completes, any buffer credits not used are credited back to * the transaction, so that at all times we know how many buffers the * outstanding updates on a transaction might possibly touch. * * This is an opaque datatype. **/ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ /** * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. * * journal_t is linked to from the fs superblock structure. * * We use the journal_t to keep track of all outstanding transaction * activity on the filesystem, and to manage the state of the log * writing process. * * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ #endif /* * Internal structures used by the logging mechanism: */ #define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ /* * On-disk structures */ /* * Descriptor block types: */ #define JBD2_DESCRIPTOR_BLOCK 1 #define JBD2_COMMIT_BLOCK 2 #define JBD2_SUPERBLOCK_V1 3 #define JBD2_SUPERBLOCK_V2 4 #define JBD2_REVOKE_BLOCK 5 /* * Standard header for all descriptor blocks: */ typedef struct journal_header_s { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; } journal_header_t; /* * Checksum types. */ #define JBD2_CRC32_CHKSUM 1 #define JBD2_MD5_CHKSUM 2 #define JBD2_SHA1_CHKSUM 3 #define JBD2_CRC32C_CHKSUM 4 #define JBD2_CRC32_CHKSUM_SIZE 4 #define JBD2_CHECKSUM_BYTES (32 / sizeof(u32)) /* * Commit block header for storing transactional checksums: * * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum* * fields are used to store a checksum of the descriptor and data blocks. * * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum * field is used to store crc32c(uuid+commit_block). Each journal metadata * block gets its own checksum, and data block checksums are stored in * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses * journal_block_tag3_t to store a full 32-bit checksum. Everything else * is the same as v2. * * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; unsigned char h_chksum_type; unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; __be64 h_commit_sec; __be32 h_commit_nsec; }; /* * The block tag: used to describe a single buffer in the journal. * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ typedef struct journal_block_tag3_s { __be32 t_blocknr; /* The on-disk block number */ __be32 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ __be32 t_checksum; /* crc32c(uuid+seq+block) */ } journal_block_tag3_t; typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ __be16 t_checksum; /* truncated crc32c(uuid+seq+block) */ __be16 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; /* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; /* * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log */ typedef struct jbd2_journal_revoke_header_s { journal_header_t r_header; __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ #define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ #define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ /* * The journal superblock. All fields are in big-endian byte order. */ typedef struct journal_superblock_s { /* 0x0000 */ journal_header_t s_header; /* 0x000C */ /* Static information describing the journal */ __be32 s_blocksize; /* journal device blocksize */ __be32 s_maxlen; /* total blocks in journal file */ __be32 s_first; /* first block of log information */ /* 0x0018 */ /* Dynamic information describing the current state of the log */ __be32 s_sequence; /* first commit ID expected in log */ __be32 s_start; /* blocknr of start of log */ /* 0x0020 */ /* Error value, as set by jbd2_journal_abort(). */ __be32 s_errno; /* 0x0024 */ /* Remaining fields are only valid in a version-2 superblock */ __be32 s_feature_compat; /* compatible feature set */ __be32 s_feature_incompat; /* incompatible feature set */ __be32 s_feature_ro_compat; /* readonly-compatible feature set */ /* 0x0030 */ __u8 s_uuid[16]; /* 128-bit uuid for journal */ /* 0x0040 */ __be32 s_nr_users; /* Nr of filesystems sharing log */ __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ /* 0x0048 */ __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ __be32 s_max_trans_data; /* Limit of data blocks per trans. */ /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; /* 0x0054 */ __be32 s_num_fc_blks; /* Number of fast commit blocks */ /* 0x0058 */ __u32 s_padding[41]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ /* 0x0400 */ } journal_superblock_t; /* Use the jbd2_{has,set,clear}_feature_* helpers; these will be removed */ #define JBD2_HAS_COMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask)))) #define JBD2_HAS_RO_COMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask)))) #define JBD2_HAS_INCOMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) #define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 #define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 /* See "journal feature predicate functions" below */ /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ #include <linux/fs.h> #include <linux/sched.h> enum jbd_state_bits { BH_JBD /* Has an attached ext3 journal_head */ = BH_PrivateStart, BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ BH_Freed, /* Has been freed (truncated) */ BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ BH_JBDPrivateStart, /* First bit available for private use by FS */ }; BUFFER_FNS(JBD, jbd) BUFFER_FNS(JWrite, jwrite) BUFFER_FNS(JBDDirty, jbddirty) TAS_BUFFER_FNS(JBDDirty, jbddirty) BUFFER_FNS(Revoked, revoked) TAS_BUFFER_FNS(Revoked, revoked) BUFFER_FNS(RevokeValid, revokevalid) TAS_BUFFER_FNS(RevokeValid, revokevalid) BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; } static inline struct journal_head *bh2jh(struct buffer_head *bh) { return bh->b_private; } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { bit_spin_lock(BH_JournalHead, &bh->b_state); } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { bit_spin_unlock(BH_JournalHead, &bh->b_state); } #define J_ASSERT(assert) BUG_ON(!(assert)) #define J_ASSERT_BH(bh, expr) J_ASSERT(expr) #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) #define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) #else #define __journal_expect(expr, why...) \ ({ \ int val = (expr); \ if (!val) { \ printk(KERN_ERR \ "JBD2 unexpected failure: %s: %s;\n", \ __func__, #expr); \ printk(KERN_ERR why "\n"); \ } \ val; \ }) #define J_EXPECT(expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) #endif /* Flags in jbd_inode->i_flags */ #define __JI_COMMIT_RUNNING 0 #define __JI_WRITE_DATA 1 #define __JI_WAIT_DATA 2 /* * Commit of the inode data in progress. We use this flag to protect us from * concurrent deletion of inode. We cannot use reference to inode for this * since we cannot afford doing last iput() on behalf of kjournald */ #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) /* Write allocated dirty buffers in this inode before commit */ #define JI_WRITE_DATA (1 << __JI_WRITE_DATA) /* Wait for outstanding data writes for this inode before commit */ #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { /** * @i_transaction: * * Which transaction does this inode belong to? Either the running * transaction or the committing one. [j_list_lock] */ transaction_t *i_transaction; /** * @i_next_transaction: * * Pointer to the running transaction modifying inode's data in case * there is already a committing transaction touching it. [j_list_lock] */ transaction_t *i_next_transaction; /** * @i_list: List of inodes in the i_transaction [j_list_lock] */ struct list_head i_list; /** * @i_vfs_inode: * * VFS inode this inode belongs to [constant for lifetime of structure] */ struct inode *i_vfs_inode; /** * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; /** * @i_dirty_start: * * Offset in bytes where the dirty range for this inode starts. * [j_list_lock] */ loff_t i_dirty_start; /** * @i_dirty_end: * * Inclusive offset in bytes where the dirty range for this inode * ends. [j_list_lock] */ loff_t i_dirty_end; }; struct jbd2_revoke_table_s; /** * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. * @h_sync: Flag for sync-on-close. * @h_jdata: Flag to force data journaling. * @h_reserved: Flag for handle for reserved credits. * @h_aborted: Flag indicating fatal error on handle. * @h_type: For handle statistics. * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. * @h_requested_credits: Holds @h_total_credits after handle is started. * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation * in so it can be fixed later. */ struct jbd2_journal_handle { union { transaction_t *h_transaction; /* Which journal handle belongs to - used iff h_reserved set */ journal_t *h_journal; }; handle_t *h_rsv_handle; int h_total_credits; int h_revoke_credits; int h_revoke_credits_requested; int h_ref; int h_err; /* Flags [no locking] */ unsigned int h_sync: 1; unsigned int h_jdata: 1; unsigned int h_reserved: 1; unsigned int h_aborted: 1; unsigned int h_type: 8; unsigned int h_line_no: 16; unsigned long h_start_jiffies; unsigned int h_requested_credits; unsigned int saved_alloc_context; }; /* * Some stats for checkpoint phase */ struct transaction_chp_stats_s { unsigned long cs_chp_time; __u32 cs_forced_to_close; __u32 cs_written; __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It * tracks a compound transaction through its various states: * * RUNNING: accepting new updates * LOCKED: Updates still running but we don't accept new ones * RUNDOWN: Updates are tidying up but have finished requesting * new buffers to modify (state not used for now) * FLUSH: All updates complete, but we are still writing to disk * COMMIT: All data on disk, writing commit record * FINISHED: We still have to keep the transaction for checkpointing. * * The transaction keeps track of all of the buffers modified by a * running transaction, and all of the buffers committed but not yet * flushed to home for finished transactions. * (Locking Documentation improved by LockDoc) */ /* * Lock ranking: * * j_list_lock * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock * ->b_state_lock * * b_state_lock * ->j_list_lock * * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ struct transaction_s { /* Pointer to the journal for this transaction. [no locking] */ journal_t *t_journal; /* Sequence number for this transaction [no locking] */ tid_t t_tid; /* * Transaction's current state * [no locking - only kjournald2 alters this] * [j_list_lock] guards transition of a transaction into T_FINISHED * state and subsequent call of __jbd2_journal_drop_transaction() * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ enum { T_RUNNING, T_LOCKED, T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, T_COMMIT_CALLBACK, T_FINISHED } t_state; /* * Where in the log does this transaction's commit start? [no locking] */ unsigned long t_log_start; /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet * modified by this transaction [j_list_lock, no locks needed fo * jbd2 thread] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock, no locks needed for jbd2 thread] */ struct journal_head *t_buffers; /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) * [j_list_lock] */ struct journal_head *t_forget; /* * Doubly-linked circular list of all buffers still to be flushed before * this transaction can be checkpointed. [j_list_lock] */ struct journal_head *t_checkpoint_list; /* * Doubly-linked circular list of metadata buffers being * shadowed by log IO. The IO buffers on the iobuf list and * the shadow buffers on this list match each other one for * one at all times. [j_list_lock, no locks needed for jbd2 * thread] */ struct journal_head *t_shadow_list; /* * List of inodes associated with the transaction; e.g., ext4 uses * this to track inodes in data=ordered and data=journal mode that * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; /* * Protects info related to handles */ spinlock_t t_handle_lock; /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; /* * When transaction started */ unsigned long t_start; /* * When commit was requested [j_state_lock] */ unsigned long t_requested; /* * Checkpointing stats [j_list_lock] */ struct transaction_chp_stats_s t_chp_stats; /* * Number of outstanding updates running on this transaction * [none] */ atomic_t t_updates; /* * Number of blocks reserved for this transaction in the journal. * This is including all credits reserved when starting transaction * handles as well as all journal descriptor blocks needed for this * transaction. [none] */ atomic_t t_outstanding_credits; /* * Number of revoke records for this transaction added by already * stopped handles. [none] */ atomic_t t_outstanding_revokes; /* * How many handles used this transaction? [none] */ atomic_t t_handle_count; /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] */ transaction_t *t_cpnext, *t_cpprev; /* * When will the transaction expire (become due for commit), in jiffies? * [no locking] */ unsigned long t_expires; /* * When this transaction started, in nanoseconds [no locking] */ ktime_t t_start_time; /* * This transaction is being forced and some process is * waiting for it to finish. */ unsigned int t_synchronous_commit:1; /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; /* * For use by the filesystem to store fs-specific data * structures associated with the transaction */ struct list_head t_private_list; }; struct transaction_run_stats_s { unsigned long rs_wait; unsigned long rs_request_delay; unsigned long rs_running; unsigned long rs_locked; unsigned long rs_flushing; unsigned long rs_logging; __u32 rs_handle_count; __u32 rs_blocks; __u32 rs_blocks_logged; }; struct transaction_stats_s { unsigned long ts_tid; unsigned long ts_requested; struct transaction_run_stats_s run; }; static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { if (end >= start) return end - start; return end + (MAX_JIFFY_OFFSET - start); } #define JBD2_NR_BATCH 64 enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; #define JBD2_FC_REPLAY_STOP 0 #define JBD2_FC_REPLAY_CONTINUE 1 /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. */ struct journal_s { /** * @j_flags: General journaling state flags [j_state_lock, * no lock for quick racy checks] */ unsigned long j_flags; /** * @j_atomic_flags: Atomic journaling state flags. */ unsigned long j_atomic_flags; /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior * abort)? [j_state_lock] */ int j_errno; /** * @j_abort_mutex: Lock the whole aborting procedure. */ struct mutex j_abort_mutex; /** * @j_sb_buffer: The first part of the superblock buffer. */ struct buffer_head *j_sb_buffer; /** * @j_superblock: The second part of the superblock buffer. */ journal_superblock_t *j_superblock; /** * @j_format_version: Version of the superblock format. */ int j_format_version; /** * @j_state_lock: Protect the various scalars in the journal. */ rwlock_t j_state_lock; /** * @j_barrier_count: * * Number of processes waiting to create a barrier lock [j_state_lock, * no lock for quick racy checks] */ int j_barrier_count; /** * @j_barrier: The barrier lock itself. */ struct mutex j_barrier; /** * @j_running_transaction: * * Transactions: The current running transaction... * [j_state_lock, no lock for quick racy checks] [caller holding * open handle] */ transaction_t *j_running_transaction; /** * @j_committing_transaction: * * the transaction we are pushing to disk * [j_state_lock] [caller holding open handle] */ transaction_t *j_committing_transaction; /** * @j_checkpoint_transactions: * * ... and a linked circular list of all transactions waiting for * checkpointing. [j_list_lock] */ transaction_t *j_checkpoint_transactions; /** * @j_wait_transaction_locked: * * Wait queue for waiting for a locked transaction to start committing, * or for a barrier lock to be released. */ wait_queue_head_t j_wait_transaction_locked; /** * @j_wait_done_commit: Wait queue for waiting for commit to complete. */ wait_queue_head_t j_wait_done_commit; /** * @j_wait_commit: Wait queue to trigger commit. */ wait_queue_head_t j_wait_commit; /** * @j_wait_updates: Wait queue to wait for updates to complete. */ wait_queue_head_t j_wait_updates; /** * @j_wait_reserved: * * Wait queue to wait for reserved buffer credits to drop. */ wait_queue_head_t j_wait_reserved; /** * @j_fc_wait: * * Wait queue to wait for completion of async fast commits. */ wait_queue_head_t j_fc_wait; /** * @j_checkpoint_mutex: * * Semaphore for locking against concurrent checkpoints. */ struct mutex j_checkpoint_mutex; /** * @j_chkpt_bhs: * * List of buffer heads used by the checkpoint routine. This * was moved from jbd2_log_do_checkpoint() to reduce stack * usage. Access to this array is controlled by the * @j_checkpoint_mutex. [j_checkpoint_mutex] */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; /** * @j_shrinker: * * Journal head shrinker, reclaim buffer's journal head which * has been written back. */ struct shrinker j_shrinker; /** * @j_checkpoint_jh_count: * * Number of journal buffers on the checkpoint list. [j_list_lock] */ struct percpu_counter j_checkpoint_jh_count; /** * @j_shrink_transaction: * * Record next transaction will shrink on the checkpoint list. * [j_list_lock] */ transaction_t *j_shrink_transaction; /** * @j_head: * * Journal head: identifies the first unused block in the journal. * [j_state_lock] */ unsigned long j_head; /** * @j_tail: * * Journal tail: identifies the oldest still-used block in the journal. * [j_state_lock] */ unsigned long j_tail; /** * @j_free: * * Journal free: how many free blocks are there in the journal? * [j_state_lock] */ unsigned long j_free; /** * @j_first: * * The block number of the first usable block in the journal * [j_state_lock]. */ unsigned long j_first; /** * @j_last: * * The block number one beyond the last usable block in the journal * [j_state_lock]. */ unsigned long j_last; /** * @j_fc_first: * * The block number of the first fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_first; /** * @j_fc_off: * * Number of fast commit blocks currently allocated. Accessed only * during fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ unsigned long j_fc_off; /** * @j_fc_last: * * The block number one beyond the last fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_last; /** * @j_dev: Device where we store the journal. */ struct block_device *j_dev; /** * @j_blocksize: Block size for the location where we store the journal. */ int j_blocksize; /** * @j_blk_offset: * * Starting block offset into the device where we store the journal. */ unsigned long long j_blk_offset; /** * @j_devname: Journal device name. */ char j_devname[BDEVNAME_SIZE+24]; /** * @j_fs_dev: * * Device which holds the client fs. For internal journal this will be * equal to j_dev. */ struct block_device *j_fs_dev; /** * @j_total_len: Total maximum capacity of the journal region on disk. */ unsigned int j_total_len; /** * @j_reserved_credits: * * Number of buffers reserved from the running transaction. */ atomic_t j_reserved_credits; /** * @j_list_lock: Protects the buffer lists and internal buffer state. */ spinlock_t j_list_lock; /** * @j_inode: * * Optional inode where we store the journal. If present, all * journal block numbers are mapped into this inode via bmap(). */ struct inode *j_inode; /** * @j_tail_sequence: * * Sequence number of the oldest transaction in the log [j_state_lock] */ tid_t j_tail_sequence; /** * @j_transaction_sequence: * * Sequence number of the next transaction to grant [j_state_lock] */ tid_t j_transaction_sequence; /** * @j_commit_sequence: * * Sequence number of the most recently committed transaction * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_sequence; /** * @j_commit_request: * * Sequence number of the most recent transaction wanting commit * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_request; /** * @j_uuid: * * Journal uuid: identifies the object (filesystem, LVM volume etc) * backed by this journal. This will eventually be replaced by an array * of uuids, allowing us to index multiple devices within a single * journal and to perform atomic updates across them. */ __u8 j_uuid[16]; /** * @j_task: Pointer to the current commit thread for this journal. */ struct task_struct *j_task; /** * @j_max_transaction_buffers: * * Maximum number of metadata buffers to allow in a single compound * commit transaction. */ int j_max_transaction_buffers; /** * @j_revoke_records_per_block: * * Number of revoke records that fit in one descriptor block. */ int j_revoke_records_per_block; /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? */ unsigned long j_commit_interval; /** * @j_commit_timer: The timer used to wakeup the commit thread. */ struct timer_list j_commit_timer; /** * @j_revoke_lock: Protect the revoke table. */ spinlock_t j_revoke_lock; /** * @j_revoke: * * The revoke table - maintains the list of revoked blocks in the * current transaction. */ struct jbd2_revoke_table_s *j_revoke; /** * @j_revoke_table: Alternate revoke tables for j_revoke. */ struct jbd2_revoke_table_s *j_revoke_table[2]; /** * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction. */ struct buffer_head **j_wbuf; /** * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only * during a fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; /** * @j_wbufsize: * * Size of @j_wbuf array. */ int j_wbufsize; /** * @j_fc_wbufsize: * * Size of @j_fc_wbuf array. */ int j_fc_wbufsize; /** * @j_last_sync_writer: * * The pid of the last person to run a synchronous operation * through the journal. */ pid_t j_last_sync_writer; /** * @j_average_commit_time: * * The average amount of time in nanoseconds it takes to commit a * transaction to disk. [j_state_lock] */ u64 j_average_commit_time; /** * @j_min_batch_time: * * Minimum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_min_batch_time; /** * @j_max_batch_time: * * Maximum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_max_batch_time; /** * @j_commit_callback: * * This function is called when a transaction is closed. */ void (*j_commit_callback)(journal_t *, transaction_t *); /** * @j_submit_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WRITE_DATA flag * before we start to write out the transaction to the journal. */ int (*j_submit_inode_data_buffers) (struct jbd2_inode *); /** * @j_finish_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WAIT_DATA flag * after we have written the transaction to the journal * but before we write out the commit block. */ int (*j_finish_inode_data_buffers) (struct jbd2_inode *); /* * Journal statistics */ /** * @j_history_lock: Protect the transactions statistics history. */ spinlock_t j_history_lock; /** * @j_proc_entry: procfs entry for the jbd statistics directory. */ struct proc_dir_entry *j_proc_entry; /** * @j_stats: Overall statistics. */ struct transaction_stats_s j_stats; /** * @j_failed_commit: Failed journal commit ID. */ unsigned int j_failed_commit; /** * @j_private: * * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here. */ void *j_private; /** * @j_chksum_driver: * * Reference to checksum algorithm driver via cryptoapi. */ struct crypto_shash *j_chksum_driver; /** * @j_csum_seed: * * Precomputed journal UUID checksum for seeding other checksums. */ __u32 j_csum_seed; #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * @j_trans_commit_map: * * Lockdep entity to track transaction commit dependencies. Handles * hold this "lock" for read, when we wait for commit, we acquire the * "lock" for writing. This matches the properties of jbd2 journalling * where the running transaction has to wait for all handles to be * dropped to commit that transaction and also acquiring a handle may * require transaction commit to finish. */ struct lockdep_map j_trans_commit_map; #endif /** * @j_fc_cleanup_callback: * * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: * * File-system specific function that performs replay of a fast * commit. JBD2 calls this function for each fast commit block found in * the journal. This function should return JBD2_FC_REPLAY_CONTINUE * to indicate that the block was processed correctly and more fast * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP * indicates the end of replay (no more blocks remaining). A negative * return value indicates error. */ int (*j_fc_replay_callback)(struct journal_s *journal, struct buffer_head *bh, enum passtype pass, int off, tid_t expected_commit_id); }; #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ } while (0) /* journal feature predicate functions */ #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_compat & \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat |= \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat &= \ ~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } #define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_ro_compat & \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat |= \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat &= \ ~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } #define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_incompat & \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat |= \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat &= \ ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } JBD2_FEATURE_COMPAT_FUNCS(checksum, CHECKSUM) JBD2_FEATURE_INCOMPAT_FUNCS(revoke, REVOKE) JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) /* * Journal flag definitions */ #define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ #define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ #define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ #define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ #define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ #define JBD2_BARRIER 0x020 /* Use IDE barriers */ #define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file * data write error in ordered * mode */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ #define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 #define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 #define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ JBD2_JOURNAL_FLUSH_ZEROOUT) /* * Journal atomic flag definitions */ #define JBD2_CHECKPOINT_IO_ERROR 0x001 /* Detect io error while writing * buffer back to disk */ /* * Function declarations for the journaling transaction and buffer * management */ /* Filing buffers */ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void __journal_free_buffer(struct journal_head *bh); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void __journal_clean_data_list(transaction_t *transaction); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); } static inline void jbd2_unfile_log_bh(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); } /* Log buffer allocation */ struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); /* * Triggers */ struct jbd2_buffer_trigger_type { /* * Fired a the moment data to write to the journal are known to be * stable - so either at the moment b_frozen_data is created or just * before a buffer is written to the journal. mapped_data is a mapped * buffer that is the frozen data for commit. */ void (*t_frozen)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size); /* * Fired during journal abort for dirty buffers that will not be * committed. */ void (*t_abort)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh); }; extern void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers); extern void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers); /* Buffer IO */ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr); /* Transaction locking */ extern void __wait_on_journal (journal_t *); /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); extern void jbd2_journal_free_transaction(transaction_t *); /* * Journal locking. * * We need to lock the journal during transaction state changes so that nobody * ever tries to take a handle on the running transaction while we are in the * middle of moving it to the commit phase. j_state_lock does this. * * Note that the locking is completely interrupt unsafe. We never touch * journal structures from interrupts. */ static inline handle_t *journal_current_handle(void) { return current->journal_info; } /* The journaling code user interface: * * Create and destroy handles * Register buffer modifications against the current transaction. */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, int revoke_records, gfp_t gfp_mask, unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); extern int jbd2__journal_restart(handle_t *, int nblocks, int revoke_records, gfp_t gfp_mask); extern int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no); extern void jbd2_journal_free_reserved(handle_t *handle); extern int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); void jbd2_journal_wait_updates(journal_t *); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); extern journal_t * jbd2_journal_init_inode (struct inode *); extern int jbd2_journal_update_format (journal_t *); extern int jbd2_journal_check_used_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, int); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_inode_ranged_write(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_submit_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_finish_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode); /* * journal_head management */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* * handle management */ extern struct kmem_cache *jbd2_handle_cache; static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags) { return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags); } static inline void jbd2_free_handle(handle_t *handle) { kmem_cache_free(jbd2_handle_cache, handle); } /* * jbd2_inode management (optional, for those file systems that want to use * dynamically allocated jbd2_inode structures) */ extern struct kmem_cache *jbd2_inode_cache; static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags) { return kmem_cache_alloc(jbd2_inode_cache, gfp_flags); } static inline void jbd2_free_inode(struct jbd2_inode *jinode) { kmem_cache_free(jbd2_inode_cache, jinode); } /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 extern int jbd2_journal_init_revoke(journal_t *, int); extern void jbd2_journal_destroy_revoke_record_cache(void); extern void jbd2_journal_destroy_revoke_table_cache(void); extern int __init jbd2_journal_init_revoke_record_cache(void); extern int __init jbd2_journal_init_revoke_table_cache(void); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); extern void jbd2_journal_write_revoke_records(transaction_t *transaction, struct list_head *log_bufs); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); extern void jbd2_journal_clear_revoke(journal_t *); extern void jbd2_journal_switch_revoke_table(journal_t *journal); extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); /* * The log thread user interface: * * Request space in the current transaction, and force transaction commit * transitions on demand. */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); int __jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); int jbd2_transaction_committed(journal_t *journal, tid_t tid); int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); int jbd2_fc_release_bufs(journal_t *journal); /* * is_journal_abort * * Simple test wrapper function to test the JBD2_ABORT state flag. This * bit, when set, indicates that we have had a fatal error somewhere, * either inside the journaling layer or indicated to us by the client * (eg. ext3), and that we and should not commit any further * transactions. */ static inline int is_journal_aborted(journal_t *journal) { return journal->j_flags & JBD2_ABORT; } static inline int is_handle_aborted(handle_t *handle) { if (handle->h_aborted || !handle->h_transaction) return 1; return is_journal_aborted(handle->h_transaction->t_journal); } static inline void jbd2_journal_abort_handle(handle_t *handle) { handle->h_aborted = 1; } #endif /* __KERNEL__ */ /* Comparison functions for transaction IDs: perform comparisons using * modulo arithmetic so that they work over sequence number wraps. */ static inline int tid_gt(tid_t x, tid_t y) { int difference = (x - y); return (difference > 0); } static inline int tid_geq(tid_t x, tid_t y) { int difference = (x - y); return (difference >= 0); } extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); static inline bool jbd2_journal_has_csum_v2or3_feature(journal_t *j) { return jbd2_has_feature_csum2(j) || jbd2_has_feature_csum3(j); } static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { WARN_ON_ONCE(jbd2_journal_has_csum_v2or3_feature(journal) && journal->j_chksum_driver == NULL); return journal->j_chksum_driver != NULL; } static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb) { int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks); return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS; } /* * Return number of free blocks in the log. Must be called under j_state_lock. */ static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ long free = journal->j_free - 32; if (journal->j_committing_transaction) { free -= atomic_read(&journal-> j_committing_transaction->t_outstanding_credits); } return max_t(long, free, 0); } /* * Definitions which augment the buffer_head layer */ /* journaling buffer types */ #define BJ_None 0 /* Not journaled */ #define BJ_Metadata 1 /* Normal journaled metadata */ #define BJ_Forget 2 /* Buffer superseded by this transaction */ #define BJ_Shadow 3 /* Buffer contents being shadowed to the log */ #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 extern int jbd_blocks_per_page(struct inode *inode); /* JBD uses a CRC32 checksum */ #define JBD_MAX_CHECKSUM_SIZE 4 static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { struct { struct shash_desc shash; char ctx[JBD_MAX_CHECKSUM_SIZE]; } desc; int err; BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) > JBD_MAX_CHECKSUM_SIZE); desc.shash.tfm = journal->j_chksum_driver; *(u32 *)desc.ctx = crc; err = crypto_shash_update(&desc.shash, address, length); BUG_ON(err); return *(u32 *)desc.ctx; } /* Return most recent uncommitted transaction */ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) { tid_t tid; read_lock(&journal->j_state_lock); tid = journal->j_commit_request; if (journal->j_running_transaction) tid = journal->j_running_transaction->t_tid; read_unlock(&journal->j_state_lock); return tid; } static inline int jbd2_handle_buffer_credits(handle_t *handle) { journal_t *journal; if (!handle->h_reserved) journal = handle->h_transaction->t_journal; else journal = handle->h_journal; return handle->h_total_credits - DIV_ROUND_UP(handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); } #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) #define print_buffer_fields(bh) do {} while (0) #define print_buffer_trace(bh) do {} while (0) #define BUFFER_TRACE(bh, info) do {} while (0) #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _LINUX_JBD2_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 | // SPDX-License-Identifier: GPL-2.0-or-later /* * sctp_offload - GRO/GSO Offloading for SCTP * * Copyright (C) 2015, Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/kprobes.h> #include <linux/socket.h> #include <linux/sctp.h> #include <linux/proc_fs.h> #include <linux/vmalloc.h> #include <linux/module.h> #include <linux/kfifo.h> #include <linux/time.h> #include <net/net_namespace.h> #include <linux/skbuff.h> #include <net/sctp/sctp.h> #include <net/sctp/checksum.h> #include <net/protocol.h> static __le32 sctp_gso_make_checksum(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; skb->csum_not_inet = 0; /* csum and csum_start in GSO CB may be needed to do the UDP * checksum when it's a UDP tunneling packet. */ SKB_GSO_CB(skb)->csum = (__force __wsum)~0; SKB_GSO_CB(skb)->csum_start = skb_headroom(skb) + skb->len; return sctp_compute_cksum(skb, skb_transport_offset(skb)); } static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct sctphdr *sh; if (!skb_is_gso_sctp(skb)) goto out; sh = sctp_hdr(skb); if (!pskb_may_pull(skb, sizeof(*sh))) goto out; __skb_pull(skb, sizeof(*sh)); if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ struct skb_shared_info *pinfo = skb_shinfo(skb); struct sk_buff *frag_iter; pinfo->gso_segs = 0; if (skb->len != skb->data_len) { /* Means we have chunks in here too */ pinfo->gso_segs++; } skb_walk_frags(skb, frag_iter) pinfo->gso_segs++; segs = NULL; goto out; } segs = skb_segment(skb, (features | NETIF_F_HW_CSUM) & ~NETIF_F_SG); if (IS_ERR(segs)) goto out; /* All that is left is update SCTP CRC if necessary */ if (!(features & NETIF_F_SCTP_CRC)) { for (skb = segs; skb; skb = skb->next) { if (skb->ip_summed == CHECKSUM_PARTIAL) { sh = sctp_hdr(skb); sh->checksum = sctp_gso_make_checksum(skb); } } } out: return segs; } static const struct net_offload sctp_offload = { .callbacks = { .gso_segment = sctp_gso_segment, }, }; static const struct net_offload sctp6_offload = { .callbacks = { .gso_segment = sctp_gso_segment, }, }; int __init sctp_offload_init(void) { int ret; ret = inet_add_offload(&sctp_offload, IPPROTO_SCTP); if (ret) goto out; ret = inet6_add_offload(&sctp6_offload, IPPROTO_SCTP); if (ret) goto ipv4; crc32c_csum_stub = &sctp_csum_ops; return ret; ipv4: inet_del_offload(&sctp_offload, IPPROTO_SCTP); out: return ret; } |
| 860 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PID_NS_H #define _LINUX_PID_NS_H #include <linux/sched.h> #include <linux/bug.h> #include <linux/mm.h> #include <linux/workqueue.h> #include <linux/threads.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/idr.h> /* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ #define MAX_PID_NS_LEVEL 32 struct fs_pin; struct pid_namespace { struct idr idr; struct rcu_head rcu; unsigned int pid_allocated; struct task_struct *child_reaper; struct kmem_cache *pid_cachep; unsigned int level; struct pid_namespace *parent; #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; #endif struct user_namespace *user_ns; struct ucounts *ucounts; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; } __randomize_layout; extern struct pid_namespace init_pid_ns; #define PIDNS_ADDING (1U << 31) #ifdef CONFIG_PID_NS static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { if (ns != &init_pid_ns) refcount_inc(&ns->ns.count); return ns; } extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *ns); extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd); extern void put_pid_ns(struct pid_namespace *ns); #else /* !CONFIG_PID_NS */ #include <linux/err.h> static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { return ns; } static inline struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *ns) { if (flags & CLONE_NEWPID) ns = ERR_PTR(-EINVAL); return ns; } static inline void put_pid_ns(struct pid_namespace *ns) { } static inline void zap_pid_ns_processes(struct pid_namespace *ns) { BUG(); } static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) { return 0; } #endif /* CONFIG_PID_NS */ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); #endif /* _LINUX_PID_NS_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FUTEX_H #define _ASM_X86_FUTEX_H #ifdef __KERNEL__ #include <linux/futex.h> #include <linux/uaccess.h> #include <asm/asm.h> #include <asm/errno.h> #include <asm/processor.h> #include <asm/smap.h> #define unsafe_atomic_op1(insn, oval, uaddr, oparg, label) \ do { \ int oldval = 0, ret; \ asm volatile("1:\t" insn "\n" \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %1) \ : "=r" (oldval), "=r" (ret), "+m" (*uaddr) \ : "0" (oparg), "1" (0)); \ if (ret) \ goto label; \ *oval = oldval; \ } while(0) #define unsafe_atomic_op2(insn, oval, uaddr, oparg, label) \ do { \ int oldval = 0, ret, tem; \ asm volatile("1:\tmovl %2, %0\n" \ "2:\tmovl\t%0, %3\n" \ "\t" insn "\n" \ "3:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \ "\tjnz\t2b\n" \ "4:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 4b, EX_TYPE_EFAULT_REG, %1) \ _ASM_EXTABLE_TYPE_REG(3b, 4b, EX_TYPE_EFAULT_REG, %1) \ : "=&a" (oldval), "=&r" (ret), \ "+m" (*uaddr), "=&r" (tem) \ : "r" (oparg), "1" (0)); \ if (ret) \ goto label; \ *oval = oldval; \ } while(0) static __always_inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { if (!user_access_begin(uaddr, sizeof(u32))) return -EFAULT; switch (op) { case FUTEX_OP_SET: unsafe_atomic_op1("xchgl %0, %2", oval, uaddr, oparg, Efault); break; case FUTEX_OP_ADD: unsafe_atomic_op1(LOCK_PREFIX "xaddl %0, %2", oval, uaddr, oparg, Efault); break; case FUTEX_OP_OR: unsafe_atomic_op2("orl %4, %3", oval, uaddr, oparg, Efault); break; case FUTEX_OP_ANDN: unsafe_atomic_op2("andl %4, %3", oval, uaddr, ~oparg, Efault); break; case FUTEX_OP_XOR: unsafe_atomic_op2("xorl %4, %3", oval, uaddr, oparg, Efault); break; default: user_access_end(); return -ENOSYS; } user_access_end(); return 0; Efault: user_access_end(); return -EFAULT; } static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { int ret = 0; if (!user_access_begin(uaddr, sizeof(u32))) return -EFAULT; asm volatile("\n" "1:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" "2:\n" _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %0) \ : "+r" (ret), "=a" (oldval), "+m" (*uaddr) : "r" (newval), "1" (oldval) : "memory" ); user_access_end(); *uval = oldval; return ret; } #endif #endif /* _ASM_X86_FUTEX_H */ |
| 88 151 55 235 5 427 15 1 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2020 Christoph Hellwig. * * Support for "universal" pointers that can point to either kernel or userspace * memory. */ #ifndef _LINUX_SOCKPTR_H #define _LINUX_SOCKPTR_H #include <linux/slab.h> #include <linux/uaccess.h> typedef struct { union { void *kernel; void __user *user; }; bool is_kernel : 1; } sockptr_t; static inline bool sockptr_is_kernel(sockptr_t sockptr) { return sockptr.is_kernel; } static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p, .is_kernel = true }; } static inline sockptr_t USER_SOCKPTR(void __user *p) { return (sockptr_t) { .user = p }; } static inline bool sockptr_is_null(sockptr_t sockptr) { if (sockptr_is_kernel(sockptr)) return !sockptr.kernel; return !sockptr.user; } static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, size_t offset, size_t size) { if (!sockptr_is_kernel(src)) return copy_from_user(dst, src.user + offset, size); memcpy(dst, src.kernel + offset, size); return 0; } static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) { return copy_from_sockptr_offset(dst, src, 0, size); } static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, const void *src, size_t size) { if (!sockptr_is_kernel(dst)) return copy_to_user(dst.user + offset, src, size); memcpy(dst.kernel + offset, src, size); return 0; } static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) { return copy_to_sockptr_offset(dst, 0, src, size); } static inline void *memdup_sockptr(sockptr_t src, size_t len) { void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_sockptr(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) { char *p = kmalloc_track_caller(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_sockptr(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { if (sockptr_is_kernel(src)) { size_t len = min(strnlen(src.kernel, count - 1) + 1, count); memcpy(dst, src.kernel, len); return len; } return strncpy_from_user(dst, src.user, count); } #endif /* _LINUX_SOCKPTR_H */ |
| 22 22 14 17 22 22 8076 8075 14 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | // SPDX-License-Identifier: GPL-2.0 /* * SafeSetID Linux Security Module * * Author: Micah Morton <mortonm@chromium.org> * * Copyright (C) 2018 The Chromium OS Authors. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2, as * published by the Free Software Foundation. * */ #define pr_fmt(fmt) "SafeSetID: " fmt #include <linux/lsm_hooks.h> #include <linux/module.h> #include <linux/ptrace.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include "lsm.h" /* Flag indicating whether initialization completed */ int safesetid_initialized __initdata; struct setid_ruleset __rcu *safesetid_setuid_rules; struct setid_ruleset __rcu *safesetid_setgid_rules; /* Compute a decision for a transition from @src to @dst under @policy. */ enum sid_policy_type _setid_policy_lookup(struct setid_ruleset *policy, kid_t src, kid_t dst) { struct setid_rule *rule; enum sid_policy_type result = SIDPOL_DEFAULT; if (policy->type == UID) { hash_for_each_possible(policy->rules, rule, next, __kuid_val(src.uid)) { if (!uid_eq(rule->src_id.uid, src.uid)) continue; if (uid_eq(rule->dst_id.uid, dst.uid)) return SIDPOL_ALLOWED; result = SIDPOL_CONSTRAINED; } } else if (policy->type == GID) { hash_for_each_possible(policy->rules, rule, next, __kgid_val(src.gid)) { if (!gid_eq(rule->src_id.gid, src.gid)) continue; if (gid_eq(rule->dst_id.gid, dst.gid)){ return SIDPOL_ALLOWED; } result = SIDPOL_CONSTRAINED; } } else { /* Should not reach here, report the ID as contrainsted */ result = SIDPOL_CONSTRAINED; } return result; } /* * Compute a decision for a transition from @src to @dst under the active * policy. */ static enum sid_policy_type setid_policy_lookup(kid_t src, kid_t dst, enum setid_type new_type) { enum sid_policy_type result = SIDPOL_DEFAULT; struct setid_ruleset *pol; rcu_read_lock(); if (new_type == UID) pol = rcu_dereference(safesetid_setuid_rules); else if (new_type == GID) pol = rcu_dereference(safesetid_setgid_rules); else { /* Should not reach here */ result = SIDPOL_CONSTRAINED; rcu_read_unlock(); return result; } if (pol) { pol->type = new_type; result = _setid_policy_lookup(pol, src, dst); } rcu_read_unlock(); return result; } static int safesetid_security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { /* We're only interested in CAP_SETUID and CAP_SETGID. */ if (cap != CAP_SETUID && cap != CAP_SETGID) return 0; /* * If CAP_SET{U/G}ID is currently used for a setid() syscall, we want to * let it go through here; the real security check happens later, in the * task_fix_set{u/g}id hook. * * NOTE: * Until we add support for restricting setgroups() calls, GID security * policies offer no meaningful security since we always return 0 here * when called from within the setgroups() syscall and there is no * additional hook later on to enforce security policies for setgroups(). */ if ((opts & CAP_OPT_INSETID) != 0) return 0; switch (cap) { case CAP_SETUID: /* * If no policy applies to this task, allow the use of CAP_SETUID for * other purposes. */ if (setid_policy_lookup((kid_t){.uid = cred->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT) return 0; /* * Reject use of CAP_SETUID for functionality other than calling * set*uid() (e.g. setting up userns uid mappings). */ pr_warn("Operation requires CAP_SETUID, which is not available to UID %u for operations besides approved set*uid transitions\n", __kuid_val(cred->uid)); return -EPERM; case CAP_SETGID: /* * If no policy applies to this task, allow the use of CAP_SETGID for * other purposes. */ if (setid_policy_lookup((kid_t){.gid = cred->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; /* * Reject use of CAP_SETUID for functionality other than calling * set*gid() (e.g. setting up userns gid mappings). */ pr_warn("Operation requires CAP_SETGID, which is not available to GID %u for operations besides approved set*gid transitions\n", __kuid_val(cred->uid)); return -EPERM; default: /* Error, the only capabilities were checking for is CAP_SETUID/GID */ return 0; } return 0; } /* * Check whether a caller with old credentials @old is allowed to switch to * credentials that contain @new_id. */ static bool id_permitted_for_cred(const struct cred *old, kid_t new_id, enum setid_type new_type) { bool permitted; /* If our old creds already had this ID in it, it's fine. */ if (new_type == UID) { if (uid_eq(new_id.uid, old->uid) || uid_eq(new_id.uid, old->euid) || uid_eq(new_id.uid, old->suid)) return true; } else if (new_type == GID){ if (gid_eq(new_id.gid, old->gid) || gid_eq(new_id.gid, old->egid) || gid_eq(new_id.gid, old->sgid)) return true; } else /* Error, new_type is an invalid type */ return false; /* * Transitions to new UIDs require a check against the policy of the old * RUID. */ permitted = setid_policy_lookup((kid_t){.uid = old->uid}, new_id, new_type) != SIDPOL_CONSTRAINED; if (!permitted) { if (new_type == UID) { pr_warn("UID transition ((%d,%d,%d) -> %d) blocked\n", __kuid_val(old->uid), __kuid_val(old->euid), __kuid_val(old->suid), __kuid_val(new_id.uid)); } else if (new_type == GID) { pr_warn("GID transition ((%d,%d,%d) -> %d) blocked\n", __kgid_val(old->gid), __kgid_val(old->egid), __kgid_val(old->sgid), __kgid_val(new_id.gid)); } else /* Error, new_type is an invalid type */ return false; } return permitted; } /* * Check whether there is either an exception for user under old cred struct to * set*uid to user under new cred struct, or the UID transition is allowed (by * Linux set*uid rules) even without CAP_SETUID. */ static int safesetid_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { /* Do nothing if there are no setuid restrictions for our old RUID. */ if (setid_policy_lookup((kid_t){.uid = old->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT) return 0; if (id_permitted_for_cred(old, (kid_t){.uid = new->uid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->euid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->suid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->fsuid}, UID)) return 0; /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } static int safesetid_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { /* Do nothing if there are no setgid restrictions for our old RGID. */ if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; if (id_permitted_for_cred(old, (kid_t){.gid = new->gid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->egid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->sgid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->fsgid}, GID)) return 0; /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } static struct security_hook_list safesetid_security_hooks[] = { LSM_HOOK_INIT(task_fix_setuid, safesetid_task_fix_setuid), LSM_HOOK_INIT(task_fix_setgid, safesetid_task_fix_setgid), LSM_HOOK_INIT(capable, safesetid_security_capable) }; static int __init safesetid_security_init(void) { security_add_hooks(safesetid_security_hooks, ARRAY_SIZE(safesetid_security_hooks), "safesetid"); /* Report that SafeSetID successfully initialized */ safesetid_initialized = 1; return 0; } DEFINE_LSM(safesetid_security_init) = { .init = safesetid_security_init, .name = "safesetid", }; |
| 19 2363 1 2 2 11 1 9 5 46 5 3 79 23 33 5 10 3 3 3 4 23 3 4 4 7 4 2 3 3 3 3 3 3 3 3 4 2 4 2 9 3 3 9 7 5 4 8 9 3 9 3 9 3 5 6 1 17 18 2 3 12 3 7 6 2516 1 3 13 32 3 3 1 1 4 10 15 60 1 2 15 3 7 2278 85 2540 86 211 2319 2522 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ioctl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/compat.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/falloc.h> #include <linux/sched/signal.h> #include <linux/fiemap.h> #include <linux/mount.h> #include <linux/fscrypt.h> #include <linux/fileattr.h> #include "internal.h" #include <asm/ioctls.h> /* So that the fiemap access checks can't overflow on 32 bit machines. */ #define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) /** * vfs_ioctl - call filesystem specific ioctl methods * @filp: open file to invoke ioctl method on * @cmd: ioctl command to execute * @arg: command-specific argument for ioctl * * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise * returns -ENOTTY. * * Returns 0 on success, -errno on error. */ long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; if (!filp->f_op->unlocked_ioctl) goto out; error = filp->f_op->unlocked_ioctl(filp, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; out: return error; } EXPORT_SYMBOL(vfs_ioctl); static int ioctl_fibmap(struct file *filp, int __user *p) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; int error, ur_block; sector_t block; if (!capable(CAP_SYS_RAWIO)) return -EPERM; error = get_user(ur_block, p); if (error) return error; if (ur_block < 0) return -EINVAL; block = ur_block; error = bmap(inode, &block); if (block > INT_MAX) { error = -ERANGE; pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n", current->comm, task_pid_nr(current), sb->s_id, filp); } if (error) ur_block = 0; else ur_block = block; if (put_user(ur_block, p)) error = -EFAULT; return error; } /** * fiemap_fill_next_extent - Fiemap helper function * @fieinfo: Fiemap context passed into ->fiemap * @logical: Extent logical start offset, in bytes * @phys: Extent physical start offset, in bytes * @len: Extent length, in bytes * @flags: FIEMAP_EXTENT flags that describe this extent * * Called from file system ->fiemap callback. Will populate extent * info as passed in via arguments and copy to user memory. On * success, extent count on fieinfo is incremented. * * Returns 0 on success, -errno on error, 1 if this was the last * extent that will fit in user array. */ #define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC) #define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED) #define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE) int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical, u64 phys, u64 len, u32 flags) { struct fiemap_extent extent; struct fiemap_extent __user *dest = fieinfo->fi_extents_start; /* only count the extents */ if (fieinfo->fi_extents_max == 0) { fieinfo->fi_extents_mapped++; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max) return 1; if (flags & SET_UNKNOWN_FLAGS) flags |= FIEMAP_EXTENT_UNKNOWN; if (flags & SET_NO_UNMOUNTED_IO_FLAGS) flags |= FIEMAP_EXTENT_ENCODED; if (flags & SET_NOT_ALIGNED_FLAGS) flags |= FIEMAP_EXTENT_NOT_ALIGNED; memset(&extent, 0, sizeof(extent)); extent.fe_logical = logical; extent.fe_physical = phys; extent.fe_length = len; extent.fe_flags = flags; dest += fieinfo->fi_extents_mapped; if (copy_to_user(dest, &extent, sizeof(extent))) return -EFAULT; fieinfo->fi_extents_mapped++; if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max) return 1; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } EXPORT_SYMBOL(fiemap_fill_next_extent); /** * fiemap_prep - check validity of requested flags for fiemap * @inode: Inode to operate on * @fieinfo: Fiemap context passed into ->fiemap * @start: Start of the mapped range * @len: Length of the mapped range, can be truncated by this function. * @supported_flags: Set of fiemap flags that the file system understands * * This function must be called from each ->fiemap instance to validate the * fiemap request against the file system parameters. * * Returns 0 on success, or a negative error on failure. */ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 *len, u32 supported_flags) { u64 maxbytes = inode->i_sb->s_maxbytes; u32 incompat_flags; int ret = 0; if (*len == 0) return -EINVAL; if (start >= maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ if (*len > maxbytes || (maxbytes - *len) < start) *len = maxbytes - start; supported_flags |= FIEMAP_FLAG_SYNC; supported_flags &= FIEMAP_FLAGS_COMPAT; incompat_flags = fieinfo->fi_flags & ~supported_flags; if (incompat_flags) { fieinfo->fi_flags = incompat_flags; return -EBADR; } if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) ret = filemap_write_and_wait(inode->i_mapping); return ret; } EXPORT_SYMBOL(fiemap_prep); static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap) { struct fiemap fiemap; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); int error; if (!inode->i_op->fiemap) return -EOPNOTSUPP; if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) return -EFAULT; if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) error = -EFAULT; return error; } static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, u64 off, u64 olen, u64 destoff) { struct fd src_file = fdget(srcfd); loff_t cloned; int ret; if (!src_file.file) return -EBADF; ret = -EXDEV; if (src_file.file->f_path.mnt != dst_file->f_path.mnt) goto fdput; cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen, 0); if (cloned < 0) ret = cloned; else if (olen && cloned != olen) ret = -EINVAL; else ret = 0; fdput: fdput(src_file); return ret; } static long ioctl_file_clone_range(struct file *file, struct file_clone_range __user *argp) { struct file_clone_range args; if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; return ioctl_file_clone(file, args.src_fd, args.src_offset, args.src_length, args.dest_offset); } /* * This provides compatibility with legacy XFS pre-allocation ioctls * which predate the fallocate syscall. * * Only the l_start, l_len and l_whence fields of the 'struct space_resv' * are used here, rest are ignored. */ static int ioctl_preallocate(struct file *filp, int mode, void __user *argp) { struct inode *inode = file_inode(filp); struct space_resv sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += filp->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(filp, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } /* on ia32 l_start is on a 32-bit boundary */ #if defined CONFIG_COMPAT && defined(CONFIG_X86_64) /* just account for different alignment */ static int compat_ioctl_preallocate(struct file *file, int mode, struct space_resv_32 __user *argp) { struct inode *inode = file_inode(file); struct space_resv_32 sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += file->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(file, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } #endif static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p) { switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); case FS_IOC_RESVSP: case FS_IOC_RESVSP64: return ioctl_preallocate(filp, 0, p); case FS_IOC_UNRESVSP: case FS_IOC_UNRESVSP64: return ioctl_preallocate(filp, FALLOC_FL_PUNCH_HOLE, p); case FS_IOC_ZERO_RANGE: return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p); } return -ENOIOCTLCMD; } static int ioctl_fionbio(struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = O_NONBLOCK; #ifdef __sparc__ /* SunOS compatibility item. */ if (O_NONBLOCK != O_NDELAY) flag |= O_NDELAY; #endif spin_lock(&filp->f_lock); if (on) filp->f_flags |= flag; else filp->f_flags &= ~flag; spin_unlock(&filp->f_lock); return error; } static int ioctl_fioasync(unsigned int fd, struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = on ? FASYNC : 0; /* Did FASYNC state change ? */ if ((flag ^ filp->f_flags) & FASYNC) { if (filp->f_op->fasync) /* fasync() adjusts filp->f_flags */ error = filp->f_op->fasync(fd, filp, on); else error = -ENOTTY; } return error < 0 ? error : 0; } static int ioctl_fsfreeze(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* If filesystem doesn't support freeze feature, return. */ if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL) return -EOPNOTSUPP; /* Freeze */ if (sb->s_op->freeze_super) return sb->s_op->freeze_super(sb); return freeze_super(sb); } static int ioctl_fsthaw(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Thaw */ if (sb->s_op->thaw_super) return sb->s_op->thaw_super(sb); return thaw_super(sb); } static int ioctl_file_dedupe_range(struct file *file, struct file_dedupe_range __user *argp) { struct file_dedupe_range *same = NULL; int ret; unsigned long size; u16 count; if (get_user(count, &argp->dest_count)) { ret = -EFAULT; goto out; } size = offsetof(struct file_dedupe_range __user, info[count]); if (size > PAGE_SIZE) { ret = -ENOMEM; goto out; } same = memdup_user(argp, size); if (IS_ERR(same)) { ret = PTR_ERR(same); same = NULL; goto out; } same->dest_count = count; ret = vfs_dedupe_file_range(file, same); if (ret) goto out; ret = copy_to_user(argp, same, size); if (ret) ret = -EFAULT; out: kfree(same); return ret; } /** * fileattr_fill_xflags - initialize fileattr with xflags * @fa: fileattr pointer * @xflags: FS_XFLAG_* flags * * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags). All * other fields are zeroed. */ void fileattr_fill_xflags(struct fileattr *fa, u32 xflags) { memset(fa, 0, sizeof(*fa)); fa->fsx_valid = true; fa->fsx_xflags = xflags; if (fa->fsx_xflags & FS_XFLAG_IMMUTABLE) fa->flags |= FS_IMMUTABLE_FL; if (fa->fsx_xflags & FS_XFLAG_APPEND) fa->flags |= FS_APPEND_FL; if (fa->fsx_xflags & FS_XFLAG_SYNC) fa->flags |= FS_SYNC_FL; if (fa->fsx_xflags & FS_XFLAG_NOATIME) fa->flags |= FS_NOATIME_FL; if (fa->fsx_xflags & FS_XFLAG_NODUMP) fa->flags |= FS_NODUMP_FL; if (fa->fsx_xflags & FS_XFLAG_DAX) fa->flags |= FS_DAX_FL; if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) fa->flags |= FS_PROJINHERIT_FL; } EXPORT_SYMBOL(fileattr_fill_xflags); /** * fileattr_fill_flags - initialize fileattr with flags * @fa: fileattr pointer * @flags: FS_*_FL flags * * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags). * All other fields are zeroed. */ void fileattr_fill_flags(struct fileattr *fa, u32 flags) { memset(fa, 0, sizeof(*fa)); fa->flags_valid = true; fa->flags = flags; if (fa->flags & FS_SYNC_FL) fa->fsx_xflags |= FS_XFLAG_SYNC; if (fa->flags & FS_IMMUTABLE_FL) fa->fsx_xflags |= FS_XFLAG_IMMUTABLE; if (fa->flags & FS_APPEND_FL) fa->fsx_xflags |= FS_XFLAG_APPEND; if (fa->flags & FS_NODUMP_FL) fa->fsx_xflags |= FS_XFLAG_NODUMP; if (fa->flags & FS_NOATIME_FL) fa->fsx_xflags |= FS_XFLAG_NOATIME; if (fa->flags & FS_DAX_FL) fa->fsx_xflags |= FS_XFLAG_DAX; if (fa->flags & FS_PROJINHERIT_FL) fa->fsx_xflags |= FS_XFLAG_PROJINHERIT; } EXPORT_SYMBOL(fileattr_fill_flags); /** * vfs_fileattr_get - retrieve miscellaneous file attributes * @dentry: the object to retrieve from * @fa: fileattr pointer * * Call i_op->fileattr_get() callback, if exists. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); if (!inode->i_op->fileattr_get) return -ENOIOCTLCMD; return inode->i_op->fileattr_get(dentry, fa); } EXPORT_SYMBOL(vfs_fileattr_get); /** * copy_fsxattr_to_user - copy fsxattr to userspace. * @fa: fileattr pointer * @ufa: fsxattr user pointer * * Return: 0 on success, or -EFAULT on failure. */ int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; memset(&xfa, 0, sizeof(xfa)); xfa.fsx_xflags = fa->fsx_xflags; xfa.fsx_extsize = fa->fsx_extsize; xfa.fsx_nextents = fa->fsx_nextents; xfa.fsx_projid = fa->fsx_projid; xfa.fsx_cowextsize = fa->fsx_cowextsize; if (copy_to_user(ufa, &xfa, sizeof(xfa))) return -EFAULT; return 0; } EXPORT_SYMBOL(copy_fsxattr_to_user); static int copy_fsxattr_from_user(struct fileattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; if (copy_from_user(&xfa, ufa, sizeof(xfa))) return -EFAULT; fileattr_fill_xflags(fa, xfa.fsx_xflags); fa->fsx_extsize = xfa.fsx_extsize; fa->fsx_nextents = xfa.fsx_nextents; fa->fsx_projid = xfa.fsx_projid; fa->fsx_cowextsize = xfa.fsx_cowextsize; return 0; } /* * Generic function to check FS_IOC_FSSETXATTR/FS_IOC_SETFLAGS values and reject * any invalid configurations. * * Note: must be called with inode lock held. */ static int fileattr_set_prepare(struct inode *inode, const struct fileattr *old_ma, struct fileattr *fa) { int err; /* * The IMMUTABLE and APPEND_ONLY flags can only be changed by * the relevant capability. */ if ((fa->flags ^ old_ma->flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; err = fscrypt_prepare_setflags(inode, old_ma->flags, fa->flags); if (err) return err; /* * Project Quota ID state is only allowed to change from within the init * namespace. Enforce that restriction only if we are trying to change * the quota ID state. Everything else is allowed in user namespaces. */ if (current_user_ns() != &init_user_ns) { if (old_ma->fsx_projid != fa->fsx_projid) return -EINVAL; if ((old_ma->fsx_xflags ^ fa->fsx_xflags) & FS_XFLAG_PROJINHERIT) return -EINVAL; } else { /* * Caller is allowed to change the project ID. If it is being * changed, make sure that the new value is valid. */ if (old_ma->fsx_projid != fa->fsx_projid && !projid_valid(make_kprojid(&init_user_ns, fa->fsx_projid))) return -EINVAL; } /* Check extent size hints. */ if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && !S_ISDIR(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) && !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EINVAL; /* * It is only valid to set the DAX flag on regular files and * directories on filesystems. */ if ((fa->fsx_xflags & FS_XFLAG_DAX) && !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; /* Extent size hints of zero turn off the flags. */ if (fa->fsx_extsize == 0) fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); if (fa->fsx_cowextsize == 0) fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; return 0; } /** * vfs_fileattr_set - change miscellaneous file attributes * @mnt_userns: user namespace of the mount * @dentry: the object to change * @fa: fileattr pointer * * After verifying permissions, call i_op->fileattr_set() callback, if * exists. * * Verifying attributes involves retrieving current attributes with * i_op->fileattr_get(), this also allows initializing attributes that have * not been set by the caller to current values. Inode lock is held * thoughout to prevent racing with another instance. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct fileattr old_ma = {}; int err; if (!inode->i_op->fileattr_set) return -ENOIOCTLCMD; if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; inode_lock(inode); err = vfs_fileattr_get(dentry, &old_ma); if (!err) { /* initialize missing bits from old_ma */ if (fa->flags_valid) { fa->fsx_xflags |= old_ma.fsx_xflags & ~FS_XFLAG_COMMON; fa->fsx_extsize = old_ma.fsx_extsize; fa->fsx_nextents = old_ma.fsx_nextents; fa->fsx_projid = old_ma.fsx_projid; fa->fsx_cowextsize = old_ma.fsx_cowextsize; } else { fa->flags |= old_ma.flags & ~FS_COMMON_FL; } err = fileattr_set_prepare(inode, &old_ma, fa); if (!err) err = inode->i_op->fileattr_set(mnt_userns, dentry, fa); } inode_unlock(inode); return err; } EXPORT_SYMBOL(vfs_fileattr_set); static int ioctl_getflags(struct file *file, unsigned int __user *argp) { struct fileattr fa = { .flags_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = put_user(fa.flags, argp); return err; } static int ioctl_setflags(struct file *file, unsigned int __user *argp) { struct user_namespace *mnt_userns = file_mnt_user_ns(file); struct dentry *dentry = file->f_path.dentry; struct fileattr fa; unsigned int flags; int err; err = get_user(flags, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { fileattr_fill_flags(&fa, flags); err = vfs_fileattr_set(mnt_userns, dentry, &fa); mnt_drop_write_file(file); } } return err; } static int ioctl_fsgetxattr(struct file *file, void __user *argp) { struct fileattr fa = { .fsx_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = copy_fsxattr_to_user(&fa, argp); return err; } static int ioctl_fssetxattr(struct file *file, void __user *argp) { struct user_namespace *mnt_userns = file_mnt_user_ns(file); struct dentry *dentry = file->f_path.dentry; struct fileattr fa; int err; err = copy_fsxattr_from_user(&fa, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { err = vfs_fileattr_set(mnt_userns, dentry, &fa); mnt_drop_write_file(file); } } return err; } /* * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d. * It's just a simple helper for sys_ioctl and compat_sys_ioctl. * * When you add any new common ioctls to the switches above and below, * please ensure they have compatible arguments in compat mode. */ static int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct inode *inode = file_inode(filp); switch (cmd) { case FIOCLEX: set_close_on_exec(fd, 1); return 0; case FIONCLEX: set_close_on_exec(fd, 0); return 0; case FIONBIO: return ioctl_fionbio(filp, argp); case FIOASYNC: return ioctl_fioasync(fd, filp, argp); case FIOQSIZE: if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { loff_t res = inode_get_bytes(inode); return copy_to_user(argp, &res, sizeof(res)) ? -EFAULT : 0; } return -ENOTTY; case FIFREEZE: return ioctl_fsfreeze(filp); case FITHAW: return ioctl_fsthaw(filp); case FS_IOC_FIEMAP: return ioctl_fiemap(filp, argp); case FIGETBSZ: /* anon_bdev filesystems may not have a block size */ if (!inode->i_sb->s_blocksize) return -EINVAL; return put_user(inode->i_sb->s_blocksize, (int __user *)argp); case FICLONE: return ioctl_file_clone(filp, arg, 0, 0, 0); case FICLONERANGE: return ioctl_file_clone_range(filp, argp); case FIDEDUPERANGE: return ioctl_file_dedupe_range(filp, argp); case FIONREAD: if (!S_ISREG(inode->i_mode)) return vfs_ioctl(filp, cmd, arg); return put_user(i_size_read(inode) - filp->f_pos, (int __user *)argp); case FS_IOC_GETFLAGS: return ioctl_getflags(filp, argp); case FS_IOC_SETFLAGS: return ioctl_setflags(filp, argp); case FS_IOC_FSGETXATTR: return ioctl_fsgetxattr(filp, argp); case FS_IOC_FSSETXATTR: return ioctl_fssetxattr(filp, argp); default: if (S_ISREG(inode->i_mode)) return file_ioctl(filp, cmd, argp); break; } return -ENOIOCTLCMD; } SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget(fd); int error; if (!f.file) return -EBADF; error = security_file_ioctl(f.file, cmd, arg); if (error) goto out; error = do_vfs_ioctl(f.file, fd, cmd, arg); if (error == -ENOIOCTLCMD) error = vfs_ioctl(f.file, cmd, arg); out: fdput(f); return error; } #ifdef CONFIG_COMPAT /** * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation * * This is not normally called as a function, but instead set in struct * file_operations as * * .compat_ioctl = compat_ptr_ioctl, * * On most architectures, the compat_ptr_ioctl() just passes all arguments * to the corresponding ->ioctl handler. The exception is arch/s390, where * compat_ptr() clears the top bit of a 32-bit pointer value, so user space * pointers to the second 2GB alias the first 2GB, as is the case for * native 32-bit s390 user space. * * The compat_ptr_ioctl() function must therefore be used only with ioctl * functions that either ignore the argument or pass a pointer to a * compatible data type. * * If any ioctl command handled by fops->unlocked_ioctl passes a plain * integer instead of a pointer, or any of the passed data types * is incompatible between 32-bit and 64-bit architectures, a proper * handler is required instead of compat_ptr_ioctl. */ long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { if (!file->f_op->unlocked_ioctl) return -ENOIOCTLCMD; return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } EXPORT_SYMBOL(compat_ptr_ioctl); COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { struct fd f = fdget(fd); int error; if (!f.file) return -EBADF; error = security_file_ioctl_compat(f.file, cmd, arg); if (error) goto out; switch (cmd) { /* FICLONE takes an int argument, so don't use compat_ptr() */ case FICLONE: error = ioctl_file_clone(f.file, arg, 0, 0, 0); break; #if defined(CONFIG_X86_64) /* these get messy on amd64 due to alignment differences */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg)); break; case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE, compat_ptr(arg)); break; case FS_IOC_ZERO_RANGE_32: error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE, compat_ptr(arg)); break; #endif /* * These access 32-bit values anyway so no further handling is * necessary. */ case FS_IOC32_GETFLAGS: case FS_IOC32_SETFLAGS: cmd = (cmd == FS_IOC32_GETFLAGS) ? FS_IOC_GETFLAGS : FS_IOC_SETFLAGS; fallthrough; /* * everything else in do_vfs_ioctl() takes either a compatible * pointer argument or no argument -- call it with a modified * argument. */ default: error = do_vfs_ioctl(f.file, fd, cmd, (unsigned long)compat_ptr(arg)); if (error != -ENOIOCTLCMD) break; if (f.file->f_op->compat_ioctl) error = f.file->f_op->compat_ioctl(f.file, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; break; } out: fdput(f); return error; } #endif |
| 1227 1231 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blkdev.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/frontswap.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> #include <linux/completion.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by get_swap_page() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but get_swap_page() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full*/ #define TTRS_FULL 0x4 /* returns 1 if swap entry is freed */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct page *page; int ret = 0; page = find_get_page(swap_address_space(entry), offset); if (!page) return 0; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming pages. So, we hold a lock on a page, * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use try_to_free_swap() with explicit lock_page() * in usual operations. */ if (trylock_page(page)) { if ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !page_mapped(page)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(page))) ret = try_to_free_swap(page); unlock_page(page); } put_page(page); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL, 0); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL, 0); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_page_sector(struct page *page) { struct swap_info_struct *sis = page_swap_info(page); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = __page_file_index(page); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO, 0)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_size(size) (size) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_size() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_size(size) 1 #endif #define LATENCY_LIMIT 256 static inline void cluster_set_flag(struct swap_cluster_info *info, unsigned int flag) { info->flags = flag; } static inline unsigned int cluster_count(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_count(struct swap_cluster_info *info, unsigned int c) { info->data = c; } static inline void cluster_set_count_flag(struct swap_cluster_info *info, unsigned int c, unsigned int f) { info->flags = f; info->data = c; } static inline unsigned int cluster_next(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_next(struct swap_cluster_info *info, unsigned int n) { info->data = n; } static inline void cluster_set_next_flag(struct swap_cluster_info *info, unsigned int n, unsigned int f) { info->flags = f; info->data = n; } static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; } static inline bool cluster_is_null(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_NEXT_NULL; } static inline void cluster_set_null(struct swap_cluster_info *info) { info->flags = CLUSTER_FLAG_NEXT_NULL; info->data = 0; } static inline bool cluster_is_huge(struct swap_cluster_info *info) { if (IS_ENABLED(CONFIG_THP_SWAP)) return info->flags & CLUSTER_FLAG_HUGE; return false; } static inline void cluster_clear_huge(struct swap_cluster_info *info) { info->flags &= ~CLUSTER_FLAG_HUGE; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = si->cluster_info; if (ci) { ci += offset / SWAPFILE_CLUSTER; spin_lock(&ci->lock); } return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { if (ci) spin_unlock(&ci->lock); } /* * Determine the locking method in use for this device. Return * swap_cluster_info if SSD-style cluster-based locking is in place. */ static inline struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; /* Try to use fine-grained SSD-style locking if available: */ ci = lock_cluster(si, offset); /* Otherwise, fall back to traditional, coarse locking: */ if (!ci) spin_lock(&si->lock); return ci; } static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci) { if (ci) unlock_cluster(ci); else spin_unlock(&si->lock); } static inline bool cluster_list_empty(struct swap_cluster_list *list) { return cluster_is_null(&list->head); } static inline unsigned int cluster_list_first(struct swap_cluster_list *list) { return cluster_next(&list->head); } static void cluster_list_init(struct swap_cluster_list *list) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } static void cluster_list_add_tail(struct swap_cluster_list *list, struct swap_cluster_info *ci, unsigned int idx) { if (cluster_list_empty(list)) { cluster_set_next_flag(&list->head, idx, 0); cluster_set_next_flag(&list->tail, idx, 0); } else { struct swap_cluster_info *ci_tail; unsigned int tail = cluster_next(&list->tail); /* * Nested cluster lock, but both cluster locks are * only acquired when we held swap_info_struct->lock */ ci_tail = ci + tail; spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); cluster_set_next(ci_tail, idx); spin_unlock(&ci_tail->lock); cluster_set_next_flag(&list->tail, idx, 0); } } static unsigned int cluster_list_del_first(struct swap_cluster_list *list, struct swap_cluster_info *ci) { unsigned int idx; idx = cluster_next(&list->head); if (cluster_next(&list->tail) == idx) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } else cluster_set_next_flag(&list->head, cluster_next(&ci[idx]), 0); return idx; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) { /* * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE); cluster_list_add_tail(&si->free_clusters, ci, idx); } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. caller should hold si->lock. */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *info, *ci; unsigned int idx; info = si->cluster_info; while (!cluster_list_empty(&si->discard_clusters)) { idx = cluster_list_del_first(&si->discard_clusters, info); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); __free_cluster(si, idx); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); unlock_cluster(ci); } } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); spin_lock(&si->lock); swap_do_scheduled_discard(si); spin_unlock(&si->lock); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx); cluster_list_del_first(&si->free_clusters, ci); cluster_set_count_flag(ci + idx, 0, 0); } static void free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info + idx; VM_BUG_ON(cluster_count(ci) != 0); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, idx); return; } __free_cluster(si, idx); } /* * The cluster corresponding to page_nr will be used. The cluster will be * removed from free cluster list and its usage counter will be increased. */ static void inc_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; if (cluster_is_free(&cluster_info[idx])) alloc_cluster(p, idx); VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) + 1); } /* * The cluster corresponding to page_nr decreases one usage. If the usage * counter becomes 0, which means no page in the cluster is in using, we can * optionally discard the cluster and add it to free cluster list. */ static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) - 1); if (cluster_count(&cluster_info[idx]) == 0) free_cluster(p, idx); } /* * It's possible scan_swap_map_slots() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */ static bool scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, unsigned long offset) { struct percpu_cluster *percpu_cluster; bool conflict; offset /= SWAPFILE_CLUSTER; conflict = !cluster_list_empty(&si->free_clusters) && offset != cluster_list_first(&si->free_clusters) && cluster_is_free(&si->cluster_info[offset]); if (!conflict) return false; percpu_cluster = this_cpu_ptr(si->percpu_cluster); cluster_set_null(&percpu_cluster->index); return true; } /* * Try to get a swap entry from current cpu's swap entry pool (a cluster). This * might involve allocating a new cluster for current CPU too. */ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, unsigned long *offset, unsigned long *scan_base) { struct percpu_cluster *cluster; struct swap_cluster_info *ci; unsigned long tmp, max; new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); if (cluster_is_null(&cluster->index)) { if (!cluster_list_empty(&si->free_clusters)) { cluster->index = si->free_clusters.head; cluster->next = cluster_next(&cluster->index) * SWAPFILE_CLUSTER; } else if (!cluster_list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ swap_do_scheduled_discard(si); *scan_base = this_cpu_read(*si->cluster_next_cpu); *offset = *scan_base; goto new_cluster; } else return false; } /* * Other CPUs can use our cluster if they can't find a free cluster, * check if there is still free entry in the cluster */ tmp = cluster->next; max = min_t(unsigned long, si->max, (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); if (tmp < max) { ci = lock_cluster(si, tmp); while (tmp < max) { if (!si->swap_map[tmp]) break; tmp++; } unlock_cluster(ci); } if (tmp >= max) { cluster_set_null(&cluster->index); goto new_cluster; } cluster->next = tmp + 1; *offset = tmp; *scan_base = tmp; return true; } static void __del_from_avail_list(struct swap_info_struct *p) { int nid; assert_spin_locked(&p->lock); for_each_node(nid) plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); } static void del_from_avail_list(struct swap_info_struct *p) { spin_lock(&swap_avail_lock); __del_from_avail_list(p); spin_unlock(&swap_avail_lock); } static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned int end = offset + nr_entries - 1; if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); si->inuse_pages += nr_entries; if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; del_from_avail_list(si); } } static void add_to_avail_list(struct swap_info_struct *p) { int nid; spin_lock(&swap_avail_lock); for_each_node(nid) { WARN_ON(!plist_node_empty(&p->avail_lists[nid])); plist_add(&p->avail_lists[nid], &swap_avail_heads[nid]); } spin_unlock(&swap_avail_lock); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); if (offset < si->lowest_bit) si->lowest_bit = offset; if (end > si->highest_bit) { bool was_full = !si->highest_bit; WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } atomic_long_add(nr_entries, &nr_swap_pages); si->inuse_pages -= nr_entries; if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); frontswap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } clear_shadow_from_swap_cache(si->type, begin, end); } static void set_cluster_next(struct swap_info_struct *si, unsigned long next) { unsigned long prev; if (!(si->flags & SWP_SOLIDSTATE)) { si->cluster_next = next; return; } prev = this_cpu_read(*si->cluster_next_cpu); /* * Cross the swap address space size aligned trunk, choose * another trunk randomly to avoid lock contention on swap * address space if possible. */ if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != (next >> SWAP_ADDRESS_SPACE_SHIFT)) { /* No free swap slots available */ if (si->highest_bit <= si->lowest_bit) return; next = si->lowest_bit + prandom_u32_max(si->highest_bit - si->lowest_bit + 1); next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); next = max_t(unsigned int, next, si->lowest_bit); } this_cpu_write(*si->cluster_next_cpu, next); } static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[]) { struct swap_cluster_info *ci; unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; int n_ret = 0; bool scanned_many = false; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ si->flags += SWP_SCANNING; /* * Use percpu scan base for SSD to reduce lock contention on * cluster and swap cache. For HDD, sequential access is more * important. */ if (si->flags & SWP_SOLIDSTATE) scan_base = this_cpu_read(*si->cluster_next_cpu); else scan_base = si->cluster_next; offset = scan_base; /* SSD algorithm */ if (si->cluster_info) { if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } else if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info * case, just handled by scan_swap_map_try_ssd_cluster() above. */ scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ for (; last_in_cluster <= si->highest_bit; offset++) { if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; } checks: if (si->cluster_info) { while (scan_swap_map_ssd_cluster_conflict(si, offset)) { /* take a break if we already got some slots */ if (n_ret) goto done; if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } } if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; ci = lock_cluster(si, offset); /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; unlock_cluster(ci); spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed) goto checks; goto scan; /* check next one */ } if (si->swap_map[offset]) { unlock_cluster(ci); if (!n_ret) goto scan; else goto done; } WRITE_ONCE(si->swap_map[offset], usage); inc_cluster_info_page(si, si->cluster_info, offset); unlock_cluster(ci); swap_range_alloc(si, offset, 1); slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ if ((n_ret == nr) || (offset >= si->highest_bit)) goto done; /* search for next available slot */ /* time to take a break? */ if (unlikely(--latency_ration < 0)) { if (n_ret) goto done; spin_unlock(&si->lock); cond_resched(); spin_lock(&si->lock); latency_ration = LATENCY_LIMIT; } /* try to get more slots in cluster */ if (si->cluster_info) { if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto checks; } else if (si->cluster_nr && !si->swap_map[++offset]) { /* non-ssd case, still more slots in cluster? */ --si->cluster_nr; goto checks; } /* * Even if there's no free clusters available (fragmented), * try to scan a little more quickly with lock held unless we * have scanned too many slots already. */ if (!scanned_many) { unsigned long scan_limit; if (offset < scan_base) scan_limit = scan_base; else scan_limit = si->highest_bit; for (; offset <= scan_limit && --latency_ration > 0; offset++) { if (!si->swap_map[offset]) goto checks; } } done: set_cluster_next(si, offset + 1); si->flags -= SWP_SCANNING; return n_ret; scan: spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); goto checks; } if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } } offset = si->lowest_bit; while (offset < scan_base) { if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); goto checks; } if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } offset++; } spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; return n_ret; } static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot) { unsigned long idx; struct swap_cluster_info *ci; unsigned long offset; /* * Should not even be attempting cluster allocations when huge * page swap is disabled. Warn and fail the allocation. */ if (!IS_ENABLED(CONFIG_THP_SWAP)) { VM_WARN_ON_ONCE(1); return 0; } if (cluster_list_empty(&si->free_clusters)) return 0; idx = cluster_list_first(&si->free_clusters); offset = idx * SWAPFILE_CLUSTER; ci = lock_cluster(si, offset); alloc_cluster(si, idx); cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE); memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER); unlock_cluster(ci); swap_range_alloc(si, offset, SWAPFILE_CLUSTER); *slot = swp_entry(si->type, offset); return 1; } static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) { unsigned long offset = idx * SWAPFILE_CLUSTER; struct swap_cluster_info *ci; ci = lock_cluster(si, offset); memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER); cluster_set_count_flag(ci, 0, 0); free_cluster(si, idx); unlock_cluster(ci); swap_range_free(si, offset, SWAPFILE_CLUSTER); } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) { unsigned long size = swap_entry_size(entry_size); struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; /* Only single cluster request supported */ WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER); spin_lock(&swap_avail_lock); avail_pgs = atomic_long_read(&nr_swap_pages) / size; if (avail_pgs <= 0) { spin_unlock(&swap_avail_lock); goto noswap; } n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); atomic_long_sub(n_goal * size, &nr_swap_pages); start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); if (plist_node_empty(&si->avail_lists[node])) { spin_unlock(&si->lock); goto nextsi; } WARN(!si->highest_bit, "swap_info %d in list but !highest_bit\n", si->type); WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); __del_from_avail_list(si); spin_unlock(&si->lock); goto nextsi; } if (size == SWAPFILE_CLUSTER) { if (si->flags & SWP_BLKDEV) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries); spin_unlock(&si->lock); if (n_ret || size == SWAPFILE_CLUSTER) goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); cond_resched(); spin_lock(&swap_avail_lock); nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long)(n_goal - n_ret) * size, &nr_swap_pages); noswap: return n_ret; } static struct swap_info_struct *__swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; unsigned long offset; if (!entry.val) goto out; p = swp_swap_info(entry); if (!p) goto bad_nofile; if (data_race(!(p->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; return p; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; p = __swap_info_get(entry); if (!p) goto out; if (data_race(!p->swap_map[swp_offset(entry)])) goto bad_free; return p; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); out: return NULL; } static struct swap_info_struct *swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) spin_lock(&p->lock); return p; } static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p != q) { if (q != NULL) spin_unlock(&q->lock); if (p != NULL) spin_lock(&p->lock); } return p; } static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, unsigned long offset, unsigned char usage) { unsigned char count; unsigned char has_cache; count = p->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(p, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(p->swap_map[offset], usage); else WRITE_ONCE(p->swap_map[offset], SWAP_HAS_CACHE); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, page * table lock is held, etc., the swap entry may become invalid because * of swapoff. Then, we need to enclose all swap related functions * with get_swap_device() and put_swap_device(), unless the swap * functions call get/put_swap_device() by themselves. * * Note that when only holding the PTL, swapoff might succeed immediately * after freeing a swap entry. Therefore, immediately after * __swap_entry_free(), the swap info might become stale and should not * be touched without a prior get_swap_device(). * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (!percpu_ref_tryget_live(&si->users)) goto out; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(). */ smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: percpu_ref_put(&si->users); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(p, offset); usage = __swap_entry_free_locked(p, offset, 1); unlock_cluster_or_swap_info(p, ci); if (!usage) free_swap_slot(entry); return usage; } static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char count; ci = lock_cluster(p, offset); count = p->swap_map[offset]; VM_BUG_ON(count != SWAP_HAS_CACHE); p->swap_map[offset] = 0; dec_cluster_info_page(p, p->cluster_info, offset); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, 1); swap_range_free(p, offset, 1); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) __swap_entry_free(p, entry); } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_page(struct page *page, swp_entry_t entry) { unsigned long offset = swp_offset(entry); unsigned long idx = offset / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned char *map; unsigned int i, free_entries = 0; unsigned char val; int size = swap_entry_size(thp_nr_pages(page)); si = _swap_info_get(entry); if (!si) return; ci = lock_cluster_or_swap_info(si, offset); if (size == SWAPFILE_CLUSTER) { VM_BUG_ON(!cluster_is_huge(ci)); map = si->swap_map + offset; for (i = 0; i < SWAPFILE_CLUSTER; i++) { val = map[i]; VM_BUG_ON(!(val & SWAP_HAS_CACHE)); if (val == SWAP_HAS_CACHE) free_entries++; } cluster_clear_huge(ci); if (free_entries == SWAPFILE_CLUSTER) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER); swap_free_cluster(si, idx); spin_unlock(&si->lock); return; } } for (i = 0; i < size; i++, entry.val++) { if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { unlock_cluster_or_swap_info(si, ci); free_swap_slot(entry); if (i == size - 1) return; lock_cluster_or_swap_info(si, offset); } } unlock_cluster_or_swap_info(si, ci); } #ifdef CONFIG_THP_SWAP int split_swap_cluster(swp_entry_t entry) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); si = _swap_info_get(entry); if (!si) return -EBUSY; ci = lock_cluster(si, offset); cluster_clear_huge(ci); unlock_cluster(ci); return 0; } #endif static int swp_entry_cmp(const void *ent1, const void *ent2) { const swp_entry_t *e1 = ent1, *e2 = ent2; return (int)swp_type(*e1) - (int)swp_type(*e2); } void swapcache_free_entries(swp_entry_t *entries, int n) { struct swap_info_struct *p, *prev; int i; if (n <= 0) return; prev = NULL; p = NULL; /* * Sort swap entries by swap device, so each lock is only taken once. * nr_swapfiles isn't absolutely correct, but the overhead of sort() is * so low that it isn't necessary to optimize further. */ if (nr_swapfiles > 1) sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); for (i = 0; i < n; ++i) { p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_free(p, entries[i]); prev = p; } if (p) spin_unlock(&p->lock); } /* * How many references to page are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int page_swapcount(struct page *page) { int count = 0; struct swap_info_struct *p; struct swap_cluster_info *ci; swp_entry_t entry; unsigned long offset; entry.val = page_private(page); p = _swap_info_get(entry); if (p) { offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); unlock_cluster_or_swap_info(p, ci); } return count; } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si; pgoff_t offset = swp_offset(entry); int count = 0; si = get_swap_device(entry); if (si) { count = swap_count(si->swap_map[offset]); put_swap_device(si); } return count; } static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { int count = 0; pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster_or_swap_info(si, ci); return count; } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int __swp_swapcount(swp_entry_t entry) { int count = 0; struct swap_info_struct *si; si = get_swap_device(entry); if (si) { count = swap_swapcount(si, entry); put_swap_device(si); } return count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *p; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; p = _swap_info_get(entry); if (!p) return 0; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(p->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_atomic(page); tmp_count = map[offset]; kunmap_atomic(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster_or_swap_info(p, ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER); int i; bool ret = false; ci = lock_cluster_or_swap_info(si, offset); if (!ci || !cluster_is_huge(ci)) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < SWAPFILE_CLUSTER; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster_or_swap_info(si, ci); return ret; } static bool page_swapped(struct page *page) { swp_entry_t entry; struct swap_info_struct *si; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) return page_swapcount(page) != 0; page = compound_head(page); entry.val = page_private(page); si = _swap_info_get(entry); if (si) return swap_page_trans_huge_swapped(si, entry); return false; } static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount, int *total_swapcount) { int i, map_swapcount, _total_mapcount, _total_swapcount; unsigned long offset = 0; struct swap_info_struct *si; struct swap_cluster_info *ci = NULL; unsigned char *map = NULL; int mapcount, swapcount = 0; /* hugetlbfs shouldn't call it */ VM_BUG_ON_PAGE(PageHuge(page), page); if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) { mapcount = page_trans_huge_mapcount(page, total_mapcount); if (PageSwapCache(page)) swapcount = page_swapcount(page); if (total_swapcount) *total_swapcount = swapcount; return mapcount + swapcount; } page = compound_head(page); _total_mapcount = _total_swapcount = map_swapcount = 0; if (PageSwapCache(page)) { swp_entry_t entry; entry.val = page_private(page); si = _swap_info_get(entry); if (si) { map = si->swap_map; offset = swp_offset(entry); } } if (map) ci = lock_cluster(si, offset); for (i = 0; i < HPAGE_PMD_NR; i++) { mapcount = atomic_read(&page[i]._mapcount) + 1; _total_mapcount += mapcount; if (map) { swapcount = swap_count(map[offset + i]); _total_swapcount += swapcount; } map_swapcount = max(map_swapcount, mapcount + swapcount); } unlock_cluster(ci); if (PageDoubleMap(page)) { map_swapcount -= 1; _total_mapcount -= HPAGE_PMD_NR; } mapcount = compound_mapcount(page); map_swapcount += mapcount; _total_mapcount += mapcount; if (total_mapcount) *total_mapcount = _total_mapcount; if (total_swapcount) *total_swapcount = _total_swapcount; return map_swapcount; } /* * We can write to an anon page without COW if there are no other references * to it. And as a side-effect, free up its swap: because the old content * on disk will never be read, and seeking back there to write new content * later would only waste time away from clustering. * * NOTE: total_map_swapcount should not be relied upon by the caller if * reuse_swap_page() returns false, but it may be always overwritten * (see the other implementation for CONFIG_SWAP=n). */ bool reuse_swap_page(struct page *page, int *total_map_swapcount) { int count, total_mapcount, total_swapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); if (unlikely(PageKsm(page))) return false; count = page_trans_huge_map_swapcount(page, &total_mapcount, &total_swapcount); if (total_map_swapcount) *total_map_swapcount = total_mapcount + total_swapcount; if (count == 1 && PageSwapCache(page) && (likely(!PageTransCompound(page)) || /* The remaining swap count will be freed soon */ total_swapcount == page_swapcount(page))) { if (!PageWriteback(page)) { page = compound_head(page); delete_from_swap_cache(page); SetPageDirty(page); } else { swp_entry_t entry; struct swap_info_struct *p; entry.val = page_private(page); p = swap_info_get(entry); if (p->flags & SWP_STABLE_WRITES) { spin_unlock(&p->lock); return false; } spin_unlock(&p->lock); } } return count <= 1; } /* * If swap is getting full, or if there are no more mappings of this page, * then try_to_free_swap is called to free its swap space. */ int try_to_free_swap(struct page *page) { VM_BUG_ON_PAGE(!PageLocked(page), page); if (!PageSwapCache(page)) return 0; if (PageWriteback(page)) return 0; if (page_swapped(page)) return 0; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to try_to_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a page which has already been recorded in the * image as a clean swapcache page, and then reuse its swap for * another page of the image. On waking from hibernation, the * original page might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return 0; page = compound_head(page); delete_from_swap_cache(page); SetPageDirty(page); return 1; } /* * Free the swap entry like above, but also try to * free the page cache entry if it is the last user. */ int free_swap_and_cache(swp_entry_t entry) { struct swap_info_struct *p; unsigned char count; if (non_swap_entry(entry)) return 1; p = get_swap_device(entry); if (p) { if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) { put_swap_device(p); return 0; } count = __swap_entry_free(p, entry); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); put_swap_device(p); } return p != NULL; } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ spin_lock(&si->lock); if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry)) atomic_long_dec(&nr_swap_pages); spin_unlock(&si->lock); fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_swap_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct page *page) { struct page *swapcache; spinlock_t *ptl; pte_t *pte; int ret = 1; swapcache = page; page = ksm_might_need_to_copy(page, vma, addr); if (unlikely(!page)) return -ENOMEM; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { ret = 0; goto out; } dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { page_add_anon_rmap(page, vma, addr, false); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr, false); lru_cache_add_inactive_or_unevictable(page, vma); } swap_free(entry); out: pte_unmap_unlock(pte, ptl); if (page != swapcache) { unlock_page(page); put_page(page); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct page *page; swp_entry_t entry; pte_t *pte; struct swap_info_struct *si; unsigned long offset; int ret = 0; volatile unsigned char *swap_map; si = swap_info[type]; pte = pte_offset_map(pmd, addr); do { if (!is_swap_pte(*pte)) continue; entry = pte_to_swp_entry(*pte); if (swp_type(entry) != type) continue; offset = swp_offset(entry); if (frontswap && !frontswap_test(si, offset)) continue; pte_unmap(pte); swap_map = &si->swap_map[offset]; page = lookup_swap_cache(entry, vma, addr); if (!page) { struct vm_fault vmf = { .vma = vma, .address = addr, .pmd = pmd, }; page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!page) { if (*swap_map == 0 || *swap_map == SWAP_MAP_BAD) goto try_next; return -ENOMEM; } lock_page(page); wait_on_page_writeback(page); ret = unuse_pte(vma, pmd, addr, entry, page); if (ret < 0) { unlock_page(page); put_page(page); goto out; } try_to_free_swap(page); unlock_page(page); put_page(page); if (*fs_pages_to_unuse && !--(*fs_pages_to_unuse)) { ret = FRONTSWAP_PAGES_UNUSED; goto out; } try_next: pte = pte_offset_map(pmd, addr); } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap(pte - 1); ret = 0; out: return ret; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; ret = unuse_pte_range(vma, pmd, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct vm_area_struct *vma; int ret = 0; mmap_read_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type, frontswap, fs_pages_to_unuse); if (ret) break; } cond_resched(); } mmap_read_unlock(mm); return ret; } /* * Scan swap_map (or frontswap_map if frontswap parameter is true) * from current position to next entry still in use. Return 0 * if there are no inuse entries after prev till end of the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev, bool frontswap) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) if (!frontswap || frontswap_test(si, i)) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } /* * If the boolean frontswap is true, only unuse pages_to_unuse pages; * pages_to_unuse==0 means all pages; ignored if frontswap is false */ int try_to_unuse(unsigned int type, bool frontswap, unsigned long pages_to_unuse) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct page *page; swp_entry_t entry; unsigned int i; if (!READ_ONCE(si->inuse_pages)) return 0; if (!frontswap) pages_to_unuse = 0; retry: retval = shmem_unuse(type, frontswap, &pages_to_unuse); if (retval) goto out; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type, frontswap, &pages_to_unuse); if (retval) { mmput(prev_mm); goto out; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i, frontswap)) != 0) { entry = swp_entry(type, i); page = find_get_page(swap_address_space(entry), i); if (!page) continue; /* * It is conceivable that a racing task removed this page from * swap cache just before we acquired the page lock. The page * might even be back in swap cache on another swap area. But * that is okay, try_to_free_swap() only removes stale pages. */ lock_page(page); wait_on_page_writeback(page); try_to_free_swap(page); unlock_page(page); put_page(page); /* * For frontswap, we just need to unuse pages_to_unuse, if * it was specified. Need not check frontswap again here as * we already zeroed out pages_to_unuse if not frontswap. */ if (pages_to_unuse && --pages_to_unuse == 0) goto out; } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() above fails, * that mm is likely to be freeing swap from exit_mmap(), which proceeds * at its own independent pace; and even shmem_writepage() could have * been preempted after get_swap_page(), temporarily hiding that swap. * It's easy and robust (though cpu-intensive) just to keep retrying. */ if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; retval = -EINTR; } out: return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. An ordered list of swap extents * is built at swapon time and is then used at swap_writepage/swap_readpage * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent list operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into an ordered extent list, in PAGE_SIZE chunks. If * some stray blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the list. To avoid much list walking, we cache the previous * search location in `curr_swap_extent', and start new searches from there. * This is extremely effective. The average number of iterations in * map_swap_page() has been measured at about 0.3 per page. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret >= 0) sis->flags |= SWP_ACTIVATED; if (!ret) { sis->flags |= SWP_FS_OPS; ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *p) { struct block_device *bdev; if (p->bdev) bdev = p->bdev; else bdev = p->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { int i; if (prio >= 0) p->prio = prio; else p->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ p->list.prio = -p->prio; for_each_node(i) { if (p->prio >= 0) p->avail_lists[i].prio = -p->prio; else { if (swap_node(p) == i) p->avail_lists[i].prio = 1; else p->avail_lists[i].prio = -p->prio; } } p->swap_map = swap_map; p->cluster_info = cluster_info; } static void _enable_swap_info(struct swap_info_struct *p) { p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for get_swap_page(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&p->list, &swap_active_head); add_to_avail_list(p); } static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, prio, swap_map, cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&p->users); spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, p->prio, p->swap_map, p->cluster_info); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } bool has_usable_swap(void) { bool ret = true; spin_lock(&swap_lock); if (plist_head_empty(&swap_active_head)) ret = false; spin_unlock(&swap_lock); return ret; } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; struct swap_cluster_info *cluster_info; unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); /* * Wait for swap operations protected by get/put_swap_device() * to complete. * * We need synchronize_rcu() here to protect the accessing to * the swap cache data structure. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev))) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); spin_lock(&p->lock); } swap_file = p->swap_file; old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, old_block_size); blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned int bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = si->pages << (PAGE_SHIFT - 10); inuse = si->inuse_pages << (PAGE_SHIFT - 10); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%u\t%s%u\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) { int error; if (S_ISBLK(inode->i_mode)) { p->bdev = blkdev_get_by_dev(inode->i_rdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); if (IS_ERR(p->bdev)) { error = PTR_ERR(p->bdev); p->bdev = NULL; return error; } p->old_block_size = block_size(p->bdev); error = set_blocksize(p->bdev, PAGE_SIZE); if (error < 0) return error; /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (blk_queue_is_zoned(p->bdev->bd_disk->queue)) return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *p, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } p->lowest_bit = 1; p->cluster_next = 1; p->cluster_nr = 0; maxpages = max_swapfile_size(); last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", maxpages << (PAGE_SHIFT - 10), last_page << (PAGE_SHIFT - 10)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } p->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long maxpages, sector_t *span) { unsigned int j, k; unsigned int nr_good_pages; int nr_extents; unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); unsigned long col = p->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; unsigned long i, idx; nr_good_pages = maxpages - 1; /* omit header page */ cluster_list_init(&p->free_clusters); cluster_list_init(&p->discard_clusters); for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; /* * Haven't marked the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, page_nr); } } /* Haven't marked the cluster free yet, no list operation involved */ for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(p, cluster_info, i); if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; /* * Not mark the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, 0); p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, span); if (nr_extents < 0) return nr_extents; nr_good_pages = p->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } if (!cluster_info) return nr_extents; /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { idx = i * SWAP_CLUSTER_COLS + j; if (idx >= nr_clusters) continue; if (cluster_count(&cluster_info[idx])) continue; cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); cluster_list_add_tail(&p->free_clusters, cluster_info, idx); } } return nr_extents; } /* * Helper to sys_swapon determining if a given swap * backing device queue supports DISCARD operations. */ static bool swap_discardable(struct swap_info_struct *si) { struct request_queue *q = bdev_get_queue(si->bdev); if (!q || !blk_queue_discard(q)) return false; return true; } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; struct swap_cluster_info *cluster_info = NULL; unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; p = alloc_swap_info(); if (IS_ERR(p)) return PTR_ERR(p); INIT_WORK(&p->discard_work, swap_discard_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } p->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(p, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->readpage) { error = -EINVAL; goto bad_swap_unlock_inode; } page = read_mapping_page(mapping, 0, swap_file); if (IS_ERR(page)) { error = PTR_ERR(page); goto bad_swap_unlock_inode; } swap_header = kmap(page); maxpages = read_swap_header(p, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue)) p->flags |= SWP_STABLE_WRITES; if (p->bdev && p->bdev->bd_disk->fops->rw_page) p->flags |= SWP_SYNCHRONOUS_IO; if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { int cpu; unsigned long ci, nr_cluster; p->flags |= SWP_SOLIDSTATE; p->cluster_next_cpu = alloc_percpu(unsigned int); if (!p->cluster_next_cpu) { error = -ENOMEM; goto bad_swap_unlock_inode; } /* * select a random position to start with to help wear leveling * SSD */ for_each_possible_cpu(cpu) { per_cpu(*p->cluster_next_cpu, cpu) = 1 + prandom_u32_max(p->highest_bit); } nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); cluster_info = kvcalloc(nr_cluster, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) { error = -ENOMEM; goto bad_swap_unlock_inode; } for (ci = 0; ci < nr_cluster; ci++) spin_lock_init(&((cluster_info + ci)->lock)); p->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!p->percpu_cluster) { error = -ENOMEM; goto bad_swap_unlock_inode; } for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(p->percpu_cluster, cpu); cluster_set_null(&cluster->index); } } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } error = swap_cgroup_swapon(p->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } /* frontswap enabled? set up bit-per-page map for frontswap */ if (IS_ENABLED(CONFIG_FRONTSWAP)) frontswap_map = kvcalloc(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL); if (p->bdev && (swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) p->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) p->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (p->flags & SWP_AREA_DISCARD) { int err = discard_swap(p); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", p, err); } } error = init_swap_address_space(p->type, maxpages); if (error) goto bad_swap_unlock_inode; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_address_space; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", (p->flags & SWP_DISCARDABLE) ? "D" : "", (p->flags & SWP_AREA_DISCARD) ? "s" : "", (p->flags & SWP_PAGE_DISCARD) ? "c" : "", (frontswap_map) ? "FS" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_address_space: exit_swap_address_space(p->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } inode = NULL; destroy_swap_extents(p); swap_cgroup_swapoff(p->type); spin_lock(&swap_lock); p->swap_file = NULL; p->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (page && !IS_ERR(page)) { kunmap(page); put_page(page); } if (name) putname(name); if (inode) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += si->inuse_pages; } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that a swap entry is valid and increment its swap map count. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) { struct swap_info_struct *p; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err; p = get_swap_device(entry); if (!p) return -EINVAL; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = p->swap_map[offset]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; err = 0; if (usage == SWAP_HAS_CACHE) { /* set SWAP_HAS_CACHE if there is no cache and entry is used */ if (!has_cache && count) has_cache = SWAP_HAS_CACHE; else if (has_cache) /* someone else added cache */ err = -EEXIST; else /* no users remaining */ err = -ENOENT; } else if (count || has_cache) { if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) err = -EINVAL; else if (swap_count_continued(p, offset, count)) count = COUNT_CONTINUED; else err = -ENOMEM; } else err = -ENOENT; /* unused swap entry */ WRITE_ONCE(p->swap_map[offset], count | has_cache); unlock_out: unlock_cluster_or_swap_info(p, ci); if (p) put_swap_device(p); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry) { __swap_duplicate(entry, SWAP_MAP_SHMEM); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: swap entry for which we allocate swap cache. * * Called when allocating swap cache for existing swap entry, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry) { return __swap_duplicate(entry, SWAP_HAS_CACHE); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); } struct swap_info_struct *page_swap_info(struct page *page) { swp_entry_t entry = { .val = page_private(page) }; return swp_swap_info(entry); } /* * out-of-line __page_file_ methods to avoid include hell. */ struct address_space *__page_file_mapping(struct page *page) { return page_swap_info(page)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(__page_file_mapping); pgoff_t __page_file_index(struct page *page) { swp_entry_t swap = { .val = page_private(page) }; return swp_offset(swap); } EXPORT_SYMBOL_GPL(__page_file_index); /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } spin_lock(&si->lock); offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } /* * We are fortunate that although vmalloc_to_page uses pte_offset_map, * no architecture is using highmem pages for kernel page tables: so it * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps. */ head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_atomic(list_page) + offset; count = *map; kunmap_atomic(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); spin_unlock(&si->lock); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster * lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_atomic(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_atomic(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_atomic(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_atomic(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_atomic(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_atomic(page) + offset; *map = COUNT_CONTINUED; kunmap_atomic(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_atomic(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_atomic(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_atomic(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_atomic(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { struct swap_info_struct *si, *next; int nid = page_to_nid(page); if (!(gfp_mask & __GFP_IO)) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_queue) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(bdev_get_queue(si->bdev), true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); return 0; } subsys_initcall(swapfile_init); |
| 5 15 14 1 2 5 2 4 5 10 12 1 3 1 1 1 6 3 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 | // SPDX-License-Identifier: GPL-2.0-only /* * File: datagram.c * * Datagram (ISI) Phonet sockets * * Copyright (C) 2008 Nokia Corporation. * * Authors: Sakari Ailus <sakari.ailus@nokia.com> * Rémi Denis-Courmont */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/socket.h> #include <asm/ioctls.h> #include <net/sock.h> #include <linux/phonet.h> #include <linux/export.h> #include <net/phonet/phonet.h> static int pn_backlog_rcv(struct sock *sk, struct sk_buff *skb); /* associated socket ceases to exist */ static void pn_sock_close(struct sock *sk, long timeout) { sk_common_release(sk); } static int pn_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct sk_buff *skb; int answ; switch (cmd) { case SIOCINQ: lock_sock(sk); skb = skb_peek(&sk->sk_receive_queue); answ = skb ? skb->len : 0; release_sock(sk); return put_user(answ, (int __user *)arg); case SIOCPNADDRESOURCE: case SIOCPNDELRESOURCE: { u32 res; if (get_user(res, (u32 __user *)arg)) return -EFAULT; if (res >= 256) return -EINVAL; if (cmd == SIOCPNADDRESOURCE) return pn_sock_bind_res(sk, res); else return pn_sock_unbind_res(sk, res); } } return -ENOIOCTLCMD; } /* Destroy socket. All references are gone. */ static void pn_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); } static int pn_init(struct sock *sk) { sk->sk_destruct = pn_destruct; return 0; } static int pn_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_pn *, target, msg->msg_name); struct sk_buff *skb; int err; if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL| MSG_CMSG_COMPAT)) return -EOPNOTSUPP; if (target == NULL) return -EDESTADDRREQ; if (msg->msg_namelen < sizeof(struct sockaddr_pn)) return -EINVAL; if (target->spn_family != AF_PHONET) return -EAFNOSUPPORT; skb = sock_alloc_send_skb(sk, MAX_PHONET_HEADER + len, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) return err; skb_reserve(skb, MAX_PHONET_HEADER); err = memcpy_from_msg((void *)skb_put(skb, len), msg, len); if (err < 0) { kfree_skb(skb); return err; } /* * Fill in the Phonet header and * finally pass the packet forwards. */ err = pn_skb_send(sk, skb, target); /* If ok, return len. */ return (err >= 0) ? len : err; } static int pn_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct sk_buff *skb = NULL; struct sockaddr_pn sa; int rval = -EOPNOTSUPP; int copylen; if (flags & ~(MSG_PEEK|MSG_TRUNC|MSG_DONTWAIT|MSG_NOSIGNAL| MSG_CMSG_COMPAT)) goto out_nofree; skb = skb_recv_datagram(sk, flags, noblock, &rval); if (skb == NULL) goto out_nofree; pn_skb_get_src_sockaddr(skb, &sa); copylen = skb->len; if (len < copylen) { msg->msg_flags |= MSG_TRUNC; copylen = len; } rval = skb_copy_datagram_msg(skb, 0, msg, copylen); if (rval) { rval = -EFAULT; goto out; } rval = (flags & MSG_TRUNC) ? skb->len : copylen; if (msg->msg_name != NULL) { __sockaddr_check_size(sizeof(sa)); memcpy(msg->msg_name, &sa, sizeof(sa)); *addr_len = sizeof(sa); } out: skb_free_datagram(sk, skb); out_nofree: return rval; } /* Queue an skb for a sock. */ static int pn_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int err = sock_queue_rcv_skb(sk, skb); if (err < 0) kfree_skb(skb); return err ? NET_RX_DROP : NET_RX_SUCCESS; } /* Module registration */ static struct proto pn_proto = { .close = pn_sock_close, .ioctl = pn_ioctl, .init = pn_init, .sendmsg = pn_sendmsg, .recvmsg = pn_recvmsg, .backlog_rcv = pn_backlog_rcv, .hash = pn_sock_hash, .unhash = pn_sock_unhash, .get_port = pn_sock_get_port, .obj_size = sizeof(struct pn_sock), .owner = THIS_MODULE, .name = "PHONET", }; static const struct phonet_protocol pn_dgram_proto = { .ops = &phonet_dgram_ops, .prot = &pn_proto, .sock_type = SOCK_DGRAM, }; int __init isi_register(void) { return phonet_proto_register(PN_PROTO_PHONET, &pn_dgram_proto); } void __exit isi_unregister(void) { phonet_proto_unregister(PN_PROTO_PHONET, &pn_dgram_proto); } |
| 3238 1122 2770 708 79 378 532 5 30 2 3 2261 905 12 12 37 98 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /** * list_tail_rcu - returns the prev pointer of the head of the list * @head: the head of the list * * Note: This should only be used with the list header, and even then * only if list_del() and similar primitives are not also used on the * list header. */ #define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #define __list_check_srcu(cond) \ ({ \ RCU_LOCKDEP_WARN(!(cond), \ "RCU-list traversed without holding the required lock!");\ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #define __list_check_srcu(cond) ({ }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); ASSERT_EXCLUSIVE_ACCESS(*first); ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * They do not exist because they would lead to subtle race conditions: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list might be non-empty when list_empty_rcu() checks it, but it * might have become empty by the time that list_first_entry_rcu() rereads * the ->next pointer, which would result in a SEGV. * * When not using RCU, it is OK for list_first_entry() to re-read that * pointer because both functions should be protected by some lock that * blocks writers. * * When using RCU, list_empty() uses READ_ONCE() to fetch the * RCU-protected ->next pointer and then compares it to the address of the * list head. However, it neither dereferences this pointer nor provides * this pointer to its caller. Thus, READ_ONCE() suffices (that is, * rcu_dereference() is not needed), which means that list_empty() can be * used anywhere you would want to use list_empty_rcu(). Just don't * expect anything useful to happen if you do a subsequent lockless * call to list_first_entry_rcu()!!! * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the first element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define list_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) WRITE_ONCE(new->next->pprev, &new->next); WRITE_ONCE(old->pprev, LIST_POISON2); } /** * hlists_swap_heads_rcu - swap the lists the hlist heads point to * @left: The hlist head on the left * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) { struct hlist_node *node1 = left->first; struct hlist_node *node2 = right->first; rcu_assign_pointer(left->first, node2); rcu_assign_pointer(right->first, node1); WRITE_ONCE(node2->pprev, &left->first); WRITE_ONCE(node1->pprev, &right->first); } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); WRITE_ONCE(next->pprev, &n->next); } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define hlist_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NFNETLINK_H #define _NFNETLINK_H #include <linux/netlink.h> #include <linux/capability.h> #include <net/netlink.h> #include <uapi/linux/netfilter/nfnetlink.h> struct nfnl_info { struct net *net; struct sock *sk; const struct nlmsghdr *nlh; const struct nfgenmsg *nfmsg; struct netlink_ext_ack *extack; }; enum nfnl_callback_type { NFNL_CB_UNSPEC = 0, NFNL_CB_MUTEX, NFNL_CB_RCU, NFNL_CB_BATCH, }; struct nfnl_callback { int (*call)(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]); const struct nla_policy *policy; enum nfnl_callback_type type; __u16 attr_count; }; enum nfnl_abort_action { NFNL_ABORT_NONE = 0, NFNL_ABORT_AUTOLOAD, NFNL_ABORT_VALIDATE, }; struct nfnetlink_subsystem { const char *name; __u8 subsys_id; /* nfnetlink subsystem ID */ __u8 cb_count; /* number of callbacks */ const struct nfnl_callback *cb; /* callback for individual types */ struct module *owner; int (*commit)(struct net *net, struct sk_buff *skb); int (*abort)(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action); bool (*valid_genid)(struct net *net, u32 genid); }; int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n); int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n); int nfnetlink_has_listeners(struct net *net, unsigned int group); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid); void nfnetlink_broadcast(struct net *net, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); static inline u16 nfnl_msg_type(u8 subsys, u8 msg_type) { return subsys << 8 | msg_type; } static inline void nfnl_fill_hdr(struct nlmsghdr *nlh, u8 family, u8 version, __be16 res_id) { struct nfgenmsg *nfmsg; nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = family; nfmsg->version = version; nfmsg->res_id = res_id; } static inline struct nlmsghdr *nfnl_msg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int flags, u8 family, u8 version, __be16 res_id) { struct nlmsghdr *nlh; nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg), flags); if (!nlh) return NULL; nfnl_fill_hdr(nlh, family, version, res_id); return nlh; } void nfnl_lock(__u8 subsys_id); void nfnl_unlock(__u8 subsys_id); #ifdef CONFIG_PROVE_LOCKING bool lockdep_nfnl_is_held(__u8 subsys_id); #else static inline bool lockdep_nfnl_is_held(__u8 subsys_id) { return true; } #endif /* CONFIG_PROVE_LOCKING */ #define MODULE_ALIAS_NFNL_SUBSYS(subsys) \ MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys)) #endif /* _NFNETLINK_H */ |
| 29 6 1 4 2 14 2 12 20 487 453 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/netlink.h> #include <linux/nospec.h> #include <linux/rtnetlink.h> #include <linux/types.h> #include <net/ip.h> #include <net/net_namespace.h> #include <net/tcp.h> static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len, u32 *metrics, struct netlink_ext_ack *extack) { bool ecn_ca = false; struct nlattr *nla; int remaining; if (!fc_mx) return 0; nla_for_each_attr(nla, fc_mx, fc_mx_len, remaining) { int type = nla_type(nla); u32 val; if (!type) continue; if (type > RTAX_MAX) { NL_SET_ERR_MSG(extack, "Invalid metric type"); return -EINVAL; } type = array_index_nospec(type, RTAX_MAX + 1); if (type == RTAX_CC_ALGO) { char tmp[TCP_CA_NAME_MAX]; nla_strscpy(tmp, nla, sizeof(tmp)); val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca); if (val == TCP_CA_UNSPEC) { NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm"); return -EINVAL; } } else { if (nla_len(nla) != sizeof(u32)) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid attribute in metrics"); return -EINVAL; } val = nla_get_u32(nla); } if (type == RTAX_ADVMSS && val > 65535 - 40) val = 65535 - 40; if (type == RTAX_MTU && val > 65535 - 15) val = 65535 - 15; if (type == RTAX_HOPLIMIT && val > 255) val = 255; if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) { NL_SET_ERR_MSG(extack, "Unknown flag set in feature mask in metrics attribute"); return -EINVAL; } metrics[type - 1] = val; } if (ecn_ca) metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; return 0; } struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, int fc_mx_len, struct netlink_ext_ack *extack) { struct dst_metrics *fib_metrics; int err; if (!fc_mx) return (struct dst_metrics *)&dst_default_metrics; fib_metrics = kzalloc(sizeof(*fib_metrics), GFP_KERNEL); if (unlikely(!fib_metrics)) return ERR_PTR(-ENOMEM); err = ip_metrics_convert(net, fc_mx, fc_mx_len, fib_metrics->metrics, extack); if (!err) { refcount_set(&fib_metrics->refcnt, 1); } else { kfree(fib_metrics); fib_metrics = ERR_PTR(err); } return fib_metrics; } EXPORT_SYMBOL_GPL(ip_fib_metrics_init); |
| 20 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Statically sized hash table implementation * (C) 2012 Sasha Levin <levinsasha928@gmail.com> */ #ifndef _LINUX_HASHTABLE_H #define _LINUX_HASHTABLE_H #include <linux/list.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> #include <linux/rculist.h> #define DEFINE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } #define DEFINE_READ_MOSTLY_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] __read_mostly = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } #define DECLARE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] #define HASH_SIZE(name) (ARRAY_SIZE(name)) #define HASH_BITS(name) ilog2(HASH_SIZE(name)) /* Use hash_32 when possible to allow for fast 32bit hashing in 64bit kernels. */ #define hash_min(val, bits) \ (sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits)) static inline void __hash_init(struct hlist_head *ht, unsigned int sz) { unsigned int i; for (i = 0; i < sz; i++) INIT_HLIST_HEAD(&ht[i]); } /** * hash_init - initialize a hash table * @hashtable: hashtable to be initialized * * Calculates the size of the hashtable from the given parameter, otherwise * same as hash_init_size. * * This has to be a macro since HASH_BITS() will not work on pointers since * it calculates the size during preprocessing. */ #define hash_init(hashtable) __hash_init(hashtable, HASH_SIZE(hashtable)) /** * hash_add - add an object to a hashtable * @hashtable: hashtable to add to * @node: the &struct hlist_node of the object to be added * @key: the key of the object to be added */ #define hash_add(hashtable, node, key) \ hlist_add_head(node, &hashtable[hash_min(key, HASH_BITS(hashtable))]) /** * hash_add_rcu - add an object to a rcu enabled hashtable * @hashtable: hashtable to add to * @node: the &struct hlist_node of the object to be added * @key: the key of the object to be added */ #define hash_add_rcu(hashtable, node, key) \ hlist_add_head_rcu(node, &hashtable[hash_min(key, HASH_BITS(hashtable))]) /** * hash_hashed - check whether an object is in any hashtable * @node: the &struct hlist_node of the object to be checked */ static inline bool hash_hashed(struct hlist_node *node) { return !hlist_unhashed(node); } static inline bool __hash_empty(struct hlist_head *ht, unsigned int sz) { unsigned int i; for (i = 0; i < sz; i++) if (!hlist_empty(&ht[i])) return false; return true; } /** * hash_empty - check whether a hashtable is empty * @hashtable: hashtable to check * * This has to be a macro since HASH_BITS() will not work on pointers since * it calculates the size during preprocessing. */ #define hash_empty(hashtable) __hash_empty(hashtable, HASH_SIZE(hashtable)) /** * hash_del - remove an object from a hashtable * @node: &struct hlist_node of the object to remove */ static inline void hash_del(struct hlist_node *node) { hlist_del_init(node); } /** * hash_del_rcu - remove an object from a rcu enabled hashtable * @node: &struct hlist_node of the object to remove */ static inline void hash_del_rcu(struct hlist_node *node) { hlist_del_init_rcu(node); } /** * hash_for_each - iterate over a hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each(name, bkt, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry(obj, &name[bkt], member) /** * hash_for_each_rcu - iterate over a rcu enabled hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each_rcu(name, bkt, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry_rcu(obj, &name[bkt], member) /** * hash_for_each_safe - iterate over a hashtable safe against removal of * hash entry * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @tmp: a &struct hlist_node used for temporary storage * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each_safe(name, bkt, tmp, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry_safe(obj, tmp, &name[bkt], member) /** * hash_for_each_possible - iterate over all possible objects hashing to the * same bucket * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible(name, obj, member, key) \ hlist_for_each_entry(obj, &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_rcu - iterate over all possible objects hashing to the * same bucket in an rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible_rcu(name, obj, member, key, cond...) \ hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\ member, ## cond) /** * hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing * to the same bucket in an rcu enabled hashtable in a rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over * * This is the same as hash_for_each_possible_rcu() except that it does * not do any RCU debugging or tracing. */ #define hash_for_each_possible_rcu_notrace(name, obj, member, key) \ hlist_for_each_entry_rcu_notrace(obj, \ &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_safe - iterate over all possible objects hashing to the * same bucket safe against removals * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @tmp: a &struct hlist_node used for temporary storage * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible_safe(name, obj, tmp, member, key) \ hlist_for_each_entry_safe(obj, tmp,\ &name[hash_min(key, HASH_BITS(name))], member) #endif |
| 7 7 7 7 7 7 7 13 13 13 22 9 9 13 11 2 13 13 13 13 6 13 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include "socket.h" #include "timers.h" #include "device.h" #include "ratelimiter.h" #include "peer.h" #include "messages.h" #include <linux/module.h> #include <linux/rtnetlink.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/suspend.h> #include <net/dst_metadata.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/ip_tunnels.h> #include <net/addrconf.h> static LIST_HEAD(device_list); static int wg_open(struct net_device *dev) { struct in_device *dev_v4 = __in_dev_get_rtnl(dev); struct inet6_dev *dev_v6 = __in6_dev_get(dev); struct wg_device *wg = netdev_priv(dev); struct wg_peer *peer; int ret; if (dev_v4) { /* At some point we might put this check near the ip_rt_send_ * redirect call of ip_forward in net/ipv4/ip_forward.c, similar * to the current secpath check. */ IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false; } if (dev_v6) dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE; mutex_lock(&wg->device_update_lock); ret = wg_socket_init(wg, wg->incoming_port); if (ret < 0) goto out; list_for_each_entry(peer, &wg->peer_list, peer_list) { wg_packet_send_staged_packets(peer); if (peer->persistent_keepalive_interval) wg_packet_send_keepalive(peer); } out: mutex_unlock(&wg->device_update_lock); return ret; } #ifdef CONFIG_PM_SLEEP static int wg_pm_notification(struct notifier_block *nb, unsigned long action, void *data) { struct wg_device *wg; struct wg_peer *peer; /* If the machine is constantly suspending and resuming, as part of * its normal operation rather than as a somewhat rare event, then we * don't actually want to clear keys. */ if (IS_ENABLED(CONFIG_PM_AUTOSLEEP) || IS_ENABLED(CONFIG_ANDROID)) return 0; if (action != PM_HIBERNATION_PREPARE && action != PM_SUSPEND_PREPARE) return 0; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) { del_timer(&peer->timer_zero_key_material); wg_noise_handshake_clear(&peer->handshake); wg_noise_keypairs_clear(&peer->keypairs); } mutex_unlock(&wg->device_update_lock); } rtnl_unlock(); rcu_barrier(); return 0; } static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification }; #endif static int wg_stop(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); struct wg_peer *peer; struct sk_buff *skb; mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) { wg_packet_purge_staged_packets(peer); wg_timers_stop(peer); wg_noise_handshake_clear(&peer->handshake); wg_noise_keypairs_clear(&peer->keypairs); wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); } mutex_unlock(&wg->device_update_lock); while ((skb = ptr_ring_consume(&wg->handshake_queue.ring)) != NULL) kfree_skb(skb); atomic_set(&wg->handshake_queue_len, 0); wg_socket_reinit(wg, NULL, NULL); return 0; } static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); struct sk_buff_head packets; struct wg_peer *peer; struct sk_buff *next; sa_family_t family; u32 mtu; int ret; if (unlikely(!wg_check_packet_protocol(skb))) { ret = -EPROTONOSUPPORT; net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name); goto err; } peer = wg_allowedips_lookup_dst(&wg->peer_allowedips, skb); if (unlikely(!peer)) { ret = -ENOKEY; if (skb->protocol == htons(ETH_P_IP)) net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI4\n", dev->name, &ip_hdr(skb)->daddr); else if (skb->protocol == htons(ETH_P_IPV6)) net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n", dev->name, &ipv6_hdr(skb)->daddr); goto err_icmp; } family = READ_ONCE(peer->endpoint.addr.sa_family); if (unlikely(family != AF_INET && family != AF_INET6)) { ret = -EDESTADDRREQ; net_dbg_ratelimited("%s: No valid endpoint has been configured or discovered for peer %llu\n", dev->name, peer->internal_id); goto err_peer; } mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; __skb_queue_head_init(&packets); if (!skb_is_gso(skb)) { skb_mark_not_on_list(skb); } else { struct sk_buff *segs = skb_gso_segment(skb, 0); if (IS_ERR(segs)) { ret = PTR_ERR(segs); goto err_peer; } dev_kfree_skb(skb); skb = segs; } skb_list_walk_safe(skb, skb, next) { skb_mark_not_on_list(skb); skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) continue; /* We only need to keep the original dst around for icmp, * so at this point we're in a position to drop it. */ skb_dst_drop(skb); PACKET_CB(skb)->mtu = mtu; __skb_queue_tail(&packets, skb); } spin_lock_bh(&peer->staged_packet_queue.lock); /* If the queue is getting too big, we start removing the oldest packets * until it's small again. We do this before adding the new packet, so * we don't remove GSO segments that are in excess. */ while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) { dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue)); DEV_STATS_INC(dev, tx_dropped); } skb_queue_splice_tail(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); wg_packet_send_staged_packets(peer); wg_peer_put(peer); return NETDEV_TX_OK; err_peer: wg_peer_put(peer); err_icmp: if (skb->protocol == htons(ETH_P_IP)) icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); else if (skb->protocol == htons(ETH_P_IPV6)) icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return ret; } static const struct net_device_ops netdev_ops = { .ndo_open = wg_open, .ndo_stop = wg_stop, .ndo_start_xmit = wg_xmit, .ndo_get_stats64 = dev_get_tstats64 }; static void wg_destruct(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); rtnl_lock(); list_del(&wg->device_list); rtnl_unlock(); mutex_lock(&wg->device_update_lock); rcu_assign_pointer(wg->creating_net, NULL); wg->incoming_port = 0; wg_socket_reinit(wg, NULL, NULL); /* The final references are cleared in the below calls to destroy_workqueue. */ wg_peer_remove_all(wg); destroy_workqueue(wg->handshake_receive_wq); destroy_workqueue(wg->handshake_send_wq); destroy_workqueue(wg->packet_crypt_wq); wg_packet_queue_free(&wg->handshake_queue, true); wg_packet_queue_free(&wg->decrypt_queue, false); wg_packet_queue_free(&wg->encrypt_queue, false); rcu_barrier(); /* Wait for all the peers to be actually freed. */ wg_ratelimiter_uninit(); memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); free_percpu(dev->tstats); kvfree(wg->index_hashtable); kvfree(wg->peer_hashtable); mutex_unlock(&wg->device_update_lock); pr_debug("%s: Interface destroyed\n", dev->name); free_netdev(dev); } static const struct device_type device_type = { .name = KBUILD_MODNAME }; static void wg_setup(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA }; const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) + max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); dev->netdev_ops = &netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->hard_header_len = 0; dev->addr_len = 0; dev->needed_headroom = DATA_PACKET_HEAD_ROOM; dev->needed_tailroom = noise_encrypted_len(MESSAGE_PADDING_MULTIPLE); dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->priv_flags |= IFF_NO_QUEUE; dev->features |= NETIF_F_LLTX; dev->features |= WG_NETDEV_FEATURES; dev->hw_features |= WG_NETDEV_FEATURES; dev->hw_enc_features |= WG_NETDEV_FEATURES; dev->mtu = ETH_DATA_LEN - overhead; dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead; SET_NETDEV_DEVTYPE(dev, &device_type); /* We need to keep the dst around in case of icmp replies. */ netif_keep_dst(dev); memset(wg, 0, sizeof(*wg)); wg->dev = dev; } static int wg_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct wg_device *wg = netdev_priv(dev); int ret = -ENOMEM; rcu_assign_pointer(wg->creating_net, src_net); init_rwsem(&wg->static_identity.lock); mutex_init(&wg->socket_update_lock); mutex_init(&wg->device_update_lock); wg_allowedips_init(&wg->peer_allowedips); wg_cookie_checker_init(&wg->cookie_checker, wg); INIT_LIST_HEAD(&wg->peer_list); wg->device_update_gen = 1; wg->peer_hashtable = wg_pubkey_hashtable_alloc(); if (!wg->peer_hashtable) return ret; wg->index_hashtable = wg_index_hashtable_alloc(); if (!wg->index_hashtable) goto err_free_peer_hashtable; dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) goto err_free_index_hashtable; wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s", WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name); if (!wg->handshake_receive_wq) goto err_free_tstats; wg->handshake_send_wq = alloc_workqueue("wg-kex-%s", WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name); if (!wg->handshake_send_wq) goto err_destroy_handshake_receive; wg->packet_crypt_wq = alloc_workqueue("wg-crypt-%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0, dev->name); if (!wg->packet_crypt_wq) goto err_destroy_handshake_send; ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker, MAX_QUEUED_PACKETS); if (ret < 0) goto err_destroy_packet_crypt; ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker, MAX_QUEUED_PACKETS); if (ret < 0) goto err_free_encrypt_queue; ret = wg_packet_queue_init(&wg->handshake_queue, wg_packet_handshake_receive_worker, MAX_QUEUED_INCOMING_HANDSHAKES); if (ret < 0) goto err_free_decrypt_queue; ret = wg_ratelimiter_init(); if (ret < 0) goto err_free_handshake_queue; ret = register_netdevice(dev); if (ret < 0) goto err_uninit_ratelimiter; list_add(&wg->device_list, &device_list); /* We wait until the end to assign priv_destructor, so that * register_netdevice doesn't call it for us if it fails. */ dev->priv_destructor = wg_destruct; pr_debug("%s: Interface created\n", dev->name); return ret; err_uninit_ratelimiter: wg_ratelimiter_uninit(); err_free_handshake_queue: wg_packet_queue_free(&wg->handshake_queue, false); err_free_decrypt_queue: wg_packet_queue_free(&wg->decrypt_queue, false); err_free_encrypt_queue: wg_packet_queue_free(&wg->encrypt_queue, false); err_destroy_packet_crypt: destroy_workqueue(wg->packet_crypt_wq); err_destroy_handshake_send: destroy_workqueue(wg->handshake_send_wq); err_destroy_handshake_receive: destroy_workqueue(wg->handshake_receive_wq); err_free_tstats: free_percpu(dev->tstats); err_free_index_hashtable: kvfree(wg->index_hashtable); err_free_peer_hashtable: kvfree(wg->peer_hashtable); return ret; } static struct rtnl_link_ops link_ops __read_mostly = { .kind = KBUILD_MODNAME, .priv_size = sizeof(struct wg_device), .setup = wg_setup, .newlink = wg_newlink, }; static void wg_netns_pre_exit(struct net *net) { struct wg_device *wg; struct wg_peer *peer; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { if (rcu_access_pointer(wg->creating_net) == net) { pr_debug("%s: Creating namespace exiting\n", wg->dev->name); netif_carrier_off(wg->dev); mutex_lock(&wg->device_update_lock); rcu_assign_pointer(wg->creating_net, NULL); wg_socket_reinit(wg, NULL, NULL); list_for_each_entry(peer, &wg->peer_list, peer_list) wg_socket_clear_peer_endpoint_src(peer); mutex_unlock(&wg->device_update_lock); } } rtnl_unlock(); } static struct pernet_operations pernet_ops = { .pre_exit = wg_netns_pre_exit }; int __init wg_device_init(void) { int ret; #ifdef CONFIG_PM_SLEEP ret = register_pm_notifier(&pm_notifier); if (ret) return ret; #endif ret = register_pernet_device(&pernet_ops); if (ret) goto error_pm; ret = rtnl_link_register(&link_ops); if (ret) goto error_pernet; return 0; error_pernet: unregister_pernet_device(&pernet_ops); error_pm: #ifdef CONFIG_PM_SLEEP unregister_pm_notifier(&pm_notifier); #endif return ret; } void wg_device_uninit(void) { rtnl_link_unregister(&link_ops); unregister_pernet_device(&pernet_ops); #ifdef CONFIG_PM_SLEEP unregister_pm_notifier(&pm_notifier); #endif rcu_barrier(); } |
| 42 105 105 77 121 17 4 13 17 225 21 543 6 6 589 591 590 9 19 4 15 19 205 205 748 749 449 317 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/l3mdev.h - L3 master device API * Copyright (c) 2015 Cumulus Networks * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> */ #ifndef _NET_L3MDEV_H_ #define _NET_L3MDEV_H_ #include <net/dst.h> #include <net/fib_rules.h> enum l3mdev_type { L3MDEV_TYPE_UNSPEC, L3MDEV_TYPE_VRF, __L3MDEV_TYPE_MAX }; #define L3MDEV_TYPE_MAX (__L3MDEV_TYPE_MAX - 1) typedef int (*lookup_by_table_id_t)(struct net *net, u32 table_d); /** * struct l3mdev_ops - l3mdev operations * * @l3mdev_fib_table: Get FIB table id to use for lookups * * @l3mdev_l3_rcv: Hook in L3 receive path * * @l3mdev_l3_out: Hook in L3 output path * * @l3mdev_link_scope_lookup: IPv6 lookup for linklocal and mcast destinations */ struct l3mdev_ops { u32 (*l3mdev_fib_table)(const struct net_device *dev); struct sk_buff * (*l3mdev_l3_rcv)(struct net_device *dev, struct sk_buff *skb, u16 proto); struct sk_buff * (*l3mdev_l3_out)(struct net_device *dev, struct sock *sk, struct sk_buff *skb, u16 proto); /* IPv6 ops */ struct dst_entry * (*l3mdev_link_scope_lookup)(const struct net_device *dev, struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn); void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn); int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id); int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg); void l3mdev_update_flow(struct net *net, struct flowi *fl); int l3mdev_master_ifindex_rcu(const struct net_device *dev); static inline int l3mdev_master_ifindex(struct net_device *dev) { int ifindex; rcu_read_lock(); ifindex = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); return ifindex; } static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) { struct net_device *dev; int rc = 0; if (likely(ifindex)) { rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); } return rc; } static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) { /* netdev_master_upper_dev_get_rcu calls * list_first_or_null_rcu to walk the upper dev list. * list_first_or_null_rcu does not handle a const arg. We aren't * making changes, just want the master device from that list so * typecast to remove the const */ struct net_device *dev = (struct net_device *)_dev; struct net_device *master; if (!dev) return NULL; if (netif_is_l3_master(dev)) master = dev; else if (netif_is_l3_slave(dev)) master = netdev_master_upper_dev_get_rcu(dev); else master = NULL; return master; } int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex); static inline int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) { rcu_read_lock(); ifindex = l3mdev_master_upper_ifindex_by_index_rcu(net, ifindex); rcu_read_unlock(); return ifindex; } u32 l3mdev_fib_table_rcu(const struct net_device *dev); u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); static inline u32 l3mdev_fib_table(const struct net_device *dev) { u32 tb_id; rcu_read_lock(); tb_id = l3mdev_fib_table_rcu(dev); rcu_read_unlock(); return tb_id; } static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { struct net_device *dev; bool rc = false; if (ifindex == 0) return false; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = netif_is_l3_master(dev); rcu_read_unlock(); return rc; } struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6); static inline struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) { struct net_device *master = NULL; if (netif_is_l3_slave(skb->dev)) master = netdev_master_upper_dev_get_rcu(skb->dev); else if (netif_is_l3_master(skb->dev) || netif_has_l3_rx_handler(skb->dev)) master = skb->dev; if (master && master->l3mdev_ops->l3mdev_l3_rcv) skb = master->l3mdev_ops->l3mdev_l3_rcv(master, skb, proto); return skb; } static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { return l3mdev_l3_rcv(skb, AF_INET); } static inline struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return l3mdev_l3_rcv(skb, AF_INET6); } static inline struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto) { struct net_device *dev = skb_dst(skb)->dev; if (netif_is_l3_slave(dev)) { struct net_device *master; master = netdev_master_upper_dev_get_rcu(dev); if (master && master->l3mdev_ops->l3mdev_l3_out) skb = master->l3mdev_ops->l3mdev_l3_out(master, sk, skb, proto); } return skb; } static inline struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return l3mdev_l3_out(sk, skb, AF_INET); } static inline struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return l3mdev_l3_out(sk, skb, AF_INET6); } #else static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev) { return 0; } static inline int l3mdev_master_ifindex(struct net_device *dev) { return 0; } static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) { return 0; } static inline int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) { return 0; } static inline int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) { return 0; } static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) { return NULL; } static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev) { return 0; } static inline u32 l3mdev_fib_table(const struct net_device *dev) { return 0; } static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) { return 0; } static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { return false; } static inline struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6) { return NULL; } static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn) { return -EOPNOTSUPP; } static inline void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn) { } static inline int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id) { return -ENODEV; } static inline int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg) { return 1; } static inline void l3mdev_update_flow(struct net *net, struct flowi *fl) { } #endif #endif /* _NET_L3MDEV_H_ */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/stat.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/export.h> #include <linux/mm.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/highuid.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include "internal.h" #include "mount.h" /** * generic_fillattr - Fill in the basic attributes from the inode struct * @mnt_userns: user namespace of the mount the inode was found from * @inode: Inode to use as the source * @stat: Where to fill in the attributes * * Fill in the basic attributes in the kstat structure from data that's to be * found on the VFS inode structure. This is the default if no getattr inode * operation is supplied. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before filling in the * uid and gid filds. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. */ void generic_fillattr(struct user_namespace *mnt_userns, struct inode *inode, struct kstat *stat) { stat->dev = inode->i_sb->s_dev; stat->ino = inode->i_ino; stat->mode = inode->i_mode; stat->nlink = inode->i_nlink; stat->uid = i_uid_into_mnt(mnt_userns, inode); stat->gid = i_gid_into_mnt(mnt_userns, inode); stat->rdev = inode->i_rdev; stat->size = i_size_read(inode); stat->atime = inode->i_atime; stat->mtime = inode->i_mtime; stat->ctime = inode->i_ctime; stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; } EXPORT_SYMBOL(generic_fillattr); /** * generic_fill_statx_attr - Fill in the statx attributes from the inode flags * @inode: Inode to use as the source * @stat: Where to fill in the attribute flags * * Fill in the STATX_ATTR_* flags in the kstat structure for properties of the * inode that are published on i_flags and enforced by the VFS. */ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat) { if (inode->i_flags & S_IMMUTABLE) stat->attributes |= STATX_ATTR_IMMUTABLE; if (inode->i_flags & S_APPEND) stat->attributes |= STATX_ATTR_APPEND; stat->attributes_mask |= KSTAT_ATTR_VFS_FLAGS; } EXPORT_SYMBOL(generic_fill_statx_attr); /** * vfs_getattr_nosec - getattr without security checks * @path: file to get attributes from * @stat: structure to return attributes in * @request_mask: STATX_xxx flags indicating what the caller wants * @query_flags: Query mode (AT_STATX_SYNC_TYPE) * * Get attributes without calling security_inode_getattr. * * Currently the only caller other than vfs_getattr is internal to the * filehandle lookup code, which uses only the inode number and returns no * attributes to any user. Any other code probably wants vfs_getattr. */ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct user_namespace *mnt_userns; struct inode *inode = d_backing_inode(path->dentry); memset(stat, 0, sizeof(*stat)); stat->result_mask |= STATX_BASIC_STATS; query_flags &= AT_STATX_SYNC_TYPE; /* allow the fs to override these if it really wants to */ /* SB_NOATIME means filesystem supplies dummy atime value */ if (inode->i_sb->s_flags & SB_NOATIME) stat->result_mask &= ~STATX_ATIME; /* * Note: If you add another clause to set an attribute flag, please * update attributes_mask below. */ if (IS_AUTOMOUNT(inode)) stat->attributes |= STATX_ATTR_AUTOMOUNT; if (IS_DAX(inode)) stat->attributes |= STATX_ATTR_DAX; stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT | STATX_ATTR_DAX); mnt_userns = mnt_user_ns(path->mnt); if (inode->i_op->getattr) return inode->i_op->getattr(mnt_userns, path, stat, request_mask, query_flags); generic_fillattr(mnt_userns, inode, stat); return 0; } EXPORT_SYMBOL(vfs_getattr_nosec); /* * vfs_getattr - Get the enhanced basic attributes of a file * @path: The file of interest * @stat: Where to return the statistics * @request_mask: STATX_xxx flags indicating what the caller wants * @query_flags: Query mode (AT_STATX_SYNC_TYPE) * * Ask the filesystem for a file's attributes. The caller must indicate in * request_mask and query_flags to indicate what they want. * * If the file is remote, the filesystem can be forced to update the attributes * from the backing store by passing AT_STATX_FORCE_SYNC in query_flags or can * suppress the update by passing AT_STATX_DONT_SYNC. * * Bits must have been set in request_mask to indicate which attributes the * caller wants retrieving. Any such attribute not requested may be returned * anyway, but the value may be approximate, and, if remote, may not have been * synchronised with the server. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ int vfs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { int retval; retval = security_inode_getattr(path); if (retval) return retval; return vfs_getattr_nosec(path, stat, request_mask, query_flags); } EXPORT_SYMBOL(vfs_getattr); /** * vfs_fstat - Get the basic attributes by file descriptor * @fd: The file descriptor referring to the file of interest * @stat: The result structure to fill in. * * This function is a wrapper around vfs_getattr(). The main difference is * that it uses a file descriptor to determine the file location. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ int vfs_fstat(int fd, struct kstat *stat) { struct fd f; int error; f = fdget_raw(fd); if (!f.file) return -EBADF; error = vfs_getattr(&f.file->f_path, stat, STATX_BASIC_STATS, 0); fdput(f); return error; } /** * vfs_statx - Get basic and extra attributes by filename * @dfd: A file descriptor representing the base dir for a relative filename * @filename: The name of the file of interest * @flags: Flags to control the query * @stat: The result structure to fill in. * @request_mask: STATX_xxx flags indicating what the caller wants * * This function is a wrapper around vfs_getattr(). The main difference is * that it uses a filename and base directory to determine the file location. * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink * at the given name from being referenced. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ static int vfs_statx(int dfd, const char __user *filename, int flags, struct kstat *stat, u32 request_mask) { struct path path; unsigned lookup_flags = 0; int error; if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH | AT_STATX_SYNC_TYPE)) return -EINVAL; if (!(flags & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (!(flags & AT_NO_AUTOMOUNT)) lookup_flags |= LOOKUP_AUTOMOUNT; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (error) goto out; error = vfs_getattr(&path, stat, request_mask, flags); stat->mnt_id = real_mount(path.mnt)->mnt_id; stat->result_mask |= STATX_MNT_ID; if (path.mnt->mnt_root == path.dentry) stat->attributes |= STATX_ATTR_MOUNT_ROOT; stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT; path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags) { return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT, stat, STATX_BASIC_STATS); } #ifdef __ARCH_WANT_OLD_STAT /* * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * statbuf) { static int warncount = 5; struct __old_kernel_stat tmp; if (warncount > 0) { warncount--; printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n", current->comm); } else if (warncount < 0) { /* it's laughable, but... */ warncount = 0; } memset(&tmp, 0, sizeof(struct __old_kernel_stat)); tmp.st_dev = old_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = old_encode_dev(stat->rdev); #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) return -EOVERFLOW; #endif tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_ctime = stat->ctime.tv_sec; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(stat, const char __user *, filename, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_stat(filename, &stat); if (error) return error; return cp_old_stat(&stat, statbuf); } SYSCALL_DEFINE2(lstat, const char __user *, filename, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (error) return error; return cp_old_stat(&stat, statbuf); } SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_old_stat(&stat, statbuf); return error; } #endif /* __ARCH_WANT_OLD_STAT */ #ifdef __ARCH_WANT_NEW_STAT #if BITS_PER_LONG == 32 # define choose_32_64(a,b) a #else # define choose_32_64(a,b) b #endif #ifndef INIT_STRUCT_STAT_PADDING # define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) #endif static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) return -EOVERFLOW; if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) return -EOVERFLOW; #endif INIT_STRUCT_STAT_PADDING(tmp); tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = new_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_ctime = stat->ctime.tv_sec; #ifdef STAT_HAVE_NSEC tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; #endif tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(newstat, const char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; int error = vfs_stat(filename, &stat); if (error) return error; return cp_new_stat(&stat, statbuf); } SYSCALL_DEFINE2(newlstat, const char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (error) return error; return cp_new_stat(&stat, statbuf); } #if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT) SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename, struct stat __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_new_stat(&stat, statbuf); } #endif SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_new_stat(&stat, statbuf); return error; } #endif static int do_readlinkat(int dfd, const char __user *pathname, char __user *buf, int bufsiz) { struct path path; int error; int empty = 0; unsigned int lookup_flags = LOOKUP_EMPTY; if (bufsiz <= 0) return -EINVAL; retry: error = user_path_at_empty(dfd, pathname, lookup_flags, &path, &empty); if (!error) { struct inode *inode = d_backing_inode(path.dentry); error = empty ? -ENOENT : -EINVAL; /* * AFS mountpoints allow readlink(2) but are not symlinks */ if (d_is_symlink(path.dentry) || inode->i_op->readlink) { error = security_inode_readlink(path.dentry); if (!error) { touch_atime(&path); error = vfs_readlink(path.dentry, buf, bufsiz); } } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname, char __user *, buf, int, bufsiz) { return do_readlinkat(dfd, pathname, buf, bufsiz); } SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf, int, bufsiz) { return do_readlinkat(AT_FDCWD, path, buf, bufsiz); } /* ---------- LFS-64 ----------- */ #if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) #ifndef INIT_STRUCT_STAT64_PADDING # define INIT_STRUCT_STAT64_PADDING(st) memset(&st, 0, sizeof(st)) #endif static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) { struct stat64 tmp; INIT_STRUCT_STAT64_PADDING(tmp); #ifdef CONFIG_MIPS /* mips has weird padding, so we don't get 64 bits there */ tmp.st_dev = new_encode_dev(stat->dev); tmp.st_rdev = new_encode_dev(stat->rdev); #else tmp.st_dev = huge_encode_dev(stat->dev); tmp.st_rdev = huge_encode_dev(stat->rdev); #endif tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; #ifdef STAT64_HAS_BROKEN_ST_INO tmp.__st_ino = stat->ino; #endif tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.st_atime = stat->atime.tv_sec; tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime = stat->ctime.tv_sec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; tmp.st_size = stat->size; tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(stat64, const char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_stat(filename, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE2(lstat64, const char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_lstat(filename, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename, struct stat64 __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_new_stat64(&stat, statbuf); } #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */ static noinline_for_stack int cp_statx(const struct kstat *stat, struct statx __user *buffer) { struct statx tmp; memset(&tmp, 0, sizeof(tmp)); tmp.stx_mask = stat->result_mask; tmp.stx_blksize = stat->blksize; tmp.stx_attributes = stat->attributes; tmp.stx_nlink = stat->nlink; tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid); tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.stx_mode = stat->mode; tmp.stx_ino = stat->ino; tmp.stx_size = stat->size; tmp.stx_blocks = stat->blocks; tmp.stx_attributes_mask = stat->attributes_mask; tmp.stx_atime.tv_sec = stat->atime.tv_sec; tmp.stx_atime.tv_nsec = stat->atime.tv_nsec; tmp.stx_btime.tv_sec = stat->btime.tv_sec; tmp.stx_btime.tv_nsec = stat->btime.tv_nsec; tmp.stx_ctime.tv_sec = stat->ctime.tv_sec; tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec; tmp.stx_mtime.tv_sec = stat->mtime.tv_sec; tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec; tmp.stx_rdev_major = MAJOR(stat->rdev); tmp.stx_rdev_minor = MINOR(stat->rdev); tmp.stx_dev_major = MAJOR(stat->dev); tmp.stx_dev_minor = MINOR(stat->dev); tmp.stx_mnt_id = stat->mnt_id; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } int do_statx(int dfd, const char __user *filename, unsigned flags, unsigned int mask, struct statx __user *buffer) { struct kstat stat; int error; if (mask & STATX__RESERVED) return -EINVAL; if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE) return -EINVAL; error = vfs_statx(dfd, filename, flags, &stat, mask); if (error) return error; return cp_statx(&stat, buffer); } /** * sys_statx - System call to get enhanced stats * @dfd: Base directory to pathwalk from *or* fd to stat. * @filename: File to stat or "" with AT_EMPTY_PATH * @flags: AT_* flags to control pathwalk. * @mask: Parts of statx struct actually required. * @buffer: Result buffer. * * Note that fstat() can be emulated by setting dfd to the fd of interest, * supplying "" as the filename and setting AT_EMPTY_PATH in the flags. */ SYSCALL_DEFINE5(statx, int, dfd, const char __user *, filename, unsigned, flags, unsigned int, mask, struct statx __user *, buffer) { return do_statx(dfd, filename, flags, mask, buffer); } #ifdef CONFIG_COMPAT static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) { struct compat_stat tmp; if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) return -EOVERFLOW; if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; memset(&tmp, 0, sizeof(tmp)); tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = new_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime = stat->ctime.tv_sec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0; } COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename, struct compat_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_stat(filename, &stat); if (error) return error; return cp_compat_stat(&stat, statbuf); } COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename, struct compat_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (error) return error; return cp_compat_stat(&stat, statbuf); } #ifndef __ARCH_WANT_STAT64 COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd, const char __user *, filename, struct compat_stat __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_compat_stat(&stat, statbuf); } #endif COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct compat_stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_compat_stat(&stat, statbuf); return error; } #endif /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */ void __inode_add_bytes(struct inode *inode, loff_t bytes) { inode->i_blocks += bytes >> 9; bytes &= 511; inode->i_bytes += bytes; if (inode->i_bytes >= 512) { inode->i_blocks++; inode->i_bytes -= 512; } } EXPORT_SYMBOL(__inode_add_bytes); void inode_add_bytes(struct inode *inode, loff_t bytes) { spin_lock(&inode->i_lock); __inode_add_bytes(inode, bytes); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(inode_add_bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes) { inode->i_blocks -= bytes >> 9; bytes &= 511; if (inode->i_bytes < bytes) { inode->i_blocks--; inode->i_bytes += 512; } inode->i_bytes -= bytes; } EXPORT_SYMBOL(__inode_sub_bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes) { spin_lock(&inode->i_lock); __inode_sub_bytes(inode, bytes); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(inode_sub_bytes); loff_t inode_get_bytes(struct inode *inode) { loff_t ret; spin_lock(&inode->i_lock); ret = __inode_get_bytes(inode); spin_unlock(&inode->i_lock); return ret; } EXPORT_SYMBOL(inode_get_bytes); void inode_set_bytes(struct inode *inode, loff_t bytes) { /* Caller is here responsible for sufficient locking * (ie. inode->i_lock) */ inode->i_blocks = bytes >> 9; inode->i_bytes = bytes & 511; } EXPORT_SYMBOL(inode_set_bytes); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/shm.c * Copyright (C) 1992, 1993 Krishna Balasubramanian * Many improvements/fixes by Bruno Haible. * Replaced `struct shm_desc' by `struct vm_area_struct', July 1994. * Fixed the shm swap deallocation (shm_unuse()), August 1998 Andrea Arcangeli. * * /proc/sysvipc/shm support (c) 1999 Dragos Acostachioaie <dragos@iname.com> * BIGMEM support, Andrea Arcangeli <andrea@suse.de> * SMP thread shm, Jean-Luc Boyard <jean-luc.boyard@siemens.fr> * HIGHMEM support, Ingo Molnar <mingo@redhat.com> * Make shmmax, shmall, shmmni sysctl'able, Christoph Rohland <cr@sap.com> * Shared /dev/zero support, Kanoj Sarcar <kanoj@sgi.com> * Move the mm functionality over to mm/shmem.c, Christoph Rohland <cr@sap.com> * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> * * namespaces support * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> * * Better ipc lock (kern_ipc_perm.lock) handling * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013. */ #include <linux/slab.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/shm.h> #include <linux/init.h> #include <linux/file.h> #include <linux/mman.h> #include <linux/shmem_fs.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/ptrace.h> #include <linux/seq_file.h> #include <linux/rwsem.h> #include <linux/nsproxy.h> #include <linux/mount.h> #include <linux/ipc_namespace.h> #include <linux/rhashtable.h> #include <linux/uaccess.h> #include "util.h" struct shmid_kernel /* private to the kernel */ { struct kern_ipc_perm shm_perm; struct file *shm_file; unsigned long shm_nattch; unsigned long shm_segsz; time64_t shm_atim; time64_t shm_dtim; time64_t shm_ctim; struct pid *shm_cprid; struct pid *shm_lprid; struct ucounts *mlock_ucounts; /* * The task created the shm object, for * task_lock(shp->shm_creator) */ struct task_struct *shm_creator; /* * List by creator. task_lock(->shm_creator) required for read/write. * If list_empty(), then the creator is dead already. */ struct list_head shm_clist; struct ipc_namespace *ns; } __randomize_layout; /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ #define SHM_LOCKED 02000 /* segment will not be swapped */ struct shm_file_data { int id; struct ipc_namespace *ns; struct file *file; const struct vm_operations_struct *vm_ops; }; #define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data)) static const struct file_operations shm_file_operations; static const struct vm_operations_struct shm_vm_ops; #define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS]) #define shm_unlock(shp) \ ipc_unlock(&(shp)->shm_perm) static int newseg(struct ipc_namespace *, struct ipc_params *); static void shm_open(struct vm_area_struct *vma); static void shm_close(struct vm_area_struct *vma); static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp); #ifdef CONFIG_PROC_FS static int sysvipc_shm_proc_show(struct seq_file *s, void *it); #endif void shm_init_ns(struct ipc_namespace *ns) { ns->shm_ctlmax = SHMMAX; ns->shm_ctlall = SHMALL; ns->shm_ctlmni = SHMMNI; ns->shm_rmid_forced = 0; ns->shm_tot = 0; ipc_init_ids(&shm_ids(ns)); } /* * Called with shm_ids.rwsem (writer) and the shp structure locked. * Only shm_ids.rwsem remains locked on exit. */ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); WARN_ON(ns != shp->ns); if (shp->shm_nattch) { shp->shm_perm.mode |= SHM_DEST; /* Do not find it any more */ ipc_set_key_private(&shm_ids(ns), &shp->shm_perm); shm_unlock(shp); } else shm_destroy(ns, shp); } #ifdef CONFIG_IPC_NS void shm_exit_ns(struct ipc_namespace *ns) { free_ipcs(ns, &shm_ids(ns), do_shm_rmid); idr_destroy(&ns->ids[IPC_SHM_IDS].ipcs_idr); rhashtable_destroy(&ns->ids[IPC_SHM_IDS].key_ht); } #endif static int __init ipc_ns_init(void) { shm_init_ns(&init_ipc_ns); return 0; } pure_initcall(ipc_ns_init); void __init shm_init(void) { ipc_init_proc_interface("sysvipc/shm", #if BITS_PER_LONG <= 32 " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n", #else " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n", #endif IPC_SHM_IDS, sysvipc_shm_proc_show); } static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct shmid_kernel, shm_perm); } static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct shmid_kernel, shm_perm); } /* * shm_lock_(check_) routines are called in the paths where the rwsem * is not necessarily held. */ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp; rcu_read_lock(); ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); if (IS_ERR(ipcp)) goto err; ipc_lock_object(ipcp); /* * ipc_rmid() may have already freed the ID while ipc_lock_object() * was spinning: here verify that the structure is still valid. * Upon races with RMID, return -EIDRM, thus indicating that * the ID points to a removed identifier. */ if (ipc_valid_object(ipcp)) { /* return a locked ipc object upon success */ return container_of(ipcp, struct shmid_kernel, shm_perm); } ipc_unlock_object(ipcp); ipcp = ERR_PTR(-EIDRM); err: rcu_read_unlock(); /* * Callers of shm_lock() must validate the status of the returned ipc * object pointer and error out as appropriate. */ return ERR_CAST(ipcp); } static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) { rcu_read_lock(); ipc_lock_object(&ipcp->shm_perm); } static void shm_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm, rcu); struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel, shm_perm); security_shm_free(&shp->shm_perm); kfree(shp); } /* * It has to be called with shp locked. * It must be called before ipc_rmid() */ static inline void shm_clist_rm(struct shmid_kernel *shp) { struct task_struct *creator; /* ensure that shm_creator does not disappear */ rcu_read_lock(); /* * A concurrent exit_shm may do a list_del_init() as well. * Just do nothing if exit_shm already did the work */ if (!list_empty(&shp->shm_clist)) { /* * shp->shm_creator is guaranteed to be valid *only* * if shp->shm_clist is not empty. */ creator = shp->shm_creator; task_lock(creator); /* * list_del_init() is a nop if the entry was already removed * from the list. */ list_del_init(&shp->shm_clist); task_unlock(creator); } rcu_read_unlock(); } static inline void shm_rmid(struct shmid_kernel *s) { shm_clist_rm(s); ipc_rmid(&shm_ids(s->ns), &s->shm_perm); } static int __shm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); if (IS_ERR(shp)) return PTR_ERR(shp); if (shp->shm_file != sfd->file) { /* ID was reused */ shm_unlock(shp); return -EINVAL; } shp->shm_atim = ktime_get_real_seconds(); ipc_update_pid(&shp->shm_lprid, task_tgid(current)); shp->shm_nattch++; shm_unlock(shp); return 0; } /* This is called by fork, once for every shm attach. */ static void shm_open(struct vm_area_struct *vma) { int err = __shm_open(vma); /* * We raced in the idr lookup or with shm_destroy(). * Either way, the ID is busted. */ WARN_ON_ONCE(err); } /* * shm_destroy - free the struct shmid_kernel * * @ns: namespace * @shp: struct to free * * It has to be called with shp and shm_ids.rwsem (writer) locked, * but returns with shp unlocked and freed. */ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) { struct file *shm_file; shm_file = shp->shm_file; shp->shm_file = NULL; ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; shm_rmid(shp); shm_unlock(shp); if (!is_file_hugepages(shm_file)) shmem_lock(shm_file, 0, shp->mlock_ucounts); else if (shp->mlock_ucounts) user_shm_unlock(i_size_read(file_inode(shm_file)), shp->mlock_ucounts); fput(shm_file); ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); } /* * shm_may_destroy - identifies whether shm segment should be destroyed now * * Returns true if and only if there are no active users of the segment and * one of the following is true: * * 1) shmctl(id, IPC_RMID, NULL) was called for this shp * * 2) sysctl kernel.shm_rmid_forced is set to 1. */ static bool shm_may_destroy(struct shmid_kernel *shp) { return (shp->shm_nattch == 0) && (shp->ns->shm_rmid_forced || (shp->shm_perm.mode & SHM_DEST)); } /* * remove the attach descriptor vma. * free memory for segment if it is marked destroyed. * The descriptor has already been removed from the current->mm->mmap list * and will later be kfree()d. */ static void shm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; struct ipc_namespace *ns = sfd->ns; down_write(&shm_ids(ns).rwsem); /* remove from the list of attaches of the shm segment */ shp = shm_lock(ns, sfd->id); /* * We raced in the idr lookup or with shm_destroy(). * Either way, the ID is busted. */ if (WARN_ON_ONCE(IS_ERR(shp))) goto done; /* no-op */ ipc_update_pid(&shp->shm_lprid, task_tgid(current)); shp->shm_dtim = ktime_get_real_seconds(); shp->shm_nattch--; if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); done: up_write(&shm_ids(ns).rwsem); } /* Called with ns->shm_ids(ns).rwsem locked */ static int shm_try_destroy_orphaned(int id, void *p, void *data) { struct ipc_namespace *ns = data; struct kern_ipc_perm *ipcp = p; struct shmid_kernel *shp = container_of(ipcp, struct shmid_kernel, shm_perm); /* * We want to destroy segments without users and with already * exit'ed originating process. * * As shp->* are changed under rwsem, it's safe to skip shp locking. */ if (!list_empty(&shp->shm_clist)) return 0; if (shm_may_destroy(shp)) { shm_lock_by_ptr(shp); shm_destroy(ns, shp); } return 0; } void shm_destroy_orphaned(struct ipc_namespace *ns) { down_write(&shm_ids(ns).rwsem); if (shm_ids(ns).in_use) idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns); up_write(&shm_ids(ns).rwsem); } /* Locking assumes this will only be called with task == current */ void exit_shm(struct task_struct *task) { for (;;) { struct shmid_kernel *shp; struct ipc_namespace *ns; task_lock(task); if (list_empty(&task->sysvshm.shm_clist)) { task_unlock(task); break; } shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel, shm_clist); /* * 1) Get pointer to the ipc namespace. It is worth to say * that this pointer is guaranteed to be valid because * shp lifetime is always shorter than namespace lifetime * in which shp lives. * We taken task_lock it means that shp won't be freed. */ ns = shp->ns; /* * 2) If kernel.shm_rmid_forced is not set then only keep track of * which shmids are orphaned, so that a later set of the sysctl * can clean them up. */ if (!ns->shm_rmid_forced) goto unlink_continue; /* * 3) get a reference to the namespace. * The refcount could be already 0. If it is 0, then * the shm objects will be free by free_ipc_work(). */ ns = get_ipc_ns_not_zero(ns); if (!ns) { unlink_continue: list_del_init(&shp->shm_clist); task_unlock(task); continue; } /* * 4) get a reference to shp. * This cannot fail: shm_clist_rm() is called before * ipc_rmid(), thus the refcount cannot be 0. */ WARN_ON(!ipc_rcu_getref(&shp->shm_perm)); /* * 5) unlink the shm segment from the list of segments * created by current. * This must be done last. After unlinking, * only the refcounts obtained above prevent IPC_RMID * from destroying the segment or the namespace. */ list_del_init(&shp->shm_clist); task_unlock(task); /* * 6) we have all references * Thus lock & if needed destroy shp. */ down_write(&shm_ids(ns).rwsem); shm_lock_by_ptr(shp); /* * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's * safe to call ipc_rcu_putref here */ ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); if (ipc_valid_object(&shp->shm_perm)) { if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); } else { /* * Someone else deleted the shp from namespace * idr/kht while we have waited. * Just unlock and continue. */ shm_unlock(shp); } up_write(&shm_ids(ns).rwsem); put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */ } } static vm_fault_t shm_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); return sfd->vm_ops->fault(vmf); } static int shm_may_split(struct vm_area_struct *vma, unsigned long addr) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); if (sfd->vm_ops->may_split) return sfd->vm_ops->may_split(vma, addr); return 0; } static unsigned long shm_pagesize(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); if (sfd->vm_ops->pagesize) return sfd->vm_ops->pagesize(vma); return PAGE_SIZE; } #ifdef CONFIG_NUMA static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); int err = 0; if (sfd->vm_ops->set_policy) err = sfd->vm_ops->set_policy(vma, new); return err; } static struct mempolicy *shm_get_policy(struct vm_area_struct *vma, unsigned long addr) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct mempolicy *pol = NULL; if (sfd->vm_ops->get_policy) pol = sfd->vm_ops->get_policy(vma, addr); else if (vma->vm_policy) pol = vma->vm_policy; return pol; } #endif static int shm_mmap(struct file *file, struct vm_area_struct *vma) { struct shm_file_data *sfd = shm_file_data(file); int ret; /* * In case of remap_file_pages() emulation, the file can represent an * IPC ID that was removed, and possibly even reused by another shm * segment already. Propagate this case as an error to caller. */ ret = __shm_open(vma); if (ret) return ret; ret = call_mmap(sfd->file, vma); if (ret) { shm_close(vma); return ret; } sfd->vm_ops = vma->vm_ops; #ifdef CONFIG_MMU WARN_ON(!sfd->vm_ops->fault); #endif vma->vm_ops = &shm_vm_ops; return 0; } static int shm_release(struct inode *ino, struct file *file) { struct shm_file_data *sfd = shm_file_data(file); put_ipc_ns(sfd->ns); fput(sfd->file); shm_file_data(file) = NULL; kfree(sfd); return 0; } static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct shm_file_data *sfd = shm_file_data(file); if (!sfd->file->f_op->fsync) return -EINVAL; return sfd->file->f_op->fsync(sfd->file, start, end, datasync); } static long shm_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct shm_file_data *sfd = shm_file_data(file); if (!sfd->file->f_op->fallocate) return -EOPNOTSUPP; return sfd->file->f_op->fallocate(file, mode, offset, len); } static unsigned long shm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct shm_file_data *sfd = shm_file_data(file); return sfd->file->f_op->get_unmapped_area(sfd->file, addr, len, pgoff, flags); } static const struct file_operations shm_file_operations = { .mmap = shm_mmap, .fsync = shm_fsync, .release = shm_release, .get_unmapped_area = shm_get_unmapped_area, .llseek = noop_llseek, .fallocate = shm_fallocate, }; /* * shm_file_operations_huge is now identical to shm_file_operations, * but we keep it distinct for the sake of is_file_shm_hugepages(). */ static const struct file_operations shm_file_operations_huge = { .mmap = shm_mmap, .fsync = shm_fsync, .release = shm_release, .get_unmapped_area = shm_get_unmapped_area, .llseek = noop_llseek, .fallocate = shm_fallocate, }; bool is_file_shm_hugepages(struct file *file) { return file->f_op == &shm_file_operations_huge; } static const struct vm_operations_struct shm_vm_ops = { .open = shm_open, /* callback for a new vm-area open */ .close = shm_close, /* callback for when the vm-area is released */ .fault = shm_fault, .may_split = shm_may_split, .pagesize = shm_pagesize, #if defined(CONFIG_NUMA) .set_policy = shm_set_policy, .get_policy = shm_get_policy, #endif }; /** * newseg - Create a new shared memory segment * @ns: namespace * @params: ptr to the structure that contains key, size and shmflg * * Called with shm_ids.rwsem held as a writer. */ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) { key_t key = params->key; int shmflg = params->flg; size_t size = params->u.size; int error; struct shmid_kernel *shp; size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; struct file *file; char name[13]; vm_flags_t acctflag = 0; if (size < SHMMIN || size > ns->shm_ctlmax) return -EINVAL; if (numpages << PAGE_SHIFT < size) return -ENOSPC; if (ns->shm_tot + numpages < ns->shm_tot || ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC; shp = kmalloc(sizeof(*shp), GFP_KERNEL_ACCOUNT); if (unlikely(!shp)) return -ENOMEM; shp->shm_perm.key = key; shp->shm_perm.mode = (shmflg & S_IRWXUGO); shp->mlock_ucounts = NULL; shp->shm_perm.security = NULL; error = security_shm_alloc(&shp->shm_perm); if (error) { kfree(shp); return error; } sprintf(name, "SYSV%08x", key); if (shmflg & SHM_HUGETLB) { struct hstate *hs; size_t hugesize; hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); if (!hs) { error = -EINVAL; goto no_file; } hugesize = ALIGN(size, huge_page_size(hs)); /* hugetlb_file_setup applies strict accounting */ if (shmflg & SHM_NORESERVE) acctflag = VM_NORESERVE; file = hugetlb_file_setup(name, hugesize, acctflag, &shp->mlock_ucounts, HUGETLB_SHMFS_INODE, (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); } else { /* * Do not allow no accounting for OVERCOMMIT_NEVER, even * if it's asked for. */ if ((shmflg & SHM_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER) acctflag = VM_NORESERVE; file = shmem_kernel_file_setup(name, size, acctflag); } error = PTR_ERR(file); if (IS_ERR(file)) goto no_file; shp->shm_cprid = get_pid(task_tgid(current)); shp->shm_lprid = NULL; shp->shm_atim = shp->shm_dtim = 0; shp->shm_ctim = ktime_get_real_seconds(); shp->shm_segsz = size; shp->shm_nattch = 0; shp->shm_file = file; shp->shm_creator = current; /* ipc_addid() locks shp upon success. */ error = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); if (error < 0) goto no_id; shp->ns = ns; task_lock(current); list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist); task_unlock(current); /* * shmid gets reported as "inode#" in /proc/pid/maps. * proc-ps tools use this. Changing this will break them. */ file_inode(file)->i_ino = shp->shm_perm.id; ns->shm_tot += numpages; error = shp->shm_perm.id; ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); return error; no_id: ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); if (is_file_hugepages(file) && shp->mlock_ucounts) user_shm_unlock(size, shp->mlock_ucounts); fput(file); ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); return error; no_file: call_rcu(&shp->shm_perm.rcu, shm_rcu_free); return error; } /* * Called with shm_ids.rwsem and ipcp locked. */ static int shm_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params) { struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); if (shp->shm_segsz < params->u.size) return -EINVAL; return 0; } long ksys_shmget(key_t key, size_t size, int shmflg) { struct ipc_namespace *ns; static const struct ipc_ops shm_ops = { .getnew = newseg, .associate = security_shm_associate, .more_checks = shm_more_checks, }; struct ipc_params shm_params; ns = current->nsproxy->ipc_ns; shm_params.key = key; shm_params.flg = shmflg; shm_params.u.size = size; return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params); } SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg) { return ksys_shmget(key, size, shmflg); } static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct shmid_ds out; memset(&out, 0, sizeof(out)); ipc64_perm_to_ipc_perm(&in->shm_perm, &out.shm_perm); out.shm_segsz = in->shm_segsz; out.shm_atime = in->shm_atime; out.shm_dtime = in->shm_dtime; out.shm_ctime = in->shm_ctime; out.shm_cpid = in->shm_cpid; out.shm_lpid = in->shm_lpid; out.shm_nattch = in->shm_nattch; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } static inline unsigned long copy_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version) { switch (version) { case IPC_64: if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; return 0; case IPC_OLD: { struct shmid_ds tbuf_old; if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; out->shm_perm.uid = tbuf_old.shm_perm.uid; out->shm_perm.gid = tbuf_old.shm_perm.gid; out->shm_perm.mode = tbuf_old.shm_perm.mode; return 0; } default: return -EINVAL; } } static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct shminfo out; if (in->shmmax > INT_MAX) out.shmmax = INT_MAX; else out.shmmax = (int)in->shmmax; out.shmmin = in->shmmin; out.shmmni = in->shmmni; out.shmseg = in->shmseg; out.shmall = in->shmall; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } /* * Calculate and add used RSS and swap pages of a shm. * Called with shm_ids.rwsem held as a reader */ static void shm_add_rss_swap(struct shmid_kernel *shp, unsigned long *rss_add, unsigned long *swp_add) { struct inode *inode; inode = file_inode(shp->shm_file); if (is_file_hugepages(shp->shm_file)) { struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_file(shp->shm_file); *rss_add += pages_per_huge_page(h) * mapping->nrpages; } else { #ifdef CONFIG_SHMEM struct shmem_inode_info *info = SHMEM_I(inode); spin_lock_irq(&info->lock); *rss_add += inode->i_mapping->nrpages; *swp_add += info->swapped; spin_unlock_irq(&info->lock); #else *rss_add += inode->i_mapping->nrpages; #endif } } /* * Called with shm_ids.rwsem held as a reader */ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, unsigned long *swp) { int next_id; int total, in_use; *rss = 0; *swp = 0; in_use = shm_ids(ns).in_use; for (total = 0, next_id = 0; total < in_use; next_id++) { struct kern_ipc_perm *ipc; struct shmid_kernel *shp; ipc = idr_find(&shm_ids(ns).ipcs_idr, next_id); if (ipc == NULL) continue; shp = container_of(ipc, struct shmid_kernel, shm_perm); shm_add_rss_swap(shp, rss, swp); total++; } } /* * This function handles some shmctl commands which require the rwsem * to be held in write mode. * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd, struct shmid64_ds *shmid64) { struct kern_ipc_perm *ipcp; struct shmid_kernel *shp; int err; down_write(&shm_ids(ns).rwsem); rcu_read_lock(); ipcp = ipcctl_obtain_check(ns, &shm_ids(ns), shmid, cmd, &shmid64->shm_perm, 0); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; } shp = container_of(ipcp, struct shmid_kernel, shm_perm); err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock1; switch (cmd) { case IPC_RMID: ipc_lock_object(&shp->shm_perm); /* do_shm_rmid unlocks the ipc object and rcu */ do_shm_rmid(ns, ipcp); goto out_up; case IPC_SET: ipc_lock_object(&shp->shm_perm); err = ipc_update_perm(&shmid64->shm_perm, ipcp); if (err) goto out_unlock0; shp->shm_ctim = ktime_get_real_seconds(); break; default: err = -EINVAL; goto out_unlock1; } out_unlock0: ipc_unlock_object(&shp->shm_perm); out_unlock1: rcu_read_unlock(); out_up: up_write(&shm_ids(ns).rwsem); return err; } static int shmctl_ipc_info(struct ipc_namespace *ns, struct shminfo64 *shminfo) { int err = security_shm_shmctl(NULL, IPC_INFO); if (!err) { memset(shminfo, 0, sizeof(*shminfo)); shminfo->shmmni = shminfo->shmseg = ns->shm_ctlmni; shminfo->shmmax = ns->shm_ctlmax; shminfo->shmall = ns->shm_ctlall; shminfo->shmmin = SHMMIN; down_read(&shm_ids(ns).rwsem); err = ipc_get_maxidx(&shm_ids(ns)); up_read(&shm_ids(ns).rwsem); if (err < 0) err = 0; } return err; } static int shmctl_shm_info(struct ipc_namespace *ns, struct shm_info *shm_info) { int err = security_shm_shmctl(NULL, SHM_INFO); if (!err) { memset(shm_info, 0, sizeof(*shm_info)); down_read(&shm_ids(ns).rwsem); shm_info->used_ids = shm_ids(ns).in_use; shm_get_stat(ns, &shm_info->shm_rss, &shm_info->shm_swp); shm_info->shm_tot = ns->shm_tot; shm_info->swap_attempts = 0; shm_info->swap_successes = 0; err = ipc_get_maxidx(&shm_ids(ns)); up_read(&shm_ids(ns).rwsem); if (err < 0) err = 0; } return err; } static int shmctl_stat(struct ipc_namespace *ns, int shmid, int cmd, struct shmid64_ds *tbuf) { struct shmid_kernel *shp; int err; memset(tbuf, 0, sizeof(*tbuf)); rcu_read_lock(); if (cmd == SHM_STAT || cmd == SHM_STAT_ANY) { shp = shm_obtain_object(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } } else { /* IPC_STAT */ shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } } /* * Semantically SHM_STAT_ANY ought to be identical to * that functionality provided by the /proc/sysvipc/ * interface. As such, only audit these calls and * do not do traditional S_IRUGO permission checks on * the ipc object. */ if (cmd == SHM_STAT_ANY) audit_ipc_obj(&shp->shm_perm); else { err = -EACCES; if (ipcperms(ns, &shp->shm_perm, S_IRUGO)) goto out_unlock; } err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock; ipc_lock_object(&shp->shm_perm); if (!ipc_valid_object(&shp->shm_perm)) { ipc_unlock_object(&shp->shm_perm); err = -EIDRM; goto out_unlock; } kernel_to_ipc64_perm(&shp->shm_perm, &tbuf->shm_perm); tbuf->shm_segsz = shp->shm_segsz; tbuf->shm_atime = shp->shm_atim; tbuf->shm_dtime = shp->shm_dtim; tbuf->shm_ctime = shp->shm_ctim; #ifndef CONFIG_64BIT tbuf->shm_atime_high = shp->shm_atim >> 32; tbuf->shm_dtime_high = shp->shm_dtim >> 32; tbuf->shm_ctime_high = shp->shm_ctim >> 32; #endif tbuf->shm_cpid = pid_vnr(shp->shm_cprid); tbuf->shm_lpid = pid_vnr(shp->shm_lprid); tbuf->shm_nattch = shp->shm_nattch; if (cmd == IPC_STAT) { /* * As defined in SUS: * Return 0 on success */ err = 0; } else { /* * SHM_STAT and SHM_STAT_ANY (both Linux specific) * Return the full id, including the sequence number */ err = shp->shm_perm.id; } ipc_unlock_object(&shp->shm_perm); out_unlock: rcu_read_unlock(); return err; } static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd) { struct shmid_kernel *shp; struct file *shm_file; int err; rcu_read_lock(); shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock1; } audit_ipc_obj(&(shp->shm_perm)); err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock1; ipc_lock_object(&shp->shm_perm); /* check if shm_destroy() is tearing down shp */ if (!ipc_valid_object(&shp->shm_perm)) { err = -EIDRM; goto out_unlock0; } if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) { kuid_t euid = current_euid(); if (!uid_eq(euid, shp->shm_perm.uid) && !uid_eq(euid, shp->shm_perm.cuid)) { err = -EPERM; goto out_unlock0; } if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) { err = -EPERM; goto out_unlock0; } } shm_file = shp->shm_file; if (is_file_hugepages(shm_file)) goto out_unlock0; if (cmd == SHM_LOCK) { struct ucounts *ucounts = current_ucounts(); err = shmem_lock(shm_file, 1, ucounts); if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) { shp->shm_perm.mode |= SHM_LOCKED; shp->mlock_ucounts = ucounts; } goto out_unlock0; } /* SHM_UNLOCK */ if (!(shp->shm_perm.mode & SHM_LOCKED)) goto out_unlock0; shmem_lock(shm_file, 0, shp->mlock_ucounts); shp->shm_perm.mode &= ~SHM_LOCKED; shp->mlock_ucounts = NULL; get_file(shm_file); ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); shmem_unlock_mapping(shm_file->f_mapping); fput(shm_file); return err; out_unlock0: ipc_unlock_object(&shp->shm_perm); out_unlock1: rcu_read_unlock(); return err; } static long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf, int version) { int err; struct ipc_namespace *ns; struct shmid64_ds sem64; if (cmd < 0 || shmid < 0) return -EINVAL; ns = current->nsproxy->ipc_ns; switch (cmd) { case IPC_INFO: { struct shminfo64 shminfo; err = shmctl_ipc_info(ns, &shminfo); if (err < 0) return err; if (copy_shminfo_to_user(buf, &shminfo, version)) err = -EFAULT; return err; } case SHM_INFO: { struct shm_info shm_info; err = shmctl_shm_info(ns, &shm_info); if (err < 0) return err; if (copy_to_user(buf, &shm_info, sizeof(shm_info))) err = -EFAULT; return err; } case SHM_STAT: case SHM_STAT_ANY: case IPC_STAT: { err = shmctl_stat(ns, shmid, cmd, &sem64); if (err < 0) return err; if (copy_shmid_to_user(buf, &sem64, version)) err = -EFAULT; return err; } case IPC_SET: if (copy_shmid_from_user(&sem64, buf, version)) return -EFAULT; fallthrough; case IPC_RMID: return shmctl_down(ns, shmid, cmd, &sem64); case SHM_LOCK: case SHM_UNLOCK: return shmctl_do_lock(ns, shmid, cmd); default: return -EINVAL; } } SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) { return ksys_shmctl(shmid, cmd, buf, IPC_64); } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION long ksys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) { int version = ipc_parse_version(&cmd); return ksys_shmctl(shmid, cmd, buf, version); } SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) { return ksys_old_shmctl(shmid, cmd, buf); } #endif #ifdef CONFIG_COMPAT struct compat_shmid_ds { struct compat_ipc_perm shm_perm; int shm_segsz; old_time32_t shm_atime; old_time32_t shm_dtime; old_time32_t shm_ctime; compat_ipc_pid_t shm_cpid; compat_ipc_pid_t shm_lpid; unsigned short shm_nattch; unsigned short shm_unused; compat_uptr_t shm_unused2; compat_uptr_t shm_unused3; }; struct compat_shminfo64 { compat_ulong_t shmmax; compat_ulong_t shmmin; compat_ulong_t shmmni; compat_ulong_t shmseg; compat_ulong_t shmall; compat_ulong_t __unused1; compat_ulong_t __unused2; compat_ulong_t __unused3; compat_ulong_t __unused4; }; struct compat_shm_info { compat_int_t used_ids; compat_ulong_t shm_tot, shm_rss, shm_swp; compat_ulong_t swap_attempts, swap_successes; }; static int copy_compat_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version) { if (in->shmmax > INT_MAX) in->shmmax = INT_MAX; if (version == IPC_64) { struct compat_shminfo64 info; memset(&info, 0, sizeof(info)); info.shmmax = in->shmmax; info.shmmin = in->shmmin; info.shmmni = in->shmmni; info.shmseg = in->shmseg; info.shmall = in->shmall; return copy_to_user(buf, &info, sizeof(info)); } else { struct shminfo info; memset(&info, 0, sizeof(info)); info.shmmax = in->shmmax; info.shmmin = in->shmmin; info.shmmni = in->shmmni; info.shmseg = in->shmseg; info.shmall = in->shmall; return copy_to_user(buf, &info, sizeof(info)); } } static int put_compat_shm_info(struct shm_info *ip, struct compat_shm_info __user *uip) { struct compat_shm_info info; memset(&info, 0, sizeof(info)); info.used_ids = ip->used_ids; info.shm_tot = ip->shm_tot; info.shm_rss = ip->shm_rss; info.shm_swp = ip->shm_swp; info.swap_attempts = ip->swap_attempts; info.swap_successes = ip->swap_successes; return copy_to_user(uip, &info, sizeof(info)); } static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version) { if (version == IPC_64) { struct compat_shmid64_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc64_perm(&v.shm_perm, &in->shm_perm); v.shm_atime = lower_32_bits(in->shm_atime); v.shm_atime_high = upper_32_bits(in->shm_atime); v.shm_dtime = lower_32_bits(in->shm_dtime); v.shm_dtime_high = upper_32_bits(in->shm_dtime); v.shm_ctime = lower_32_bits(in->shm_ctime); v.shm_ctime_high = upper_32_bits(in->shm_ctime); v.shm_segsz = in->shm_segsz; v.shm_nattch = in->shm_nattch; v.shm_cpid = in->shm_cpid; v.shm_lpid = in->shm_lpid; return copy_to_user(buf, &v, sizeof(v)); } else { struct compat_shmid_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc_perm(&v.shm_perm, &in->shm_perm); v.shm_perm.key = in->shm_perm.key; v.shm_atime = in->shm_atime; v.shm_dtime = in->shm_dtime; v.shm_ctime = in->shm_ctime; v.shm_segsz = in->shm_segsz; v.shm_nattch = in->shm_nattch; v.shm_cpid = in->shm_cpid; v.shm_lpid = in->shm_lpid; return copy_to_user(buf, &v, sizeof(v)); } } static int copy_compat_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version) { memset(out, 0, sizeof(*out)); if (version == IPC_64) { struct compat_shmid64_ds __user *p = buf; return get_compat_ipc64_perm(&out->shm_perm, &p->shm_perm); } else { struct compat_shmid_ds __user *p = buf; return get_compat_ipc_perm(&out->shm_perm, &p->shm_perm); } } static long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr, int version) { struct ipc_namespace *ns; struct shmid64_ds sem64; int err; ns = current->nsproxy->ipc_ns; if (cmd < 0 || shmid < 0) return -EINVAL; switch (cmd) { case IPC_INFO: { struct shminfo64 shminfo; err = shmctl_ipc_info(ns, &shminfo); if (err < 0) return err; if (copy_compat_shminfo_to_user(uptr, &shminfo, version)) err = -EFAULT; return err; } case SHM_INFO: { struct shm_info shm_info; err = shmctl_shm_info(ns, &shm_info); if (err < 0) return err; if (put_compat_shm_info(&shm_info, uptr)) err = -EFAULT; return err; } case IPC_STAT: case SHM_STAT_ANY: case SHM_STAT: err = shmctl_stat(ns, shmid, cmd, &sem64); if (err < 0) return err; if (copy_compat_shmid_to_user(uptr, &sem64, version)) err = -EFAULT; return err; case IPC_SET: if (copy_compat_shmid_from_user(&sem64, uptr, version)) return -EFAULT; fallthrough; case IPC_RMID: return shmctl_down(ns, shmid, cmd, &sem64); case SHM_LOCK: case SHM_UNLOCK: return shmctl_do_lock(ns, shmid, cmd); default: return -EINVAL; } return err; } COMPAT_SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, void __user *, uptr) { return compat_ksys_shmctl(shmid, cmd, uptr, IPC_64); } #ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr) { int version = compat_ipc_parse_version(&cmd); return compat_ksys_shmctl(shmid, cmd, uptr, version); } COMPAT_SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, void __user *, uptr) { return compat_ksys_old_shmctl(shmid, cmd, uptr); } #endif #endif /* * Fix shmaddr, allocate descriptor, map shm, add attach descriptor to lists. * * NOTE! Despite the name, this is NOT a direct system call entrypoint. The * "raddr" thing points to kernel space, and there has to be a wrapper around * this. */ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, unsigned long shmlba) { struct shmid_kernel *shp; unsigned long addr = (unsigned long)shmaddr; unsigned long size; struct file *file, *base; int err; unsigned long flags = MAP_SHARED; unsigned long prot; int acc_mode; struct ipc_namespace *ns; struct shm_file_data *sfd; int f_flags; unsigned long populate = 0; err = -EINVAL; if (shmid < 0) goto out; if (addr) { if (addr & (shmlba - 1)) { if (shmflg & SHM_RND) { addr &= ~(shmlba - 1); /* round down */ /* * Ensure that the round-down is non-nil * when remapping. This can happen for * cases when addr < shmlba. */ if (!addr && (shmflg & SHM_REMAP)) goto out; } else #ifndef __ARCH_FORCE_SHMLBA if (addr & ~PAGE_MASK) #endif goto out; } flags |= MAP_FIXED; } else if ((shmflg & SHM_REMAP)) goto out; if (shmflg & SHM_RDONLY) { prot = PROT_READ; acc_mode = S_IRUGO; f_flags = O_RDONLY; } else { prot = PROT_READ | PROT_WRITE; acc_mode = S_IRUGO | S_IWUGO; f_flags = O_RDWR; } if (shmflg & SHM_EXEC) { prot |= PROT_EXEC; acc_mode |= S_IXUGO; } /* * We cannot rely on the fs check since SYSV IPC does have an * additional creator id... */ ns = current->nsproxy->ipc_ns; rcu_read_lock(); shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } err = -EACCES; if (ipcperms(ns, &shp->shm_perm, acc_mode)) goto out_unlock; err = security_shm_shmat(&shp->shm_perm, shmaddr, shmflg); if (err) goto out_unlock; ipc_lock_object(&shp->shm_perm); /* check if shm_destroy() is tearing down shp */ if (!ipc_valid_object(&shp->shm_perm)) { ipc_unlock_object(&shp->shm_perm); err = -EIDRM; goto out_unlock; } /* * We need to take a reference to the real shm file to prevent the * pointer from becoming stale in cases where the lifetime of the outer * file extends beyond that of the shm segment. It's not usually * possible, but it can happen during remap_file_pages() emulation as * that unmaps the memory, then does ->mmap() via file reference only. * We'll deny the ->mmap() if the shm segment was since removed, but to * detect shm ID reuse we need to compare the file pointers. */ base = get_file(shp->shm_file); shp->shm_nattch++; size = i_size_read(file_inode(base)); ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); err = -ENOMEM; sfd = kzalloc(sizeof(*sfd), GFP_KERNEL); if (!sfd) { fput(base); goto out_nattch; } file = alloc_file_clone(base, f_flags, is_file_hugepages(base) ? &shm_file_operations_huge : &shm_file_operations); err = PTR_ERR(file); if (IS_ERR(file)) { kfree(sfd); fput(base); goto out_nattch; } sfd->id = shp->shm_perm.id; sfd->ns = get_ipc_ns(ns); sfd->file = base; sfd->vm_ops = NULL; file->private_data = sfd; err = security_mmap_file(file, prot, flags); if (err) goto out_fput; if (mmap_write_lock_killable(current->mm)) { err = -EINTR; goto out_fput; } if (addr && !(shmflg & SHM_REMAP)) { err = -EINVAL; if (addr + size < addr) goto invalid; if (find_vma_intersection(current->mm, addr, addr + size)) goto invalid; } addr = do_mmap(file, addr, size, prot, flags, 0, &populate, NULL); *raddr = addr; err = 0; if (IS_ERR_VALUE(addr)) err = (long)addr; invalid: mmap_write_unlock(current->mm); if (populate) mm_populate(addr, populate); out_fput: fput(file); out_nattch: down_write(&shm_ids(ns).rwsem); shp = shm_lock(ns, shmid); shp->shm_nattch--; if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); up_write(&shm_ids(ns).rwsem); return err; out_unlock: rcu_read_unlock(); out: return err; } SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) { unsigned long ret; long err; err = do_shmat(shmid, shmaddr, shmflg, &ret, SHMLBA); if (err) return err; force_successful_syscall_return(); return (long)ret; } #ifdef CONFIG_COMPAT #ifndef COMPAT_SHMLBA #define COMPAT_SHMLBA SHMLBA #endif COMPAT_SYSCALL_DEFINE3(shmat, int, shmid, compat_uptr_t, shmaddr, int, shmflg) { unsigned long ret; long err; err = do_shmat(shmid, compat_ptr(shmaddr), shmflg, &ret, COMPAT_SHMLBA); if (err) return err; force_successful_syscall_return(); return (long)ret; } #endif /* * detach and kill segment if marked destroyed. * The work is done in shm_close. */ long ksys_shmdt(char __user *shmaddr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long addr = (unsigned long)shmaddr; int retval = -EINVAL; #ifdef CONFIG_MMU loff_t size = 0; struct file *file; struct vm_area_struct *next; #endif if (addr & ~PAGE_MASK) return retval; if (mmap_write_lock_killable(mm)) return -EINTR; /* * This function tries to be smart and unmap shm segments that * were modified by partial mlock or munmap calls: * - It first determines the size of the shm segment that should be * unmapped: It searches for a vma that is backed by shm and that * started at address shmaddr. It records it's size and then unmaps * it. * - Then it unmaps all shm vmas that started at shmaddr and that * are within the initially determined size and that are from the * same shm segment from which we determined the size. * Errors from do_munmap are ignored: the function only fails if * it's called with invalid parameters or if it's called to unmap * a part of a vma. Both calls in this function are for full vmas, * the parameters are directly copied from the vma itself and always * valid - therefore do_munmap cannot fail. (famous last words?) */ /* * If it had been mremap()'d, the starting address would not * match the usual checks anyway. So assume all vma's are * above the starting address given. */ vma = find_vma(mm, addr); #ifdef CONFIG_MMU while (vma) { next = vma->vm_next; /* * Check if the starting address would match, i.e. it's * a fragment created by mprotect() and/or munmap(), or it * otherwise it starts at this address with no hassles. */ if ((vma->vm_ops == &shm_vm_ops) && (vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) { /* * Record the file of the shm segment being * unmapped. With mremap(), someone could place * page from another segment but with equal offsets * in the range we are unmapping. */ file = vma->vm_file; size = i_size_read(file_inode(vma->vm_file)); do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL); /* * We discovered the size of the shm segment, so * break out of here and fall through to the next * loop that uses the size information to stop * searching for matching vma's. */ retval = 0; vma = next; break; } vma = next; } /* * We need look no further than the maximum address a fragment * could possibly have landed at. Also cast things to loff_t to * prevent overflows and make comparisons vs. equal-width types. */ size = PAGE_ALIGN(size); while (vma && (loff_t)(vma->vm_end - addr) <= size) { next = vma->vm_next; /* finding a matching vma now does not alter retval */ if ((vma->vm_ops == &shm_vm_ops) && ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) && (vma->vm_file == file)) do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL); vma = next; } #else /* CONFIG_MMU */ /* under NOMMU conditions, the exact address to be destroyed must be * given */ if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) { do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL); retval = 0; } #endif mmap_write_unlock(mm); return retval; } SYSCALL_DEFINE1(shmdt, char __user *, shmaddr) { return ksys_shmdt(shmaddr); } #ifdef CONFIG_PROC_FS static int sysvipc_shm_proc_show(struct seq_file *s, void *it) { struct pid_namespace *pid_ns = ipc_seq_pid_ns(s); struct user_namespace *user_ns = seq_user_ns(s); struct kern_ipc_perm *ipcp = it; struct shmid_kernel *shp; unsigned long rss = 0, swp = 0; shp = container_of(ipcp, struct shmid_kernel, shm_perm); shm_add_rss_swap(shp, &rss, &swp); #if BITS_PER_LONG <= 32 #define SIZE_SPEC "%10lu" #else #define SIZE_SPEC "%21lu" #endif seq_printf(s, "%10d %10d %4o " SIZE_SPEC " %5u %5u " "%5lu %5u %5u %5u %5u %10llu %10llu %10llu " SIZE_SPEC " " SIZE_SPEC "\n", shp->shm_perm.key, shp->shm_perm.id, shp->shm_perm.mode, shp->shm_segsz, pid_nr_ns(shp->shm_cprid, pid_ns), pid_nr_ns(shp->shm_lprid, pid_ns), shp->shm_nattch, from_kuid_munged(user_ns, shp->shm_perm.uid), from_kgid_munged(user_ns, shp->shm_perm.gid), from_kuid_munged(user_ns, shp->shm_perm.cuid), from_kgid_munged(user_ns, shp->shm_perm.cgid), shp->shm_atim, shp->shm_dtim, shp->shm_ctim, rss * PAGE_SIZE, swp * PAGE_SIZE); return 0; } #endif |
| 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 | // SPDX-License-Identifier: GPL-2.0-only /* * Linux VM pressure * * Copyright 2012 Linaro Ltd. * Anton Vorontsov <anton.vorontsov@linaro.org> * * Based on ideas from Andrew Morton, David Rientjes, KOSAKI Motohiro, * Leonid Moiseichuk, Mel Gorman, Minchan Kim and Pekka Enberg. */ #include <linux/cgroup.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/eventfd.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/printk.h> #include <linux/vmpressure.h> /* * The window size (vmpressure_win) is the number of scanned pages before * we try to analyze scanned/reclaimed ratio. So the window is used as a * rate-limit tunable for the "low" level notification, and also for * averaging the ratio for medium/critical levels. Using small window * sizes can cause lot of false positives, but too big window size will * delay the notifications. * * As the vmscan reclaimer logic works with chunks which are multiple of * SWAP_CLUSTER_MAX, it makes sense to use it for the window size as well. * * TODO: Make the window size depend on machine size, as we do for vmstat * thresholds. Currently we set it to 512 pages (2MB for 4KB pages). */ static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 16; /* * These thresholds are used when we account memory pressure through * scanned/reclaimed ratio. The current values were chosen empirically. In * essence, they are percents: the higher the value, the more number * unsuccessful reclaims there were. */ static const unsigned int vmpressure_level_med = 60; static const unsigned int vmpressure_level_critical = 95; /* * When there are too little pages left to scan, vmpressure() may miss the * critical pressure as number of pages will be less than "window size". * However, in that case the vmscan priority will raise fast as the * reclaimer will try to scan LRUs more deeply. * * The vmscan logic considers these special priorities: * * prio == DEF_PRIORITY (12): reclaimer starts with that value * prio <= DEF_PRIORITY - 2 : kswapd becomes somewhat overwhelmed * prio == 0 : close to OOM, kernel scans every page in an lru * * Any value in this range is acceptable for this tunable (i.e. from 12 to * 0). Current value for the vmpressure_level_critical_prio is chosen * empirically, but the number, in essence, means that we consider * critical level when scanning depth is ~10% of the lru size (vmscan * scans 'lru_size >> prio' pages, so it is actually 12.5%, or one * eights). */ static const unsigned int vmpressure_level_critical_prio = ilog2(100 / 10); static struct vmpressure *work_to_vmpressure(struct work_struct *work) { return container_of(work, struct vmpressure, work); } static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) { struct mem_cgroup *memcg = vmpressure_to_memcg(vmpr); memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return memcg_to_vmpressure(memcg); } enum vmpressure_levels { VMPRESSURE_LOW = 0, VMPRESSURE_MEDIUM, VMPRESSURE_CRITICAL, VMPRESSURE_NUM_LEVELS, }; enum vmpressure_modes { VMPRESSURE_NO_PASSTHROUGH = 0, VMPRESSURE_HIERARCHY, VMPRESSURE_LOCAL, VMPRESSURE_NUM_MODES, }; static const char * const vmpressure_str_levels[] = { [VMPRESSURE_LOW] = "low", [VMPRESSURE_MEDIUM] = "medium", [VMPRESSURE_CRITICAL] = "critical", }; static const char * const vmpressure_str_modes[] = { [VMPRESSURE_NO_PASSTHROUGH] = "default", [VMPRESSURE_HIERARCHY] = "hierarchy", [VMPRESSURE_LOCAL] = "local", }; static enum vmpressure_levels vmpressure_level(unsigned long pressure) { if (pressure >= vmpressure_level_critical) return VMPRESSURE_CRITICAL; else if (pressure >= vmpressure_level_med) return VMPRESSURE_MEDIUM; return VMPRESSURE_LOW; } static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, unsigned long reclaimed) { unsigned long scale = scanned + reclaimed; unsigned long pressure = 0; /* * reclaimed can be greater than scanned for things such as reclaimed * slab pages. shrink_node() just adds reclaimed pages without a * related increment to scanned pages. */ if (reclaimed >= scanned) goto out; /* * We calculate the ratio (in percents) of how many pages were * scanned vs. reclaimed in a given time frame (window). Note that * time is in VM reclaimer's "ticks", i.e. number of pages * scanned. This makes it possible to set desired reaction time * and serves as a ratelimit. */ pressure = scale - (reclaimed * scale / scanned); pressure = pressure * 100 / scale; out: pr_debug("%s: %3lu (s: %lu r: %lu)\n", __func__, pressure, scanned, reclaimed); return vmpressure_level(pressure); } struct vmpressure_event { struct eventfd_ctx *efd; enum vmpressure_levels level; enum vmpressure_modes mode; struct list_head node; }; static bool vmpressure_event(struct vmpressure *vmpr, const enum vmpressure_levels level, bool ancestor, bool signalled) { struct vmpressure_event *ev; bool ret = false; mutex_lock(&vmpr->events_lock); list_for_each_entry(ev, &vmpr->events, node) { if (ancestor && ev->mode == VMPRESSURE_LOCAL) continue; if (signalled && ev->mode == VMPRESSURE_NO_PASSTHROUGH) continue; if (level < ev->level) continue; eventfd_signal(ev->efd, 1); ret = true; } mutex_unlock(&vmpr->events_lock); return ret; } static void vmpressure_work_fn(struct work_struct *work) { struct vmpressure *vmpr = work_to_vmpressure(work); unsigned long scanned; unsigned long reclaimed; enum vmpressure_levels level; bool ancestor = false; bool signalled = false; spin_lock(&vmpr->sr_lock); /* * Several contexts might be calling vmpressure(), so it is * possible that the work was rescheduled again before the old * work context cleared the counters. In that case we will run * just after the old work returns, but then scanned might be zero * here. No need for any locks here since we don't care if * vmpr->reclaimed is in sync. */ scanned = vmpr->tree_scanned; if (!scanned) { spin_unlock(&vmpr->sr_lock); return; } reclaimed = vmpr->tree_reclaimed; vmpr->tree_scanned = 0; vmpr->tree_reclaimed = 0; spin_unlock(&vmpr->sr_lock); level = vmpressure_calc_level(scanned, reclaimed); do { if (vmpressure_event(vmpr, level, ancestor, signalled)) signalled = true; ancestor = true; } while ((vmpr = vmpressure_parent(vmpr))); } /** * vmpressure() - Account memory pressure through scanned/reclaimed ratio * @gfp: reclaimer's gfp mask * @memcg: cgroup memory controller handle * @tree: legacy subtree mode * @scanned: number of pages scanned * @reclaimed: number of pages reclaimed * * This function should be called from the vmscan reclaim path to account * "instantaneous" memory pressure (scanned/reclaimed ratio). The raw * pressure index is then further refined and averaged over time. * * If @tree is set, vmpressure is in traditional userspace reporting * mode: @memcg is considered the pressure root and userspace is * notified of the entire subtree's reclaim efficiency. * * If @tree is not set, reclaim efficiency is recorded for @memcg, and * only in-kernel users are notified. * * This function does not return any value. */ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed) { struct vmpressure *vmpr; if (mem_cgroup_disabled()) return; /* * The in-kernel users only care about the reclaim efficiency * for this @memcg rather than the whole subtree, and there * isn't and won't be any in-kernel user in a legacy cgroup. */ if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !tree) return; vmpr = memcg_to_vmpressure(memcg); /* * Here we only want to account pressure that userland is able to * help us with. For example, suppose that DMA zone is under * pressure; if we notify userland about that kind of pressure, * then it will be mostly a waste as it will trigger unnecessary * freeing of memory by userland (since userland is more likely to * have HIGHMEM/MOVABLE pages instead of the DMA fallback). That * is why we include only movable, highmem and FS/IO pages. * Indirect reclaim (kswapd) sets sc->gfp_mask to GFP_KERNEL, so * we account it too. */ if (!(gfp & (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_IO | __GFP_FS))) return; /* * If we got here with no pages scanned, then that is an indicator * that reclaimer was unable to find any shrinkable LRUs at the * current scanning depth. But it does not mean that we should * report the critical pressure, yet. If the scanning priority * (scanning depth) goes too high (deep), we will be notified * through vmpressure_prio(). But so far, keep calm. */ if (!scanned) return; if (tree) { spin_lock(&vmpr->sr_lock); scanned = vmpr->tree_scanned += scanned; vmpr->tree_reclaimed += reclaimed; spin_unlock(&vmpr->sr_lock); if (scanned < vmpressure_win) return; schedule_work(&vmpr->work); } else { enum vmpressure_levels level; /* For now, no users for root-level efficiency */ if (!memcg || mem_cgroup_is_root(memcg)) return; spin_lock(&vmpr->sr_lock); scanned = vmpr->scanned += scanned; reclaimed = vmpr->reclaimed += reclaimed; if (scanned < vmpressure_win) { spin_unlock(&vmpr->sr_lock); return; } vmpr->scanned = vmpr->reclaimed = 0; spin_unlock(&vmpr->sr_lock); level = vmpressure_calc_level(scanned, reclaimed); if (level > VMPRESSURE_LOW) { /* * Let the socket buffer allocator know that * we are having trouble reclaiming LRU pages. * * For hysteresis keep the pressure state * asserted for a second in which subsequent * pressure events can occur. */ memcg->socket_pressure = jiffies + HZ; } } } /** * vmpressure_prio() - Account memory pressure through reclaimer priority level * @gfp: reclaimer's gfp mask * @memcg: cgroup memory controller handle * @prio: reclaimer's priority * * This function should be called from the reclaim path every time when * the vmscan's reclaiming priority (scanning depth) changes. * * This function does not return any value. */ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) { /* * We only use prio for accounting critical level. For more info * see comment for vmpressure_level_critical_prio variable above. */ if (prio > vmpressure_level_critical_prio) return; /* * OK, the prio is below the threshold, updating vmpressure * information before shrinker dives into long shrinking of long * range vmscan. Passing scanned = vmpressure_win, reclaimed = 0 * to the vmpressure() basically means that we signal 'critical' * level. */ vmpressure(gfp, memcg, true, vmpressure_win, 0); } #define MAX_VMPRESSURE_ARGS_LEN (strlen("critical") + strlen("hierarchy") + 2) /** * vmpressure_register_event() - Bind vmpressure notifications to an eventfd * @memcg: memcg that is interested in vmpressure notifications * @eventfd: eventfd context to link notifications with * @args: event arguments (pressure level threshold, optional mode) * * This function associates eventfd context with the vmpressure * infrastructure, so that the notifications will be delivered to the * @eventfd. The @args parameter is a comma-delimited string that denotes a * pressure level threshold (one of vmpressure_str_levels, i.e. "low", "medium", * or "critical") and an optional mode (one of vmpressure_str_modes, i.e. * "hierarchy" or "local"). * * To be used as memcg event method. * * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could * not be parsed. */ int vmpressure_register_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd, const char *args) { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH; enum vmpressure_levels level; char *spec, *spec_orig; char *token; int ret = 0; spec_orig = spec = kstrndup(args, MAX_VMPRESSURE_ARGS_LEN, GFP_KERNEL); if (!spec) return -ENOMEM; /* Find required level */ token = strsep(&spec, ","); ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); if (ret < 0) goto out; level = ret; /* Find optional mode */ token = strsep(&spec, ","); if (token) { ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); if (ret < 0) goto out; mode = ret; } ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) { ret = -ENOMEM; goto out; } ev->efd = eventfd; ev->level = level; ev->mode = mode; mutex_lock(&vmpr->events_lock); list_add(&ev->node, &vmpr->events); mutex_unlock(&vmpr->events_lock); ret = 0; out: kfree(spec_orig); return ret; } /** * vmpressure_unregister_event() - Unbind eventfd from vmpressure * @memcg: memcg handle * @eventfd: eventfd context that was used to link vmpressure with the @cg * * This function does internal manipulations to detach the @eventfd from * the vmpressure notifications, and then frees internal resources * associated with the @eventfd (but the @eventfd itself is not freed). * * To be used as memcg event method. */ void vmpressure_unregister_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd) { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; mutex_lock(&vmpr->events_lock); list_for_each_entry(ev, &vmpr->events, node) { if (ev->efd != eventfd) continue; list_del(&ev->node); kfree(ev); break; } mutex_unlock(&vmpr->events_lock); } /** * vmpressure_init() - Initialize vmpressure control structure * @vmpr: Structure to be initialized * * This function should be called on every allocated vmpressure structure * before any usage. */ void vmpressure_init(struct vmpressure *vmpr) { spin_lock_init(&vmpr->sr_lock); mutex_init(&vmpr->events_lock); INIT_LIST_HEAD(&vmpr->events); INIT_WORK(&vmpr->work, vmpressure_work_fn); } /** * vmpressure_cleanup() - shuts down vmpressure control structure * @vmpr: Structure to be cleaned up * * This function should be called before the structure in which it is * embedded is cleaned up. */ void vmpressure_cleanup(struct vmpressure *vmpr) { /* * Make sure there is no pending work before eventfd infrastructure * goes away. */ flush_work(&vmpr->work); } |
| 49 49 49 49 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS An implementation of the IP virtual server support for the * LINUX operating system. IPVS is now implemented as a module * over the Netfilter framework. IPVS can be used to build a * high-performance and highly available server based on a * cluster of servers. * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Peter Kese <peter.kese@ijs.si> * Julian Anastasov <ja@ssi.bg> * * The IPVS code for kernel 2.2 was done by Wensong Zhang and Peter Kese, * with changes/fixes from Julian Anastasov, Lars Marowsky-Bree, Horms * and others. * * Changes: * Paul `Rusty' Russell properly handle non-linear skbs * Harald Welte don't use nfcache */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/sctp.h> #include <linux/icmp.h> #include <linux/slab.h> #include <net/ip.h> #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> /* for icmp_send */ #include <net/gue.h> #include <net/gre.h> #include <net/route.h> #include <net/ip6_checksum.h> #include <net/netns/generic.h> /* net_generic() */ #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <linux/netfilter_ipv6.h> #include <net/ip6_route.h> #endif #include <net/ip_vs.h> #include <linux/indirect_call_wrapper.h> EXPORT_SYMBOL(register_ip_vs_scheduler); EXPORT_SYMBOL(unregister_ip_vs_scheduler); EXPORT_SYMBOL(ip_vs_proto_name); EXPORT_SYMBOL(ip_vs_conn_new); EXPORT_SYMBOL(ip_vs_conn_in_get); EXPORT_SYMBOL(ip_vs_conn_out_get); #ifdef CONFIG_IP_VS_PROTO_TCP EXPORT_SYMBOL(ip_vs_tcp_conn_listen); #endif EXPORT_SYMBOL(ip_vs_conn_put); #ifdef CONFIG_IP_VS_DEBUG EXPORT_SYMBOL(ip_vs_get_debug_level); #endif EXPORT_SYMBOL(ip_vs_new_conn_out); #if defined(CONFIG_IP_VS_PROTO_TCP) && defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) \ INDIRECT_CALL_2(f, tcp_snat_handler, udp_snat_handler, __VA_ARGS__) #elif defined(CONFIG_IP_VS_PROTO_TCP) #define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, tcp_snat_handler, __VA_ARGS__) #elif defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, udp_snat_handler, __VA_ARGS__) #else #define SNAT_CALL(f, ...) f(__VA_ARGS__) #endif static unsigned int ip_vs_net_id __read_mostly; /* netns cnt used for uniqueness */ static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0); /* ID used in ICMP lookups */ #define icmp_id(icmph) (((icmph)->un).echo.id) #define icmpv6_id(icmph) (icmph->icmp6_dataun.u_echo.identifier) const char *ip_vs_proto_name(unsigned int proto) { static char buf[20]; switch (proto) { case IPPROTO_IP: return "IP"; case IPPROTO_UDP: return "UDP"; case IPPROTO_TCP: return "TCP"; case IPPROTO_SCTP: return "SCTP"; case IPPROTO_ICMP: return "ICMP"; #ifdef CONFIG_IP_VS_IPV6 case IPPROTO_ICMPV6: return "ICMPv6"; #endif default: sprintf(buf, "IP_%u", proto); return buf; } } void ip_vs_init_hash_table(struct list_head *table, int rows) { while (--rows >= 0) INIT_LIST_HEAD(&table[rows]); } static inline void ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; local_bh_disable(); s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); local_bh_enable(); } } static inline void ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; local_bh_disable(); s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); local_bh_enable(); } } static inline void ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) { struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_cpu_stats *s; local_bh_disable(); s = this_cpu_ptr(cp->dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); local_bh_enable(); } static inline void ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { if (likely(pd->pp->state_transition)) pd->pp->state_transition(cp, direction, skb, pd); } static inline int ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, struct sk_buff *skb, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { ip_vs_conn_fill_param(svc->ipvs, svc->af, protocol, caddr, cport, vaddr, vport, p); p->pe = rcu_dereference(svc->pe); if (p->pe && p->pe->fill_param) return p->pe->fill_param(p, skb); return 0; } /* * IPVS persistent scheduling function * It creates a connection entry according to its template if exists, * or selects a server and creates a connection entry plus a template. * Locking: we are svc user (svc->refcnt), so we hold all dests too * Protocols supported: TCP, UDP */ static struct ip_vs_conn * ip_vs_sched_persist(struct ip_vs_service *svc, struct sk_buff *skb, __be16 src_port, __be16 dst_port, int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp = NULL; struct ip_vs_dest *dest; struct ip_vs_conn *ct; __be16 dport = 0; /* destination port to forward */ unsigned int flags; struct ip_vs_conn_param param; const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; union nf_inet_addr snet; /* source network of the client, after masking */ const union nf_inet_addr *src_addr, *dst_addr; if (likely(!ip_vs_iph_inverse(iph))) { src_addr = &iph->saddr; dst_addr = &iph->daddr; } else { src_addr = &iph->daddr; dst_addr = &iph->saddr; } /* Mask saddr with the netmask to adjust template granularity */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) ipv6_addr_prefix(&snet.in6, &src_addr->in6, (__force __u32) svc->netmask); else #endif snet.ip = src_addr->ip & svc->netmask; IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u " "mnet %s\n", IP_VS_DBG_ADDR(svc->af, src_addr), ntohs(src_port), IP_VS_DBG_ADDR(svc->af, dst_addr), ntohs(dst_port), IP_VS_DBG_ADDR(svc->af, &snet)); /* * As far as we know, FTP is a very complicated network protocol, and * it uses control connection and data connections. For active FTP, * FTP server initialize data connection to the client, its source port * is often 20. For passive FTP, FTP server tells the clients the port * that it passively listens to, and the client issues the data * connection. In the tunneling or direct routing mode, the load * balancer is on the client-to-server half of connection, the port * number is unknown to the load balancer. So, a conn template like * <caddr, 0, vaddr, 0, daddr, 0> is created for persistent FTP * service, and a template like <caddr, 0, vaddr, vport, daddr, dport> * is created for other persistent services. */ { int protocol = iph->protocol; const union nf_inet_addr *vaddr = dst_addr; __be16 vport = 0; if (dst_port == svc->port) { /* non-FTP template: * <protocol, caddr, 0, vaddr, vport, daddr, dport> * FTP template: * <protocol, caddr, 0, vaddr, 0, daddr, 0> */ if (svc->port != FTPPORT) vport = dst_port; } else { /* Note: persistent fwmark-based services and * persistent port zero service are handled here. * fwmark template: * <IPPROTO_IP,caddr,0,fwmark,0,daddr,0> * port zero template: * <protocol,caddr,0,vaddr,0,daddr,0> */ if (svc->fwmark) { protocol = IPPROTO_IP; vaddr = &fwmark; } } /* return *ignored = -1 so NF_DROP can be used */ if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, vaddr, vport, ¶m) < 0) { *ignored = -1; return NULL; } } /* Check if a template already exists */ ct = ip_vs_ct_in_get(¶m); if (!ct || !ip_vs_check_template(ct, NULL)) { struct ip_vs_scheduler *sched; /* * No template found or the dest of the connection * template is not available. * return *ignored=0 i.e. ICMP and NF_DROP */ sched = rcu_dereference(svc->scheduler); if (sched) { /* read svc->sched_data after svc->scheduler */ smp_rmb(); dest = sched->schedule(svc, skb, iph); } else { dest = NULL; } if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); *ignored = 0; return NULL; } if (dst_port == svc->port && svc->port != FTPPORT) dport = dest->port; /* Create a template * This adds param.pe_data to the template, * and thus param.pe_data will be destroyed * when the template expires */ ct = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, IP_VS_CONN_F_TEMPLATE, dest, skb->mark); if (ct == NULL) { kfree(param.pe_data); *ignored = -1; return NULL; } ct->timeout = svc->timeout; } else { /* set destination with the found template */ dest = ct->dest; kfree(param.pe_data); } dport = dst_port; if (dport == svc->port && dest->port) dport = dest->port; flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a new connection according to the template */ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, src_addr, src_port, dst_addr, dst_port, ¶m); cp = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, flags, dest, skb->mark); if (cp == NULL) { ip_vs_conn_put(ct); *ignored = -1; return NULL; } /* * Add its control */ ip_vs_control_add(cp, ct); ip_vs_conn_put(ct); ip_vs_conn_stats(cp, svc); return cp; } /* * IPVS main scheduling function * It selects a server according to the virtual service, and * creates a connection entry. * Protocols supported: TCP, UDP * * Usage of *ignored * * 1 : protocol tried to schedule (eg. on SYN), found svc but the * svc/scheduler decides that this packet should be accepted with * NF_ACCEPT because it must not be scheduled. * * 0 : scheduler can not find destination, so try bypass or * return ICMP and then NF_DROP (ip_vs_leave). * * -1 : scheduler tried to schedule but fatal error occurred, eg. * ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param * failure such as missing Call-ID, ENOMEM on skb_linearize * or pe_data. In this case we should return NF_DROP without * any attempts to send ICMP with ip_vs_leave. */ struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; struct ip_vs_conn *cp = NULL; struct ip_vs_scheduler *sched; struct ip_vs_dest *dest; __be16 _ports[2], *pptr, cport, vport; const void *caddr, *vaddr; unsigned int flags; *ignored = 1; /* * IPv6 frags, only the first hit here. */ pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (pptr == NULL) return NULL; if (likely(!ip_vs_iph_inverse(iph))) { cport = pptr[0]; caddr = &iph->saddr; vport = pptr[1]; vaddr = &iph->daddr; } else { cport = pptr[1]; caddr = &iph->daddr; vport = pptr[0]; vaddr = &iph->saddr; } /* * FTPDATA needs this check when using local real server. * Never schedule Active FTPDATA connections from real server. * For LVS-NAT they must be already created. For other methods * with persistence the connection is created on SYN+ACK. */ if (cport == FTPDATA) { IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling FTPDATA"); return NULL; } /* * Do not schedule replies from local real server. */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) { iph->hdr_flags ^= IP_VS_HDR_INVERSE; cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, svc->ipvs, svc->af, skb, iph); iph->hdr_flags ^= IP_VS_HDR_INVERSE; if (cp) { IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling reply for existing" " connection"); __ip_vs_conn_put(cp); return NULL; } } /* * Persistent service */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) return ip_vs_sched_persist(svc, skb, cport, vport, ignored, iph); *ignored = 0; /* * Non-persistent service */ if (!svc->fwmark && vport != svc->port) { if (!svc->port) pr_err("Schedule: port zero only supported " "in persistent services, " "check your ipvs configuration\n"); return NULL; } sched = rcu_dereference(svc->scheduler); if (sched) { /* read svc->sched_data after svc->scheduler */ smp_rmb(); dest = sched->schedule(svc, skb, iph); } else { dest = NULL; } if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); return NULL; } flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a connection entry. */ { struct ip_vs_conn_param p; ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, &p); cp = ip_vs_conn_new(&p, dest->af, &dest->addr, dest->port ? dest->port : vport, flags, dest, skb->mark); if (!cp) { *ignored = -1; return NULL; } } IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", ip_vs_fwd_tag(cp), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); ip_vs_conn_stats(cp, svc); return cp; } static inline int ip_vs_addr_is_unicast(struct net *net, int af, union nf_inet_addr *addr) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) return ipv6_addr_type(&addr->in6) & IPV6_ADDR_UNICAST; #endif return (inet_addr_type(net, addr->ip) == RTN_UNICAST); } /* * Pass or drop the packet. * Called by ip_vs_in, when the virtual service is available but * no destination is available for a new connection. */ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph) { __be16 _ports[2], *pptr, dport; struct netns_ipvs *ipvs = svc->ipvs; struct net *net = ipvs->net; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (!pptr) return NF_DROP; dport = likely(!ip_vs_iph_inverse(iph)) ? pptr[1] : pptr[0]; /* if it is fwmark-based service, the cache_bypass sysctl is up and the destination is a non-local unicast, then create a cache_bypass connection entry */ if (sysctl_cache_bypass(ipvs) && svc->fwmark && !(iph->hdr_flags & (IP_VS_HDR_INVERSE | IP_VS_HDR_ICMP)) && ip_vs_addr_is_unicast(net, svc->af, &iph->daddr)) { int ret; struct ip_vs_conn *cp; unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } }; /* create a new connection entry */ IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, svc->af, &daddr, 0, IP_VS_CONN_F_BYPASS | flags, NULL, skb->mark); if (!cp) return NF_DROP; } /* statistics */ ip_vs_in_stats(cp, skb); /* set state */ ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); /* transmit the first SYN packet */ ret = cp->packet_xmit(skb, cp, pd->pp, iph); /* do not touch skb anymore */ if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control) atomic_inc(&cp->control->in_pkts); else atomic_inc(&cp->in_pkts); ip_vs_conn_put(cp); return ret; } /* * When the virtual ftp service is presented, packets destined * for other services on the VIP may get here (except services * listed in the ipvs table), pass the packets, because it is * not ipvs job to decide to drop the packets. */ if (svc->port == FTPPORT && dport != FTPPORT) return NF_ACCEPT; if (unlikely(ip_vs_iph_icmp(iph))) return NF_DROP; /* * Notify the client that the destination is unreachable, and * release the socket buffer. * Since it is in IP layer, the TCP socket is not actually * created, the TCP RST packet cannot be sent, instead that * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) { if (!skb->dev) skb->dev = net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); return NF_DROP; } #ifdef CONFIG_SYSCTL static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return ipvs->sysctl_snat_reroute; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return ipvs->sysctl_nat_icmp_send; } #else static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return 0; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; } #endif __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); } static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum) { if (NF_INET_LOCAL_IN == hooknum) return IP_DEFRAG_VS_IN; if (NF_INET_FORWARD == hooknum) return IP_DEFRAG_VS_FWD; return IP_DEFRAG_VS_OUT; } static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs, struct sk_buff *skb, u_int32_t user) { int err; local_bh_disable(); err = ip_defrag(ipvs->net, skb, user); local_bh_enable(); if (!err) ip_send_check(ip_hdr(skb)); return err; } static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, unsigned int hooknum) { if (!sysctl_snat_reroute(ipvs)) return 0; /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */ if (NF_INET_LOCAL_IN == hooknum) return 0; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0) return 1; } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0) return 1; return 0; } /* * Packet has been made sufficiently writable in caller * - inout: 1=in->out, 0=out->in */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct iphdr *iph = ip_hdr(skb); unsigned int icmp_offset = iph->ihl*4; struct icmphdr *icmph = (struct icmphdr *)(skb_network_header(skb) + icmp_offset); struct iphdr *ciph = (struct iphdr *)(icmph + 1); if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); ciph->daddr = cp->vaddr.ip; ip_send_check(ciph); } else { iph->daddr = cp->daddr.ip; ip_send_check(iph); ciph->saddr = cp->daddr.ip; ip_send_check(ciph); } /* the TCP/UDP/SCTP port */ if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol || IPPROTO_SCTP == ciph->protocol) { __be16 *ports = (void *)ciph + ciph->ihl*4; if (inout) ports[1] = cp->vport; else ports[0] = cp->dport; } /* And finally the ICMP checksum */ icmph->checksum = 0; icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset); skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMP"); else IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMP"); } #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct ipv6hdr *iph = ipv6_hdr(skb); unsigned int icmp_offset = 0; unsigned int offs = 0; /* header offset*/ int protocol; struct icmp6hdr *icmph; struct ipv6hdr *ciph; unsigned short fragoffs; ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL); icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset); offs = icmp_offset + sizeof(struct icmp6hdr); ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs); protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL); if (inout) { iph->saddr = cp->vaddr.in6; ciph->daddr = cp->vaddr.in6; } else { iph->daddr = cp->daddr.in6; ciph->saddr = cp->daddr.in6; } /* the TCP/UDP/SCTP port */ if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol)) { __be16 *ports = (void *)(skb_network_header(skb) + offs); IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__, ntohs(inout ? ports[1] : ports[0]), ntohs(inout ? cp->vport : cp->dport)); if (inout) ports[1] = cp->vport; else ports[0] = cp->dport; } /* And finally the ICMP checksum */ icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, skb->len - icmp_offset, IPPROTO_ICMPV6, 0); skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset; skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum); skb->ip_summed = CHECKSUM_PARTIAL; if (inout) IP_VS_DBG_PKT(11, AF_INET6, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMPv6"); else IP_VS_DBG_PKT(11, AF_INET6, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMPv6"); } #endif /* Handle relevant response ICMP messages - forward to the right * destination host. */ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, __u8 protocol, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, unsigned int offset, unsigned int ihl, unsigned int hooknum) { unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { /* Failed checksum! */ IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n", IP_VS_DBG_ADDR(af, snet)); goto out; } if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol) offset += 2 * sizeof(__u16); if (skb_ensure_writable(skb, offset)) goto out; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_nat_icmp_v6(skb, pp, cp, 1); else #endif ip_vs_nat_icmp(skb, pp, cp, 1); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; after_nat: /* do the statistics and put it back */ ip_vs_out_stats(cp, skb); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); verdict = NF_ACCEPT; out: __ip_vs_conn_put(cp); return verdict; } /* * Handle ICMP messages in the inside-to-outside direction (outgoing). * Find any that might be relevant, check against existing connections. * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; unsigned int offset, ihl; union nf_inet_addr snet; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } iph = ip_hdr(skb); offset = ihl = iph->ihl * 4; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), &iph->saddr, &iph->daddr); /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if ((ic->type != ICMP_DEST_UNREACH) && (ic->type != ICMP_SOURCE_QUENCH) && (ic->type != ICMP_TIME_EXCEEDED)) { *related = 0; return NF_ACCEPT; } /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(cih->protocol); if (!pp) return NF_ACCEPT; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET, skb, &ciph); if (!cp) return NF_ACCEPT; snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, pp, ciph.len, ihl, hooknum); } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *ipvsh) { struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; union nf_inet_addr snet; unsigned int offset; *related = 1; ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } /* Fragment header that is before ICMP header tells us that: * it's not an error message since they can't be fragmented. */ if (ipvsh->flags & IP6_FH_F_FRAG) return NF_DROP; IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n", ic->icmp6_type, ntohs(icmpv6_id(ic)), &ipvsh->saddr, &ipvsh->daddr); if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, ipvsh->len + sizeof(_icmph), true, &ciph)) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET6, skb, &ciph); if (!cp) return NF_ACCEPT; snet.in6 = ciph.saddr.in6; offset = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, pp, offset, sizeof(struct ipv6hdr), hooknum); } #endif /* * Check if sctp chunc is ABORT chunk */ static inline int is_sctp_abort(const struct sk_buff *skb, int nh_len) { struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, nh_len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return 0; if (sch->type == SCTP_CID_ABORT) return 1; return 0; } static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len) { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, nh_len, sizeof(_tcph), &_tcph); if (th == NULL) return 0; return th->rst; } static inline bool is_new_conn(const struct sk_buff *skb, struct ip_vs_iphdr *iph) { switch (iph->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); if (th == NULL) return false; return th->syn; } case IPPROTO_SCTP: { struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, iph->len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return false; return sch->type == SCTP_CID_INIT; } default: return false; } } static inline bool is_new_conn_expected(const struct ip_vs_conn *cp, int conn_reuse_mode) { /* Controlled (FTP DATA or persistence)? */ if (cp->control) return false; switch (cp->protocol) { case IPPROTO_TCP: return (cp->state == IP_VS_TCP_S_TIME_WAIT) || (cp->state == IP_VS_TCP_S_CLOSE) || ((conn_reuse_mode & 2) && (cp->state == IP_VS_TCP_S_FIN_WAIT) && (cp->flags & IP_VS_CONN_F_NOOUTPUT)); case IPPROTO_SCTP: return cp->state == IP_VS_SCTP_S_CLOSED; default: return false; } } /* Generic function to create new connections for outgoing RS packets * * Pre-requisites for successful connection creation: * 1) Virtual Service is NOT fwmark based: * In fwmark-VS actual vaddr and vport are unknown to IPVS * 2) Real Server and Virtual Service were NOT configured without port: * This is to allow match of different VS to the same RS ip-addr */ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct sk_buff *skb, const struct ip_vs_iphdr *iph, __be16 dport, __be16 cport) { struct ip_vs_conn_param param; struct ip_vs_conn *ct = NULL, *cp = NULL; const union nf_inet_addr *vaddr, *daddr, *caddr; union nf_inet_addr snet; __be16 vport; unsigned int flags; EnterFunction(12); vaddr = &svc->addr; vport = svc->port; daddr = &iph->saddr; caddr = &iph->daddr; /* check pre-requisites are satisfied */ if (svc->fwmark) return NULL; if (!vport || !dport) return NULL; /* for persistent service first create connection template */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) { /* apply netmask the same way ingress-side does */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) ipv6_addr_prefix(&snet.in6, &caddr->in6, (__force __u32)svc->netmask); else #endif snet.ip = caddr->ip & svc->netmask; /* fill params and create template if not existent */ if (ip_vs_conn_fill_param_persist(svc, skb, iph->protocol, &snet, 0, vaddr, vport, ¶m) < 0) return NULL; ct = ip_vs_ct_in_get(¶m); /* check if template exists and points to the same dest */ if (!ct || !ip_vs_check_template(ct, dest)) { ct = ip_vs_conn_new(¶m, dest->af, daddr, dport, IP_VS_CONN_F_TEMPLATE, dest, 0); if (!ct) { kfree(param.pe_data); return NULL; } ct->timeout = svc->timeout; } else { kfree(param.pe_data); } } /* connection flags */ flags = ((svc->flags & IP_VS_SVC_F_ONEPACKET) && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* create connection */ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, ¶m); cp = ip_vs_conn_new(¶m, dest->af, daddr, dport, flags, dest, 0); if (!cp) { if (ct) ip_vs_conn_put(ct); return NULL; } if (ct) { ip_vs_control_add(cp, ct); ip_vs_conn_put(ct); } ip_vs_conn_stats(cp, svc); /* return connection (will be used to handle outgoing packet) */ IP_VS_DBG_BUF(6, "New connection RS-initiated:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", ip_vs_fwd_tag(cp), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); LeaveFunction(12); return cp; } /* Handle outgoing packets which are considered requests initiated by * real servers, so that subsequent responses from external client can be * routed to the right real server. * Used also for outgoing responses in OPS mode. * * Connection management is handled by persistent-engine specific callback. */ static struct ip_vs_conn *__ip_vs_rs_conn_out(unsigned int hooknum, struct netns_ipvs *ipvs, int af, struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest; struct ip_vs_conn *cp = NULL; __be16 _ports[2], *pptr; if (hooknum == NF_INET_LOCAL_IN) return NULL; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (!pptr) return NULL; dest = ip_vs_find_real_service(ipvs, af, iph->protocol, &iph->saddr, pptr[0]); if (dest) { struct ip_vs_service *svc; struct ip_vs_pe *pe; svc = rcu_dereference(dest->svc); if (svc) { pe = rcu_dereference(svc->pe); if (pe && pe->conn_out) cp = pe->conn_out(svc, dest, skb, iph, pptr[0], pptr[1]); } } return cp; } /* Handle response packets: rewrite addresses and send away... */ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph, unsigned int hooknum) { struct ip_vs_protocol *pp = pd->pp; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet"); if (skb_ensure_writable(skb, iph->len)) goto drop; /* mangle the packet */ if (pp->snat_handler && !SNAT_CALL(pp->snat_handler, skb, pp, cp, iph)) goto drop; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ipv6_hdr(skb)->saddr = cp->vaddr.in6; else #endif { ip_hdr(skb)->saddr = cp->vaddr.ip; ip_send_check(ip_hdr(skb)); } /* * nf_iterate does not expect change in the skb->dst->dev. * It looks like it is not fatal to enable this code for hooks * where our handlers are at the end of the chain list and * when all next handlers use skb->dst->dev and not outdev. * It will definitely route properly the inout NAT traffic * when multiple paths are used. */ /* For policy routing, packets originating from this * machine itself may be routed differently to packets * passing through. We want this packet to be routed as * if it came from this machine itself. So re-compute * the routing information. */ if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto drop; IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT"); after_nat: ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); LeaveFunction(11); return NF_ACCEPT; drop: ip_vs_conn_put(cp); kfree_skb(skb); LeaveFunction(11); return NF_STOLEN; } /* * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) { struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; struct sock *sk; EnterFunction(11); /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; sk = skb_to_full_sk(skb); /* Bad... Do not break raw sockets */ if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) return NF_ACCEPT; } if (unlikely(!skb_dst(skb))) return NF_ACCEPT; if (!ipvs->enable) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_out_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) return verdict; } } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) return NF_ACCEPT; pp = pd->pp; /* reassemble IP fragments */ #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET) #endif if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; ip_vs_fill_iph_skb(AF_INET, skb, false, &iph); } /* * Check if the packet belongs to an existing entry */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); /* Check for real-server-started requests */ if (atomic_read(&ipvs->conn_out_counter)) { /* Currently only for UDP: * connection oriented protocols typically use * ephemeral ports for outgoing connections, so * related incoming responses would not match any VS */ if (pp->protocol == IPPROTO_UDP) { cp = __ip_vs_rs_conn_out(hooknum, ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); } } if (sysctl_nat_icmp_send(ipvs) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || pp->protocol == IPPROTO_SCTP)) { __be16 _ports[2], *pptr; pptr = frag_safe_skb_hp(skb, iph.len, sizeof(_ports), _ports); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ if (ip_vs_has_real_service(ipvs, af, iph.protocol, &iph.saddr, pptr[0])) { /* * Notify the real server: there is no * existing entry if it is not RST * packet or not TCP packet. */ if ((iph.protocol != IPPROTO_TCP && iph.protocol != IPPROTO_SCTP) || ((iph.protocol == IPPROTO_TCP && !is_tcp_reset(skb, iph.len)) || (iph.protocol == IPPROTO_SCTP && !is_sctp_abort(skb, iph.len)))) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (!skb->dev) skb->dev = ipvs->net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); return NF_DROP; } } } IP_VS_DBG_PKT(12, af, pp, skb, iph.off, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; } /* * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, * used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); } /* * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_local_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); } #ifdef CONFIG_IP_VS_IPV6 /* * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, * used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); } /* * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_local_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); } #endif static unsigned int ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; if (!iph->fragoffs) { /* No (second) fragments need to enter here, as nf_defrag_ipv6 * replayed fragment zero will already have created the cp */ /* Schedule and create new connection entry into cpp */ if (!pp->conn_schedule(ipvs, af, skb, pd, verdict, cpp, iph)) return 0; } if (unlikely(!*cpp)) { /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, iph->off, "ip_vs_in: packet continues traversal as normal"); /* Fragment couldn't be mapped to a conn entry */ if (iph->fragoffs) IP_VS_DBG_PKT(7, af, pp, skb, iph->off, "unhandled fragment"); *verdict = NF_ACCEPT; return 0; } return 1; } /* Check the UDP tunnel and return its header length */ static int ipvs_udp_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, unsigned int offset, __u16 af, const union nf_inet_addr *daddr, __u8 *proto) { struct udphdr _udph, *udph; struct ip_vs_dest *dest; udph = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (!udph) goto unk; offset += sizeof(struct udphdr); dest = ip_vs_find_tunnel(ipvs, af, daddr, udph->dest); if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { struct guehdr _gueh, *gueh; gueh = skb_header_pointer(skb, offset, sizeof(_gueh), &_gueh); if (!gueh) goto unk; if (gueh->control != 0 || gueh->version != 0) goto unk; /* Later we can support also IPPROTO_IPV6 */ if (gueh->proto_ctype != IPPROTO_IPIP) goto unk; *proto = gueh->proto_ctype; return sizeof(struct udphdr) + sizeof(struct guehdr) + (gueh->hlen << 2); } unk: return 0; } /* Check the GRE tunnel and return its header length */ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, unsigned int offset, __u16 af, const union nf_inet_addr *daddr, __u8 *proto) { struct gre_base_hdr _greh, *greh; struct ip_vs_dest *dest; greh = skb_header_pointer(skb, offset, sizeof(_greh), &_greh); if (!greh) goto unk; dest = ip_vs_find_tunnel(ipvs, af, daddr, 0); if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { __be16 type; /* Only support version 0 and C (csum) */ if ((greh->flags & ~GRE_CSUM) != 0) goto unk; type = greh->protocol; /* Later we can support also IPPROTO_IPV6 */ if (type != htons(ETH_P_IP)) goto unk; *proto = IPPROTO_IPIP; return gre_calc_hlen(gre_flags_to_tnl_flags(greh->flags)); } unk: return 0; } /* * Handle ICMP messages in the outside-to-inside direction (incoming). * Find any that might be relevant, check against existing connections, * forward to the right destination host if relevant. * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, offset2, ihl, verdict; bool tunnel, new_cp = false; union nf_inet_addr *raddr; char *outer_proto = "IPIP"; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } iph = ip_hdr(skb); offset = ihl = iph->ihl * 4; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), &iph->saddr, &iph->daddr); /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if ((ic->type != ICMP_DEST_UNREACH) && (ic->type != ICMP_SOURCE_QUENCH) && (ic->type != ICMP_TIME_EXCEEDED)) { *related = 0; return NF_ACCEPT; } /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ raddr = (union nf_inet_addr *)&cih->daddr; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; if (cih->protocol == IPPROTO_IPIP) { struct ip_vs_dest *dest; if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; /* Error for our IPIP must arrive at LOCAL_IN */ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) return NF_ACCEPT; dest = ip_vs_find_tunnel(ipvs, AF_INET, raddr, 0); /* Only for known tunnel */ if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; offset += cih->ihl * 4; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ cih->protocol == IPPROTO_GRE) && /* Can be GRE encap */ /* Error for our tunnel must arrive at LOCAL_IN */ (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { __u8 iproto; int ulen; /* Non-first fragment has no UDP/GRE header */ if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; offset2 = offset + cih->ihl * 4; if (cih->protocol == IPPROTO_UDP) { ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); outer_proto = "UDP"; } else { ulen = ipvs_gre_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); outer_proto = "GRE"; } if (ulen > 0) { /* Skip IP and UDP/GRE tunnel headers */ offset = offset2 + ulen; /* Now we should be at the original IP header */ cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih && cih->version == 4 && cih->ihl >= 5 && iproto == IPPROTO_IPIP) tunnel = true; else return NF_ACCEPT; } } pd = ip_vs_proto_data_get(ipvs, cih->protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); offset2 = offset; ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); offset = ciph.len; /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, AF_INET, skb, &ciph); if (!cp) { int v; if (tunnel || !sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } verdict = NF_DROP; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { /* Failed checksum! */ IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n", &iph->saddr); goto out; } if (tunnel) { __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { struct ip_vs_dest *dest = cp->dest; u32 mtu = ntohs(ic->un.frag.mtu); __be16 frag_off = cih->frag_off; /* Strip outer IP and ICMP, go to IPIP/UDP/GRE header */ if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL) goto ignore_tunnel; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for %s %pI4->%pI4: mtu=%u\n", outer_proto, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); ipv4_update_pmtu(skb, ipvs->net, mtu, 0, 0); /* Client uses PMTUD? */ if (!(frag_off & htons(IP_DF))) goto ignore_tunnel; /* Prefer the resulting PMTU */ if (dest) { struct ip_vs_dest_dst *dest_dst; dest_dst = rcu_dereference(dest->dest_dst); if (dest_dst) mtu = dst_mtu(dest_dst->dst_cache); } if (mtu > 68 + sizeof(struct iphdr)) mtu -= sizeof(struct iphdr); info = htonl(mtu); } /* Strip outer IP, ICMP and IPIP/UDP/GRE, go to IP header of * original request. */ if (pskb_pull(skb, offset2) == NULL) goto ignore_tunnel; skb_reset_network_header(skb); IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, type, code, ntohl(info)); icmp_send(skb, type, code, info); /* ICMP can be shorter but anyways, account it */ ip_vs_out_stats(cp, skb); ignore_tunnel: consume_skb(skb); verdict = NF_STOLEN; goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol || IPPROTO_SCTP == cih->protocol) offset += 2 * sizeof(__u16); verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); out: if (likely(!new_cp)) __ip_vs_conn_put(cp); else ip_vs_conn_put(cp); return verdict; } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *iph) { struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, verdict; bool new_cp = false; *related = 1; ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } /* Fragment header that is before ICMP header tells us that: * it's not an error message since they can't be fragmented. */ if (iph->flags & IP6_FH_F_FRAG) return NF_DROP; IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n", ic->icmp6_type, ntohs(icmpv6_id(ic)), &iph->saddr, &iph->daddr); offset = iph->len + sizeof(_icmph); if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, offset, true, &ciph)) return NF_ACCEPT; pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; /* Cannot handle fragmented embedded protocol */ if (ciph.fragoffs) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, "Checking incoming ICMPv6 for"); /* The embedded headers contain source and dest in reverse order * if not from localhost */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, AF_INET6, skb, &ciph); if (!cp) { int v; if (!sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET6, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } /* VS/TUN, VS/DR and LOCALNODE just let it go */ if ((hooknum == NF_INET_LOCAL_OUT) && (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) { verdict = NF_ACCEPT; goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); /* Need to mangle contained IPv6 header in ICMPv6 packet */ offset = ciph.len; if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || IPPROTO_SCTP == ciph.protocol) offset += 2 * sizeof(__u16); /* Also mangle ports */ verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph); out: if (likely(!new_cp)) __ip_vs_conn_put(cp); else ip_vs_conn_put(cp); return verdict; } #endif /* * Check if it's for virtual services, look it up, * and send it on its way... */ static unsigned int ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) { struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; struct sock *sk; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; /* * Big tappo: * - remote client: only PACKET_HOST * - route: used for struct net when skb->dev is unset */ if (unlikely((skb->pkt_type != PACKET_HOST && hooknum != NF_INET_LOCAL_OUT) || !skb_dst(skb))) { ip_vs_fill_iph_skb(af, skb, false, &iph); IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s" " ignored in hook %u\n", skb->pkt_type, iph.protocol, IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); /* Bad... Do not break raw sockets */ sk = skb_to_full_sk(skb); if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) return NF_ACCEPT; } #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_in_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) return verdict; } } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_in_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } /* Protocol supported? */ pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) { /* The only way we'll see this packet again is if it's * encapsulated, so mark it with ipvs_property=1 so we * skip it if we're ignoring tunneled packets */ if (sysctl_ignore_tunneled(ipvs)) skb->ipvs_property = 1; return NF_ACCEPT; } pp = pd->pp; /* * Check if the packet belongs to an existing connection entry */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, af, skb, &iph); if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); } else if (conn_reuse_mode && is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; } else { /* Do not reschedule controlling connection * that uses conntrack while it is still * referenced by controlled connection(s). */ resched = !old_ct; } } if (resched) { if (!old_ct) cp->flags &= ~IP_VS_CONN_F_NFCT; if (!atomic_read(&cp->n_control)) ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); if (old_ct) return NF_DROP; cp = NULL; } } /* Check the server status */ if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ if (sysctl_expire_nodest_conn(ipvs)) { bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!old_ct) cp->flags &= ~IP_VS_CONN_F_NFCT; ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); if (old_ct) return NF_DROP; cp = NULL; } else { __ip_vs_conn_put(cp); return NF_DROP; } } if (unlikely(!cp)) { int v; if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph)) return v; } IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); ip_vs_in_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp, &iph); /* do not touch skb anymore */ else { IP_VS_DBG_RL("warning: packet_xmit is null"); ret = NF_ACCEPT; } /* Increase its packet counter and check if it is needed * to be synchronized * * Sync connection if it is about to close to * encorage the standby servers to update the connections timeout * * For ONE_PKT let ip_vs_sync_conn() do the filter work. */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) pkts = sysctl_sync_threshold(ipvs); else pkts = atomic_inc_return(&cp->in_pkts); if (ipvs->sync_state & IP_VS_STATE_MASTER) ip_vs_sync_conn(ipvs, cp, pkts); else if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control) /* increment is done inside ip_vs_sync_conn too */ atomic_inc(&cp->control->in_pkts); ip_vs_conn_put(cp); return ret; } /* * AF_INET handler in NF_INET_LOCAL_IN chain * Schedule and forward packets from remote clients */ static unsigned int ip_vs_remote_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); } /* * AF_INET handler in NF_INET_LOCAL_OUT chain * Schedule and forward packets from local clients */ static unsigned int ip_vs_local_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); } #ifdef CONFIG_IP_VS_IPV6 /* * AF_INET6 handler in NF_INET_LOCAL_IN chain * Schedule and forward packets from remote clients */ static unsigned int ip_vs_remote_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); } /* * AF_INET6 handler in NF_INET_LOCAL_OUT chain * Schedule and forward packets from local clients */ static unsigned int ip_vs_local_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); } #endif /* * It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP * related packets destined for 0.0.0.0/0. * When fwmark-based virtual service is used, such as transparent * cache cluster, TCP packets can be marked and routed to ip_vs_in, * but ICMP destined for 0.0.0.0/0 cannot not be easily marked and * sent to ip_vs_in_icmp. So, catch them at the NF_INET_FORWARD chain * and send them to ip_vs_in_icmp. */ static unsigned int ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int r; struct netns_ipvs *ipvs = net_ipvs(state->net); if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp(ipvs, skb, &r, state->hook); } #ifdef CONFIG_IP_VS_IPV6 static unsigned int ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int r; struct netns_ipvs *ipvs = net_ipvs(state->net); struct ip_vs_iphdr iphdr; ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); if (iphdr.protocol != IPPROTO_ICMPV6) return NF_ACCEPT; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); } #endif static const struct nf_hook_ops ip_vs_ops4[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { .hook = ip_vs_remote_request4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_local_reply4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { .hook = ip_vs_local_request4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 100, }, }; #ifdef CONFIG_IP_VS_IPV6 static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { .hook = ip_vs_remote_request6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_local_reply6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { .hook = ip_vs_local_request6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp_v6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 100, }, }; #endif int ip_vs_register_hooks(struct netns_ipvs *ipvs, unsigned int af) { const struct nf_hook_ops *ops; unsigned int count; unsigned int afmask; int ret = 0; if (af == AF_INET6) { #ifdef CONFIG_IP_VS_IPV6 ops = ip_vs_ops6; count = ARRAY_SIZE(ip_vs_ops6); afmask = 2; #else return -EINVAL; #endif } else { ops = ip_vs_ops4; count = ARRAY_SIZE(ip_vs_ops4); afmask = 1; } if (!(ipvs->hooks_afmask & afmask)) { ret = nf_register_net_hooks(ipvs->net, ops, count); if (ret >= 0) ipvs->hooks_afmask |= afmask; } return ret; } void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af) { const struct nf_hook_ops *ops; unsigned int count; unsigned int afmask; if (af == AF_INET6) { #ifdef CONFIG_IP_VS_IPV6 ops = ip_vs_ops6; count = ARRAY_SIZE(ip_vs_ops6); afmask = 2; #else return; #endif } else { ops = ip_vs_ops4; count = ARRAY_SIZE(ip_vs_ops4); afmask = 1; } if (ipvs->hooks_afmask & afmask) { nf_unregister_net_hooks(ipvs->net, ops, count); ipvs->hooks_afmask &= ~afmask; } } /* * Initialize IP Virtual Server netns mem. */ static int __net_init __ip_vs_init(struct net *net) { struct netns_ipvs *ipvs; ipvs = net_generic(net, ip_vs_net_id); if (ipvs == NULL) return -ENOMEM; /* Hold the beast until a service is registered */ ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; if (ip_vs_estimator_net_init(ipvs) < 0) goto estimator_fail; if (ip_vs_control_net_init(ipvs) < 0) goto control_fail; if (ip_vs_protocol_net_init(ipvs) < 0) goto protocol_fail; if (ip_vs_app_net_init(ipvs) < 0) goto app_fail; if (ip_vs_conn_net_init(ipvs) < 0) goto conn_fail; if (ip_vs_sync_net_init(ipvs) < 0) goto sync_fail; return 0; /* * Error handling */ sync_fail: ip_vs_conn_net_cleanup(ipvs); conn_fail: ip_vs_app_net_cleanup(ipvs); app_fail: ip_vs_protocol_net_cleanup(ipvs); protocol_fail: ip_vs_control_net_cleanup(ipvs); control_fail: ip_vs_estimator_net_cleanup(ipvs); estimator_fail: net->ipvs = NULL; return -ENOMEM; } static void __net_exit __ip_vs_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; ip_vs_service_nets_cleanup(net_list); /* ip_vs_flush() with locks */ list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_conn_net_cleanup(ipvs); ip_vs_app_net_cleanup(ipvs); ip_vs_protocol_net_cleanup(ipvs); ip_vs_control_net_cleanup(ipvs); ip_vs_estimator_net_cleanup(ipvs); IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen); net->ipvs = NULL; } } static void __net_exit __ip_vs_dev_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; EnterFunction(2); list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_unregister_hooks(ipvs, AF_INET); ip_vs_unregister_hooks(ipvs, AF_INET6); ipvs->enable = 0; /* Disable packet reception */ smp_wmb(); ip_vs_sync_net_cleanup(ipvs); } LeaveFunction(2); } static struct pernet_operations ipvs_core_ops = { .init = __ip_vs_init, .exit_batch = __ip_vs_cleanup_batch, .id = &ip_vs_net_id, .size = sizeof(struct netns_ipvs), }; static struct pernet_operations ipvs_core_dev_ops = { .exit_batch = __ip_vs_dev_cleanup_batch, }; /* * Initialize IP Virtual Server */ static int __init ip_vs_init(void) { int ret; ret = ip_vs_control_init(); if (ret < 0) { pr_err("can't setup control.\n"); goto exit; } ip_vs_protocol_init(); ret = ip_vs_conn_init(); if (ret < 0) { pr_err("can't setup connection table.\n"); goto cleanup_protocol; } ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ if (ret < 0) goto cleanup_conn; ret = register_pernet_device(&ipvs_core_dev_ops); if (ret < 0) goto cleanup_sub; ret = ip_vs_register_nl_ioctl(); if (ret < 0) { pr_err("can't register netlink/ioctl.\n"); goto cleanup_dev; } pr_info("ipvs loaded.\n"); return ret; cleanup_dev: unregister_pernet_device(&ipvs_core_dev_ops); cleanup_sub: unregister_pernet_subsys(&ipvs_core_ops); cleanup_conn: ip_vs_conn_cleanup(); cleanup_protocol: ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); exit: return ret; } static void __exit ip_vs_cleanup(void) { ip_vs_unregister_nl_ioctl(); unregister_pernet_device(&ipvs_core_dev_ops); unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_conn_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); pr_info("ipvs unloaded.\n"); } module_init(ip_vs_init); module_exit(ip_vs_cleanup); MODULE_LICENSE("GPL"); |
| 76 176 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2005 Intel Corporation. All rights reserved. */ #ifndef IB_ADDR_H #define IB_ADDR_H #include <linux/ethtool.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/socket.h> #include <linux/if_vlan.h> #include <net/ipv6.h> #include <net/if_inet6.h> #include <net/ip.h> #include <rdma/ib_verbs.h> #include <rdma/ib_pack.h> #include <net/net_namespace.h> /** * struct rdma_dev_addr - Contains resolved RDMA hardware addresses * @src_dev_addr: Source MAC address. * @dst_dev_addr: Destination MAC address. * @broadcast: Broadcast address of the device. * @dev_type: The interface hardware type of the device. * @bound_dev_if: An optional device interface index. * @transport: The transport type used. * @net: Network namespace containing the bound_dev_if net_dev. * @sgid_attr: GID attribute to use for identified SGID */ struct rdma_dev_addr { unsigned char src_dev_addr[MAX_ADDR_LEN]; unsigned char dst_dev_addr[MAX_ADDR_LEN]; unsigned char broadcast[MAX_ADDR_LEN]; unsigned short dev_type; int bound_dev_if; enum rdma_transport_type transport; struct net *net; const struct ib_gid_attr *sgid_attr; enum rdma_network_type network; int hoplimit; }; /** * rdma_translate_ip - Translate a local IP address to an RDMA hardware * address. * * The dev_addr->net field must be initialized. */ int rdma_translate_ip(const struct sockaddr *addr, struct rdma_dev_addr *dev_addr); /** * rdma_resolve_ip - Resolve source and destination IP addresses to * RDMA hardware addresses. * @src_addr: An optional source address to use in the resolution. If a * source address is not provided, a usable address will be returned via * the callback. * @dst_addr: The destination address to resolve. * @addr: A reference to a data location that will receive the resolved * addresses. The data location must remain valid until the callback has * been invoked. The net field of the addr struct must be valid. * @timeout_ms: Amount of time to wait for the address resolution to complete. * @callback: Call invoked once address resolution has completed, timed out, * or been canceled. A status of 0 indicates success. * @resolve_by_gid_attr: Resolve the ip based on the GID attribute from * rdma_dev_addr. * @context: User-specified context associated with the call. */ int rdma_resolve_ip(struct sockaddr *src_addr, const struct sockaddr *dst_addr, struct rdma_dev_addr *addr, unsigned long timeout_ms, void (*callback)(int status, struct sockaddr *src_addr, struct rdma_dev_addr *addr, void *context), bool resolve_by_gid_attr, void *context); void rdma_addr_cancel(struct rdma_dev_addr *addr); int rdma_addr_size(const struct sockaddr *addr); int rdma_addr_size_in6(struct sockaddr_in6 *addr); int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr); static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr) { return ((u16)dev_addr->broadcast[8] << 8) | (u16)dev_addr->broadcast[9]; } static inline void ib_addr_set_pkey(struct rdma_dev_addr *dev_addr, u16 pkey) { dev_addr->broadcast[8] = pkey >> 8; dev_addr->broadcast[9] = (unsigned char) pkey; } static inline void ib_addr_get_mgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->broadcast + 4, sizeof *gid); } static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr) { return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0; } static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev) { return is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 0xffff; } static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid) { switch (addr->sa_family) { case AF_INET: ipv6_addr_set_v4mapped(((struct sockaddr_in *) addr)->sin_addr.s_addr, (struct in6_addr *)gid); break; case AF_INET6: *(struct in6_addr *)&gid->raw = ((struct sockaddr_in6 *)addr)->sin6_addr; break; default: return -EINVAL; } return 0; } /* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */ static inline void rdma_gid2ip(struct sockaddr *out, const union ib_gid *gid) { if (ipv6_addr_v4mapped((struct in6_addr *)gid)) { struct sockaddr_in *out_in = (struct sockaddr_in *)out; memset(out_in, 0, sizeof(*out_in)); out_in->sin_family = AF_INET; memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4); } else { struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out; memset(out_in, 0, sizeof(*out_in)); out_in->sin6_family = AF_INET6; memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16); } } /* * rdma_get/set_sgid/dgid() APIs are applicable to IB, and iWarp. * They are not applicable to RoCE. * RoCE GIDs are derived from the IP addresses. */ static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(*gid)); } static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); } static inline void rdma_addr_get_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof *gid); } static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); } static inline enum ib_mtu iboe_get_mtu(int mtu) { /* * Reduce IB headers from effective IBoE MTU. */ mtu = mtu - (IB_GRH_BYTES + IB_UDP_BYTES + IB_BTH_BYTES + IB_EXT_XRC_BYTES + IB_EXT_ATOMICETH_BYTES + IB_ICRC_BYTES); if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096)) return IB_MTU_4096; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_2048)) return IB_MTU_2048; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_1024)) return IB_MTU_1024; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_512)) return IB_MTU_512; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_256)) return IB_MTU_256; else return 0; } static inline int rdma_link_local_addr(struct in6_addr *addr) { if (addr->s6_addr32[0] == htonl(0xfe800000) && addr->s6_addr32[1] == 0) return 1; return 0; } static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac) { memcpy(mac, &addr->s6_addr[8], 3); memcpy(mac + 3, &addr->s6_addr[13], 3); mac[0] ^= 2; } static inline int rdma_is_multicast_addr(struct in6_addr *addr) { __be32 ipv4_addr; if (addr->s6_addr[0] == 0xff) return 1; ipv4_addr = addr->s6_addr32[3]; return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr)); } static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac) { int i; mac[0] = 0x33; mac[1] = 0x33; for (i = 2; i < 6; ++i) mac[i] = addr->s6_addr[i + 10]; } static inline u16 rdma_get_vlan_id(union ib_gid *dgid) { u16 vid; vid = dgid->raw[11] << 8 | dgid->raw[12]; return vid < 0x1000 ? vid : 0xffff; } static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev) { return is_vlan_dev(dev) ? vlan_dev_real_dev(dev) : NULL; } #endif /* IB_ADDR_H */ |
| 49 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * NFS exporting and validation. * * We maintain a list of clients, each of which has a list of * exports. To export an fs to a given client, you first have * to create the client entry with NFSCTL_ADDCLIENT, which * creates a client control block and adds it to the hash * table. Then, you call NFSCTL_EXPORT for each fs. * * * Copyright (C) 1995, 1996 Olaf Kirch, <okir@monad.swb.de> */ #include <linux/slab.h> #include <linux/namei.h> #include <linux/module.h> #include <linux/exportfs.h> #include <linux/sunrpc/svc_xprt.h> #include "nfsd.h" #include "nfsfh.h" #include "netns.h" #include "pnfs.h" #include "filecache.h" #include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_EXPORT /* * We have two caches. * One maps client+vfsmnt+dentry to export options - the export map * The other maps client+filehandle-fragment to export options. - the expkey map * * The export options are actually stored in the first map, and the * second map contains a reference to the entry in the first map. */ #define EXPKEY_HASHBITS 8 #define EXPKEY_HASHMAX (1 << EXPKEY_HASHBITS) #define EXPKEY_HASHMASK (EXPKEY_HASHMAX -1) static void expkey_put(struct kref *ref) { struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); if (test_bit(CACHE_VALID, &key->h.flags) && !test_bit(CACHE_NEGATIVE, &key->h.flags)) path_put(&key->ek_path); auth_domain_put(key->ek_client); kfree_rcu(key, ek_rcu); } static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_pipe_upcall(cd, h); } static void expkey_request(struct cache_detail *cd, struct cache_head *h, char **bpp, int *blen) { /* client fsidtype \xfsid */ struct svc_expkey *ek = container_of(h, struct svc_expkey, h); char type[5]; qword_add(bpp, blen, ek->ek_client->name); snprintf(type, 5, "%d", ek->ek_fsidtype); qword_add(bpp, blen, type); qword_addhex(bpp, blen, (char*)ek->ek_fsid, key_len(ek->ek_fsidtype)); (*bpp)[-1] = '\n'; } static struct svc_expkey *svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new, struct svc_expkey *old); static struct svc_expkey *svc_expkey_lookup(struct cache_detail *cd, struct svc_expkey *); static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) { /* client fsidtype fsid expiry [path] */ char *buf; int len; struct auth_domain *dom = NULL; int err; int fsidtype; char *ep; struct svc_expkey key; struct svc_expkey *ek = NULL; if (mesg[mlen - 1] != '\n') return -EINVAL; mesg[mlen-1] = 0; buf = kmalloc(PAGE_SIZE, GFP_KERNEL); err = -ENOMEM; if (!buf) goto out; err = -EINVAL; if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0) goto out; err = -ENOENT; dom = auth_domain_find(buf); if (!dom) goto out; dprintk("found domain %s\n", buf); err = -EINVAL; if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0) goto out; fsidtype = simple_strtoul(buf, &ep, 10); if (*ep) goto out; dprintk("found fsidtype %d\n", fsidtype); if (key_len(fsidtype)==0) /* invalid type */ goto out; if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0) goto out; dprintk("found fsid length %d\n", len); if (len != key_len(fsidtype)) goto out; /* OK, we seem to have a valid key */ key.h.flags = 0; key.h.expiry_time = get_expiry(&mesg); if (key.h.expiry_time == 0) goto out; key.ek_client = dom; key.ek_fsidtype = fsidtype; memcpy(key.ek_fsid, buf, len); ek = svc_expkey_lookup(cd, &key); err = -ENOMEM; if (!ek) goto out; /* now we want a pathname, or empty meaning NEGATIVE */ err = -EINVAL; len = qword_get(&mesg, buf, PAGE_SIZE); if (len < 0) goto out; dprintk("Path seems to be <%s>\n", buf); err = 0; if (len == 0) { set_bit(CACHE_NEGATIVE, &key.h.flags); ek = svc_expkey_update(cd, &key, ek); if (ek) trace_nfsd_expkey_update(ek, NULL); else err = -ENOMEM; } else { err = kern_path(buf, 0, &key.ek_path); if (err) goto out; dprintk("Found the path %s\n", buf); ek = svc_expkey_update(cd, &key, ek); if (ek) trace_nfsd_expkey_update(ek, buf); else err = -ENOMEM; path_put(&key.ek_path); } cache_flush(); out: if (ek) cache_put(&ek->h, cd); if (dom) auth_domain_put(dom); kfree(buf); return err; } static int expkey_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { struct svc_expkey *ek ; int i; if (h ==NULL) { seq_puts(m, "#domain fsidtype fsid [path]\n"); return 0; } ek = container_of(h, struct svc_expkey, h); seq_printf(m, "%s %d 0x", ek->ek_client->name, ek->ek_fsidtype); for (i=0; i < key_len(ek->ek_fsidtype)/4; i++) seq_printf(m, "%08x", ek->ek_fsid[i]); if (test_bit(CACHE_VALID, &h->flags) && !test_bit(CACHE_NEGATIVE, &h->flags)) { seq_printf(m, " "); seq_path(m, &ek->ek_path, "\\ \t\n"); } seq_printf(m, "\n"); return 0; } static inline int expkey_match (struct cache_head *a, struct cache_head *b) { struct svc_expkey *orig = container_of(a, struct svc_expkey, h); struct svc_expkey *new = container_of(b, struct svc_expkey, h); if (orig->ek_fsidtype != new->ek_fsidtype || orig->ek_client != new->ek_client || memcmp(orig->ek_fsid, new->ek_fsid, key_len(orig->ek_fsidtype)) != 0) return 0; return 1; } static inline void expkey_init(struct cache_head *cnew, struct cache_head *citem) { struct svc_expkey *new = container_of(cnew, struct svc_expkey, h); struct svc_expkey *item = container_of(citem, struct svc_expkey, h); kref_get(&item->ek_client->ref); new->ek_client = item->ek_client; new->ek_fsidtype = item->ek_fsidtype; memcpy(new->ek_fsid, item->ek_fsid, sizeof(new->ek_fsid)); } static inline void expkey_update(struct cache_head *cnew, struct cache_head *citem) { struct svc_expkey *new = container_of(cnew, struct svc_expkey, h); struct svc_expkey *item = container_of(citem, struct svc_expkey, h); new->ek_path = item->ek_path; path_get(&item->ek_path); } static struct cache_head *expkey_alloc(void) { struct svc_expkey *i = kmalloc(sizeof(*i), GFP_KERNEL); if (i) return &i->h; else return NULL; } static void expkey_flush(void) { /* * Take the nfsd_mutex here to ensure that the file cache is not * destroyed while we're in the middle of flushing. */ mutex_lock(&nfsd_mutex); nfsd_file_cache_purge(current->nsproxy->net_ns); mutex_unlock(&nfsd_mutex); } static const struct cache_detail svc_expkey_cache_template = { .owner = THIS_MODULE, .hash_size = EXPKEY_HASHMAX, .name = "nfsd.fh", .cache_put = expkey_put, .cache_upcall = expkey_upcall, .cache_request = expkey_request, .cache_parse = expkey_parse, .cache_show = expkey_show, .match = expkey_match, .init = expkey_init, .update = expkey_update, .alloc = expkey_alloc, .flush = expkey_flush, }; static int svc_expkey_hash(struct svc_expkey *item) { int hash = item->ek_fsidtype; char * cp = (char*)item->ek_fsid; int len = key_len(item->ek_fsidtype); hash ^= hash_mem(cp, len, EXPKEY_HASHBITS); hash ^= hash_ptr(item->ek_client, EXPKEY_HASHBITS); hash &= EXPKEY_HASHMASK; return hash; } static struct svc_expkey * svc_expkey_lookup(struct cache_detail *cd, struct svc_expkey *item) { struct cache_head *ch; int hash = svc_expkey_hash(item); ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash); if (ch) return container_of(ch, struct svc_expkey, h); else return NULL; } static struct svc_expkey * svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new, struct svc_expkey *old) { struct cache_head *ch; int hash = svc_expkey_hash(new); ch = sunrpc_cache_update(cd, &new->h, &old->h, hash); if (ch) return container_of(ch, struct svc_expkey, h); else return NULL; } #define EXPORT_HASHBITS 8 #define EXPORT_HASHMAX (1<< EXPORT_HASHBITS) static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc) { struct nfsd4_fs_location *locations = fsloc->locations; int i; if (!locations) return; for (i = 0; i < fsloc->locations_count; i++) { kfree(locations[i].path); kfree(locations[i].hosts); } kfree(locations); fsloc->locations = NULL; } static int export_stats_init(struct export_stats *stats) { stats->start_time = ktime_get_seconds(); return nfsd_percpu_counters_init(stats->counter, EXP_STATS_COUNTERS_NUM); } static void export_stats_reset(struct export_stats *stats) { if (stats) nfsd_percpu_counters_reset(stats->counter, EXP_STATS_COUNTERS_NUM); } static void export_stats_destroy(struct export_stats *stats) { if (stats) nfsd_percpu_counters_destroy(stats->counter, EXP_STATS_COUNTERS_NUM); } static void svc_export_put(struct kref *ref) { struct svc_export *exp = container_of(ref, struct svc_export, h.ref); path_put(&exp->ex_path); auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); export_stats_destroy(exp->ex_stats); kfree(exp->ex_stats); kfree(exp->ex_uuid); kfree_rcu(exp, ex_rcu); } static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_pipe_upcall(cd, h); } static void svc_export_request(struct cache_detail *cd, struct cache_head *h, char **bpp, int *blen) { /* client path */ struct svc_export *exp = container_of(h, struct svc_export, h); char *pth; qword_add(bpp, blen, exp->ex_client->name); pth = d_path(&exp->ex_path, *bpp, *blen); if (IS_ERR(pth)) { /* is this correct? */ (*bpp)[0] = '\n'; return; } qword_add(bpp, blen, pth); (*bpp)[-1] = '\n'; } static struct svc_export *svc_export_update(struct svc_export *new, struct svc_export *old); static struct svc_export *svc_export_lookup(struct svc_export *); static int check_export(struct path *path, int *flags, unsigned char *uuid) { struct inode *inode = d_inode(path->dentry); /* * We currently export only dirs, regular files, and (for v4 * pseudoroot) symlinks. */ if (!S_ISDIR(inode->i_mode) && !S_ISLNK(inode->i_mode) && !S_ISREG(inode->i_mode)) return -ENOTDIR; /* * Mountd should never pass down a writeable V4ROOT export, but, * just to make sure: */ if (*flags & NFSEXP_V4ROOT) *flags |= NFSEXP_READONLY; /* There are two requirements on a filesystem to be exportable. * 1: We must be able to identify the filesystem from a number. * either a device number (so FS_REQUIRES_DEV needed) * or an FSID number (so NFSEXP_FSID or ->uuid is needed). * 2: We must be able to find an inode from a filehandle. * This means that s_export_op must be set. * 3: We must not currently be on an idmapped mount. */ if (!(inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV) && !(*flags & NFSEXP_FSID) && uuid == NULL) { dprintk("exp_export: export of non-dev fs without fsid\n"); return -EINVAL; } if (!inode->i_sb->s_export_op || !inode->i_sb->s_export_op->fh_to_dentry) { dprintk("exp_export: export of invalid fs type.\n"); return -EINVAL; } if (is_idmapped_mnt(path->mnt)) { dprintk("exp_export: export of idmapped mounts not yet supported.\n"); return -EINVAL; } if (inode->i_sb->s_export_op->flags & EXPORT_OP_NOSUBTREECHK && !(*flags & NFSEXP_NOSUBTREECHECK)) { dprintk("%s: %s does not support subtree checking!\n", __func__, inode->i_sb->s_type->name); return -EINVAL; } return 0; } #ifdef CONFIG_NFSD_V4 static int fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc) { int len; int migrated, i, err; /* more than one fsloc */ if (fsloc->locations) return -EINVAL; /* listsize */ err = get_uint(mesg, &fsloc->locations_count); if (err) return err; if (fsloc->locations_count > MAX_FS_LOCATIONS) return -EINVAL; if (fsloc->locations_count == 0) return 0; fsloc->locations = kcalloc(fsloc->locations_count, sizeof(struct nfsd4_fs_location), GFP_KERNEL); if (!fsloc->locations) return -ENOMEM; for (i=0; i < fsloc->locations_count; i++) { /* colon separated host list */ err = -EINVAL; len = qword_get(mesg, buf, PAGE_SIZE); if (len <= 0) goto out_free_all; err = -ENOMEM; fsloc->locations[i].hosts = kstrdup(buf, GFP_KERNEL); if (!fsloc->locations[i].hosts) goto out_free_all; err = -EINVAL; /* slash separated path component list */ len = qword_get(mesg, buf, PAGE_SIZE); if (len <= 0) goto out_free_all; err = -ENOMEM; fsloc->locations[i].path = kstrdup(buf, GFP_KERNEL); if (!fsloc->locations[i].path) goto out_free_all; } /* migrated */ err = get_int(mesg, &migrated); if (err) goto out_free_all; err = -EINVAL; if (migrated < 0 || migrated > 1) goto out_free_all; fsloc->migrated = migrated; return 0; out_free_all: nfsd4_fslocs_free(fsloc); return err; } static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { struct exp_flavor_info *f; u32 listsize; int err; /* more than one secinfo */ if (exp->ex_nflavors) return -EINVAL; err = get_uint(mesg, &listsize); if (err) return err; if (listsize > MAX_SECINFO_LIST) return -EINVAL; for (f = exp->ex_flavors; f < exp->ex_flavors + listsize; f++) { err = get_uint(mesg, &f->pseudoflavor); if (err) return err; /* * XXX: It would be nice to also check whether this * pseudoflavor is supported, so we can discover the * problem at export time instead of when a client fails * to authenticate. */ err = get_uint(mesg, &f->flags); if (err) return err; /* Only some flags are allowed to differ between flavors: */ if (~NFSEXP_SECINFO_FLAGS & (f->flags ^ exp->ex_flags)) return -EINVAL; } exp->ex_nflavors = listsize; return 0; } #else /* CONFIG_NFSD_V4 */ static inline int fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc){return 0;} static inline int secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; } #endif static inline int nfsd_uuid_parse(char **mesg, char *buf, unsigned char **puuid) { int len; /* more than one uuid */ if (*puuid) return -EINVAL; /* expect a 16 byte uuid encoded as \xXXXX... */ len = qword_get(mesg, buf, PAGE_SIZE); if (len != EX_UUID_LEN) return -EINVAL; *puuid = kmemdup(buf, EX_UUID_LEN, GFP_KERNEL); if (*puuid == NULL) return -ENOMEM; return 0; } static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) { /* client path expiry [flags anonuid anongid fsid] */ char *buf; int len; int err; struct auth_domain *dom = NULL; struct svc_export exp = {}, *expp; int an_int; if (mesg[mlen-1] != '\n') return -EINVAL; mesg[mlen-1] = 0; buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!buf) return -ENOMEM; /* client */ err = -EINVAL; len = qword_get(&mesg, buf, PAGE_SIZE); if (len <= 0) goto out; err = -ENOENT; dom = auth_domain_find(buf); if (!dom) goto out; /* path */ err = -EINVAL; if ((len = qword_get(&mesg, buf, PAGE_SIZE)) <= 0) goto out1; err = kern_path(buf, 0, &exp.ex_path); if (err) goto out1; exp.ex_client = dom; exp.cd = cd; exp.ex_devid_map = NULL; /* expiry */ err = -EINVAL; exp.h.expiry_time = get_expiry(&mesg); if (exp.h.expiry_time == 0) goto out3; /* flags */ err = get_int(&mesg, &an_int); if (err == -ENOENT) { err = 0; set_bit(CACHE_NEGATIVE, &exp.h.flags); } else { if (err || an_int < 0) goto out3; exp.ex_flags= an_int; /* anon uid */ err = get_int(&mesg, &an_int); if (err) goto out3; exp.ex_anon_uid= make_kuid(current_user_ns(), an_int); /* anon gid */ err = get_int(&mesg, &an_int); if (err) goto out3; exp.ex_anon_gid= make_kgid(current_user_ns(), an_int); /* fsid */ err = get_int(&mesg, &an_int); if (err) goto out3; exp.ex_fsid = an_int; while ((len = qword_get(&mesg, buf, PAGE_SIZE)) > 0) { if (strcmp(buf, "fsloc") == 0) err = fsloc_parse(&mesg, buf, &exp.ex_fslocs); else if (strcmp(buf, "uuid") == 0) err = nfsd_uuid_parse(&mesg, buf, &exp.ex_uuid); else if (strcmp(buf, "secinfo") == 0) err = secinfo_parse(&mesg, buf, &exp); else /* quietly ignore unknown words and anything * following. Newer user-space can try to set * new values, then see what the result was. */ break; if (err) goto out4; } err = check_export(&exp.ex_path, &exp.ex_flags, exp.ex_uuid); if (err) goto out4; /* * No point caching this if it would immediately expire. * Also, this protects exportfs's dummy export from the * anon_uid/anon_gid checks: */ if (exp.h.expiry_time < seconds_since_boot()) goto out4; /* * For some reason exportfs has been passing down an * invalid (-1) uid & gid on the "dummy" export which it * uses to test export support. To make sure exportfs * sees errors from check_export we therefore need to * delay these checks till after check_export: */ err = -EINVAL; if (!uid_valid(exp.ex_anon_uid)) goto out4; if (!gid_valid(exp.ex_anon_gid)) goto out4; err = 0; nfsd4_setup_layout_type(&exp); } expp = svc_export_lookup(&exp); if (!expp) { err = -ENOMEM; goto out4; } expp = svc_export_update(&exp, expp); if (expp) { trace_nfsd_export_update(expp); cache_flush(); exp_put(expp); } else err = -ENOMEM; out4: nfsd4_fslocs_free(&exp.ex_fslocs); kfree(exp.ex_uuid); out3: path_put(&exp.ex_path); out1: auth_domain_put(dom); out: kfree(buf); return err; } static void exp_flags(struct seq_file *m, int flag, int fsid, kuid_t anonu, kgid_t anong, struct nfsd4_fs_locations *fslocs); static void show_secinfo(struct seq_file *m, struct svc_export *exp); static int is_export_stats_file(struct seq_file *m) { /* * The export_stats file uses the same ops as the exports file. * We use the file's name to determine the reported info per export. * There is no rename in nsfdfs, so d_name.name is stable. */ return !strcmp(m->file->f_path.dentry->d_name.name, "export_stats"); } static int svc_export_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { struct svc_export *exp; bool export_stats = is_export_stats_file(m); if (h == NULL) { if (export_stats) seq_puts(m, "#path domain start-time\n#\tstats\n"); else seq_puts(m, "#path domain(flags)\n"); return 0; } exp = container_of(h, struct svc_export, h); seq_path(m, &exp->ex_path, " \t\n\\"); seq_putc(m, '\t'); seq_escape(m, exp->ex_client->name, " \t\n\\"); if (export_stats) { struct percpu_counter *counter = exp->ex_stats->counter; seq_printf(m, "\t%lld\n", exp->ex_stats->start_time); seq_printf(m, "\tfh_stale: %lld\n", percpu_counter_sum_positive(&counter[EXP_STATS_FH_STALE])); seq_printf(m, "\tio_read: %lld\n", percpu_counter_sum_positive(&counter[EXP_STATS_IO_READ])); seq_printf(m, "\tio_write: %lld\n", percpu_counter_sum_positive(&counter[EXP_STATS_IO_WRITE])); seq_putc(m, '\n'); return 0; } seq_putc(m, '('); if (test_bit(CACHE_VALID, &h->flags) && !test_bit(CACHE_NEGATIVE, &h->flags)) { exp_flags(m, exp->ex_flags, exp->ex_fsid, exp->ex_anon_uid, exp->ex_anon_gid, &exp->ex_fslocs); if (exp->ex_uuid) { int i; seq_puts(m, ",uuid="); for (i = 0; i < EX_UUID_LEN; i++) { if ((i&3) == 0 && i) seq_putc(m, ':'); seq_printf(m, "%02x", exp->ex_uuid[i]); } } show_secinfo(m, exp); } seq_puts(m, ")\n"); return 0; } static int svc_export_match(struct cache_head *a, struct cache_head *b) { struct svc_export *orig = container_of(a, struct svc_export, h); struct svc_export *new = container_of(b, struct svc_export, h); return orig->ex_client == new->ex_client && path_equal(&orig->ex_path, &new->ex_path); } static void svc_export_init(struct cache_head *cnew, struct cache_head *citem) { struct svc_export *new = container_of(cnew, struct svc_export, h); struct svc_export *item = container_of(citem, struct svc_export, h); kref_get(&item->ex_client->ref); new->ex_client = item->ex_client; new->ex_path = item->ex_path; path_get(&item->ex_path); new->ex_fslocs.locations = NULL; new->ex_fslocs.locations_count = 0; new->ex_fslocs.migrated = 0; new->ex_layout_types = 0; new->ex_uuid = NULL; new->cd = item->cd; export_stats_reset(new->ex_stats); } static void export_update(struct cache_head *cnew, struct cache_head *citem) { struct svc_export *new = container_of(cnew, struct svc_export, h); struct svc_export *item = container_of(citem, struct svc_export, h); int i; new->ex_flags = item->ex_flags; new->ex_anon_uid = item->ex_anon_uid; new->ex_anon_gid = item->ex_anon_gid; new->ex_fsid = item->ex_fsid; new->ex_devid_map = item->ex_devid_map; item->ex_devid_map = NULL; new->ex_uuid = item->ex_uuid; item->ex_uuid = NULL; new->ex_fslocs.locations = item->ex_fslocs.locations; item->ex_fslocs.locations = NULL; new->ex_fslocs.locations_count = item->ex_fslocs.locations_count; item->ex_fslocs.locations_count = 0; new->ex_fslocs.migrated = item->ex_fslocs.migrated; item->ex_fslocs.migrated = 0; new->ex_layout_types = item->ex_layout_types; new->ex_nflavors = item->ex_nflavors; for (i = 0; i < MAX_SECINFO_LIST; i++) { new->ex_flavors[i] = item->ex_flavors[i]; } } static struct cache_head *svc_export_alloc(void) { struct svc_export *i = kmalloc(sizeof(*i), GFP_KERNEL); if (!i) return NULL; i->ex_stats = kmalloc(sizeof(*(i->ex_stats)), GFP_KERNEL); if (!i->ex_stats) { kfree(i); return NULL; } if (export_stats_init(i->ex_stats)) { kfree(i->ex_stats); kfree(i); return NULL; } return &i->h; } static const struct cache_detail svc_export_cache_template = { .owner = THIS_MODULE, .hash_size = EXPORT_HASHMAX, .name = "nfsd.export", .cache_put = svc_export_put, .cache_upcall = svc_export_upcall, .cache_request = svc_export_request, .cache_parse = svc_export_parse, .cache_show = svc_export_show, .match = svc_export_match, .init = svc_export_init, .update = export_update, .alloc = svc_export_alloc, }; static int svc_export_hash(struct svc_export *exp) { int hash; hash = hash_ptr(exp->ex_client, EXPORT_HASHBITS); hash ^= hash_ptr(exp->ex_path.dentry, EXPORT_HASHBITS); hash ^= hash_ptr(exp->ex_path.mnt, EXPORT_HASHBITS); return hash; } static struct svc_export * svc_export_lookup(struct svc_export *exp) { struct cache_head *ch; int hash = svc_export_hash(exp); ch = sunrpc_cache_lookup_rcu(exp->cd, &exp->h, hash); if (ch) return container_of(ch, struct svc_export, h); else return NULL; } static struct svc_export * svc_export_update(struct svc_export *new, struct svc_export *old) { struct cache_head *ch; int hash = svc_export_hash(old); ch = sunrpc_cache_update(old->cd, &new->h, &old->h, hash); if (ch) return container_of(ch, struct svc_export, h); else return NULL; } static struct svc_expkey * exp_find_key(struct cache_detail *cd, struct auth_domain *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp) { struct svc_expkey key, *ek; int err; if (!clp) return ERR_PTR(-ENOENT); key.ek_client = clp; key.ek_fsidtype = fsid_type; memcpy(key.ek_fsid, fsidv, key_len(fsid_type)); ek = svc_expkey_lookup(cd, &key); if (ek == NULL) return ERR_PTR(-ENOMEM); err = cache_check(cd, &ek->h, reqp); if (err) { trace_nfsd_exp_find_key(&key, err); return ERR_PTR(err); } return ek; } static struct svc_export * exp_get_by_name(struct cache_detail *cd, struct auth_domain *clp, const struct path *path, struct cache_req *reqp) { struct svc_export *exp, key; int err; if (!clp) return ERR_PTR(-ENOENT); key.ex_client = clp; key.ex_path = *path; key.cd = cd; exp = svc_export_lookup(&key); if (exp == NULL) return ERR_PTR(-ENOMEM); err = cache_check(cd, &exp->h, reqp); if (err) { trace_nfsd_exp_get_by_name(&key, err); return ERR_PTR(err); } return exp; } /* * Find the export entry for a given dentry. */ static struct svc_export * exp_parent(struct cache_detail *cd, struct auth_domain *clp, struct path *path) { struct dentry *saved = dget(path->dentry); struct svc_export *exp = exp_get_by_name(cd, clp, path, NULL); while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(path->dentry)) { struct dentry *parent = dget_parent(path->dentry); dput(path->dentry); path->dentry = parent; exp = exp_get_by_name(cd, clp, path, NULL); } dput(path->dentry); path->dentry = saved; return exp; } /* * Obtain the root fh on behalf of a client. * This could be done in user space, but I feel that it adds some safety * since its harder to fool a kernel module than a user space program. */ int exp_rootfh(struct net *net, struct auth_domain *clp, char *name, struct knfsd_fh *f, int maxsize) { struct svc_export *exp; struct path path; struct inode *inode; struct svc_fh fh; int err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct cache_detail *cd = nn->svc_export_cache; err = -EPERM; /* NB: we probably ought to check that it's NUL-terminated */ if (kern_path(name, 0, &path)) { printk("nfsd: exp_rootfh path not found %s", name); return err; } inode = d_inode(path.dentry); dprintk("nfsd: exp_rootfh(%s [%p] %s:%s/%ld)\n", name, path.dentry, clp->name, inode->i_sb->s_id, inode->i_ino); exp = exp_parent(cd, clp, &path); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto out; } /* * fh must be initialized before calling fh_compose */ fh_init(&fh, maxsize); if (fh_compose(&fh, exp, path.dentry, NULL)) err = -EINVAL; else err = 0; memcpy(f, &fh.fh_handle, sizeof(struct knfsd_fh)); fh_put(&fh); exp_put(exp); out: path_put(&path); return err; } static struct svc_export *exp_find(struct cache_detail *cd, struct auth_domain *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp) { struct svc_export *exp; struct nfsd_net *nn = net_generic(cd->net, nfsd_net_id); struct svc_expkey *ek = exp_find_key(nn->svc_expkey_cache, clp, fsid_type, fsidv, reqp); if (IS_ERR(ek)) return ERR_CAST(ek); exp = exp_get_by_name(cd, clp, &ek->ek_path, reqp); cache_put(&ek->h, nn->svc_expkey_cache); if (IS_ERR(exp)) return ERR_CAST(exp); return exp; } __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp) { struct exp_flavor_info *f; struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors; /* legacy gss-only clients are always OK: */ if (exp->ex_client == rqstp->rq_gssclient) return 0; /* ip-address based client; check sec= export option: */ for (f = exp->ex_flavors; f < end; f++) { if (f->pseudoflavor == rqstp->rq_cred.cr_flavor) return 0; } /* defaults in absence of sec= options: */ if (exp->ex_nflavors == 0) { if (rqstp->rq_cred.cr_flavor == RPC_AUTH_NULL || rqstp->rq_cred.cr_flavor == RPC_AUTH_UNIX) return 0; } /* If the compound op contains a spo_must_allowed op, * it will be sent with integrity/protection which * will have to be expressly allowed on mounts that * don't support it */ if (nfsd4_spo_must_allow(rqstp)) return 0; return rqstp->rq_vers < 4 ? nfserr_acces : nfserr_wrongsec; } /* * Uses rq_client and rq_gssclient to find an export; uses rq_client (an * auth_unix client) if it's available and has secinfo information; * otherwise, will try to use rq_gssclient. * * Called from functions that handle requests; functions that do work on * behalf of mountd are passed a single client name to use, and should * use exp_get_by_name() or exp_find(). */ struct svc_export * rqst_exp_get_by_name(struct svc_rqst *rqstp, struct path *path) { struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT); struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct cache_detail *cd = nn->svc_export_cache; if (rqstp->rq_client == NULL) goto gss; /* First try the auth_unix client: */ exp = exp_get_by_name(cd, rqstp->rq_client, path, &rqstp->rq_chandle); if (PTR_ERR(exp) == -ENOENT) goto gss; if (IS_ERR(exp)) return exp; /* If it has secinfo, assume there are no gss/... clients */ if (exp->ex_nflavors > 0) return exp; gss: /* Otherwise, try falling back on gss client */ if (rqstp->rq_gssclient == NULL) return exp; gssexp = exp_get_by_name(cd, rqstp->rq_gssclient, path, &rqstp->rq_chandle); if (PTR_ERR(gssexp) == -ENOENT) return exp; if (!IS_ERR(exp)) exp_put(exp); return gssexp; } struct svc_export * rqst_exp_find(struct svc_rqst *rqstp, int fsid_type, u32 *fsidv) { struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT); struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct cache_detail *cd = nn->svc_export_cache; if (rqstp->rq_client == NULL) goto gss; /* First try the auth_unix client: */ exp = exp_find(cd, rqstp->rq_client, fsid_type, fsidv, &rqstp->rq_chandle); if (PTR_ERR(exp) == -ENOENT) goto gss; if (IS_ERR(exp)) return exp; /* If it has secinfo, assume there are no gss/... clients */ if (exp->ex_nflavors > 0) return exp; gss: /* Otherwise, try falling back on gss client */ if (rqstp->rq_gssclient == NULL) return exp; gssexp = exp_find(cd, rqstp->rq_gssclient, fsid_type, fsidv, &rqstp->rq_chandle); if (PTR_ERR(gssexp) == -ENOENT) return exp; if (!IS_ERR(exp)) exp_put(exp); return gssexp; } struct svc_export * rqst_exp_parent(struct svc_rqst *rqstp, struct path *path) { struct dentry *saved = dget(path->dentry); struct svc_export *exp = rqst_exp_get_by_name(rqstp, path); while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(path->dentry)) { struct dentry *parent = dget_parent(path->dentry); dput(path->dentry); path->dentry = parent; exp = rqst_exp_get_by_name(rqstp, path); } dput(path->dentry); path->dentry = saved; return exp; } struct svc_export *rqst_find_fsidzero_export(struct svc_rqst *rqstp) { u32 fsidv[2]; mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL); return rqst_exp_find(rqstp, FSID_NUM, fsidv); } /* * Called when we need the filehandle for the root of the pseudofs, * for a given NFSv4 client. The root is defined to be the * export point with fsid==0 */ __be32 exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp) { struct svc_export *exp; __be32 rv; exp = rqst_find_fsidzero_export(rqstp); if (IS_ERR(exp)) return nfserrno(PTR_ERR(exp)); rv = fh_compose(fhp, exp, exp->ex_path.dentry, NULL); exp_put(exp); return rv; } static struct flags { int flag; char *name[2]; } expflags[] = { { NFSEXP_READONLY, {"ro", "rw"}}, { NFSEXP_INSECURE_PORT, {"insecure", ""}}, { NFSEXP_ROOTSQUASH, {"root_squash", "no_root_squash"}}, { NFSEXP_ALLSQUASH, {"all_squash", ""}}, { NFSEXP_ASYNC, {"async", "sync"}}, { NFSEXP_GATHERED_WRITES, {"wdelay", "no_wdelay"}}, { NFSEXP_NOREADDIRPLUS, {"nordirplus", ""}}, { NFSEXP_NOHIDE, {"nohide", ""}}, { NFSEXP_CROSSMOUNT, {"crossmnt", ""}}, { NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}}, { NFSEXP_NOAUTHNLM, {"insecure_locks", ""}}, { NFSEXP_V4ROOT, {"v4root", ""}}, { NFSEXP_PNFS, {"pnfs", ""}}, { NFSEXP_SECURITY_LABEL, {"security_label", ""}}, { 0, {"", ""}} }; static void show_expflags(struct seq_file *m, int flags, int mask) { struct flags *flg; int state, first = 0; for (flg = expflags; flg->flag; flg++) { if (flg->flag & ~mask) continue; state = (flg->flag & flags) ? 0 : 1; if (*flg->name[state]) seq_printf(m, "%s%s", first++?",":"", flg->name[state]); } } static void show_secinfo_flags(struct seq_file *m, int flags) { seq_printf(m, ","); show_expflags(m, flags, NFSEXP_SECINFO_FLAGS); } static bool secinfo_flags_equal(int f, int g) { f &= NFSEXP_SECINFO_FLAGS; g &= NFSEXP_SECINFO_FLAGS; return f == g; } static int show_secinfo_run(struct seq_file *m, struct exp_flavor_info **fp, struct exp_flavor_info *end) { int flags; flags = (*fp)->flags; seq_printf(m, ",sec=%d", (*fp)->pseudoflavor); (*fp)++; while (*fp != end && secinfo_flags_equal(flags, (*fp)->flags)) { seq_printf(m, ":%d", (*fp)->pseudoflavor); (*fp)++; } return flags; } static void show_secinfo(struct seq_file *m, struct svc_export *exp) { struct exp_flavor_info *f; struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors; int flags; if (exp->ex_nflavors == 0) return; f = exp->ex_flavors; flags = show_secinfo_run(m, &f, end); if (!secinfo_flags_equal(flags, exp->ex_flags)) show_secinfo_flags(m, flags); while (f != end) { flags = show_secinfo_run(m, &f, end); show_secinfo_flags(m, flags); } } static void exp_flags(struct seq_file *m, int flag, int fsid, kuid_t anonu, kgid_t anong, struct nfsd4_fs_locations *fsloc) { struct user_namespace *userns = m->file->f_cred->user_ns; show_expflags(m, flag, NFSEXP_ALLFLAGS); if (flag & NFSEXP_FSID) seq_printf(m, ",fsid=%d", fsid); if (!uid_eq(anonu, make_kuid(userns, (uid_t)-2)) && !uid_eq(anonu, make_kuid(userns, 0x10000-2))) seq_printf(m, ",anonuid=%u", from_kuid_munged(userns, anonu)); if (!gid_eq(anong, make_kgid(userns, (gid_t)-2)) && !gid_eq(anong, make_kgid(userns, 0x10000-2))) seq_printf(m, ",anongid=%u", from_kgid_munged(userns, anong)); if (fsloc && fsloc->locations_count > 0) { char *loctype = (fsloc->migrated) ? "refer" : "replicas"; int i; seq_printf(m, ",%s=", loctype); seq_escape(m, fsloc->locations[0].path, ",;@ \t\n\\"); seq_putc(m, '@'); seq_escape(m, fsloc->locations[0].hosts, ",;@ \t\n\\"); for (i = 1; i < fsloc->locations_count; i++) { seq_putc(m, ';'); seq_escape(m, fsloc->locations[i].path, ",;@ \t\n\\"); seq_putc(m, '@'); seq_escape(m, fsloc->locations[i].hosts, ",;@ \t\n\\"); } } } static int e_show(struct seq_file *m, void *p) { struct cache_head *cp = p; struct svc_export *exp = container_of(cp, struct svc_export, h); struct cache_detail *cd = m->private; bool export_stats = is_export_stats_file(m); if (p == SEQ_START_TOKEN) { seq_puts(m, "# Version 1.1\n"); if (export_stats) seq_puts(m, "# Path Client Start-time\n#\tStats\n"); else seq_puts(m, "# Path Client(Flags) # IPs\n"); return 0; } if (!cache_get_rcu(&exp->h)) return 0; if (cache_check(cd, &exp->h, NULL)) return 0; exp_put(exp); return svc_export_show(m, cd, cp); } const struct seq_operations nfs_exports_op = { .start = cache_seq_start_rcu, .next = cache_seq_next_rcu, .stop = cache_seq_stop_rcu, .show = e_show, }; /* * Initialize the exports module. */ int nfsd_export_init(struct net *net) { int rv; struct nfsd_net *nn = net_generic(net, nfsd_net_id); dprintk("nfsd: initializing export module (net: %x).\n", net->ns.inum); nn->svc_export_cache = cache_create_net(&svc_export_cache_template, net); if (IS_ERR(nn->svc_export_cache)) return PTR_ERR(nn->svc_export_cache); rv = cache_register_net(nn->svc_export_cache, net); if (rv) goto destroy_export_cache; nn->svc_expkey_cache = cache_create_net(&svc_expkey_cache_template, net); if (IS_ERR(nn->svc_expkey_cache)) { rv = PTR_ERR(nn->svc_expkey_cache); goto unregister_export_cache; } rv = cache_register_net(nn->svc_expkey_cache, net); if (rv) goto destroy_expkey_cache; return 0; destroy_expkey_cache: cache_destroy_net(nn->svc_expkey_cache, net); unregister_export_cache: cache_unregister_net(nn->svc_export_cache, net); destroy_export_cache: cache_destroy_net(nn->svc_export_cache, net); return rv; } /* * Flush exports table - called when last nfsd thread is killed */ void nfsd_export_flush(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); cache_purge(nn->svc_expkey_cache); cache_purge(nn->svc_export_cache); } /* * Shutdown the exports module. */ void nfsd_export_shutdown(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); dprintk("nfsd: shutting down export module (net: %x).\n", net->ns.inum); cache_unregister_net(nn->svc_expkey_cache, net); cache_unregister_net(nn->svc_export_cache, net); cache_destroy_net(nn->svc_expkey_cache, net); cache_destroy_net(nn->svc_export_cache, net); svcauth_unix_purge(net); dprintk("nfsd: export shutdown complete (net: %x).\n", net->ns.inum); } |
| 600 14 575 93 603 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* Connection tracking via netlink socket. Allows for user space * protocol helpers and general trouble making from userspace. * * (C) 2001 by Jay Schulist <jschlst@samba.org> * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org> * (C) 2003 by Patrick Mchardy <kaber@trash.net> * (C) 2005-2012 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial connection tracking via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) * * Further development of this code funded by Astaro AG (http://www.astaro.com) * * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. */ #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/rculist.h> #include <linux/rculist_nulls.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/security.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/netlink.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/siphash.h> #include <linux/netfilter.h> #include <net/netlink.h> #include <net/sock.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_conntrack_synproxy.h> #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_helper.h> #endif #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> #include "nf_internals.h" MODULE_LICENSE("GPL"); static int ctnetlink_dump_tuples_proto(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *l4proto) { int ret = 0; struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, CTA_TUPLE_PROTO); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTO_NUM, tuple->dst.protonum)) goto nla_put_failure; if (likely(l4proto->tuple_to_nlattr)) ret = l4proto->tuple_to_nlattr(skb, tuple); nla_nest_end(skb, nest_parms); return ret; nla_put_failure: return -1; } static int ipv4_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) || nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip)) return -EMSGSIZE; return 0; } static int ipv6_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) || nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6)) return -EMSGSIZE; return 0; } static int ctnetlink_dump_tuples_ip(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { int ret = 0; struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, CTA_TUPLE_IP); if (!nest_parms) goto nla_put_failure; switch (tuple->src.l3num) { case NFPROTO_IPV4: ret = ipv4_tuple_to_nlattr(skb, tuple); break; case NFPROTO_IPV6: ret = ipv6_tuple_to_nlattr(skb, tuple); break; } nla_nest_end(skb, nest_parms); return ret; nla_put_failure: return -1; } static int ctnetlink_dump_tuples(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { const struct nf_conntrack_l4proto *l4proto; int ret; rcu_read_lock(); ret = ctnetlink_dump_tuples_ip(skb, tuple); if (ret >= 0) { l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto); } rcu_read_unlock(); return ret; } static int ctnetlink_dump_zone_id(struct sk_buff *skb, int attrtype, const struct nf_conntrack_zone *zone, int dir) { if (zone->id == NF_CT_DEFAULT_ZONE_ID || zone->dir != dir) return 0; if (nla_put_be16(skb, attrtype, htons(zone->id))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_status(struct sk_buff *skb, const struct nf_conn *ct) { if (nla_put_be32(skb, CTA_STATUS, htonl(ct->status))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct, bool skip_zero) { long timeout = nf_ct_expires(ct) / HZ; if (skip_zero && timeout == 0) return 0; if (nla_put_be32(skb, CTA_TIMEOUT, htonl(timeout))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct, bool destroy) { const struct nf_conntrack_l4proto *l4proto; struct nlattr *nest_proto; int ret; l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (!l4proto->to_nlattr) return 0; nest_proto = nla_nest_start(skb, CTA_PROTOINFO); if (!nest_proto) goto nla_put_failure; ret = l4proto->to_nlattr(skb, nest_proto, ct, destroy); nla_nest_end(skb, nest_proto); return ret; nla_put_failure: return -1; } static int ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_helper; const struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_helper *helper; if (!help) return 0; rcu_read_lock(); helper = rcu_dereference(help->helper); if (!helper) goto out; nest_helper = nla_nest_start(skb, CTA_HELP); if (!nest_helper) goto nla_put_failure; if (nla_put_string(skb, CTA_HELP_NAME, helper->name)) goto nla_put_failure; if (helper->to_nlattr) helper->to_nlattr(skb, ct); nla_nest_end(skb, nest_helper); out: rcu_read_unlock(); return 0; nla_put_failure: rcu_read_unlock(); return -1; } static int dump_counters(struct sk_buff *skb, struct nf_conn_acct *acct, enum ip_conntrack_dir dir, int type) { enum ctattr_type attr = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG; struct nf_conn_counter *counter = acct->counter; struct nlattr *nest_count; u64 pkts, bytes; if (type == IPCTNL_MSG_CT_GET_CTRZERO) { pkts = atomic64_xchg(&counter[dir].packets, 0); bytes = atomic64_xchg(&counter[dir].bytes, 0); } else { pkts = atomic64_read(&counter[dir].packets); bytes = atomic64_read(&counter[dir].bytes); } nest_count = nla_nest_start(skb, attr); if (!nest_count) goto nla_put_failure; if (nla_put_be64(skb, CTA_COUNTERS_PACKETS, cpu_to_be64(pkts), CTA_COUNTERS_PAD) || nla_put_be64(skb, CTA_COUNTERS_BYTES, cpu_to_be64(bytes), CTA_COUNTERS_PAD)) goto nla_put_failure; nla_nest_end(skb, nest_count); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_acct(struct sk_buff *skb, const struct nf_conn *ct, int type) { struct nf_conn_acct *acct = nf_conn_acct_find(ct); if (!acct) return 0; if (dump_counters(skb, acct, IP_CT_DIR_ORIGINAL, type) < 0) return -1; if (dump_counters(skb, acct, IP_CT_DIR_REPLY, type) < 0) return -1; return 0; } static int ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_count; const struct nf_conn_tstamp *tstamp; tstamp = nf_conn_tstamp_find(ct); if (!tstamp) return 0; nest_count = nla_nest_start(skb, CTA_TIMESTAMP); if (!nest_count) goto nla_put_failure; if (nla_put_be64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start), CTA_TIMESTAMP_PAD) || (tstamp->stop != 0 && nla_put_be64(skb, CTA_TIMESTAMP_STOP, cpu_to_be64(tstamp->stop), CTA_TIMESTAMP_PAD))) goto nla_put_failure; nla_nest_end(skb, nest_count); return 0; nla_put_failure: return -1; } #ifdef CONFIG_NF_CONNTRACK_MARK static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct, bool dump) { u32 mark = READ_ONCE(ct->mark); if (!mark && !dump) return 0; if (nla_put_be32(skb, CTA_MARK, htonl(mark))) goto nla_put_failure; return 0; nla_put_failure: return -1; } #else #define ctnetlink_dump_mark(a, b, c) (0) #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_secctx; int len, ret; char *secctx; ret = security_secid_to_secctx(ct->secmark, &secctx, &len); if (ret) return 0; ret = -1; nest_secctx = nla_nest_start(skb, CTA_SECCTX); if (!nest_secctx) goto nla_put_failure; if (nla_put_string(skb, CTA_SECCTX_NAME, secctx)) goto nla_put_failure; nla_nest_end(skb, nest_secctx); ret = 0; nla_put_failure: security_release_secctx(secctx, len); return ret; } #else #define ctnetlink_dump_secctx(a, b) (0) #endif #ifdef CONFIG_NF_CONNTRACK_EVENTS static inline int ctnetlink_label_size(const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); if (!labels) return 0; return nla_total_size(sizeof(labels->bits)); } #endif static int ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); unsigned int i; if (!labels) return 0; i = 0; do { if (labels->bits[i] != 0) return nla_put(skb, CTA_LABELS, sizeof(labels->bits), labels->bits); i++; } while (i < ARRAY_SIZE(labels->bits)); return 0; } #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple) static int ctnetlink_dump_master(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_parms; if (!(ct->status & IPS_EXPECTED)) return 0; nest_parms = nla_nest_start(skb, CTA_TUPLE_MASTER); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, master_tuple(ct)) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int dump_ct_seq_adj(struct sk_buff *skb, const struct nf_ct_seqadj *seq, int type) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, type); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_SEQADJ_CORRECTION_POS, htonl(seq->correction_pos)) || nla_put_be32(skb, CTA_SEQADJ_OFFSET_BEFORE, htonl(seq->offset_before)) || nla_put_be32(skb, CTA_SEQADJ_OFFSET_AFTER, htonl(seq->offset_after))) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_ct_seq_adj(struct sk_buff *skb, struct nf_conn *ct) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); struct nf_ct_seqadj *seq; if (!(ct->status & IPS_SEQ_ADJUST) || !seqadj) return 0; spin_lock_bh(&ct->lock); seq = &seqadj->seq[IP_CT_DIR_ORIGINAL]; if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_ORIG) == -1) goto err; seq = &seqadj->seq[IP_CT_DIR_REPLY]; if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_REPLY) == -1) goto err; spin_unlock_bh(&ct->lock); return 0; err: spin_unlock_bh(&ct->lock); return -1; } static int ctnetlink_dump_ct_synproxy(struct sk_buff *skb, struct nf_conn *ct) { struct nf_conn_synproxy *synproxy = nfct_synproxy(ct); struct nlattr *nest_parms; if (!synproxy) return 0; nest_parms = nla_nest_start(skb, CTA_SYNPROXY); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_SYNPROXY_ISN, htonl(synproxy->isn)) || nla_put_be32(skb, CTA_SYNPROXY_ITS, htonl(synproxy->its)) || nla_put_be32(skb, CTA_SYNPROXY_TSOFF, htonl(synproxy->tsoff))) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) { __be32 id = (__force __be32)nf_ct_get_id(ct); if (nla_put_be32(skb, CTA_ID, id)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct) { if (nla_put_be32(skb, CTA_USE, htonl(refcount_read(&ct->ct_general.use)))) goto nla_put_failure; return 0; nla_put_failure: return -1; } /* all these functions access ct->ext. Caller must either hold a reference * on ct or prevent its deletion by holding either the bucket spinlock or * pcpu dying list lock. */ static int ctnetlink_dump_extinfo(struct sk_buff *skb, struct nf_conn *ct, u32 type) { if (ctnetlink_dump_acct(skb, ct, type) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0 || ctnetlink_dump_helpinfo(skb, ct) < 0 || ctnetlink_dump_labels(skb, ct) < 0 || ctnetlink_dump_ct_seq_adj(skb, ct) < 0 || ctnetlink_dump_ct_synproxy(skb, ct) < 0) return -1; return 0; } static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || ctnetlink_dump_mark(skb, ct, true) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || ctnetlink_dump_master(skb, ct) < 0) return -1; if (!test_bit(IPS_OFFLOAD_BIT, &ct->status) && (ctnetlink_dump_timeout(skb, ct, false) < 0 || ctnetlink_dump_protoinfo(skb, ct, false) < 0)) return -1; return 0; } static int ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct nf_conn *ct, bool extinfo, unsigned int flags) { const struct nf_conntrack_zone *zone; struct nlmsghdr *nlh; struct nlattr *nest_parms; unsigned int event; if (portid) flags |= NLM_F_MULTI; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW); nlh = nfnl_msg_put(skb, portid, seq, event, flags, nf_ct_l3num(ct), NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_info(skb, ct) < 0) goto nla_put_failure; if (extinfo && ctnetlink_dump_extinfo(skb, ct, type) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } static const struct nla_policy cta_ip_nla_policy[CTA_IP_MAX + 1] = { [CTA_IP_V4_SRC] = { .type = NLA_U32 }, [CTA_IP_V4_DST] = { .type = NLA_U32 }, [CTA_IP_V6_SRC] = { .len = sizeof(__be32) * 4 }, [CTA_IP_V6_DST] = { .len = sizeof(__be32) * 4 }, }; #if defined(CONFIG_NETFILTER_NETLINK_GLUE_CT) || defined(CONFIG_NF_CONNTRACK_EVENTS) static size_t ctnetlink_proto_size(const struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; size_t len, len4 = 0; len = nla_policy_len(cta_ip_nla_policy, CTA_IP_MAX + 1); len *= 3u; /* ORIG, REPLY, MASTER */ l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); len += l4proto->nlattr_size; if (l4proto->nlattr_tuple_size) { len4 = l4proto->nlattr_tuple_size(); len4 *= 3u; /* ORIG, REPLY, MASTER */ } return len + len4; } #endif static inline size_t ctnetlink_acct_size(const struct nf_conn *ct) { if (!nf_ct_ext_exist(ct, NF_CT_EXT_ACCT)) return 0; return 2 * nla_total_size(0) /* CTA_COUNTERS_ORIG|REPL */ + 2 * nla_total_size_64bit(sizeof(uint64_t)) /* CTA_COUNTERS_PACKETS */ + 2 * nla_total_size_64bit(sizeof(uint64_t)) /* CTA_COUNTERS_BYTES */ ; } static inline int ctnetlink_secctx_size(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_SECMARK int len, ret; ret = security_secid_to_secctx(ct->secmark, NULL, &len); if (ret) return 0; return nla_total_size(0) /* CTA_SECCTX */ + nla_total_size(sizeof(char) * len); /* CTA_SECCTX_NAME */ #else return 0; #endif } static inline size_t ctnetlink_timestamp_size(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP if (!nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP)) return 0; return nla_total_size(0) + 2 * nla_total_size_64bit(sizeof(uint64_t)); #else return 0; #endif } #ifdef CONFIG_NF_CONNTRACK_EVENTS static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) { return NLMSG_ALIGN(sizeof(struct nfgenmsg)) + 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + ctnetlink_acct_size(ct) + ctnetlink_timestamp_size(ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + nla_total_size(0) /* CTA_PROTOINFO */ + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) #if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif #ifdef CONFIG_NF_CONNTRACK_MARK + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif #ifdef CONFIG_NF_CONNTRACK_ZONES + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE|CTA_TUPLE_ZONE */ #endif + ctnetlink_proto_size(ct) + ctnetlink_label_size(ct) ; } static int ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) { const struct nf_conntrack_zone *zone; struct net *net; struct nlmsghdr *nlh; struct nlattr *nest_parms; struct nf_conn *ct = item->ct; struct sk_buff *skb; unsigned int type; unsigned int flags = 0, group; int err; if (events & (1 << IPCT_DESTROY)) { type = IPCTNL_MSG_CT_DELETE; group = NFNLGRP_CONNTRACK_DESTROY; } else if (events & ((1 << IPCT_NEW) | (1 << IPCT_RELATED))) { type = IPCTNL_MSG_CT_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_NEW; } else if (events) { type = IPCTNL_MSG_CT_NEW; group = NFNLGRP_CONNTRACK_UPDATE; } else return 0; net = nf_ct_net(ct); if (!item->report && !nfnetlink_has_listeners(net, group)) return 0; skb = nlmsg_new(ctnetlink_nlmsg_size(ct), GFP_ATOMIC); if (skb == NULL) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, type); nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, nf_ct_l3num(ct), NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_status(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_DESTROY)) { if (ctnetlink_dump_timeout(skb, ct, true) < 0) goto nla_put_failure; if (ctnetlink_dump_acct(skb, ct, type) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0 || ctnetlink_dump_protoinfo(skb, ct, true) < 0) goto nla_put_failure; } else { if (ctnetlink_dump_timeout(skb, ct, false) < 0) goto nla_put_failure; if (events & (1 << IPCT_PROTOINFO) && ctnetlink_dump_protoinfo(skb, ct, false) < 0) goto nla_put_failure; if ((events & (1 << IPCT_HELPER) || nfct_help(ct)) && ctnetlink_dump_helpinfo(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_SECMARK if ((events & (1 << IPCT_SECMARK) || ct->secmark) && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif if (events & (1 << IPCT_LABEL) && ctnetlink_dump_labels(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_RELATED) && ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_SEQADJ) && ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_SYNPROXY) && ctnetlink_dump_ct_synproxy(skb, ct) < 0) goto nla_put_failure; } #ifdef CONFIG_NF_CONNTRACK_MARK if (ctnetlink_dump_mark(skb, ct, events & (1 << IPCT_MARK))) goto nla_put_failure; #endif nlmsg_end(skb, nlh); err = nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); if (err == -ENOBUFS || err == -EAGAIN) return -ENOBUFS; return 0; nla_put_failure: nlmsg_cancel(skb, nlh); nlmsg_failure: kfree_skb(skb); errout: if (nfnetlink_set_err(net, 0, group, -ENOBUFS) > 0) return -ENOBUFS; return 0; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ static int ctnetlink_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_put((struct nf_conn *)cb->args[1]); kfree(cb->data); return 0; } struct ctnetlink_filter_u32 { u32 val; u32 mask; }; struct ctnetlink_filter { u8 family; u_int32_t orig_flags; u_int32_t reply_flags; struct nf_conntrack_tuple orig; struct nf_conntrack_tuple reply; struct nf_conntrack_zone zone; struct ctnetlink_filter_u32 mark; struct ctnetlink_filter_u32 status; }; static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = { [CTA_FILTER_ORIG_FLAGS] = { .type = NLA_U32 }, [CTA_FILTER_REPLY_FLAGS] = { .type = NLA_U32 }, }; static int ctnetlink_parse_filter(const struct nlattr *attr, struct ctnetlink_filter *filter) { struct nlattr *tb[CTA_FILTER_MAX + 1]; int ret = 0; ret = nla_parse_nested(tb, CTA_FILTER_MAX, attr, cta_filter_nla_policy, NULL); if (ret) return ret; if (tb[CTA_FILTER_ORIG_FLAGS]) { filter->orig_flags = nla_get_u32(tb[CTA_FILTER_ORIG_FLAGS]); if (filter->orig_flags & ~CTA_FILTER_F_ALL) return -EOPNOTSUPP; } if (tb[CTA_FILTER_REPLY_FLAGS]) { filter->reply_flags = nla_get_u32(tb[CTA_FILTER_REPLY_FLAGS]); if (filter->reply_flags & ~CTA_FILTER_F_ALL) return -EOPNOTSUPP; } return 0; } static int ctnetlink_parse_zone(const struct nlattr *attr, struct nf_conntrack_zone *zone); static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone, u_int32_t flags); static int ctnetlink_filter_parse_mark(struct ctnetlink_filter_u32 *mark, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK]) { mark->val = ntohl(nla_get_be32(cda[CTA_MARK])); if (cda[CTA_MARK_MASK]) mark->mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); else mark->mask = 0xffffffff; } else if (cda[CTA_MARK_MASK]) { return -EINVAL; } #endif return 0; } static int ctnetlink_filter_parse_status(struct ctnetlink_filter_u32 *status, const struct nlattr * const cda[]) { if (cda[CTA_STATUS]) { status->val = ntohl(nla_get_be32(cda[CTA_STATUS])); if (cda[CTA_STATUS_MASK]) status->mask = ntohl(nla_get_be32(cda[CTA_STATUS_MASK])); else status->mask = status->val; /* status->val == 0? always true, else always false. */ if (status->mask == 0) return -EINVAL; } else if (cda[CTA_STATUS_MASK]) { return -EINVAL; } /* CTA_STATUS is NLA_U32, if this fires UAPI needs to be extended */ BUILD_BUG_ON(__IPS_MAX_BIT >= 32); return 0; } static struct ctnetlink_filter * ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) { struct ctnetlink_filter *filter; int err; #ifndef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK] || cda[CTA_MARK_MASK]) return ERR_PTR(-EOPNOTSUPP); #endif filter = kzalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) return ERR_PTR(-ENOMEM); filter->family = family; err = ctnetlink_filter_parse_mark(&filter->mark, cda); if (err) goto err_filter; err = ctnetlink_filter_parse_status(&filter->status, cda); if (err) goto err_filter; if (!cda[CTA_FILTER]) return filter; err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); if (err < 0) goto err_filter; err = ctnetlink_parse_filter(cda[CTA_FILTER], filter); if (err < 0) goto err_filter; if (filter->orig_flags) { if (!cda[CTA_TUPLE_ORIG]) { err = -EINVAL; goto err_filter; } err = ctnetlink_parse_tuple_filter(cda, &filter->orig, CTA_TUPLE_ORIG, filter->family, &filter->zone, filter->orig_flags); if (err < 0) goto err_filter; } if (filter->reply_flags) { if (!cda[CTA_TUPLE_REPLY]) { err = -EINVAL; goto err_filter; } err = ctnetlink_parse_tuple_filter(cda, &filter->reply, CTA_TUPLE_REPLY, filter->family, &filter->zone, filter->reply_flags); if (err < 0) goto err_filter; } return filter; err_filter: kfree(filter); return ERR_PTR(err); } static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) { return family || cda[CTA_MARK] || cda[CTA_FILTER] || cda[CTA_STATUS]; } static int ctnetlink_start(struct netlink_callback *cb) { const struct nlattr * const *cda = cb->data; struct ctnetlink_filter *filter = NULL; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u8 family = nfmsg->nfgen_family; if (ctnetlink_needs_filter(family, cda)) { filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); } cb->data = filter; return 0; } static int ctnetlink_filter_match_tuple(struct nf_conntrack_tuple *filter_tuple, struct nf_conntrack_tuple *ct_tuple, u_int32_t flags, int family) { switch (family) { case NFPROTO_IPV4: if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && filter_tuple->src.u3.ip != ct_tuple->src.u3.ip) return 0; if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && filter_tuple->dst.u3.ip != ct_tuple->dst.u3.ip) return 0; break; case NFPROTO_IPV6: if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && !ipv6_addr_cmp(&filter_tuple->src.u3.in6, &ct_tuple->src.u3.in6)) return 0; if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && !ipv6_addr_cmp(&filter_tuple->dst.u3.in6, &ct_tuple->dst.u3.in6)) return 0; break; } if ((flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) && filter_tuple->dst.protonum != ct_tuple->dst.protonum) return 0; switch (ct_tuple->dst.protonum) { case IPPROTO_TCP: case IPPROTO_UDP: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) && filter_tuple->src.u.tcp.port != ct_tuple->src.u.tcp.port) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) && filter_tuple->dst.u.tcp.port != ct_tuple->dst.u.tcp.port) return 0; break; case IPPROTO_ICMP: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) && filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) && filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) && filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) return 0; break; case IPPROTO_ICMPV6: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) && filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) && filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) && filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) return 0; break; } return 1; } static int ctnetlink_filter_match(struct nf_conn *ct, void *data) { struct ctnetlink_filter *filter = data; struct nf_conntrack_tuple *tuple; u32 status; if (filter == NULL) goto out; /* Match entries of a given L3 protocol number. * If it is not specified, ie. l3proto == 0, * then match everything. */ if (filter->family && nf_ct_l3num(ct) != filter->family) goto ignore_entry; if (filter->orig_flags) { tuple = nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL); if (!ctnetlink_filter_match_tuple(&filter->orig, tuple, filter->orig_flags, filter->family)) goto ignore_entry; } if (filter->reply_flags) { tuple = nf_ct_tuple(ct, IP_CT_DIR_REPLY); if (!ctnetlink_filter_match_tuple(&filter->reply, tuple, filter->reply_flags, filter->family)) goto ignore_entry; } #ifdef CONFIG_NF_CONNTRACK_MARK if ((READ_ONCE(ct->mark) & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif status = (u32)READ_ONCE(ct->status); if ((status & filter->status.mask) != filter->status.val) goto ignore_entry; out: return 1; ignore_entry: return 0; } static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0; struct net *net = sock_net(skb->sk); struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nf_conn *nf_ct_evict[8]; int res, i; spinlock_t *lockp; last = (struct nf_conn *)cb->args[1]; i = 0; local_bh_disable(); for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) { restart: while (i) { i--; if (nf_ct_should_gc(nf_ct_evict[i])) nf_ct_kill(nf_ct_evict[i]); nf_ct_put(nf_ct_evict[i]); } lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS]; nf_conntrack_lock(lockp); if (cb->args[0] >= nf_conntrack_htable_size) { spin_unlock(lockp); goto out; } hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[cb->args[0]], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = nf_ct_tuplehash_to_ctrack(h); if (nf_ct_is_expired(ct)) { if (i < ARRAY_SIZE(nf_ct_evict) && refcount_inc_not_zero(&ct->ct_general.use)) nf_ct_evict[i++] = ct; continue; } if (!net_eq(net, nf_ct_net(ct))) continue; if (cb->args[1]) { if (ct != last) continue; cb->args[1] = 0; } if (!ctnetlink_filter_match(ct, cb->data)) continue; res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, true, flags); if (res < 0) { nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; spin_unlock(lockp); goto out; } } spin_unlock(lockp); if (cb->args[1]) { cb->args[1] = 0; goto restart; } } out: local_bh_enable(); if (last) { /* nf ct hash resize happened, now clear the leftover. */ if ((struct nf_conn *)cb->args[1] == last) cb->args[1] = 0; nf_ct_put(last); } while (i) { i--; if (nf_ct_should_gc(nf_ct_evict[i])) nf_ct_kill(nf_ct_evict[i]); nf_ct_put(nf_ct_evict[i]); } return skb->len; } static int ipv4_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_IP_V4_SRC]) return -EINVAL; t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); } if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { if (!tb[CTA_IP_V4_DST]) return -EINVAL; t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); } return 0; } static int ipv6_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_IP_V6_SRC]) return -EINVAL; t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); } if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { if (!tb[CTA_IP_V6_DST]) return -EINVAL; t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); } return 0; } static int ctnetlink_parse_tuple_ip(struct nlattr *attr, struct nf_conntrack_tuple *tuple, u_int32_t flags) { struct nlattr *tb[CTA_IP_MAX+1]; int ret = 0; ret = nla_parse_nested_deprecated(tb, CTA_IP_MAX, attr, NULL, NULL); if (ret < 0) return ret; ret = nla_validate_nested_deprecated(attr, CTA_IP_MAX, cta_ip_nla_policy, NULL); if (ret) return ret; switch (tuple->src.l3num) { case NFPROTO_IPV4: ret = ipv4_nlattr_to_tuple(tb, tuple, flags); break; case NFPROTO_IPV6: ret = ipv6_nlattr_to_tuple(tb, tuple, flags); break; } return ret; } static const struct nla_policy proto_nla_policy[CTA_PROTO_MAX+1] = { [CTA_PROTO_NUM] = { .type = NLA_U8 }, }; static int ctnetlink_parse_tuple_proto(struct nlattr *attr, struct nf_conntrack_tuple *tuple, u_int32_t flags) { const struct nf_conntrack_l4proto *l4proto; struct nlattr *tb[CTA_PROTO_MAX+1]; int ret = 0; ret = nla_parse_nested_deprecated(tb, CTA_PROTO_MAX, attr, proto_nla_policy, NULL); if (ret < 0) return ret; if (!(flags & CTA_FILTER_FLAG(CTA_PROTO_NUM))) return 0; if (!tb[CTA_PROTO_NUM]) return -EINVAL; tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]); rcu_read_lock(); l4proto = nf_ct_l4proto_find(tuple->dst.protonum); if (likely(l4proto->nlattr_to_tuple)) { ret = nla_validate_nested_deprecated(attr, CTA_PROTO_MAX, l4proto->nla_policy, NULL); if (ret == 0) ret = l4proto->nlattr_to_tuple(tb, tuple, flags); } rcu_read_unlock(); return ret; } static int ctnetlink_parse_zone(const struct nlattr *attr, struct nf_conntrack_zone *zone) { nf_ct_zone_init(zone, NF_CT_DEFAULT_ZONE_ID, NF_CT_DEFAULT_ZONE_DIR, 0); #ifdef CONFIG_NF_CONNTRACK_ZONES if (attr) zone->id = ntohs(nla_get_be16(attr)); #else if (attr) return -EOPNOTSUPP; #endif return 0; } static int ctnetlink_parse_tuple_zone(struct nlattr *attr, enum ctattr_type type, struct nf_conntrack_zone *zone) { int ret; if (zone->id != NF_CT_DEFAULT_ZONE_ID) return -EINVAL; ret = ctnetlink_parse_zone(attr, zone); if (ret < 0) return ret; if (type == CTA_TUPLE_REPLY) zone->dir = NF_CT_ZONE_DIR_REPL; else zone->dir = NF_CT_ZONE_DIR_ORIG; return 0; } static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = { [CTA_TUPLE_IP] = { .type = NLA_NESTED }, [CTA_TUPLE_PROTO] = { .type = NLA_NESTED }, [CTA_TUPLE_ZONE] = { .type = NLA_U16 }, }; #define CTA_FILTER_F_ALL_CTA_PROTO \ (CTA_FILTER_F_CTA_PROTO_SRC_PORT | \ CTA_FILTER_F_CTA_PROTO_DST_PORT | \ CTA_FILTER_F_CTA_PROTO_ICMP_TYPE | \ CTA_FILTER_F_CTA_PROTO_ICMP_CODE | \ CTA_FILTER_F_CTA_PROTO_ICMP_ID | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_TYPE | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_CODE | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_ID) static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone, u_int32_t flags) { struct nlattr *tb[CTA_TUPLE_MAX+1]; int err; memset(tuple, 0, sizeof(*tuple)); err = nla_parse_nested_deprecated(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy, NULL); if (err < 0) return err; if (l3num != NFPROTO_IPV4 && l3num != NFPROTO_IPV6) return -EOPNOTSUPP; tuple->src.l3num = l3num; if (flags & CTA_FILTER_FLAG(CTA_IP_DST) || flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_TUPLE_IP]) return -EINVAL; err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple, flags); if (err < 0) return err; } if (flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) { if (!tb[CTA_TUPLE_PROTO]) return -EINVAL; err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO], tuple, flags); if (err < 0) return err; } else if (flags & CTA_FILTER_FLAG(ALL_CTA_PROTO)) { /* Can't manage proto flags without a protonum */ return -EINVAL; } if ((flags & CTA_FILTER_FLAG(CTA_TUPLE_ZONE)) && tb[CTA_TUPLE_ZONE]) { if (!zone) return -EINVAL; err = ctnetlink_parse_tuple_zone(tb[CTA_TUPLE_ZONE], type, zone); if (err < 0) return err; } /* orig and expect tuples get DIR_ORIGINAL */ if (type == CTA_TUPLE_REPLY) tuple->dst.dir = IP_CT_DIR_REPLY; else tuple->dst.dir = IP_CT_DIR_ORIGINAL; return 0; } static int ctnetlink_parse_tuple(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone) { return ctnetlink_parse_tuple_filter(cda, tuple, type, l3num, zone, CTA_FILTER_FLAG(ALL)); } static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { [CTA_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, }; static int ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, struct nlattr **helpinfo) { int err; struct nlattr *tb[CTA_HELP_MAX+1]; err = nla_parse_nested_deprecated(tb, CTA_HELP_MAX, attr, help_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_HELP_NAME]) return -EINVAL; *helper_name = nla_data(tb[CTA_HELP_NAME]); if (tb[CTA_HELP_INFO]) *helpinfo = tb[CTA_HELP_INFO]; return 0; } static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_TUPLE_ORIG] = { .type = NLA_NESTED }, [CTA_TUPLE_REPLY] = { .type = NLA_NESTED }, [CTA_STATUS] = { .type = NLA_U32 }, [CTA_PROTOINFO] = { .type = NLA_NESTED }, [CTA_HELP] = { .type = NLA_NESTED }, [CTA_NAT_SRC] = { .type = NLA_NESTED }, [CTA_TIMEOUT] = { .type = NLA_U32 }, [CTA_MARK] = { .type = NLA_U32 }, [CTA_ID] = { .type = NLA_U32 }, [CTA_NAT_DST] = { .type = NLA_NESTED }, [CTA_TUPLE_MASTER] = { .type = NLA_NESTED }, [CTA_NAT_SEQ_ADJ_ORIG] = { .type = NLA_NESTED }, [CTA_NAT_SEQ_ADJ_REPLY] = { .type = NLA_NESTED }, [CTA_ZONE] = { .type = NLA_U16 }, [CTA_MARK_MASK] = { .type = NLA_U32 }, [CTA_LABELS] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, [CTA_LABELS_MASK] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, [CTA_FILTER] = { .type = NLA_NESTED }, [CTA_STATUS_MASK] = { .type = NLA_U32 }, }; static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) { return ctnetlink_filter_match(ct, data); } static int ctnetlink_flush_conntrack(struct net *net, const struct nlattr * const cda[], u32 portid, int report, u8 family) { struct ctnetlink_filter *filter = NULL; if (ctnetlink_needs_filter(family, cda)) { if (cda[CTA_FILTER]) return -EOPNOTSUPP; filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); } nf_ct_iterate_cleanup_net(net, ctnetlink_flush_iterate, filter, portid, report); kfree(filter); return 0; } static int ctnetlink_del_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u8 family = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; struct nf_conn *ct; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, family, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, family, &zone); else { u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC; return ctnetlink_flush_conntrack(info->net, cda, NETLINK_CB(skb).portid, nlmsg_report(info->nlh), u3); } if (err < 0) return err; h = nf_conntrack_find_get(info->net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); if (cda[CTA_ID]) { __be32 id = nla_get_be32(cda[CTA_ID]); if (id != (__force __be32)nf_ct_get_id(ct)) { nf_ct_put(ct); return -ENOENT; } } nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); nf_ct_put(ct); return 0; } static int ctnetlink_get_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; struct sk_buff *skb2; struct nf_conn *ct; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = ctnetlink_start, .dump = ctnetlink_dump_table, .done = ctnetlink_done, .data = (void *)cda, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3, &zone); else return -EINVAL; if (err < 0) return err; h = nf_conntrack_find_get(info->net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb2) { nf_ct_put(ct); return -ENOMEM; } err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), ct, true, 0); nf_ct_put(ct); if (err <= 0) { kfree_skb(skb2); return -ENOMEM; } return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static int ctnetlink_done_list(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_put((struct nf_conn *)cb->args[1]); return 0; } static int ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying) { struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; int res; int cpu; struct hlist_nulls_head *list; struct net *net = sock_net(skb->sk); if (cb->args[2]) return 0; last = (struct nf_conn *)cb->args[1]; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { struct ct_pcpu *pcpu; if (!cpu_possible(cpu)) continue; pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); spin_lock_bh(&pcpu->lock); list = dying ? &pcpu->dying : &pcpu->unconfirmed; restart: hlist_nulls_for_each_entry(h, n, list, hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (l3proto && nf_ct_l3num(ct) != l3proto) continue; if (cb->args[1]) { if (ct != last) continue; cb->args[1] = 0; } /* We can't dump extension info for the unconfirmed * list because unconfirmed conntracks can have * ct->ext reallocated (and thus freed). * * In the dying list case ct->ext can't be free'd * until after we drop pcpu->lock. */ res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, dying ? true : false, 0); if (res < 0) { if (!refcount_inc_not_zero(&ct->ct_general.use)) continue; cb->args[0] = cpu; cb->args[1] = (unsigned long)ct; spin_unlock_bh(&pcpu->lock); goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } spin_unlock_bh(&pcpu->lock); } cb->args[2] = 1; out: if (last) nf_ct_put(last); return skb->len; } static int ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb) { return ctnetlink_dump_list(skb, cb, true); } static int ctnetlink_get_ct_dying(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_dump_dying, .done = ctnetlink_done_list, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return -EOPNOTSUPP; } static int ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb) { return ctnetlink_dump_list(skb, cb, false); } static int ctnetlink_get_ct_unconfirmed(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_dump_unconfirmed, .done = ctnetlink_done_list, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return -EOPNOTSUPP; } #if IS_ENABLED(CONFIG_NF_NAT) static int ctnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) __must_hold(RCU) { const struct nf_nat_hook *nat_hook; int err; nat_hook = rcu_dereference(nf_nat_hook); if (!nat_hook) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); if (request_module("nf-nat") < 0) { nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); if (nat_hook) return -EAGAIN; #endif return -EOPNOTSUPP; } err = nat_hook->parse_nat_setup(ct, manip, attr); if (err == -EAGAIN) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); if (request_module("nf-nat-%u", nf_ct_l3num(ct)) < 0) { nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); #else err = -EOPNOTSUPP; #endif } return err; } #endif static void __ctnetlink_change_status(struct nf_conn *ct, unsigned long on, unsigned long off) { unsigned int bit; /* Ignore these unchangable bits */ on &= ~IPS_UNCHANGEABLE_MASK; off &= ~IPS_UNCHANGEABLE_MASK; for (bit = 0; bit < __IPS_MAX_BIT; bit++) { if (on & (1 << bit)) set_bit(bit, &ct->status); else if (off & (1 << bit)) clear_bit(bit, &ct->status); } } static int ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) { unsigned long d; unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS])); d = ct->status ^ status; if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING)) /* unchangeable */ return -EBUSY; if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY)) /* SEEN_REPLY bit can only be set */ return -EBUSY; if (d & IPS_ASSURED && !(status & IPS_ASSURED)) /* ASSURED bit can only be set */ return -EBUSY; __ctnetlink_change_status(ct, status, 0); return 0; } static int ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[]) { #if IS_ENABLED(CONFIG_NF_NAT) int ret; if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) return 0; ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST, cda[CTA_NAT_DST]); if (ret < 0) return ret; return ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC, cda[CTA_NAT_SRC]); #else if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) return 0; return -EOPNOTSUPP; #endif } static int ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conntrack_helper *helper; struct nf_conn_help *help = nfct_help(ct); char *helpname = NULL; struct nlattr *helpinfo = NULL; int err; err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) return err; /* don't change helper of sibling connections */ if (ct->master) { /* If we try to change the helper to the same thing twice, * treat the second attempt as a no-op instead of returning * an error. */ err = -EBUSY; if (help) { rcu_read_lock(); helper = rcu_dereference(help->helper); if (helper && !strcmp(helper->name, helpname)) err = 0; rcu_read_unlock(); } return err; } if (!strcmp(helpname, "")) { if (help && help->helper) { /* we had a helper before ... */ nf_ct_remove_expectations(ct); RCU_INIT_POINTER(help->helper, NULL); } return 0; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); return -EOPNOTSUPP; } if (help) { if (help->helper == helper) { /* update private helper data if allowed. */ if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); err = 0; } else err = -EBUSY; } else { /* we cannot set a helper for an existing conntrack */ err = -EOPNOTSUPP; } rcu_read_unlock(); return err; } static int ctnetlink_change_timeout(struct nf_conn *ct, const struct nlattr * const cda[]) { u64 timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; if (timeout > INT_MAX) timeout = INT_MAX; WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout); if (test_bit(IPS_DYING_BIT, &ct->status)) return -ETIME; return 0; } #if defined(CONFIG_NF_CONNTRACK_MARK) static void ctnetlink_change_mark(struct nf_conn *ct, const struct nlattr * const cda[]) { u32 mark, newmark, mask = 0; if (cda[CTA_MARK_MASK]) mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK])); mark = ntohl(nla_get_be32(cda[CTA_MARK])); newmark = (READ_ONCE(ct->mark) & mask) ^ mark; if (newmark != READ_ONCE(ct->mark)) WRITE_ONCE(ct->mark, newmark); } #endif static const struct nla_policy protoinfo_policy[CTA_PROTOINFO_MAX+1] = { [CTA_PROTOINFO_TCP] = { .type = NLA_NESTED }, [CTA_PROTOINFO_DCCP] = { .type = NLA_NESTED }, [CTA_PROTOINFO_SCTP] = { .type = NLA_NESTED }, }; static int ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[]) { const struct nlattr *attr = cda[CTA_PROTOINFO]; const struct nf_conntrack_l4proto *l4proto; struct nlattr *tb[CTA_PROTOINFO_MAX+1]; int err = 0; err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy, NULL); if (err < 0) return err; l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (l4proto->from_nlattr) err = l4proto->from_nlattr(tb, ct); return err; } static const struct nla_policy seqadj_policy[CTA_SEQADJ_MAX+1] = { [CTA_SEQADJ_CORRECTION_POS] = { .type = NLA_U32 }, [CTA_SEQADJ_OFFSET_BEFORE] = { .type = NLA_U32 }, [CTA_SEQADJ_OFFSET_AFTER] = { .type = NLA_U32 }, }; static int change_seq_adj(struct nf_ct_seqadj *seq, const struct nlattr * const attr) { int err; struct nlattr *cda[CTA_SEQADJ_MAX+1]; err = nla_parse_nested_deprecated(cda, CTA_SEQADJ_MAX, attr, seqadj_policy, NULL); if (err < 0) return err; if (!cda[CTA_SEQADJ_CORRECTION_POS]) return -EINVAL; seq->correction_pos = ntohl(nla_get_be32(cda[CTA_SEQADJ_CORRECTION_POS])); if (!cda[CTA_SEQADJ_OFFSET_BEFORE]) return -EINVAL; seq->offset_before = ntohl(nla_get_be32(cda[CTA_SEQADJ_OFFSET_BEFORE])); if (!cda[CTA_SEQADJ_OFFSET_AFTER]) return -EINVAL; seq->offset_after = ntohl(nla_get_be32(cda[CTA_SEQADJ_OFFSET_AFTER])); return 0; } static int ctnetlink_change_seq_adj(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); int ret = 0; if (!seqadj) return 0; spin_lock_bh(&ct->lock); if (cda[CTA_SEQ_ADJ_ORIG]) { ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_ORIGINAL], cda[CTA_SEQ_ADJ_ORIG]); if (ret < 0) goto err; set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); } if (cda[CTA_SEQ_ADJ_REPLY]) { ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_REPLY], cda[CTA_SEQ_ADJ_REPLY]); if (ret < 0) goto err; set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); } spin_unlock_bh(&ct->lock); return 0; err: spin_unlock_bh(&ct->lock); return ret; } static const struct nla_policy synproxy_policy[CTA_SYNPROXY_MAX + 1] = { [CTA_SYNPROXY_ISN] = { .type = NLA_U32 }, [CTA_SYNPROXY_ITS] = { .type = NLA_U32 }, [CTA_SYNPROXY_TSOFF] = { .type = NLA_U32 }, }; static int ctnetlink_change_synproxy(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conn_synproxy *synproxy = nfct_synproxy(ct); struct nlattr *tb[CTA_SYNPROXY_MAX + 1]; int err; if (!synproxy) return 0; err = nla_parse_nested_deprecated(tb, CTA_SYNPROXY_MAX, cda[CTA_SYNPROXY], synproxy_policy, NULL); if (err < 0) return err; if (!tb[CTA_SYNPROXY_ISN] || !tb[CTA_SYNPROXY_ITS] || !tb[CTA_SYNPROXY_TSOFF]) return -EINVAL; synproxy->isn = ntohl(nla_get_be32(tb[CTA_SYNPROXY_ISN])); synproxy->its = ntohl(nla_get_be32(tb[CTA_SYNPROXY_ITS])); synproxy->tsoff = ntohl(nla_get_be32(tb[CTA_SYNPROXY_TSOFF])); return 0; } static int ctnetlink_attach_labels(struct nf_conn *ct, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_CONNTRACK_LABELS size_t len = nla_len(cda[CTA_LABELS]); const void *mask = cda[CTA_LABELS_MASK]; if (len & (sizeof(u32)-1)) /* must be multiple of u32 */ return -EINVAL; if (mask) { if (nla_len(cda[CTA_LABELS_MASK]) == 0 || nla_len(cda[CTA_LABELS_MASK]) != len) return -EINVAL; mask = nla_data(cda[CTA_LABELS_MASK]); } len /= sizeof(u32); return nf_connlabels_replace(ct, nla_data(cda[CTA_LABELS]), mask, len); #else return -EOPNOTSUPP; #endif } static int ctnetlink_change_conntrack(struct nf_conn *ct, const struct nlattr * const cda[]) { int err; /* only allow NAT changes and master assignation for new conntracks */ if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST] || cda[CTA_TUPLE_MASTER]) return -EOPNOTSUPP; if (cda[CTA_HELP]) { err = ctnetlink_change_helper(ct, cda); if (err < 0) return err; } if (cda[CTA_TIMEOUT]) { err = ctnetlink_change_timeout(ct, cda); if (err < 0) return err; } if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); if (err < 0) return err; } if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) return err; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ctnetlink_change_mark(ct, cda); #endif if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) { err = ctnetlink_change_seq_adj(ct, cda); if (err < 0) return err; } if (cda[CTA_SYNPROXY]) { err = ctnetlink_change_synproxy(ct, cda); if (err < 0) return err; } if (cda[CTA_LABELS]) { err = ctnetlink_attach_labels(ct, cda); if (err < 0) return err; } return 0; } static struct nf_conn * ctnetlink_create_conntrack(struct net *net, const struct nf_conntrack_zone *zone, const struct nlattr * const cda[], struct nf_conntrack_tuple *otuple, struct nf_conntrack_tuple *rtuple, u8 u3) { struct nf_conn *ct; int err = -EINVAL; struct nf_conntrack_helper *helper; struct nf_conn_tstamp *tstamp; u64 timeout; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) return ERR_PTR(-ENOMEM); if (!cda[CTA_TIMEOUT]) goto err1; timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; if (timeout > INT_MAX) timeout = INT_MAX; ct->timeout = (u32)timeout + nfct_time_stamp; rcu_read_lock(); if (cda[CTA_HELP]) { char *helpname = NULL; struct nlattr *helpinfo = NULL; err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) goto err2; helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { err = -EOPNOTSUPP; goto err1; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper) { err = -EAGAIN; goto err2; } rcu_read_unlock(); #endif err = -EOPNOTSUPP; goto err1; } else { struct nf_conn_help *help; help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help == NULL) { err = -ENOMEM; goto err2; } /* set private helper data if allowed. */ if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); /* disable helper auto-assignment for this entry */ ct->status |= IPS_HELPER; RCU_INIT_POINTER(help->helper, helper); } } else { /* try an implicit helper assignation */ err = __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC); if (err < 0) goto err2; } err = ctnetlink_setup_nat(ct, cda); if (err < 0) goto err2; nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); nf_ct_labels_ext_add(ct); nfct_seqadj_ext_add(ct); nfct_synproxy_ext_add(ct); /* we must add conntrack extensions before confirmation. */ ct->status |= IPS_CONFIRMED; if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); if (err < 0) goto err2; } if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) { err = ctnetlink_change_seq_adj(ct, cda); if (err < 0) goto err2; } memset(&ct->proto, 0, sizeof(ct->proto)); if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) goto err2; } if (cda[CTA_SYNPROXY]) { err = ctnetlink_change_synproxy(ct, cda); if (err < 0) goto err2; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ctnetlink_change_mark(ct, cda); #endif /* setup master conntrack: this is a confirmed expectation */ if (cda[CTA_TUPLE_MASTER]) { struct nf_conntrack_tuple master; struct nf_conntrack_tuple_hash *master_h; struct nf_conn *master_ct; err = ctnetlink_parse_tuple(cda, &master, CTA_TUPLE_MASTER, u3, NULL); if (err < 0) goto err2; master_h = nf_conntrack_find_get(net, zone, &master); if (master_h == NULL) { err = -ENOENT; goto err2; } master_ct = nf_ct_tuplehash_to_ctrack(master_h); __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = master_ct; } tstamp = nf_conn_tstamp_find(ct); if (tstamp) tstamp->start = ktime_get_real_ns(); err = nf_conntrack_hash_check_insert(ct); if (err < 0) goto err3; rcu_read_unlock(); return ct; err3: if (ct->master) nf_ct_put(ct->master); err2: rcu_read_unlock(); err1: nf_conntrack_free(ct); return ERR_PTR(err); } static int ctnetlink_new_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_zone zone; struct nf_conn *ct; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) { err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG, u3, &zone); if (err < 0) return err; } if (cda[CTA_TUPLE_REPLY]) { err = ctnetlink_parse_tuple(cda, &rtuple, CTA_TUPLE_REPLY, u3, &zone); if (err < 0) return err; } if (cda[CTA_TUPLE_ORIG]) h = nf_conntrack_find_get(info->net, &zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) h = nf_conntrack_find_get(info->net, &zone, &rtuple); if (h == NULL) { err = -ENOENT; if (info->nlh->nlmsg_flags & NLM_F_CREATE) { enum ip_conntrack_events events; if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) return -EINVAL; if (otuple.dst.protonum != rtuple.dst.protonum) return -EINVAL; ct = ctnetlink_create_conntrack(info->net, &zone, cda, &otuple, &rtuple, u3); if (IS_ERR(ct)) return PTR_ERR(ct); err = 0; if (test_bit(IPS_EXPECTED_BIT, &ct->status)) events = 1 << IPCT_RELATED; else events = 1 << IPCT_NEW; if (cda[CTA_LABELS] && ctnetlink_attach_labels(ct, cda) == 0) events |= (1 << IPCT_LABEL); nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_PROTOINFO) | (1 << IPCT_SEQADJ) | (1 << IPCT_MARK) | (1 << IPCT_SYNPROXY) | events, ct, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); nf_ct_put(ct); } return err; } /* implicit 'else' */ err = -EEXIST; ct = nf_ct_tuplehash_to_ctrack(h); if (!(info->nlh->nlmsg_flags & NLM_F_EXCL)) { err = ctnetlink_change_conntrack(ct, cda); if (err == 0) { nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_LABEL) | (1 << IPCT_PROTOINFO) | (1 << IPCT_SEQADJ) | (1 << IPCT_MARK) | (1 << IPCT_SYNPROXY), ct, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } } nf_ct_put(ct); return err; } static int ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, __u16 cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS_CPU); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, htons(cpu)); if (!nlh) goto nlmsg_failure; if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || nla_put_be32(skb, CTA_STATS_INSERT_FAILED, htonl(st->insert_failed)) || nla_put_be32(skb, CTA_STATS_DROP, htonl(st->drop)) || nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) || nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) || nla_put_be32(skb, CTA_STATS_SEARCH_RESTART, htonl(st->search_restart)) || nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE, htonl(st->clash_resolve)) || nla_put_be32(skb, CTA_STATS_CHAIN_TOOLONG, htonl(st->chaintoolong))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) { int cpu; struct net *net = sock_net(skb->sk); if (cb->args[0] == nr_cpu_ids) return 0; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { const struct ip_conntrack_stat *st; if (!cpu_possible(cpu)) continue; st = per_cpu_ptr(net->ct.stat, cpu); if (ctnetlink_ct_stat_cpu_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; } cb->args[0] = cpu; return skb->len; } static int ctnetlink_stat_ct_cpu(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_ct_stat_cpu_dump, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return 0; } static int ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct net *net) { unsigned int flags = portid ? NLM_F_MULTI : 0, event; unsigned int nr_conntracks; struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; nr_conntracks = nf_conntrack_count(net); if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks))) goto nla_put_failure; if (nla_put_be32(skb, CTA_STATS_GLOBAL_MAX_ENTRIES, htonl(nf_conntrack_max))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_stat_ct(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { struct sk_buff *skb2; int err; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) return -ENOMEM; err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), sock_net(skb->sk)); if (err <= 0) { kfree_skb(skb2); return -ENOMEM; } return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { [CTA_EXPECT_MASTER] = { .type = NLA_NESTED }, [CTA_EXPECT_TUPLE] = { .type = NLA_NESTED }, [CTA_EXPECT_MASK] = { .type = NLA_NESTED }, [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, [CTA_EXPECT_ID] = { .type = NLA_U32 }, [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, }; static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, struct nf_conntrack_helper *helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask); #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT static size_t ctnetlink_glue_build_size(const struct nf_conn *ct) { return 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + nla_total_size(0) /* CTA_PROTOINFO */ + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) + ctnetlink_acct_size(ct) + ctnetlink_timestamp_size(ct) #if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif #ifdef CONFIG_NF_CONNTRACK_MARK + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif #ifdef CONFIG_NF_CONNTRACK_ZONES + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE|CTA_TUPLE_ZONE */ #endif + ctnetlink_proto_size(ct) ; } static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_status(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_timeout(skb, ct, false) < 0) goto nla_put_failure; if (ctnetlink_dump_protoinfo(skb, ct, false) < 0) goto nla_put_failure; if (ctnetlink_dump_acct(skb, ct, IPCTNL_MSG_CT_GET) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_helpinfo(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_SECMARK if (ct->secmark && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif if (ct->master && ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; if ((ct->status & IPS_SEQ_ADJUST) && ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_ct_synproxy(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK if (ctnetlink_dump_mark(skb, ct, true) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static int ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, u_int16_t ct_attr, u_int16_t ct_info_attr) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, ct_attr); if (!nest_parms) goto nla_put_failure; if (__ctnetlink_glue_build(skb, ct) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (nla_put_be32(skb, ct_info_attr, htonl(ctinfo))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static int ctnetlink_update_status(struct nf_conn *ct, const struct nlattr * const cda[]) { unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS])); unsigned long d = ct->status ^ status; if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY)) /* SEEN_REPLY bit can only be set */ return -EBUSY; if (d & IPS_ASSURED && !(status & IPS_ASSURED)) /* ASSURED bit can only be set */ return -EBUSY; /* This check is less strict than ctnetlink_change_status() * because callers often flip IPS_EXPECTED bits when sending * an NFQA_CT attribute to the kernel. So ignore the * unchangeable bits but do not error out. Also user programs * are allowed to clear the bits that they are allowed to change. */ __ctnetlink_change_status(ct, status, ~status); return 0; } static int ctnetlink_glue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) { int err; if (cda[CTA_TIMEOUT]) { err = ctnetlink_change_timeout(ct, cda); if (err < 0) return err; } if (cda[CTA_STATUS]) { err = ctnetlink_update_status(ct, cda); if (err < 0) return err; } if (cda[CTA_HELP]) { err = ctnetlink_change_helper(ct, cda); if (err < 0) return err; } if (cda[CTA_LABELS]) { err = ctnetlink_attach_labels(ct, cda); if (err < 0) return err; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) { ctnetlink_change_mark(ct, cda); } #endif return 0; } static int ctnetlink_glue_parse(const struct nlattr *attr, struct nf_conn *ct) { struct nlattr *cda[CTA_MAX+1]; int ret; ret = nla_parse_nested_deprecated(cda, CTA_MAX, attr, ct_nla_policy, NULL); if (ret < 0) return ret; return ctnetlink_glue_parse_ct((const struct nlattr **)cda, ct); } static int ctnetlink_glue_exp_parse(const struct nlattr * const *cda, const struct nf_conn *ct, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { int err; err = ctnetlink_parse_tuple(cda, tuple, CTA_EXPECT_TUPLE, nf_ct_l3num(ct), NULL); if (err < 0) return err; return ctnetlink_parse_tuple(cda, mask, CTA_EXPECT_MASK, nf_ct_l3num(ct), NULL); } static int ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report) { struct nlattr *cda[CTA_EXPECT_MAX+1]; struct nf_conntrack_tuple tuple, mask; struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; int err; err = nla_parse_nested_deprecated(cda, CTA_EXPECT_MAX, attr, exp_nla_policy, NULL); if (err < 0) return err; err = ctnetlink_glue_exp_parse((const struct nlattr * const *)cda, ct, &tuple, &mask); if (err < 0) return err; if (cda[CTA_EXPECT_HELP_NAME]) { const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) return -EOPNOTSUPP; } exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct, helper, &tuple, &mask); if (IS_ERR(exp)) return PTR_ERR(exp); err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); return err; } static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int diff) { if (!(ct->status & IPS_NAT_MASK)) return; nf_ct_tcp_seqadj_set(skb, ct, ctinfo, diff); } static const struct nfnl_ct_hook ctnetlink_glue_hook = { .build_size = ctnetlink_glue_build_size, .build = ctnetlink_glue_build, .parse = ctnetlink_glue_parse, .attach_expect = ctnetlink_glue_attach_expect, .seq_adjust = ctnetlink_glue_seqadj, }; #endif /* CONFIG_NETFILTER_NETLINK_GLUE_CT */ /*********************************************************************** * EXPECT ***********************************************************************/ static int ctnetlink_exp_dump_tuple(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, u32 type) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, type); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, tuple) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_exp_dump_mask(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple_mask *mask) { const struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple m; struct nlattr *nest_parms; int ret; memset(&m, 0xFF, sizeof(m)); memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3)); m.src.u.all = mask->src.u.all; m.src.l3num = tuple->src.l3num; m.dst.protonum = tuple->dst.protonum; nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK); if (!nest_parms) goto nla_put_failure; rcu_read_lock(); ret = ctnetlink_dump_tuples_ip(skb, &m); if (ret >= 0) { l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto); } rcu_read_unlock(); if (unlikely(ret < 0)) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } #if IS_ENABLED(CONFIG_NF_NAT) static const union nf_inet_addr any_addr; #endif static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { static __read_mostly siphash_key_t exp_id_seed; unsigned long a, b, c, d; net_get_random_once(&exp_id_seed, sizeof(exp_id_seed)); a = (unsigned long)exp; b = (unsigned long)exp->helper; c = (unsigned long)exp->master; d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed); #ifdef CONFIG_64BIT return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed); #else return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed); #endif } static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) { struct nf_conn *master = exp->master; long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ; struct nf_conn_help *help; #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *nest_parms; struct nf_conntrack_tuple nat_tuple = {}; #endif struct nf_ct_helper_expectfn *expfn; if (timeout < 0) timeout = 0; if (ctnetlink_exp_dump_tuple(skb, &exp->tuple, CTA_EXPECT_TUPLE) < 0) goto nla_put_failure; if (ctnetlink_exp_dump_mask(skb, &exp->tuple, &exp->mask) < 0) goto nla_put_failure; if (ctnetlink_exp_dump_tuple(skb, &master->tuplehash[IP_CT_DIR_ORIGINAL].tuple, CTA_EXPECT_MASTER) < 0) goto nla_put_failure; #if IS_ENABLED(CONFIG_NF_NAT) if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) || exp->saved_proto.all) { nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_EXPECT_NAT_DIR, htonl(exp->dir))) goto nla_put_failure; nat_tuple.src.l3num = nf_ct_l3num(master); nat_tuple.src.u3 = exp->saved_addr; nat_tuple.dst.protonum = nf_ct_protonum(master); nat_tuple.src.u = exp->saved_proto; if (ctnetlink_exp_dump_tuple(skb, &nat_tuple, CTA_EXPECT_NAT_TUPLE) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); } #endif if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) || nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) || nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) goto nla_put_failure; help = nfct_help(master); if (help) { struct nf_conntrack_helper *helper; helper = rcu_dereference(help->helper); if (helper && nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name)) goto nla_put_failure; } expfn = nf_ct_helper_expectfn_find_by_symbol(exp->expectfn); if (expfn != NULL && nla_put_string(skb, CTA_EXPECT_FN, expfn->name)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int event, const struct nf_conntrack_expect *exp) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, exp->tuple.src.l3num, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } #ifdef CONFIG_NF_CONNTRACK_EVENTS static int ctnetlink_expect_event(unsigned int events, const struct nf_exp_event *item) { struct nf_conntrack_expect *exp = item->exp; struct net *net = nf_ct_exp_net(exp); struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int type, group; int flags = 0; if (events & (1 << IPEXP_DESTROY)) { type = IPCTNL_MSG_EXP_DELETE; group = NFNLGRP_CONNTRACK_EXP_DESTROY; } else if (events & (1 << IPEXP_NEW)) { type = IPCTNL_MSG_EXP_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_EXP_NEW; } else return 0; if (!item->report && !nfnetlink_has_listeners(net, group)) return 0; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (skb == NULL) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, type); nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, exp->tuple.src.l3num, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); nlmsg_failure: kfree_skb(skb); errout: nfnetlink_set_err(net, 0, 0, -ENOBUFS); return 0; } #endif static int ctnetlink_exp_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]); return 0; } static int ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]], hnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (!net_eq(nf_ct_net(exp->master), net)) continue; if (cb->args[1]) { if (exp != last) continue; cb->args[1] = 0; } if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } } out: rcu_read_unlock(); if (last) nf_ct_expect_put(last); return skb->len; } static int ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nf_conn *ct = cb->data; struct nf_conn_help *help = nfct_help(ct); u_int8_t l3proto = nfmsg->nfgen_family; if (cb->args[0]) return 0; rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; restart: hlist_for_each_entry_rcu(exp, &help->expectations, lnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (cb->args[1]) { if (exp != last) continue; cb->args[1] = 0; } if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } cb->args[0] = 1; out: rcu_read_unlock(); if (last) nf_ct_expect_put(last); return skb->len; } static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { int err; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conntrack_zone zone; struct netlink_dump_control c = { .dump = ctnetlink_exp_ct_dump_table, .done = ctnetlink_exp_done, }; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; h = nf_conntrack_find_get(net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); /* No expectation linked to this connection tracking. */ if (!nfct_help(ct)) { nf_ct_put(ct); return 0; } c.data = ct; err = netlink_dump_start(ctnl, skb, nlh, &c); nf_ct_put(ct); return err; } static int ctnetlink_get_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; struct sk_buff *skb2; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { if (cda[CTA_EXPECT_MASTER]) return ctnetlink_dump_exp_ct(info->net, info->sk, skb, info->nlh, cda, info->extack); else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, .done = ctnetlink_exp_done, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } } err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; if (cda[CTA_EXPECT_TUPLE]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); else if (cda[CTA_EXPECT_MASTER]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3, NULL); else return -EINVAL; if (err < 0) return err; exp = nf_ct_expect_find_get(info->net, &zone, &tuple); if (!exp) return -ENOENT; if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } } skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb2) { nf_ct_expect_put(exp); return -ENOMEM; } rcu_read_lock(); err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); rcu_read_unlock(); nf_ct_expect_put(exp); if (err <= 0) { kfree_skb(skb2); return -ENOMEM; } return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data) { const struct nf_conn_help *m_help; const char *name = data; m_help = nfct_help(exp->master); return strcmp(m_help->helper->name, name) == 0; } static bool expect_iter_all(struct nf_conntrack_expect *exp, void *data) { return true; } static int ctnetlink_del_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; int err; if (cda[CTA_EXPECT_TUPLE]) { /* delete a single expect by tuple */ err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; /* bump usage count to 2 */ exp = nf_ct_expect_find_get(info->net, &zone, &tuple); if (!exp) return -ENOENT; if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } } /* after list removal, usage count == 1 */ spin_lock_bh(&nf_conntrack_expect_lock); if (del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); nf_ct_expect_put(exp); } spin_unlock_bh(&nf_conntrack_expect_lock); /* have to put what we 'get' above. * after this line usage count == 0 */ nf_ct_expect_put(exp); } else if (cda[CTA_EXPECT_HELP_NAME]) { char *name = nla_data(cda[CTA_EXPECT_HELP_NAME]); nf_ct_expect_iterate_net(info->net, expect_iter_name, name, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } else { /* This basically means we have to flush everything*/ nf_ct_expect_iterate_net(info->net, expect_iter_all, NULL, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } return 0; } static int ctnetlink_change_expect(struct nf_conntrack_expect *x, const struct nlattr * const cda[]) { if (cda[CTA_EXPECT_TIMEOUT]) { if (!del_timer(&x->timeout)) return -ETIME; x->timeout.expires = jiffies + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ; add_timer(&x->timeout); } return 0; } #if IS_ENABLED(CONFIG_NF_NAT) static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, }; #endif static int ctnetlink_parse_expect_nat(const struct nlattr *attr, struct nf_conntrack_expect *exp, u_int8_t u3) { #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *tb[CTA_EXPECT_NAT_MAX+1]; struct nf_conntrack_tuple nat_tuple = {}; int err; err = nla_parse_nested_deprecated(tb, CTA_EXPECT_NAT_MAX, attr, exp_nat_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_EXPECT_NAT_DIR] || !tb[CTA_EXPECT_NAT_TUPLE]) return -EINVAL; err = ctnetlink_parse_tuple((const struct nlattr * const *)tb, &nat_tuple, CTA_EXPECT_NAT_TUPLE, u3, NULL); if (err < 0) return err; exp->saved_addr = nat_tuple.src.u3; exp->saved_proto = nat_tuple.src.u; exp->dir = ntohl(nla_get_be32(tb[CTA_EXPECT_NAT_DIR])); return 0; #else return -EOPNOTSUPP; #endif } static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, struct nf_conntrack_helper *helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { u_int32_t class = 0; struct nf_conntrack_expect *exp; struct nf_conn_help *help; int err; help = nfct_help(ct); if (!help) return ERR_PTR(-EOPNOTSUPP); if (cda[CTA_EXPECT_CLASS] && helper) { class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS])); if (class > helper->expect_class_max) return ERR_PTR(-EINVAL); } exp = nf_ct_expect_alloc(ct); if (!exp) return ERR_PTR(-ENOMEM); if (cda[CTA_EXPECT_FLAGS]) { exp->flags = ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS])); exp->flags &= ~NF_CT_EXPECT_USERSPACE; } else { exp->flags = 0; } if (cda[CTA_EXPECT_FN]) { const char *name = nla_data(cda[CTA_EXPECT_FN]); struct nf_ct_helper_expectfn *expfn; expfn = nf_ct_helper_expectfn_find_by_name(name); if (expfn == NULL) { err = -EINVAL; goto err_out; } exp->expectfn = expfn->expectfn; } else exp->expectfn = NULL; exp->class = class; exp->master = ct; exp->helper = helper; exp->tuple = *tuple; exp->mask.src.u3 = mask->src.u3; exp->mask.src.u.all = mask->src.u.all; if (cda[CTA_EXPECT_NAT]) { err = ctnetlink_parse_expect_nat(cda[CTA_EXPECT_NAT], exp, nf_ct_l3num(ct)); if (err < 0) goto err_out; } return exp; err_out: nf_ct_expect_put(exp); return ERR_PTR(err); } static int ctnetlink_create_expect(struct net *net, const struct nf_conntrack_zone *zone, const struct nlattr * const cda[], u_int8_t u3, u32 portid, int report) { struct nf_conntrack_tuple tuple, mask, master_tuple; struct nf_conntrack_tuple_hash *h = NULL; struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; struct nf_conn *ct; int err; /* caller guarantees that those three CTA_EXPECT_* exist */ err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3, NULL); if (err < 0) return err; /* Look for master conntrack of this expectation */ h = nf_conntrack_find_get(net, zone, &master_tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); rcu_read_lock(); if (cda[CTA_EXPECT_HELP_NAME]) { const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); helper = __nf_conntrack_helper_find(helpname, u3, nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { err = -EOPNOTSUPP; goto err_ct; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, u3, nf_ct_protonum(ct)); if (helper) { err = -EAGAIN; goto err_rcu; } rcu_read_unlock(); #endif err = -EOPNOTSUPP; goto err_ct; } } exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto err_rcu; } err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); err_rcu: rcu_read_unlock(); err_ct: nf_ct_put(ct); return err; } static int ctnetlink_new_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; int err; if (!cda[CTA_EXPECT_TUPLE] || !cda[CTA_EXPECT_MASK] || !cda[CTA_EXPECT_MASTER]) return -EINVAL; err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; spin_lock_bh(&nf_conntrack_expect_lock); exp = __nf_ct_expect_find(info->net, &zone, &tuple); if (!exp) { spin_unlock_bh(&nf_conntrack_expect_lock); err = -ENOENT; if (info->nlh->nlmsg_flags & NLM_F_CREATE) { err = ctnetlink_create_expect(info->net, &zone, cda, u3, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } return err; } err = -EEXIST; if (!(info->nlh->nlmsg_flags & NLM_F_EXCL)) err = ctnetlink_change_expect(exp, cda); spin_unlock_bh(&nf_conntrack_expect_lock); return err; } static int ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_EXP_GET_STATS_CPU); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, htons(cpu)); if (!nlh) goto nlmsg_failure; if (nla_put_be32(skb, CTA_STATS_EXP_NEW, htonl(st->expect_new)) || nla_put_be32(skb, CTA_STATS_EXP_CREATE, htonl(st->expect_create)) || nla_put_be32(skb, CTA_STATS_EXP_DELETE, htonl(st->expect_delete))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) { int cpu; struct net *net = sock_net(skb->sk); if (cb->args[0] == nr_cpu_ids) return 0; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { const struct ip_conntrack_stat *st; if (!cpu_possible(cpu)) continue; st = per_cpu_ptr(net->ct.stat, cpu); if (ctnetlink_exp_stat_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; } cb->args[0] = cpu; return skb->len; } static int ctnetlink_stat_exp_cpu(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_exp_stat_cpu_dump, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return 0; } #ifdef CONFIG_NF_CONNTRACK_EVENTS static struct nf_ct_event_notifier ctnl_notifier = { .ct_event = ctnetlink_conntrack_event, .exp_event = ctnetlink_expect_event, }; #endif static const struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = { [IPCTNL_MSG_CT_NEW] = { .call = ctnetlink_new_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET] = { .call = ctnetlink_get_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_DELETE] = { .call = ctnetlink_del_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET_CTRZERO] = { .call = ctnetlink_get_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET_STATS_CPU] = { .call = ctnetlink_stat_ct_cpu, .type = NFNL_CB_MUTEX, }, [IPCTNL_MSG_CT_GET_STATS] = { .call = ctnetlink_stat_ct, .type = NFNL_CB_MUTEX, }, [IPCTNL_MSG_CT_GET_DYING] = { .call = ctnetlink_get_ct_dying, .type = NFNL_CB_MUTEX, }, [IPCTNL_MSG_CT_GET_UNCONFIRMED] = { .call = ctnetlink_get_ct_unconfirmed, .type = NFNL_CB_MUTEX, }, }; static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { [IPCTNL_MSG_EXP_GET] = { .call = ctnetlink_get_expect, .type = NFNL_CB_MUTEX, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_NEW] = { .call = ctnetlink_new_expect, .type = NFNL_CB_MUTEX, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_DELETE] = { .call = ctnetlink_del_expect, .type = NFNL_CB_MUTEX, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_GET_STATS_CPU] = { .call = ctnetlink_stat_exp_cpu, .type = NFNL_CB_MUTEX, }, }; static const struct nfnetlink_subsystem ctnl_subsys = { .name = "conntrack", .subsys_id = NFNL_SUBSYS_CTNETLINK, .cb_count = IPCTNL_MSG_MAX, .cb = ctnl_cb, }; static const struct nfnetlink_subsystem ctnl_exp_subsys = { .name = "conntrack_expect", .subsys_id = NFNL_SUBSYS_CTNETLINK_EXP, .cb_count = IPCTNL_MSG_EXP_MAX, .cb = ctnl_exp_cb, }; MODULE_ALIAS("ip_conntrack_netlink"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __net_init ctnetlink_net_init(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_EVENTS nf_conntrack_register_notifier(net, &ctnl_notifier); #endif return 0; } static void ctnetlink_net_pre_exit(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_EVENTS nf_conntrack_unregister_notifier(net); #endif } static struct pernet_operations ctnetlink_net_ops = { .init = ctnetlink_net_init, .pre_exit = ctnetlink_net_pre_exit, }; static int __init ctnetlink_init(void) { int ret; ret = nfnetlink_subsys_register(&ctnl_subsys); if (ret < 0) { pr_err("ctnetlink_init: cannot register with nfnetlink.\n"); goto err_out; } ret = nfnetlink_subsys_register(&ctnl_exp_subsys); if (ret < 0) { pr_err("ctnetlink_init: cannot register exp with nfnetlink.\n"); goto err_unreg_subsys; } ret = register_pernet_subsys(&ctnetlink_net_ops); if (ret < 0) { pr_err("ctnetlink_init: cannot register pernet operations\n"); goto err_unreg_exp_subsys; } #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT /* setup interaction between nf_queue and nf_conntrack_netlink. */ RCU_INIT_POINTER(nfnl_ct_hook, &ctnetlink_glue_hook); #endif return 0; err_unreg_exp_subsys: nfnetlink_subsys_unregister(&ctnl_exp_subsys); err_unreg_subsys: nfnetlink_subsys_unregister(&ctnl_subsys); err_out: return ret; } static void __exit ctnetlink_exit(void) { unregister_pernet_subsys(&ctnetlink_net_ops); nfnetlink_subsys_unregister(&ctnl_exp_subsys); nfnetlink_subsys_unregister(&ctnl_subsys); #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT RCU_INIT_POINTER(nfnl_ct_hook, NULL); #endif synchronize_rcu(); } module_init(ctnetlink_init); module_exit(ctnetlink_exit); |
| 15 15 159 158 209 97 96 94 96 97 97 96 97 97 186 186 159 159 159 159 179 186 1 4 4 186 25 186 178 179 182 14 7 7 178 21 182 186 181 181 179 179 7 29 29 29 186 25 25 26 25 21 22 15 15 21 21 186 180 29 29 29 29 185 186 186 186 21 21 21 21 21 21 21 21 21 21 21 21 21 21 21 21 12 10 21 21 21 2 21 21 21 21 8 8 21 21 21 8 14 17 1 17 14 8 17 21 21 21 8 21 21 21 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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) 2001-2003 Intel Corp. * * This file is part of the SCTP kernel implementation * * These functions implement the sctp_outq class. The outqueue handles * bundling and queueing of outgoing SCTP chunks. * * 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> * Perry Melange <pmelange@null.cc.uic.edu> * Xingang Guo <xingang.guo@intel.com> * Hui Huang <hui.huang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Jon Grimm <jgrimm@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/list.h> /* For struct list_head */ #include <linux/socket.h> #include <linux/ip.h> #include <linux/slab.h> #include <net/sock.h> /* For skb_set_owner_w */ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> #include <trace/events/sctp.h> /* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); static void sctp_check_transmitted(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, union sctp_addr *saddr, struct sctp_sackhdr *sack, __u32 *highest_new_tsn); static void sctp_mark_missing(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, __u32 highest_new_tsn, int count_of_newacks); static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp); /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, struct sctp_chunk *ch) { struct sctp_stream_out_ext *oute; __u16 stream; list_add(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add(&ch->stream_list, &oute->outq); } /* Take data from the front of the queue. */ static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q) { return q->sched->dequeue(q); } /* Add data chunk to the end of the queue. */ static inline void sctp_outq_tail_data(struct sctp_outq *q, struct sctp_chunk *ch) { struct sctp_stream_out_ext *oute; __u16 stream; list_add_tail(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add_tail(&ch->stream_list, &oute->outq); } /* * SFR-CACC algorithm: * D) If count_of_newacks is greater than or equal to 2 * and t was not sent to the current primary then the * sender MUST NOT increment missing report count for t. */ static inline int sctp_cacc_skip_3_1_d(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks) { if (count_of_newacks >= 2 && transport != primary) return 1; return 0; } /* * SFR-CACC algorithm: * F) If count_of_newacks is less than 2, let d be the * destination to which t was sent. If cacc_saw_newack * is 0 for destination d, then the sender MUST NOT * increment missing report count for t. */ static inline int sctp_cacc_skip_3_1_f(struct sctp_transport *transport, int count_of_newacks) { if (count_of_newacks < 2 && (transport && !transport->cacc.cacc_saw_newack)) return 1; return 0; } /* * SFR-CACC algorithm: * 3.1) If CYCLING_CHANGEOVER is 0, the sender SHOULD * execute steps C, D, F. * * C has been implemented in sctp_outq_sack */ static inline int sctp_cacc_skip_3_1(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks) { if (!primary->cacc.cycling_changeover) { if (sctp_cacc_skip_3_1_d(primary, transport, count_of_newacks)) return 1; if (sctp_cacc_skip_3_1_f(transport, count_of_newacks)) return 1; return 0; } return 0; } /* * SFR-CACC algorithm: * 3.2) Else if CYCLING_CHANGEOVER is 1, and t is less * than next_tsn_at_change of the current primary, then * the sender MUST NOT increment missing report count * for t. */ static inline int sctp_cacc_skip_3_2(struct sctp_transport *primary, __u32 tsn) { if (primary->cacc.cycling_changeover && TSN_lt(tsn, primary->cacc.next_tsn_at_change)) return 1; return 0; } /* * SFR-CACC algorithm: * 3) If the missing report count for TSN t is to be * incremented according to [RFC2960] and * [SCTP_STEWART-2002], and CHANGEOVER_ACTIVE is set, * then the sender MUST further execute steps 3.1 and * 3.2 to determine if the missing report count for * TSN t SHOULD NOT be incremented. * * 3.3) If 3.1 and 3.2 do not dictate that the missing * report count for t should not be incremented, then * the sender SHOULD increment missing report count for * t (according to [RFC2960] and [SCTP_STEWART_2002]). */ static inline int sctp_cacc_skip(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks, __u32 tsn) { if (primary->cacc.changeover_active && (sctp_cacc_skip_3_1(primary, transport, count_of_newacks) || sctp_cacc_skip_3_2(primary, tsn))) return 1; return 0; } /* Initialize an existing sctp_outq. This does the boring stuff. * You still need to define handlers if you really want to DO * something with this structure... */ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) { memset(q, 0, sizeof(struct sctp_outq)); q->asoc = asoc; INIT_LIST_HEAD(&q->out_chunk_list); INIT_LIST_HEAD(&q->control_chunk_list); INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); sctp_sched_set_sched(asoc, sctp_sk(asoc->base.sk)->default_ss); } /* Free the outqueue structure and any related pending chunks. */ static void __sctp_outq_teardown(struct sctp_outq *q) { struct sctp_transport *transport; struct list_head *lchunk, *temp; struct sctp_chunk *chunk, *tmp; /* Throw away unacknowledged chunks. */ list_for_each_entry(transport, &q->asoc->peer.transport_addr_list, transports) { while ((lchunk = sctp_list_dequeue(&transport->transmitted)) != NULL) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); /* Mark as part of a failed message. */ sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } } /* Throw away chunks that have been gap ACKed. */ list_for_each_safe(lchunk, temp, &q->sacked) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any chunks in the retransmit queue. */ list_for_each_safe(lchunk, temp, &q->retransmit) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any chunks that are in the abandoned queue. */ list_for_each_safe(lchunk, temp, &q->abandoned) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any leftover data chunks. */ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { sctp_sched_dequeue_done(q, chunk); /* Mark as send failure. */ sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any leftover control chunks. */ list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { list_del_init(&chunk->list); sctp_chunk_free(chunk); } } void sctp_outq_teardown(struct sctp_outq *q) { __sctp_outq_teardown(q); sctp_outq_init(q->asoc, q); } /* Free the outqueue structure and any related pending chunks. */ void sctp_outq_free(struct sctp_outq *q) { /* Throw away leftover chunks. */ __sctp_outq_teardown(q); } /* Put a new chunk in an sctp_outq. */ void sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp) { struct net *net = q->asoc->base.net; pr_debug("%s: outq:%p, chunk:%p[%s]\n", __func__, q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk"); /* If it is data, queue it up, otherwise, send it * immediately. */ if (sctp_chunk_is_data(chunk)) { pr_debug("%s: outqueueing: outq:%p, chunk:%p[%s])\n", __func__, q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk"); sctp_outq_tail_data(q, chunk); if (chunk->asoc->peer.prsctp_capable && SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) chunk->asoc->sent_cnt_removable++; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS); else SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS); } else { list_add_tail(&chunk->list, &q->control_chunk_list); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); } if (!q->cork) sctp_outq_flush(q, 0, gfp); } /* Insert a chunk into the sorted list based on the TSNs. The retransmit list * and the abandoned list are in ascending order. */ static void sctp_insert_list(struct list_head *head, struct list_head *new) { struct list_head *pos; struct sctp_chunk *nchunk, *lchunk; __u32 ntsn, ltsn; int done = 0; nchunk = list_entry(new, struct sctp_chunk, transmitted_list); ntsn = ntohl(nchunk->subh.data_hdr->tsn); list_for_each(pos, head) { lchunk = list_entry(pos, struct sctp_chunk, transmitted_list); ltsn = ntohl(lchunk->subh.data_hdr->tsn); if (TSN_lt(ntsn, ltsn)) { list_add(new, pos->prev); done = 1; break; } } if (!done) list_add_tail(new, head); } static int sctp_prsctp_prune_sent(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, struct list_head *queue, int msg_len) { struct sctp_chunk *chk, *temp; list_for_each_entry_safe(chk, temp, queue, transmitted_list) { struct sctp_stream_out *streamout; if (!chk->msg->abandoned && (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; chk->msg->abandoned = 1; list_del_init(&chk->transmitted_list); sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); streamout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; if (queue != &asoc->outqueue.retransmit && !chk->tsn_gap_acked) { if (chk->transport) chk->transport->flight_size -= sctp_data_size(chk); asoc->outqueue.outstanding_bytes -= sctp_data_size(chk); } msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); if (msg_len <= 0) break; } return msg_len; } static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len) { struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; struct sctp_stream_out *sout; q->sched->unsched_all(&asoc->stream); list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { if (!chk->msg->abandoned && (!(chk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG) || !SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; chk->msg->abandoned = 1; sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; sout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); sout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; /* clear out_curr if all frag chunks are pruned */ if (asoc->stream.out_curr == sout && list_is_last(&chk->frag_list, &chk->msg->chunks)) asoc->stream.out_curr = NULL; msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); sctp_chunk_free(chk); if (msg_len <= 0) break; } q->sched->sched_all(&asoc->stream); return msg_len; } /* Abandon the chunks according their priorities */ void sctp_prsctp_prune(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len) { struct sctp_transport *transport; if (!asoc->peer.prsctp_capable || !asoc->sent_cnt_removable) return; msg_len = sctp_prsctp_prune_sent(asoc, sinfo, &asoc->outqueue.retransmit, msg_len); if (msg_len <= 0) return; list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { msg_len = sctp_prsctp_prune_sent(asoc, sinfo, &transport->transmitted, msg_len); if (msg_len <= 0) return; } sctp_prsctp_prune_unsent(asoc, sinfo, msg_len); } /* Mark all the eligible packets on a transport for retransmission. */ void sctp_retransmit_mark(struct sctp_outq *q, struct sctp_transport *transport, __u8 reason) { struct list_head *lchunk, *ltemp; struct sctp_chunk *chunk; /* Walk through the specified transmitted queue. */ list_for_each_safe(lchunk, ltemp, &transport->transmitted) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); /* If the chunk is abandoned, move it to abandoned list. */ if (sctp_chunk_abandoned(chunk)) { list_del_init(lchunk); sctp_insert_list(&q->abandoned, lchunk); /* If this chunk has not been previousely acked, * stop considering it 'outstanding'. Our peer * will most likely never see it since it will * not be retransmitted */ if (!chunk->tsn_gap_acked) { if (chunk->transport) chunk->transport->flight_size -= sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); q->asoc->peer.rwnd += sctp_data_size(chunk); } continue; } /* If we are doing retransmission due to a timeout or pmtu * discovery, only the chunks that are not yet acked should * be added to the retransmit queue. */ if ((reason == SCTP_RTXR_FAST_RTX && (chunk->fast_retransmit == SCTP_NEED_FRTX)) || (reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) { /* RFC 2960 6.2.1 Processing a Received SACK * * C) Any time a DATA chunk is marked for * retransmission (via either T3-rtx timer expiration * (Section 6.3.3) or via fast retransmit * (Section 7.2.4)), add the data size of those * chunks to the rwnd. */ q->asoc->peer.rwnd += sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); if (chunk->transport) transport->flight_size -= sctp_data_size(chunk); /* sctpimpguide-05 Section 2.8.2 * M5) If a T3-rtx timer expires, the * 'TSN.Missing.Report' of all affected TSNs is set * to 0. */ chunk->tsn_missing_report = 0; /* If a chunk that is being used for RTT measurement * has to be retransmitted, we cannot use this chunk * anymore for RTT measurements. Reset rto_pending so * that a new RTT measurement is started when a new * data chunk is sent. */ if (chunk->rtt_in_progress) { chunk->rtt_in_progress = 0; transport->rto_pending = 0; } /* Move the chunk to the retransmit queue. The chunks * on the retransmit queue are always kept in order. */ list_del_init(lchunk); sctp_insert_list(&q->retransmit, lchunk); } } pr_debug("%s: transport:%p, reason:%d, cwnd:%d, ssthresh:%d, " "flight_size:%d, pba:%d\n", __func__, transport, reason, transport->cwnd, transport->ssthresh, transport->flight_size, transport->partial_bytes_acked); } /* Mark all the eligible packets on a transport for retransmission and force * one packet out. */ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, enum sctp_retransmit_reason reason) { struct net *net = q->asoc->base.net; switch (reason) { case SCTP_RTXR_T3_RTX: SCTP_INC_STATS(net, SCTP_MIB_T3_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_T3_RTX); /* Update the retran path if the T3-rtx timer has expired for * the current retran path. */ if (transport == transport->asoc->peer.retran_path) sctp_assoc_update_retran_path(transport->asoc); transport->asoc->rtx_data_chunks += transport->asoc->unack_data; break; case SCTP_RTXR_FAST_RTX: SCTP_INC_STATS(net, SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); q->fast_rtx = 1; break; case SCTP_RTXR_PMTUD: SCTP_INC_STATS(net, SCTP_MIB_PMTUD_RETRANSMITS); break; case SCTP_RTXR_T1_RTX: SCTP_INC_STATS(net, SCTP_MIB_T1_RETRANSMITS); transport->asoc->init_retries++; break; default: BUG(); } sctp_retransmit_mark(q, transport, reason); /* PR-SCTP A5) Any time the T3-rtx timer expires, on any destination, * the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by * following the procedures outlined in C1 - C5. */ if (reason == SCTP_RTXR_T3_RTX) q->asoc->stream.si->generate_ftsn(q, q->asoc->ctsn_ack_point); /* Flush the queues only on timeout, since fast_rtx is only * triggered during sack processing and the queue * will be flushed at the end. */ if (reason != SCTP_RTXR_FAST_RTX) sctp_outq_flush(q, /* rtx_timeout */ 1, GFP_ATOMIC); } /* * Transmit DATA chunks on the retransmit queue. Upon return from * __sctp_outq_flush_rtx() the packet 'pkt' may contain chunks which * need to be transmitted by the caller. * We assume that pkt->transport has already been set. * * The return value is a normal kernel error return value. */ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, int rtx_timeout, int *start_timer, gfp_t gfp) { struct sctp_transport *transport = pkt->transport; struct sctp_chunk *chunk, *chunk1; struct list_head *lqueue; enum sctp_xmit status; int error = 0; int timer = 0; int done = 0; int fast_rtx; lqueue = &q->retransmit; fast_rtx = q->fast_rtx; /* This loop handles time-out retransmissions, fast retransmissions, * and retransmissions due to opening of whindow. * * RFC 2960 6.3.3 Handle T3-rtx Expiration * * 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. * * [Just to be painfully clear, if we are retransmitting * because a timeout just happened, we should send only ONE * packet of retransmitted data.] * * For fast retransmissions we also send only ONE packet. However, * if we are just flushing the queue due to open window, we'll * try to send as much as possible. */ list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) { /* If the chunk is abandoned, move it to abandoned list. */ if (sctp_chunk_abandoned(chunk)) { list_del_init(&chunk->transmitted_list); sctp_insert_list(&q->abandoned, &chunk->transmitted_list); continue; } /* Make sure that Gap Acked TSNs are not retransmitted. A * simple approach is just to move such TSNs out of the * way and into a 'transmitted' queue and skip to the * next chunk. */ if (chunk->tsn_gap_acked) { list_move_tail(&chunk->transmitted_list, &transport->transmitted); continue; } /* If we are doing fast retransmit, ignore non-fast_rtransmit * chunks */ if (fast_rtx && !chunk->fast_retransmit) continue; redo: /* Attempt to append this chunk to the packet. */ status = sctp_packet_append_chunk(pkt, chunk); switch (status) { case SCTP_XMIT_PMTU_FULL: if (!pkt->has_data && !pkt->has_cookie_echo) { /* If this packet did not contain DATA then * retransmission did not happen, so do it * again. We'll ignore the error here since * control chunks are already freed so there * is nothing we can do. */ sctp_packet_transmit(pkt, gfp); goto redo; } /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* If we are retransmitting, we should only * send a single packet. * Otherwise, try appending this chunk again. */ if (rtx_timeout || fast_rtx) done = 1; else goto redo; /* Bundle next chunk in the next round. */ break; case SCTP_XMIT_RWND_FULL: /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* Stop sending DATA as there is no more room * at the receiver. */ done = 1; break; case SCTP_XMIT_DELAY: /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* Stop sending DATA because of nagle delay. */ done = 1; break; default: /* The append was successful, so add this chunk to * the transmitted list. */ list_move_tail(&chunk->transmitted_list, &transport->transmitted); /* Mark the chunk as ineligible for fast retransmit * after it is retransmitted. */ if (chunk->fast_retransmit == SCTP_NEED_FRTX) chunk->fast_retransmit = SCTP_DONT_FRTX; q->asoc->stats.rtxchunks++; break; } /* Set the timer if there were no errors */ if (!error && !timer) timer = 1; if (done) break; } /* If we are here due to a retransmit timeout or a fast * retransmit and if there are any chunks left in the retransmit * queue that could not fit in the PMTU sized packet, they need * to be marked as ineligible for a subsequent fast retransmit. */ if (rtx_timeout || fast_rtx) { list_for_each_entry(chunk1, lqueue, transmitted_list) { if (chunk1->fast_retransmit == SCTP_NEED_FRTX) chunk1->fast_retransmit = SCTP_DONT_FRTX; } } *start_timer = timer; /* Clear fast retransmit hint */ if (fast_rtx) q->fast_rtx = 0; return error; } /* Cork the outqueue so queued chunks are really queued. */ void sctp_outq_uncork(struct sctp_outq *q, gfp_t gfp) { if (q->cork) q->cork = 0; sctp_outq_flush(q, 0, gfp); } static int sctp_packet_singleton(struct sctp_transport *transport, struct sctp_chunk *chunk, gfp_t gfp) { const struct sctp_association *asoc = transport->asoc; const __u16 sport = asoc->base.bind_addr.port; const __u16 dport = asoc->peer.port; const __u32 vtag = asoc->peer.i.init_tag; struct sctp_packet singleton; sctp_packet_init(&singleton, transport, sport, dport); sctp_packet_config(&singleton, vtag, 0); if (sctp_packet_append_chunk(&singleton, chunk) != SCTP_XMIT_OK) { list_del_init(&chunk->list); sctp_chunk_free(chunk); return -ENOMEM; } return sctp_packet_transmit(&singleton, gfp); } /* Struct to hold the context during sctp outq flush */ struct sctp_flush_ctx { struct sctp_outq *q; /* Current transport being used. It's NOT the same as curr active one */ struct sctp_transport *transport; /* These transports have chunks to send. */ struct list_head transport_list; struct sctp_association *asoc; /* Packet on the current transport above */ struct sctp_packet *packet; gfp_t gfp; }; /* transport: current transport */ static void sctp_outq_select_transport(struct sctp_flush_ctx *ctx, struct sctp_chunk *chunk) { struct sctp_transport *new_transport = chunk->transport; if (!new_transport) { if (!sctp_chunk_is_data(chunk)) { /* If we have a prior transport pointer, see if * the destination address of the chunk * matches the destination address of the * current transport. If not a match, then * try to look up the transport with a given * destination address. We do this because * after processing ASCONFs, we may have new * transports created. */ if (ctx->transport && sctp_cmp_addr_exact(&chunk->dest, &ctx->transport->ipaddr)) new_transport = ctx->transport; else new_transport = sctp_assoc_lookup_paddr(ctx->asoc, &chunk->dest); } /* if we still don't have a new transport, then * use the current active path. */ if (!new_transport) new_transport = ctx->asoc->peer.active_path; } else { __u8 type; switch (new_transport->state) { case SCTP_INACTIVE: case SCTP_UNCONFIRMED: case SCTP_PF: /* If the chunk is Heartbeat or Heartbeat Ack, * send it to chunk->transport, even if it's * inactive. * * 3.3.6 Heartbeat Acknowledgement: * ... * A HEARTBEAT ACK is always sent to the source IP * address of the IP datagram containing the * HEARTBEAT chunk to which this ack is responding. * ... * * ASCONF_ACKs also must be sent to the source. */ type = chunk->chunk_hdr->type; if (type != SCTP_CID_HEARTBEAT && type != SCTP_CID_HEARTBEAT_ACK && type != SCTP_CID_ASCONF_ACK) new_transport = ctx->asoc->peer.active_path; break; default: break; } } /* Are we switching transports? Take care of transport locks. */ if (new_transport != ctx->transport) { ctx->transport = new_transport; ctx->packet = &ctx->transport->packet; if (list_empty(&ctx->transport->send_ready)) list_add_tail(&ctx->transport->send_ready, &ctx->transport_list); sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag, ctx->asoc->peer.ecn_capable); /* We've switched transports, so apply the * Burst limit to the new transport. */ sctp_transport_burst_limited(ctx->transport); } } static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) { struct sctp_chunk *chunk, *tmp; enum sctp_xmit status; int one_packet, error; list_for_each_entry_safe(chunk, tmp, &ctx->q->control_chunk_list, list) { one_packet = 0; /* RFC 5061, 5.3 * F1) This means that until such time as the ASCONF * containing the add is acknowledged, the sender MUST * NOT use the new IP address as a source for ANY SCTP * packet except on carrying an ASCONF Chunk. */ if (ctx->asoc->src_out_of_asoc_ok && chunk->chunk_hdr->type != SCTP_CID_ASCONF) continue; list_del_init(&chunk->list); /* Pick the right transport to use. Should always be true for * the first chunk as we don't have a transport by then. */ sctp_outq_select_transport(ctx, chunk); switch (chunk->chunk_hdr->type) { /* 6.10 Bundling * ... * An endpoint MUST NOT bundle INIT, INIT ACK or SHUTDOWN * COMPLETE with any other chunks. [Send them immediately.] */ case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: case SCTP_CID_SHUTDOWN_COMPLETE: error = sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); if (error < 0) { ctx->asoc->base.sk->sk_err = -error; return; } ctx->asoc->stats.octrlchunks++; break; case SCTP_CID_ABORT: if (sctp_test_T_bit(chunk)) ctx->packet->vtag = ctx->asoc->c.my_vtag; fallthrough; /* The following chunks are "response" chunks, i.e. * they are generated in response to something we * received. If we are sending these, then we can * send only 1 packet containing these chunks. */ case SCTP_CID_HEARTBEAT_ACK: case SCTP_CID_SHUTDOWN_ACK: case SCTP_CID_COOKIE_ACK: case SCTP_CID_COOKIE_ECHO: case SCTP_CID_ERROR: case SCTP_CID_ECN_CWR: case SCTP_CID_ASCONF_ACK: one_packet = 1; fallthrough; case SCTP_CID_HEARTBEAT: if (chunk->pmtu_probe) { error = sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); if (!error) ctx->asoc->stats.octrlchunks++; break; } fallthrough; case SCTP_CID_SACK: case SCTP_CID_SHUTDOWN: case SCTP_CID_ECN_ECNE: case SCTP_CID_ASCONF: case SCTP_CID_FWD_TSN: case SCTP_CID_I_FWD_TSN: case SCTP_CID_RECONF: status = sctp_packet_transmit_chunk(ctx->packet, chunk, one_packet, ctx->gfp); if (status != SCTP_XMIT_OK) { /* put the chunk back */ list_add(&chunk->list, &ctx->q->control_chunk_list); break; } ctx->asoc->stats.octrlchunks++; /* PR-SCTP C5) If a FORWARD TSN is sent, the * sender MUST assure that at least one T3-rtx * timer is running. */ if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN || chunk->chunk_hdr->type == SCTP_CID_I_FWD_TSN) { sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; } if (chunk == ctx->asoc->strreset_chunk) sctp_transport_reset_reconf_timer(ctx->transport); break; default: /* We built a chunk with an illegal type! */ BUG(); } } } /* Returns false if new data shouldn't be sent */ static bool sctp_outq_flush_rtx(struct sctp_flush_ctx *ctx, int rtx_timeout) { int error, start_timer = 0; if (ctx->asoc->peer.retran_path->state == SCTP_UNCONFIRMED) return false; if (ctx->transport != ctx->asoc->peer.retran_path) { /* Switch transports & prepare the packet. */ ctx->transport = ctx->asoc->peer.retran_path; ctx->packet = &ctx->transport->packet; if (list_empty(&ctx->transport->send_ready)) list_add_tail(&ctx->transport->send_ready, &ctx->transport_list); sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag, ctx->asoc->peer.ecn_capable); } error = __sctp_outq_flush_rtx(ctx->q, ctx->packet, rtx_timeout, &start_timer, ctx->gfp); if (error < 0) ctx->asoc->base.sk->sk_err = -error; if (start_timer) { sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; } /* This can happen on COOKIE-ECHO resend. Only * one chunk can get bundled with a COOKIE-ECHO. */ if (ctx->packet->has_cookie_echo) return false; /* Don't send new data if there is still data * waiting to retransmit. */ if (!list_empty(&ctx->q->retransmit)) return false; return true; } static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, int rtx_timeout) { struct sctp_chunk *chunk; enum sctp_xmit status; /* Is it OK to send data chunks? */ switch (ctx->asoc->state) { case SCTP_STATE_COOKIE_ECHOED: /* Only allow bundling when this packet has a COOKIE-ECHO * chunk. */ if (!ctx->packet || !ctx->packet->has_cookie_echo) return; fallthrough; case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: break; default: /* Do nothing. */ return; } /* RFC 2960 6.1 Transmission of DATA Chunks * * C) When the time comes for the sender to transmit, * before sending new DATA chunks, the sender MUST * first transmit any outstanding DATA chunks which * are marked for retransmission (limited by the * current cwnd). */ if (!list_empty(&ctx->q->retransmit) && !sctp_outq_flush_rtx(ctx, rtx_timeout)) return; /* Apply Max.Burst limitation to the current transport in * case it will be used for new data. We are going to * rest it before we return, but we want to apply the limit * to the currently queued data. */ if (ctx->transport) sctp_transport_burst_limited(ctx->transport); /* Finally, transmit new packets. */ while ((chunk = sctp_outq_dequeue_data(ctx->q)) != NULL) { __u32 sid = ntohs(chunk->subh.data_hdr->stream); __u8 stream_state = SCTP_SO(&ctx->asoc->stream, sid)->state; /* Has this chunk expired? */ if (sctp_chunk_abandoned(chunk)) { sctp_sched_dequeue_done(ctx->q, chunk); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; } if (stream_state == SCTP_STREAM_CLOSED) { sctp_outq_head_data(ctx->q, chunk); break; } sctp_outq_select_transport(ctx, chunk); pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p skb->users:%d\n", __func__, ctx->q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk", ntohl(chunk->subh.data_hdr->tsn), chunk->skb ? chunk->skb->head : NULL, chunk->skb ? refcount_read(&chunk->skb->users) : -1); /* Add the chunk to the packet. */ status = sctp_packet_transmit_chunk(ctx->packet, chunk, 0, ctx->gfp); if (status != SCTP_XMIT_OK) { /* We could not append this chunk, so put * the chunk back on the output queue. */ pr_debug("%s: could not transmit tsn:0x%x, status:%d\n", __func__, ntohl(chunk->subh.data_hdr->tsn), status); sctp_outq_head_data(ctx->q, chunk); break; } /* The sender is in the SHUTDOWN-PENDING state, * The sender MAY set the I-bit in the DATA * chunk header. */ if (ctx->asoc->state == SCTP_STATE_SHUTDOWN_PENDING) chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) ctx->asoc->stats.ouodchunks++; else ctx->asoc->stats.oodchunks++; /* Only now it's safe to consider this * chunk as sent, sched-wise. */ sctp_sched_dequeue_done(ctx->q, chunk); list_add_tail(&chunk->transmitted_list, &ctx->transport->transmitted); sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; /* Only let one DATA chunk get bundled with a * COOKIE-ECHO chunk. */ if (ctx->packet->has_cookie_echo) break; } } static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx) { struct sock *sk = ctx->asoc->base.sk; struct list_head *ltransport; struct sctp_packet *packet; struct sctp_transport *t; int error = 0; while ((ltransport = sctp_list_dequeue(&ctx->transport_list)) != NULL) { t = list_entry(ltransport, struct sctp_transport, send_ready); packet = &t->packet; if (!sctp_packet_empty(packet)) { rcu_read_lock(); if (t->dst && __sk_dst_get(sk) != t->dst) { dst_hold(t->dst); sk_setup_caps(sk, t->dst); } rcu_read_unlock(); error = sctp_packet_transmit(packet, ctx->gfp); if (error < 0) ctx->q->asoc->base.sk->sk_err = -error; } /* Clear the burst limited state, if any */ sctp_transport_burst_reset(t); } } /* Try to flush an outqueue. * * Description: Send everything in q which we legally can, subject to * congestion limitations. * * Note: This function can be called from multiple contexts so appropriate * locking concerns must be made. Today we use the sock lock to protect * this function. */ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) { struct sctp_flush_ctx ctx = { .q = q, .transport = NULL, .transport_list = LIST_HEAD_INIT(ctx.transport_list), .asoc = q->asoc, .packet = NULL, .gfp = gfp, }; /* 6.10 Bundling * ... * When bundling control chunks with DATA chunks, an * endpoint MUST place control chunks first in the outbound * SCTP packet. The transmitter MUST transmit DATA chunks * within a SCTP packet in increasing order of TSN. * ... */ sctp_outq_flush_ctrl(&ctx); if (q->asoc->src_out_of_asoc_ok) goto sctp_flush_out; sctp_outq_flush_data(&ctx, rtx_timeout); sctp_flush_out: sctp_outq_flush_transports(&ctx); } /* Update unack_data based on the incoming SACK chunk */ static void sctp_sack_update_unack_data(struct sctp_association *assoc, struct sctp_sackhdr *sack) { union sctp_sack_variable *frags; __u16 unack_data; int i; unack_data = assoc->next_tsn - assoc->ctsn_ack_point - 1; frags = sack->variable; for (i = 0; i < ntohs(sack->num_gap_ack_blocks); i++) { unack_data -= ((ntohs(frags[i].gab.end) - ntohs(frags[i].gab.start) + 1)); } assoc->unack_data = unack_data; } /* This is where we REALLY process a SACK. * * Process the SACK against the outqueue. Mostly, this just frees * things off the transmitted queue. */ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) { struct sctp_association *asoc = q->asoc; struct sctp_sackhdr *sack = chunk->subh.sack_hdr; struct sctp_transport *transport; struct sctp_chunk *tchunk = NULL; struct list_head *lchunk, *transport_list, *temp; union sctp_sack_variable *frags = sack->variable; __u32 sack_ctsn, ctsn, tsn; __u32 highest_tsn, highest_new_tsn; __u32 sack_a_rwnd; unsigned int outstanding; struct sctp_transport *primary = asoc->peer.primary_path; int count_of_newacks = 0; int gap_ack_blocks; u8 accum_moved = 0; /* Grab the association's destination address list. */ transport_list = &asoc->peer.transport_addr_list; /* SCTP path tracepoint for congestion control debugging. */ if (trace_sctp_probe_path_enabled()) { list_for_each_entry(transport, transport_list, transports) trace_sctp_probe_path(transport, asoc); } sack_ctsn = ntohl(sack->cum_tsn_ack); gap_ack_blocks = ntohs(sack->num_gap_ack_blocks); asoc->stats.gapcnt += gap_ack_blocks; /* * SFR-CACC algorithm: * On receipt of a SACK the sender SHOULD execute the * following statements. * * 1) If the cumulative ack in the SACK passes next tsn_at_change * on the current primary, the CHANGEOVER_ACTIVE flag SHOULD be * cleared. The CYCLING_CHANGEOVER flag SHOULD also be cleared for * all destinations. * 2) If the SACK contains gap acks and the flag CHANGEOVER_ACTIVE * is set the receiver of the SACK MUST take the following actions: * * A) Initialize the cacc_saw_newack to 0 for all destination * addresses. * * Only bother if changeover_active is set. Otherwise, this is * totally suboptimal to do on every SACK. */ if (primary->cacc.changeover_active) { u8 clear_cycling = 0; if (TSN_lte(primary->cacc.next_tsn_at_change, sack_ctsn)) { primary->cacc.changeover_active = 0; clear_cycling = 1; } if (clear_cycling || gap_ack_blocks) { list_for_each_entry(transport, transport_list, transports) { if (clear_cycling) transport->cacc.cycling_changeover = 0; if (gap_ack_blocks) transport->cacc.cacc_saw_newack = 0; } } } /* Get the highest TSN in the sack. */ highest_tsn = sack_ctsn; if (gap_ack_blocks) highest_tsn += ntohs(frags[gap_ack_blocks - 1].gab.end); if (TSN_lt(asoc->highest_sacked, highest_tsn)) asoc->highest_sacked = highest_tsn; highest_new_tsn = sack_ctsn; /* Run through the retransmit queue. Credit bytes received * and free those chunks that we can. */ sctp_check_transmitted(q, &q->retransmit, NULL, NULL, sack, &highest_new_tsn); /* Run through the transmitted queue. * Credit bytes received and free those chunks which we can. * * This is a MASSIVE candidate for optimization. */ list_for_each_entry(transport, transport_list, transports) { sctp_check_transmitted(q, &transport->transmitted, transport, &chunk->source, sack, &highest_new_tsn); /* * SFR-CACC algorithm: * C) Let count_of_newacks be the number of * destinations for which cacc_saw_newack is set. */ if (transport->cacc.cacc_saw_newack) count_of_newacks++; } /* Move the Cumulative TSN Ack Point if appropriate. */ if (TSN_lt(asoc->ctsn_ack_point, sack_ctsn)) { asoc->ctsn_ack_point = sack_ctsn; accum_moved = 1; } if (gap_ack_blocks) { if (asoc->fast_recovery && accum_moved) highest_new_tsn = highest_tsn; list_for_each_entry(transport, transport_list, transports) sctp_mark_missing(q, &transport->transmitted, transport, highest_new_tsn, count_of_newacks); } /* Update unack_data field in the assoc. */ sctp_sack_update_unack_data(asoc, sack); ctsn = asoc->ctsn_ack_point; /* Throw away stuff rotting on the sack queue. */ list_for_each_safe(lchunk, temp, &q->sacked) { tchunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); tsn = ntohl(tchunk->subh.data_hdr->tsn); if (TSN_lte(tsn, ctsn)) { list_del_init(&tchunk->transmitted_list); if (asoc->peer.prsctp_capable && SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) asoc->sent_cnt_removable--; sctp_chunk_free(tchunk); } } /* 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. */ sack_a_rwnd = ntohl(sack->a_rwnd); asoc->peer.zero_window_announced = !sack_a_rwnd; outstanding = q->outstanding_bytes; if (outstanding < sack_a_rwnd) sack_a_rwnd -= outstanding; else sack_a_rwnd = 0; asoc->peer.rwnd = sack_a_rwnd; asoc->stream.si->generate_ftsn(q, sack_ctsn); pr_debug("%s: sack cumulative tsn ack:0x%x\n", __func__, sack_ctsn); pr_debug("%s: cumulative tsn ack of assoc:%p is 0x%x, " "advertised peer ack point:0x%x\n", __func__, asoc, ctsn, asoc->adv_peer_ack_point); return sctp_outq_is_empty(q); } /* Is the outqueue empty? * The queue is empty when we have not pending data, no in-flight data * and nothing pending retransmissions. */ int sctp_outq_is_empty(const struct sctp_outq *q) { return q->out_qlen == 0 && q->outstanding_bytes == 0 && list_empty(&q->retransmit); } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ /* Go through a transport's transmitted list or the association's retransmit * list and move chunks that are acked by the Cumulative TSN Ack to q->sacked. * The retransmit list will not have an associated transport. * * I added coherent debug information output. --xguo * * Instead of printing 'sacked' or 'kept' for each TSN on the * transmitted_queue, we print a range: SACKED: TSN1-TSN2, TSN3, TSN4-TSN5. * KEPT TSN6-TSN7, etc. */ static void sctp_check_transmitted(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, union sctp_addr *saddr, struct sctp_sackhdr *sack, __u32 *highest_new_tsn_in_sack) { struct list_head *lchunk; struct sctp_chunk *tchunk; struct list_head tlist; __u32 tsn; __u32 sack_ctsn; __u32 rtt; __u8 restart_timer = 0; int bytes_acked = 0; int migrate_bytes = 0; bool forward_progress = false; sack_ctsn = ntohl(sack->cum_tsn_ack); INIT_LIST_HEAD(&tlist); /* The while loop will skip empty transmitted queues. */ while (NULL != (lchunk = sctp_list_dequeue(transmitted_queue))) { tchunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); if (sctp_chunk_abandoned(tchunk)) { /* Move the chunk to abandoned list. */ sctp_insert_list(&q->abandoned, lchunk); /* If this chunk has not been acked, stop * considering it as 'outstanding'. */ if (transmitted_queue != &q->retransmit && !tchunk->tsn_gap_acked) { if (tchunk->transport) tchunk->transport->flight_size -= sctp_data_size(tchunk); q->outstanding_bytes -= sctp_data_size(tchunk); } continue; } tsn = ntohl(tchunk->subh.data_hdr->tsn); if (sctp_acked(sack, tsn)) { /* If this queue is the retransmit queue, the * retransmit timer has already reclaimed * the outstanding bytes for this chunk, so only * count bytes associated with a transport. */ if (transport && !tchunk->tsn_gap_acked) { /* If this chunk is being used for RTT * measurement, calculate the RTT and update * the RTO using this value. * * 6.3.1 C5) Karn's algorithm: RTT measurements * MUST NOT be made using packets that were * retransmitted (and thus for which it is * ambiguous whether the reply was for the * first instance of the packet or a later * instance). */ if (!sctp_chunk_retransmitted(tchunk) && tchunk->rtt_in_progress) { tchunk->rtt_in_progress = 0; rtt = jiffies - tchunk->sent_at; sctp_transport_update_rto(transport, rtt); } if (TSN_lte(tsn, sack_ctsn)) { /* * SFR-CACC algorithm: * 2) If the SACK contains gap acks * and the flag CHANGEOVER_ACTIVE is * set the receiver of the SACK MUST * take the following action: * * B) For each TSN t being acked that * has not been acked in any SACK so * far, set cacc_saw_newack to 1 for * the destination that the TSN was * sent to. */ if (sack->num_gap_ack_blocks && q->asoc->peer.primary_path->cacc. changeover_active) transport->cacc.cacc_saw_newack = 1; } } /* If the chunk hasn't been marked as ACKED, * mark it and account bytes_acked if the * chunk had a valid transport (it will not * have a transport if ASCONF had deleted it * while DATA was outstanding). */ if (!tchunk->tsn_gap_acked) { tchunk->tsn_gap_acked = 1; if (TSN_lt(*highest_new_tsn_in_sack, tsn)) *highest_new_tsn_in_sack = tsn; bytes_acked += sctp_data_size(tchunk); if (!tchunk->transport) migrate_bytes += sctp_data_size(tchunk); forward_progress = true; } if (TSN_lte(tsn, sack_ctsn)) { /* RFC 2960 6.3.2 Retransmission Timer Rules * * R3) Whenever a SACK is received * that acknowledges the DATA chunk * with the earliest outstanding TSN * for that address, restart T3-rtx * timer for that address with its * current RTO. */ restart_timer = 1; forward_progress = true; list_add_tail(&tchunk->transmitted_list, &q->sacked); } else { /* RFC2960 7.2.4, sctpimpguide-05 2.8.2 * M2) Each time a SACK arrives reporting * 'Stray DATA chunk(s)' record the highest TSN * reported as newly acknowledged, call this * value 'HighestTSNinSack'. A newly * acknowledged DATA chunk is one not * previously acknowledged in a SACK. * * When the SCTP sender of data receives a SACK * chunk that acknowledges, for the first time, * the receipt of a DATA chunk, all the still * unacknowledged DATA chunks whose TSN is * older than that newly acknowledged DATA * chunk, are qualified as 'Stray DATA chunks'. */ list_add_tail(lchunk, &tlist); } } else { if (tchunk->tsn_gap_acked) { pr_debug("%s: receiver reneged on data TSN:0x%x\n", __func__, tsn); tchunk->tsn_gap_acked = 0; if (tchunk->transport) bytes_acked -= sctp_data_size(tchunk); /* RFC 2960 6.3.2 Retransmission Timer Rules * * R4) Whenever a SACK is received missing a * TSN that was previously acknowledged via a * Gap Ack Block, start T3-rtx for the * destination address to which the DATA * chunk was originally * transmitted if it is not already running. */ restart_timer = 1; } list_add_tail(lchunk, &tlist); } } if (transport) { if (bytes_acked) { struct sctp_association *asoc = transport->asoc; /* We may have counted DATA that was migrated * to this transport due to DEL-IP operation. * Subtract those bytes, since the were never * send on this transport and shouldn't be * credited to this transport. */ bytes_acked -= migrate_bytes; /* 8.2. When an outstanding TSN is acknowledged, * the endpoint shall clear the error counter of * the destination transport address to which the * DATA chunk was last sent. * The association's overall error counter is * also cleared. */ transport->error_count = 0; transport->asoc->overall_error_count = 0; forward_progress = true; /* * While in SHUTDOWN PENDING, we may have started * the T5 shutdown guard timer after reaching the * retransmission limit. Stop that timer as soon * as the receiver acknowledged any data. */ if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING && del_timer(&asoc->timers [SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD])) sctp_association_put(asoc); /* Mark the destination transport address as * active if it is not so marked. */ if ((transport->state == SCTP_INACTIVE || transport->state == SCTP_UNCONFIRMED) && sctp_cmp_addr_exact(&transport->ipaddr, saddr)) { sctp_assoc_control_transport( transport->asoc, transport, SCTP_TRANSPORT_UP, SCTP_RECEIVED_SACK); } sctp_transport_raise_cwnd(transport, sack_ctsn, bytes_acked); transport->flight_size -= bytes_acked; if (transport->flight_size == 0) transport->partial_bytes_acked = 0; q->outstanding_bytes -= bytes_acked + migrate_bytes; } else { /* RFC 2960 6.1, sctpimpguide-06 2.15.2 * When a sender is doing zero window probing, it * should not timeout the association if it continues * to receive new packets from the receiver. The * reason is that the receiver MAY keep its window * closed for an indefinite time. * A sender is doing zero window probing when the * receiver's advertised window is zero, and there is * only one data chunk in flight to the receiver. * * Allow the association to timeout while in SHUTDOWN * PENDING or SHUTDOWN RECEIVED in case the receiver * stays in zero window mode forever. */ if (!q->asoc->peer.rwnd && !list_empty(&tlist) && (sack_ctsn+2 == q->asoc->next_tsn) && q->asoc->state < SCTP_STATE_SHUTDOWN_PENDING) { pr_debug("%s: sack received for zero window " "probe:%u\n", __func__, sack_ctsn); q->asoc->overall_error_count = 0; transport->error_count = 0; } } /* RFC 2960 6.3.2 Retransmission Timer Rules * * R2) Whenever all outstanding data sent to an address have * been acknowledged, turn off the T3-rtx timer of that * address. */ if (!transport->flight_size) { if (del_timer(&transport->T3_rtx_timer)) sctp_transport_put(transport); } else if (restart_timer) { if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) sctp_transport_hold(transport); } if (forward_progress) { if (transport->dst) sctp_transport_dst_confirm(transport); } } list_splice(&tlist, transmitted_queue); } /* Mark chunks as missing and consequently may get retransmitted. */ static void sctp_mark_missing(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, __u32 highest_new_tsn_in_sack, int count_of_newacks) { struct sctp_chunk *chunk; __u32 tsn; char do_fast_retransmit = 0; struct sctp_association *asoc = q->asoc; struct sctp_transport *primary = asoc->peer.primary_path; list_for_each_entry(chunk, transmitted_queue, transmitted_list) { tsn = ntohl(chunk->subh.data_hdr->tsn); /* RFC 2960 7.2.4, sctpimpguide-05 2.8.2 M3) Examine all * 'Unacknowledged TSN's', if the TSN number of an * 'Unacknowledged TSN' is smaller than the 'HighestTSNinSack' * value, increment the 'TSN.Missing.Report' count on that * chunk if it has NOT been fast retransmitted or marked for * fast retransmit already. */ if (chunk->fast_retransmit == SCTP_CAN_FRTX && !chunk->tsn_gap_acked && TSN_lt(tsn, highest_new_tsn_in_sack)) { /* SFR-CACC may require us to skip marking * this chunk as missing. */ if (!transport || !sctp_cacc_skip(primary, chunk->transport, count_of_newacks, tsn)) { chunk->tsn_missing_report++; pr_debug("%s: tsn:0x%x missing counter:%d\n", __func__, tsn, chunk->tsn_missing_report); } } /* * M4) If any DATA chunk is found to have a * 'TSN.Missing.Report' * value larger than or equal to 3, mark that chunk for * retransmission and start the fast retransmit procedure. */ if (chunk->tsn_missing_report >= 3) { chunk->fast_retransmit = SCTP_NEED_FRTX; do_fast_retransmit = 1; } } if (transport) { if (do_fast_retransmit) sctp_retransmit(q, transport, SCTP_RTXR_FAST_RTX); pr_debug("%s: transport:%p, cwnd:%d, ssthresh:%d, " "flight_size:%d, pba:%d\n", __func__, transport, transport->cwnd, transport->ssthresh, transport->flight_size, transport->partial_bytes_acked); } } /* Is the given TSN acked by this packet? */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn) { __u32 ctsn = ntohl(sack->cum_tsn_ack); union sctp_sack_variable *frags; __u16 tsn_offset, blocks; int i; if (TSN_lte(tsn, ctsn)) goto pass; /* 3.3.4 Selective Acknowledgment (SACK) (3): * * Gap Ack Blocks: * These fields contain the Gap Ack Blocks. They are repeated * for each Gap Ack Block up to the number of Gap Ack Blocks * defined in the Number of Gap Ack Blocks field. All DATA * chunks with TSNs greater than or equal to (Cumulative TSN * Ack + Gap Ack Block Start) and less than or equal to * (Cumulative TSN Ack + Gap Ack Block End) of each Gap Ack * Block are assumed to have been received correctly. */ frags = sack->variable; blocks = ntohs(sack->num_gap_ack_blocks); tsn_offset = tsn - ctsn; for (i = 0; i < blocks; ++i) { if (tsn_offset >= ntohs(frags[i].gab.start) && tsn_offset <= ntohs(frags[i].gab.end)) goto pass; } return 0; pass: return 1; } static inline int sctp_get_skip_pos(struct sctp_fwdtsn_skip *skiplist, int nskips, __be16 stream) { int i; for (i = 0; i < nskips; i++) { if (skiplist[i].stream == stream) return i; } return i; } /* Create and add a fwdtsn chunk to the outq's control queue if needed. */ void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 ctsn) { struct sctp_association *asoc = q->asoc; struct sctp_chunk *ftsn_chunk = NULL; struct sctp_fwdtsn_skip ftsn_skip_arr[10]; int nskips = 0; int skip_pos = 0; __u32 tsn; struct sctp_chunk *chunk; struct list_head *lchunk, *temp; if (!asoc->peer.prsctp_capable) return; /* PR-SCTP C1) Let SackCumAck be the Cumulative TSN ACK carried in the * received SACK. * * If (Advanced.Peer.Ack.Point < SackCumAck), then update * Advanced.Peer.Ack.Point to be equal to SackCumAck. */ if (TSN_lt(asoc->adv_peer_ack_point, ctsn)) asoc->adv_peer_ack_point = ctsn; /* PR-SCTP C2) Try to further advance the "Advanced.Peer.Ack.Point" * locally, that is, to move "Advanced.Peer.Ack.Point" up as long as * the chunk next in the out-queue space is marked as "abandoned" as * shown in the following example: * * Assuming that a SACK arrived with the Cumulative TSN ACK 102 * and the Advanced.Peer.Ack.Point is updated to this value: * * out-queue at the end of ==> out-queue after Adv.Ack.Point * normal SACK processing local advancement * ... ... * Adv.Ack.Pt-> 102 acked 102 acked * 103 abandoned 103 abandoned * 104 abandoned Adv.Ack.P-> 104 abandoned * 105 105 * 106 acked 106 acked * ... ... * * In this example, the data sender successfully advanced the * "Advanced.Peer.Ack.Point" from 102 to 104 locally. */ list_for_each_safe(lchunk, temp, &q->abandoned) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); tsn = ntohl(chunk->subh.data_hdr->tsn); /* Remove any chunks in the abandoned queue that are acked by * the ctsn. */ if (TSN_lte(tsn, ctsn)) { list_del_init(lchunk); sctp_chunk_free(chunk); } else { if (TSN_lte(tsn, asoc->adv_peer_ack_point+1)) { asoc->adv_peer_ack_point = tsn; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) continue; skip_pos = sctp_get_skip_pos(&ftsn_skip_arr[0], nskips, chunk->subh.data_hdr->stream); ftsn_skip_arr[skip_pos].stream = chunk->subh.data_hdr->stream; ftsn_skip_arr[skip_pos].ssn = chunk->subh.data_hdr->ssn; if (skip_pos == nskips) nskips++; if (nskips == 10) break; } else break; } } /* PR-SCTP C3) If, after step C1 and C2, the "Advanced.Peer.Ack.Point" * is greater than the Cumulative TSN ACK carried in the received * SACK, the data sender MUST send the data receiver a FORWARD TSN * chunk containing the latest value of the * "Advanced.Peer.Ack.Point". * * C4) For each "abandoned" TSN the sender of the FORWARD TSN SHOULD * list each stream and sequence number in the forwarded TSN. This * information will enable the receiver to easily find any * stranded TSN's waiting on stream reorder queues. Each stream * SHOULD only be reported once; this means that if multiple * abandoned messages occur in the same stream then only the * highest abandoned stream sequence number is reported. If the * total size of the FORWARD TSN does NOT fit in a single MTU then * the sender of the FORWARD TSN SHOULD lower the * Advanced.Peer.Ack.Point to the last TSN that will fit in a * single MTU. */ if (asoc->adv_peer_ack_point > ctsn) ftsn_chunk = sctp_make_fwdtsn(asoc, asoc->adv_peer_ack_point, nskips, &ftsn_skip_arr[0]); if (ftsn_chunk) { list_add_tail(&ftsn_chunk->list, &q->control_chunk_list); SCTP_INC_STATS(asoc->base.net, SCTP_MIB_OUTCTRLCHUNKS); } } |
| 89 98 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 | /* SPDX-License-Identifier: GPL-2.0 */ /* * INETPEER - A storage for permanent information about peers * * Authors: Andrey V. Savochkin <saw@msu.ru> */ #ifndef _NET_INETPEER_H #define _NET_INETPEER_H #include <linux/types.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/spinlock.h> #include <linux/rtnetlink.h> #include <net/ipv6.h> #include <linux/atomic.h> /* IPv4 address key for cache lookups */ struct ipv4_addr_key { __be32 addr; int vif; }; #define INETPEER_MAXKEYSZ (sizeof(struct in6_addr) / sizeof(u32)) struct inetpeer_addr { union { struct ipv4_addr_key a4; struct in6_addr a6; u32 key[INETPEER_MAXKEYSZ]; }; __u16 family; }; struct inet_peer { struct rb_node rb_node; struct inetpeer_addr daddr; u32 metrics[RTAX_MAX]; u32 rate_tokens; /* rate limiting for ICMP */ u32 n_redirects; unsigned long rate_last; /* * Once inet_peer is queued for deletion (refcnt == 0), following field * is not available: rid * We can share memory with rcu_head to help keep inet_peer small. */ union { struct { atomic_t rid; /* Frag reception counter */ }; struct rcu_head rcu; }; /* following fields might be frequently dirtied */ __u32 dtime; /* the time of last use of not referenced entries */ refcount_t refcnt; }; struct inet_peer_base { struct rb_root rb_root; seqlock_t lock; int total; }; void inet_peer_base_init(struct inet_peer_base *); void inet_initpeers(void) __init; #define INETPEER_METRICS_NEW (~(u32) 0) static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip) { iaddr->a4.addr = ip; iaddr->a4.vif = 0; iaddr->family = AF_INET; } static inline __be32 inetpeer_get_addr_v4(struct inetpeer_addr *iaddr) { return iaddr->a4.addr; } static inline void inetpeer_set_addr_v6(struct inetpeer_addr *iaddr, struct in6_addr *in6) { iaddr->a6 = *in6; iaddr->family = AF_INET6; } static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr) { return &iaddr->a6; } /* can be called with or without local BH being disabled */ struct inet_peer *inet_getpeer(struct inet_peer_base *base, const struct inetpeer_addr *daddr, int create); static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base, __be32 v4daddr, int vif, int create) { struct inetpeer_addr daddr; daddr.a4.addr = v4daddr; daddr.a4.vif = vif; daddr.family = AF_INET; return inet_getpeer(base, &daddr, create); } static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base, const struct in6_addr *v6daddr, int create) { struct inetpeer_addr daddr; daddr.a6 = *v6daddr; daddr.family = AF_INET6; return inet_getpeer(base, &daddr, create); } static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { int i, n; if (a->family == AF_INET) n = sizeof(a->a4) / sizeof(u32); else n = sizeof(a->a6) / sizeof(u32); for (i = 0; i < n; i++) { if (a->key[i] == b->key[i]) continue; if (a->key[i] < b->key[i]) return -1; return 1; } return 0; } /* can be called from BH context or outside */ void inet_putpeer(struct inet_peer *p); bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout); void inetpeer_invalidate_tree(struct inet_peer_base *); #endif /* _NET_INETPEER_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 | // SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/fast_commit.c * * Written by Harshad Shirwadkar <harshadshirwadkar@gmail.com> * * Ext4 fast commits routines. */ #include "ext4.h" #include "ext4_jbd2.h" #include "ext4_extents.h" #include "mballoc.h" /* * Ext4 Fast Commits * ----------------- * * Ext4 fast commits implement fine grained journalling for Ext4. * * Fast commits are organized as a log of tag-length-value (TLV) structs. (See * struct ext4_fc_tl). Each TLV contains some delta that is replayed TLV by * TLV during the recovery phase. For the scenarios for which we currently * don't have replay code, fast commit falls back to full commits. * Fast commits record delta in one of the following three categories. * * (A) Directory entry updates: * * - EXT4_FC_TAG_UNLINK - records directory entry unlink * - EXT4_FC_TAG_LINK - records directory entry link * - EXT4_FC_TAG_CREAT - records inode and directory entry creation * * (B) File specific data range updates: * * - EXT4_FC_TAG_ADD_RANGE - records addition of new blocks to an inode * - EXT4_FC_TAG_DEL_RANGE - records deletion of blocks from an inode * * (C) Inode metadata (mtime / ctime etc): * * - EXT4_FC_TAG_INODE - record the inode that should be replayed * during recovery. Note that iblocks field is * not replayed and instead derived during * replay. * Commit Operation * ---------------- * With fast commits, we maintain all the directory entry operations in the * order in which they are issued in an in-memory queue. This queue is flushed * to disk during the commit operation. We also maintain a list of inodes * that need to be committed during a fast commit in another in memory queue of * inodes. During the commit operation, we commit in the following order: * * [1] Lock inodes for any further data updates by setting COMMITTING state * [2] Submit data buffers of all the inodes * [3] Wait for [2] to complete * [4] Commit all the directory entry updates in the fast commit space * [5] Commit all the changed inode structures * [6] Write tail tag (this tag ensures the atomicity, please read the following * section for more details). * [7] Wait for [4], [5] and [6] to complete. * * All the inode updates must call ext4_fc_start_update() before starting an * update. If such an ongoing update is present, fast commit waits for it to * complete. The completion of such an update is marked by * ext4_fc_stop_update(). * * Fast Commit Ineligibility * ------------------------- * * Not all operations are supported by fast commits today (e.g extended * attributes). Fast commit ineligibility is marked by calling * ext4_fc_mark_ineligible(): This makes next fast commit operation to fall back * to full commit. * * Atomicity of commits * -------------------- * In order to guarantee atomicity during the commit operation, fast commit * uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail * tag contains CRC of the contents and TID of the transaction after which * this fast commit should be applied. Recovery code replays fast commit * logs only if there's at least 1 valid tail present. For every fast commit * operation, there is 1 tail. This means, we may end up with multiple tails * in the fast commit space. Here's an example: * * - Create a new file A and remove existing file B * - fsync() * - Append contents to file A * - Truncate file A * - fsync() * * The fast commit space at the end of above operations would look like this: * [HEAD] [CREAT A] [UNLINK B] [TAIL] [ADD_RANGE A] [DEL_RANGE A] [TAIL] * |<--- Fast Commit 1 --->|<--- Fast Commit 2 ---->| * * Replay code should thus check for all the valid tails in the FC area. * * Fast Commit Replay Idempotence * ------------------------------ * * Fast commits tags are idempotent in nature provided the recovery code follows * certain rules. The guiding principle that the commit path follows while * committing is that it stores the result of a particular operation instead of * storing the procedure. * * Let's consider this rename operation: 'mv /a /b'. Let's assume dirent '/a' * was associated with inode 10. During fast commit, instead of storing this * operation as a procedure "rename a to b", we store the resulting file system * state as a "series" of outcomes: * * - Link dirent b to inode 10 * - Unlink dirent a * - Inode <10> with valid refcount * * Now when recovery code runs, it needs "enforce" this state on the file * system. This is what guarantees idempotence of fast commit replay. * * Let's take an example of a procedure that is not idempotent and see how fast * commits make it idempotent. Consider following sequence of operations: * * rm A; mv B A; read A * (x) (y) (z) * * (x), (y) and (z) are the points at which we can crash. If we store this * sequence of operations as is then the replay is not idempotent. Let's say * while in replay, we crash at (z). During the second replay, file A (which was * actually created as a result of "mv B A" operation) would get deleted. Thus, * file named A would be absent when we try to read A. So, this sequence of * operations is not idempotent. However, as mentioned above, instead of storing * the procedure fast commits store the outcome of each procedure. Thus the fast * commit log for above procedure would be as follows: * * (Let's assume dirent A was linked to inode 10 and dirent B was linked to * inode 11 before the replay) * * [Unlink A] [Link A to inode 11] [Unlink B] [Inode 11] * (w) (x) (y) (z) * * If we crash at (z), we will have file A linked to inode 11. During the second * replay, we will remove file A (inode 11). But we will create it back and make * it point to inode 11. We won't find B, so we'll just skip that step. At this * point, the refcount for inode 11 is not reliable, but that gets fixed by the * replay of last inode 11 tag. Crashes at points (w), (x) and (y) get handled * similarly. Thus, by converting a non-idempotent procedure into a series of * idempotent outcomes, fast commits ensured idempotence during the replay. * * TODOs * ----- * * 0) Fast commit replay path hardening: Fast commit replay code should use * journal handles to make sure all the updates it does during the replay * path are atomic. With that if we crash during fast commit replay, after * trying to do recovery again, we will find a file system where fast commit * area is invalid (because new full commit would be found). In order to deal * with that, fast commit replay code should ensure that the "FC_REPLAY" * superblock state is persisted before starting the replay, so that after * the crash, fast commit recovery code can look at that flag and perform * fast commit recovery even if that area is invalidated by later full * commits. * * 1) Make fast commit atomic updates more fine grained. Today, a fast commit * eligible update must be protected within ext4_fc_start_update() and * ext4_fc_stop_update(). These routines are called at much higher * routines. This can be made more fine grained by combining with * ext4_journal_start(). * * 2) Same above for ext4_fc_start_ineligible() and ext4_fc_stop_ineligible() * * 3) Handle more ineligible cases. */ #include <trace/events/ext4.h> static struct kmem_cache *ext4_fc_dentry_cachep; static void ext4_end_buffer_io_sync(struct buffer_head *bh, int uptodate) { BUFFER_TRACE(bh, ""); if (uptodate) { ext4_debug("%s: Block %lld up-to-date", __func__, bh->b_blocknr); set_buffer_uptodate(bh); } else { ext4_debug("%s: Block %lld not up-to-date", __func__, bh->b_blocknr); clear_buffer_uptodate(bh); } unlock_buffer(bh); } static inline void ext4_fc_reset_inode(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); ei->i_fc_lblk_start = 0; ei->i_fc_lblk_len = 0; } void ext4_fc_init_inode(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); ext4_fc_reset_inode(inode); ext4_clear_inode_state(inode, EXT4_STATE_FC_COMMITTING); INIT_LIST_HEAD(&ei->i_fc_list); init_waitqueue_head(&ei->i_fc_wait); atomic_set(&ei->i_fc_updates, 0); } /* This function must be called with sbi->s_fc_lock held. */ static void ext4_fc_wait_committing_inode(struct inode *inode) __releases(&EXT4_SB(inode->i_sb)->s_fc_lock) { wait_queue_head_t *wq; struct ext4_inode_info *ei = EXT4_I(inode); #if (BITS_PER_LONG < 64) DEFINE_WAIT_BIT(wait, &ei->i_state_flags, EXT4_STATE_FC_COMMITTING); wq = bit_waitqueue(&ei->i_state_flags, EXT4_STATE_FC_COMMITTING); #else DEFINE_WAIT_BIT(wait, &ei->i_flags, EXT4_STATE_FC_COMMITTING); wq = bit_waitqueue(&ei->i_flags, EXT4_STATE_FC_COMMITTING); #endif lockdep_assert_held(&EXT4_SB(inode->i_sb)->s_fc_lock); prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); schedule(); finish_wait(wq, &wait.wq_entry); } /* * Inform Ext4's fast about start of an inode update * * This function is called by the high level call VFS callbacks before * performing any inode update. This function blocks if there's an ongoing * fast commit on the inode in question. */ void ext4_fc_start_update(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)) return; restart: spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock); if (list_empty(&ei->i_fc_list)) goto out; if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) { ext4_fc_wait_committing_inode(inode); goto restart; } out: atomic_inc(&ei->i_fc_updates); spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); } /* * Stop inode update and wake up waiting fast commits if any. */ void ext4_fc_stop_update(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)) return; if (atomic_dec_and_test(&ei->i_fc_updates)) wake_up_all(&ei->i_fc_wait); } /* * Remove inode from fast commit list. If the inode is being committed * we wait until inode commit is done. */ void ext4_fc_del(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)) return; restart: spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock); if (list_empty(&ei->i_fc_list)) { spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); return; } if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) { ext4_fc_wait_committing_inode(inode); goto restart; } list_del_init(&ei->i_fc_list); spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); } /* * Mark file system as fast commit ineligible, and record latest * ineligible transaction tid. This means until the recorded * transaction, commit operation would result in a full jbd2 commit. */ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle) { struct ext4_sb_info *sbi = EXT4_SB(sb); tid_t tid; if (!test_opt2(sb, JOURNAL_FAST_COMMIT) || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return; ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); if (handle && !IS_ERR(handle)) tid = handle->h_transaction->t_tid; else { read_lock(&sbi->s_journal->j_state_lock); tid = sbi->s_journal->j_running_transaction ? sbi->s_journal->j_running_transaction->t_tid : 0; read_unlock(&sbi->s_journal->j_state_lock); } spin_lock(&sbi->s_fc_lock); if (tid_gt(tid, sbi->s_fc_ineligible_tid)) sbi->s_fc_ineligible_tid = tid; spin_unlock(&sbi->s_fc_lock); WARN_ON(reason >= EXT4_FC_REASON_MAX); sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; } /* * Generic fast commit tracking function. If this is the first time this we are * called after a full commit, we initialize fast commit fields and then call * __fc_track_fn() with update = 0. If we have already been called after a full * commit, we pass update = 1. Based on that, the track function can determine * if it needs to track a field for the first time or if it needs to just * update the previously tracked value. * * If enqueue is set, this function enqueues the inode in fast commit list. */ static int ext4_fc_track_template( handle_t *handle, struct inode *inode, int (*__fc_track_fn)(handle_t *handle, struct inode *, void *, bool), void *args, int enqueue) { bool update = false; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); tid_t tid = 0; int ret; tid = handle->h_transaction->t_tid; mutex_lock(&ei->i_fc_lock); if (tid == ei->i_sync_tid) { update = true; } else { ext4_fc_reset_inode(inode); ei->i_sync_tid = tid; } ret = __fc_track_fn(handle, inode, args, update); mutex_unlock(&ei->i_fc_lock); if (!enqueue) return ret; spin_lock(&sbi->s_fc_lock); if (list_empty(&EXT4_I(inode)->i_fc_list)) list_add_tail(&EXT4_I(inode)->i_fc_list, (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) ? &sbi->s_fc_q[FC_Q_STAGING] : &sbi->s_fc_q[FC_Q_MAIN]); spin_unlock(&sbi->s_fc_lock); return ret; } struct __track_dentry_update_args { struct dentry *dentry; int op; }; /* __track_fn for directory entry updates. Called with ei->i_fc_lock. */ static int __track_dentry_update(handle_t *handle, struct inode *inode, void *arg, bool update) { struct ext4_fc_dentry_update *node; struct ext4_inode_info *ei = EXT4_I(inode); struct __track_dentry_update_args *dentry_update = (struct __track_dentry_update_args *)arg; struct dentry *dentry = dentry_update->dentry; struct inode *dir = dentry->d_parent->d_inode; struct super_block *sb = inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); mutex_unlock(&ei->i_fc_lock); if (IS_ENCRYPTED(dir)) { ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_ENCRYPTED_FILENAME, handle); mutex_lock(&ei->i_fc_lock); return -EOPNOTSUPP; } node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS); if (!node) { ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } node->fcd_op = dentry_update->op; node->fcd_parent = dir->i_ino; node->fcd_ino = inode->i_ino; if (dentry->d_name.len > DNAME_INLINE_LEN) { node->fcd_name.name = kmalloc(dentry->d_name.len, GFP_NOFS); if (!node->fcd_name.name) { kmem_cache_free(ext4_fc_dentry_cachep, node); ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } memcpy((u8 *)node->fcd_name.name, dentry->d_name.name, dentry->d_name.len); } else { memcpy(node->fcd_iname, dentry->d_name.name, dentry->d_name.len); node->fcd_name.name = node->fcd_iname; } node->fcd_name.len = dentry->d_name.len; spin_lock(&sbi->s_fc_lock); if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_STAGING]); else list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_MAIN]); spin_unlock(&sbi->s_fc_lock); mutex_lock(&ei->i_fc_lock); return 0; } void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; args.dentry = dentry; args.op = EXT4_FC_TAG_UNLINK; ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_unlink(inode, dentry, ret); } void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || (sbi->s_mount_state & EXT4_FC_REPLAY)) return; if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) return; __ext4_fc_track_unlink(handle, inode, dentry); } void __ext4_fc_track_link(handle_t *handle, struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; args.dentry = dentry; args.op = EXT4_FC_TAG_LINK; ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_link(inode, dentry, ret); } void ext4_fc_track_link(handle_t *handle, struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || (sbi->s_mount_state & EXT4_FC_REPLAY)) return; if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) return; __ext4_fc_track_link(handle, inode, dentry); } void __ext4_fc_track_create(handle_t *handle, struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; args.dentry = dentry; args.op = EXT4_FC_TAG_CREAT; ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_create(inode, dentry, ret); } void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || (sbi->s_mount_state & EXT4_FC_REPLAY)) return; if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) return; __ext4_fc_track_create(handle, inode, dentry); } /* __track_fn for inode tracking */ static int __track_inode(handle_t *handle, struct inode *inode, void *arg, bool update) { if (update) return -EEXIST; EXT4_I(inode)->i_fc_lblk_len = 0; return 0; } void ext4_fc_track_inode(handle_t *handle, struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int ret; if (S_ISDIR(inode->i_mode)) return; if (ext4_should_journal_data(inode)) { ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_INODE_JOURNAL_DATA, handle); return; } if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || (sbi->s_mount_state & EXT4_FC_REPLAY)) return; if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) return; ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1); trace_ext4_fc_track_inode(inode, ret); } struct __track_range_args { ext4_lblk_t start, end; }; /* __track_fn for tracking data updates */ static int __track_range(handle_t *handle, struct inode *inode, void *arg, bool update) { struct ext4_inode_info *ei = EXT4_I(inode); ext4_lblk_t oldstart; struct __track_range_args *__arg = (struct __track_range_args *)arg; if (inode->i_ino < EXT4_FIRST_INO(inode->i_sb)) { ext4_debug("Special inode %ld being modified\n", inode->i_ino); return -ECANCELED; } oldstart = ei->i_fc_lblk_start; if (update && ei->i_fc_lblk_len > 0) { ei->i_fc_lblk_start = min(ei->i_fc_lblk_start, __arg->start); ei->i_fc_lblk_len = max(oldstart + ei->i_fc_lblk_len - 1, __arg->end) - ei->i_fc_lblk_start + 1; } else { ei->i_fc_lblk_start = __arg->start; ei->i_fc_lblk_len = __arg->end - __arg->start + 1; } return 0; } void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct __track_range_args args; int ret; if (S_ISDIR(inode->i_mode)) return; if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || (sbi->s_mount_state & EXT4_FC_REPLAY)) return; if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) return; if (ext4_has_inline_data(inode)) { ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); return; } args.start = start; args.end = end; ret = ext4_fc_track_template(handle, inode, __track_range, &args, 1); trace_ext4_fc_track_range(inode, start, end, ret); } static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail) { int write_flags = REQ_SYNC; struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh; /* Add REQ_FUA | REQ_PREFLUSH only its tail */ if (test_opt(sb, BARRIER) && is_tail) write_flags |= REQ_FUA | REQ_PREFLUSH; lock_buffer(bh); set_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = ext4_end_buffer_io_sync; submit_bh(REQ_OP_WRITE, write_flags, bh); EXT4_SB(sb)->s_fc_bh = NULL; } /* Ext4 commit path routines */ /* memcpy to fc reserved space and update CRC */ static void *ext4_fc_memcpy(struct super_block *sb, void *dst, const void *src, int len, u32 *crc) { if (crc) *crc = ext4_chksum(EXT4_SB(sb), *crc, src, len); return memcpy(dst, src, len); } /* memzero and update CRC */ static void *ext4_fc_memzero(struct super_block *sb, void *dst, int len, u32 *crc) { void *ret; ret = memset(dst, 0, len); if (crc) *crc = ext4_chksum(EXT4_SB(sb), *crc, dst, len); return ret; } /* * Allocate len bytes on a fast commit buffer. * * During the commit time this function is used to manage fast commit * block space. We don't split a fast commit log onto different * blocks. So this function makes sure that if there's not enough space * on the current block, the remaining space in the current block is * marked as unused by adding EXT4_FC_TAG_PAD tag. In that case, * new block is from jbd2 and CRC is updated to reflect the padding * we added. */ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc) { struct ext4_fc_tl tl; struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh; int bsize = sbi->s_journal->j_blocksize; int ret, off = sbi->s_fc_bytes % bsize; int remaining; u8 *dst; /* * If 'len' is too long to fit in any block alongside a PAD tlv, then we * cannot fulfill the request. */ if (len > bsize - EXT4_FC_TAG_BASE_LEN) return NULL; if (!sbi->s_fc_bh) { ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh); if (ret) return NULL; sbi->s_fc_bh = bh; } dst = sbi->s_fc_bh->b_data + off; /* * Allocate the bytes in the current block if we can do so while still * leaving enough space for a PAD tlv. */ remaining = bsize - EXT4_FC_TAG_BASE_LEN - off; if (len <= remaining) { sbi->s_fc_bytes += len; return dst; } /* * Else, terminate the current block with a PAD tlv, then allocate a new * block and allocate the bytes at the start of that new block. */ tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_PAD); tl.fc_len = cpu_to_le16(remaining); ext4_fc_memcpy(sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, crc); ext4_fc_memzero(sb, dst + EXT4_FC_TAG_BASE_LEN, remaining, crc); ext4_fc_submit_bh(sb, false); ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh); if (ret) return NULL; sbi->s_fc_bh = bh; sbi->s_fc_bytes += bsize - off + len; return sbi->s_fc_bh->b_data; } /* * Complete a fast commit by writing tail tag. * * Writing tail tag marks the end of a fast commit. In order to guarantee * atomicity, after writing tail tag, even if there's space remaining * in the block, next commit shouldn't use it. That's why tail tag * has the length as that of the remaining space on the block. */ static int ext4_fc_write_tail(struct super_block *sb, u32 crc) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_tl tl; struct ext4_fc_tail tail; int off, bsize = sbi->s_journal->j_blocksize; u8 *dst; /* * ext4_fc_reserve_space takes care of allocating an extra block if * there's no enough space on this block for accommodating this tail. */ dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + sizeof(tail), &crc); if (!dst) return -ENOSPC; off = sbi->s_fc_bytes % bsize; tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_TAIL); tl.fc_len = cpu_to_le16(bsize - off + sizeof(struct ext4_fc_tail)); sbi->s_fc_bytes = round_up(sbi->s_fc_bytes, bsize); ext4_fc_memcpy(sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, &crc); dst += EXT4_FC_TAG_BASE_LEN; tail.fc_tid = cpu_to_le32(sbi->s_journal->j_running_transaction->t_tid); ext4_fc_memcpy(sb, dst, &tail.fc_tid, sizeof(tail.fc_tid), &crc); dst += sizeof(tail.fc_tid); tail.fc_crc = cpu_to_le32(crc); ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL); dst += sizeof(tail.fc_crc); memset(dst, 0, bsize - off); /* Don't leak uninitialized memory. */ ext4_fc_submit_bh(sb, true); return 0; } /* * Adds tag, length, value and updates CRC. Returns true if tlv was added. * Returns false if there's not enough space. */ static bool ext4_fc_add_tlv(struct super_block *sb, u16 tag, u16 len, u8 *val, u32 *crc) { struct ext4_fc_tl tl; u8 *dst; dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + len, crc); if (!dst) return false; tl.fc_tag = cpu_to_le16(tag); tl.fc_len = cpu_to_le16(len); ext4_fc_memcpy(sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, crc); ext4_fc_memcpy(sb, dst + EXT4_FC_TAG_BASE_LEN, val, len, crc); return true; } /* Same as above, but adds dentry tlv. */ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc, struct ext4_fc_dentry_update *fc_dentry) { struct ext4_fc_dentry_info fcd; struct ext4_fc_tl tl; int dlen = fc_dentry->fcd_name.len; u8 *dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + sizeof(fcd) + dlen, crc); if (!dst) return false; fcd.fc_parent_ino = cpu_to_le32(fc_dentry->fcd_parent); fcd.fc_ino = cpu_to_le32(fc_dentry->fcd_ino); tl.fc_tag = cpu_to_le16(fc_dentry->fcd_op); tl.fc_len = cpu_to_le16(sizeof(fcd) + dlen); ext4_fc_memcpy(sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, crc); dst += EXT4_FC_TAG_BASE_LEN; ext4_fc_memcpy(sb, dst, &fcd, sizeof(fcd), crc); dst += sizeof(fcd); ext4_fc_memcpy(sb, dst, fc_dentry->fcd_name.name, dlen, crc); dst += dlen; return true; } /* * Writes inode in the fast commit space under TLV with tag @tag. * Returns 0 on success, error on failure. */ static int ext4_fc_write_inode(struct inode *inode, u32 *crc) { struct ext4_inode_info *ei = EXT4_I(inode); int inode_len = EXT4_GOOD_OLD_INODE_SIZE; int ret; struct ext4_iloc iloc; struct ext4_fc_inode fc_inode; struct ext4_fc_tl tl; u8 *dst; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) inode_len += ei->i_extra_isize; fc_inode.fc_ino = cpu_to_le32(inode->i_ino); tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_INODE); tl.fc_len = cpu_to_le16(inode_len + sizeof(fc_inode.fc_ino)); ret = -ECANCELED; dst = ext4_fc_reserve_space(inode->i_sb, EXT4_FC_TAG_BASE_LEN + inode_len + sizeof(fc_inode.fc_ino), crc); if (!dst) goto err; if (!ext4_fc_memcpy(inode->i_sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, crc)) goto err; dst += EXT4_FC_TAG_BASE_LEN; if (!ext4_fc_memcpy(inode->i_sb, dst, &fc_inode, sizeof(fc_inode), crc)) goto err; dst += sizeof(fc_inode); if (!ext4_fc_memcpy(inode->i_sb, dst, (u8 *)ext4_raw_inode(&iloc), inode_len, crc)) goto err; ret = 0; err: brelse(iloc.bh); return ret; } /* * Writes updated data ranges for the inode in question. Updates CRC. * Returns 0 on success, error otherwise. */ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc) { ext4_lblk_t old_blk_size, cur_lblk_off, new_blk_size; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_map_blocks map; struct ext4_fc_add_range fc_ext; struct ext4_fc_del_range lrange; struct ext4_extent *ex; int ret; mutex_lock(&ei->i_fc_lock); if (ei->i_fc_lblk_len == 0) { mutex_unlock(&ei->i_fc_lock); return 0; } old_blk_size = ei->i_fc_lblk_start; new_blk_size = ei->i_fc_lblk_start + ei->i_fc_lblk_len - 1; ei->i_fc_lblk_len = 0; mutex_unlock(&ei->i_fc_lock); cur_lblk_off = old_blk_size; ext4_debug("will try writing %d to %d for inode %ld\n", cur_lblk_off, new_blk_size, inode->i_ino); while (cur_lblk_off <= new_blk_size) { map.m_lblk = cur_lblk_off; map.m_len = new_blk_size - cur_lblk_off + 1; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) return -ECANCELED; if (map.m_len == 0) { cur_lblk_off++; continue; } if (ret == 0) { lrange.fc_ino = cpu_to_le32(inode->i_ino); lrange.fc_lblk = cpu_to_le32(map.m_lblk); lrange.fc_len = cpu_to_le32(map.m_len); if (!ext4_fc_add_tlv(inode->i_sb, EXT4_FC_TAG_DEL_RANGE, sizeof(lrange), (u8 *)&lrange, crc)) return -ENOSPC; } else { unsigned int max = (map.m_flags & EXT4_MAP_UNWRITTEN) ? EXT_UNWRITTEN_MAX_LEN : EXT_INIT_MAX_LEN; /* Limit the number of blocks in one extent */ map.m_len = min(max, map.m_len); fc_ext.fc_ino = cpu_to_le32(inode->i_ino); ex = (struct ext4_extent *)&fc_ext.fc_ex; ex->ee_block = cpu_to_le32(map.m_lblk); ex->ee_len = cpu_to_le16(map.m_len); ext4_ext_store_pblock(ex, map.m_pblk); if (map.m_flags & EXT4_MAP_UNWRITTEN) ext4_ext_mark_unwritten(ex); else ext4_ext_mark_initialized(ex); if (!ext4_fc_add_tlv(inode->i_sb, EXT4_FC_TAG_ADD_RANGE, sizeof(fc_ext), (u8 *)&fc_ext, crc)) return -ENOSPC; } cur_lblk_off += map.m_len; } return 0; } /* Submit data for all the fast commit inodes */ static int ext4_fc_submit_inode_data_all(journal_t *journal) { struct super_block *sb = (struct super_block *)(journal->j_private); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *ei; int ret = 0; spin_lock(&sbi->s_fc_lock); list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING); while (atomic_read(&ei->i_fc_updates)) { DEFINE_WAIT(wait); prepare_to_wait(&ei->i_fc_wait, &wait, TASK_UNINTERRUPTIBLE); if (atomic_read(&ei->i_fc_updates)) { spin_unlock(&sbi->s_fc_lock); schedule(); spin_lock(&sbi->s_fc_lock); } finish_wait(&ei->i_fc_wait, &wait); } spin_unlock(&sbi->s_fc_lock); ret = jbd2_submit_inode_data(ei->jinode); if (ret) return ret; spin_lock(&sbi->s_fc_lock); } spin_unlock(&sbi->s_fc_lock); return ret; } /* Wait for completion of data for all the fast commit inodes */ static int ext4_fc_wait_inode_data_all(journal_t *journal) { struct super_block *sb = (struct super_block *)(journal->j_private); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *pos, *n; int ret = 0; spin_lock(&sbi->s_fc_lock); list_for_each_entry_safe(pos, n, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { if (!ext4_test_inode_state(&pos->vfs_inode, EXT4_STATE_FC_COMMITTING)) continue; spin_unlock(&sbi->s_fc_lock); ret = jbd2_wait_inode_data(journal, pos->jinode); if (ret) return ret; spin_lock(&sbi->s_fc_lock); } spin_unlock(&sbi->s_fc_lock); return 0; } /* Commit all the directory entry updates */ static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc) __acquires(&sbi->s_fc_lock) __releases(&sbi->s_fc_lock) { struct super_block *sb = (struct super_block *)(journal->j_private); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_dentry_update *fc_dentry, *fc_dentry_n; struct inode *inode; struct ext4_inode_info *ei, *ei_n; int ret; if (list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN])) return 0; list_for_each_entry_safe(fc_dentry, fc_dentry_n, &sbi->s_fc_dentry_q[FC_Q_MAIN], fcd_list) { if (fc_dentry->fcd_op != EXT4_FC_TAG_CREAT) { spin_unlock(&sbi->s_fc_lock); if (!ext4_fc_add_dentry_tlv(sb, crc, fc_dentry)) { ret = -ENOSPC; goto lock_and_exit; } spin_lock(&sbi->s_fc_lock); continue; } inode = NULL; list_for_each_entry_safe(ei, ei_n, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { if (ei->vfs_inode.i_ino == fc_dentry->fcd_ino) { inode = &ei->vfs_inode; break; } } /* * If we don't find inode in our list, then it was deleted, * in which case, we don't need to record it's create tag. */ if (!inode) continue; spin_unlock(&sbi->s_fc_lock); /* * We first write the inode and then the create dirent. This * allows the recovery code to create an unnamed inode first * and then link it to a directory entry. This allows us * to use namei.c routines almost as is and simplifies * the recovery code. */ ret = ext4_fc_write_inode(inode, crc); if (ret) goto lock_and_exit; ret = ext4_fc_write_inode_data(inode, crc); if (ret) goto lock_and_exit; if (!ext4_fc_add_dentry_tlv(sb, crc, fc_dentry)) { ret = -ENOSPC; goto lock_and_exit; } spin_lock(&sbi->s_fc_lock); } return 0; lock_and_exit: spin_lock(&sbi->s_fc_lock); return ret; } static int ext4_fc_perform_commit(journal_t *journal) { struct super_block *sb = (struct super_block *)(journal->j_private); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *iter; struct ext4_fc_head head; struct inode *inode; struct blk_plug plug; int ret = 0; u32 crc = 0; ret = ext4_fc_submit_inode_data_all(journal); if (ret) return ret; ret = ext4_fc_wait_inode_data_all(journal); if (ret) return ret; /* * If file system device is different from journal device, issue a cache * flush before we start writing fast commit blocks. */ if (journal->j_fs_dev != journal->j_dev) blkdev_issue_flush(journal->j_fs_dev); blk_start_plug(&plug); if (sbi->s_fc_bytes == 0) { /* * Add a head tag only if this is the first fast commit * in this TID. */ head.fc_features = cpu_to_le32(EXT4_FC_SUPPORTED_FEATURES); head.fc_tid = cpu_to_le32( sbi->s_journal->j_running_transaction->t_tid); if (!ext4_fc_add_tlv(sb, EXT4_FC_TAG_HEAD, sizeof(head), (u8 *)&head, &crc)) { ret = -ENOSPC; goto out; } } spin_lock(&sbi->s_fc_lock); ret = ext4_fc_commit_dentry_updates(journal, &crc); if (ret) { spin_unlock(&sbi->s_fc_lock); goto out; } list_for_each_entry(iter, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { inode = &iter->vfs_inode; if (!ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) continue; spin_unlock(&sbi->s_fc_lock); ret = ext4_fc_write_inode_data(inode, &crc); if (ret) goto out; ret = ext4_fc_write_inode(inode, &crc); if (ret) goto out; spin_lock(&sbi->s_fc_lock); } spin_unlock(&sbi->s_fc_lock); ret = ext4_fc_write_tail(sb, crc); out: blk_finish_plug(&plug); return ret; } static void ext4_fc_update_stats(struct super_block *sb, int status, u64 commit_time, int nblks) { struct ext4_fc_stats *stats = &EXT4_SB(sb)->s_fc_stats; ext4_debug("Fast commit ended with status = %d", status); if (status == EXT4_FC_STATUS_OK) { stats->fc_num_commits++; stats->fc_numblks += nblks; if (likely(stats->s_fc_avg_commit_time)) stats->s_fc_avg_commit_time = (commit_time + stats->s_fc_avg_commit_time * 3) / 4; else stats->s_fc_avg_commit_time = commit_time; } else if (status == EXT4_FC_STATUS_FAILED || status == EXT4_FC_STATUS_INELIGIBLE) { if (status == EXT4_FC_STATUS_FAILED) stats->fc_failed_commits++; stats->fc_ineligible_commits++; } else { stats->fc_skipped_commits++; } trace_ext4_fc_commit_stop(sb, nblks, status); } /* * The main commit entry point. Performs a fast commit for transaction * commit_tid if needed. If it's not possible to perform a fast commit * due to various reasons, we fall back to full commit. Returns 0 * on success, error otherwise. */ int ext4_fc_commit(journal_t *journal, tid_t commit_tid) { struct super_block *sb = (struct super_block *)(journal->j_private); struct ext4_sb_info *sbi = EXT4_SB(sb); int nblks = 0, ret, bsize = journal->j_blocksize; int subtid = atomic_read(&sbi->s_fc_subtid); int status = EXT4_FC_STATUS_OK, fc_bufs_before = 0; ktime_t start_time, commit_time; trace_ext4_fc_commit_start(sb); start_time = ktime_get(); if (!test_opt2(sb, JOURNAL_FAST_COMMIT)) return jbd2_complete_transaction(journal, commit_tid); restart_fc: ret = jbd2_fc_begin_commit(journal, commit_tid); if (ret == -EALREADY) { /* There was an ongoing commit, check if we need to restart */ if (atomic_read(&sbi->s_fc_subtid) <= subtid && tid_gt(commit_tid, journal->j_commit_sequence)) goto restart_fc; ext4_fc_update_stats(sb, EXT4_FC_STATUS_SKIPPED, 0, 0); return 0; } else if (ret) { /* * Commit couldn't start. Just update stats and perform a * full commit. */ ext4_fc_update_stats(sb, EXT4_FC_STATUS_FAILED, 0, 0); return jbd2_complete_transaction(journal, commit_tid); } /* * After establishing journal barrier via jbd2_fc_begin_commit(), check * if we are fast commit ineligible. */ if (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE)) { status = EXT4_FC_STATUS_INELIGIBLE; goto fallback; } fc_bufs_before = (sbi->s_fc_bytes + bsize - 1) / bsize; ret = ext4_fc_perform_commit(journal); if (ret < 0) { status = EXT4_FC_STATUS_FAILED; goto fallback; } nblks = (sbi->s_fc_bytes + bsize - 1) / bsize - fc_bufs_before; ret = jbd2_fc_wait_bufs(journal, nblks); if (ret < 0) { status = EXT4_FC_STATUS_FAILED; goto fallback; } atomic_inc(&sbi->s_fc_subtid); ret = jbd2_fc_end_commit(journal); /* * weight the commit time higher than the average time so we * don't react too strongly to vast changes in the commit time */ commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time)); ext4_fc_update_stats(sb, status, commit_time, nblks); return ret; fallback: ret = jbd2_fc_end_commit_fallback(journal); ext4_fc_update_stats(sb, status, 0, 0); return ret; } /* * Fast commit cleanup routine. This is called after every fast commit and * full commit. full is true if we are called after a full commit. */ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *iter, *iter_n; struct ext4_fc_dentry_update *fc_dentry; if (full && sbi->s_fc_bh) sbi->s_fc_bh = NULL; jbd2_fc_release_bufs(journal); spin_lock(&sbi->s_fc_lock); list_for_each_entry_safe(iter, iter_n, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { list_del_init(&iter->i_fc_list); ext4_clear_inode_state(&iter->vfs_inode, EXT4_STATE_FC_COMMITTING); if (tid_geq(tid, iter->i_sync_tid)) { ext4_fc_reset_inode(&iter->vfs_inode); } else if (full) { /* * We are called after a full commit, inode has been * modified while the commit was running. Re-enqueue * the inode into STAGING, which will then be splice * back into MAIN. This cannot happen during * fastcommit because the journal is locked all the * time in that case (and tid doesn't increase so * tid check above isn't reliable). */ list_add_tail(&EXT4_I(&iter->vfs_inode)->i_fc_list, &sbi->s_fc_q[FC_Q_STAGING]); } /* Make sure EXT4_STATE_FC_COMMITTING bit is clear */ smp_mb(); #if (BITS_PER_LONG < 64) wake_up_bit(&iter->i_state_flags, EXT4_STATE_FC_COMMITTING); #else wake_up_bit(&iter->i_flags, EXT4_STATE_FC_COMMITTING); #endif } while (!list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN])) { fc_dentry = list_first_entry(&sbi->s_fc_dentry_q[FC_Q_MAIN], struct ext4_fc_dentry_update, fcd_list); list_del_init(&fc_dentry->fcd_list); spin_unlock(&sbi->s_fc_lock); if (fc_dentry->fcd_name.name && fc_dentry->fcd_name.len > DNAME_INLINE_LEN) kfree(fc_dentry->fcd_name.name); kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry); spin_lock(&sbi->s_fc_lock); } list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING], &sbi->s_fc_dentry_q[FC_Q_MAIN]); list_splice_init(&sbi->s_fc_q[FC_Q_STAGING], &sbi->s_fc_q[FC_Q_MAIN]); if (tid_geq(tid, sbi->s_fc_ineligible_tid)) { sbi->s_fc_ineligible_tid = 0; ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); } if (full) sbi->s_fc_bytes = 0; spin_unlock(&sbi->s_fc_lock); trace_ext4_fc_stats(sb); } /* Ext4 Replay Path Routines */ /* Helper struct for dentry replay routines */ struct dentry_info_args { int parent_ino, dname_len, ino, inode_len; char *dname; }; /* Same as struct ext4_fc_tl, but uses native endianness fields */ struct ext4_fc_tl_mem { u16 fc_tag; u16 fc_len; }; static inline void tl_to_darg(struct dentry_info_args *darg, struct ext4_fc_tl_mem *tl, u8 *val) { struct ext4_fc_dentry_info fcd; memcpy(&fcd, val, sizeof(fcd)); darg->parent_ino = le32_to_cpu(fcd.fc_parent_ino); darg->ino = le32_to_cpu(fcd.fc_ino); darg->dname = val + offsetof(struct ext4_fc_dentry_info, fc_dname); darg->dname_len = tl->fc_len - sizeof(struct ext4_fc_dentry_info); } static inline void ext4_fc_get_tl(struct ext4_fc_tl_mem *tl, u8 *val) { struct ext4_fc_tl tl_disk; memcpy(&tl_disk, val, EXT4_FC_TAG_BASE_LEN); tl->fc_len = le16_to_cpu(tl_disk.fc_len); tl->fc_tag = le16_to_cpu(tl_disk.fc_tag); } /* Unlink replay function */ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { struct inode *inode, *old_parent; struct qstr entry; struct dentry_info_args darg; int ret = 0; tl_to_darg(&darg, tl, val); trace_ext4_fc_replay(sb, EXT4_FC_TAG_UNLINK, darg.ino, darg.parent_ino, darg.dname_len); entry.name = darg.dname; entry.len = darg.dname_len; inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode %d not found", darg.ino); return 0; } old_parent = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(old_parent)) { ext4_debug("Dir with inode %d not found", darg.parent_ino); iput(inode); return 0; } ret = __ext4_unlink(old_parent, &entry, inode, NULL); /* -ENOENT ok coz it might not exist anymore. */ if (ret == -ENOENT) ret = 0; iput(old_parent); iput(inode); return ret; } static int ext4_fc_replay_link_internal(struct super_block *sb, struct dentry_info_args *darg, struct inode *inode) { struct inode *dir = NULL; struct dentry *dentry_dir = NULL, *dentry_inode = NULL; struct qstr qstr_dname = QSTR_INIT(darg->dname, darg->dname_len); int ret = 0; dir = ext4_iget(sb, darg->parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(dir)) { ext4_debug("Dir with inode %d not found.", darg->parent_ino); dir = NULL; goto out; } dentry_dir = d_obtain_alias(dir); if (IS_ERR(dentry_dir)) { ext4_debug("Failed to obtain dentry"); dentry_dir = NULL; goto out; } dentry_inode = d_alloc(dentry_dir, &qstr_dname); if (!dentry_inode) { ext4_debug("Inode dentry not created."); ret = -ENOMEM; goto out; } ret = __ext4_link(dir, inode, dentry_inode); /* * It's possible that link already existed since data blocks * for the dir in question got persisted before we crashed OR * we replayed this tag and crashed before the entire replay * could complete. */ if (ret && ret != -EEXIST) { ext4_debug("Failed to link\n"); goto out; } ret = 0; out: if (dentry_dir) { d_drop(dentry_dir); dput(dentry_dir); } else if (dir) { iput(dir); } if (dentry_inode) { d_drop(dentry_inode); dput(dentry_inode); } return ret; } /* Link replay function */ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { struct inode *inode; struct dentry_info_args darg; int ret = 0; tl_to_darg(&darg, tl, val); trace_ext4_fc_replay(sb, EXT4_FC_TAG_LINK, darg.ino, darg.parent_ino, darg.dname_len); inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode not found."); return 0; } ret = ext4_fc_replay_link_internal(sb, &darg, inode); iput(inode); return ret; } /* * Record all the modified inodes during replay. We use this later to setup * block bitmaps correctly. */ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino) { struct ext4_fc_replay_state *state; int i; state = &EXT4_SB(sb)->s_fc_replay_state; for (i = 0; i < state->fc_modified_inodes_used; i++) if (state->fc_modified_inodes[i] == ino) return 0; if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) { int *fc_modified_inodes; fc_modified_inodes = krealloc(state->fc_modified_inodes, sizeof(int) * (state->fc_modified_inodes_size + EXT4_FC_REPLAY_REALLOC_INCREMENT), GFP_KERNEL); if (!fc_modified_inodes) return -ENOMEM; state->fc_modified_inodes = fc_modified_inodes; state->fc_modified_inodes_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; } state->fc_modified_inodes[state->fc_modified_inodes_used++] = ino; return 0; } /* * Inode replay function */ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { struct ext4_fc_inode fc_inode; struct ext4_inode *raw_inode; struct ext4_inode *raw_fc_inode; struct inode *inode = NULL; struct ext4_iloc iloc; int inode_len, ino, ret, tag = tl->fc_tag; struct ext4_extent_header *eh; memcpy(&fc_inode, val, sizeof(fc_inode)); ino = le32_to_cpu(fc_inode.fc_ino); trace_ext4_fc_replay(sb, tag, ino, 0, 0); inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (!IS_ERR(inode)) { ext4_ext_clear_bb(inode); iput(inode); } inode = NULL; ret = ext4_fc_record_modified_inode(sb, ino); if (ret) goto out; raw_fc_inode = (struct ext4_inode *) (val + offsetof(struct ext4_fc_inode, fc_raw_inode)); ret = ext4_get_fc_inode_loc(sb, ino, &iloc); if (ret) goto out; inode_len = tl->fc_len - sizeof(struct ext4_fc_inode); raw_inode = ext4_raw_inode(&iloc); memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block)); memcpy(&raw_inode->i_generation, &raw_fc_inode->i_generation, inode_len - offsetof(struct ext4_inode, i_generation)); if (le32_to_cpu(raw_inode->i_flags) & EXT4_EXTENTS_FL) { eh = (struct ext4_extent_header *)(&raw_inode->i_block[0]); if (eh->eh_magic != EXT4_EXT_MAGIC) { memset(eh, 0, sizeof(*eh)); eh->eh_magic = EXT4_EXT_MAGIC; eh->eh_max = cpu_to_le16( (sizeof(raw_inode->i_block) - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent)); } } else if (le32_to_cpu(raw_inode->i_flags) & EXT4_INLINE_DATA_FL) { memcpy(raw_inode->i_block, raw_fc_inode->i_block, sizeof(raw_inode->i_block)); } /* Immediately update the inode on disk. */ ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh); if (ret) goto out; ret = sync_dirty_buffer(iloc.bh); if (ret) goto out; ret = ext4_mark_inode_used(sb, ino); if (ret) goto out; /* Given that we just wrote the inode on disk, this SHOULD succeed. */ inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode not found."); return -EFSCORRUPTED; } /* * Our allocator could have made different decisions than before * crashing. This should be fixed but until then, we calculate * the number of blocks the inode. */ ext4_ext_replay_set_iblocks(inode); inode->i_generation = le32_to_cpu(ext4_raw_inode(&iloc)->i_generation); ext4_reset_inode_seed(inode); ext4_inode_csum_set(inode, ext4_raw_inode(&iloc), EXT4_I(inode)); ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh); sync_dirty_buffer(iloc.bh); brelse(iloc.bh); out: iput(inode); if (!ret) blkdev_issue_flush(sb->s_bdev); return 0; } /* * Dentry create replay function. * * EXT4_FC_TAG_CREAT is preceded by EXT4_FC_TAG_INODE_FULL. Which means, the * inode for which we are trying to create a dentry here, should already have * been replayed before we start here. */ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { int ret = 0; struct inode *inode = NULL; struct inode *dir = NULL; struct dentry_info_args darg; tl_to_darg(&darg, tl, val); trace_ext4_fc_replay(sb, EXT4_FC_TAG_CREAT, darg.ino, darg.parent_ino, darg.dname_len); /* This takes care of update group descriptor and other metadata */ ret = ext4_mark_inode_used(sb, darg.ino); if (ret) goto out; inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("inode %d not found.", darg.ino); inode = NULL; ret = -EINVAL; goto out; } if (S_ISDIR(inode->i_mode)) { /* * If we are creating a directory, we need to make sure that the * dot and dot dot dirents are setup properly. */ dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(dir)) { ext4_debug("Dir %d not found.", darg.ino); goto out; } ret = ext4_init_new_dir(NULL, dir, inode); iput(dir); if (ret) { ret = 0; goto out; } } ret = ext4_fc_replay_link_internal(sb, &darg, inode); if (ret) goto out; set_nlink(inode, 1); ext4_mark_inode_dirty(NULL, inode); out: if (inode) iput(inode); return ret; } /* * Record physical disk regions which are in use as per fast commit area, * and used by inodes during replay phase. Our simple replay phase * allocator excludes these regions from allocation. */ int ext4_fc_record_regions(struct super_block *sb, int ino, ext4_lblk_t lblk, ext4_fsblk_t pblk, int len, int replay) { struct ext4_fc_replay_state *state; struct ext4_fc_alloc_region *region; state = &EXT4_SB(sb)->s_fc_replay_state; /* * during replay phase, the fc_regions_valid may not same as * fc_regions_used, update it when do new additions. */ if (replay && state->fc_regions_used != state->fc_regions_valid) state->fc_regions_used = state->fc_regions_valid; if (state->fc_regions_used == state->fc_regions_size) { struct ext4_fc_alloc_region *fc_regions; fc_regions = krealloc(state->fc_regions, sizeof(struct ext4_fc_alloc_region) * (state->fc_regions_size + EXT4_FC_REPLAY_REALLOC_INCREMENT), GFP_KERNEL); if (!fc_regions) return -ENOMEM; state->fc_regions_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; state->fc_regions = fc_regions; } region = &state->fc_regions[state->fc_regions_used++]; region->ino = ino; region->lblk = lblk; region->pblk = pblk; region->len = len; if (replay) state->fc_regions_valid++; return 0; } /* Replay add range tag */ static int ext4_fc_replay_add_range(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { struct ext4_fc_add_range fc_add_ex; struct ext4_extent newex, *ex; struct inode *inode; ext4_lblk_t start, cur; int remaining, len; ext4_fsblk_t start_pblk; struct ext4_map_blocks map; struct ext4_ext_path *path = NULL; int ret; memcpy(&fc_add_ex, val, sizeof(fc_add_ex)); ex = (struct ext4_extent *)&fc_add_ex.fc_ex; trace_ext4_fc_replay(sb, EXT4_FC_TAG_ADD_RANGE, le32_to_cpu(fc_add_ex.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_get_actual_len(ex)); inode = ext4_iget(sb, le32_to_cpu(fc_add_ex.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode not found."); return 0; } ret = ext4_fc_record_modified_inode(sb, inode->i_ino); if (ret) goto out; start = le32_to_cpu(ex->ee_block); start_pblk = ext4_ext_pblock(ex); len = ext4_ext_get_actual_len(ex); cur = start; remaining = len; ext4_debug("ADD_RANGE, lblk %d, pblk %lld, len %d, unwritten %d, inode %ld\n", start, start_pblk, len, ext4_ext_is_unwritten(ex), inode->i_ino); while (remaining > 0) { map.m_lblk = cur; map.m_len = remaining; map.m_pblk = 0; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) goto out; if (ret == 0) { /* Range is not mapped */ path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) goto out; memset(&newex, 0, sizeof(newex)); newex.ee_block = cpu_to_le32(cur); ext4_ext_store_pblock( &newex, start_pblk + cur - start); newex.ee_len = cpu_to_le16(map.m_len); if (ext4_ext_is_unwritten(ex)) ext4_ext_mark_unwritten(&newex); down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_insert_extent( NULL, inode, &path, &newex, 0); up_write((&EXT4_I(inode)->i_data_sem)); ext4_ext_drop_refs(path); kfree(path); if (ret) goto out; goto next; } if (start_pblk + cur - start != map.m_pblk) { /* * Logical to physical mapping changed. This can happen * if this range was removed and then reallocated to * map to new physical blocks during a fast commit. */ ret = ext4_ext_replay_update_ex(inode, cur, map.m_len, ext4_ext_is_unwritten(ex), start_pblk + cur - start); if (ret) goto out; /* * Mark the old blocks as free since they aren't used * anymore. We maintain an array of all the modified * inodes. In case these blocks are still used at either * a different logical range in the same inode or in * some different inode, we will mark them as allocated * at the end of the FC replay using our array of * modified inodes. */ ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); goto next; } /* Range is mapped and needs a state change */ ext4_debug("Converting from %ld to %d %lld", map.m_flags & EXT4_MAP_UNWRITTEN, ext4_ext_is_unwritten(ex), map.m_pblk); ret = ext4_ext_replay_update_ex(inode, cur, map.m_len, ext4_ext_is_unwritten(ex), map.m_pblk); if (ret) goto out; /* * We may have split the extent tree while toggling the state. * Try to shrink the extent tree now. */ ext4_ext_replay_shrink_inode(inode, start + len); next: cur += map.m_len; remaining -= map.m_len; } ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >> sb->s_blocksize_bits); out: iput(inode); return 0; } /* Replay DEL_RANGE tag */ static int ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { struct inode *inode; struct ext4_fc_del_range lrange; struct ext4_map_blocks map; ext4_lblk_t cur, remaining; int ret; memcpy(&lrange, val, sizeof(lrange)); cur = le32_to_cpu(lrange.fc_lblk); remaining = le32_to_cpu(lrange.fc_len); trace_ext4_fc_replay(sb, EXT4_FC_TAG_DEL_RANGE, le32_to_cpu(lrange.fc_ino), cur, remaining); inode = ext4_iget(sb, le32_to_cpu(lrange.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode %d not found", le32_to_cpu(lrange.fc_ino)); return 0; } ret = ext4_fc_record_modified_inode(sb, inode->i_ino); if (ret) goto out; ext4_debug("DEL_RANGE, inode %ld, lblk %d, len %d\n", inode->i_ino, le32_to_cpu(lrange.fc_lblk), le32_to_cpu(lrange.fc_len)); while (remaining > 0) { map.m_lblk = cur; map.m_len = remaining; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) goto out; if (ret > 0) { remaining -= ret; cur += ret; ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); } else { remaining -= map.m_len; cur += map.m_len; } } down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_remove_space(inode, le32_to_cpu(lrange.fc_lblk), le32_to_cpu(lrange.fc_lblk) + le32_to_cpu(lrange.fc_len) - 1); up_write(&EXT4_I(inode)->i_data_sem); if (ret) goto out; ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >> sb->s_blocksize_bits); ext4_mark_inode_dirty(NULL, inode); out: iput(inode); return 0; } static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) { struct ext4_fc_replay_state *state; struct inode *inode; struct ext4_ext_path *path = NULL; struct ext4_map_blocks map; int i, ret, j; ext4_lblk_t cur, end; state = &EXT4_SB(sb)->s_fc_replay_state; for (i = 0; i < state->fc_modified_inodes_used; i++) { inode = ext4_iget(sb, state->fc_modified_inodes[i], EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode %d not found.", state->fc_modified_inodes[i]); continue; } cur = 0; end = EXT_MAX_BLOCKS; while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) break; if (ret > 0) { path = ext4_find_extent(inode, map.m_lblk, NULL, 0); if (!IS_ERR(path)) { for (j = 0; j < path->p_depth; j++) ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, 1); ext4_ext_drop_refs(path); kfree(path); } cur += ret; ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 1); } else { cur = cur + (map.m_len ? map.m_len : 1); } } iput(inode); } } /* * Check if block is in excluded regions for block allocation. The simple * allocator that runs during replay phase is calls this function to see * if it is okay to use a block. */ bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t blk) { int i; struct ext4_fc_replay_state *state; state = &EXT4_SB(sb)->s_fc_replay_state; for (i = 0; i < state->fc_regions_valid; i++) { if (state->fc_regions[i].ino == 0 || state->fc_regions[i].len == 0) continue; if (blk >= state->fc_regions[i].pblk && blk < state->fc_regions[i].pblk + state->fc_regions[i].len) return true; } return false; } /* Cleanup function called after replay */ void ext4_fc_replay_cleanup(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); sbi->s_mount_state &= ~EXT4_FC_REPLAY; kfree(sbi->s_fc_replay_state.fc_regions); kfree(sbi->s_fc_replay_state.fc_modified_inodes); } static bool ext4_fc_value_len_isvalid(struct ext4_sb_info *sbi, int tag, int len) { switch (tag) { case EXT4_FC_TAG_ADD_RANGE: return len == sizeof(struct ext4_fc_add_range); case EXT4_FC_TAG_DEL_RANGE: return len == sizeof(struct ext4_fc_del_range); case EXT4_FC_TAG_CREAT: case EXT4_FC_TAG_LINK: case EXT4_FC_TAG_UNLINK: len -= sizeof(struct ext4_fc_dentry_info); return len >= 1 && len <= EXT4_NAME_LEN; case EXT4_FC_TAG_INODE: len -= sizeof(struct ext4_fc_inode); return len >= EXT4_GOOD_OLD_INODE_SIZE && len <= sbi->s_inode_size; case EXT4_FC_TAG_PAD: return true; /* padding can have any length */ case EXT4_FC_TAG_TAIL: return len >= sizeof(struct ext4_fc_tail); case EXT4_FC_TAG_HEAD: return len == sizeof(struct ext4_fc_head); } return false; } /* * Recovery Scan phase handler * * This function is called during the scan phase and is responsible * for doing following things: * - Make sure the fast commit area has valid tags for replay * - Count number of tags that need to be replayed by the replay handler * - Verify CRC * - Create a list of excluded blocks for allocation during replay phase * * This function returns JBD2_FC_REPLAY_CONTINUE to indicate that SCAN is * incomplete and JBD2 should send more blocks. It returns JBD2_FC_REPLAY_STOP * to indicate that scan has finished and JBD2 can now start replay phase. * It returns a negative error to indicate that there was an error. At the end * of a successful scan phase, sbi->s_fc_replay_state.fc_replay_num_tags is set * to indicate the number of tags that need to replayed during the replay phase. */ static int ext4_fc_replay_scan(journal_t *journal, struct buffer_head *bh, int off, tid_t expected_tid) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_replay_state *state; int ret = JBD2_FC_REPLAY_CONTINUE; struct ext4_fc_add_range ext; struct ext4_fc_tl_mem tl; struct ext4_fc_tail tail; __u8 *start, *end, *cur, *val; struct ext4_fc_head head; struct ext4_extent *ex; state = &sbi->s_fc_replay_state; start = (u8 *)bh->b_data; end = start + journal->j_blocksize; if (state->fc_replay_expected_off == 0) { state->fc_cur_tag = 0; state->fc_replay_num_tags = 0; state->fc_crc = 0; state->fc_regions = NULL; state->fc_regions_valid = state->fc_regions_used = state->fc_regions_size = 0; /* Check if we can stop early */ if (le16_to_cpu(((struct ext4_fc_tl *)start)->fc_tag) != EXT4_FC_TAG_HEAD) return 0; } if (off != state->fc_replay_expected_off) { ret = -EFSCORRUPTED; goto out_err; } state->fc_replay_expected_off++; for (cur = start; cur <= end - EXT4_FC_TAG_BASE_LEN; cur = cur + EXT4_FC_TAG_BASE_LEN + tl.fc_len) { ext4_fc_get_tl(&tl, cur); val = cur + EXT4_FC_TAG_BASE_LEN; if (tl.fc_len > end - val || !ext4_fc_value_len_isvalid(sbi, tl.fc_tag, tl.fc_len)) { ret = state->fc_replay_num_tags ? JBD2_FC_REPLAY_STOP : -ECANCELED; goto out_err; } ext4_debug("Scan phase, tag:%s, blk %lld\n", tag2str(tl.fc_tag), bh->b_blocknr); switch (tl.fc_tag) { case EXT4_FC_TAG_ADD_RANGE: memcpy(&ext, val, sizeof(ext)); ex = (struct ext4_extent *)&ext.fc_ex; ret = ext4_fc_record_regions(sb, le32_to_cpu(ext.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), ext4_ext_get_actual_len(ex), 0); if (ret < 0) break; ret = JBD2_FC_REPLAY_CONTINUE; fallthrough; case EXT4_FC_TAG_DEL_RANGE: case EXT4_FC_TAG_LINK: case EXT4_FC_TAG_UNLINK: case EXT4_FC_TAG_CREAT: case EXT4_FC_TAG_INODE: case EXT4_FC_TAG_PAD: state->fc_cur_tag++; state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, EXT4_FC_TAG_BASE_LEN + tl.fc_len); break; case EXT4_FC_TAG_TAIL: state->fc_cur_tag++; memcpy(&tail, val, sizeof(tail)); state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, EXT4_FC_TAG_BASE_LEN + offsetof(struct ext4_fc_tail, fc_crc)); if (le32_to_cpu(tail.fc_tid) == expected_tid && le32_to_cpu(tail.fc_crc) == state->fc_crc) { state->fc_replay_num_tags = state->fc_cur_tag; state->fc_regions_valid = state->fc_regions_used; } else { ret = state->fc_replay_num_tags ? JBD2_FC_REPLAY_STOP : -EFSBADCRC; } state->fc_crc = 0; break; case EXT4_FC_TAG_HEAD: memcpy(&head, val, sizeof(head)); if (le32_to_cpu(head.fc_features) & ~EXT4_FC_SUPPORTED_FEATURES) { ret = -EOPNOTSUPP; break; } if (le32_to_cpu(head.fc_tid) != expected_tid) { ret = JBD2_FC_REPLAY_STOP; break; } state->fc_cur_tag++; state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, EXT4_FC_TAG_BASE_LEN + tl.fc_len); break; default: ret = state->fc_replay_num_tags ? JBD2_FC_REPLAY_STOP : -ECANCELED; } if (ret < 0 || ret == JBD2_FC_REPLAY_STOP) break; } out_err: trace_ext4_fc_replay_scan(sb, ret, off); return ret; } /* * Main recovery path entry point. * The meaning of return codes is similar as above. */ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, enum passtype pass, int off, tid_t expected_tid) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_tl_mem tl; __u8 *start, *end, *cur, *val; int ret = JBD2_FC_REPLAY_CONTINUE; struct ext4_fc_replay_state *state = &sbi->s_fc_replay_state; struct ext4_fc_tail tail; if (pass == PASS_SCAN) { state->fc_current_pass = PASS_SCAN; return ext4_fc_replay_scan(journal, bh, off, expected_tid); } if (state->fc_current_pass != pass) { state->fc_current_pass = pass; sbi->s_mount_state |= EXT4_FC_REPLAY; } if (!sbi->s_fc_replay_state.fc_replay_num_tags) { ext4_debug("Replay stops\n"); ext4_fc_set_bitmaps_and_counters(sb); return 0; } #ifdef CONFIG_EXT4_DEBUG if (sbi->s_fc_debug_max_replay && off >= sbi->s_fc_debug_max_replay) { pr_warn("Dropping fc block %d because max_replay set\n", off); return JBD2_FC_REPLAY_STOP; } #endif start = (u8 *)bh->b_data; end = start + journal->j_blocksize; for (cur = start; cur <= end - EXT4_FC_TAG_BASE_LEN; cur = cur + EXT4_FC_TAG_BASE_LEN + tl.fc_len) { ext4_fc_get_tl(&tl, cur); val = cur + EXT4_FC_TAG_BASE_LEN; if (state->fc_replay_num_tags == 0) { ret = JBD2_FC_REPLAY_STOP; ext4_fc_set_bitmaps_and_counters(sb); break; } ext4_debug("Replay phase, tag:%s\n", tag2str(tl.fc_tag)); state->fc_replay_num_tags--; switch (tl.fc_tag) { case EXT4_FC_TAG_LINK: ret = ext4_fc_replay_link(sb, &tl, val); break; case EXT4_FC_TAG_UNLINK: ret = ext4_fc_replay_unlink(sb, &tl, val); break; case EXT4_FC_TAG_ADD_RANGE: ret = ext4_fc_replay_add_range(sb, &tl, val); break; case EXT4_FC_TAG_CREAT: ret = ext4_fc_replay_create(sb, &tl, val); break; case EXT4_FC_TAG_DEL_RANGE: ret = ext4_fc_replay_del_range(sb, &tl, val); break; case EXT4_FC_TAG_INODE: ret = ext4_fc_replay_inode(sb, &tl, val); break; case EXT4_FC_TAG_PAD: trace_ext4_fc_replay(sb, EXT4_FC_TAG_PAD, 0, tl.fc_len, 0); break; case EXT4_FC_TAG_TAIL: trace_ext4_fc_replay(sb, EXT4_FC_TAG_TAIL, 0, tl.fc_len, 0); memcpy(&tail, val, sizeof(tail)); WARN_ON(le32_to_cpu(tail.fc_tid) != expected_tid); break; case EXT4_FC_TAG_HEAD: break; default: trace_ext4_fc_replay(sb, tl.fc_tag, 0, tl.fc_len, 0); ret = -ECANCELED; break; } if (ret < 0) break; ret = JBD2_FC_REPLAY_CONTINUE; } return ret; } void ext4_fc_init(struct super_block *sb, journal_t *journal) { /* * We set replay callback even if fast commit disabled because we may * could still have fast commit blocks that need to be replayed even if * fast commit has now been turned off. */ journal->j_fc_replay_callback = ext4_fc_replay; if (!test_opt2(sb, JOURNAL_FAST_COMMIT)) return; journal->j_fc_cleanup_callback = ext4_fc_cleanup; } static const char * const fc_ineligible_reasons[] = { [EXT4_FC_REASON_XATTR] = "Extended attributes changed", [EXT4_FC_REASON_CROSS_RENAME] = "Cross rename", [EXT4_FC_REASON_JOURNAL_FLAG_CHANGE] = "Journal flag changed", [EXT4_FC_REASON_NOMEM] = "Insufficient memory", [EXT4_FC_REASON_SWAP_BOOT] = "Swap boot", [EXT4_FC_REASON_RESIZE] = "Resize", [EXT4_FC_REASON_RENAME_DIR] = "Dir renamed", [EXT4_FC_REASON_FALLOC_RANGE] = "Falloc range op", [EXT4_FC_REASON_INODE_JOURNAL_DATA] = "Data journalling", [EXT4_FC_REASON_ENCRYPTED_FILENAME] = "Encrypted filename", }; int ext4_fc_info_show(struct seq_file *seq, void *v) { struct ext4_sb_info *sbi = EXT4_SB((struct super_block *)seq->private); struct ext4_fc_stats *stats = &sbi->s_fc_stats; int i; if (v != SEQ_START_TOKEN) return 0; seq_printf(seq, "fc stats:\n%ld commits\n%ld ineligible\n%ld numblks\n%lluus avg_commit_time\n", stats->fc_num_commits, stats->fc_ineligible_commits, stats->fc_numblks, div_u64(stats->s_fc_avg_commit_time, 1000)); seq_puts(seq, "Ineligible reasons:\n"); for (i = 0; i < EXT4_FC_REASON_MAX; i++) seq_printf(seq, "\"%s\":\t%d\n", fc_ineligible_reasons[i], stats->fc_ineligible_reason_count[i]); return 0; } int __init ext4_fc_init_dentry_cache(void) { ext4_fc_dentry_cachep = KMEM_CACHE(ext4_fc_dentry_update, SLAB_RECLAIM_ACCOUNT); if (ext4_fc_dentry_cachep == NULL) return -ENOMEM; return 0; } void ext4_fc_destroy_dentry_cache(void) { kmem_cache_destroy(ext4_fc_dentry_cachep); } |
| 176 159 159 158 159 253 14 2 74 5 91 42 26 26 7 2 10 189 1 90 192 192 203 205 205 4 1 1 1 201 2 8 192 192 41 15 15 28 28 3 3 3 3 53 53 3 3 2 6 41 28 3 209 164 48 3 190 2 6 10 7 9 7 9 25 26 1 4 17 32 4 28 4 28 1 1 19 3 1 2 1 17 1 17 18 6 35 3 32 6 6 29 29 13 4 38 38 38 11 7 8 12 37 1 37 37 193 11 4 7 250 2 249 23 60 1 46 16 57 5 207 1 1 5 14 3 184 2 153 16 13 21 13 5 2 5 13 13 12 10 175 3 10 165 171 170 166 4 170 170 4 4 3 8 161 161 7 159 159 8 153 17 204 172 172 3 175 250 251 216 190 201 3 2 7 185 57 14 1 4 175 151 193 2 2 11 12 12 6 5 5 2 3 5 5 3 2 1 1 1 2 1 2 2 1 9 1 8 5 8 4 4 2 1 2 15 15 12 1 2 2 6 9 11 4 8 7 12 3 8 7 12 3 12 3 13 2 30 9 21 2 1 2 17 6 17 17 16 15 3 2 1 2 1 3 2 1 2 1 18 1 17 3 3 11 6 4 7 3 7 7 20 1 13 6 9 1 2 6 3 5 5 3 6 2 2 2 7 1 1 5 1 1 3 2 2 6 3 1 2 2 2 1 10 1 3 6 9 9 2 4 4 4 3 1 1 1 1 8 1 7 1 1 5 4 2 1 2 1 1 1 1 10 1 3 6 9 4 3 8 6 2 2 2 1 1 10 1 1 8 2 2 4 4 1 1 8 1 7 2 1 4 2 1 2 8 2 6 1 1 4 3 1 1 8 1 7 2 1 4 3 2 6 1 3 4 3 23 1 22 8 12 12 4 3 2 6 1 1 9 2 7 7 11 1 1 3 6 9 2 2 5 6 1 7 1 6 6 8 1 1 6 1 1 4 3 2 5 1 1 3 1 5 1 4 1 5 1 4 2 15 1 1 13 3 1 9 4 6 11 1 10 10 6 5 1 4 4 1 2 2 2 2 8 2 6 6 6 1 1 4 4 11 1 5 5 5 1 12 1 1 4 6 6 557 562 68 339 333 2 47 6 6 29 3 9 5 30 20 3 9 2 7 6 1 4 1 9 2 8 4 10 2 1 10 8 7 8 6 12 11 2 9 11 7 8 5 5 5 15 11 5 8 8 6 11 12 6 6 4 2 103 103 88 15 104 40 40 39 1 40 1 7 7 7 14 9 18 14 14 6 6 6 3 3 3 17 13 13 4 12 9 7 89 199 198 199 166 166 166 8 25 4 11 11 11 3 11 11 3 189 188 1 188 3 3 192 189 2 19 21 21 21 21 210 5 33 32 2 16 2 4 2 18 2 2 2 3 2 2 6 6 2 12 12 12 1 1 10 8 6 2 2 6 6 19 19 17 18 18 16 1 3 15 18 38 10 10 46 47 47 47 47 51 50 4 1 2 1 2 2 23 23 22 21 1 23 23 6 44 171 171 137 10 5 15 1 76 75 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 | // 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) 2001-2003 Intel Corp. * Copyright (c) 2001-2002 Nokia, Inc. * Copyright (c) 2001 La Monte H.P. Yarroll * * This file is part of the SCTP kernel implementation * * These functions interface with the sockets layer to implement the * SCTP Extensions for the Sockets API. * * Note that the descriptions from the specification are USER level * functions--this file is the functions which populate the struct proto * for SCTP which is the BOTTOM of the sockets interface. * * 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> * Narasimha Budihal <narsi@refcode.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Xingang Guo <xingang.guo@intel.com> * Daisy Chang <daisyc@us.ibm.com> * Sridhar Samudrala <samudrala@us.ibm.com> * Inaky Perez-Gonzalez <inaky.gonzalez@intel.com> * Ardelle Fan <ardelle.fan@intel.com> * Ryan Layer <rmlayer@us.ibm.com> * Anup Pemmaiah <pemmaiah@cc.usu.edu> * Kevin Gao <kevin.gao@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <crypto/hash.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/wait.h> #include <linux/time.h> #include <linux/sched/signal.h> #include <linux/ip.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/compat.h> #include <linux/rhashtable.h> #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> #include <net/ipv6.h> #include <net/inet_common.h> #include <net/busy_poll.h> #include <linux/socket.h> /* for sa_family_t */ #include <linux/export.h> #include <net/sock.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> /* Forward declarations for internal helper functions. */ static bool sctp_writeable(const struct sock *sk); static void sctp_wfree(struct sk_buff *skb); static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, size_t msg_len); static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p); static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p); static int sctp_wait_for_accept(struct sock *sk, long timeo); static void sctp_wait_for_close(struct sock *sk, long timeo); static void sctp_destruct_sock(struct sock *sk); static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, union sctp_addr *addr, int len); static int sctp_bindx_add(struct sock *, struct sockaddr *, int); static int sctp_bindx_rem(struct sock *, struct sockaddr *, int); static int sctp_send_asconf_add_ip(struct sock *, struct sockaddr *, int); static int sctp_send_asconf_del_ip(struct sock *, struct sockaddr *, int); static int sctp_send_asconf(struct sctp_association *asoc, struct sctp_chunk *chunk); static int sctp_do_bind(struct sock *, union sctp_addr *, int); static int sctp_autobind(struct sock *sk); static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sctp_association *assoc, enum sctp_socket_type type); static unsigned long sctp_memory_pressure; static atomic_long_t sctp_memory_allocated; struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) { WRITE_ONCE(sctp_memory_pressure, 1); } /* Get the sndbuf space available at the time on the association. */ static inline int sctp_wspace(struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; return asoc->ep->sndbuf_policy ? sk->sk_sndbuf - asoc->sndbuf_used : sk_stream_wspace(sk); } /* Increment the used sndbuf space count of the corresponding association by * the size of the outgoing data chunk. * Also, set the skb destructor for sndbuf accounting later. * * Since it is always 1-1 between chunk and skb, and also a new skb is always * allocated for chunk bundling in sctp_packet_transmit(), we can use the * destructor in the data chunk skb for the purpose of the sndbuf space * tracking. */ static inline void sctp_set_owner_w(struct sctp_chunk *chunk) { struct sctp_association *asoc = chunk->asoc; struct sock *sk = asoc->base.sk; /* The sndbuf space is tracked per association. */ sctp_association_hold(asoc); if (chunk->shkey) sctp_auth_shkey_hold(chunk->shkey); skb_set_owner_w(chunk->skb, sk); chunk->skb->destructor = sctp_wfree; /* Save the chunk pointer in skb for sctp_wfree to use later. */ skb_shinfo(chunk->skb)->destructor_arg = chunk; refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); asoc->sndbuf_used += chunk->skb->truesize + sizeof(struct sctp_chunk); sk_wmem_queued_add(sk, chunk->skb->truesize + sizeof(struct sctp_chunk)); sk_mem_charge(sk, chunk->skb->truesize); } static void sctp_clear_owner_w(struct sctp_chunk *chunk) { skb_orphan(chunk->skb); } #define traverse_and_process() \ do { \ msg = chunk->msg; \ if (msg == prev_msg) \ continue; \ list_for_each_entry(c, &msg->chunks, frag_list) { \ if ((clear && asoc->base.sk == c->skb->sk) || \ (!clear && asoc->base.sk != c->skb->sk)) \ cb(c); \ } \ prev_msg = msg; \ } while (0) static void sctp_for_each_tx_datachunk(struct sctp_association *asoc, bool clear, void (*cb)(struct sctp_chunk *)) { struct sctp_datamsg *msg, *prev_msg = NULL; struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chunk, *c; struct sctp_transport *t; list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) list_for_each_entry(chunk, &t->transmitted, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->retransmit, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->sacked, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->abandoned, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->out_chunk_list, list) traverse_and_process(); } static void sctp_for_each_rx_skb(struct sctp_association *asoc, struct sock *sk, void (*cb)(struct sk_buff *, struct sock *)) { struct sk_buff *skb, *tmp; sctp_skb_for_each(skb, &asoc->ulpq.lobby, tmp) cb(skb, sk); sctp_skb_for_each(skb, &asoc->ulpq.reasm, tmp) cb(skb, sk); sctp_skb_for_each(skb, &asoc->ulpq.reasm_uo, tmp) cb(skb, sk); } /* Verify that this is a valid address. */ static inline int sctp_verify_addr(struct sock *sk, union sctp_addr *addr, int len) { struct sctp_af *af; /* Verify basic sockaddr. */ af = sctp_sockaddr_af(sctp_sk(sk), addr, len); if (!af) return -EINVAL; /* Is this a valid SCTP address? */ if (!af->addr_valid(addr, sctp_sk(sk), NULL)) return -EINVAL; if (!sctp_sk(sk)->pf->send_verify(sctp_sk(sk), (addr))) return -EINVAL; return 0; } /* Look up the association by its id. If this is not a UDP-style * socket, the ID field is always ignored. */ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id) { struct sctp_association *asoc = NULL; /* If this is not a UDP-style socket, assoc id should be ignored. */ if (!sctp_style(sk, UDP)) { /* Return NULL if the socket state is not ESTABLISHED. It * could be a TCP-style listening socket or a socket which * hasn't yet called connect() to establish an association. */ if (!sctp_sstate(sk, ESTABLISHED) && !sctp_sstate(sk, CLOSING)) return NULL; /* Get the first and the only association from the list. */ if (!list_empty(&sctp_sk(sk)->ep->asocs)) asoc = list_entry(sctp_sk(sk)->ep->asocs.next, struct sctp_association, asocs); return asoc; } /* Otherwise this is a UDP-style socket. */ if (id <= SCTP_ALL_ASSOC) return NULL; spin_lock_bh(&sctp_assocs_id_lock); asoc = (struct sctp_association *)idr_find(&sctp_assocs_id, (int)id); if (asoc && (asoc->base.sk != sk || asoc->base.dead)) asoc = NULL; spin_unlock_bh(&sctp_assocs_id_lock); return asoc; } /* Look up the transport from an address and an assoc id. If both address and * id are specified, the associations matching the address and the id should be * the same. */ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk, struct sockaddr_storage *addr, sctp_assoc_t id) { struct sctp_association *addr_asoc = NULL, *id_asoc = NULL; struct sctp_af *af = sctp_get_af_specific(addr->ss_family); union sctp_addr *laddr = (union sctp_addr *)addr; struct sctp_transport *transport; if (!af || sctp_verify_addr(sk, laddr, af->sockaddr_len)) return NULL; addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep, laddr, &transport); if (!addr_asoc) return NULL; id_asoc = sctp_id2assoc(sk, id); if (id_asoc && (id_asoc != addr_asoc)) return NULL; sctp_get_pf_specific(sk->sk_family)->addr_to_user(sctp_sk(sk), (union sctp_addr *)addr); return transport; } /* API 3.1.2 bind() - UDP Style Syntax * The syntax of bind() is, * * ret = bind(int sd, struct sockaddr *addr, int addrlen); * * sd - the socket descriptor returned by socket(). * addr - the address structure (struct sockaddr_in or struct * sockaddr_in6 [RFC 2553]), * addr_len - the size of the address structure. */ static int sctp_bind(struct sock *sk, struct sockaddr *addr, int addr_len) { int retval = 0; lock_sock(sk); pr_debug("%s: sk:%p, addr:%p, addr_len:%d\n", __func__, sk, addr, addr_len); /* Disallow binding twice. */ if (!sctp_sk(sk)->ep->base.bind_addr.port) retval = sctp_do_bind(sk, (union sctp_addr *)addr, addr_len); else retval = -EINVAL; release_sock(sk); return retval; } static int sctp_get_port_local(struct sock *, union sctp_addr *); /* Verify this is a valid sockaddr. */ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, union sctp_addr *addr, int len) { struct sctp_af *af; /* Check minimum size. */ if (len < sizeof (struct sockaddr)) return NULL; if (!opt->pf->af_supported(addr->sa.sa_family, opt)) return NULL; if (addr->sa.sa_family == AF_INET6) { if (len < SIN6_LEN_RFC2133) return NULL; /* V4 mapped address are really of AF_INET family */ if (ipv6_addr_v4mapped(&addr->v6.sin6_addr) && !opt->pf->af_supported(AF_INET, opt)) return NULL; } /* If we get this far, af is valid. */ af = sctp_get_af_specific(addr->sa.sa_family); if (len < af->sockaddr_len) return NULL; return af; } static void sctp_auto_asconf_init(struct sctp_sock *sp) { struct net *net = sock_net(&sp->inet.sk); if (net->sctp.default_auto_asconf) { spin_lock_bh(&net->sctp.addr_wq_lock); list_add_tail(&sp->auto_asconf_list, &net->sctp.auto_asconf_splist); spin_unlock_bh(&net->sctp.addr_wq_lock); sp->do_auto_asconf = 1; } } /* Bind a local address either to an endpoint or to an association. */ static int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) { struct net *net = sock_net(sk); struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; struct sctp_bind_addr *bp = &ep->base.bind_addr; struct sctp_af *af; unsigned short snum; int ret = 0; /* Common sockaddr verification. */ af = sctp_sockaddr_af(sp, addr, len); if (!af) { pr_debug("%s: sk:%p, newaddr:%p, len:%d EINVAL\n", __func__, sk, addr, len); return -EINVAL; } snum = ntohs(addr->v4.sin_port); pr_debug("%s: sk:%p, new addr:%pISc, port:%d, new port:%d, len:%d\n", __func__, sk, &addr->sa, bp->port, snum, len); /* PF specific bind() address verification. */ if (!sp->pf->bind_verify(sp, addr)) return -EADDRNOTAVAIL; /* We must either be unbound, or bind to the same port. * It's OK to allow 0 ports if we are already bound. * We'll just inhert an already bound port in this case */ if (bp->port) { if (!snum) snum = bp->port; else if (snum != bp->port) { pr_debug("%s: new port %d doesn't match existing port " "%d\n", __func__, snum, bp->port); return -EINVAL; } } if (snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; /* See if the address matches any of the addresses we may have * already bound before checking against other endpoints. */ if (sctp_bind_addr_match(bp, addr, sp)) return -EINVAL; /* Make sure we are allowed to bind here. * The function sctp_get_port_local() does duplicate address * detection. */ addr->v4.sin_port = htons(snum); if (sctp_get_port_local(sk, addr)) return -EADDRINUSE; /* Refresh ephemeral port. */ if (!bp->port) { bp->port = inet_sk(sk)->inet_num; sctp_auto_asconf_init(sp); } /* Add the address to the bind address list. * Use GFP_ATOMIC since BHs will be disabled. */ ret = sctp_add_bind_addr(bp, addr, af->sockaddr_len, SCTP_ADDR_SRC, GFP_ATOMIC); if (ret) { sctp_put_port(sk); return ret; } /* Copy back into socket for getsockname() use. */ inet_sk(sk)->inet_sport = htons(inet_sk(sk)->inet_num); sp->pf->to_sk_saddr(addr, sk); return ret; } /* ADDIP Section 4.1.1 Congestion Control of ASCONF Chunks * * R1) One and only one ASCONF Chunk MAY be in transit and unacknowledged * at any one time. If a sender, after sending an ASCONF chunk, decides * it needs to transfer another ASCONF Chunk, it MUST wait until the * ASCONF-ACK Chunk returns from the previous ASCONF Chunk before sending a * subsequent ASCONF. Note this restriction binds each side, so at any * time two ASCONF may be in-transit on any given association (one sent * from each endpoint). */ static int sctp_send_asconf(struct sctp_association *asoc, struct sctp_chunk *chunk) { int retval = 0; /* If there is an outstanding ASCONF chunk, queue it for later * transmission. */ if (asoc->addip_last_asconf) { list_add_tail(&chunk->list, &asoc->addip_chunk_list); goto out; } /* Hold the chunk until an ASCONF_ACK is received. */ sctp_chunk_hold(chunk); retval = sctp_primitive_ASCONF(asoc->base.net, asoc, chunk); if (retval) sctp_chunk_free(chunk); else asoc->addip_last_asconf = chunk; out: return retval; } /* Add a list of addresses as bind addresses to local endpoint or * association. * * Basically run through each address specified in the addrs/addrcnt * array/length pair, determine if it is IPv6 or IPv4 and call * sctp_do_bind() on it. * * If any of them fails, then the operation will be reversed and the * ones that were added will be removed. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_bindx_add(struct sock *sk, struct sockaddr *addrs, int addrcnt) { int cnt; int retval = 0; void *addr_buf; struct sockaddr *sa_addr; struct sctp_af *af; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); addr_buf = addrs; for (cnt = 0; cnt < addrcnt; cnt++) { /* The list may contain either IPv4 or IPv6 address; * determine the address length for walking thru the list. */ sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa_family); if (!af) { retval = -EINVAL; goto err_bindx_add; } retval = sctp_do_bind(sk, (union sctp_addr *)sa_addr, af->sockaddr_len); addr_buf += af->sockaddr_len; err_bindx_add: if (retval < 0) { /* Failed. Cleanup the ones that have been added */ if (cnt > 0) sctp_bindx_rem(sk, addrs, cnt); return retval; } } return retval; } /* Send an ASCONF chunk with Add IP address parameters to all the peers of the * associations that are part of the endpoint indicating that a list of local * addresses are added to the endpoint. * * If any of the addresses is already in the bind address list of the * association, we do not send the chunk for that association. But it will not * affect other associations. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_send_asconf_add_ip(struct sock *sk, struct sockaddr *addrs, int addrcnt) { struct sctp_sock *sp; struct sctp_endpoint *ep; struct sctp_association *asoc; struct sctp_bind_addr *bp; struct sctp_chunk *chunk; struct sctp_sockaddr_entry *laddr; union sctp_addr *addr; union sctp_addr saveaddr; void *addr_buf; struct sctp_af *af; struct list_head *p; int i; int retval = 0; sp = sctp_sk(sk); ep = sp->ep; if (!ep->asconf_enable) return retval; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); list_for_each_entry(asoc, &ep->asocs, asocs) { if (!asoc->peer.asconf_capable) continue; if (asoc->peer.addip_disabled_mask & SCTP_PARAM_ADD_IP) continue; if (!sctp_state(asoc, ESTABLISHED)) continue; /* Check if any address in the packed array of addresses is * in the bind address list of the association. If so, * do not send the asconf chunk to its peer, but continue with * other associations. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); if (!af) { retval = -EINVAL; goto out; } if (sctp_assoc_lookup_laddr(asoc, addr)) break; addr_buf += af->sockaddr_len; } if (i < addrcnt) continue; /* Use the first valid address in bind addr list of * association as Address Parameter of ASCONF CHUNK. */ bp = &asoc->base.bind_addr; p = bp->address_list.next; laddr = list_entry(p, struct sctp_sockaddr_entry, list); chunk = sctp_make_asconf_update_ip(asoc, &laddr->a, addrs, addrcnt, SCTP_PARAM_ADD_IP); if (!chunk) { retval = -ENOMEM; goto out; } /* Add the new addresses to the bind address list with * use_as_src set to 0. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); memcpy(&saveaddr, addr, af->sockaddr_len); retval = sctp_add_bind_addr(bp, &saveaddr, sizeof(saveaddr), SCTP_ADDR_NEW, GFP_ATOMIC); addr_buf += af->sockaddr_len; } if (asoc->src_out_of_asoc_ok) { struct sctp_transport *trans; list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { trans->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); trans->ssthresh = asoc->peer.i.a_rwnd; trans->rto = asoc->rto_initial; sctp_max_rto(asoc, trans); trans->rtt = trans->srtt = trans->rttvar = 0; /* Clear the source and route cache */ sctp_transport_route(trans, NULL, sctp_sk(asoc->base.sk)); } } retval = sctp_send_asconf(asoc, chunk); } out: return retval; } /* Remove a list of addresses from bind addresses list. Do not remove the * last address. * * Basically run through each address specified in the addrs/addrcnt * array/length pair, determine if it is IPv6 or IPv4 and call * sctp_del_bind() on it. * * If any of them fails, then the operation will be reversed and the * ones that were removed will be added back. * * At least one address has to be left; if only one address is * available, the operation will return -EBUSY. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; int cnt; struct sctp_bind_addr *bp = &ep->base.bind_addr; int retval = 0; void *addr_buf; union sctp_addr *sa_addr; struct sctp_af *af; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); addr_buf = addrs; for (cnt = 0; cnt < addrcnt; cnt++) { /* If the bind address list is empty or if there is only one * bind address, there is nothing more to be removed (we need * at least one address here). */ if (list_empty(&bp->address_list) || (sctp_list_single_entry(&bp->address_list))) { retval = -EBUSY; goto err_bindx_rem; } sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa.sa_family); if (!af) { retval = -EINVAL; goto err_bindx_rem; } if (!af->addr_valid(sa_addr, sp, NULL)) { retval = -EADDRNOTAVAIL; goto err_bindx_rem; } if (sa_addr->v4.sin_port && sa_addr->v4.sin_port != htons(bp->port)) { retval = -EINVAL; goto err_bindx_rem; } if (!sa_addr->v4.sin_port) sa_addr->v4.sin_port = htons(bp->port); /* FIXME - There is probably a need to check if sk->sk_saddr and * sk->sk_rcv_addr are currently set to one of the addresses to * be removed. This is something which needs to be looked into * when we are fixing the outstanding issues with multi-homing * socket routing and failover schemes. Refer to comments in * sctp_do_bind(). -daisy */ retval = sctp_del_bind_addr(bp, sa_addr); addr_buf += af->sockaddr_len; err_bindx_rem: if (retval < 0) { /* Failed. Add the ones that has been removed back */ if (cnt > 0) sctp_bindx_add(sk, addrs, cnt); return retval; } } return retval; } /* Send an ASCONF chunk with Delete IP address parameters to all the peers of * the associations that are part of the endpoint indicating that a list of * local addresses are removed from the endpoint. * * If any of the addresses is already in the bind address list of the * association, we do not send the chunk for that association. But it will not * affect other associations. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_send_asconf_del_ip(struct sock *sk, struct sockaddr *addrs, int addrcnt) { struct sctp_sock *sp; struct sctp_endpoint *ep; struct sctp_association *asoc; struct sctp_transport *transport; struct sctp_bind_addr *bp; struct sctp_chunk *chunk; union sctp_addr *laddr; void *addr_buf; struct sctp_af *af; struct sctp_sockaddr_entry *saddr; int i; int retval = 0; int stored = 0; chunk = NULL; sp = sctp_sk(sk); ep = sp->ep; if (!ep->asconf_enable) return retval; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); list_for_each_entry(asoc, &ep->asocs, asocs) { if (!asoc->peer.asconf_capable) continue; if (asoc->peer.addip_disabled_mask & SCTP_PARAM_DEL_IP) continue; if (!sctp_state(asoc, ESTABLISHED)) continue; /* Check if any address in the packed array of addresses is * not present in the bind address list of the association. * If so, do not send the asconf chunk to its peer, but * continue with other associations. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { laddr = addr_buf; af = sctp_get_af_specific(laddr->v4.sin_family); if (!af) { retval = -EINVAL; goto out; } if (!sctp_assoc_lookup_laddr(asoc, laddr)) break; addr_buf += af->sockaddr_len; } if (i < addrcnt) continue; /* Find one address in the association's bind address list * that is not in the packed array of addresses. This is to * make sure that we do not delete all the addresses in the * association. */ bp = &asoc->base.bind_addr; laddr = sctp_find_unmatch_addr(bp, (union sctp_addr *)addrs, addrcnt, sp); if ((laddr == NULL) && (addrcnt == 1)) { if (asoc->asconf_addr_del_pending) continue; asoc->asconf_addr_del_pending = kzalloc(sizeof(union sctp_addr), GFP_ATOMIC); if (asoc->asconf_addr_del_pending == NULL) { retval = -ENOMEM; goto out; } asoc->asconf_addr_del_pending->sa.sa_family = addrs->sa_family; asoc->asconf_addr_del_pending->v4.sin_port = htons(bp->port); if (addrs->sa_family == AF_INET) { struct sockaddr_in *sin; sin = (struct sockaddr_in *)addrs; asoc->asconf_addr_del_pending->v4.sin_addr.s_addr = sin->sin_addr.s_addr; } else if (addrs->sa_family == AF_INET6) { struct sockaddr_in6 *sin6; sin6 = (struct sockaddr_in6 *)addrs; asoc->asconf_addr_del_pending->v6.sin6_addr = sin6->sin6_addr; } pr_debug("%s: keep the last address asoc:%p %pISc at %p\n", __func__, asoc, &asoc->asconf_addr_del_pending->sa, asoc->asconf_addr_del_pending); asoc->src_out_of_asoc_ok = 1; stored = 1; goto skip_mkasconf; } if (laddr == NULL) return -EINVAL; /* We do not need RCU protection throughout this loop * because this is done under a socket lock from the * setsockopt call. */ chunk = sctp_make_asconf_update_ip(asoc, laddr, addrs, addrcnt, SCTP_PARAM_DEL_IP); if (!chunk) { retval = -ENOMEM; goto out; } skip_mkasconf: /* Reset use_as_src flag for the addresses in the bind address * list that are to be deleted. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { laddr = addr_buf; af = sctp_get_af_specific(laddr->v4.sin_family); list_for_each_entry(saddr, &bp->address_list, list) { if (sctp_cmp_addr_exact(&saddr->a, laddr)) saddr->state = SCTP_ADDR_DEL; } addr_buf += af->sockaddr_len; } /* Update the route and saddr entries for all the transports * as some of the addresses in the bind address list are * about to be deleted and cannot be used as source addresses. */ list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { sctp_transport_route(transport, NULL, sctp_sk(asoc->base.sk)); } if (stored) /* We don't need to transmit ASCONF */ continue; retval = sctp_send_asconf(asoc, chunk); } out: return retval; } /* set addr events to assocs in the endpoint. ep and addr_wq must be locked */ int sctp_asconf_mgmt(struct sctp_sock *sp, struct sctp_sockaddr_entry *addrw) { struct sock *sk = sctp_opt2sk(sp); union sctp_addr *addr; struct sctp_af *af; /* It is safe to write port space in caller. */ addr = &addrw->a; addr->v4.sin_port = htons(sp->ep->base.bind_addr.port); af = sctp_get_af_specific(addr->sa.sa_family); if (!af) return -EINVAL; if (sctp_verify_addr(sk, addr, af->sockaddr_len)) return -EINVAL; if (addrw->state == SCTP_ADDR_NEW) return sctp_send_asconf_add_ip(sk, (struct sockaddr *)addr, 1); else return sctp_send_asconf_del_ip(sk, (struct sockaddr *)addr, 1); } /* Helper for tunneling sctp_bindx() requests through sctp_setsockopt() * * API 8.1 * int sctp_bindx(int sd, struct sockaddr *addrs, int addrcnt, * int flags); * * If sd is an IPv4 socket, the addresses passed must be IPv4 addresses. * If the sd is an IPv6 socket, the addresses passed can either be IPv4 * or IPv6 addresses. * * A single address may be specified as INADDR_ANY or IN6ADDR_ANY, see * Section 3.1.2 for this usage. * * addrs is a pointer to an array of one or more socket addresses. Each * address is contained in its appropriate structure (i.e. struct * sockaddr_in or struct sockaddr_in6) the family of the address type * must be used to distinguish the address length (note that this * representation is termed a "packed array" of addresses). The caller * specifies the number of addresses in the array with addrcnt. * * On success, sctp_bindx() returns 0. On failure, sctp_bindx() returns * -1, and sets errno to the appropriate error code. * * For SCTP, the port given in each socket address must be the same, or * sctp_bindx() will fail, setting errno to EINVAL. * * The flags parameter is formed from the bitwise OR of zero or more of * the following currently defined flags: * * SCTP_BINDX_ADD_ADDR * * SCTP_BINDX_REM_ADDR * * SCTP_BINDX_ADD_ADDR directs SCTP to add the given addresses to the * association, and SCTP_BINDX_REM_ADDR directs SCTP to remove the given * addresses from the association. The two flags are mutually exclusive; * if both are given, sctp_bindx() will fail with EINVAL. A caller may * not remove all addresses from an association; sctp_bindx() will * reject such an attempt with EINVAL. * * An application can use sctp_bindx(SCTP_BINDX_ADD_ADDR) to associate * additional addresses with an endpoint after calling bind(). Or use * sctp_bindx(SCTP_BINDX_REM_ADDR) to remove some addresses a listening * socket is associated with so that no new association accepted will be * associated with those addresses. If the endpoint supports dynamic * address a SCTP_BINDX_REM_ADDR or SCTP_BINDX_ADD_ADDR may cause a * endpoint to send the appropriate message to the peer to change the * peers address lists. * * Adding and removing addresses from a connected association is * optional functionality. Implementations that do not support this * functionality should return EOPNOTSUPP. * * Basically do nothing but copying the addresses from user to kernel * land and invoking either sctp_bindx_add() or sctp_bindx_rem() on the sk. * This is used for tunneling the sctp_bindx() request through sctp_setsockopt() * from userspace. * * On exit there is no need to do sockfd_put(), sys_setsockopt() does * it. * * sk The sk of the socket * addrs The pointer to the addresses * addrssize Size of the addrs buffer * op Operation to perform (add or remove, see the flags of * sctp_bindx) * * Returns 0 if ok, <0 errno code on error. */ static int sctp_setsockopt_bindx(struct sock *sk, struct sockaddr *addrs, int addrs_size, int op) { int err; int addrcnt = 0; int walk_size = 0; struct sockaddr *sa_addr; void *addr_buf = addrs; struct sctp_af *af; pr_debug("%s: sk:%p addrs:%p addrs_size:%d opt:%d\n", __func__, sk, addr_buf, addrs_size, op); if (unlikely(addrs_size <= 0)) return -EINVAL; /* Walk through the addrs buffer and count the number of addresses. */ while (walk_size < addrs_size) { if (walk_size + sizeof(sa_family_t) > addrs_size) return -EINVAL; sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa_family); /* If the address family is not supported or if this address * causes the address buffer to overflow return EINVAL. */ if (!af || (walk_size + af->sockaddr_len) > addrs_size) return -EINVAL; addrcnt++; addr_buf += af->sockaddr_len; walk_size += af->sockaddr_len; } /* Do the work. */ switch (op) { case SCTP_BINDX_ADD_ADDR: /* Allow security module to validate bindx addresses. */ err = security_sctp_bind_connect(sk, SCTP_SOCKOPT_BINDX_ADD, addrs, addrs_size); if (err) return err; err = sctp_bindx_add(sk, addrs, addrcnt); if (err) return err; return sctp_send_asconf_add_ip(sk, addrs, addrcnt); case SCTP_BINDX_REM_ADDR: err = sctp_bindx_rem(sk, addrs, addrcnt); if (err) return err; return sctp_send_asconf_del_ip(sk, addrs, addrcnt); default: return -EINVAL; } } static int sctp_bind_add(struct sock *sk, struct sockaddr *addrs, int addrlen) { int err; lock_sock(sk); err = sctp_setsockopt_bindx(sk, addrs, addrlen, SCTP_BINDX_ADD_ADDR); release_sock(sk); return err; } static int sctp_connect_new_asoc(struct sctp_endpoint *ep, const union sctp_addr *daddr, const struct sctp_initmsg *init, struct sctp_transport **tp) { struct sctp_association *asoc; struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); enum sctp_scope scope; int err; if (sctp_endpoint_is_peeled_off(ep, daddr)) return -EADDRNOTAVAIL; if (!ep->base.bind_addr.port) { if (sctp_autobind(sk)) return -EAGAIN; } else { if (inet_port_requires_bind_service(net, ep->base.bind_addr.port) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; } scope = sctp_scope(daddr); asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); if (!asoc) return -ENOMEM; err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL); if (err < 0) goto free; *tp = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); if (!*tp) { err = -ENOMEM; goto free; } if (!init) return 0; if (init->sinit_num_ostreams) { __u16 outcnt = init->sinit_num_ostreams; asoc->c.sinit_num_ostreams = outcnt; /* outcnt has been changed, need to re-init stream */ err = sctp_stream_init(&asoc->stream, outcnt, 0, GFP_KERNEL); if (err) goto free; } if (init->sinit_max_instreams) asoc->c.sinit_max_instreams = init->sinit_max_instreams; if (init->sinit_max_attempts) asoc->max_init_attempts = init->sinit_max_attempts; if (init->sinit_max_init_timeo) asoc->max_init_timeo = msecs_to_jiffies(init->sinit_max_init_timeo); return 0; free: sctp_association_free(asoc); return err; } static int sctp_connect_add_peer(struct sctp_association *asoc, union sctp_addr *daddr, int addr_len) { struct sctp_endpoint *ep = asoc->ep; struct sctp_association *old; struct sctp_transport *t; int err; err = sctp_verify_addr(ep->base.sk, daddr, addr_len); if (err) return err; old = sctp_endpoint_lookup_assoc(ep, daddr, &t); if (old && old != asoc) return old->state >= SCTP_STATE_ESTABLISHED ? -EISCONN : -EALREADY; if (sctp_endpoint_is_peeled_off(ep, daddr)) return -EADDRNOTAVAIL; t = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); if (!t) return -ENOMEM; return 0; } /* __sctp_connect(struct sock* sk, struct sockaddr *kaddrs, int addrs_size) * * Common routine for handling connect() and sctp_connectx(). * Connect will come in with just a single address. */ static int __sctp_connect(struct sock *sk, struct sockaddr *kaddrs, int addrs_size, int flags, sctp_assoc_t *assoc_id) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; struct sctp_transport *transport; struct sctp_association *asoc; void *addr_buf = kaddrs; union sctp_addr *daddr; struct sctp_af *af; int walk_size, err; long timeo; if (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING) || (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))) return -EISCONN; daddr = addr_buf; af = sctp_get_af_specific(daddr->sa.sa_family); if (!af || af->sockaddr_len > addrs_size) return -EINVAL; err = sctp_verify_addr(sk, daddr, af->sockaddr_len); if (err) return err; asoc = sctp_endpoint_lookup_assoc(ep, daddr, &transport); if (asoc) return asoc->state >= SCTP_STATE_ESTABLISHED ? -EISCONN : -EALREADY; err = sctp_connect_new_asoc(ep, daddr, NULL, &transport); if (err) return err; asoc = transport->asoc; addr_buf += af->sockaddr_len; walk_size = af->sockaddr_len; while (walk_size < addrs_size) { err = -EINVAL; if (walk_size + sizeof(sa_family_t) > addrs_size) goto out_free; daddr = addr_buf; af = sctp_get_af_specific(daddr->sa.sa_family); if (!af || af->sockaddr_len + walk_size > addrs_size) goto out_free; if (asoc->peer.port != ntohs(daddr->v4.sin_port)) goto out_free; err = sctp_connect_add_peer(asoc, daddr, af->sockaddr_len); if (err) goto out_free; addr_buf += af->sockaddr_len; walk_size += af->sockaddr_len; } /* In case the user of sctp_connectx() wants an association * id back, assign one now. */ if (assoc_id) { err = sctp_assoc_set_id(asoc, GFP_KERNEL); if (err < 0) goto out_free; } err = sctp_primitive_ASSOCIATE(sock_net(sk), asoc, NULL); if (err < 0) goto out_free; /* Initialize sk's dport and daddr for getpeername() */ inet_sk(sk)->inet_dport = htons(asoc->peer.port); sp->pf->to_sk_daddr(daddr, sk); sk->sk_err = 0; if (assoc_id) *assoc_id = asoc->assoc_id; timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); return sctp_wait_for_connect(asoc, &timeo); out_free: pr_debug("%s: took out_free path with asoc:%p kaddrs:%p err:%d\n", __func__, asoc, kaddrs, err); sctp_association_free(asoc); return err; } /* Helper for tunneling sctp_connectx() requests through sctp_setsockopt() * * API 8.9 * int sctp_connectx(int sd, struct sockaddr *addrs, int addrcnt, * sctp_assoc_t *asoc); * * If sd is an IPv4 socket, the addresses passed must be IPv4 addresses. * If the sd is an IPv6 socket, the addresses passed can either be IPv4 * or IPv6 addresses. * * A single address may be specified as INADDR_ANY or IN6ADDR_ANY, see * Section 3.1.2 for this usage. * * addrs is a pointer to an array of one or more socket addresses. Each * address is contained in its appropriate structure (i.e. struct * sockaddr_in or struct sockaddr_in6) the family of the address type * must be used to distengish the address length (note that this * representation is termed a "packed array" of addresses). The caller * specifies the number of addresses in the array with addrcnt. * * On success, sctp_connectx() returns 0. It also sets the assoc_id to * the association id of the new association. On failure, sctp_connectx() * returns -1, and sets errno to the appropriate error code. The assoc_id * is not touched by the kernel. * * For SCTP, the port given in each socket address must be the same, or * sctp_connectx() will fail, setting errno to EINVAL. * * An application can use sctp_connectx to initiate an association with * an endpoint that is multi-homed. Much like sctp_bindx() this call * allows a caller to specify multiple addresses at which a peer can be * reached. The way the SCTP stack uses the list of addresses to set up * the association is implementation dependent. This function only * specifies that the stack will try to make use of all the addresses in * the list when needed. * * Note that the list of addresses passed in is only used for setting up * the association. It does not necessarily equal the set of addresses * the peer uses for the resulting association. If the caller wants to * find out the set of peer addresses, it must use sctp_getpaddrs() to * retrieve them after the association has been set up. * * Basically do nothing but copying the addresses from user to kernel * land and invoking either sctp_connectx(). This is used for tunneling * the sctp_connectx() request through sctp_setsockopt() from userspace. * * On exit there is no need to do sockfd_put(), sys_setsockopt() does * it. * * sk The sk of the socket * addrs The pointer to the addresses * addrssize Size of the addrs buffer * * Returns >=0 if ok, <0 errno code on error. */ static int __sctp_setsockopt_connectx(struct sock *sk, struct sockaddr *kaddrs, int addrs_size, sctp_assoc_t *assoc_id) { int err = 0, flags = 0; pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n", __func__, sk, kaddrs, addrs_size); /* make sure the 1st addr's sa_family is accessible later */ if (unlikely(addrs_size < sizeof(sa_family_t))) return -EINVAL; /* Allow security module to validate connectx addresses. */ err = security_sctp_bind_connect(sk, SCTP_SOCKOPT_CONNECTX, (struct sockaddr *)kaddrs, addrs_size); if (err) return err; /* in-kernel sockets don't generally have a file allocated to them * if all they do is call sock_create_kern(). */ if (sk->sk_socket->file) flags = sk->sk_socket->file->f_flags; return __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id); } /* * This is an older interface. It's kept for backward compatibility * to the option that doesn't provide association id. */ static int sctp_setsockopt_connectx_old(struct sock *sk, struct sockaddr *kaddrs, int addrs_size) { return __sctp_setsockopt_connectx(sk, kaddrs, addrs_size, NULL); } /* * New interface for the API. The since the API is done with a socket * option, to make it simple we feed back the association id is as a return * indication to the call. Error is always negative and association id is * always positive. */ static int sctp_setsockopt_connectx(struct sock *sk, struct sockaddr *kaddrs, int addrs_size) { sctp_assoc_t assoc_id = 0; int err = 0; err = __sctp_setsockopt_connectx(sk, kaddrs, addrs_size, &assoc_id); if (err) return err; else return assoc_id; } /* * New (hopefully final) interface for the API. * We use the sctp_getaddrs_old structure so that use-space library * can avoid any unnecessary allocations. The only different part * is that we store the actual length of the address buffer into the * addrs_num structure member. That way we can re-use the existing * code. */ #ifdef CONFIG_COMPAT struct compat_sctp_getaddrs_old { sctp_assoc_t assoc_id; s32 addr_num; compat_uptr_t addrs; /* struct sockaddr * */ }; #endif static int sctp_getsockopt_connectx3(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_getaddrs_old param; sctp_assoc_t assoc_id = 0; struct sockaddr *kaddrs; int err = 0; #ifdef CONFIG_COMPAT if (in_compat_syscall()) { struct compat_sctp_getaddrs_old param32; if (len < sizeof(param32)) return -EINVAL; if (copy_from_user(¶m32, optval, sizeof(param32))) return -EFAULT; param.assoc_id = param32.assoc_id; param.addr_num = param32.addr_num; param.addrs = compat_ptr(param32.addrs); } else #endif { if (len < sizeof(param)) return -EINVAL; if (copy_from_user(¶m, optval, sizeof(param))) return -EFAULT; } kaddrs = memdup_user(param.addrs, param.addr_num); if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); err = __sctp_setsockopt_connectx(sk, kaddrs, param.addr_num, &assoc_id); kfree(kaddrs); if (err == 0 || err == -EINPROGRESS) { if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) return -EFAULT; if (put_user(sizeof(assoc_id), optlen)) return -EFAULT; } return err; } /* API 3.1.4 close() - UDP Style Syntax * Applications use close() to perform graceful shutdown (as described in * Section 10.1 of [SCTP]) on ALL the associations currently represented * by a UDP-style socket. * * The syntax is * * ret = close(int sd); * * sd - the socket descriptor of the associations to be closed. * * To gracefully shutdown a specific association represented by the * UDP-style socket, an application should use the sendmsg() call, * passing no user data, but including the appropriate flag in the * ancillary data (see Section xxxx). * * If sd in the close() call is a branched-off socket representing only * one association, the shutdown is performed on that association only. * * 4.1.6 close() - TCP Style Syntax * * Applications use close() to gracefully close down an association. * * The syntax is: * * int close(int sd); * * sd - the socket descriptor of the association to be closed. * * After an application calls close() on a socket descriptor, no further * socket operations will succeed on that descriptor. * * API 7.1.4 SO_LINGER * * An application using the TCP-style socket can use this option to * perform the SCTP ABORT primitive. The linger option structure is: * * struct linger { * int l_onoff; // option on/off * int l_linger; // linger time * }; * * To enable the option, set l_onoff to 1. If the l_linger value is set * to 0, calling close() is the same as the ABORT primitive. If the * value is set to a negative value, the setsockopt() call will return * an error. If the value is set to a positive value linger_time, the * close() can be blocked for at most linger_time ms. If the graceful * shutdown phase does not finish during this period, close() will * return but the graceful shutdown phase continues in the system. */ static void sctp_close(struct sock *sk, long timeout) { struct net *net = sock_net(sk); struct sctp_endpoint *ep; struct sctp_association *asoc; struct list_head *pos, *temp; unsigned int data_was_unread; pr_debug("%s: sk:%p, timeout:%ld\n", __func__, sk, timeout); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); sk->sk_shutdown = SHUTDOWN_MASK; inet_sk_set_state(sk, SCTP_SS_CLOSING); ep = sctp_sk(sk)->ep; /* Clean up any skbs sitting on the receive queue. */ data_was_unread = sctp_queue_purge_ulpevents(&sk->sk_receive_queue); data_was_unread += sctp_queue_purge_ulpevents(&sctp_sk(sk)->pd_lobby); /* Walk all associations on an endpoint. */ list_for_each_safe(pos, temp, &ep->asocs) { asoc = list_entry(pos, struct sctp_association, asocs); if (sctp_style(sk, TCP)) { /* A closed association can still be in the list if * it belongs to a TCP-style listening socket that is * not yet accepted. If so, free it. If not, send an * ABORT or SHUTDOWN based on the linger options. */ if (sctp_state(asoc, CLOSED)) { sctp_association_free(asoc); continue; } } if (data_was_unread || !skb_queue_empty(&asoc->ulpq.lobby) || !skb_queue_empty(&asoc->ulpq.reasm) || !skb_queue_empty(&asoc->ulpq.reasm_uo) || (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)) { struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, NULL, 0); sctp_primitive_ABORT(net, asoc, chunk); } else sctp_primitive_SHUTDOWN(net, asoc, NULL); } /* On a TCP-style socket, block for at most linger_time if set. */ if (sctp_style(sk, TCP) && timeout) sctp_wait_for_close(sk, timeout); /* This will run the backlog queue. */ release_sock(sk); /* Supposedly, no process has access to the socket, but * the net layers still may. * Also, sctp_destroy_sock() needs to be called with addr_wq_lock * held and that should be grabbed before socket lock. */ spin_lock_bh(&net->sctp.addr_wq_lock); bh_lock_sock_nested(sk); /* Hold the sock, since sk_common_release() will put sock_put() * and we have just a little more cleanup. */ sock_hold(sk); sk_common_release(sk); bh_unlock_sock(sk); spin_unlock_bh(&net->sctp.addr_wq_lock); sock_put(sk); SCTP_DBG_OBJCNT_DEC(sock); } /* Handle EPIPE error. */ static int sctp_error(struct sock *sk, int flags, int err) { if (err == -EPIPE) err = sock_error(sk) ? : -EPIPE; if (err == -EPIPE && !(flags & MSG_NOSIGNAL)) send_sig(SIGPIPE, current, 0); return err; } /* API 3.1.3 sendmsg() - UDP Style Syntax * * An application uses sendmsg() and recvmsg() calls to transmit data to * and receive data from its peer. * * ssize_t sendmsg(int socket, const struct msghdr *message, * int flags); * * socket - the socket descriptor of the endpoint. * message - pointer to the msghdr structure which contains a single * user message and possibly some ancillary data. * * See Section 5 for complete description of the data * structures. * * flags - flags sent or received with the user message, see Section * 5 for complete description of the flags. * * Note: This function could use a rewrite especially when explicit * connect support comes in. */ /* BUG: We do not implement the equivalent of sk_stream_wait_memory(). */ static int sctp_msghdr_parse(const struct msghdr *msg, struct sctp_cmsgs *cmsgs); static int sctp_sendmsg_parse(struct sock *sk, struct sctp_cmsgs *cmsgs, struct sctp_sndrcvinfo *srinfo, const struct msghdr *msg, size_t msg_len) { __u16 sflags; int err; if (sctp_sstate(sk, LISTENING) && sctp_style(sk, TCP)) return -EPIPE; if (msg_len > sk->sk_sndbuf) return -EMSGSIZE; memset(cmsgs, 0, sizeof(*cmsgs)); err = sctp_msghdr_parse(msg, cmsgs); if (err) { pr_debug("%s: msghdr parse err:%x\n", __func__, err); return err; } memset(srinfo, 0, sizeof(*srinfo)); if (cmsgs->srinfo) { srinfo->sinfo_stream = cmsgs->srinfo->sinfo_stream; srinfo->sinfo_flags = cmsgs->srinfo->sinfo_flags; srinfo->sinfo_ppid = cmsgs->srinfo->sinfo_ppid; srinfo->sinfo_context = cmsgs->srinfo->sinfo_context; srinfo->sinfo_assoc_id = cmsgs->srinfo->sinfo_assoc_id; srinfo->sinfo_timetolive = cmsgs->srinfo->sinfo_timetolive; } if (cmsgs->sinfo) { srinfo->sinfo_stream = cmsgs->sinfo->snd_sid; srinfo->sinfo_flags = cmsgs->sinfo->snd_flags; srinfo->sinfo_ppid = cmsgs->sinfo->snd_ppid; srinfo->sinfo_context = cmsgs->sinfo->snd_context; srinfo->sinfo_assoc_id = cmsgs->sinfo->snd_assoc_id; } if (cmsgs->prinfo) { srinfo->sinfo_timetolive = cmsgs->prinfo->pr_value; SCTP_PR_SET_POLICY(srinfo->sinfo_flags, cmsgs->prinfo->pr_policy); } sflags = srinfo->sinfo_flags; if (!sflags && msg_len) return 0; if (sctp_style(sk, TCP) && (sflags & (SCTP_EOF | SCTP_ABORT))) return -EINVAL; if (((sflags & SCTP_EOF) && msg_len > 0) || (!(sflags & (SCTP_EOF | SCTP_ABORT)) && msg_len == 0)) return -EINVAL; if ((sflags & SCTP_ADDR_OVER) && !msg->msg_name) return -EINVAL; return 0; } static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, struct sctp_cmsgs *cmsgs, union sctp_addr *daddr, struct sctp_transport **tp) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; struct cmsghdr *cmsg; __be32 flowinfo = 0; struct sctp_af *af; int err; *tp = NULL; if (sflags & (SCTP_EOF | SCTP_ABORT)) return -EINVAL; if (sctp_style(sk, TCP) && (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING))) return -EADDRNOTAVAIL; /* Label connection socket for first association 1-to-many * style for client sequence socket()->sendmsg(). This * needs to be done before sctp_assoc_add_peer() as that will * set up the initial packet that needs to account for any * security ip options (CIPSO/CALIPSO) added to the packet. */ af = sctp_get_af_specific(daddr->sa.sa_family); if (!af) return -EINVAL; err = security_sctp_bind_connect(sk, SCTP_SENDMSG_CONNECT, (struct sockaddr *)daddr, af->sockaddr_len); if (err < 0) return err; err = sctp_connect_new_asoc(ep, daddr, cmsgs->init, tp); if (err) return err; asoc = (*tp)->asoc; if (!cmsgs->addrs_msg) return 0; if (daddr->sa.sa_family == AF_INET6) flowinfo = daddr->v6.sin6_flowinfo; /* sendv addr list parse */ for_each_cmsghdr(cmsg, cmsgs->addrs_msg) { union sctp_addr _daddr; int dlen; if (cmsg->cmsg_level != IPPROTO_SCTP || (cmsg->cmsg_type != SCTP_DSTADDRV4 && cmsg->cmsg_type != SCTP_DSTADDRV6)) continue; daddr = &_daddr; memset(daddr, 0, sizeof(*daddr)); dlen = cmsg->cmsg_len - sizeof(struct cmsghdr); if (cmsg->cmsg_type == SCTP_DSTADDRV4) { if (dlen < sizeof(struct in_addr)) { err = -EINVAL; goto free; } dlen = sizeof(struct in_addr); daddr->v4.sin_family = AF_INET; daddr->v4.sin_port = htons(asoc->peer.port); memcpy(&daddr->v4.sin_addr, CMSG_DATA(cmsg), dlen); } else { if (dlen < sizeof(struct in6_addr)) { err = -EINVAL; goto free; } dlen = sizeof(struct in6_addr); daddr->v6.sin6_flowinfo = flowinfo; daddr->v6.sin6_family = AF_INET6; daddr->v6.sin6_port = htons(asoc->peer.port); memcpy(&daddr->v6.sin6_addr, CMSG_DATA(cmsg), dlen); } err = sctp_connect_add_peer(asoc, daddr, sizeof(*daddr)); if (err) goto free; } return 0; free: sctp_association_free(asoc); return err; } static int sctp_sendmsg_check_sflags(struct sctp_association *asoc, __u16 sflags, struct msghdr *msg, size_t msg_len) { struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); if (sctp_state(asoc, CLOSED) && sctp_style(sk, TCP)) return -EPIPE; if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP) && !sctp_state(asoc, ESTABLISHED)) return 0; if (sflags & SCTP_EOF) { pr_debug("%s: shutting down association:%p\n", __func__, asoc); sctp_primitive_SHUTDOWN(net, asoc, NULL); return 0; } if (sflags & SCTP_ABORT) { struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, msg, msg_len); if (!chunk) return -ENOMEM; pr_debug("%s: aborting association:%p\n", __func__, asoc); sctp_primitive_ABORT(net, asoc, chunk); iov_iter_revert(&msg->msg_iter, msg_len); return 0; } return 1; } static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, struct msghdr *msg, size_t msg_len, struct sctp_transport *transport, struct sctp_sndrcvinfo *sinfo) { struct sock *sk = asoc->base.sk; struct sctp_sock *sp = sctp_sk(sk); struct net *net = sock_net(sk); struct sctp_datamsg *datamsg; bool wait_connect = false; struct sctp_chunk *chunk; long timeo; int err; if (sinfo->sinfo_stream >= asoc->stream.outcnt) { err = -EINVAL; goto err; } if (unlikely(!SCTP_SO(&asoc->stream, sinfo->sinfo_stream)->ext)) { err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream); if (err) goto err; } if (sp->disable_fragments && msg_len > asoc->frag_point) { err = -EMSGSIZE; goto err; } if (asoc->pmtu_pending) { if (sp->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); asoc->pmtu_pending = 0; } if (sctp_wspace(asoc) < (int)msg_len) sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); if (sk_under_memory_pressure(sk)) sk_mem_reclaim(sk); if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) goto err; if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) { err = -EINVAL; goto err; } } if (sctp_state(asoc, CLOSED)) { err = sctp_primitive_ASSOCIATE(net, asoc, NULL); if (err) goto err; if (asoc->ep->intl_enable) { timeo = sock_sndtimeo(sk, 0); err = sctp_wait_for_connect(asoc, &timeo); if (err) { err = -ESRCH; goto err; } } else { wait_connect = true; } pr_debug("%s: we associated primitively\n", __func__); } datamsg = sctp_datamsg_from_user(asoc, sinfo, &msg->msg_iter); if (IS_ERR(datamsg)) { err = PTR_ERR(datamsg); goto err; } asoc->force_delay = !!(msg->msg_flags & MSG_MORE); list_for_each_entry(chunk, &datamsg->chunks, frag_list) { sctp_chunk_hold(chunk); sctp_set_owner_w(chunk); chunk->transport = transport; } err = sctp_primitive_SEND(net, asoc, datamsg); if (err) { sctp_datamsg_free(datamsg); goto err; } pr_debug("%s: we sent primitively\n", __func__); sctp_datamsg_put(datamsg); if (unlikely(wait_connect)) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); sctp_wait_for_connect(asoc, &timeo); } err = msg_len; err: return err; } static union sctp_addr *sctp_sendmsg_get_daddr(struct sock *sk, const struct msghdr *msg, struct sctp_cmsgs *cmsgs) { union sctp_addr *daddr = NULL; int err; if (!sctp_style(sk, UDP_HIGH_BANDWIDTH) && msg->msg_name) { int len = msg->msg_namelen; if (len > sizeof(*daddr)) len = sizeof(*daddr); daddr = (union sctp_addr *)msg->msg_name; err = sctp_verify_addr(sk, daddr, len); if (err) return ERR_PTR(err); } return daddr; } static void sctp_sendmsg_update_sinfo(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, struct sctp_cmsgs *cmsgs) { if (!cmsgs->srinfo && !cmsgs->sinfo) { sinfo->sinfo_stream = asoc->default_stream; sinfo->sinfo_ppid = asoc->default_ppid; sinfo->sinfo_context = asoc->default_context; sinfo->sinfo_assoc_id = sctp_assoc2id(asoc); if (!cmsgs->prinfo) sinfo->sinfo_flags = asoc->default_flags; } if (!cmsgs->srinfo && !cmsgs->prinfo) sinfo->sinfo_timetolive = asoc->default_timetolive; if (cmsgs->authinfo) { /* Reuse sinfo_tsn to indicate that authinfo was set and * sinfo_ssn to save the keyid on tx path. */ sinfo->sinfo_tsn = 1; sinfo->sinfo_ssn = cmsgs->authinfo->auth_keynumber; } } static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_transport *transport = NULL; struct sctp_sndrcvinfo _sinfo, *sinfo; struct sctp_association *asoc, *tmp; struct sctp_cmsgs cmsgs; union sctp_addr *daddr; bool new = false; __u16 sflags; int err; /* Parse and get snd_info */ err = sctp_sendmsg_parse(sk, &cmsgs, &_sinfo, msg, msg_len); if (err) goto out; sinfo = &_sinfo; sflags = sinfo->sinfo_flags; /* Get daddr from msg */ daddr = sctp_sendmsg_get_daddr(sk, msg, &cmsgs); if (IS_ERR(daddr)) { err = PTR_ERR(daddr); goto out; } lock_sock(sk); /* SCTP_SENDALL process */ if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) { list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err == 0) continue; if (err < 0) goto out_unlock; sctp_sendmsg_update_sinfo(asoc, sinfo, &cmsgs); err = sctp_sendmsg_to_asoc(asoc, msg, msg_len, NULL, sinfo); if (err < 0) goto out_unlock; iov_iter_revert(&msg->msg_iter, err); } goto out_unlock; } /* Get and check or create asoc */ if (daddr) { asoc = sctp_endpoint_lookup_assoc(ep, daddr, &transport); if (asoc) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err <= 0) goto out_unlock; } else { err = sctp_sendmsg_new_asoc(sk, sflags, &cmsgs, daddr, &transport); if (err) goto out_unlock; asoc = transport->asoc; new = true; } if (!sctp_style(sk, TCP) && !(sflags & SCTP_ADDR_OVER)) transport = NULL; } else { asoc = sctp_id2assoc(sk, sinfo->sinfo_assoc_id); if (!asoc) { err = -EPIPE; goto out_unlock; } err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err <= 0) goto out_unlock; } /* Update snd_info with the asoc */ sctp_sendmsg_update_sinfo(asoc, sinfo, &cmsgs); /* Send msg to the asoc */ err = sctp_sendmsg_to_asoc(asoc, msg, msg_len, transport, sinfo); if (err < 0 && err != -ESRCH && new) sctp_association_free(asoc); out_unlock: release_sock(sk); out: return sctp_error(sk, msg->msg_flags, err); } /* This is an extended version of skb_pull() that removes the data from the * start of a skb even when data is spread across the list of skb's in the * frag_list. len specifies the total amount of data that needs to be removed. * when 'len' bytes could be removed from the skb, it returns 0. * If 'len' exceeds the total skb length, it returns the no. of bytes that * could not be removed. */ static int sctp_skb_pull(struct sk_buff *skb, int len) { struct sk_buff *list; int skb_len = skb_headlen(skb); int rlen; if (len <= skb_len) { __skb_pull(skb, len); return 0; } len -= skb_len; __skb_pull(skb, skb_len); skb_walk_frags(skb, list) { rlen = sctp_skb_pull(list, len); skb->len -= (len-rlen); skb->data_len -= (len-rlen); if (!rlen) return 0; len = rlen; } return len; } /* API 3.1.3 recvmsg() - UDP Style Syntax * * ssize_t recvmsg(int socket, struct msghdr *message, * int flags); * * socket - the socket descriptor of the endpoint. * message - pointer to the msghdr structure which contains a single * user message and possibly some ancillary data. * * See Section 5 for complete description of the data * structures. * * flags - flags sent or received with the user message, see Section * 5 for complete description of the flags. */ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct sctp_ulpevent *event = NULL; struct sctp_sock *sp = sctp_sk(sk); struct sk_buff *skb, *head_skb; int copied; int err = 0; int skb_len; pr_debug("%s: sk:%p, msghdr:%p, len:%zd, noblock:%d, flags:0x%x, " "addr_len:%p)\n", __func__, sk, msg, len, noblock, flags, addr_len); lock_sock(sk); if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED) && !sctp_sstate(sk, CLOSING) && !sctp_sstate(sk, CLOSED)) { err = -ENOTCONN; goto out; } skb = sctp_skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; /* Get the total length of the skb including any skb's in the * frag_list. */ skb_len = skb->len; copied = skb_len; if (copied > len) copied = len; err = skb_copy_datagram_msg(skb, 0, msg, copied); event = sctp_skb2event(skb); if (err) goto out_free; if (event->chunk && event->chunk->head_skb) head_skb = event->chunk->head_skb; else head_skb = skb; sock_recv_ts_and_drops(msg, sk, head_skb); if (sctp_ulpevent_is_notification(event)) { msg->msg_flags |= MSG_NOTIFICATION; sp->pf->event_msgname(event, msg->msg_name, addr_len); } else { sp->pf->skb_msgname(head_skb, msg->msg_name, addr_len); } /* Check if we allow SCTP_NXTINFO. */ if (sp->recvnxtinfo) sctp_ulpevent_read_nxtinfo(event, msg, sk); /* Check if we allow SCTP_RCVINFO. */ if (sp->recvrcvinfo) sctp_ulpevent_read_rcvinfo(event, msg); /* Check if we allow SCTP_SNDRCVINFO. */ if (sctp_ulpevent_type_enabled(sp->subscribe, SCTP_DATA_IO_EVENT)) sctp_ulpevent_read_sndrcvinfo(event, msg); err = copied; /* If skb's length exceeds the user's buffer, update the skb and * push it back to the receive_queue so that the next call to * recvmsg() will return the remaining data. Don't set MSG_EOR. */ if (skb_len > copied) { msg->msg_flags &= ~MSG_EOR; if (flags & MSG_PEEK) goto out_free; sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); /* When only partial message is copied to the user, increase * rwnd by that amount. If all the data in the skb is read, * rwnd is updated when the event is freed. */ if (!sctp_ulpevent_is_notification(event)) sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) msg->msg_flags |= MSG_EOR; else msg->msg_flags &= ~MSG_EOR; out_free: if (flags & MSG_PEEK) { /* Release the skb reference acquired after peeking the skb in * sctp_skb_recv_datagram(). */ kfree_skb(skb); } else { /* Free the event which includes releasing the reference to * the owner of the skb, freeing the skb and updating the * rwnd. */ sctp_ulpevent_free(event); } out: release_sock(sk); return err; } /* 7.1.12 Enable/Disable message fragmentation (SCTP_DISABLE_FRAGMENTS) * * This option is a on/off flag. If enabled no SCTP message * fragmentation will be performed. Instead if a message being sent * exceeds the current PMTU size, the message will NOT be sent and * instead a error will be indicated to the user. */ static int sctp_setsockopt_disable_fragments(struct sock *sk, int *val, unsigned int optlen) { if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->disable_fragments = (*val == 0) ? 0 : 1; return 0; } static int sctp_setsockopt_events(struct sock *sk, __u8 *sn_type, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; int i; if (optlen > sizeof(struct sctp_event_subscribe)) return -EINVAL; for (i = 0; i < optlen; i++) sctp_ulpevent_type_set(&sp->subscribe, SCTP_SN_TYPE_BASE + i, sn_type[i]); list_for_each_entry(asoc, &sp->ep->asocs, asocs) asoc->subscribe = sctp_sk(sk)->subscribe; /* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT, * if there is no data to be sent or retransmit, the stack will * immediately send up this notification. */ if (sctp_ulpevent_type_enabled(sp->subscribe, SCTP_SENDER_DRY_EVENT)) { struct sctp_ulpevent *event; asoc = sctp_id2assoc(sk, 0); if (asoc && sctp_outq_is_empty(&asoc->outqueue)) { event = sctp_ulpevent_make_sender_dry_event(asoc, GFP_USER | __GFP_NOWARN); if (!event) return -ENOMEM; asoc->stream.si->enqueue_event(&asoc->ulpq, event); } } return 0; } /* 7.1.8 Automatic Close of associations (SCTP_AUTOCLOSE) * * This socket option is applicable to the UDP-style socket only. When * set it will cause associations that are idle for more than the * specified number of seconds to automatically close. An association * being idle is defined an association that has NOT sent or received * user data. The special value of '0' indicates that no automatic * close of any associations should be performed. The option expects an * integer defining the number of seconds of idle time before an * association is closed. */ static int sctp_setsockopt_autoclose(struct sock *sk, u32 *optval, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct net *net = sock_net(sk); /* Applicable to UDP-style socket only */ if (sctp_style(sk, TCP)) return -EOPNOTSUPP; if (optlen != sizeof(int)) return -EINVAL; sp->autoclose = *optval; if (sp->autoclose > net->sctp.max_autoclose) sp->autoclose = net->sctp.max_autoclose; return 0; } /* 7.1.13 Peer Address Parameters (SCTP_PEER_ADDR_PARAMS) * * Applications can enable or disable heartbeats for any peer address of * an association, modify an address's heartbeat interval, force a * heartbeat to be sent immediately, and adjust the address's maximum * number of retransmissions sent before an address is considered * unreachable. The following structure is used to access and modify an * address's parameters: * * struct sctp_paddrparams { * sctp_assoc_t spp_assoc_id; * struct sockaddr_storage spp_address; * uint32_t spp_hbinterval; * uint16_t spp_pathmaxrxt; * uint32_t spp_pathmtu; * uint32_t spp_sackdelay; * uint32_t spp_flags; * uint32_t spp_ipv6_flowlabel; * uint8_t spp_dscp; * }; * * spp_assoc_id - (one-to-many style socket) This is filled in the * application, and identifies the association for * this query. * spp_address - This specifies which address is of interest. * spp_hbinterval - This contains the value of the heartbeat interval, * in milliseconds. If a value of zero * is present in this field then no changes are to * be made to this parameter. * spp_pathmaxrxt - This contains the maximum number of * retransmissions before this address shall be * considered unreachable. If a value of zero * is present in this field then no changes are to * be made to this parameter. * spp_pathmtu - When Path MTU discovery is disabled the value * specified here will be the "fixed" path mtu. * Note that if the spp_address field is empty * then all associations on this address will * have this fixed path mtu set upon them. * * spp_sackdelay - When delayed sack is enabled, this value specifies * the number of milliseconds that sacks will be delayed * for. This value will apply to all addresses of an * association if the spp_address field is empty. Note * also, that if delayed sack is enabled and this * value is set to 0, no change is made to the last * recorded delayed sack timer value. * * spp_flags - These flags are used to control various features * on an association. The flag field may contain * zero or more of the following options. * * SPP_HB_ENABLE - Enable heartbeats on the * specified address. Note that if the address * field is empty all addresses for the association * have heartbeats enabled upon them. * * SPP_HB_DISABLE - Disable heartbeats on the * speicifed address. Note that if the address * field is empty all addresses for the association * will have their heartbeats disabled. Note also * that SPP_HB_ENABLE and SPP_HB_DISABLE are * mutually exclusive, only one of these two should * be specified. Enabling both fields will have * undetermined results. * * SPP_HB_DEMAND - Request a user initiated heartbeat * to be made immediately. * * SPP_HB_TIME_IS_ZERO - Specify's that the time for * heartbeat delayis to be set to the value of 0 * milliseconds. * * SPP_PMTUD_ENABLE - This field will enable PMTU * discovery upon the specified address. Note that * if the address feild is empty then all addresses * on the association are effected. * * SPP_PMTUD_DISABLE - This field will disable PMTU * discovery upon the specified address. Note that * if the address feild is empty then all addresses * on the association are effected. Not also that * SPP_PMTUD_ENABLE and SPP_PMTUD_DISABLE are mutually * exclusive. Enabling both will have undetermined * results. * * SPP_SACKDELAY_ENABLE - Setting this flag turns * on delayed sack. The time specified in spp_sackdelay * is used to specify the sack delay for this address. Note * that if spp_address is empty then all addresses will * enable delayed sack and take on the sack delay * value specified in spp_sackdelay. * SPP_SACKDELAY_DISABLE - Setting this flag turns * off delayed sack. If the spp_address field is blank then * delayed sack is disabled for the entire association. Note * also that this field is mutually exclusive to * SPP_SACKDELAY_ENABLE, setting both will have undefined * results. * * SPP_IPV6_FLOWLABEL: Setting this flag enables the * setting of the IPV6 flow label value. The value is * contained in the spp_ipv6_flowlabel field. * Upon retrieval, this flag will be set to indicate that * the spp_ipv6_flowlabel field has a valid value returned. * If a specific destination address is set (in the * spp_address field), then the value returned is that of * the address. If just an association is specified (and * no address), then the association's default flow label * is returned. If neither an association nor a destination * is specified, then the socket's default flow label is * returned. For non-IPv6 sockets, this flag will be left * cleared. * * SPP_DSCP: Setting this flag enables the setting of the * Differentiated Services Code Point (DSCP) value * associated with either the association or a specific * address. The value is obtained in the spp_dscp field. * Upon retrieval, this flag will be set to indicate that * the spp_dscp field has a valid value returned. If a * specific destination address is set when called (in the * spp_address field), then that specific destination * address's DSCP value is returned. If just an association * is specified, then the association's default DSCP is * returned. If neither an association nor a destination is * specified, then the socket's default DSCP is returned. * * spp_ipv6_flowlabel * - This field is used in conjunction with the * SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label. * The 20 least significant bits are used for the flow * label. This setting has precedence over any IPv6-layer * setting. * * spp_dscp - This field is used in conjunction with the SPP_DSCP flag * and contains the DSCP. The 6 most significant bits are * used for the DSCP. This setting has precedence over any * IPv4- or IPv6- layer setting. */ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, struct sctp_transport *trans, struct sctp_association *asoc, struct sctp_sock *sp, int hb_change, int pmtud_change, int sackdelay_change) { int error; if (params->spp_flags & SPP_HB_DEMAND && trans) { error = sctp_primitive_REQUESTHEARTBEAT(trans->asoc->base.net, trans->asoc, trans); if (error) return error; } /* Note that unless the spp_flag is set to SPP_HB_ENABLE the value of * this field is ignored. Note also that a value of zero indicates * the current setting should be left unchanged. */ if (params->spp_flags & SPP_HB_ENABLE) { /* Re-zero the interval if the SPP_HB_TIME_IS_ZERO is * set. This lets us use 0 value when this flag * is set. */ if (params->spp_flags & SPP_HB_TIME_IS_ZERO) params->spp_hbinterval = 0; if (params->spp_hbinterval || (params->spp_flags & SPP_HB_TIME_IS_ZERO)) { if (trans) { trans->hbinterval = msecs_to_jiffies(params->spp_hbinterval); sctp_transport_reset_hb_timer(trans); } else if (asoc) { asoc->hbinterval = msecs_to_jiffies(params->spp_hbinterval); } else { sp->hbinterval = params->spp_hbinterval; } } } if (hb_change) { if (trans) { trans->param_flags = (trans->param_flags & ~SPP_HB) | hb_change; } else if (asoc) { asoc->param_flags = (asoc->param_flags & ~SPP_HB) | hb_change; } else { sp->param_flags = (sp->param_flags & ~SPP_HB) | hb_change; } } /* When Path MTU discovery is disabled the value specified here will * be the "fixed" path mtu (i.e. the value of the spp_flags field must * include the flag SPP_PMTUD_DISABLE for this field to have any * effect). */ if ((params->spp_flags & SPP_PMTUD_DISABLE) && params->spp_pathmtu) { if (trans) { trans->pathmtu = params->spp_pathmtu; sctp_assoc_sync_pmtu(asoc); } else if (asoc) { sctp_assoc_set_pmtu(asoc, params->spp_pathmtu); } else { sp->pathmtu = params->spp_pathmtu; } } if (pmtud_change) { if (trans) { int update = (trans->param_flags & SPP_PMTUD_DISABLE) && (params->spp_flags & SPP_PMTUD_ENABLE); trans->param_flags = (trans->param_flags & ~SPP_PMTUD) | pmtud_change; if (update) { sctp_transport_pmtu(trans, sctp_opt2sk(sp)); sctp_assoc_sync_pmtu(asoc); } sctp_transport_pl_reset(trans); } else if (asoc) { asoc->param_flags = (asoc->param_flags & ~SPP_PMTUD) | pmtud_change; } else { sp->param_flags = (sp->param_flags & ~SPP_PMTUD) | pmtud_change; } } /* Note that unless the spp_flag is set to SPP_SACKDELAY_ENABLE the * value of this field is ignored. Note also that a value of zero * indicates the current setting should be left unchanged. */ if ((params->spp_flags & SPP_SACKDELAY_ENABLE) && params->spp_sackdelay) { if (trans) { trans->sackdelay = msecs_to_jiffies(params->spp_sackdelay); } else if (asoc) { asoc->sackdelay = msecs_to_jiffies(params->spp_sackdelay); } else { sp->sackdelay = params->spp_sackdelay; } } if (sackdelay_change) { if (trans) { trans->param_flags = (trans->param_flags & ~SPP_SACKDELAY) | sackdelay_change; } else if (asoc) { asoc->param_flags = (asoc->param_flags & ~SPP_SACKDELAY) | sackdelay_change; } else { sp->param_flags = (sp->param_flags & ~SPP_SACKDELAY) | sackdelay_change; } } /* Note that a value of zero indicates the current setting should be left unchanged. */ if (params->spp_pathmaxrxt) { if (trans) { trans->pathmaxrxt = params->spp_pathmaxrxt; } else if (asoc) { asoc->pathmaxrxt = params->spp_pathmaxrxt; } else { sp->pathmaxrxt = params->spp_pathmaxrxt; } } if (params->spp_flags & SPP_IPV6_FLOWLABEL) { if (trans) { if (trans->ipaddr.sa.sa_family == AF_INET6) { trans->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } } else if (asoc) { struct sctp_transport *t; list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (t->ipaddr.sa.sa_family != AF_INET6) continue; t->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; t->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } asoc->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; asoc->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } else if (sctp_opt2sk(sp)->sk_family == AF_INET6) { sp->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; sp->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } } if (params->spp_flags & SPP_DSCP) { if (trans) { trans->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; trans->dscp |= SCTP_DSCP_SET_MASK; } else if (asoc) { struct sctp_transport *t; list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { t->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; t->dscp |= SCTP_DSCP_SET_MASK; } asoc->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; asoc->dscp |= SCTP_DSCP_SET_MASK; } else { sp->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; sp->dscp |= SCTP_DSCP_SET_MASK; } } return 0; } static int sctp_setsockopt_peer_addr_params(struct sock *sk, struct sctp_paddrparams *params, unsigned int optlen) { struct sctp_transport *trans = NULL; struct sctp_association *asoc = NULL; struct sctp_sock *sp = sctp_sk(sk); int error; int hb_change, pmtud_change, sackdelay_change; if (optlen == ALIGN(offsetof(struct sctp_paddrparams, spp_ipv6_flowlabel), 4)) { if (params->spp_flags & (SPP_DSCP | SPP_IPV6_FLOWLABEL)) return -EINVAL; } else if (optlen != sizeof(*params)) { return -EINVAL; } /* Validate flags and value parameters. */ hb_change = params->spp_flags & SPP_HB; pmtud_change = params->spp_flags & SPP_PMTUD; sackdelay_change = params->spp_flags & SPP_SACKDELAY; if (hb_change == SPP_HB || pmtud_change == SPP_PMTUD || sackdelay_change == SPP_SACKDELAY || params->spp_sackdelay > 500 || (params->spp_pathmtu && params->spp_pathmtu < SCTP_DEFAULT_MINSEGMENT)) return -EINVAL; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ if (!sctp_is_any(sk, (union sctp_addr *)¶ms->spp_address)) { trans = sctp_addr_id2transport(sk, ¶ms->spp_address, params->spp_assoc_id); if (!trans) return -EINVAL; } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params->spp_assoc_id); if (!asoc && params->spp_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* Heartbeat demand can only be sent on a transport or * association, but not a socket. */ if (params->spp_flags & SPP_HB_DEMAND && !trans && !asoc) return -EINVAL; /* Process parameters. */ error = sctp_apply_peer_addr_params(params, trans, asoc, sp, hb_change, pmtud_change, sackdelay_change); if (error) return error; /* If changes are for association, also apply parameters to each * transport. */ if (!trans && asoc) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { sctp_apply_peer_addr_params(params, trans, asoc, sp, hb_change, pmtud_change, sackdelay_change); } } return 0; } static inline __u32 sctp_spp_sackdelay_enable(__u32 param_flags) { return (param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_ENABLE; } static inline __u32 sctp_spp_sackdelay_disable(__u32 param_flags) { return (param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_DISABLE; } static void sctp_apply_asoc_delayed_ack(struct sctp_sack_info *params, struct sctp_association *asoc) { struct sctp_transport *trans; if (params->sack_delay) { asoc->sackdelay = msecs_to_jiffies(params->sack_delay); asoc->param_flags = sctp_spp_sackdelay_enable(asoc->param_flags); } if (params->sack_freq == 1) { asoc->param_flags = sctp_spp_sackdelay_disable(asoc->param_flags); } else if (params->sack_freq > 1) { asoc->sackfreq = params->sack_freq; asoc->param_flags = sctp_spp_sackdelay_enable(asoc->param_flags); } list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { if (params->sack_delay) { trans->sackdelay = msecs_to_jiffies(params->sack_delay); trans->param_flags = sctp_spp_sackdelay_enable(trans->param_flags); } if (params->sack_freq == 1) { trans->param_flags = sctp_spp_sackdelay_disable(trans->param_flags); } else if (params->sack_freq > 1) { trans->sackfreq = params->sack_freq; trans->param_flags = sctp_spp_sackdelay_enable(trans->param_flags); } } } /* * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) * * This option will effect the way delayed acks are performed. This * option allows you to get or set the delayed ack time, in * milliseconds. It also allows changing the delayed ack frequency. * Changing the frequency to 1 disables the delayed sack algorithm. If * the assoc_id is 0, then this sets or gets the endpoints default * values. If the assoc_id field is non-zero, then the set or get * effects the specified association for the one to many model (the * assoc_id field is ignored by the one to one model). Note that if * sack_delay or sack_freq are 0 when setting this option, then the * current values will remain unchanged. * * struct sctp_sack_info { * sctp_assoc_t sack_assoc_id; * uint32_t sack_delay; * uint32_t sack_freq; * }; * * sack_assoc_id - This parameter, indicates which association the user * is performing an action upon. Note that if this field's value is * zero then the endpoints default value is changed (effecting future * associations only). * * sack_delay - This parameter contains the number of milliseconds that * the user is requesting the delayed ACK timer be set to. Note that * this value is defined in the standard to be between 200 and 500 * milliseconds. * * sack_freq - This parameter contains the number of packets that must * be received before a sack is sent without waiting for the delay * timer to expire. The default value for this is 2, setting this * value to 1 will disable the delayed sack algorithm. */ static int __sctp_setsockopt_delayed_ack(struct sock *sk, struct sctp_sack_info *params) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; /* Validate value parameter. */ if (params->sack_delay > 500) return -EINVAL; /* Get association, if sack_assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params->sack_assoc_id); if (!asoc && params->sack_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { sctp_apply_asoc_delayed_ack(params, asoc); return 0; } if (sctp_style(sk, TCP)) params->sack_assoc_id = SCTP_FUTURE_ASSOC; if (params->sack_assoc_id == SCTP_FUTURE_ASSOC || params->sack_assoc_id == SCTP_ALL_ASSOC) { if (params->sack_delay) { sp->sackdelay = params->sack_delay; sp->param_flags = sctp_spp_sackdelay_enable(sp->param_flags); } if (params->sack_freq == 1) { sp->param_flags = sctp_spp_sackdelay_disable(sp->param_flags); } else if (params->sack_freq > 1) { sp->sackfreq = params->sack_freq; sp->param_flags = sctp_spp_sackdelay_enable(sp->param_flags); } } if (params->sack_assoc_id == SCTP_CURRENT_ASSOC || params->sack_assoc_id == SCTP_ALL_ASSOC) list_for_each_entry(asoc, &sp->ep->asocs, asocs) sctp_apply_asoc_delayed_ack(params, asoc); return 0; } static int sctp_setsockopt_delayed_ack(struct sock *sk, struct sctp_sack_info *params, unsigned int optlen) { if (optlen == sizeof(struct sctp_assoc_value)) { struct sctp_assoc_value *v = (struct sctp_assoc_value *)params; struct sctp_sack_info p; pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of struct sctp_assoc_value in delayed_ack socket option.\n" "Use struct sctp_sack_info instead\n", current->comm, task_pid_nr(current)); p.sack_assoc_id = v->assoc_id; p.sack_delay = v->assoc_value; p.sack_freq = v->assoc_value ? 0 : 1; return __sctp_setsockopt_delayed_ack(sk, &p); } if (optlen != sizeof(struct sctp_sack_info)) return -EINVAL; if (params->sack_delay == 0 && params->sack_freq == 0) return 0; return __sctp_setsockopt_delayed_ack(sk, params); } /* 7.1.3 Initialization Parameters (SCTP_INITMSG) * * Applications can specify protocol parameters for the default association * initialization. The option name argument to setsockopt() and getsockopt() * is SCTP_INITMSG. * * Setting initialization parameters is effective only on an unconnected * socket (for UDP-style sockets only future associations are effected * by the change). With TCP-style sockets, this option is inherited by * sockets derived from a listener socket. */ static int sctp_setsockopt_initmsg(struct sock *sk, struct sctp_initmsg *sinit, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); if (optlen != sizeof(struct sctp_initmsg)) return -EINVAL; if (sinit->sinit_num_ostreams) sp->initmsg.sinit_num_ostreams = sinit->sinit_num_ostreams; if (sinit->sinit_max_instreams) sp->initmsg.sinit_max_instreams = sinit->sinit_max_instreams; if (sinit->sinit_max_attempts) sp->initmsg.sinit_max_attempts = sinit->sinit_max_attempts; if (sinit->sinit_max_init_timeo) sp->initmsg.sinit_max_init_timeo = sinit->sinit_max_init_timeo; return 0; } /* * 7.1.14 Set default send parameters (SCTP_DEFAULT_SEND_PARAM) * * Applications that wish to use the sendto() system call may wish to * specify a default set of parameters that would normally be supplied * through the inclusion of ancillary data. This socket option allows * such an application to set the default sctp_sndrcvinfo structure. * The application that wishes to use this socket option simply passes * in to this call the sctp_sndrcvinfo structure defined in Section * 5.2.2) The input parameters accepted by this call include * sinfo_stream, sinfo_flags, sinfo_ppid, sinfo_context, * sinfo_timetolive. The user must provide the sinfo_assoc_id field in * to this call if the caller is using the UDP model. */ static int sctp_setsockopt_default_send_param(struct sock *sk, struct sctp_sndrcvinfo *info, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; if (optlen != sizeof(*info)) return -EINVAL; if (info->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | SCTP_ABORT | SCTP_EOF)) return -EINVAL; asoc = sctp_id2assoc(sk, info->sinfo_assoc_id); if (!asoc && info->sinfo_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { asoc->default_stream = info->sinfo_stream; asoc->default_flags = info->sinfo_flags; asoc->default_ppid = info->sinfo_ppid; asoc->default_context = info->sinfo_context; asoc->default_timetolive = info->sinfo_timetolive; return 0; } if (sctp_style(sk, TCP)) info->sinfo_assoc_id = SCTP_FUTURE_ASSOC; if (info->sinfo_assoc_id == SCTP_FUTURE_ASSOC || info->sinfo_assoc_id == SCTP_ALL_ASSOC) { sp->default_stream = info->sinfo_stream; sp->default_flags = info->sinfo_flags; sp->default_ppid = info->sinfo_ppid; sp->default_context = info->sinfo_context; sp->default_timetolive = info->sinfo_timetolive; } if (info->sinfo_assoc_id == SCTP_CURRENT_ASSOC || info->sinfo_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &sp->ep->asocs, asocs) { asoc->default_stream = info->sinfo_stream; asoc->default_flags = info->sinfo_flags; asoc->default_ppid = info->sinfo_ppid; asoc->default_context = info->sinfo_context; asoc->default_timetolive = info->sinfo_timetolive; } } return 0; } /* RFC6458, Section 8.1.31. Set/get Default Send Parameters * (SCTP_DEFAULT_SNDINFO) */ static int sctp_setsockopt_default_sndinfo(struct sock *sk, struct sctp_sndinfo *info, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; if (optlen != sizeof(*info)) return -EINVAL; if (info->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | SCTP_ABORT | SCTP_EOF)) return -EINVAL; asoc = sctp_id2assoc(sk, info->snd_assoc_id); if (!asoc && info->snd_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { asoc->default_stream = info->snd_sid; asoc->default_flags = info->snd_flags; asoc->default_ppid = info->snd_ppid; asoc->default_context = info->snd_context; return 0; } if (sctp_style(sk, TCP)) info->snd_assoc_id = SCTP_FUTURE_ASSOC; if (info->snd_assoc_id == SCTP_FUTURE_ASSOC || info->snd_assoc_id == SCTP_ALL_ASSOC) { sp->default_stream = info->snd_sid; sp->default_flags = info->snd_flags; sp->default_ppid = info->snd_ppid; sp->default_context = info->snd_context; } if (info->snd_assoc_id == SCTP_CURRENT_ASSOC || info->snd_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &sp->ep->asocs, asocs) { asoc->default_stream = info->snd_sid; asoc->default_flags = info->snd_flags; asoc->default_ppid = info->snd_ppid; asoc->default_context = info->snd_context; } } return 0; } /* 7.1.10 Set Primary Address (SCTP_PRIMARY_ADDR) * * Requests that the local SCTP stack use the enclosed peer address as * the association primary. The enclosed address must be one of the * association peer's addresses. */ static int sctp_setsockopt_primary_addr(struct sock *sk, struct sctp_prim *prim, unsigned int optlen) { struct sctp_transport *trans; struct sctp_af *af; int err; if (optlen != sizeof(struct sctp_prim)) return -EINVAL; /* Allow security module to validate address but need address len. */ af = sctp_get_af_specific(prim->ssp_addr.ss_family); if (!af) return -EINVAL; err = security_sctp_bind_connect(sk, SCTP_PRIMARY_ADDR, (struct sockaddr *)&prim->ssp_addr, af->sockaddr_len); if (err) return err; trans = sctp_addr_id2transport(sk, &prim->ssp_addr, prim->ssp_assoc_id); if (!trans) return -EINVAL; sctp_assoc_set_primary(trans->asoc, trans); return 0; } /* * 7.1.5 SCTP_NODELAY * * Turn on/off any Nagle-like algorithm. This means that packets are * generally sent as soon as possible and no unnecessary delays are * introduced, at the cost of more packets in the network. Expects an * integer boolean flag. */ static int sctp_setsockopt_nodelay(struct sock *sk, int *val, unsigned int optlen) { if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->nodelay = (*val == 0) ? 0 : 1; return 0; } /* * * 7.1.1 SCTP_RTOINFO * * The protocol parameters used to initialize and bound retransmission * timeout (RTO) are tunable. sctp_rtoinfo structure is used to access * and modify these parameters. * All parameters are time values, in milliseconds. A value of 0, when * modifying the parameters, indicates that the current value should not * be changed. * */ static int sctp_setsockopt_rtoinfo(struct sock *sk, struct sctp_rtoinfo *rtoinfo, unsigned int optlen) { struct sctp_association *asoc; unsigned long rto_min, rto_max; struct sctp_sock *sp = sctp_sk(sk); if (optlen != sizeof (struct sctp_rtoinfo)) return -EINVAL; asoc = sctp_id2assoc(sk, rtoinfo->srto_assoc_id); /* Set the values to the specific association */ if (!asoc && rtoinfo->srto_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; rto_max = rtoinfo->srto_max; rto_min = rtoinfo->srto_min; if (rto_max) rto_max = asoc ? msecs_to_jiffies(rto_max) : rto_max; else rto_max = asoc ? asoc->rto_max : sp->rtoinfo.srto_max; if (rto_min) rto_min = asoc ? msecs_to_jiffies(rto_min) : rto_min; else rto_min = asoc ? asoc->rto_min : sp->rtoinfo.srto_min; if (rto_min > rto_max) return -EINVAL; if (asoc) { if (rtoinfo->srto_initial != 0) asoc->rto_initial = msecs_to_jiffies(rtoinfo->srto_initial); asoc->rto_max = rto_max; asoc->rto_min = rto_min; } else { /* If there is no association or the association-id = 0 * set the values to the endpoint. */ if (rtoinfo->srto_initial != 0) sp->rtoinfo.srto_initial = rtoinfo->srto_initial; sp->rtoinfo.srto_max = rto_max; sp->rtoinfo.srto_min = rto_min; } return 0; } /* * * 7.1.2 SCTP_ASSOCINFO * * This option is used to tune the maximum retransmission attempts * of the association. * Returns an error if the new association retransmission value is * greater than the sum of the retransmission value of the peer. * See [SCTP] for more information. * */ static int sctp_setsockopt_associnfo(struct sock *sk, struct sctp_assocparams *assocparams, unsigned int optlen) { struct sctp_association *asoc; if (optlen != sizeof(struct sctp_assocparams)) return -EINVAL; asoc = sctp_id2assoc(sk, assocparams->sasoc_assoc_id); if (!asoc && assocparams->sasoc_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* Set the values to the specific association */ if (asoc) { if (assocparams->sasoc_asocmaxrxt != 0) { __u32 path_sum = 0; int paths = 0; struct sctp_transport *peer_addr; list_for_each_entry(peer_addr, &asoc->peer.transport_addr_list, transports) { path_sum += peer_addr->pathmaxrxt; paths++; } /* Only validate asocmaxrxt if we have more than * one path/transport. We do this because path * retransmissions are only counted when we have more * then one path. */ if (paths > 1 && assocparams->sasoc_asocmaxrxt > path_sum) return -EINVAL; asoc->max_retrans = assocparams->sasoc_asocmaxrxt; } if (assocparams->sasoc_cookie_life != 0) asoc->cookie_life = ms_to_ktime(assocparams->sasoc_cookie_life); } else { /* Set the values to the endpoint */ struct sctp_sock *sp = sctp_sk(sk); if (assocparams->sasoc_asocmaxrxt != 0) sp->assocparams.sasoc_asocmaxrxt = assocparams->sasoc_asocmaxrxt; if (assocparams->sasoc_cookie_life != 0) sp->assocparams.sasoc_cookie_life = assocparams->sasoc_cookie_life; } return 0; } /* * 7.1.16 Set/clear IPv4 mapped addresses (SCTP_I_WANT_MAPPED_V4_ADDR) * * This socket option is a boolean flag which turns on or off mapped V4 * addresses. If this option is turned on and the socket is type * PF_INET6, then IPv4 addresses will be mapped to V6 representation. * If this option is turned off, then no mapping will be done of V4 * addresses and a user will receive both PF_INET6 and PF_INET type * addresses on the socket. */ static int sctp_setsockopt_mappedv4(struct sock *sk, int *val, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); if (optlen < sizeof(int)) return -EINVAL; if (*val) sp->v4mapped = 1; else sp->v4mapped = 0; return 0; } /* * 8.1.16. Get or Set the Maximum Fragmentation Size (SCTP_MAXSEG) * This option will get or set the maximum size to put in any outgoing * SCTP DATA chunk. If a message is larger than this size it will be * fragmented by SCTP into the specified size. Note that the underlying * SCTP implementation may fragment into smaller sized chunks when the * PMTU of the underlying association is smaller than the value set by * the user. The default value for this option is '0' which indicates * the user is NOT limiting fragmentation and only the PMTU will effect * SCTP's choice of DATA chunk size. Note also that values set larger * than the maximum size of an IP datagram will effectively let SCTP * control fragmentation (i.e. the same as setting this option to 0). * * The following structure is used to access and modify this parameter: * * struct sctp_assoc_value { * sctp_assoc_t assoc_id; * uint32_t assoc_value; * }; * * assoc_id: This parameter is ignored for one-to-one style sockets. * For one-to-many style sockets this parameter indicates which * association the user is performing an action upon. Note that if * this field's value is zero then the endpoints default value is * changed (effecting future associations only). * assoc_value: This parameter specifies the maximum size in bytes. */ static int sctp_setsockopt_maxseg(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; sctp_assoc_t assoc_id; int val; if (optlen == sizeof(int)) { pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of int in maxseg socket option.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); assoc_id = SCTP_FUTURE_ASSOC; val = *(int *)params; } else if (optlen == sizeof(struct sctp_assoc_value)) { assoc_id = params->assoc_id; val = params->assoc_value; } else { return -EINVAL; } asoc = sctp_id2assoc(sk, assoc_id); if (!asoc && assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (val) { int min_len, max_len; __u16 datasize = asoc ? sctp_datachk_len(&asoc->stream) : sizeof(struct sctp_data_chunk); min_len = sctp_min_frag_point(sp, datasize); max_len = SCTP_MAX_CHUNK_LEN - datasize; if (val < min_len || val > max_len) return -EINVAL; } if (asoc) { asoc->user_frag = val; sctp_assoc_update_frag_point(asoc); } else { sp->user_frag = val; } return 0; } /* * 7.1.9 Set Peer Primary Address (SCTP_SET_PEER_PRIMARY_ADDR) * * Requests that the peer mark the enclosed address as the association * primary. The enclosed address must be one of the association's * locally bound addresses. The following structure is used to make a * set primary request: */ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, struct sctp_setpeerprim *prim, unsigned int optlen) { struct sctp_sock *sp; struct sctp_association *asoc = NULL; struct sctp_chunk *chunk; struct sctp_af *af; int err; sp = sctp_sk(sk); if (!sp->ep->asconf_enable) return -EPERM; if (optlen != sizeof(struct sctp_setpeerprim)) return -EINVAL; asoc = sctp_id2assoc(sk, prim->sspp_assoc_id); if (!asoc) return -EINVAL; if (!asoc->peer.asconf_capable) return -EPERM; if (asoc->peer.addip_disabled_mask & SCTP_PARAM_SET_PRIMARY) return -EPERM; if (!sctp_state(asoc, ESTABLISHED)) return -ENOTCONN; af = sctp_get_af_specific(prim->sspp_addr.ss_family); if (!af) return -EINVAL; if (!af->addr_valid((union sctp_addr *)&prim->sspp_addr, sp, NULL)) return -EADDRNOTAVAIL; if (!sctp_assoc_lookup_laddr(asoc, (union sctp_addr *)&prim->sspp_addr)) return -EADDRNOTAVAIL; /* Allow security module to validate address. */ err = security_sctp_bind_connect(sk, SCTP_SET_PEER_PRIMARY_ADDR, (struct sockaddr *)&prim->sspp_addr, af->sockaddr_len); if (err) return err; /* Create an ASCONF chunk with SET_PRIMARY parameter */ chunk = sctp_make_asconf_set_prim(asoc, (union sctp_addr *)&prim->sspp_addr); if (!chunk) return -ENOMEM; err = sctp_send_asconf(asoc, chunk); pr_debug("%s: we set peer primary addr primitively\n", __func__); return err; } static int sctp_setsockopt_adaptation_layer(struct sock *sk, struct sctp_setadaptation *adapt, unsigned int optlen) { if (optlen != sizeof(struct sctp_setadaptation)) return -EINVAL; sctp_sk(sk)->adaptation_ind = adapt->ssb_adaptation_ind; return 0; } /* * 7.1.29. Set or Get the default context (SCTP_CONTEXT) * * The context field in the sctp_sndrcvinfo structure is normally only * used when a failed message is retrieved holding the value that was * sent down on the actual send call. This option allows the setting of * a default context on an association basis that will be received on * reading messages from the peer. This is especially helpful in the * one-2-many model for an application to keep some reference to an * internal state machine that is processing messages on the * association. Note that the setting of this value only effects * received messages from the peer and does not effect the value that is * saved with outbound messages. */ static int sctp_setsockopt_context(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; if (optlen != sizeof(struct sctp_assoc_value)) return -EINVAL; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { asoc->default_rcv_context = params->assoc_value; return 0; } if (sctp_style(sk, TCP)) params->assoc_id = SCTP_FUTURE_ASSOC; if (params->assoc_id == SCTP_FUTURE_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) sp->default_rcv_context = params->assoc_value; if (params->assoc_id == SCTP_CURRENT_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) list_for_each_entry(asoc, &sp->ep->asocs, asocs) asoc->default_rcv_context = params->assoc_value; return 0; } /* * 7.1.24. Get or set fragmented interleave (SCTP_FRAGMENT_INTERLEAVE) * * This options will at a minimum specify if the implementation is doing * fragmented interleave. Fragmented interleave, for a one to many * socket, is when subsequent calls to receive a message may return * parts of messages from different associations. Some implementations * may allow you to turn this value on or off. If so, when turned off, * no fragment interleave will occur (which will cause a head of line * blocking amongst multiple associations sharing the same one to many * socket). When this option is turned on, then each receive call may * come from a different association (thus the user must receive data * with the extended calls (e.g. sctp_recvmsg) to keep track of which * association each receive belongs to. * * This option takes a boolean value. A non-zero value indicates that * fragmented interleave is on. A value of zero indicates that * fragmented interleave is off. * * Note that it is important that an implementation that allows this * option to be turned on, have it off by default. Otherwise an unaware * application using the one to many model may become confused and act * incorrectly. */ static int sctp_setsockopt_fragment_interleave(struct sock *sk, int *val, unsigned int optlen) { if (optlen != sizeof(int)) return -EINVAL; sctp_sk(sk)->frag_interleave = !!*val; if (!sctp_sk(sk)->frag_interleave) sctp_sk(sk)->ep->intl_enable = 0; return 0; } /* * 8.1.21. Set or Get the SCTP Partial Delivery Point * (SCTP_PARTIAL_DELIVERY_POINT) * * This option will set or get the SCTP partial delivery point. This * point is the size of a message where the partial delivery API will be * invoked to help free up rwnd space for the peer. Setting this to a * lower value will cause partial deliveries to happen more often. The * calls argument is an integer that sets or gets the partial delivery * point. Note also that the call will fail if the user attempts to set * this value larger than the socket receive buffer size. * * Note that any single message having a length smaller than or equal to * the SCTP partial delivery point will be delivered in one single read * call as long as the user provided buffer is large enough to hold the * message. */ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, u32 *val, unsigned int optlen) { if (optlen != sizeof(u32)) return -EINVAL; /* Note: We double the receive buffer from what the user sets * it to be, also initial rwnd is based on rcvbuf/2. */ if (*val > (sk->sk_rcvbuf >> 1)) return -EINVAL; sctp_sk(sk)->pd_point = *val; return 0; /* is this the right error code? */ } /* * 7.1.28. Set or Get the maximum burst (SCTP_MAX_BURST) * * This option will allow a user to change the maximum burst of packets * that can be emitted by this association. Note that the default value * is 4, and some implementations may restrict this setting so that it * can only be lowered. * * NOTE: This text doesn't seem right. Do this on a socket basis with * future associations inheriting the socket value. */ static int sctp_setsockopt_maxburst(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; sctp_assoc_t assoc_id; u32 assoc_value; if (optlen == sizeof(int)) { pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of int in max_burst socket option deprecated.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); assoc_id = SCTP_FUTURE_ASSOC; assoc_value = *((int *)params); } else if (optlen == sizeof(struct sctp_assoc_value)) { assoc_id = params->assoc_id; assoc_value = params->assoc_value; } else return -EINVAL; asoc = sctp_id2assoc(sk, assoc_id); if (!asoc && assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { asoc->max_burst = assoc_value; return 0; } if (sctp_style(sk, TCP)) assoc_id = SCTP_FUTURE_ASSOC; if (assoc_id == SCTP_FUTURE_ASSOC || assoc_id == SCTP_ALL_ASSOC) sp->max_burst = assoc_value; if (assoc_id == SCTP_CURRENT_ASSOC || assoc_id == SCTP_ALL_ASSOC) list_for_each_entry(asoc, &sp->ep->asocs, asocs) asoc->max_burst = assoc_value; return 0; } /* * 7.1.18. Add a chunk that must be authenticated (SCTP_AUTH_CHUNK) * * This set option adds a chunk type that the user is requesting to be * received only in an authenticated way. Changes to the list of chunks * will only effect future associations on the socket. */ static int sctp_setsockopt_auth_chunk(struct sock *sk, struct sctp_authchunk *val, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authchunk)) return -EINVAL; switch (val->sauth_chunk) { case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: case SCTP_CID_SHUTDOWN_COMPLETE: case SCTP_CID_AUTH: return -EINVAL; } /* add this chunk id to the endpoint */ return sctp_auth_ep_add_chunkid(ep, val->sauth_chunk); } /* * 7.1.19. Get or set the list of supported HMAC Identifiers (SCTP_HMAC_IDENT) * * This option gets or sets the list of HMAC algorithms that the local * endpoint requires the peer to use. */ static int sctp_setsockopt_hmac_ident(struct sock *sk, struct sctp_hmacalgo *hmacs, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; u32 idents; if (!ep->auth_enable) return -EACCES; if (optlen < sizeof(struct sctp_hmacalgo)) return -EINVAL; optlen = min_t(unsigned int, optlen, sizeof(struct sctp_hmacalgo) + SCTP_AUTH_NUM_HMACS * sizeof(u16)); idents = hmacs->shmac_num_idents; if (idents == 0 || idents > SCTP_AUTH_NUM_HMACS || (idents * sizeof(u16)) > (optlen - sizeof(struct sctp_hmacalgo))) return -EINVAL; return sctp_auth_ep_set_hmacs(ep, hmacs); } /* * 7.1.20. Set a shared key (SCTP_AUTH_KEY) * * This option will set a shared secret key which is used to build an * association shared key. */ static int sctp_setsockopt_auth_key(struct sock *sk, struct sctp_authkey *authkey, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; int ret = -EINVAL; if (optlen <= sizeof(struct sctp_authkey)) return -EINVAL; /* authkey->sca_keylength is u16, so optlen can't be bigger than * this. */ optlen = min_t(unsigned int, optlen, USHRT_MAX + sizeof(*authkey)); if (authkey->sca_keylength > optlen - sizeof(*authkey)) goto out; asoc = sctp_id2assoc(sk, authkey->sca_assoc_id); if (!asoc && authkey->sca_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) goto out; if (asoc) { ret = sctp_auth_set_key(ep, asoc, authkey); goto out; } if (sctp_style(sk, TCP)) authkey->sca_assoc_id = SCTP_FUTURE_ASSOC; if (authkey->sca_assoc_id == SCTP_FUTURE_ASSOC || authkey->sca_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_set_key(ep, asoc, authkey); if (ret) goto out; } ret = 0; if (authkey->sca_assoc_id == SCTP_CURRENT_ASSOC || authkey->sca_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &ep->asocs, asocs) { int res = sctp_auth_set_key(ep, asoc, authkey); if (res && !ret) ret = res; } } out: memzero_explicit(authkey, optlen); return ret; } /* * 7.1.21. Get or set the active shared key (SCTP_AUTH_ACTIVE_KEY) * * This option will get or set the active shared key to be used to build * the association shared key. */ static int sctp_setsockopt_active_key(struct sock *sk, struct sctp_authkeyid *val, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; int ret = 0; if (optlen != sizeof(struct sctp_authkeyid)) return -EINVAL; asoc = sctp_id2assoc(sk, val->scact_assoc_id); if (!asoc && val->scact_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) return sctp_auth_set_active_key(ep, asoc, val->scact_keynumber); if (sctp_style(sk, TCP)) val->scact_assoc_id = SCTP_FUTURE_ASSOC; if (val->scact_assoc_id == SCTP_FUTURE_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_set_active_key(ep, asoc, val->scact_keynumber); if (ret) return ret; } if (val->scact_assoc_id == SCTP_CURRENT_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &ep->asocs, asocs) { int res = sctp_auth_set_active_key(ep, asoc, val->scact_keynumber); if (res && !ret) ret = res; } } return ret; } /* * 7.1.22. Delete a shared key (SCTP_AUTH_DELETE_KEY) * * This set option will delete a shared secret key from use. */ static int sctp_setsockopt_del_key(struct sock *sk, struct sctp_authkeyid *val, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; int ret = 0; if (optlen != sizeof(struct sctp_authkeyid)) return -EINVAL; asoc = sctp_id2assoc(sk, val->scact_assoc_id); if (!asoc && val->scact_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) return sctp_auth_del_key_id(ep, asoc, val->scact_keynumber); if (sctp_style(sk, TCP)) val->scact_assoc_id = SCTP_FUTURE_ASSOC; if (val->scact_assoc_id == SCTP_FUTURE_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_del_key_id(ep, asoc, val->scact_keynumber); if (ret) return ret; } if (val->scact_assoc_id == SCTP_CURRENT_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &ep->asocs, asocs) { int res = sctp_auth_del_key_id(ep, asoc, val->scact_keynumber); if (res && !ret) ret = res; } } return ret; } /* * 8.3.4 Deactivate a Shared Key (SCTP_AUTH_DEACTIVATE_KEY) * * This set option will deactivate a shared secret key. */ static int sctp_setsockopt_deactivate_key(struct sock *sk, struct sctp_authkeyid *val, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; int ret = 0; if (optlen != sizeof(struct sctp_authkeyid)) return -EINVAL; asoc = sctp_id2assoc(sk, val->scact_assoc_id); if (!asoc && val->scact_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) return sctp_auth_deact_key_id(ep, asoc, val->scact_keynumber); if (sctp_style(sk, TCP)) val->scact_assoc_id = SCTP_FUTURE_ASSOC; if (val->scact_assoc_id == SCTP_FUTURE_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_deact_key_id(ep, asoc, val->scact_keynumber); if (ret) return ret; } if (val->scact_assoc_id == SCTP_CURRENT_ASSOC || val->scact_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &ep->asocs, asocs) { int res = sctp_auth_deact_key_id(ep, asoc, val->scact_keynumber); if (res && !ret) ret = res; } } return ret; } /* * 8.1.23 SCTP_AUTO_ASCONF * * This option will enable or disable the use of the automatic generation of * ASCONF chunks to add and delete addresses to an existing association. Note * that this option has two caveats namely: a) it only affects sockets that * are bound to all addresses available to the SCTP stack, and b) the system * administrator may have an overriding control that turns the ASCONF feature * off no matter what setting the socket option may have. * This option expects an integer boolean flag, where a non-zero value turns on * the option, and a zero value turns off the option. * Note. In this implementation, socket operation overrides default parameter * being set by sysctl as well as FreeBSD implementation */ static int sctp_setsockopt_auto_asconf(struct sock *sk, int *val, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); if (optlen < sizeof(int)) return -EINVAL; if (!sctp_is_ep_boundall(sk) && *val) return -EINVAL; if ((*val && sp->do_auto_asconf) || (!*val && !sp->do_auto_asconf)) return 0; spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock); if (*val == 0 && sp->do_auto_asconf) { list_del(&sp->auto_asconf_list); sp->do_auto_asconf = 0; } else if (*val && !sp->do_auto_asconf) { list_add_tail(&sp->auto_asconf_list, &sock_net(sk)->sctp.auto_asconf_splist); sp->do_auto_asconf = 1; } spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock); return 0; } /* * SCTP_PEER_ADDR_THLDS * * This option allows us to alter the partially failed threshold for one or all * transports in an association. See Section 6.1 of: * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt */ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, struct sctp_paddrthlds_v2 *val, unsigned int optlen, bool v2) { struct sctp_transport *trans; struct sctp_association *asoc; int len; len = v2 ? sizeof(*val) : sizeof(struct sctp_paddrthlds); if (optlen < len) return -EINVAL; if (v2 && val->spt_pathpfthld > val->spt_pathcpthld) return -EINVAL; if (!sctp_is_any(sk, (const union sctp_addr *)&val->spt_address)) { trans = sctp_addr_id2transport(sk, &val->spt_address, val->spt_assoc_id); if (!trans) return -ENOENT; if (val->spt_pathmaxrxt) trans->pathmaxrxt = val->spt_pathmaxrxt; if (v2) trans->ps_retrans = val->spt_pathcpthld; trans->pf_retrans = val->spt_pathpfthld; return 0; } asoc = sctp_id2assoc(sk, val->spt_assoc_id); if (!asoc && val->spt_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { if (val->spt_pathmaxrxt) trans->pathmaxrxt = val->spt_pathmaxrxt; if (v2) trans->ps_retrans = val->spt_pathcpthld; trans->pf_retrans = val->spt_pathpfthld; } if (val->spt_pathmaxrxt) asoc->pathmaxrxt = val->spt_pathmaxrxt; if (v2) asoc->ps_retrans = val->spt_pathcpthld; asoc->pf_retrans = val->spt_pathpfthld; } else { struct sctp_sock *sp = sctp_sk(sk); if (val->spt_pathmaxrxt) sp->pathmaxrxt = val->spt_pathmaxrxt; if (v2) sp->ps_retrans = val->spt_pathcpthld; sp->pf_retrans = val->spt_pathpfthld; } return 0; } static int sctp_setsockopt_recvrcvinfo(struct sock *sk, int *val, unsigned int optlen) { if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->recvrcvinfo = (*val == 0) ? 0 : 1; return 0; } static int sctp_setsockopt_recvnxtinfo(struct sock *sk, int *val, unsigned int optlen) { if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->recvnxtinfo = (*val == 0) ? 0 : 1; return 0; } static int sctp_setsockopt_pr_supported(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; if (optlen != sizeof(*params)) return -EINVAL; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; sctp_sk(sk)->ep->prsctp_enable = !!params->assoc_value; return 0; } static int sctp_setsockopt_default_prinfo(struct sock *sk, struct sctp_default_prinfo *info, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; int retval = -EINVAL; if (optlen != sizeof(*info)) goto out; if (info->pr_policy & ~SCTP_PR_SCTP_MASK) goto out; if (info->pr_policy == SCTP_PR_SCTP_NONE) info->pr_value = 0; asoc = sctp_id2assoc(sk, info->pr_assoc_id); if (!asoc && info->pr_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) goto out; retval = 0; if (asoc) { SCTP_PR_SET_POLICY(asoc->default_flags, info->pr_policy); asoc->default_timetolive = info->pr_value; goto out; } if (sctp_style(sk, TCP)) info->pr_assoc_id = SCTP_FUTURE_ASSOC; if (info->pr_assoc_id == SCTP_FUTURE_ASSOC || info->pr_assoc_id == SCTP_ALL_ASSOC) { SCTP_PR_SET_POLICY(sp->default_flags, info->pr_policy); sp->default_timetolive = info->pr_value; } if (info->pr_assoc_id == SCTP_CURRENT_ASSOC || info->pr_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &sp->ep->asocs, asocs) { SCTP_PR_SET_POLICY(asoc->default_flags, info->pr_policy); asoc->default_timetolive = info->pr_value; } } out: return retval; } static int sctp_setsockopt_reconfig_supported(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) goto out; sctp_sk(sk)->ep->reconf_enable = !!params->assoc_value; retval = 0; out: return retval; } static int sctp_setsockopt_enable_strreset(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; if (params->assoc_value & (~SCTP_ENABLE_STRRESET_MASK)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) goto out; retval = 0; if (asoc) { asoc->strreset_enable = params->assoc_value; goto out; } if (sctp_style(sk, TCP)) params->assoc_id = SCTP_FUTURE_ASSOC; if (params->assoc_id == SCTP_FUTURE_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) ep->strreset_enable = params->assoc_value; if (params->assoc_id == SCTP_CURRENT_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) list_for_each_entry(asoc, &ep->asocs, asocs) asoc->strreset_enable = params->assoc_value; out: return retval; } static int sctp_setsockopt_reset_streams(struct sock *sk, struct sctp_reset_streams *params, unsigned int optlen) { struct sctp_association *asoc; if (optlen < sizeof(*params)) return -EINVAL; /* srs_number_streams is u16, so optlen can't be bigger than this. */ optlen = min_t(unsigned int, optlen, USHRT_MAX + sizeof(__u16) * sizeof(*params)); if (params->srs_number_streams * sizeof(__u16) > optlen - sizeof(*params)) return -EINVAL; asoc = sctp_id2assoc(sk, params->srs_assoc_id); if (!asoc) return -EINVAL; return sctp_send_reset_streams(asoc, params); } static int sctp_setsockopt_reset_assoc(struct sock *sk, sctp_assoc_t *associd, unsigned int optlen) { struct sctp_association *asoc; if (optlen != sizeof(*associd)) return -EINVAL; asoc = sctp_id2assoc(sk, *associd); if (!asoc) return -EINVAL; return sctp_send_reset_assoc(asoc); } static int sctp_setsockopt_add_streams(struct sock *sk, struct sctp_add_streams *params, unsigned int optlen) { struct sctp_association *asoc; if (optlen != sizeof(*params)) return -EINVAL; asoc = sctp_id2assoc(sk, params->sas_assoc_id); if (!asoc) return -EINVAL; return sctp_send_add_streams(asoc, params); } static int sctp_setsockopt_scheduler(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; int retval = 0; if (optlen < sizeof(*params)) return -EINVAL; if (params->assoc_value > SCTP_SS_MAX) return -EINVAL; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) return sctp_sched_set_sched(asoc, params->assoc_value); if (sctp_style(sk, TCP)) params->assoc_id = SCTP_FUTURE_ASSOC; if (params->assoc_id == SCTP_FUTURE_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) sp->default_ss = params->assoc_value; if (params->assoc_id == SCTP_CURRENT_ASSOC || params->assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &sp->ep->asocs, asocs) { int ret = sctp_sched_set_sched(asoc, params->assoc_value); if (ret && !retval) retval = ret; } } return retval; } static int sctp_setsockopt_scheduler_value(struct sock *sk, struct sctp_stream_value *params, unsigned int optlen) { struct sctp_association *asoc; int retval = -EINVAL; if (optlen < sizeof(*params)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_CURRENT_ASSOC && sctp_style(sk, UDP)) goto out; if (asoc) { retval = sctp_sched_set_value(asoc, params->stream_id, params->stream_value, GFP_KERNEL); goto out; } retval = 0; list_for_each_entry(asoc, &sctp_sk(sk)->ep->asocs, asocs) { int ret = sctp_sched_set_value(asoc, params->stream_id, params->stream_value, GFP_KERNEL); if (ret && !retval) /* try to return the 1st error. */ retval = ret; } out: return retval; } static int sctp_setsockopt_interleaving_supported(struct sock *sk, struct sctp_assoc_value *p, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; if (optlen < sizeof(*p)) return -EINVAL; asoc = sctp_id2assoc(sk, p->assoc_id); if (!asoc && p->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (!sock_net(sk)->sctp.intl_enable || !sp->frag_interleave) { return -EPERM; } sp->ep->intl_enable = !!p->assoc_value; return 0; } static int sctp_setsockopt_reuse_port(struct sock *sk, int *val, unsigned int optlen) { if (!sctp_style(sk, TCP)) return -EOPNOTSUPP; if (sctp_sk(sk)->ep->base.bind_addr.port) return -EFAULT; if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->reuse = !!*val; return 0; } static int sctp_assoc_ulpevent_type_set(struct sctp_event *param, struct sctp_association *asoc) { struct sctp_ulpevent *event; sctp_ulpevent_type_set(&asoc->subscribe, param->se_type, param->se_on); if (param->se_type == SCTP_SENDER_DRY_EVENT && param->se_on) { if (sctp_outq_is_empty(&asoc->outqueue)) { event = sctp_ulpevent_make_sender_dry_event(asoc, GFP_USER | __GFP_NOWARN); if (!event) return -ENOMEM; asoc->stream.si->enqueue_event(&asoc->ulpq, event); } } return 0; } static int sctp_setsockopt_event(struct sock *sk, struct sctp_event *param, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; int retval = 0; if (optlen < sizeof(*param)) return -EINVAL; if (param->se_type < SCTP_SN_TYPE_BASE || param->se_type > SCTP_SN_TYPE_MAX) return -EINVAL; asoc = sctp_id2assoc(sk, param->se_assoc_id); if (!asoc && param->se_assoc_id > SCTP_ALL_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) return sctp_assoc_ulpevent_type_set(param, asoc); if (sctp_style(sk, TCP)) param->se_assoc_id = SCTP_FUTURE_ASSOC; if (param->se_assoc_id == SCTP_FUTURE_ASSOC || param->se_assoc_id == SCTP_ALL_ASSOC) sctp_ulpevent_type_set(&sp->subscribe, param->se_type, param->se_on); if (param->se_assoc_id == SCTP_CURRENT_ASSOC || param->se_assoc_id == SCTP_ALL_ASSOC) { list_for_each_entry(asoc, &sp->ep->asocs, asocs) { int ret = sctp_assoc_ulpevent_type_set(param, asoc); if (ret && !retval) retval = ret; } } return retval; } static int sctp_setsockopt_asconf_supported(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; struct sctp_endpoint *ep; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) goto out; ep = sctp_sk(sk)->ep; ep->asconf_enable = !!params->assoc_value; if (ep->asconf_enable && ep->auth_enable) { sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF); sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF_ACK); } retval = 0; out: return retval; } static int sctp_setsockopt_auth_supported(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; struct sctp_endpoint *ep; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) goto out; ep = sctp_sk(sk)->ep; if (params->assoc_value) { retval = sctp_auth_init(ep, GFP_KERNEL); if (retval) goto out; if (ep->asconf_enable) { sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF); sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF_ACK); } } ep->auth_enable = !!params->assoc_value; retval = 0; out: return retval; } static int sctp_setsockopt_ecn_supported(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) goto out; sctp_sk(sk)->ep->ecn_enable = !!params->assoc_value; retval = 0; out: return retval; } static int sctp_setsockopt_pf_expose(struct sock *sk, struct sctp_assoc_value *params, unsigned int optlen) { struct sctp_association *asoc; int retval = -EINVAL; if (optlen != sizeof(*params)) goto out; if (params->assoc_value > SCTP_PF_EXPOSE_MAX) goto out; asoc = sctp_id2assoc(sk, params->assoc_id); if (!asoc && params->assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) goto out; if (asoc) asoc->pf_expose = params->assoc_value; else sctp_sk(sk)->pf_expose = params->assoc_value; retval = 0; out: return retval; } static int sctp_setsockopt_encap_port(struct sock *sk, struct sctp_udpencaps *encap, unsigned int optlen) { struct sctp_association *asoc; struct sctp_transport *t; __be16 encap_port; if (optlen != sizeof(*encap)) return -EINVAL; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ encap_port = (__force __be16)encap->sue_port; if (!sctp_is_any(sk, (union sctp_addr *)&encap->sue_address)) { t = sctp_addr_id2transport(sk, &encap->sue_address, encap->sue_assoc_id); if (!t) return -EINVAL; t->encap_port = encap_port; return 0; } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, encap->sue_assoc_id); if (!asoc && encap->sue_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* If changes are for association, also apply encap_port to * each transport. */ if (asoc) { list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) t->encap_port = encap_port; asoc->encap_port = encap_port; return 0; } sctp_sk(sk)->encap_port = encap_port; return 0; } static int sctp_setsockopt_probe_interval(struct sock *sk, struct sctp_probeinterval *params, unsigned int optlen) { struct sctp_association *asoc; struct sctp_transport *t; __u32 probe_interval; if (optlen != sizeof(*params)) return -EINVAL; probe_interval = params->spi_interval; if (probe_interval && probe_interval < SCTP_PROBE_TIMER_MIN) return -EINVAL; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ if (!sctp_is_any(sk, (union sctp_addr *)¶ms->spi_address)) { t = sctp_addr_id2transport(sk, ¶ms->spi_address, params->spi_assoc_id); if (!t) return -EINVAL; t->probe_interval = msecs_to_jiffies(probe_interval); sctp_transport_pl_reset(t); return 0; } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params->spi_assoc_id); if (!asoc && params->spi_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* If changes are for association, also apply probe_interval to * each transport. */ if (asoc) { list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { t->probe_interval = msecs_to_jiffies(probe_interval); sctp_transport_pl_reset(t); } asoc->probe_interval = msecs_to_jiffies(probe_interval); return 0; } sctp_sk(sk)->probe_interval = probe_interval; return 0; } /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve * socket options. Socket options are used to change the default * behavior of sockets calls. They are described in Section 7. * * The syntax is: * * ret = getsockopt(int sd, int level, int optname, void __user *optval, * int __user *optlen); * ret = setsockopt(int sd, int level, int optname, const void __user *optval, * int optlen); * * sd - the socket descript. * level - set to IPPROTO_SCTP for all SCTP options. * optname - the option name. * optval - the buffer to store the value of the option. * optlen - the size of the buffer. */ static int sctp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { void *kopt = NULL; int retval = 0; pr_debug("%s: sk:%p, optname:%d\n", __func__, sk, optname); /* I can hardly begin to describe how wrong this is. This is * so broken as to be worse than useless. The API draft * REALLY is NOT helpful here... I am not convinced that the * semantics of setsockopt() with a level OTHER THAN SOL_SCTP * are at all well-founded. */ if (level != SOL_SCTP) { struct sctp_af *af = sctp_sk(sk)->pf->af; return af->setsockopt(sk, level, optname, optval, optlen); } if (optlen > 0) { /* Trim it to the biggest size sctp sockopt may need if necessary */ optlen = min_t(unsigned int, optlen, PAGE_ALIGN(USHRT_MAX + sizeof(__u16) * sizeof(struct sctp_reset_streams))); kopt = memdup_sockptr(optval, optlen); if (IS_ERR(kopt)) return PTR_ERR(kopt); } lock_sock(sk); switch (optname) { case SCTP_SOCKOPT_BINDX_ADD: /* 'optlen' is the size of the addresses buffer. */ retval = sctp_setsockopt_bindx(sk, kopt, optlen, SCTP_BINDX_ADD_ADDR); break; case SCTP_SOCKOPT_BINDX_REM: /* 'optlen' is the size of the addresses buffer. */ retval = sctp_setsockopt_bindx(sk, kopt, optlen, SCTP_BINDX_REM_ADDR); break; case SCTP_SOCKOPT_CONNECTX_OLD: /* 'optlen' is the size of the addresses buffer. */ retval = sctp_setsockopt_connectx_old(sk, kopt, optlen); break; case SCTP_SOCKOPT_CONNECTX: /* 'optlen' is the size of the addresses buffer. */ retval = sctp_setsockopt_connectx(sk, kopt, optlen); break; case SCTP_DISABLE_FRAGMENTS: retval = sctp_setsockopt_disable_fragments(sk, kopt, optlen); break; case SCTP_EVENTS: retval = sctp_setsockopt_events(sk, kopt, optlen); break; case SCTP_AUTOCLOSE: retval = sctp_setsockopt_autoclose(sk, kopt, optlen); break; case SCTP_PEER_ADDR_PARAMS: retval = sctp_setsockopt_peer_addr_params(sk, kopt, optlen); break; case SCTP_DELAYED_SACK: retval = sctp_setsockopt_delayed_ack(sk, kopt, optlen); break; case SCTP_PARTIAL_DELIVERY_POINT: retval = sctp_setsockopt_partial_delivery_point(sk, kopt, optlen); break; case SCTP_INITMSG: retval = sctp_setsockopt_initmsg(sk, kopt, optlen); break; case SCTP_DEFAULT_SEND_PARAM: retval = sctp_setsockopt_default_send_param(sk, kopt, optlen); break; case SCTP_DEFAULT_SNDINFO: retval = sctp_setsockopt_default_sndinfo(sk, kopt, optlen); break; case SCTP_PRIMARY_ADDR: retval = sctp_setsockopt_primary_addr(sk, kopt, optlen); break; case SCTP_SET_PEER_PRIMARY_ADDR: retval = sctp_setsockopt_peer_primary_addr(sk, kopt, optlen); break; case SCTP_NODELAY: retval = sctp_setsockopt_nodelay(sk, kopt, optlen); break; case SCTP_RTOINFO: retval = sctp_setsockopt_rtoinfo(sk, kopt, optlen); break; case SCTP_ASSOCINFO: retval = sctp_setsockopt_associnfo(sk, kopt, optlen); break; case SCTP_I_WANT_MAPPED_V4_ADDR: retval = sctp_setsockopt_mappedv4(sk, kopt, optlen); break; case SCTP_MAXSEG: retval = sctp_setsockopt_maxseg(sk, kopt, optlen); break; case SCTP_ADAPTATION_LAYER: retval = sctp_setsockopt_adaptation_layer(sk, kopt, optlen); break; case SCTP_CONTEXT: retval = sctp_setsockopt_context(sk, kopt, optlen); break; case SCTP_FRAGMENT_INTERLEAVE: retval = sctp_setsockopt_fragment_interleave(sk, kopt, optlen); break; case SCTP_MAX_BURST: retval = sctp_setsockopt_maxburst(sk, kopt, optlen); break; case SCTP_AUTH_CHUNK: retval = sctp_setsockopt_auth_chunk(sk, kopt, optlen); break; case SCTP_HMAC_IDENT: retval = sctp_setsockopt_hmac_ident(sk, kopt, optlen); break; case SCTP_AUTH_KEY: retval = sctp_setsockopt_auth_key(sk, kopt, optlen); break; case SCTP_AUTH_ACTIVE_KEY: retval = sctp_setsockopt_active_key(sk, kopt, optlen); break; case SCTP_AUTH_DELETE_KEY: retval = sctp_setsockopt_del_key(sk, kopt, optlen); break; case SCTP_AUTH_DEACTIVATE_KEY: retval = sctp_setsockopt_deactivate_key(sk, kopt, optlen); break; case SCTP_AUTO_ASCONF: retval = sctp_setsockopt_auto_asconf(sk, kopt, optlen); break; case SCTP_PEER_ADDR_THLDS: retval = sctp_setsockopt_paddr_thresholds(sk, kopt, optlen, false); break; case SCTP_PEER_ADDR_THLDS_V2: retval = sctp_setsockopt_paddr_thresholds(sk, kopt, optlen, true); break; case SCTP_RECVRCVINFO: retval = sctp_setsockopt_recvrcvinfo(sk, kopt, optlen); break; case SCTP_RECVNXTINFO: retval = sctp_setsockopt_recvnxtinfo(sk, kopt, optlen); break; case SCTP_PR_SUPPORTED: retval = sctp_setsockopt_pr_supported(sk, kopt, optlen); break; case SCTP_DEFAULT_PRINFO: retval = sctp_setsockopt_default_prinfo(sk, kopt, optlen); break; case SCTP_RECONFIG_SUPPORTED: retval = sctp_setsockopt_reconfig_supported(sk, kopt, optlen); break; case SCTP_ENABLE_STREAM_RESET: retval = sctp_setsockopt_enable_strreset(sk, kopt, optlen); break; case SCTP_RESET_STREAMS: retval = sctp_setsockopt_reset_streams(sk, kopt, optlen); break; case SCTP_RESET_ASSOC: retval = sctp_setsockopt_reset_assoc(sk, kopt, optlen); break; case SCTP_ADD_STREAMS: retval = sctp_setsockopt_add_streams(sk, kopt, optlen); break; case SCTP_STREAM_SCHEDULER: retval = sctp_setsockopt_scheduler(sk, kopt, optlen); break; case SCTP_STREAM_SCHEDULER_VALUE: retval = sctp_setsockopt_scheduler_value(sk, kopt, optlen); break; case SCTP_INTERLEAVING_SUPPORTED: retval = sctp_setsockopt_interleaving_supported(sk, kopt, optlen); break; case SCTP_REUSE_PORT: retval = sctp_setsockopt_reuse_port(sk, kopt, optlen); break; case SCTP_EVENT: retval = sctp_setsockopt_event(sk, kopt, optlen); break; case SCTP_ASCONF_SUPPORTED: retval = sctp_setsockopt_asconf_supported(sk, kopt, optlen); break; case SCTP_AUTH_SUPPORTED: retval = sctp_setsockopt_auth_supported(sk, kopt, optlen); break; case SCTP_ECN_SUPPORTED: retval = sctp_setsockopt_ecn_supported(sk, kopt, optlen); break; case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE: retval = sctp_setsockopt_pf_expose(sk, kopt, optlen); break; case SCTP_REMOTE_UDP_ENCAPS_PORT: retval = sctp_setsockopt_encap_port(sk, kopt, optlen); break; case SCTP_PLPMTUD_PROBE_INTERVAL: retval = sctp_setsockopt_probe_interval(sk, kopt, optlen); break; default: retval = -ENOPROTOOPT; break; } release_sock(sk); kfree(kopt); return retval; } /* API 3.1.6 connect() - UDP Style Syntax * * An application may use the connect() call in the UDP model to initiate an * association without sending data. * * The syntax is: * * ret = connect(int sd, const struct sockaddr *nam, socklen_t len); * * sd: the socket descriptor to have a new association added to. * * nam: the address structure (either struct sockaddr_in or struct * sockaddr_in6 defined in RFC2553 [7]). * * len: the size of the address. */ static int sctp_connect(struct sock *sk, struct sockaddr *addr, int addr_len, int flags) { struct sctp_af *af; int err = -EINVAL; lock_sock(sk); pr_debug("%s: sk:%p, sockaddr:%p, addr_len:%d\n", __func__, sk, addr, addr_len); /* Validate addr_len before calling common connect/connectx routine. */ af = sctp_get_af_specific(addr->sa_family); if (af && addr_len >= af->sockaddr_len) err = __sctp_connect(sk, addr, af->sockaddr_len, flags, NULL); release_sock(sk); return err; } int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) return -EOPNOTSUPP; return sctp_connect(sock->sk, uaddr, addr_len, flags); } /* FIXME: Write comments. */ static int sctp_disconnect(struct sock *sk, int flags) { return -EOPNOTSUPP; /* STUB */ } /* 4.1.4 accept() - TCP Style Syntax * * Applications use accept() call to remove an established SCTP * association from the accept queue of the endpoint. A new socket * descriptor will be returned from accept() to represent the newly * formed association. */ static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) { struct sctp_sock *sp; struct sctp_endpoint *ep; struct sock *newsk = NULL; struct sctp_association *asoc; long timeo; int error = 0; lock_sock(sk); sp = sctp_sk(sk); ep = sp->ep; if (!sctp_style(sk, TCP)) { error = -EOPNOTSUPP; goto out; } if (!sctp_sstate(sk, LISTENING)) { error = -EINVAL; goto out; } timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); error = sctp_wait_for_accept(sk, timeo); if (error) goto out; /* We treat the list of associations on the endpoint as the accept * queue and pick the first association on the list. */ asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); newsk = sp->pf->create_accept_sk(sk, asoc, kern); if (!newsk) { error = -ENOMEM; goto out; } /* Populate the fields of the newsk from the oldsk and migrate the * asoc to the newsk. */ error = sctp_sock_migrate(sk, newsk, asoc, SCTP_SOCKET_TCP); if (error) { sk_common_release(newsk); newsk = NULL; } out: release_sock(sk); *err = error; return newsk; } /* The SCTP ioctl handler. */ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg) { int rc = -ENOTCONN; lock_sock(sk); /* * SEQPACKET-style sockets in LISTENING state are valid, for * SCTP, so only discard TCP-style sockets in LISTENING state. */ if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING)) goto out; switch (cmd) { case SIOCINQ: { struct sk_buff *skb; unsigned int amount = 0; skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) { /* * We will only return the amount of this packet since * that is all that will be read. */ amount = skb->len; } rc = put_user(amount, (int __user *)arg); break; } default: rc = -ENOIOCTLCMD; break; } out: release_sock(sk); return rc; } /* This is the function which gets called during socket creation to * initialized the SCTP-specific portion of the sock. * The sock structure should already be zero-filled memory. */ static int sctp_init_sock(struct sock *sk) { struct net *net = sock_net(sk); struct sctp_sock *sp; pr_debug("%s: sk:%p\n", __func__, sk); sp = sctp_sk(sk); /* Initialize the SCTP per socket area. */ switch (sk->sk_type) { case SOCK_SEQPACKET: sp->type = SCTP_SOCKET_UDP; break; case SOCK_STREAM: sp->type = SCTP_SOCKET_TCP; break; default: return -ESOCKTNOSUPPORT; } sk->sk_gso_type = SKB_GSO_SCTP; /* Initialize default send parameters. These parameters can be * modified with the SCTP_DEFAULT_SEND_PARAM socket option. */ sp->default_stream = 0; sp->default_ppid = 0; sp->default_flags = 0; sp->default_context = 0; sp->default_timetolive = 0; sp->default_rcv_context = 0; sp->max_burst = net->sctp.max_burst; sp->sctp_hmac_alg = net->sctp.sctp_hmac_alg; /* Initialize default setup parameters. These parameters * can be modified with the SCTP_INITMSG socket option or * overridden by the SCTP_INIT CMSG. */ sp->initmsg.sinit_num_ostreams = sctp_max_outstreams; sp->initmsg.sinit_max_instreams = sctp_max_instreams; sp->initmsg.sinit_max_attempts = net->sctp.max_retrans_init; sp->initmsg.sinit_max_init_timeo = net->sctp.rto_max; /* Initialize default RTO related parameters. These parameters can * be modified for with the SCTP_RTOINFO socket option. */ sp->rtoinfo.srto_initial = net->sctp.rto_initial; sp->rtoinfo.srto_max = net->sctp.rto_max; sp->rtoinfo.srto_min = net->sctp.rto_min; /* Initialize default association related parameters. These parameters * can be modified with the SCTP_ASSOCINFO socket option. */ sp->assocparams.sasoc_asocmaxrxt = net->sctp.max_retrans_association; sp->assocparams.sasoc_number_peer_destinations = 0; sp->assocparams.sasoc_peer_rwnd = 0; sp->assocparams.sasoc_local_rwnd = 0; sp->assocparams.sasoc_cookie_life = net->sctp.valid_cookie_life; /* Initialize default event subscriptions. By default, all the * options are off. */ sp->subscribe = 0; /* Default Peer Address Parameters. These defaults can * be modified via SCTP_PEER_ADDR_PARAMS */ sp->hbinterval = net->sctp.hb_interval; sp->udp_port = htons(net->sctp.udp_port); sp->encap_port = htons(net->sctp.encap_port); sp->pathmaxrxt = net->sctp.max_retrans_path; sp->pf_retrans = net->sctp.pf_retrans; sp->ps_retrans = net->sctp.ps_retrans; sp->pf_expose = net->sctp.pf_expose; sp->pathmtu = 0; /* allow default discovery */ sp->sackdelay = net->sctp.sack_timeout; sp->sackfreq = 2; sp->param_flags = SPP_HB_ENABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; sp->default_ss = SCTP_SS_DEFAULT; /* If enabled no SCTP message fragmentation will be performed. * Configure through SCTP_DISABLE_FRAGMENTS socket option. */ sp->disable_fragments = 0; /* Enable Nagle algorithm by default. */ sp->nodelay = 0; sp->recvrcvinfo = 0; sp->recvnxtinfo = 0; /* Enable by default. */ sp->v4mapped = 1; /* Auto-close idle associations after the configured * number of seconds. A value of 0 disables this * feature. Configure through the SCTP_AUTOCLOSE socket option, * for UDP-style sockets only. */ sp->autoclose = 0; /* User specified fragmentation limit. */ sp->user_frag = 0; sp->adaptation_ind = 0; sp->pf = sctp_get_pf_specific(sk->sk_family); /* Control variables for partial data delivery. */ atomic_set(&sp->pd_mode, 0); skb_queue_head_init(&sp->pd_lobby); sp->frag_interleave = 0; sp->probe_interval = net->sctp.probe_interval; /* Create a per socket endpoint structure. Even if we * change the data structure relationships, this may still * be useful for storing pre-connect address information. */ sp->ep = sctp_endpoint_new(sk, GFP_KERNEL); if (!sp->ep) return -ENOMEM; sp->hmac = NULL; sk->sk_destruct = sctp_destruct_sock; SCTP_DBG_OBJCNT_INC(sock); sk_sockets_allocated_inc(sk); sock_prot_inuse_add(net, sk->sk_prot, 1); return 0; } /* Cleanup any SCTP per socket resources. Must be called with * sock_net(sk)->sctp.addr_wq_lock held if sp->do_auto_asconf is true */ static void sctp_destroy_sock(struct sock *sk) { struct sctp_sock *sp; pr_debug("%s: sk:%p\n", __func__, sk); /* Release our hold on the endpoint. */ sp = sctp_sk(sk); /* This could happen during socket init, thus we bail out * early, since the rest of the below is not setup either. */ if (sp->ep == NULL) return; if (sp->do_auto_asconf) { sp->do_auto_asconf = 0; list_del(&sp->auto_asconf_list); } sctp_endpoint_free(sp->ep); sk_sockets_allocated_dec(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); } /* Triggered when there are no references on the socket anymore */ static void sctp_destruct_common(struct sock *sk) { struct sctp_sock *sp = sctp_sk(sk); /* Free up the HMAC transform. */ crypto_free_shash(sp->hmac); } static void sctp_destruct_sock(struct sock *sk) { sctp_destruct_common(sk); inet_sock_destruct(sk); } /* API 4.1.7 shutdown() - TCP Style Syntax * int shutdown(int socket, int how); * * sd - the socket descriptor of the association to be closed. * how - Specifies the type of shutdown. The values are * as follows: * SHUT_RD * Disables further receive operations. No SCTP * protocol action is taken. * SHUT_WR * Disables further send operations, and initiates * the SCTP shutdown sequence. * SHUT_RDWR * Disables further send and receive operations * and initiates the SCTP shutdown sequence. */ static void sctp_shutdown(struct sock *sk, int how) { struct net *net = sock_net(sk); struct sctp_endpoint *ep; if (!sctp_style(sk, TCP)) return; ep = sctp_sk(sk)->ep; if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) { struct sctp_association *asoc; inet_sk_set_state(sk, SCTP_SS_CLOSING); asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); sctp_primitive_SHUTDOWN(net, asoc, NULL); } } int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, struct sctp_info *info) { struct sctp_transport *prim; struct list_head *pos; int mask; memset(info, 0, sizeof(*info)); if (!asoc) { struct sctp_sock *sp = sctp_sk(sk); info->sctpi_s_autoclose = sp->autoclose; info->sctpi_s_adaptation_ind = sp->adaptation_ind; info->sctpi_s_pd_point = sp->pd_point; info->sctpi_s_nodelay = sp->nodelay; info->sctpi_s_disable_fragments = sp->disable_fragments; info->sctpi_s_v4mapped = sp->v4mapped; info->sctpi_s_frag_interleave = sp->frag_interleave; info->sctpi_s_type = sp->type; return 0; } info->sctpi_tag = asoc->c.my_vtag; info->sctpi_state = asoc->state; info->sctpi_rwnd = asoc->a_rwnd; info->sctpi_unackdata = asoc->unack_data; info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); info->sctpi_instrms = asoc->stream.incnt; info->sctpi_outstrms = asoc->stream.outcnt; list_for_each(pos, &asoc->base.inqueue.in_chunk_list) info->sctpi_inqueue++; list_for_each(pos, &asoc->outqueue.out_chunk_list) info->sctpi_outqueue++; info->sctpi_overall_error = asoc->overall_error_count; info->sctpi_max_burst = asoc->max_burst; info->sctpi_maxseg = asoc->frag_point; info->sctpi_peer_rwnd = asoc->peer.rwnd; info->sctpi_peer_tag = asoc->c.peer_vtag; mask = asoc->peer.ecn_capable << 1; mask = (mask | asoc->peer.ipv4_address) << 1; mask = (mask | asoc->peer.ipv6_address) << 1; mask = (mask | asoc->peer.hostname_address) << 1; mask = (mask | asoc->peer.asconf_capable) << 1; mask = (mask | asoc->peer.prsctp_capable) << 1; mask = (mask | asoc->peer.auth_capable); info->sctpi_peer_capable = mask; mask = asoc->peer.sack_needed << 1; mask = (mask | asoc->peer.sack_generation) << 1; mask = (mask | asoc->peer.zero_window_announced); info->sctpi_peer_sack = mask; info->sctpi_isacks = asoc->stats.isacks; info->sctpi_osacks = asoc->stats.osacks; info->sctpi_opackets = asoc->stats.opackets; info->sctpi_ipackets = asoc->stats.ipackets; info->sctpi_rtxchunks = asoc->stats.rtxchunks; info->sctpi_outofseqtsns = asoc->stats.outofseqtsns; info->sctpi_idupchunks = asoc->stats.idupchunks; info->sctpi_gapcnt = asoc->stats.gapcnt; info->sctpi_ouodchunks = asoc->stats.ouodchunks; info->sctpi_iuodchunks = asoc->stats.iuodchunks; info->sctpi_oodchunks = asoc->stats.oodchunks; info->sctpi_iodchunks = asoc->stats.iodchunks; info->sctpi_octrlchunks = asoc->stats.octrlchunks; info->sctpi_ictrlchunks = asoc->stats.ictrlchunks; prim = asoc->peer.primary_path; memcpy(&info->sctpi_p_address, &prim->ipaddr, sizeof(prim->ipaddr)); info->sctpi_p_state = prim->state; info->sctpi_p_cwnd = prim->cwnd; info->sctpi_p_srtt = prim->srtt; info->sctpi_p_rto = jiffies_to_msecs(prim->rto); info->sctpi_p_hbinterval = prim->hbinterval; info->sctpi_p_pathmaxrxt = prim->pathmaxrxt; info->sctpi_p_sackdelay = jiffies_to_msecs(prim->sackdelay); info->sctpi_p_ssthresh = prim->ssthresh; info->sctpi_p_partial_bytes_acked = prim->partial_bytes_acked; info->sctpi_p_flight_size = prim->flight_size; info->sctpi_p_error = prim->error_count; return 0; } EXPORT_SYMBOL_GPL(sctp_get_sctp_info); /* use callback to avoid exporting the core structure */ void sctp_transport_walk_start(struct rhashtable_iter *iter) __acquires(RCU) { rhltable_walk_enter(&sctp_transport_hashtable, iter); rhashtable_walk_start(iter); } void sctp_transport_walk_stop(struct rhashtable_iter *iter) __releases(RCU) { rhashtable_walk_stop(iter); rhashtable_walk_exit(iter); } struct sctp_transport *sctp_transport_get_next(struct net *net, struct rhashtable_iter *iter) { struct sctp_transport *t; t = rhashtable_walk_next(iter); for (; t; t = rhashtable_walk_next(iter)) { if (IS_ERR(t)) { if (PTR_ERR(t) == -EAGAIN) continue; break; } if (!sctp_transport_hold(t)) continue; if (net_eq(t->asoc->base.net, net) && t->asoc->peer.primary_path == t) break; sctp_transport_put(t); } return t; } struct sctp_transport *sctp_transport_get_idx(struct net *net, struct rhashtable_iter *iter, int pos) { struct sctp_transport *t; if (!pos) return SEQ_START_TOKEN; while ((t = sctp_transport_get_next(net, iter)) && !IS_ERR(t)) { if (!--pos) break; sctp_transport_put(t); } return t; } int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p) { int err = 0; int hash = 0; struct sctp_endpoint *ep; struct sctp_hashbucket *head; for (head = sctp_ep_hashtable; hash < sctp_ep_hashsize; hash++, head++) { read_lock_bh(&head->lock); sctp_for_each_hentry(ep, &head->chain) { err = cb(ep, p); if (err) break; } read_unlock_bh(&head->lock); } return err; } EXPORT_SYMBOL_GPL(sctp_for_each_endpoint); int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, void *p) { struct sctp_transport *transport; struct sctp_endpoint *ep; int err = -ENOENT; rcu_read_lock(); transport = sctp_addrs_lookup_transport(net, laddr, paddr); if (!transport) { rcu_read_unlock(); return err; } ep = transport->asoc->ep; if (!sctp_endpoint_hold(ep)) { /* asoc can be peeled off */ sctp_transport_put(transport); rcu_read_unlock(); return err; } rcu_read_unlock(); err = cb(ep, transport, p); sctp_endpoint_put(ep); sctp_transport_put(transport); return err; } EXPORT_SYMBOL_GPL(sctp_transport_lookup_process); int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done, struct net *net, int *pos, void *p) { struct rhashtable_iter hti; struct sctp_transport *tsp; struct sctp_endpoint *ep; int ret; again: ret = 0; sctp_transport_walk_start(&hti); tsp = sctp_transport_get_idx(net, &hti, *pos + 1); for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) { ep = tsp->asoc->ep; if (sctp_endpoint_hold(ep)) { /* asoc can be peeled off */ ret = cb(ep, tsp, p); if (ret) break; sctp_endpoint_put(ep); } (*pos)++; sctp_transport_put(tsp); } sctp_transport_walk_stop(&hti); if (ret) { if (cb_done && !cb_done(ep, tsp, p)) { (*pos)++; sctp_endpoint_put(ep); sctp_transport_put(tsp); goto again; } sctp_endpoint_put(ep); sctp_transport_put(tsp); } return ret; } EXPORT_SYMBOL_GPL(sctp_transport_traverse_process); /* 7.2.1 Association Status (SCTP_STATUS) * Applications can retrieve current status information about an * association, including association state, peer receiver window size, * number of unacked data chunks, and number of data chunks pending * receipt. This information is read-only. */ static int sctp_getsockopt_sctp_status(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_status status; struct sctp_association *asoc = NULL; struct sctp_transport *transport; sctp_assoc_t associd; int retval = 0; if (len < sizeof(status)) { retval = -EINVAL; goto out; } len = sizeof(status); if (copy_from_user(&status, optval, len)) { retval = -EFAULT; goto out; } associd = status.sstat_assoc_id; asoc = sctp_id2assoc(sk, associd); if (!asoc) { retval = -EINVAL; goto out; } transport = asoc->peer.primary_path; status.sstat_assoc_id = sctp_assoc2id(asoc); status.sstat_state = sctp_assoc_to_state(asoc); status.sstat_rwnd = asoc->peer.rwnd; status.sstat_unackdata = asoc->unack_data; status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); status.sstat_instrms = asoc->stream.incnt; status.sstat_outstrms = asoc->stream.outcnt; status.sstat_fragmentation_point = asoc->frag_point; status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc); memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr, transport->af_specific->sockaddr_len); /* Map ipv4 address into v4-mapped-on-v6 address. */ sctp_get_pf_specific(sk->sk_family)->addr_to_user(sctp_sk(sk), (union sctp_addr *)&status.sstat_primary.spinfo_address); status.sstat_primary.spinfo_state = transport->state; status.sstat_primary.spinfo_cwnd = transport->cwnd; status.sstat_primary.spinfo_srtt = transport->srtt; status.sstat_primary.spinfo_rto = jiffies_to_msecs(transport->rto); status.sstat_primary.spinfo_mtu = transport->pathmtu; if (status.sstat_primary.spinfo_state == SCTP_UNKNOWN) status.sstat_primary.spinfo_state = SCTP_ACTIVE; if (put_user(len, optlen)) { retval = -EFAULT; goto out; } pr_debug("%s: len:%d, state:%d, rwnd:%d, assoc_id:%d\n", __func__, len, status.sstat_state, status.sstat_rwnd, status.sstat_assoc_id); if (copy_to_user(optval, &status, len)) { retval = -EFAULT; goto out; } out: return retval; } /* 7.2.2 Peer Address Information (SCTP_GET_PEER_ADDR_INFO) * * Applications can retrieve information about a specific peer address * of an association, including its reachability state, congestion * window, and retransmission timer values. This information is * read-only. */ static int sctp_getsockopt_peer_addr_info(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_paddrinfo pinfo; struct sctp_transport *transport; int retval = 0; if (len < sizeof(pinfo)) { retval = -EINVAL; goto out; } len = sizeof(pinfo); if (copy_from_user(&pinfo, optval, len)) { retval = -EFAULT; goto out; } transport = sctp_addr_id2transport(sk, &pinfo.spinfo_address, pinfo.spinfo_assoc_id); if (!transport) { retval = -EINVAL; goto out; } if (transport->state == SCTP_PF && transport->asoc->pf_expose == SCTP_PF_EXPOSE_DISABLE) { retval = -EACCES; goto out; } pinfo.spinfo_assoc_id = sctp_assoc2id(transport->asoc); pinfo.spinfo_state = transport->state; pinfo.spinfo_cwnd = transport->cwnd; pinfo.spinfo_srtt = transport->srtt; pinfo.spinfo_rto = jiffies_to_msecs(transport->rto); pinfo.spinfo_mtu = transport->pathmtu; if (pinfo.spinfo_state == SCTP_UNKNOWN) pinfo.spinfo_state = SCTP_ACTIVE; if (put_user(len, optlen)) { retval = -EFAULT; goto out; } if (copy_to_user(optval, &pinfo, len)) { retval = -EFAULT; goto out; } out: return retval; } /* 7.1.12 Enable/Disable message fragmentation (SCTP_DISABLE_FRAGMENTS) * * This option is a on/off flag. If enabled no SCTP message * fragmentation will be performed. Instead if a message being sent * exceeds the current PMTU size, the message will NOT be sent and * instead a error will be indicated to the user. */ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = (sctp_sk(sk)->disable_fragments == 1); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* 7.1.15 Set notification and ancillary events (SCTP_EVENTS) * * This socket option is used to specify various notifications and * ancillary data the user wishes to receive. */ static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_event_subscribe subscribe; __u8 *sn_type = (__u8 *)&subscribe; int i; if (len == 0) return -EINVAL; if (len > sizeof(struct sctp_event_subscribe)) len = sizeof(struct sctp_event_subscribe); if (put_user(len, optlen)) return -EFAULT; for (i = 0; i < len; i++) sn_type[i] = sctp_ulpevent_type_enabled(sctp_sk(sk)->subscribe, SCTP_SN_TYPE_BASE + i); if (copy_to_user(optval, &subscribe, len)) return -EFAULT; return 0; } /* 7.1.8 Automatic Close of associations (SCTP_AUTOCLOSE) * * This socket option is applicable to the UDP-style socket only. When * set it will cause associations that are idle for more than the * specified number of seconds to automatically close. An association * being idle is defined an association that has NOT sent or received * user data. The special value of '0' indicates that no automatic * close of any associations should be performed. The option expects an * integer defining the number of seconds of idle time before an * association is closed. */ static int sctp_getsockopt_autoclose(struct sock *sk, int len, char __user *optval, int __user *optlen) { /* Applicable to UDP-style socket only */ if (sctp_style(sk, TCP)) return -EOPNOTSUPP; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); if (put_user(len, optlen)) return -EFAULT; if (put_user(sctp_sk(sk)->autoclose, (int __user *)optval)) return -EFAULT; return 0; } /* Helper routine to branch off an association to a new socket. */ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) { struct sctp_association *asoc = sctp_id2assoc(sk, id); struct sctp_sock *sp = sctp_sk(sk); struct socket *sock; int err = 0; /* Do not peel off from one netns to another one. */ if (!net_eq(current->nsproxy->net_ns, sock_net(sk))) return -EINVAL; if (!asoc) return -EINVAL; /* An association cannot be branched off from an already peeled-off * socket, nor is this supported for tcp style sockets. */ if (!sctp_style(sk, UDP)) return -EINVAL; /* Create a new socket. */ err = sock_create(sk->sk_family, SOCK_SEQPACKET, IPPROTO_SCTP, &sock); if (err < 0) return err; sctp_copy_sock(sock->sk, sk, asoc); /* Make peeled-off sockets more like 1-1 accepted sockets. * Set the daddr and initialize id to something more random and also * copy over any ip options. */ sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sock->sk); sp->pf->copy_ip_options(sk, sock->sk); /* Populate the fields of the newsk from the oldsk and migrate the * asoc to the newsk. */ err = sctp_sock_migrate(sk, sock->sk, asoc, SCTP_SOCKET_UDP_HIGH_BANDWIDTH); if (err) { sock_release(sock); sock = NULL; } *sockp = sock; return err; } EXPORT_SYMBOL(sctp_do_peeloff); static int sctp_getsockopt_peeloff_common(struct sock *sk, sctp_peeloff_arg_t *peeloff, struct file **newfile, unsigned flags) { struct socket *newsock; int retval; retval = sctp_do_peeloff(sk, peeloff->associd, &newsock); if (retval < 0) goto out; /* Map the socket to an unused fd that can be returned to the user. */ retval = get_unused_fd_flags(flags & SOCK_CLOEXEC); if (retval < 0) { sock_release(newsock); goto out; } *newfile = sock_alloc_file(newsock, 0, NULL); if (IS_ERR(*newfile)) { put_unused_fd(retval); retval = PTR_ERR(*newfile); *newfile = NULL; return retval; } pr_debug("%s: sk:%p, newsk:%p, sd:%d\n", __func__, sk, newsock->sk, retval); peeloff->sd = retval; if (flags & SOCK_NONBLOCK) (*newfile)->f_flags |= O_NONBLOCK; out: return retval; } static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval, int __user *optlen) { sctp_peeloff_arg_t peeloff; struct file *newfile = NULL; int retval = 0; if (len < sizeof(sctp_peeloff_arg_t)) return -EINVAL; len = sizeof(sctp_peeloff_arg_t); if (copy_from_user(&peeloff, optval, len)) return -EFAULT; retval = sctp_getsockopt_peeloff_common(sk, &peeloff, &newfile, 0); if (retval < 0) goto out; /* Return the fd mapped to the new socket. */ if (put_user(len, optlen)) { fput(newfile); put_unused_fd(retval); return -EFAULT; } if (copy_to_user(optval, &peeloff, len)) { fput(newfile); put_unused_fd(retval); return -EFAULT; } fd_install(retval, newfile); out: return retval; } static int sctp_getsockopt_peeloff_flags(struct sock *sk, int len, char __user *optval, int __user *optlen) { sctp_peeloff_flags_arg_t peeloff; struct file *newfile = NULL; int retval = 0; if (len < sizeof(sctp_peeloff_flags_arg_t)) return -EINVAL; len = sizeof(sctp_peeloff_flags_arg_t); if (copy_from_user(&peeloff, optval, len)) return -EFAULT; retval = sctp_getsockopt_peeloff_common(sk, &peeloff.p_arg, &newfile, peeloff.flags); if (retval < 0) goto out; /* Return the fd mapped to the new socket. */ if (put_user(len, optlen)) { fput(newfile); put_unused_fd(retval); return -EFAULT; } if (copy_to_user(optval, &peeloff, len)) { fput(newfile); put_unused_fd(retval); return -EFAULT; } fd_install(retval, newfile); out: return retval; } /* 7.1.13 Peer Address Parameters (SCTP_PEER_ADDR_PARAMS) * * Applications can enable or disable heartbeats for any peer address of * an association, modify an address's heartbeat interval, force a * heartbeat to be sent immediately, and adjust the address's maximum * number of retransmissions sent before an address is considered * unreachable. The following structure is used to access and modify an * address's parameters: * * struct sctp_paddrparams { * sctp_assoc_t spp_assoc_id; * struct sockaddr_storage spp_address; * uint32_t spp_hbinterval; * uint16_t spp_pathmaxrxt; * uint32_t spp_pathmtu; * uint32_t spp_sackdelay; * uint32_t spp_flags; * }; * * spp_assoc_id - (one-to-many style socket) This is filled in the * application, and identifies the association for * this query. * spp_address - This specifies which address is of interest. * spp_hbinterval - This contains the value of the heartbeat interval, * in milliseconds. If a value of zero * is present in this field then no changes are to * be made to this parameter. * spp_pathmaxrxt - This contains the maximum number of * retransmissions before this address shall be * considered unreachable. If a value of zero * is present in this field then no changes are to * be made to this parameter. * spp_pathmtu - When Path MTU discovery is disabled the value * specified here will be the "fixed" path mtu. * Note that if the spp_address field is empty * then all associations on this address will * have this fixed path mtu set upon them. * * spp_sackdelay - When delayed sack is enabled, this value specifies * the number of milliseconds that sacks will be delayed * for. This value will apply to all addresses of an * association if the spp_address field is empty. Note * also, that if delayed sack is enabled and this * value is set to 0, no change is made to the last * recorded delayed sack timer value. * * spp_flags - These flags are used to control various features * on an association. The flag field may contain * zero or more of the following options. * * SPP_HB_ENABLE - Enable heartbeats on the * specified address. Note that if the address * field is empty all addresses for the association * have heartbeats enabled upon them. * * SPP_HB_DISABLE - Disable heartbeats on the * speicifed address. Note that if the address * field is empty all addresses for the association * will have their heartbeats disabled. Note also * that SPP_HB_ENABLE and SPP_HB_DISABLE are * mutually exclusive, only one of these two should * be specified. Enabling both fields will have * undetermined results. * * SPP_HB_DEMAND - Request a user initiated heartbeat * to be made immediately. * * SPP_PMTUD_ENABLE - This field will enable PMTU * discovery upon the specified address. Note that * if the address feild is empty then all addresses * on the association are effected. * * SPP_PMTUD_DISABLE - This field will disable PMTU * discovery upon the specified address. Note that * if the address feild is empty then all addresses * on the association are effected. Not also that * SPP_PMTUD_ENABLE and SPP_PMTUD_DISABLE are mutually * exclusive. Enabling both will have undetermined * results. * * SPP_SACKDELAY_ENABLE - Setting this flag turns * on delayed sack. The time specified in spp_sackdelay * is used to specify the sack delay for this address. Note * that if spp_address is empty then all addresses will * enable delayed sack and take on the sack delay * value specified in spp_sackdelay. * SPP_SACKDELAY_DISABLE - Setting this flag turns * off delayed sack. If the spp_address field is blank then * delayed sack is disabled for the entire association. Note * also that this field is mutually exclusive to * SPP_SACKDELAY_ENABLE, setting both will have undefined * results. * * SPP_IPV6_FLOWLABEL: Setting this flag enables the * setting of the IPV6 flow label value. The value is * contained in the spp_ipv6_flowlabel field. * Upon retrieval, this flag will be set to indicate that * the spp_ipv6_flowlabel field has a valid value returned. * If a specific destination address is set (in the * spp_address field), then the value returned is that of * the address. If just an association is specified (and * no address), then the association's default flow label * is returned. If neither an association nor a destination * is specified, then the socket's default flow label is * returned. For non-IPv6 sockets, this flag will be left * cleared. * * SPP_DSCP: Setting this flag enables the setting of the * Differentiated Services Code Point (DSCP) value * associated with either the association or a specific * address. The value is obtained in the spp_dscp field. * Upon retrieval, this flag will be set to indicate that * the spp_dscp field has a valid value returned. If a * specific destination address is set when called (in the * spp_address field), then that specific destination * address's DSCP value is returned. If just an association * is specified, then the association's default DSCP is * returned. If neither an association nor a destination is * specified, then the socket's default DSCP is returned. * * spp_ipv6_flowlabel * - This field is used in conjunction with the * SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label. * The 20 least significant bits are used for the flow * label. This setting has precedence over any IPv6-layer * setting. * * spp_dscp - This field is used in conjunction with the SPP_DSCP flag * and contains the DSCP. The 6 most significant bits are * used for the DSCP. This setting has precedence over any * IPv4- or IPv6- layer setting. */ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_paddrparams params; struct sctp_transport *trans = NULL; struct sctp_association *asoc = NULL; struct sctp_sock *sp = sctp_sk(sk); if (len >= sizeof(params)) len = sizeof(params); else if (len >= ALIGN(offsetof(struct sctp_paddrparams, spp_ipv6_flowlabel), 4)) len = ALIGN(offsetof(struct sctp_paddrparams, spp_ipv6_flowlabel), 4); else return -EINVAL; if (copy_from_user(¶ms, optval, len)) return -EFAULT; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ if (!sctp_is_any(sk, (union sctp_addr *)¶ms.spp_address)) { trans = sctp_addr_id2transport(sk, ¶ms.spp_address, params.spp_assoc_id); if (!trans) { pr_debug("%s: failed no transport\n", __func__); return -EINVAL; } } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.spp_assoc_id); if (!asoc && params.spp_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { pr_debug("%s: failed no association\n", __func__); return -EINVAL; } if (trans) { /* Fetch transport values. */ params.spp_hbinterval = jiffies_to_msecs(trans->hbinterval); params.spp_pathmtu = trans->pathmtu; params.spp_pathmaxrxt = trans->pathmaxrxt; params.spp_sackdelay = jiffies_to_msecs(trans->sackdelay); /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = trans->param_flags; if (trans->flowlabel & SCTP_FLOWLABEL_SET_MASK) { params.spp_ipv6_flowlabel = trans->flowlabel & SCTP_FLOWLABEL_VAL_MASK; params.spp_flags |= SPP_IPV6_FLOWLABEL; } if (trans->dscp & SCTP_DSCP_SET_MASK) { params.spp_dscp = trans->dscp & SCTP_DSCP_VAL_MASK; params.spp_flags |= SPP_DSCP; } } else if (asoc) { /* Fetch association values. */ params.spp_hbinterval = jiffies_to_msecs(asoc->hbinterval); params.spp_pathmtu = asoc->pathmtu; params.spp_pathmaxrxt = asoc->pathmaxrxt; params.spp_sackdelay = jiffies_to_msecs(asoc->sackdelay); /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = asoc->param_flags; if (asoc->flowlabel & SCTP_FLOWLABEL_SET_MASK) { params.spp_ipv6_flowlabel = asoc->flowlabel & SCTP_FLOWLABEL_VAL_MASK; params.spp_flags |= SPP_IPV6_FLOWLABEL; } if (asoc->dscp & SCTP_DSCP_SET_MASK) { params.spp_dscp = asoc->dscp & SCTP_DSCP_VAL_MASK; params.spp_flags |= SPP_DSCP; } } else { /* Fetch socket values. */ params.spp_hbinterval = sp->hbinterval; params.spp_pathmtu = sp->pathmtu; params.spp_sackdelay = sp->sackdelay; params.spp_pathmaxrxt = sp->pathmaxrxt; /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = sp->param_flags; if (sp->flowlabel & SCTP_FLOWLABEL_SET_MASK) { params.spp_ipv6_flowlabel = sp->flowlabel & SCTP_FLOWLABEL_VAL_MASK; params.spp_flags |= SPP_IPV6_FLOWLABEL; } if (sp->dscp & SCTP_DSCP_SET_MASK) { params.spp_dscp = sp->dscp & SCTP_DSCP_VAL_MASK; params.spp_flags |= SPP_DSCP; } } if (copy_to_user(optval, ¶ms, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } /* * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) * * This option will effect the way delayed acks are performed. This * option allows you to get or set the delayed ack time, in * milliseconds. It also allows changing the delayed ack frequency. * Changing the frequency to 1 disables the delayed sack algorithm. If * the assoc_id is 0, then this sets or gets the endpoints default * values. If the assoc_id field is non-zero, then the set or get * effects the specified association for the one to many model (the * assoc_id field is ignored by the one to one model). Note that if * sack_delay or sack_freq are 0 when setting this option, then the * current values will remain unchanged. * * struct sctp_sack_info { * sctp_assoc_t sack_assoc_id; * uint32_t sack_delay; * uint32_t sack_freq; * }; * * sack_assoc_id - This parameter, indicates which association the user * is performing an action upon. Note that if this field's value is * zero then the endpoints default value is changed (effecting future * associations only). * * sack_delay - This parameter contains the number of milliseconds that * the user is requesting the delayed ACK timer be set to. Note that * this value is defined in the standard to be between 200 and 500 * milliseconds. * * sack_freq - This parameter contains the number of packets that must * be received before a sack is sent without waiting for the delay * timer to expire. The default value for this is 2, setting this * value to 1 will disable the delayed sack algorithm. */ static int sctp_getsockopt_delayed_ack(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_sack_info params; struct sctp_association *asoc = NULL; struct sctp_sock *sp = sctp_sk(sk); if (len >= sizeof(struct sctp_sack_info)) { len = sizeof(struct sctp_sack_info); if (copy_from_user(¶ms, optval, len)) return -EFAULT; } else if (len == sizeof(struct sctp_assoc_value)) { pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of struct sctp_assoc_value in delayed_ack socket option.\n" "Use struct sctp_sack_info instead\n", current->comm, task_pid_nr(current)); if (copy_from_user(¶ms, optval, len)) return -EFAULT; } else return -EINVAL; /* Get association, if sack_assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.sack_assoc_id); if (!asoc && params.sack_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { /* Fetch association values. */ if (asoc->param_flags & SPP_SACKDELAY_ENABLE) { params.sack_delay = jiffies_to_msecs(asoc->sackdelay); params.sack_freq = asoc->sackfreq; } else { params.sack_delay = 0; params.sack_freq = 1; } } else { /* Fetch socket values. */ if (sp->param_flags & SPP_SACKDELAY_ENABLE) { params.sack_delay = sp->sackdelay; params.sack_freq = sp->sackfreq; } else { params.sack_delay = 0; params.sack_freq = 1; } } if (copy_to_user(optval, ¶ms, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } /* 7.1.3 Initialization Parameters (SCTP_INITMSG) * * Applications can specify protocol parameters for the default association * initialization. The option name argument to setsockopt() and getsockopt() * is SCTP_INITMSG. * * Setting initialization parameters is effective only on an unconnected * socket (for UDP-style sockets only future associations are effected * by the change). With TCP-style sockets, this option is inherited by * sockets derived from a listener socket. */ static int sctp_getsockopt_initmsg(struct sock *sk, int len, char __user *optval, int __user *optlen) { if (len < sizeof(struct sctp_initmsg)) return -EINVAL; len = sizeof(struct sctp_initmsg); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &sctp_sk(sk)->initmsg, len)) return -EFAULT; return 0; } static int sctp_getsockopt_peer_addrs(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_association *asoc; int cnt = 0; struct sctp_getaddrs getaddrs; struct sctp_transport *from; void __user *to; union sctp_addr temp; struct sctp_sock *sp = sctp_sk(sk); int addrlen; size_t space_left; int bytes_copied; if (len < sizeof(struct sctp_getaddrs)) return -EINVAL; if (copy_from_user(&getaddrs, optval, sizeof(struct sctp_getaddrs))) return -EFAULT; /* For UDP-style sockets, id specifies the association to query. */ asoc = sctp_id2assoc(sk, getaddrs.assoc_id); if (!asoc) return -EINVAL; to = optval + offsetof(struct sctp_getaddrs, addrs); space_left = len - offsetof(struct sctp_getaddrs, addrs); list_for_each_entry(from, &asoc->peer.transport_addr_list, transports) { memcpy(&temp, &from->ipaddr, sizeof(temp)); addrlen = sctp_get_pf_specific(sk->sk_family) ->addr_to_user(sp, &temp); if (space_left < addrlen) return -ENOMEM; if (copy_to_user(to, &temp, addrlen)) return -EFAULT; to += addrlen; cnt++; space_left -= addrlen; } if (put_user(cnt, &((struct sctp_getaddrs __user *)optval)->addr_num)) return -EFAULT; bytes_copied = ((char __user *)to) - optval; if (put_user(bytes_copied, optlen)) return -EFAULT; return 0; } static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, size_t space_left, int *bytes_copied) { struct sctp_sockaddr_entry *addr; union sctp_addr temp; int cnt = 0; int addrlen; struct net *net = sock_net(sk); rcu_read_lock(); list_for_each_entry_rcu(addr, &net->sctp.local_addr_list, list) { if (!addr->valid) continue; if ((PF_INET == sk->sk_family) && (AF_INET6 == addr->a.sa.sa_family)) continue; if ((PF_INET6 == sk->sk_family) && inet_v6_ipv6only(sk) && (AF_INET == addr->a.sa.sa_family)) continue; memcpy(&temp, &addr->a, sizeof(temp)); if (!temp.v4.sin_port) temp.v4.sin_port = htons(port); addrlen = sctp_get_pf_specific(sk->sk_family) ->addr_to_user(sctp_sk(sk), &temp); if (space_left < addrlen) { cnt = -ENOMEM; break; } memcpy(to, &temp, addrlen); to += addrlen; cnt++; space_left -= addrlen; *bytes_copied += addrlen; } rcu_read_unlock(); return cnt; } static int sctp_getsockopt_local_addrs(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_bind_addr *bp; struct sctp_association *asoc; int cnt = 0; struct sctp_getaddrs getaddrs; struct sctp_sockaddr_entry *addr; void __user *to; union sctp_addr temp; struct sctp_sock *sp = sctp_sk(sk); int addrlen; int err = 0; size_t space_left; int bytes_copied = 0; void *addrs; void *buf; if (len < sizeof(struct sctp_getaddrs)) return -EINVAL; if (copy_from_user(&getaddrs, optval, sizeof(struct sctp_getaddrs))) return -EFAULT; /* * For UDP-style sockets, id specifies the association to query. * If the id field is set to the value '0' then the locally bound * addresses are returned without regard to any particular * association. */ if (0 == getaddrs.assoc_id) { bp = &sctp_sk(sk)->ep->base.bind_addr; } else { asoc = sctp_id2assoc(sk, getaddrs.assoc_id); if (!asoc) return -EINVAL; bp = &asoc->base.bind_addr; } to = optval + offsetof(struct sctp_getaddrs, addrs); space_left = len - offsetof(struct sctp_getaddrs, addrs); addrs = kmalloc(space_left, GFP_USER | __GFP_NOWARN); if (!addrs) return -ENOMEM; /* If the endpoint is bound to 0.0.0.0 or ::0, get the valid * addresses from the global local address list. */ if (sctp_list_single_entry(&bp->address_list)) { addr = list_entry(bp->address_list.next, struct sctp_sockaddr_entry, list); if (sctp_is_any(sk, &addr->a)) { cnt = sctp_copy_laddrs(sk, bp->port, addrs, space_left, &bytes_copied); if (cnt < 0) { err = cnt; goto out; } goto copy_getaddrs; } } buf = addrs; /* Protection on the bound address list is not needed since * in the socket option context we hold a socket lock and * thus the bound address list can't change. */ list_for_each_entry(addr, &bp->address_list, list) { memcpy(&temp, &addr->a, sizeof(temp)); addrlen = sctp_get_pf_specific(sk->sk_family) ->addr_to_user(sp, &temp); if (space_left < addrlen) { err = -ENOMEM; /*fixme: right error?*/ goto out; } memcpy(buf, &temp, addrlen); buf += addrlen; bytes_copied += addrlen; cnt++; space_left -= addrlen; } copy_getaddrs: if (copy_to_user(to, addrs, bytes_copied)) { err = -EFAULT; goto out; } if (put_user(cnt, &((struct sctp_getaddrs __user *)optval)->addr_num)) { err = -EFAULT; goto out; } /* XXX: We should have accounted for sizeof(struct sctp_getaddrs) too, * but we can't change it anymore. */ if (put_user(bytes_copied, optlen)) err = -EFAULT; out: kfree(addrs); return err; } /* 7.1.10 Set Primary Address (SCTP_PRIMARY_ADDR) * * Requests that the local SCTP stack use the enclosed peer address as * the association primary. The enclosed address must be one of the * association peer's addresses. */ static int sctp_getsockopt_primary_addr(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_prim prim; struct sctp_association *asoc; struct sctp_sock *sp = sctp_sk(sk); if (len < sizeof(struct sctp_prim)) return -EINVAL; len = sizeof(struct sctp_prim); if (copy_from_user(&prim, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, prim.ssp_assoc_id); if (!asoc) return -EINVAL; if (!asoc->peer.primary_path) return -ENOTCONN; memcpy(&prim.ssp_addr, &asoc->peer.primary_path->ipaddr, asoc->peer.primary_path->af_specific->sockaddr_len); sctp_get_pf_specific(sk->sk_family)->addr_to_user(sp, (union sctp_addr *)&prim.ssp_addr); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &prim, len)) return -EFAULT; return 0; } /* * 7.1.11 Set Adaptation Layer Indicator (SCTP_ADAPTATION_LAYER) * * Requests that the local endpoint set the specified Adaptation Layer * Indication parameter for all future INIT and INIT-ACK exchanges. */ static int sctp_getsockopt_adaptation_layer(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_setadaptation adaptation; if (len < sizeof(struct sctp_setadaptation)) return -EINVAL; len = sizeof(struct sctp_setadaptation); adaptation.ssb_adaptation_ind = sctp_sk(sk)->adaptation_ind; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &adaptation, len)) return -EFAULT; return 0; } /* * * 7.1.14 Set default send parameters (SCTP_DEFAULT_SEND_PARAM) * * Applications that wish to use the sendto() system call may wish to * specify a default set of parameters that would normally be supplied * through the inclusion of ancillary data. This socket option allows * such an application to set the default sctp_sndrcvinfo structure. * The application that wishes to use this socket option simply passes * in to this call the sctp_sndrcvinfo structure defined in Section * 5.2.2) The input parameters accepted by this call include * sinfo_stream, sinfo_flags, sinfo_ppid, sinfo_context, * sinfo_timetolive. The user must provide the sinfo_assoc_id field in * to this call if the caller is using the UDP model. * * For getsockopt, it get the default sctp_sndrcvinfo structure. */ static int sctp_getsockopt_default_send_param(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_sndrcvinfo info; if (len < sizeof(info)) return -EINVAL; len = sizeof(info); if (copy_from_user(&info, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, info.sinfo_assoc_id); if (!asoc && info.sinfo_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { info.sinfo_stream = asoc->default_stream; info.sinfo_flags = asoc->default_flags; info.sinfo_ppid = asoc->default_ppid; info.sinfo_context = asoc->default_context; info.sinfo_timetolive = asoc->default_timetolive; } else { info.sinfo_stream = sp->default_stream; info.sinfo_flags = sp->default_flags; info.sinfo_ppid = sp->default_ppid; info.sinfo_context = sp->default_context; info.sinfo_timetolive = sp->default_timetolive; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &info, len)) return -EFAULT; return 0; } /* RFC6458, Section 8.1.31. Set/get Default Send Parameters * (SCTP_DEFAULT_SNDINFO) */ static int sctp_getsockopt_default_sndinfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_sndinfo info; if (len < sizeof(info)) return -EINVAL; len = sizeof(info); if (copy_from_user(&info, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, info.snd_assoc_id); if (!asoc && info.snd_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { info.snd_sid = asoc->default_stream; info.snd_flags = asoc->default_flags; info.snd_ppid = asoc->default_ppid; info.snd_context = asoc->default_context; } else { info.snd_sid = sp->default_stream; info.snd_flags = sp->default_flags; info.snd_ppid = sp->default_ppid; info.snd_context = sp->default_context; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &info, len)) return -EFAULT; return 0; } /* * * 7.1.5 SCTP_NODELAY * * Turn on/off any Nagle-like algorithm. This means that packets are * generally sent as soon as possible and no unnecessary delays are * introduced, at the cost of more packets in the network. Expects an * integer boolean flag. */ static int sctp_getsockopt_nodelay(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = (sctp_sk(sk)->nodelay == 1); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * * 7.1.1 SCTP_RTOINFO * * The protocol parameters used to initialize and bound retransmission * timeout (RTO) are tunable. sctp_rtoinfo structure is used to access * and modify these parameters. * All parameters are time values, in milliseconds. A value of 0, when * modifying the parameters, indicates that the current value should not * be changed. * */ static int sctp_getsockopt_rtoinfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_rtoinfo rtoinfo; struct sctp_association *asoc; if (len < sizeof (struct sctp_rtoinfo)) return -EINVAL; len = sizeof(struct sctp_rtoinfo); if (copy_from_user(&rtoinfo, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, rtoinfo.srto_assoc_id); if (!asoc && rtoinfo.srto_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* Values corresponding to the specific association. */ if (asoc) { rtoinfo.srto_initial = jiffies_to_msecs(asoc->rto_initial); rtoinfo.srto_max = jiffies_to_msecs(asoc->rto_max); rtoinfo.srto_min = jiffies_to_msecs(asoc->rto_min); } else { /* Values corresponding to the endpoint. */ struct sctp_sock *sp = sctp_sk(sk); rtoinfo.srto_initial = sp->rtoinfo.srto_initial; rtoinfo.srto_max = sp->rtoinfo.srto_max; rtoinfo.srto_min = sp->rtoinfo.srto_min; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &rtoinfo, len)) return -EFAULT; return 0; } /* * * 7.1.2 SCTP_ASSOCINFO * * This option is used to tune the maximum retransmission attempts * of the association. * Returns an error if the new association retransmission value is * greater than the sum of the retransmission value of the peer. * See [SCTP] for more information. * */ static int sctp_getsockopt_associnfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assocparams assocparams; struct sctp_association *asoc; struct list_head *pos; int cnt = 0; if (len < sizeof (struct sctp_assocparams)) return -EINVAL; len = sizeof(struct sctp_assocparams); if (copy_from_user(&assocparams, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, assocparams.sasoc_assoc_id); if (!asoc && assocparams.sasoc_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; /* Values correspoinding to the specific association */ if (asoc) { assocparams.sasoc_asocmaxrxt = asoc->max_retrans; assocparams.sasoc_peer_rwnd = asoc->peer.rwnd; assocparams.sasoc_local_rwnd = asoc->a_rwnd; assocparams.sasoc_cookie_life = ktime_to_ms(asoc->cookie_life); list_for_each(pos, &asoc->peer.transport_addr_list) { cnt++; } assocparams.sasoc_number_peer_destinations = cnt; } else { /* Values corresponding to the endpoint */ struct sctp_sock *sp = sctp_sk(sk); assocparams.sasoc_asocmaxrxt = sp->assocparams.sasoc_asocmaxrxt; assocparams.sasoc_peer_rwnd = sp->assocparams.sasoc_peer_rwnd; assocparams.sasoc_local_rwnd = sp->assocparams.sasoc_local_rwnd; assocparams.sasoc_cookie_life = sp->assocparams.sasoc_cookie_life; assocparams.sasoc_number_peer_destinations = sp->assocparams. sasoc_number_peer_destinations; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &assocparams, len)) return -EFAULT; return 0; } /* * 7.1.16 Set/clear IPv4 mapped addresses (SCTP_I_WANT_MAPPED_V4_ADDR) * * This socket option is a boolean flag which turns on or off mapped V4 * addresses. If this option is turned on and the socket is type * PF_INET6, then IPv4 addresses will be mapped to V6 representation. * If this option is turned off, then no mapping will be done of V4 * addresses and a user will receive both PF_INET6 and PF_INET type * addresses on the socket. */ static int sctp_getsockopt_mappedv4(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val; struct sctp_sock *sp = sctp_sk(sk); if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = sp->v4mapped; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * 7.1.29. Set or Get the default context (SCTP_CONTEXT) * (chapter and verse is quoted at sctp_setsockopt_context()) */ static int sctp_getsockopt_context(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; if (len < sizeof(struct sctp_assoc_value)) return -EINVAL; len = sizeof(struct sctp_assoc_value); if (copy_from_user(¶ms, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; params.assoc_value = asoc ? asoc->default_rcv_context : sctp_sk(sk)->default_rcv_context; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, ¶ms, len)) return -EFAULT; return 0; } /* * 8.1.16. Get or Set the Maximum Fragmentation Size (SCTP_MAXSEG) * This option will get or set the maximum size to put in any outgoing * SCTP DATA chunk. If a message is larger than this size it will be * fragmented by SCTP into the specified size. Note that the underlying * SCTP implementation may fragment into smaller sized chunks when the * PMTU of the underlying association is smaller than the value set by * the user. The default value for this option is '0' which indicates * the user is NOT limiting fragmentation and only the PMTU will effect * SCTP's choice of DATA chunk size. Note also that values set larger * than the maximum size of an IP datagram will effectively let SCTP * control fragmentation (i.e. the same as setting this option to 0). * * The following structure is used to access and modify this parameter: * * struct sctp_assoc_value { * sctp_assoc_t assoc_id; * uint32_t assoc_value; * }; * * assoc_id: This parameter is ignored for one-to-one style sockets. * For one-to-many style sockets this parameter indicates which * association the user is performing an action upon. Note that if * this field's value is zero then the endpoints default value is * changed (effecting future associations only). * assoc_value: This parameter specifies the maximum size in bytes. */ static int sctp_getsockopt_maxseg(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; if (len == sizeof(int)) { pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of int in maxseg socket option.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); params.assoc_id = SCTP_FUTURE_ASSOC; } else if (len >= sizeof(struct sctp_assoc_value)) { len = sizeof(struct sctp_assoc_value); if (copy_from_user(¶ms, optval, len)) return -EFAULT; } else return -EINVAL; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) params.assoc_value = asoc->frag_point; else params.assoc_value = sctp_sk(sk)->user_frag; if (put_user(len, optlen)) return -EFAULT; if (len == sizeof(int)) { if (copy_to_user(optval, ¶ms.assoc_value, len)) return -EFAULT; } else { if (copy_to_user(optval, ¶ms, len)) return -EFAULT; } return 0; } /* * 7.1.24. Get or set fragmented interleave (SCTP_FRAGMENT_INTERLEAVE) * (chapter and verse is quoted at sctp_setsockopt_fragment_interleave()) */ static int sctp_getsockopt_fragment_interleave(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = sctp_sk(sk)->frag_interleave; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * 7.1.25. Set or Get the sctp partial delivery point * (chapter and verse is quoted at sctp_setsockopt_partial_delivery_point()) */ static int sctp_getsockopt_partial_delivery_point(struct sock *sk, int len, char __user *optval, int __user *optlen) { u32 val; if (len < sizeof(u32)) return -EINVAL; len = sizeof(u32); val = sctp_sk(sk)->pd_point; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * 7.1.28. Set or Get the maximum burst (SCTP_MAX_BURST) * (chapter and verse is quoted at sctp_setsockopt_maxburst()) */ static int sctp_getsockopt_maxburst(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; if (len == sizeof(int)) { pr_warn_ratelimited(DEPRECATED "%s (pid %d) " "Use of int in max_burst socket option.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); params.assoc_id = SCTP_FUTURE_ASSOC; } else if (len >= sizeof(struct sctp_assoc_value)) { len = sizeof(struct sctp_assoc_value); if (copy_from_user(¶ms, optval, len)) return -EFAULT; } else return -EINVAL; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; params.assoc_value = asoc ? asoc->max_burst : sctp_sk(sk)->max_burst; if (len == sizeof(int)) { if (copy_to_user(optval, ¶ms.assoc_value, len)) return -EFAULT; } else { if (copy_to_user(optval, ¶ms, len)) return -EFAULT; } return 0; } static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_hmacalgo __user *p = (void __user *)optval; struct sctp_hmac_algo_param *hmacs; __u16 data_len = 0; u32 num_idents; int i; if (!ep->auth_enable) return -EACCES; hmacs = ep->auth_hmacs_list; data_len = ntohs(hmacs->param_hdr.length) - sizeof(struct sctp_paramhdr); if (len < sizeof(struct sctp_hmacalgo) + data_len) return -EINVAL; len = sizeof(struct sctp_hmacalgo) + data_len; num_idents = data_len / sizeof(u16); if (put_user(len, optlen)) return -EFAULT; if (put_user(num_idents, &p->shmac_num_idents)) return -EFAULT; for (i = 0; i < num_idents; i++) { __u16 hmacid = ntohs(hmacs->hmac_ids[i]); if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16))) return -EFAULT; } return 0; } static int sctp_getsockopt_active_key(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; if (len < sizeof(struct sctp_authkeyid)) return -EINVAL; len = sizeof(struct sctp_authkeyid); if (copy_from_user(&val, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, val.scact_assoc_id); if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { if (!asoc->peer.auth_capable) return -EACCES; val.scact_keynumber = asoc->active_key_id; } else { if (!ep->auth_enable) return -EACCES; val.scact_keynumber = ep->active_key_id; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; struct sctp_chunks_param *ch; u32 num_chunks = 0; char __user *to; if (len < sizeof(struct sctp_authchunks)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; to = p->gauth_chunks; asoc = sctp_id2assoc(sk, val.gauth_assoc_id); if (!asoc) return -EINVAL; if (!asoc->peer.auth_capable) return -EACCES; ch = asoc->peer.peer_chunks; if (!ch) goto num; /* See if the user provided enough room for all the data */ num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr); if (len < num_chunks) return -EINVAL; if (copy_to_user(to, ch->chunks, num_chunks)) return -EFAULT; num: len = sizeof(struct sctp_authchunks) + num_chunks; if (put_user(len, optlen)) return -EFAULT; if (put_user(num_chunks, &p->gauth_number_of_chunks)) return -EFAULT; return 0; } static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; struct sctp_chunks_param *ch; u32 num_chunks = 0; char __user *to; if (len < sizeof(struct sctp_authchunks)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; to = p->gauth_chunks; asoc = sctp_id2assoc(sk, val.gauth_assoc_id); if (!asoc && val.gauth_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { if (!asoc->peer.auth_capable) return -EACCES; ch = (struct sctp_chunks_param *)asoc->c.auth_chunks; } else { if (!ep->auth_enable) return -EACCES; ch = ep->auth_chunk_list; } if (!ch) goto num; num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr); if (len < sizeof(struct sctp_authchunks) + num_chunks) return -EINVAL; if (copy_to_user(to, ch->chunks, num_chunks)) return -EFAULT; num: len = sizeof(struct sctp_authchunks) + num_chunks; if (put_user(len, optlen)) return -EFAULT; if (put_user(num_chunks, &p->gauth_number_of_chunks)) return -EFAULT; return 0; } /* * 8.2.5. Get the Current Number of Associations (SCTP_GET_ASSOC_NUMBER) * This option gets the current number of associations that are attached * to a one-to-many style socket. The option value is an uint32_t. */ static int sctp_getsockopt_assoc_number(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; u32 val = 0; if (sctp_style(sk, TCP)) return -EOPNOTSUPP; if (len < sizeof(u32)) return -EINVAL; len = sizeof(u32); list_for_each_entry(asoc, &(sp->ep->asocs), asocs) { val++; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * 8.1.23 SCTP_AUTO_ASCONF * See the corresponding setsockopt entry as description */ static int sctp_getsockopt_auto_asconf(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val = 0; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); if (sctp_sk(sk)->do_auto_asconf && sctp_is_ep_boundall(sk)) val = 1; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * 8.2.6. Get the Current Identifiers of Associations * (SCTP_GET_ASSOC_ID_LIST) * * This option gets the current list of SCTP association identifiers of * the SCTP associations handled by a one-to-many style socket. */ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_assoc_ids *ids; size_t ids_size; u32 num = 0; if (sctp_style(sk, TCP)) return -EOPNOTSUPP; if (len < sizeof(struct sctp_assoc_ids)) return -EINVAL; list_for_each_entry(asoc, &(sp->ep->asocs), asocs) { num++; } ids_size = struct_size(ids, gaids_assoc_id, num); if (len < ids_size) return -EINVAL; len = ids_size; ids = kmalloc(len, GFP_USER | __GFP_NOWARN); if (unlikely(!ids)) return -ENOMEM; ids->gaids_number_of_ids = num; num = 0; list_for_each_entry(asoc, &(sp->ep->asocs), asocs) { ids->gaids_assoc_id[num++] = asoc->assoc_id; } if (put_user(len, optlen) || copy_to_user(optval, ids, len)) { kfree(ids); return -EFAULT; } kfree(ids); return 0; } /* * SCTP_PEER_ADDR_THLDS * * This option allows us to fetch the partially failed threshold for one or all * transports in an association. See Section 6.1 of: * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt */ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, char __user *optval, int len, int __user *optlen, bool v2) { struct sctp_paddrthlds_v2 val; struct sctp_transport *trans; struct sctp_association *asoc; int min; min = v2 ? sizeof(val) : sizeof(struct sctp_paddrthlds); if (len < min) return -EINVAL; len = min; if (copy_from_user(&val, optval, len)) return -EFAULT; if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { trans = sctp_addr_id2transport(sk, &val.spt_address, val.spt_assoc_id); if (!trans) return -ENOENT; val.spt_pathmaxrxt = trans->pathmaxrxt; val.spt_pathpfthld = trans->pf_retrans; val.spt_pathcpthld = trans->ps_retrans; goto out; } asoc = sctp_id2assoc(sk, val.spt_assoc_id); if (!asoc && val.spt_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { val.spt_pathpfthld = asoc->pf_retrans; val.spt_pathmaxrxt = asoc->pathmaxrxt; val.spt_pathcpthld = asoc->ps_retrans; } else { struct sctp_sock *sp = sctp_sk(sk); val.spt_pathpfthld = sp->pf_retrans; val.spt_pathmaxrxt = sp->pathmaxrxt; val.spt_pathcpthld = sp->ps_retrans; } out: if (put_user(len, optlen) || copy_to_user(optval, &val, len)) return -EFAULT; return 0; } /* * SCTP_GET_ASSOC_STATS * * This option retrieves local per endpoint statistics. It is modeled * after OpenSolaris' implementation */ static int sctp_getsockopt_assoc_stats(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_stats sas; struct sctp_association *asoc = NULL; /* User must provide at least the assoc id */ if (len < sizeof(sctp_assoc_t)) return -EINVAL; /* Allow the struct to grow and fill in as much as possible */ len = min_t(size_t, len, sizeof(sas)); if (copy_from_user(&sas, optval, len)) return -EFAULT; asoc = sctp_id2assoc(sk, sas.sas_assoc_id); if (!asoc) return -EINVAL; sas.sas_rtxchunks = asoc->stats.rtxchunks; sas.sas_gapcnt = asoc->stats.gapcnt; sas.sas_outofseqtsns = asoc->stats.outofseqtsns; sas.sas_osacks = asoc->stats.osacks; sas.sas_isacks = asoc->stats.isacks; sas.sas_octrlchunks = asoc->stats.octrlchunks; sas.sas_ictrlchunks = asoc->stats.ictrlchunks; sas.sas_oodchunks = asoc->stats.oodchunks; sas.sas_iodchunks = asoc->stats.iodchunks; sas.sas_ouodchunks = asoc->stats.ouodchunks; sas.sas_iuodchunks = asoc->stats.iuodchunks; sas.sas_idupchunks = asoc->stats.idupchunks; sas.sas_opackets = asoc->stats.opackets; sas.sas_ipackets = asoc->stats.ipackets; /* New high max rto observed, will return 0 if not a single * RTO update took place. obs_rto_ipaddr will be bogus * in such a case */ sas.sas_maxrto = asoc->stats.max_obs_rto; memcpy(&sas.sas_obs_rto_ipaddr, &asoc->stats.obs_rto_ipaddr, sizeof(struct sockaddr_storage)); /* Mark beginning of a new observation period */ asoc->stats.max_obs_rto = asoc->rto_min; if (put_user(len, optlen)) return -EFAULT; pr_debug("%s: len:%d, assoc_id:%d\n", __func__, len, sas.sas_assoc_id); if (copy_to_user(optval, &sas, len)) return -EFAULT; return 0; } static int sctp_getsockopt_recvrcvinfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val = 0; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); if (sctp_sk(sk)->recvrcvinfo) val = 1; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int sctp_getsockopt_recvnxtinfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val = 0; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); if (sctp_sk(sk)->recvnxtinfo) val = 1; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int sctp_getsockopt_pr_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.prsctp_capable : sctp_sk(sk)->ep->prsctp_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_default_prinfo(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_default_prinfo info; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(info)) { retval = -EINVAL; goto out; } len = sizeof(info); if (copy_from_user(&info, optval, len)) goto out; asoc = sctp_id2assoc(sk, info.pr_assoc_id); if (!asoc && info.pr_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } if (asoc) { info.pr_policy = SCTP_PR_POLICY(asoc->default_flags); info.pr_value = asoc->default_timetolive; } else { struct sctp_sock *sp = sctp_sk(sk); info.pr_policy = SCTP_PR_POLICY(sp->default_flags); info.pr_value = sp->default_timetolive; } if (put_user(len, optlen)) goto out; if (copy_to_user(optval, &info, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_prstatus params; struct sctp_association *asoc; int policy; int retval = -EINVAL; if (len < sizeof(params)) goto out; len = sizeof(params); if (copy_from_user(¶ms, optval, len)) { retval = -EFAULT; goto out; } policy = params.sprstat_policy; if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) || ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK))) goto out; asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); if (!asoc) goto out; if (policy == SCTP_PR_SCTP_ALL) { params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) { params.sprstat_abandoned_unsent += asoc->abandoned_unsent[policy]; params.sprstat_abandoned_sent += asoc->abandoned_sent[policy]; } } else { params.sprstat_abandoned_unsent = asoc->abandoned_unsent[__SCTP_PR_INDEX(policy)]; params.sprstat_abandoned_sent = asoc->abandoned_sent[__SCTP_PR_INDEX(policy)]; } if (put_user(len, optlen)) { retval = -EFAULT; goto out; } if (copy_to_user(optval, ¶ms, len)) { retval = -EFAULT; goto out; } retval = 0; out: return retval; } static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_stream_out_ext *streamoute; struct sctp_association *asoc; struct sctp_prstatus params; int retval = -EINVAL; int policy; if (len < sizeof(params)) goto out; len = sizeof(params); if (copy_from_user(¶ms, optval, len)) { retval = -EFAULT; goto out; } policy = params.sprstat_policy; if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) || ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK))) goto out; asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); if (!asoc || params.sprstat_sid >= asoc->stream.outcnt) goto out; streamoute = SCTP_SO(&asoc->stream, params.sprstat_sid)->ext; if (!streamoute) { /* Not allocated yet, means all stats are 0 */ params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; retval = 0; goto out; } if (policy == SCTP_PR_SCTP_ALL) { params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) { params.sprstat_abandoned_unsent += streamoute->abandoned_unsent[policy]; params.sprstat_abandoned_sent += streamoute->abandoned_sent[policy]; } } else { params.sprstat_abandoned_unsent = streamoute->abandoned_unsent[__SCTP_PR_INDEX(policy)]; params.sprstat_abandoned_sent = streamoute->abandoned_sent[__SCTP_PR_INDEX(policy)]; } if (put_user(len, optlen) || copy_to_user(optval, ¶ms, len)) { retval = -EFAULT; goto out; } retval = 0; out: return retval; } static int sctp_getsockopt_reconfig_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.reconf_capable : sctp_sk(sk)->ep->reconf_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_enable_strreset(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->strreset_enable : sctp_sk(sk)->ep->strreset_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_scheduler(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? sctp_sched_get_sched(asoc) : sctp_sk(sk)->default_ss; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_scheduler_value(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_stream_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc) { retval = -EINVAL; goto out; } retval = sctp_sched_get_value(asoc, params.stream_id, ¶ms.stream_value); if (retval) goto out; if (put_user(len, optlen)) { retval = -EFAULT; goto out; } if (copy_to_user(optval, ¶ms, len)) { retval = -EFAULT; goto out; } out: return retval; } static int sctp_getsockopt_interleaving_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.intl_capable : sctp_sk(sk)->ep->intl_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_reuse_port(struct sock *sk, int len, char __user *optval, int __user *optlen) { int val; if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = sctp_sk(sk)->reuse; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int sctp_getsockopt_event(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_association *asoc; struct sctp_event param; __u16 subscribe; if (len < sizeof(param)) return -EINVAL; len = sizeof(param); if (copy_from_user(¶m, optval, len)) return -EFAULT; if (param.se_type < SCTP_SN_TYPE_BASE || param.se_type > SCTP_SN_TYPE_MAX) return -EINVAL; asoc = sctp_id2assoc(sk, param.se_assoc_id); if (!asoc && param.se_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) return -EINVAL; subscribe = asoc ? asoc->subscribe : sctp_sk(sk)->subscribe; param.se_on = sctp_ulpevent_type_enabled(subscribe, param.se_type); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, ¶m, len)) return -EFAULT; return 0; } static int sctp_getsockopt_asconf_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.asconf_capable : sctp_sk(sk)->ep->asconf_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_auth_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.auth_capable : sctp_sk(sk)->ep->auth_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_ecn_supported(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->peer.ecn_capable : sctp_sk(sk)->ep->ecn_enable; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_pf_expose(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EFAULT; if (len < sizeof(params)) { retval = -EINVAL; goto out; } len = sizeof(params); if (copy_from_user(¶ms, optval, len)) goto out; asoc = sctp_id2assoc(sk, params.assoc_id); if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } params.assoc_value = asoc ? asoc->pf_expose : sctp_sk(sk)->pf_expose; if (put_user(len, optlen)) goto out; if (copy_to_user(optval, ¶ms, len)) goto out; retval = 0; out: return retval; } static int sctp_getsockopt_encap_port(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_association *asoc; struct sctp_udpencaps encap; struct sctp_transport *t; __be16 encap_port; if (len < sizeof(encap)) return -EINVAL; len = sizeof(encap); if (copy_from_user(&encap, optval, len)) return -EFAULT; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ if (!sctp_is_any(sk, (union sctp_addr *)&encap.sue_address)) { t = sctp_addr_id2transport(sk, &encap.sue_address, encap.sue_assoc_id); if (!t) { pr_debug("%s: failed no transport\n", __func__); return -EINVAL; } encap_port = t->encap_port; goto out; } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, encap.sue_assoc_id); if (!asoc && encap.sue_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { pr_debug("%s: failed no association\n", __func__); return -EINVAL; } if (asoc) { encap_port = asoc->encap_port; goto out; } encap_port = sctp_sk(sk)->encap_port; out: encap.sue_port = (__force uint16_t)encap_port; if (copy_to_user(optval, &encap, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } static int sctp_getsockopt_probe_interval(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_probeinterval params; struct sctp_association *asoc; struct sctp_transport *t; __u32 probe_interval; if (len < sizeof(params)) return -EINVAL; len = sizeof(params); if (copy_from_user(¶ms, optval, len)) return -EFAULT; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ if (!sctp_is_any(sk, (union sctp_addr *)¶ms.spi_address)) { t = sctp_addr_id2transport(sk, ¶ms.spi_address, params.spi_assoc_id); if (!t) { pr_debug("%s: failed no transport\n", __func__); return -EINVAL; } probe_interval = jiffies_to_msecs(t->probe_interval); goto out; } /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the * socket is a one to many style socket, and an association * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.spi_assoc_id); if (!asoc && params.spi_assoc_id != SCTP_FUTURE_ASSOC && sctp_style(sk, UDP)) { pr_debug("%s: failed no association\n", __func__); return -EINVAL; } if (asoc) { probe_interval = jiffies_to_msecs(asoc->probe_interval); goto out; } probe_interval = sctp_sk(sk)->probe_interval; out: params.spi_interval = probe_interval; if (copy_to_user(optval, ¶ms, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int retval = 0; int len; pr_debug("%s: sk:%p, optname:%d\n", __func__, sk, optname); /* I can hardly begin to describe how wrong this is. This is * so broken as to be worse than useless. The API draft * REALLY is NOT helpful here... I am not convinced that the * semantics of getsockopt() with a level OTHER THAN SOL_SCTP * are at all well-founded. */ if (level != SOL_SCTP) { struct sctp_af *af = sctp_sk(sk)->pf->af; retval = af->getsockopt(sk, level, optname, optval, optlen); return retval; } if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; lock_sock(sk); switch (optname) { case SCTP_STATUS: retval = sctp_getsockopt_sctp_status(sk, len, optval, optlen); break; case SCTP_DISABLE_FRAGMENTS: retval = sctp_getsockopt_disable_fragments(sk, len, optval, optlen); break; case SCTP_EVENTS: retval = sctp_getsockopt_events(sk, len, optval, optlen); break; case SCTP_AUTOCLOSE: retval = sctp_getsockopt_autoclose(sk, len, optval, optlen); break; case SCTP_SOCKOPT_PEELOFF: retval = sctp_getsockopt_peeloff(sk, len, optval, optlen); break; case SCTP_SOCKOPT_PEELOFF_FLAGS: retval = sctp_getsockopt_peeloff_flags(sk, len, optval, optlen); break; case SCTP_PEER_ADDR_PARAMS: retval = sctp_getsockopt_peer_addr_params(sk, len, optval, optlen); break; case SCTP_DELAYED_SACK: retval = sctp_getsockopt_delayed_ack(sk, len, optval, optlen); break; case SCTP_INITMSG: retval = sctp_getsockopt_initmsg(sk, len, optval, optlen); break; case SCTP_GET_PEER_ADDRS: retval = sctp_getsockopt_peer_addrs(sk, len, optval, optlen); break; case SCTP_GET_LOCAL_ADDRS: retval = sctp_getsockopt_local_addrs(sk, len, optval, optlen); break; case SCTP_SOCKOPT_CONNECTX3: retval = sctp_getsockopt_connectx3(sk, len, optval, optlen); break; case SCTP_DEFAULT_SEND_PARAM: retval = sctp_getsockopt_default_send_param(sk, len, optval, optlen); break; case SCTP_DEFAULT_SNDINFO: retval = sctp_getsockopt_default_sndinfo(sk, len, optval, optlen); break; case SCTP_PRIMARY_ADDR: retval = sctp_getsockopt_primary_addr(sk, len, optval, optlen); break; case SCTP_NODELAY: retval = sctp_getsockopt_nodelay(sk, len, optval, optlen); break; case SCTP_RTOINFO: retval = sctp_getsockopt_rtoinfo(sk, len, optval, optlen); break; case SCTP_ASSOCINFO: retval = sctp_getsockopt_associnfo(sk, len, optval, optlen); break; case SCTP_I_WANT_MAPPED_V4_ADDR: retval = sctp_getsockopt_mappedv4(sk, len, optval, optlen); break; case SCTP_MAXSEG: retval = sctp_getsockopt_maxseg(sk, len, optval, optlen); break; case SCTP_GET_PEER_ADDR_INFO: retval = sctp_getsockopt_peer_addr_info(sk, len, optval, optlen); break; case SCTP_ADAPTATION_LAYER: retval = sctp_getsockopt_adaptation_layer(sk, len, optval, optlen); break; case SCTP_CONTEXT: retval = sctp_getsockopt_context(sk, len, optval, optlen); break; case SCTP_FRAGMENT_INTERLEAVE: retval = sctp_getsockopt_fragment_interleave(sk, len, optval, optlen); break; case SCTP_PARTIAL_DELIVERY_POINT: retval = sctp_getsockopt_partial_delivery_point(sk, len, optval, optlen); break; case SCTP_MAX_BURST: retval = sctp_getsockopt_maxburst(sk, len, optval, optlen); break; case SCTP_AUTH_KEY: case SCTP_AUTH_CHUNK: case SCTP_AUTH_DELETE_KEY: case SCTP_AUTH_DEACTIVATE_KEY: retval = -EOPNOTSUPP; break; case SCTP_HMAC_IDENT: retval = sctp_getsockopt_hmac_ident(sk, len, optval, optlen); break; case SCTP_AUTH_ACTIVE_KEY: retval = sctp_getsockopt_active_key(sk, len, optval, optlen); break; case SCTP_PEER_AUTH_CHUNKS: retval = sctp_getsockopt_peer_auth_chunks(sk, len, optval, optlen); break; case SCTP_LOCAL_AUTH_CHUNKS: retval = sctp_getsockopt_local_auth_chunks(sk, len, optval, optlen); break; case SCTP_GET_ASSOC_NUMBER: retval = sctp_getsockopt_assoc_number(sk, len, optval, optlen); break; case SCTP_GET_ASSOC_ID_LIST: retval = sctp_getsockopt_assoc_ids(sk, len, optval, optlen); break; case SCTP_AUTO_ASCONF: retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen); break; case SCTP_PEER_ADDR_THLDS: retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen, false); break; case SCTP_PEER_ADDR_THLDS_V2: retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen, true); break; case SCTP_GET_ASSOC_STATS: retval = sctp_getsockopt_assoc_stats(sk, len, optval, optlen); break; case SCTP_RECVRCVINFO: retval = sctp_getsockopt_recvrcvinfo(sk, len, optval, optlen); break; case SCTP_RECVNXTINFO: retval = sctp_getsockopt_recvnxtinfo(sk, len, optval, optlen); break; case SCTP_PR_SUPPORTED: retval = sctp_getsockopt_pr_supported(sk, len, optval, optlen); break; case SCTP_DEFAULT_PRINFO: retval = sctp_getsockopt_default_prinfo(sk, len, optval, optlen); break; case SCTP_PR_ASSOC_STATUS: retval = sctp_getsockopt_pr_assocstatus(sk, len, optval, optlen); break; case SCTP_PR_STREAM_STATUS: retval = sctp_getsockopt_pr_streamstatus(sk, len, optval, optlen); break; case SCTP_RECONFIG_SUPPORTED: retval = sctp_getsockopt_reconfig_supported(sk, len, optval, optlen); break; case SCTP_ENABLE_STREAM_RESET: retval = sctp_getsockopt_enable_strreset(sk, len, optval, optlen); break; case SCTP_STREAM_SCHEDULER: retval = sctp_getsockopt_scheduler(sk, len, optval, optlen); break; case SCTP_STREAM_SCHEDULER_VALUE: retval = sctp_getsockopt_scheduler_value(sk, len, optval, optlen); break; case SCTP_INTERLEAVING_SUPPORTED: retval = sctp_getsockopt_interleaving_supported(sk, len, optval, optlen); break; case SCTP_REUSE_PORT: retval = sctp_getsockopt_reuse_port(sk, len, optval, optlen); break; case SCTP_EVENT: retval = sctp_getsockopt_event(sk, len, optval, optlen); break; case SCTP_ASCONF_SUPPORTED: retval = sctp_getsockopt_asconf_supported(sk, len, optval, optlen); break; case SCTP_AUTH_SUPPORTED: retval = sctp_getsockopt_auth_supported(sk, len, optval, optlen); break; case SCTP_ECN_SUPPORTED: retval = sctp_getsockopt_ecn_supported(sk, len, optval, optlen); break; case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE: retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen); break; case SCTP_REMOTE_UDP_ENCAPS_PORT: retval = sctp_getsockopt_encap_port(sk, len, optval, optlen); break; case SCTP_PLPMTUD_PROBE_INTERVAL: retval = sctp_getsockopt_probe_interval(sk, len, optval, optlen); break; default: retval = -ENOPROTOOPT; break; } release_sock(sk); return retval; } static bool sctp_bpf_bypass_getsockopt(int level, int optname) { if (level == SOL_SCTP) { switch (optname) { case SCTP_SOCKOPT_PEELOFF: case SCTP_SOCKOPT_PEELOFF_FLAGS: case SCTP_SOCKOPT_CONNECTX3: return true; default: return false; } } return false; } static int sctp_hash(struct sock *sk) { /* STUB */ return 0; } static void sctp_unhash(struct sock *sk) { /* STUB */ } /* Check if port is acceptable. Possibly find first available port. * * The port hash table (contained in the 'global' SCTP protocol storage * returned by struct sctp_protocol *sctp_get_protocol()). The hash * table is an array of 4096 lists (sctp_bind_hashbucket). Each * list (the list number is the port number hashed out, so as you * would expect from a hash function, all the ports in a given list have * such a number that hashes out to the same list number; you were * expecting that, right?); so each list has a set of ports, with a * link to the socket (struct sock) that uses it, the port number and * a fastreuse flag (FIXME: NPI ipg). */ static struct sctp_bind_bucket *sctp_bucket_create( struct sctp_bind_hashbucket *head, struct net *, unsigned short snum); static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) { struct sctp_sock *sp = sctp_sk(sk); bool reuse = (sk->sk_reuse || sp->reuse); struct sctp_bind_hashbucket *head; /* hash list */ struct net *net = sock_net(sk); kuid_t uid = sock_i_uid(sk); struct sctp_bind_bucket *pp; unsigned short snum; int ret; snum = ntohs(addr->v4.sin_port); pr_debug("%s: begins, snum:%d\n", __func__, snum); if (snum == 0) { /* Search for an available port. */ int low, high, remaining, index; unsigned int rover; inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rover = prandom_u32() % remaining + low; do { rover++; if ((rover < low) || (rover > high)) rover = low; if (inet_is_local_reserved_port(net, rover)) continue; index = sctp_phashfn(net, rover); head = &sctp_port_hashtable[index]; spin_lock_bh(&head->lock); sctp_for_each_hentry(pp, &head->chain) if ((pp->port == rover) && net_eq(net, pp->net)) goto next; break; next: spin_unlock_bh(&head->lock); cond_resched(); } while (--remaining > 0); /* Exhausted local port range during search? */ ret = 1; if (remaining <= 0) return ret; /* OK, here is the one we will use. HEAD (the port * hash table list entry) is non-NULL and we hold it's * mutex. */ snum = rover; } else { /* We are given an specific port number; we verify * that it is not being used. If it is used, we will * exahust the search in the hash list corresponding * to the port number (snum) - we detect that with the * port iterator, pp being NULL. */ head = &sctp_port_hashtable[sctp_phashfn(net, snum)]; spin_lock_bh(&head->lock); sctp_for_each_hentry(pp, &head->chain) { if ((pp->port == snum) && net_eq(pp->net, net)) goto pp_found; } } pp = NULL; goto pp_not_found; pp_found: if (!hlist_empty(&pp->owner)) { /* We had a port hash table hit - there is an * available port (pp != NULL) and it is being * used by other socket (pp->owner not empty); that other * socket is going to be sk2. */ struct sock *sk2; pr_debug("%s: found a possible match\n", __func__); if ((pp->fastreuse && reuse && sk->sk_state != SCTP_SS_LISTENING) || (pp->fastreuseport && sk->sk_reuseport && uid_eq(pp->fastuid, uid))) goto success; /* Run through the list of sockets bound to the port * (pp->port) [via the pointers bind_next and * bind_pprev in the struct sock *sk2 (pp->sk)]. On each one, * we get the endpoint they describe and run through * the endpoint's list of IP (v4 or v6) addresses, * comparing each of the addresses with the address of * the socket sk. If we find a match, then that means * that this port/socket (sk) combination are already * in an endpoint. */ sk_for_each_bound(sk2, &pp->owner) { struct sctp_sock *sp2 = sctp_sk(sk2); struct sctp_endpoint *ep2 = sp2->ep; if (sk == sk2 || (reuse && (sk2->sk_reuse || sp2->reuse) && sk2->sk_state != SCTP_SS_LISTENING) || (sk->sk_reuseport && sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)))) continue; if (sctp_bind_addr_conflict(&ep2->base.bind_addr, addr, sp2, sp)) { ret = 1; goto fail_unlock; } } pr_debug("%s: found a match\n", __func__); } pp_not_found: /* If there was a hash table miss, create a new port. */ ret = 1; if (!pp && !(pp = sctp_bucket_create(head, net, snum))) goto fail_unlock; /* In either case (hit or miss), make sure fastreuse is 1 only * if sk->sk_reuse is too (that is, if the caller requested * SO_REUSEADDR on this socket -sk-). */ if (hlist_empty(&pp->owner)) { if (reuse && sk->sk_state != SCTP_SS_LISTENING) pp->fastreuse = 1; else pp->fastreuse = 0; if (sk->sk_reuseport) { pp->fastreuseport = 1; pp->fastuid = uid; } else { pp->fastreuseport = 0; } } else { if (pp->fastreuse && (!reuse || sk->sk_state == SCTP_SS_LISTENING)) pp->fastreuse = 0; if (pp->fastreuseport && (!sk->sk_reuseport || !uid_eq(pp->fastuid, uid))) pp->fastreuseport = 0; } /* We are set, so fill up all the data in the hash table * entry, tie the socket list information with the rest of the * sockets FIXME: Blurry, NPI (ipg). */ success: if (!sp->bind_hash) { inet_sk(sk)->inet_num = snum; sk_add_bind_node(sk, &pp->owner); sp->bind_hash = pp; } ret = 0; fail_unlock: spin_unlock_bh(&head->lock); return ret; } /* Assign a 'snum' port to the socket. If snum == 0, an ephemeral * port is requested. */ static int sctp_get_port(struct sock *sk, unsigned short snum) { union sctp_addr addr; struct sctp_af *af = sctp_sk(sk)->pf->af; /* Set up a dummy address struct from the sk. */ af->from_sk(&addr, sk); addr.v4.sin_port = htons(snum); /* Note: sk->sk_num gets filled in if ephemeral port request. */ return sctp_get_port_local(sk, &addr); } /* * Move a socket to LISTENING state. */ static int sctp_listen_start(struct sock *sk, int backlog) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; struct crypto_shash *tfm = NULL; char alg[32]; int err; /* Allocate HMAC for generating cookie. */ if (!sp->hmac && sp->sctp_hmac_alg) { sprintf(alg, "hmac(%s)", sp->sctp_hmac_alg); tfm = crypto_alloc_shash(alg, 0, 0); if (IS_ERR(tfm)) { net_info_ratelimited("failed to load transform for %s: %ld\n", sp->sctp_hmac_alg, PTR_ERR(tfm)); return -ENOSYS; } sctp_sk(sk)->hmac = tfm; } /* * If a bind() or sctp_bindx() is not called prior to a listen() * call that allows new associations to be accepted, the system * picks an ephemeral port and will choose an address set equivalent * to binding with a wildcard address. * * This is not currently spelled out in the SCTP sockets * extensions draft, but follows the practice as seen in TCP * sockets. * */ inet_sk_set_state(sk, SCTP_SS_LISTENING); if (!ep->base.bind_addr.port) { if (sctp_autobind(sk)) { err = -EAGAIN; goto err; } } else { if (sctp_get_port(sk, inet_sk(sk)->inet_num)) { err = -EADDRINUSE; goto err; } } WRITE_ONCE(sk->sk_max_ack_backlog, backlog); err = sctp_hash_endpoint(ep); if (err) goto err; return 0; err: inet_sk_set_state(sk, SCTP_SS_CLOSED); return err; } /* * 4.1.3 / 5.1.3 listen() * * By default, new associations are not accepted for UDP style sockets. * An application uses listen() to mark a socket as being able to * accept new associations. * * On TCP style sockets, applications use listen() to ready the SCTP * endpoint for accepting inbound associations. * * On both types of endpoints a backlog of '0' disables listening. * * Move a socket to LISTENING state. */ int sctp_inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; struct sctp_endpoint *ep = sctp_sk(sk)->ep; int err = -EINVAL; if (unlikely(backlog < 0)) return err; lock_sock(sk); /* Peeled-off sockets are not allowed to listen(). */ if (sctp_style(sk, UDP_HIGH_BANDWIDTH)) goto out; if (sock->state != SS_UNCONNECTED) goto out; if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED)) goto out; /* If backlog is zero, disable listening. */ if (!backlog) { if (sctp_sstate(sk, CLOSED)) goto out; err = 0; sctp_unhash_endpoint(ep); sk->sk_state = SCTP_SS_CLOSED; if (sk->sk_reuse || sctp_sk(sk)->reuse) sctp_sk(sk)->bind_hash->fastreuse = 1; goto out; } /* If we are already listening, just update the backlog */ if (sctp_sstate(sk, LISTENING)) WRITE_ONCE(sk->sk_max_ack_backlog, backlog); else { err = sctp_listen_start(sk, backlog); if (err) goto out; } err = 0; out: release_sock(sk); return err; } /* * This function is done by modeling the current datagram_poll() and the * tcp_poll(). Note that, based on these implementations, we don't * lock the socket in this function, even though it seems that, * ideally, locking or some other mechanisms can be used to ensure * the integrity of the counters (sndbuf and wmem_alloc) used * in this place. We assume that we don't need locks either until proven * otherwise. * * Another thing to note is that we include the Async I/O support * here, again, by modeling the current TCP/UDP code. We don't have * a good way to test with it yet. */ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct sctp_sock *sp = sctp_sk(sk); __poll_t mask; poll_wait(file, sk_sleep(sk), wait); sock_rps_record_flow(sk); /* A TCP-style listening socket becomes readable when the accept queue * is not empty. */ if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING)) return (!list_empty(&sp->ep->asocs)) ? (EPOLLIN | EPOLLRDNORM) : 0; mask = 0; /* Is there any exceptional events? */ if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* Is it readable? Reconsider this code with TCP-style support. */ if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* The association is either gone or not ready. */ if (!sctp_style(sk, UDP) && sctp_sstate(sk, CLOSED)) return mask; /* Is it writable? */ if (sctp_writeable(sk)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* * Since the socket is not locked, the buffer * might be made available after the writeable check and * before the bit is set. This could cause a lost I/O * signal. tcp_poll() has a race breaker for this race * condition. Based on their implementation, we put * in the following code to cover it as well. */ if (sctp_writeable(sk)) mask |= EPOLLOUT | EPOLLWRNORM; } return mask; } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ static struct sctp_bind_bucket *sctp_bucket_create( struct sctp_bind_hashbucket *head, struct net *net, unsigned short snum) { struct sctp_bind_bucket *pp; pp = kmem_cache_alloc(sctp_bucket_cachep, GFP_ATOMIC); if (pp) { SCTP_DBG_OBJCNT_INC(bind_bucket); pp->port = snum; pp->fastreuse = 0; INIT_HLIST_HEAD(&pp->owner); pp->net = net; hlist_add_head(&pp->node, &head->chain); } return pp; } /* Caller must hold hashbucket lock for this tb with local BH disabled */ static void sctp_bucket_destroy(struct sctp_bind_bucket *pp) { if (pp && hlist_empty(&pp->owner)) { __hlist_del(&pp->node); kmem_cache_free(sctp_bucket_cachep, pp); SCTP_DBG_OBJCNT_DEC(bind_bucket); } } /* Release this socket's reference to a local port. */ static inline void __sctp_put_port(struct sock *sk) { struct sctp_bind_hashbucket *head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), inet_sk(sk)->inet_num)]; struct sctp_bind_bucket *pp; spin_lock(&head->lock); pp = sctp_sk(sk)->bind_hash; __sk_del_bind_node(sk); sctp_sk(sk)->bind_hash = NULL; inet_sk(sk)->inet_num = 0; sctp_bucket_destroy(pp); spin_unlock(&head->lock); } void sctp_put_port(struct sock *sk) { local_bh_disable(); __sctp_put_port(sk); local_bh_enable(); } /* * The system picks an ephemeral port and choose an address set equivalent * to binding with a wildcard address. * One of those addresses will be the primary address for the association. * This automatically enables the multihoming capability of SCTP. */ static int sctp_autobind(struct sock *sk) { union sctp_addr autoaddr; struct sctp_af *af; __be16 port; /* Initialize a local sockaddr structure to INADDR_ANY. */ af = sctp_sk(sk)->pf->af; port = htons(inet_sk(sk)->inet_num); af->inaddr_any(&autoaddr, port); return sctp_do_bind(sk, &autoaddr, af->sockaddr_len); } /* Parse out IPPROTO_SCTP CMSG headers. Perform only minimal validation. * * From RFC 2292 * 4.2 The cmsghdr Structure * * * When ancillary data is sent or received, any number of ancillary data * objects can be specified by the msg_control and msg_controllen members of * the msghdr structure, because each object is preceded by * a cmsghdr structure defining the object's length (the cmsg_len member). * Historically Berkeley-derived implementations have passed only one object * at a time, but this API allows multiple objects to be * passed in a single call to sendmsg() or recvmsg(). The following example * shows two ancillary data objects in a control buffer. * * |<--------------------------- msg_controllen -------------------------->| * | | * * |<----- ancillary data object ----->|<----- ancillary data object ----->| * * |<---------- CMSG_SPACE() --------->|<---------- CMSG_SPACE() --------->| * | | | * * |<---------- cmsg_len ---------->| |<--------- cmsg_len ----------->| | * * |<--------- CMSG_LEN() --------->| |<-------- CMSG_LEN() ---------->| | * | | | | | * * +-----+-----+-----+--+-----------+--+-----+-----+-----+--+-----------+--+ * |cmsg_|cmsg_|cmsg_|XX| |XX|cmsg_|cmsg_|cmsg_|XX| |XX| * * |len |level|type |XX|cmsg_data[]|XX|len |level|type |XX|cmsg_data[]|XX| * * +-----+-----+-----+--+-----------+--+-----+-----+-----+--+-----------+--+ * ^ * | * * msg_control * points here */ static int sctp_msghdr_parse(const struct msghdr *msg, struct sctp_cmsgs *cmsgs) { struct msghdr *my_msg = (struct msghdr *)msg; struct cmsghdr *cmsg; for_each_cmsghdr(cmsg, my_msg) { if (!CMSG_OK(my_msg, cmsg)) return -EINVAL; /* Should we parse this header or ignore? */ if (cmsg->cmsg_level != IPPROTO_SCTP) continue; /* Strictly check lengths following example in SCM code. */ switch (cmsg->cmsg_type) { case SCTP_INIT: /* SCTP Socket API Extension * 5.3.1 SCTP Initiation Structure (SCTP_INIT) * * This cmsghdr structure provides information for * initializing new SCTP associations with sendmsg(). * The SCTP_INITMSG socket option uses this same data * structure. This structure is not used for * recvmsg(). * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ ---------------------- * IPPROTO_SCTP SCTP_INIT struct sctp_initmsg */ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_initmsg))) return -EINVAL; cmsgs->init = CMSG_DATA(cmsg); break; case SCTP_SNDRCV: /* SCTP Socket API Extension * 5.3.2 SCTP Header Information Structure(SCTP_SNDRCV) * * This cmsghdr structure specifies SCTP options for * sendmsg() and describes SCTP header information * about a received message through recvmsg(). * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ ---------------------- * IPPROTO_SCTP SCTP_SNDRCV struct sctp_sndrcvinfo */ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_sndrcvinfo))) return -EINVAL; cmsgs->srinfo = CMSG_DATA(cmsg); if (cmsgs->srinfo->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | SCTP_SACK_IMMEDIATELY | SCTP_SENDALL | SCTP_PR_SCTP_MASK | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; case SCTP_SNDINFO: /* SCTP Socket API Extension * 5.3.4 SCTP Send Information Structure (SCTP_SNDINFO) * * This cmsghdr structure specifies SCTP options for * sendmsg(). This structure and SCTP_RCVINFO replaces * SCTP_SNDRCV which has been deprecated. * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ --------------------- * IPPROTO_SCTP SCTP_SNDINFO struct sctp_sndinfo */ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_sndinfo))) return -EINVAL; cmsgs->sinfo = CMSG_DATA(cmsg); if (cmsgs->sinfo->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | SCTP_SACK_IMMEDIATELY | SCTP_SENDALL | SCTP_PR_SCTP_MASK | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; case SCTP_PRINFO: /* SCTP Socket API Extension * 5.3.7 SCTP PR-SCTP Information Structure (SCTP_PRINFO) * * This cmsghdr structure specifies SCTP options for sendmsg(). * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ --------------------- * IPPROTO_SCTP SCTP_PRINFO struct sctp_prinfo */ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_prinfo))) return -EINVAL; cmsgs->prinfo = CMSG_DATA(cmsg); if (cmsgs->prinfo->pr_policy & ~SCTP_PR_SCTP_MASK) return -EINVAL; if (cmsgs->prinfo->pr_policy == SCTP_PR_SCTP_NONE) cmsgs->prinfo->pr_value = 0; break; case SCTP_AUTHINFO: /* SCTP Socket API Extension * 5.3.8 SCTP AUTH Information Structure (SCTP_AUTHINFO) * * This cmsghdr structure specifies SCTP options for sendmsg(). * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ --------------------- * IPPROTO_SCTP SCTP_AUTHINFO struct sctp_authinfo */ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_authinfo))) return -EINVAL; cmsgs->authinfo = CMSG_DATA(cmsg); break; case SCTP_DSTADDRV4: case SCTP_DSTADDRV6: /* SCTP Socket API Extension * 5.3.9/10 SCTP Destination IPv4/6 Address Structure (SCTP_DSTADDRV4/6) * * This cmsghdr structure specifies SCTP options for sendmsg(). * * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ --------------------- * IPPROTO_SCTP SCTP_DSTADDRV4 struct in_addr * ------------ ------------ --------------------- * IPPROTO_SCTP SCTP_DSTADDRV6 struct in6_addr */ cmsgs->addrs_msg = my_msg; break; default: return -EINVAL; } } return 0; } /* * Wait for a packet.. * Note: This function is the same function as in core/datagram.c * with a few modifications to make lksctp work. */ static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p) { int error; DEFINE_WAIT(wait); prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* Socket errors? */ error = sock_error(sk); if (error) goto out; if (!skb_queue_empty(&sk->sk_receive_queue)) goto ready; /* Socket shut down? */ if (sk->sk_shutdown & RCV_SHUTDOWN) goto out; /* Sequenced packets can come disconnected. If so we report the * problem. */ error = -ENOTCONN; /* Is there a good reason to think that we may receive some data? */ if (list_empty(&sctp_sk(sk)->ep->asocs) && !sctp_sstate(sk, LISTENING)) goto out; /* Handle signals. */ if (signal_pending(current)) goto interrupted; /* Let another process have a go. Since we are going to sleep * anyway. Note: This may cause odd behaviors if the message * does not fit in the user's buffer, but this seems to be the * only way to honor MSG_DONTWAIT realistically. */ release_sock(sk); *timeo_p = schedule_timeout(*timeo_p); lock_sock(sk); ready: finish_wait(sk_sleep(sk), &wait); return 0; interrupted: error = sock_intr_errno(*timeo_p); out: finish_wait(sk_sleep(sk), &wait); *err = error; return error; } /* Receive a datagram. * Note: This is pretty much the same routine as in core/datagram.c * with a few changes to make lksctp work. */ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, int noblock, int *err) { int error; struct sk_buff *skb; long timeo; timeo = sock_rcvtimeo(sk, noblock); pr_debug("%s: timeo:%ld, max:%ld\n", __func__, timeo, MAX_SCHEDULE_TIMEOUT); do { /* Again only user level code calls this function, * so nothing interrupt level * will suddenly eat the receive_queue. * * Look at current nfs client by the way... * However, this function was correct in any case. 8) */ if (flags & MSG_PEEK) { skb = skb_peek(&sk->sk_receive_queue); if (skb) refcount_inc(&skb->users); } else { skb = __skb_dequeue(&sk->sk_receive_queue); } if (skb) return skb; /* Caller is allowed not to check sk->sk_err before calling. */ error = sock_error(sk); if (error) goto no_packet; if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk_can_busy_loop(sk)) { sk_busy_loop(sk, noblock); if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) continue; } /* User doesn't want to wait. */ error = -EAGAIN; if (!timeo) goto no_packet; } while (sctp_wait_for_packet(sk, err, &timeo) == 0); return NULL; no_packet: *err = error; return NULL; } /* If sndbuf has changed, wake up per association sndbuf waiters. */ static void __sctp_write_space(struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; if (sctp_wspace(asoc) <= 0) return; if (waitqueue_active(&asoc->wait)) wake_up_interruptible(&asoc->wait); if (sctp_writeable(sk)) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (wq) { if (waitqueue_active(&wq->wait)) wake_up_interruptible(&wq->wait); /* Note that we try to include the Async I/O support * here by modeling from the current TCP/UDP code. * We have not tested with it yet. */ if (!(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } } static void sctp_wake_up_waiters(struct sock *sk, struct sctp_association *asoc) { struct sctp_association *tmp = asoc; /* We do accounting for the sndbuf space per association, * so we only need to wake our own association. */ if (asoc->ep->sndbuf_policy) return __sctp_write_space(asoc); /* If association goes down and is just flushing its * outq, then just normally notify others. */ if (asoc->base.dead) return sctp_write_space(sk); /* Accounting for the sndbuf space is per socket, so we * need to wake up others, try to be fair and in case of * other associations, let them have a go first instead * of just doing a sctp_write_space() call. * * Note that we reach sctp_wake_up_waiters() only when * associations free up queued chunks, thus we are under * lock and the list of associations on a socket is * guaranteed not to change. */ for (tmp = list_next_entry(tmp, asocs); 1; tmp = list_next_entry(tmp, asocs)) { /* Manually skip the head element. */ if (&tmp->asocs == &((sctp_sk(sk))->ep->asocs)) continue; /* Wake up association. */ __sctp_write_space(tmp); /* We've reached the end. */ if (tmp == asoc) break; } } /* Do accounting for the sndbuf space. * Decrement the used sndbuf space of the corresponding association by the * data size which was just transmitted(freed). */ static void sctp_wfree(struct sk_buff *skb) { struct sctp_chunk *chunk = skb_shinfo(skb)->destructor_arg; struct sctp_association *asoc = chunk->asoc; struct sock *sk = asoc->base.sk; sk_mem_uncharge(sk, skb->truesize); sk_wmem_queued_add(sk, -(skb->truesize + sizeof(struct sctp_chunk))); asoc->sndbuf_used -= skb->truesize + sizeof(struct sctp_chunk); WARN_ON(refcount_sub_and_test(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc)); if (chunk->shkey) { struct sctp_shared_key *shkey = chunk->shkey; /* refcnt == 2 and !list_empty mean after this release, it's * not being used anywhere, and it's time to notify userland * that this shkey can be freed if it's been deactivated. */ if (shkey->deactivated && !list_empty(&shkey->key_list) && refcount_read(&shkey->refcnt) == 2) { struct sctp_ulpevent *ev; ev = sctp_ulpevent_make_authkey(asoc, shkey->key_id, SCTP_AUTH_FREE_KEY, GFP_KERNEL); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } sctp_auth_shkey_release(chunk->shkey); } sock_wfree(skb); sctp_wake_up_waiters(sk, asoc); sctp_association_put(asoc); } /* Do accounting for the receive space on the socket. * Accounting for the association is done in ulpevent.c * We set this as a destructor for the cloned data skbs so that * accounting is done at the correct time. */ void sctp_sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct sctp_ulpevent *event = sctp_skb2event(skb); atomic_sub(event->rmem_len, &sk->sk_rmem_alloc); /* * Mimic the behavior of sock_rfree */ sk_mem_uncharge(sk, event->rmem_len); } /* Helper function to wait for space in the sndbuf. */ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, size_t msg_len) { struct sock *sk = asoc->base.sk; long current_timeo = *timeo_p; DEFINE_WAIT(wait); int err = 0; pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc, *timeo_p, msg_len); /* Increment the association's refcnt. */ sctp_association_hold(asoc); /* Wait on the association specific sndbuf space. */ for (;;) { prepare_to_wait_exclusive(&asoc->wait, &wait, TASK_INTERRUPTIBLE); if (asoc->base.dead) goto do_dead; if (!*timeo_p) goto do_nonblock; if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING) goto do_error; if (signal_pending(current)) goto do_interrupted; if (sk_under_memory_pressure(sk)) sk_mem_reclaim(sk); if ((int)msg_len <= sctp_wspace(asoc) && sk_wmem_schedule(sk, msg_len)) break; /* Let another process have a go. Since we are going * to sleep anyway. */ release_sock(sk); current_timeo = schedule_timeout(current_timeo); lock_sock(sk); if (sk != asoc->base.sk) goto do_error; *timeo_p = current_timeo; } out: finish_wait(&asoc->wait, &wait); /* Release the association's refcnt. */ sctp_association_put(asoc); return err; do_dead: err = -ESRCH; goto out; do_error: err = -EPIPE; goto out; do_interrupted: err = sock_intr_errno(*timeo_p); goto out; do_nonblock: err = -EAGAIN; goto out; } void sctp_data_ready(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLRDNORM | EPOLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } /* If socket sndbuf has changed, wake up all per association waiters. */ void sctp_write_space(struct sock *sk) { struct sctp_association *asoc; /* Wake up the tasks in each wait queue. */ list_for_each_entry(asoc, &((sctp_sk(sk))->ep->asocs), asocs) { __sctp_write_space(asoc); } } /* Is there any sndbuf space available on the socket? * * Note that sk_wmem_alloc is the sum of the send buffers on all of the * associations on the same socket. For a UDP-style socket with * multiple associations, it is possible for it to be "unwriteable" * prematurely. I assume that this is acceptable because * a premature "unwriteable" is better than an accidental "writeable" which * would cause an unwanted block under certain circumstances. For the 1-1 * UDP-style sockets or TCP-style sockets, this code should work. * - Daisy */ static bool sctp_writeable(const struct sock *sk) { return READ_ONCE(sk->sk_sndbuf) > READ_ONCE(sk->sk_wmem_queued); } /* Wait for an association to go into ESTABLISHED state. If timeout is 0, * returns immediately with EINPROGRESS. */ static int sctp_wait_for_connect(struct sctp_association *asoc, long *timeo_p) { struct sock *sk = asoc->base.sk; int err = 0; long current_timeo = *timeo_p; DEFINE_WAIT(wait); pr_debug("%s: asoc:%p, timeo:%ld\n", __func__, asoc, *timeo_p); /* Increment the association's refcnt. */ sctp_association_hold(asoc); for (;;) { prepare_to_wait_exclusive(&asoc->wait, &wait, TASK_INTERRUPTIBLE); if (!*timeo_p) goto do_nonblock; if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING || asoc->base.dead) goto do_error; if (signal_pending(current)) goto do_interrupted; if (sctp_state(asoc, ESTABLISHED)) break; /* Let another process have a go. Since we are going * to sleep anyway. */ release_sock(sk); current_timeo = schedule_timeout(current_timeo); lock_sock(sk); *timeo_p = current_timeo; } out: finish_wait(&asoc->wait, &wait); /* Release the association's refcnt. */ sctp_association_put(asoc); return err; do_error: if (asoc->init_err_counter + 1 > asoc->max_init_attempts) err = -ETIMEDOUT; else err = -ECONNREFUSED; goto out; do_interrupted: err = sock_intr_errno(*timeo_p); goto out; do_nonblock: err = -EINPROGRESS; goto out; } static int sctp_wait_for_accept(struct sock *sk, long timeo) { struct sctp_endpoint *ep; int err = 0; DEFINE_WAIT(wait); ep = sctp_sk(sk)->ep; for (;;) { prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (list_empty(&ep->asocs)) { release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); } err = -EINVAL; if (!sctp_sstate(sk, LISTENING)) break; err = 0; if (!list_empty(&ep->asocs)) break; err = sock_intr_errno(timeo); if (signal_pending(current)) break; err = -EAGAIN; if (!timeo) break; } finish_wait(sk_sleep(sk), &wait); return err; } static void sctp_wait_for_close(struct sock *sk, long timeout) { DEFINE_WAIT(wait); do { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (list_empty(&sctp_sk(sk)->ep->asocs)) break; release_sock(sk); timeout = schedule_timeout(timeout); lock_sock(sk); } while (!signal_pending(current) && timeout); finish_wait(sk_sleep(sk), &wait); } static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk) { struct sk_buff *frag; if (!skb->data_len) goto done; /* Don't forget the fragments. */ skb_walk_frags(skb, frag) sctp_skb_set_owner_r_frag(frag, sk); done: sctp_skb_set_owner_r(skb, sk); } void sctp_copy_sock(struct sock *newsk, struct sock *sk, struct sctp_association *asoc) { struct inet_sock *inet = inet_sk(sk); struct inet_sock *newinet; struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; newsk->sk_type = sk->sk_type; newsk->sk_bound_dev_if = sk->sk_bound_dev_if; newsk->sk_flags = sk->sk_flags; newsk->sk_tsflags = sk->sk_tsflags; newsk->sk_no_check_tx = sk->sk_no_check_tx; newsk->sk_no_check_rx = sk->sk_no_check_rx; newsk->sk_reuse = sk->sk_reuse; sctp_sk(newsk)->reuse = sp->reuse; newsk->sk_shutdown = sk->sk_shutdown; newsk->sk_destruct = sk->sk_destruct; newsk->sk_family = sk->sk_family; newsk->sk_protocol = IPPROTO_SCTP; newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; newsk->sk_sndbuf = sk->sk_sndbuf; newsk->sk_rcvbuf = sk->sk_rcvbuf; newsk->sk_lingertime = sk->sk_lingertime; newsk->sk_rcvtimeo = sk->sk_rcvtimeo; newsk->sk_sndtimeo = sk->sk_sndtimeo; newsk->sk_rxhash = sk->sk_rxhash; newinet = inet_sk(newsk); /* Initialize sk's sport, dport, rcv_saddr and daddr for * getsockname() and getpeername() */ newinet->inet_sport = inet->inet_sport; newinet->inet_saddr = inet->inet_saddr; newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; newinet->inet_id = prandom_u32(); newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; newinet->mc_ttl = 1; newinet->mc_index = 0; newinet->mc_list = NULL; if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); /* Set newsk security attributes from original sk and connection * security attribute from ep. */ security_sctp_sk_clone(ep, sk, newsk); } static inline void sctp_copy_descendant(struct sock *sk_to, const struct sock *sk_from) { size_t ancestor_size = sizeof(struct inet_sock); ancestor_size += sk_from->sk_prot->obj_size; ancestor_size -= offsetof(struct sctp_sock, pd_lobby); __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); } /* Populate the fields of the newsk from the oldsk and migrate the assoc * and its messages to the newsk. */ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sctp_association *assoc, enum sctp_socket_type type) { struct sctp_sock *oldsp = sctp_sk(oldsk); struct sctp_sock *newsp = sctp_sk(newsk); struct sctp_bind_bucket *pp; /* hash list port iterator */ struct sctp_endpoint *newep = newsp->ep; struct sk_buff *skb, *tmp; struct sctp_ulpevent *event; struct sctp_bind_hashbucket *head; int err; /* Migrate socket buffer sizes and all the socket level options to the * new socket. */ newsk->sk_sndbuf = oldsk->sk_sndbuf; newsk->sk_rcvbuf = oldsk->sk_rcvbuf; /* Brute force copy old sctp opt. */ sctp_copy_descendant(newsk, oldsk); /* Restore the ep value that was overwritten with the above structure * copy. */ newsp->ep = newep; newsp->hmac = NULL; /* Hook this new socket in to the bind_hash list. */ head = &sctp_port_hashtable[sctp_phashfn(sock_net(oldsk), inet_sk(oldsk)->inet_num)]; spin_lock_bh(&head->lock); pp = sctp_sk(oldsk)->bind_hash; sk_add_bind_node(newsk, &pp->owner); sctp_sk(newsk)->bind_hash = pp; inet_sk(newsk)->inet_num = inet_sk(oldsk)->inet_num; spin_unlock_bh(&head->lock); /* Copy the bind_addr list from the original endpoint to the new * endpoint so that we can handle restarts properly */ err = sctp_bind_addr_dup(&newsp->ep->base.bind_addr, &oldsp->ep->base.bind_addr, GFP_KERNEL); if (err) return err; /* New ep's auth_hmacs should be set if old ep's is set, in case * that net->sctp.auth_enable has been changed to 0 by users and * new ep's auth_hmacs couldn't be set in sctp_endpoint_init(). */ if (oldsp->ep->auth_hmacs) { err = sctp_auth_init_hmacs(newsp->ep, GFP_KERNEL); if (err) return err; } sctp_auto_asconf_init(newsp); /* Move any messages in the old socket's receive queue that are for the * peeled off association to the new socket's receive queue. */ sctp_skb_for_each(skb, &oldsk->sk_receive_queue, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { __skb_unlink(skb, &oldsk->sk_receive_queue); __skb_queue_tail(&newsk->sk_receive_queue, skb); sctp_skb_set_owner_r_frag(skb, newsk); } } /* Clean up any messages pending delivery due to partial * delivery. Three cases: * 1) No partial deliver; no work. * 2) Peeling off partial delivery; keep pd_lobby in new pd_lobby. * 3) Peeling off non-partial delivery; move pd_lobby to receive_queue. */ atomic_set(&sctp_sk(newsk)->pd_mode, assoc->ulpq.pd_mode); if (atomic_read(&sctp_sk(oldsk)->pd_mode)) { struct sk_buff_head *queue; /* Decide which queue to move pd_lobby skbs to. */ if (assoc->ulpq.pd_mode) { queue = &newsp->pd_lobby; } else queue = &newsk->sk_receive_queue; /* Walk through the pd_lobby, looking for skbs that * need moved to the new socket. */ sctp_skb_for_each(skb, &oldsp->pd_lobby, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { __skb_unlink(skb, &oldsp->pd_lobby); __skb_queue_tail(queue, skb); sctp_skb_set_owner_r_frag(skb, newsk); } } /* Clear up any skbs waiting for the partial * delivery to finish. */ if (assoc->ulpq.pd_mode) sctp_clear_pd(oldsk, NULL); } sctp_for_each_rx_skb(assoc, newsk, sctp_skb_set_owner_r_frag); /* Set the type of socket to indicate that it is peeled off from the * original UDP-style socket or created with the accept() call on a * TCP-style socket.. */ newsp->type = type; /* Mark the new socket "in-use" by the user so that any packets * that may arrive on the association after we've moved it are * queued to the backlog. This prevents a potential race between * backlog processing on the old socket and new-packet processing * on the new socket. * * The caller has just allocated newsk so we can guarantee that other * paths won't try to lock it and then oldsk. */ lock_sock_nested(newsk, SINGLE_DEPTH_NESTING); sctp_for_each_tx_datachunk(assoc, true, sctp_clear_owner_w); sctp_assoc_migrate(assoc, newsk); sctp_for_each_tx_datachunk(assoc, false, sctp_set_owner_w); /* If the association on the newsk is already closed before accept() * is called, set RCV_SHUTDOWN flag. */ if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP)) { inet_sk_set_state(newsk, SCTP_SS_CLOSED); newsk->sk_shutdown |= RCV_SHUTDOWN; } else { inet_sk_set_state(newsk, SCTP_SS_ESTABLISHED); } release_sock(newsk); return 0; } /* This proto struct describes the ULP interface for SCTP. */ struct proto sctp_prot = { .name = "SCTP", .owner = THIS_MODULE, .close = sctp_close, .disconnect = sctp_disconnect, .accept = sctp_accept, .ioctl = sctp_ioctl, .init = sctp_init_sock, .destroy = sctp_destroy_sock, .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, .bind_add = sctp_bind_add, .backlog_rcv = sctp_backlog_rcv, .hash = sctp_hash, .unhash = sctp_unhash, .no_autobind = true, .obj_size = sizeof(struct sctp_sock), .useroffset = offsetof(struct sctp_sock, subscribe), .usersize = offsetof(struct sctp_sock, initmsg) - offsetof(struct sctp_sock, subscribe) + sizeof_field(struct sctp_sock, initmsg), .sysctl_mem = sysctl_sctp_mem, .sysctl_rmem = sysctl_sctp_rmem, .sysctl_wmem = sysctl_sctp_wmem, .memory_pressure = &sctp_memory_pressure, .enter_memory_pressure = sctp_enter_memory_pressure, .memory_allocated = &sctp_memory_allocated, .sockets_allocated = &sctp_sockets_allocated, }; #if IS_ENABLED(CONFIG_IPV6) static void sctp_v6_destruct_sock(struct sock *sk) { sctp_destruct_common(sk); inet6_sock_destruct(sk); } static int sctp_v6_init_sock(struct sock *sk) { int ret = sctp_init_sock(sk); if (!ret) sk->sk_destruct = sctp_v6_destruct_sock; return ret; } struct proto sctpv6_prot = { .name = "SCTPv6", .owner = THIS_MODULE, .close = sctp_close, .disconnect = sctp_disconnect, .accept = sctp_accept, .ioctl = sctp_ioctl, .init = sctp_v6_init_sock, .destroy = sctp_destroy_sock, .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, .bind_add = sctp_bind_add, .backlog_rcv = sctp_backlog_rcv, .hash = sctp_hash, .unhash = sctp_unhash, .no_autobind = true, .obj_size = sizeof(struct sctp6_sock), .useroffset = offsetof(struct sctp6_sock, sctp.subscribe), .usersize = offsetof(struct sctp6_sock, sctp.initmsg) - offsetof(struct sctp6_sock, sctp.subscribe) + sizeof_field(struct sctp6_sock, sctp.initmsg), .sysctl_mem = sysctl_sctp_mem, .sysctl_rmem = sysctl_sctp_rmem, .sysctl_wmem = sysctl_sctp_wmem, .memory_pressure = &sctp_memory_pressure, .enter_memory_pressure = sctp_enter_memory_pressure, .memory_allocated = &sctp_memory_allocated, .sockets_allocated = &sctp_sockets_allocated, }; #endif /* IS_ENABLED(CONFIG_IPV6) */ |
| 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen */ #include "network-coding.h" #include "main.h" #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/byteorder/generic.h> #include <linux/compiler.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if_ether.h> #include <linux/if_packet.h> #include <linux/init.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/prandom.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/workqueue.h> #include <uapi/linux/batadv_packet.h> #include "hash.h" #include "log.h" #include "originator.h" #include "routing.h" #include "send.h" #include "tvlv.h" static struct lock_class_key batadv_nc_coding_hash_lock_class_key; static struct lock_class_key batadv_nc_decoding_hash_lock_class_key; static void batadv_nc_worker(struct work_struct *work); static int batadv_nc_recv_coded_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); /** * batadv_nc_init() - one-time initialization for network coding * * Return: 0 on success or negative error number in case of failure */ int __init batadv_nc_init(void) { int ret; /* Register our packet type */ ret = batadv_recv_handler_register(BATADV_CODED, batadv_nc_recv_coded_packet); return ret; } /** * batadv_nc_start_timer() - initialise the nc periodic worker * @bat_priv: the bat priv with all the soft interface information */ static void batadv_nc_start_timer(struct batadv_priv *bat_priv) { queue_delayed_work(batadv_event_workqueue, &bat_priv->nc.work, msecs_to_jiffies(10)); } /** * batadv_nc_tvlv_container_update() - update the network coding tvlv container * after network coding setting change * @bat_priv: the bat priv with all the soft interface information */ static void batadv_nc_tvlv_container_update(struct batadv_priv *bat_priv) { char nc_mode; nc_mode = atomic_read(&bat_priv->network_coding); switch (nc_mode) { case 0: batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_NC, 1); break; case 1: batadv_tvlv_container_register(bat_priv, BATADV_TVLV_NC, 1, NULL, 0); break; } } /** * batadv_nc_status_update() - update the network coding tvlv container after * network coding setting change * @net_dev: the soft interface net device */ void batadv_nc_status_update(struct net_device *net_dev) { struct batadv_priv *bat_priv = netdev_priv(net_dev); batadv_nc_tvlv_container_update(bat_priv); } /** * batadv_nc_tvlv_ogm_handler_v1() - process incoming nc tvlv container * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node of the ogm * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags) * @tvlv_value: tvlv buffer containing the gateway data * @tvlv_value_len: tvlv buffer length */ static void batadv_nc_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 flags, void *tvlv_value, u16 tvlv_value_len) { if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) clear_bit(BATADV_ORIG_CAPA_HAS_NC, &orig->capabilities); else set_bit(BATADV_ORIG_CAPA_HAS_NC, &orig->capabilities); } /** * batadv_nc_mesh_init() - initialise coding hash table and start housekeeping * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success or negative error number in case of failure */ int batadv_nc_mesh_init(struct batadv_priv *bat_priv) { bat_priv->nc.timestamp_fwd_flush = jiffies; bat_priv->nc.timestamp_sniffed_purge = jiffies; if (bat_priv->nc.coding_hash || bat_priv->nc.decoding_hash) return 0; bat_priv->nc.coding_hash = batadv_hash_new(128); if (!bat_priv->nc.coding_hash) goto err; batadv_hash_set_lock_class(bat_priv->nc.coding_hash, &batadv_nc_coding_hash_lock_class_key); bat_priv->nc.decoding_hash = batadv_hash_new(128); if (!bat_priv->nc.decoding_hash) { batadv_hash_destroy(bat_priv->nc.coding_hash); goto err; } batadv_hash_set_lock_class(bat_priv->nc.decoding_hash, &batadv_nc_decoding_hash_lock_class_key); INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker); batadv_nc_start_timer(bat_priv); batadv_tvlv_handler_register(bat_priv, batadv_nc_tvlv_ogm_handler_v1, NULL, BATADV_TVLV_NC, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); batadv_nc_tvlv_container_update(bat_priv); return 0; err: return -ENOMEM; } /** * batadv_nc_init_bat_priv() - initialise the nc specific bat_priv variables * @bat_priv: the bat priv with all the soft interface information */ void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv) { atomic_set(&bat_priv->network_coding, 0); bat_priv->nc.min_tq = 200; bat_priv->nc.max_fwd_delay = 10; bat_priv->nc.max_buffer_time = 200; } /** * batadv_nc_init_orig() - initialise the nc fields of an orig_node * @orig_node: the orig_node which is going to be initialised */ void batadv_nc_init_orig(struct batadv_orig_node *orig_node) { INIT_LIST_HEAD(&orig_node->in_coding_list); INIT_LIST_HEAD(&orig_node->out_coding_list); spin_lock_init(&orig_node->in_coding_list_lock); spin_lock_init(&orig_node->out_coding_list_lock); } /** * batadv_nc_node_release() - release nc_node from lists and queue for free * after rcu grace period * @ref: kref pointer of the nc_node */ static void batadv_nc_node_release(struct kref *ref) { struct batadv_nc_node *nc_node; nc_node = container_of(ref, struct batadv_nc_node, refcount); batadv_orig_node_put(nc_node->orig_node); kfree_rcu(nc_node, rcu); } /** * batadv_nc_node_put() - decrement the nc_node refcounter and possibly * release it * @nc_node: nc_node to be free'd */ static void batadv_nc_node_put(struct batadv_nc_node *nc_node) { if (!nc_node) return; kref_put(&nc_node->refcount, batadv_nc_node_release); } /** * batadv_nc_path_release() - release nc_path from lists and queue for free * after rcu grace period * @ref: kref pointer of the nc_path */ static void batadv_nc_path_release(struct kref *ref) { struct batadv_nc_path *nc_path; nc_path = container_of(ref, struct batadv_nc_path, refcount); kfree_rcu(nc_path, rcu); } /** * batadv_nc_path_put() - decrement the nc_path refcounter and possibly * release it * @nc_path: nc_path to be free'd */ static void batadv_nc_path_put(struct batadv_nc_path *nc_path) { if (!nc_path) return; kref_put(&nc_path->refcount, batadv_nc_path_release); } /** * batadv_nc_packet_free() - frees nc packet * @nc_packet: the nc packet to free * @dropped: whether the packet is freed because is dropped */ static void batadv_nc_packet_free(struct batadv_nc_packet *nc_packet, bool dropped) { if (dropped) kfree_skb(nc_packet->skb); else consume_skb(nc_packet->skb); batadv_nc_path_put(nc_packet->nc_path); kfree(nc_packet); } /** * batadv_nc_to_purge_nc_node() - checks whether an nc node has to be purged * @bat_priv: the bat priv with all the soft interface information * @nc_node: the nc node to check * * Return: true if the entry has to be purged now, false otherwise */ static bool batadv_nc_to_purge_nc_node(struct batadv_priv *bat_priv, struct batadv_nc_node *nc_node) { if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) return true; return batadv_has_timed_out(nc_node->last_seen, BATADV_NC_NODE_TIMEOUT); } /** * batadv_nc_to_purge_nc_path_coding() - checks whether an nc path has timed out * @bat_priv: the bat priv with all the soft interface information * @nc_path: the nc path to check * * Return: true if the entry has to be purged now, false otherwise */ static bool batadv_nc_to_purge_nc_path_coding(struct batadv_priv *bat_priv, struct batadv_nc_path *nc_path) { if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) return true; /* purge the path when no packets has been added for 10 times the * max_fwd_delay time */ return batadv_has_timed_out(nc_path->last_valid, bat_priv->nc.max_fwd_delay * 10); } /** * batadv_nc_to_purge_nc_path_decoding() - checks whether an nc path has timed * out * @bat_priv: the bat priv with all the soft interface information * @nc_path: the nc path to check * * Return: true if the entry has to be purged now, false otherwise */ static bool batadv_nc_to_purge_nc_path_decoding(struct batadv_priv *bat_priv, struct batadv_nc_path *nc_path) { if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) return true; /* purge the path when no packets has been added for 10 times the * max_buffer time */ return batadv_has_timed_out(nc_path->last_valid, bat_priv->nc.max_buffer_time * 10); } /** * batadv_nc_purge_orig_nc_nodes() - go through list of nc nodes and purge stale * entries * @bat_priv: the bat priv with all the soft interface information * @list: list of nc nodes * @lock: nc node list lock * @to_purge: function in charge to decide whether an entry has to be purged or * not. This function takes the nc node as argument and has to return * a boolean value: true if the entry has to be deleted, false * otherwise */ static void batadv_nc_purge_orig_nc_nodes(struct batadv_priv *bat_priv, struct list_head *list, spinlock_t *lock, bool (*to_purge)(struct batadv_priv *, struct batadv_nc_node *)) { struct batadv_nc_node *nc_node, *nc_node_tmp; /* For each nc_node in list */ spin_lock_bh(lock); list_for_each_entry_safe(nc_node, nc_node_tmp, list, list) { /* if an helper function has been passed as parameter, * ask it if the entry has to be purged or not */ if (to_purge && !to_purge(bat_priv, nc_node)) continue; batadv_dbg(BATADV_DBG_NC, bat_priv, "Removing nc_node %pM -> %pM\n", nc_node->addr, nc_node->orig_node->orig); list_del_rcu(&nc_node->list); batadv_nc_node_put(nc_node); } spin_unlock_bh(lock); } /** * batadv_nc_purge_orig() - purges all nc node data attached of the given * originator * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig_node with the nc node entries to be purged * @to_purge: function in charge to decide whether an entry has to be purged or * not. This function takes the nc node as argument and has to return * a boolean value: true is the entry has to be deleted, false * otherwise */ void batadv_nc_purge_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, bool (*to_purge)(struct batadv_priv *, struct batadv_nc_node *)) { /* Check ingoing nc_node's of this orig_node */ batadv_nc_purge_orig_nc_nodes(bat_priv, &orig_node->in_coding_list, &orig_node->in_coding_list_lock, to_purge); /* Check outgoing nc_node's of this orig_node */ batadv_nc_purge_orig_nc_nodes(bat_priv, &orig_node->out_coding_list, &orig_node->out_coding_list_lock, to_purge); } /** * batadv_nc_purge_orig_hash() - traverse entire originator hash to check if * they have timed out nc nodes * @bat_priv: the bat priv with all the soft interface information */ static void batadv_nc_purge_orig_hash(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; struct batadv_orig_node *orig_node; u32 i; if (!hash) return; /* For each orig_node */ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) batadv_nc_purge_orig(bat_priv, orig_node, batadv_nc_to_purge_nc_node); rcu_read_unlock(); } } /** * batadv_nc_purge_paths() - traverse all nc paths part of the hash and remove * unused ones * @bat_priv: the bat priv with all the soft interface information * @hash: hash table containing the nc paths to check * @to_purge: function in charge to decide whether an entry has to be purged or * not. This function takes the nc node as argument and has to return * a boolean value: true is the entry has to be deleted, false * otherwise */ static void batadv_nc_purge_paths(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, bool (*to_purge)(struct batadv_priv *, struct batadv_nc_path *)) { struct hlist_head *head; struct hlist_node *node_tmp; struct batadv_nc_path *nc_path; spinlock_t *lock; /* Protects lists in hash */ u32 i; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; lock = &hash->list_locks[i]; /* For each nc_path in this bin */ spin_lock_bh(lock); hlist_for_each_entry_safe(nc_path, node_tmp, head, hash_entry) { /* if an helper function has been passed as parameter, * ask it if the entry has to be purged or not */ if (to_purge && !to_purge(bat_priv, nc_path)) continue; /* purging an non-empty nc_path should never happen, but * is observed under high CPU load. Delay the purging * until next iteration to allow the packet_list to be * emptied first. */ if (!unlikely(list_empty(&nc_path->packet_list))) { net_ratelimited_function(printk, KERN_WARNING "Skipping free of non-empty nc_path (%pM -> %pM)!\n", nc_path->prev_hop, nc_path->next_hop); continue; } /* nc_path is unused, so remove it */ batadv_dbg(BATADV_DBG_NC, bat_priv, "Remove nc_path %pM -> %pM\n", nc_path->prev_hop, nc_path->next_hop); hlist_del_rcu(&nc_path->hash_entry); batadv_nc_path_put(nc_path); } spin_unlock_bh(lock); } } /** * batadv_nc_hash_key_gen() - computes the nc_path hash key * @key: buffer to hold the final hash key * @src: source ethernet mac address going into the hash key * @dst: destination ethernet mac address going into the hash key */ static void batadv_nc_hash_key_gen(struct batadv_nc_path *key, const char *src, const char *dst) { memcpy(key->prev_hop, src, sizeof(key->prev_hop)); memcpy(key->next_hop, dst, sizeof(key->next_hop)); } /** * batadv_nc_hash_choose() - compute the hash value for an nc path * @data: data to hash * @size: size of the hash table * * Return: the selected index in the hash table for the given data. */ static u32 batadv_nc_hash_choose(const void *data, u32 size) { const struct batadv_nc_path *nc_path = data; u32 hash = 0; hash = jhash(&nc_path->prev_hop, sizeof(nc_path->prev_hop), hash); hash = jhash(&nc_path->next_hop, sizeof(nc_path->next_hop), hash); return hash % size; } /** * batadv_nc_hash_compare() - comparing function used in the network coding hash * tables * @node: node in the local table * @data2: second object to compare the node to * * Return: true if the two entry are the same, false otherwise */ static bool batadv_nc_hash_compare(const struct hlist_node *node, const void *data2) { const struct batadv_nc_path *nc_path1, *nc_path2; nc_path1 = container_of(node, struct batadv_nc_path, hash_entry); nc_path2 = data2; /* Return 1 if the two keys are identical */ if (!batadv_compare_eth(nc_path1->prev_hop, nc_path2->prev_hop)) return false; if (!batadv_compare_eth(nc_path1->next_hop, nc_path2->next_hop)) return false; return true; } /** * batadv_nc_hash_find() - search for an existing nc path and return it * @hash: hash table containing the nc path * @data: search key * * Return: the nc_path if found, NULL otherwise. */ static struct batadv_nc_path * batadv_nc_hash_find(struct batadv_hashtable *hash, void *data) { struct hlist_head *head; struct batadv_nc_path *nc_path, *nc_path_tmp = NULL; int index; if (!hash) return NULL; index = batadv_nc_hash_choose(data, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(nc_path, head, hash_entry) { if (!batadv_nc_hash_compare(&nc_path->hash_entry, data)) continue; if (!kref_get_unless_zero(&nc_path->refcount)) continue; nc_path_tmp = nc_path; break; } rcu_read_unlock(); return nc_path_tmp; } /** * batadv_nc_send_packet() - send non-coded packet and free nc_packet struct * @nc_packet: the nc packet to send */ static void batadv_nc_send_packet(struct batadv_nc_packet *nc_packet) { batadv_send_unicast_skb(nc_packet->skb, nc_packet->neigh_node); nc_packet->skb = NULL; batadv_nc_packet_free(nc_packet, false); } /** * batadv_nc_sniffed_purge() - Checks timestamp of given sniffed nc_packet. * @bat_priv: the bat priv with all the soft interface information * @nc_path: the nc path the packet belongs to * @nc_packet: the nc packet to be checked * * Checks whether the given sniffed (overheard) nc_packet has hit its buffering * timeout. If so, the packet is no longer kept and the entry deleted from the * queue. Has to be called with the appropriate locks. * * Return: false as soon as the entry in the fifo queue has not been timed out * yet and true otherwise. */ static bool batadv_nc_sniffed_purge(struct batadv_priv *bat_priv, struct batadv_nc_path *nc_path, struct batadv_nc_packet *nc_packet) { unsigned long timeout = bat_priv->nc.max_buffer_time; bool res = false; lockdep_assert_held(&nc_path->packet_list_lock); /* Packets are added to tail, so the remaining packets did not time * out and we can stop processing the current queue */ if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE && !batadv_has_timed_out(nc_packet->timestamp, timeout)) goto out; /* purge nc packet */ list_del(&nc_packet->list); batadv_nc_packet_free(nc_packet, true); res = true; out: return res; } /** * batadv_nc_fwd_flush() - Checks the timestamp of the given nc packet. * @bat_priv: the bat priv with all the soft interface information * @nc_path: the nc path the packet belongs to * @nc_packet: the nc packet to be checked * * Checks whether the given nc packet has hit its forward timeout. If so, the * packet is no longer delayed, immediately sent and the entry deleted from the * queue. Has to be called with the appropriate locks. * * Return: false as soon as the entry in the fifo queue has not been timed out * yet and true otherwise. */ static bool batadv_nc_fwd_flush(struct batadv_priv *bat_priv, struct batadv_nc_path *nc_path, struct batadv_nc_packet *nc_packet) { unsigned long timeout = bat_priv->nc.max_fwd_delay; lockdep_assert_held(&nc_path->packet_list_lock); /* Packets are added to tail, so the remaining packets did not time * out and we can stop processing the current queue */ if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE && !batadv_has_timed_out(nc_packet->timestamp, timeout)) return false; /* Send packet */ batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD); batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES, nc_packet->skb->len + ETH_HLEN); list_del(&nc_packet->list); batadv_nc_send_packet(nc_packet); return true; } /** * batadv_nc_process_nc_paths() - traverse given nc packet pool and free timed * out nc packets * @bat_priv: the bat priv with all the soft interface information * @hash: to be processed hash table * @process_fn: Function called to process given nc packet. Should return true * to encourage this function to proceed with the next packet. * Otherwise the rest of the current queue is skipped. */ static void batadv_nc_process_nc_paths(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, bool (*process_fn)(struct batadv_priv *, struct batadv_nc_path *, struct batadv_nc_packet *)) { struct hlist_head *head; struct batadv_nc_packet *nc_packet, *nc_packet_tmp; struct batadv_nc_path *nc_path; bool ret; int i; if (!hash) return; /* Loop hash table bins */ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; /* Loop coding paths */ rcu_read_lock(); hlist_for_each_entry_rcu(nc_path, head, hash_entry) { /* Loop packets */ spin_lock_bh(&nc_path->packet_list_lock); list_for_each_entry_safe(nc_packet, nc_packet_tmp, &nc_path->packet_list, list) { ret = process_fn(bat_priv, nc_path, nc_packet); if (!ret) break; } spin_unlock_bh(&nc_path->packet_list_lock); } rcu_read_unlock(); } } /** * batadv_nc_worker() - periodic task for housekeeping related to network * coding * @work: kernel work struct */ static void batadv_nc_worker(struct work_struct *work) { struct delayed_work *delayed_work; struct batadv_priv_nc *priv_nc; struct batadv_priv *bat_priv; unsigned long timeout; delayed_work = to_delayed_work(work); priv_nc = container_of(delayed_work, struct batadv_priv_nc, work); bat_priv = container_of(priv_nc, struct batadv_priv, nc); batadv_nc_purge_orig_hash(bat_priv); batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, batadv_nc_to_purge_nc_path_coding); batadv_nc_purge_paths(bat_priv, bat_priv->nc.decoding_hash, batadv_nc_to_purge_nc_path_decoding); timeout = bat_priv->nc.max_fwd_delay; if (batadv_has_timed_out(bat_priv->nc.timestamp_fwd_flush, timeout)) { batadv_nc_process_nc_paths(bat_priv, bat_priv->nc.coding_hash, batadv_nc_fwd_flush); bat_priv->nc.timestamp_fwd_flush = jiffies; } if (batadv_has_timed_out(bat_priv->nc.timestamp_sniffed_purge, bat_priv->nc.max_buffer_time)) { batadv_nc_process_nc_paths(bat_priv, bat_priv->nc.decoding_hash, batadv_nc_sniffed_purge); bat_priv->nc.timestamp_sniffed_purge = jiffies; } /* Schedule a new check */ batadv_nc_start_timer(bat_priv); } /** * batadv_can_nc_with_orig() - checks whether the given orig node is suitable * for coding or not * @bat_priv: the bat priv with all the soft interface information * @orig_node: neighboring orig node which may be used as nc candidate * @ogm_packet: incoming ogm packet also used for the checks * * Return: true if: * 1) The OGM must have the most recent sequence number. * 2) The TTL must be decremented by one and only one. * 3) The OGM must be received from the first hop from orig_node. * 4) The TQ value of the OGM must be above bat_priv->nc.min_tq. */ static bool batadv_can_nc_with_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_ogm_packet *ogm_packet) { struct batadv_orig_ifinfo *orig_ifinfo; u32 last_real_seqno; u8 last_ttl; orig_ifinfo = batadv_orig_ifinfo_get(orig_node, BATADV_IF_DEFAULT); if (!orig_ifinfo) return false; last_ttl = orig_ifinfo->last_ttl; last_real_seqno = orig_ifinfo->last_real_seqno; batadv_orig_ifinfo_put(orig_ifinfo); if (last_real_seqno != ntohl(ogm_packet->seqno)) return false; if (last_ttl != ogm_packet->ttl + 1) return false; if (!batadv_compare_eth(ogm_packet->orig, ogm_packet->prev_sender)) return false; if (ogm_packet->tq < bat_priv->nc.min_tq) return false; return true; } /** * batadv_nc_find_nc_node() - search for an existing nc node and return it * @orig_node: orig node originating the ogm packet * @orig_neigh_node: neighboring orig node from which we received the ogm packet * (can be equal to orig_node) * @in_coding: traverse incoming or outgoing network coding list * * Return: the nc_node if found, NULL otherwise. */ static struct batadv_nc_node * batadv_nc_find_nc_node(struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, bool in_coding) { struct batadv_nc_node *nc_node, *nc_node_out = NULL; struct list_head *list; if (in_coding) list = &orig_neigh_node->in_coding_list; else list = &orig_neigh_node->out_coding_list; /* Traverse list of nc_nodes to orig_node */ rcu_read_lock(); list_for_each_entry_rcu(nc_node, list, list) { if (!batadv_compare_eth(nc_node->addr, orig_node->orig)) continue; if (!kref_get_unless_zero(&nc_node->refcount)) continue; /* Found a match */ nc_node_out = nc_node; break; } rcu_read_unlock(); return nc_node_out; } /** * batadv_nc_get_nc_node() - retrieves an nc node or creates the entry if it was * not found * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node originating the ogm packet * @orig_neigh_node: neighboring orig node from which we received the ogm packet * (can be equal to orig_node) * @in_coding: traverse incoming or outgoing network coding list * * Return: the nc_node if found or created, NULL in case of an error. */ static struct batadv_nc_node * batadv_nc_get_nc_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, bool in_coding) { struct batadv_nc_node *nc_node; spinlock_t *lock; /* Used to lock list selected by "int in_coding" */ struct list_head *list; /* Select ingoing or outgoing coding node */ if (in_coding) { lock = &orig_neigh_node->in_coding_list_lock; list = &orig_neigh_node->in_coding_list; } else { lock = &orig_neigh_node->out_coding_list_lock; list = &orig_neigh_node->out_coding_list; } spin_lock_bh(lock); /* Check if nc_node is already added */ nc_node = batadv_nc_find_nc_node(orig_node, orig_neigh_node, in_coding); /* Node found */ if (nc_node) goto unlock; nc_node = kzalloc(sizeof(*nc_node), GFP_ATOMIC); if (!nc_node) goto unlock; /* Initialize nc_node */ INIT_LIST_HEAD(&nc_node->list); kref_init(&nc_node->refcount); ether_addr_copy(nc_node->addr, orig_node->orig); kref_get(&orig_neigh_node->refcount); nc_node->orig_node = orig_neigh_node; batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_node %pM -> %pM\n", nc_node->addr, nc_node->orig_node->orig); /* Add nc_node to orig_node */ kref_get(&nc_node->refcount); list_add_tail_rcu(&nc_node->list, list); unlock: spin_unlock_bh(lock); return nc_node; } /** * batadv_nc_update_nc_node() - updates stored incoming and outgoing nc node * structs (best called on incoming OGMs) * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node originating the ogm packet * @orig_neigh_node: neighboring orig node from which we received the ogm packet * (can be equal to orig_node) * @ogm_packet: incoming ogm packet * @is_single_hop_neigh: orig_node is a single hop neighbor */ void batadv_nc_update_nc_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, struct batadv_ogm_packet *ogm_packet, int is_single_hop_neigh) { struct batadv_nc_node *in_nc_node = NULL; struct batadv_nc_node *out_nc_node = NULL; /* Check if network coding is enabled */ if (!atomic_read(&bat_priv->network_coding)) goto out; /* check if orig node is network coding enabled */ if (!test_bit(BATADV_ORIG_CAPA_HAS_NC, &orig_node->capabilities)) goto out; /* accept ogms from 'good' neighbors and single hop neighbors */ if (!batadv_can_nc_with_orig(bat_priv, orig_node, ogm_packet) && !is_single_hop_neigh) goto out; /* Add orig_node as in_nc_node on hop */ in_nc_node = batadv_nc_get_nc_node(bat_priv, orig_node, orig_neigh_node, true); if (!in_nc_node) goto out; in_nc_node->last_seen = jiffies; /* Add hop as out_nc_node on orig_node */ out_nc_node = batadv_nc_get_nc_node(bat_priv, orig_neigh_node, orig_node, false); if (!out_nc_node) goto out; out_nc_node->last_seen = jiffies; out: batadv_nc_node_put(in_nc_node); batadv_nc_node_put(out_nc_node); } /** * batadv_nc_get_path() - get existing nc_path or allocate a new one * @bat_priv: the bat priv with all the soft interface information * @hash: hash table containing the nc path * @src: ethernet source address - first half of the nc path search key * @dst: ethernet destination address - second half of the nc path search key * * Return: pointer to nc_path if the path was found or created, returns NULL * on error. */ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, u8 *src, u8 *dst) { int hash_added; struct batadv_nc_path *nc_path, nc_path_key; batadv_nc_hash_key_gen(&nc_path_key, src, dst); /* Search for existing nc_path */ nc_path = batadv_nc_hash_find(hash, (void *)&nc_path_key); if (nc_path) { /* Set timestamp to delay removal of nc_path */ nc_path->last_valid = jiffies; return nc_path; } /* No existing nc_path was found; create a new */ nc_path = kzalloc(sizeof(*nc_path), GFP_ATOMIC); if (!nc_path) return NULL; /* Initialize nc_path */ INIT_LIST_HEAD(&nc_path->packet_list); spin_lock_init(&nc_path->packet_list_lock); kref_init(&nc_path->refcount); nc_path->last_valid = jiffies; ether_addr_copy(nc_path->next_hop, dst); ether_addr_copy(nc_path->prev_hop, src); batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_path %pM -> %pM\n", nc_path->prev_hop, nc_path->next_hop); /* Add nc_path to hash table */ kref_get(&nc_path->refcount); hash_added = batadv_hash_add(hash, batadv_nc_hash_compare, batadv_nc_hash_choose, &nc_path_key, &nc_path->hash_entry); if (hash_added < 0) { kfree(nc_path); return NULL; } return nc_path; } /** * batadv_nc_random_weight_tq() - scale the receivers TQ-value to avoid unfair * selection of a receiver with slightly lower TQ than the other * @tq: to be weighted tq value * * Return: scaled tq value */ static u8 batadv_nc_random_weight_tq(u8 tq) { /* randomize the estimated packet loss (max TQ - estimated TQ) */ u8 rand_tq = prandom_u32_max(BATADV_TQ_MAX_VALUE + 1 - tq); /* convert to (randomized) estimated tq again */ return BATADV_TQ_MAX_VALUE - rand_tq; } /** * batadv_nc_memxor() - XOR destination with source * @dst: byte array to XOR into * @src: byte array to XOR from * @len: length of destination array */ static void batadv_nc_memxor(char *dst, const char *src, unsigned int len) { unsigned int i; for (i = 0; i < len; ++i) dst[i] ^= src[i]; } /** * batadv_nc_code_packets() - code a received unicast_packet with an nc packet * into a coded_packet and send it * @bat_priv: the bat priv with all the soft interface information * @skb: data skb to forward * @ethhdr: pointer to the ethernet header inside the skb * @nc_packet: structure containing the packet to the skb can be coded with * @neigh_node: next hop to forward packet to * * Return: true if both packets are consumed, false otherwise. */ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, struct sk_buff *skb, struct ethhdr *ethhdr, struct batadv_nc_packet *nc_packet, struct batadv_neigh_node *neigh_node) { u8 tq_weighted_neigh, tq_weighted_coding, tq_tmp; struct sk_buff *skb_dest, *skb_src; struct batadv_unicast_packet *packet1; struct batadv_unicast_packet *packet2; struct batadv_coded_packet *coded_packet; struct batadv_neigh_node *neigh_tmp, *router_neigh, *first_dest; struct batadv_neigh_node *router_coding = NULL, *second_dest; struct batadv_neigh_ifinfo *router_neigh_ifinfo = NULL; struct batadv_neigh_ifinfo *router_coding_ifinfo = NULL; u8 *first_source, *second_source; __be32 packet_id1, packet_id2; size_t count; bool res = false; int coding_len; int unicast_size = sizeof(*packet1); int coded_size = sizeof(*coded_packet); int header_add = coded_size - unicast_size; /* TODO: do we need to consider the outgoing interface for * coded packets? */ router_neigh = batadv_orig_router_get(neigh_node->orig_node, BATADV_IF_DEFAULT); if (!router_neigh) goto out; router_neigh_ifinfo = batadv_neigh_ifinfo_get(router_neigh, BATADV_IF_DEFAULT); if (!router_neigh_ifinfo) goto out; neigh_tmp = nc_packet->neigh_node; router_coding = batadv_orig_router_get(neigh_tmp->orig_node, BATADV_IF_DEFAULT); if (!router_coding) goto out; router_coding_ifinfo = batadv_neigh_ifinfo_get(router_coding, BATADV_IF_DEFAULT); if (!router_coding_ifinfo) goto out; tq_tmp = router_neigh_ifinfo->bat_iv.tq_avg; tq_weighted_neigh = batadv_nc_random_weight_tq(tq_tmp); tq_tmp = router_coding_ifinfo->bat_iv.tq_avg; tq_weighted_coding = batadv_nc_random_weight_tq(tq_tmp); /* Select one destination for the MAC-header dst-field based on * weighted TQ-values. */ if (tq_weighted_neigh >= tq_weighted_coding) { /* Destination from nc_packet is selected for MAC-header */ first_dest = nc_packet->neigh_node; first_source = nc_packet->nc_path->prev_hop; second_dest = neigh_node; second_source = ethhdr->h_source; packet1 = (struct batadv_unicast_packet *)nc_packet->skb->data; packet2 = (struct batadv_unicast_packet *)skb->data; packet_id1 = nc_packet->packet_id; packet_id2 = batadv_skb_crc32(skb, skb->data + sizeof(*packet2)); } else { /* Destination for skb is selected for MAC-header */ first_dest = neigh_node; first_source = ethhdr->h_source; second_dest = nc_packet->neigh_node; second_source = nc_packet->nc_path->prev_hop; packet1 = (struct batadv_unicast_packet *)skb->data; packet2 = (struct batadv_unicast_packet *)nc_packet->skb->data; packet_id1 = batadv_skb_crc32(skb, skb->data + sizeof(*packet1)); packet_id2 = nc_packet->packet_id; } /* Instead of zero padding the smallest data buffer, we * code into the largest. */ if (skb->len <= nc_packet->skb->len) { skb_dest = nc_packet->skb; skb_src = skb; } else { skb_dest = skb; skb_src = nc_packet->skb; } /* coding_len is used when decoding the packet shorter packet */ coding_len = skb_src->len - unicast_size; if (skb_linearize(skb_dest) < 0 || skb_linearize(skb_src) < 0) goto out; skb_push(skb_dest, header_add); coded_packet = (struct batadv_coded_packet *)skb_dest->data; skb_reset_mac_header(skb_dest); coded_packet->packet_type = BATADV_CODED; coded_packet->version = BATADV_COMPAT_VERSION; coded_packet->ttl = packet1->ttl; /* Info about first unicast packet */ ether_addr_copy(coded_packet->first_source, first_source); ether_addr_copy(coded_packet->first_orig_dest, packet1->dest); coded_packet->first_crc = packet_id1; coded_packet->first_ttvn = packet1->ttvn; /* Info about second unicast packet */ ether_addr_copy(coded_packet->second_dest, second_dest->addr); ether_addr_copy(coded_packet->second_source, second_source); ether_addr_copy(coded_packet->second_orig_dest, packet2->dest); coded_packet->second_crc = packet_id2; coded_packet->second_ttl = packet2->ttl; coded_packet->second_ttvn = packet2->ttvn; coded_packet->coded_len = htons(coding_len); /* This is where the magic happens: Code skb_src into skb_dest */ batadv_nc_memxor(skb_dest->data + coded_size, skb_src->data + unicast_size, coding_len); /* Update counters accordingly */ if (BATADV_SKB_CB(skb_src)->decoded && BATADV_SKB_CB(skb_dest)->decoded) { /* Both packets are recoded */ count = skb_src->len + ETH_HLEN; count += skb_dest->len + ETH_HLEN; batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE, 2); batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES, count); } else if (!BATADV_SKB_CB(skb_src)->decoded && !BATADV_SKB_CB(skb_dest)->decoded) { /* Both packets are newly coded */ count = skb_src->len + ETH_HLEN; count += skb_dest->len + ETH_HLEN; batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE, 2); batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES, count); } else if (BATADV_SKB_CB(skb_src)->decoded && !BATADV_SKB_CB(skb_dest)->decoded) { /* skb_src recoded and skb_dest is newly coded */ batadv_inc_counter(bat_priv, BATADV_CNT_NC_RECODE); batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES, skb_src->len + ETH_HLEN); batadv_inc_counter(bat_priv, BATADV_CNT_NC_CODE); batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES, skb_dest->len + ETH_HLEN); } else if (!BATADV_SKB_CB(skb_src)->decoded && BATADV_SKB_CB(skb_dest)->decoded) { /* skb_src is newly coded and skb_dest is recoded */ batadv_inc_counter(bat_priv, BATADV_CNT_NC_CODE); batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES, skb_src->len + ETH_HLEN); batadv_inc_counter(bat_priv, BATADV_CNT_NC_RECODE); batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES, skb_dest->len + ETH_HLEN); } /* skb_src is now coded into skb_dest, so free it */ consume_skb(skb_src); /* avoid duplicate free of skb from nc_packet */ nc_packet->skb = NULL; batadv_nc_packet_free(nc_packet, false); /* Send the coded packet and return true */ batadv_send_unicast_skb(skb_dest, first_dest); res = true; out: batadv_neigh_node_put(router_neigh); batadv_neigh_node_put(router_coding); batadv_neigh_ifinfo_put(router_neigh_ifinfo); batadv_neigh_ifinfo_put(router_coding_ifinfo); return res; } /** * batadv_nc_skb_coding_possible() - true if a decoded skb is available at dst. * @skb: data skb to forward * @dst: destination mac address of the other skb to code with * @src: source mac address of skb * * Whenever we network code a packet we have to check whether we received it in * a network coded form. If so, we may not be able to use it for coding because * some neighbors may also have received (overheard) the packet in the network * coded form without being able to decode it. It is hard to know which of the * neighboring nodes was able to decode the packet, therefore we can only * re-code the packet if the source of the previous encoded packet is involved. * Since the source encoded the packet we can be certain it has all necessary * decode information. * * Return: true if coding of a decoded packet is allowed. */ static bool batadv_nc_skb_coding_possible(struct sk_buff *skb, u8 *dst, u8 *src) { if (BATADV_SKB_CB(skb)->decoded && !batadv_compare_eth(dst, src)) return false; return true; } /** * batadv_nc_path_search() - Find the coding path matching in_nc_node and * out_nc_node to retrieve a buffered packet that can be used for coding. * @bat_priv: the bat priv with all the soft interface information * @in_nc_node: pointer to skb next hop's neighbor nc node * @out_nc_node: pointer to skb source's neighbor nc node * @skb: data skb to forward * @eth_dst: next hop mac address of skb * * Return: true if coding of a decoded skb is allowed. */ static struct batadv_nc_packet * batadv_nc_path_search(struct batadv_priv *bat_priv, struct batadv_nc_node *in_nc_node, struct batadv_nc_node *out_nc_node, struct sk_buff *skb, u8 *eth_dst) { struct batadv_nc_path *nc_path, nc_path_key; struct batadv_nc_packet *nc_packet_out = NULL; struct batadv_nc_packet *nc_packet, *nc_packet_tmp; struct batadv_hashtable *hash = bat_priv->nc.coding_hash; int idx; if (!hash) return NULL; /* Create almost path key */ batadv_nc_hash_key_gen(&nc_path_key, in_nc_node->addr, out_nc_node->addr); idx = batadv_nc_hash_choose(&nc_path_key, hash->size); /* Check for coding opportunities in this nc_path */ rcu_read_lock(); hlist_for_each_entry_rcu(nc_path, &hash->table[idx], hash_entry) { if (!batadv_compare_eth(nc_path->prev_hop, in_nc_node->addr)) continue; if (!batadv_compare_eth(nc_path->next_hop, out_nc_node->addr)) continue; spin_lock_bh(&nc_path->packet_list_lock); if (list_empty(&nc_path->packet_list)) { spin_unlock_bh(&nc_path->packet_list_lock); continue; } list_for_each_entry_safe(nc_packet, nc_packet_tmp, &nc_path->packet_list, list) { if (!batadv_nc_skb_coding_possible(nc_packet->skb, eth_dst, in_nc_node->addr)) continue; /* Coding opportunity is found! */ list_del(&nc_packet->list); nc_packet_out = nc_packet; break; } spin_unlock_bh(&nc_path->packet_list_lock); break; } rcu_read_unlock(); return nc_packet_out; } /** * batadv_nc_skb_src_search() - Loops through the list of neighboring nodes of * the skb's sender (may be equal to the originator). * @bat_priv: the bat priv with all the soft interface information * @skb: data skb to forward * @eth_dst: next hop mac address of skb * @eth_src: source mac address of skb * @in_nc_node: pointer to skb next hop's neighbor nc node * * Return: an nc packet if a suitable coding packet was found, NULL otherwise. */ static struct batadv_nc_packet * batadv_nc_skb_src_search(struct batadv_priv *bat_priv, struct sk_buff *skb, u8 *eth_dst, u8 *eth_src, struct batadv_nc_node *in_nc_node) { struct batadv_orig_node *orig_node; struct batadv_nc_node *out_nc_node; struct batadv_nc_packet *nc_packet = NULL; orig_node = batadv_orig_hash_find(bat_priv, eth_src); if (!orig_node) return NULL; rcu_read_lock(); list_for_each_entry_rcu(out_nc_node, &orig_node->out_coding_list, list) { /* Check if the skb is decoded and if recoding is possible */ if (!batadv_nc_skb_coding_possible(skb, out_nc_node->addr, eth_src)) continue; /* Search for an opportunity in this nc_path */ nc_packet = batadv_nc_path_search(bat_priv, in_nc_node, out_nc_node, skb, eth_dst); if (nc_packet) break; } rcu_read_unlock(); batadv_orig_node_put(orig_node); return nc_packet; } /** * batadv_nc_skb_store_before_coding() - set the ethernet src and dst of the * unicast skb before it is stored for use in later decoding * @bat_priv: the bat priv with all the soft interface information * @skb: data skb to store * @eth_dst_new: new destination mac address of skb */ static void batadv_nc_skb_store_before_coding(struct batadv_priv *bat_priv, struct sk_buff *skb, u8 *eth_dst_new) { struct ethhdr *ethhdr; /* Copy skb header to change the mac header */ skb = pskb_copy_for_clone(skb, GFP_ATOMIC); if (!skb) return; /* Set the mac header as if we actually sent the packet uncoded */ ethhdr = eth_hdr(skb); ether_addr_copy(ethhdr->h_source, ethhdr->h_dest); ether_addr_copy(ethhdr->h_dest, eth_dst_new); /* Set data pointer to MAC header to mimic packets from our tx path */ skb_push(skb, ETH_HLEN); /* Add the packet to the decoding packet pool */ batadv_nc_skb_store_for_decoding(bat_priv, skb); /* batadv_nc_skb_store_for_decoding() clones the skb, so we must free * our ref */ consume_skb(skb); } /** * batadv_nc_skb_dst_search() - Loops through list of neighboring nodes to dst. * @skb: data skb to forward * @neigh_node: next hop to forward packet to * @ethhdr: pointer to the ethernet header inside the skb * * Loops through the list of neighboring nodes the next hop has a good * connection to (receives OGMs with a sufficient quality). We need to find a * neighbor of our next hop that potentially sent a packet which our next hop * also received (overheard) and has stored for later decoding. * * Return: true if the skb was consumed (encoded packet sent) or false otherwise */ static bool batadv_nc_skb_dst_search(struct sk_buff *skb, struct batadv_neigh_node *neigh_node, struct ethhdr *ethhdr) { struct net_device *netdev = neigh_node->if_incoming->soft_iface; struct batadv_priv *bat_priv = netdev_priv(netdev); struct batadv_orig_node *orig_node = neigh_node->orig_node; struct batadv_nc_node *nc_node; struct batadv_nc_packet *nc_packet = NULL; rcu_read_lock(); list_for_each_entry_rcu(nc_node, &orig_node->in_coding_list, list) { /* Search for coding opportunity with this in_nc_node */ nc_packet = batadv_nc_skb_src_search(bat_priv, skb, neigh_node->addr, ethhdr->h_source, nc_node); /* Opportunity was found, so stop searching */ if (nc_packet) break; } rcu_read_unlock(); if (!nc_packet) return false; /* Save packets for later decoding */ batadv_nc_skb_store_before_coding(bat_priv, skb, neigh_node->addr); batadv_nc_skb_store_before_coding(bat_priv, nc_packet->skb, nc_packet->neigh_node->addr); /* Code and send packets */ if (batadv_nc_code_packets(bat_priv, skb, ethhdr, nc_packet, neigh_node)) return true; /* out of mem ? Coding failed - we have to free the buffered packet * to avoid memleaks. The skb passed as argument will be dealt with * by the calling function. */ batadv_nc_send_packet(nc_packet); return false; } /** * batadv_nc_skb_add_to_path() - buffer skb for later encoding / decoding * @skb: skb to add to path * @nc_path: path to add skb to * @neigh_node: next hop to forward packet to * @packet_id: checksum to identify packet * * Return: true if the packet was buffered or false in case of an error. */ static bool batadv_nc_skb_add_to_path(struct sk_buff *skb, struct batadv_nc_path *nc_path, struct batadv_neigh_node *neigh_node, __be32 packet_id) { struct batadv_nc_packet *nc_packet; nc_packet = kzalloc(sizeof(*nc_packet), GFP_ATOMIC); if (!nc_packet) return false; /* Initialize nc_packet */ nc_packet->timestamp = jiffies; nc_packet->packet_id = packet_id; nc_packet->skb = skb; nc_packet->neigh_node = neigh_node; nc_packet->nc_path = nc_path; /* Add coding packet to list */ spin_lock_bh(&nc_path->packet_list_lock); list_add_tail(&nc_packet->list, &nc_path->packet_list); spin_unlock_bh(&nc_path->packet_list_lock); return true; } /** * batadv_nc_skb_forward() - try to code a packet or add it to the coding packet * buffer * @skb: data skb to forward * @neigh_node: next hop to forward packet to * * Return: true if the skb was consumed (encoded packet sent) or false otherwise */ bool batadv_nc_skb_forward(struct sk_buff *skb, struct batadv_neigh_node *neigh_node) { const struct net_device *netdev = neigh_node->if_incoming->soft_iface; struct batadv_priv *bat_priv = netdev_priv(netdev); struct batadv_unicast_packet *packet; struct batadv_nc_path *nc_path; struct ethhdr *ethhdr = eth_hdr(skb); __be32 packet_id; u8 *payload; /* Check if network coding is enabled */ if (!atomic_read(&bat_priv->network_coding)) goto out; /* We only handle unicast packets */ payload = skb_network_header(skb); packet = (struct batadv_unicast_packet *)payload; if (packet->packet_type != BATADV_UNICAST) goto out; /* Try to find a coding opportunity and send the skb if one is found */ if (batadv_nc_skb_dst_search(skb, neigh_node, ethhdr)) return true; /* Find or create a nc_path for this src-dst pair */ nc_path = batadv_nc_get_path(bat_priv, bat_priv->nc.coding_hash, ethhdr->h_source, neigh_node->addr); if (!nc_path) goto out; /* Add skb to nc_path */ packet_id = batadv_skb_crc32(skb, payload + sizeof(*packet)); if (!batadv_nc_skb_add_to_path(skb, nc_path, neigh_node, packet_id)) goto free_nc_path; /* Packet is consumed */ return true; free_nc_path: batadv_nc_path_put(nc_path); out: /* Packet is not consumed */ return false; } /** * batadv_nc_skb_store_for_decoding() - save a clone of the skb which can be * used when decoding coded packets * @bat_priv: the bat priv with all the soft interface information * @skb: data skb to store */ void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_unicast_packet *packet; struct batadv_nc_path *nc_path; struct ethhdr *ethhdr = eth_hdr(skb); __be32 packet_id; u8 *payload; /* Check if network coding is enabled */ if (!atomic_read(&bat_priv->network_coding)) goto out; /* Check for supported packet type */ payload = skb_network_header(skb); packet = (struct batadv_unicast_packet *)payload; if (packet->packet_type != BATADV_UNICAST) goto out; /* Find existing nc_path or create a new */ nc_path = batadv_nc_get_path(bat_priv, bat_priv->nc.decoding_hash, ethhdr->h_source, ethhdr->h_dest); if (!nc_path) goto out; /* Clone skb and adjust skb->data to point at batman header */ skb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!skb)) goto free_nc_path; if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) goto free_skb; if (unlikely(!skb_pull_rcsum(skb, ETH_HLEN))) goto free_skb; /* Add skb to nc_path */ packet_id = batadv_skb_crc32(skb, payload + sizeof(*packet)); if (!batadv_nc_skb_add_to_path(skb, nc_path, NULL, packet_id)) goto free_skb; batadv_inc_counter(bat_priv, BATADV_CNT_NC_BUFFER); return; free_skb: kfree_skb(skb); free_nc_path: batadv_nc_path_put(nc_path); out: return; } /** * batadv_nc_skb_store_sniffed_unicast() - check if a received unicast packet * should be saved in the decoding buffer and, if so, store it there * @bat_priv: the bat priv with all the soft interface information * @skb: unicast skb to store */ void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct ethhdr *ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_dest)) return; /* Set data pointer to MAC header to mimic packets from our tx path */ skb_push(skb, ETH_HLEN); batadv_nc_skb_store_for_decoding(bat_priv, skb); } /** * batadv_nc_skb_decode_packet() - decode given skb using the decode data stored * in nc_packet * @bat_priv: the bat priv with all the soft interface information * @skb: unicast skb to decode * @nc_packet: decode data needed to decode the skb * * Return: pointer to decoded unicast packet if the packet was decoded or NULL * in case of an error. */ static struct batadv_unicast_packet * batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_nc_packet *nc_packet) { const int h_size = sizeof(struct batadv_unicast_packet); const int h_diff = sizeof(struct batadv_coded_packet) - h_size; struct batadv_unicast_packet *unicast_packet; struct batadv_coded_packet coded_packet_tmp; struct ethhdr *ethhdr, ethhdr_tmp; u8 *orig_dest, ttl, ttvn; unsigned int coding_len; int err; /* Save headers temporarily */ memcpy(&coded_packet_tmp, skb->data, sizeof(coded_packet_tmp)); memcpy(ðhdr_tmp, skb_mac_header(skb), sizeof(ethhdr_tmp)); if (skb_cow(skb, 0) < 0) return NULL; if (unlikely(!skb_pull_rcsum(skb, h_diff))) return NULL; /* Data points to batman header, so set mac header 14 bytes before * and network to data */ skb_set_mac_header(skb, -ETH_HLEN); skb_reset_network_header(skb); /* Reconstruct original mac header */ ethhdr = eth_hdr(skb); *ethhdr = ethhdr_tmp; /* Select the correct unicast header information based on the location * of our mac address in the coded_packet header */ if (batadv_is_my_mac(bat_priv, coded_packet_tmp.second_dest)) { /* If we are the second destination the packet was overheard, * so the Ethernet address must be copied to h_dest and * pkt_type changed from PACKET_OTHERHOST to PACKET_HOST */ ether_addr_copy(ethhdr->h_dest, coded_packet_tmp.second_dest); skb->pkt_type = PACKET_HOST; orig_dest = coded_packet_tmp.second_orig_dest; ttl = coded_packet_tmp.second_ttl; ttvn = coded_packet_tmp.second_ttvn; } else { orig_dest = coded_packet_tmp.first_orig_dest; ttl = coded_packet_tmp.ttl; ttvn = coded_packet_tmp.first_ttvn; } coding_len = ntohs(coded_packet_tmp.coded_len); if (coding_len > skb->len) return NULL; /* Here the magic is reversed: * extract the missing packet from the received coded packet */ batadv_nc_memxor(skb->data + h_size, nc_packet->skb->data + h_size, coding_len); /* Resize decoded skb if decoded with larger packet */ if (nc_packet->skb->len > coding_len + h_size) { err = pskb_trim_rcsum(skb, coding_len + h_size); if (err) return NULL; } /* Create decoded unicast packet */ unicast_packet = (struct batadv_unicast_packet *)skb->data; unicast_packet->packet_type = BATADV_UNICAST; unicast_packet->version = BATADV_COMPAT_VERSION; unicast_packet->ttl = ttl; ether_addr_copy(unicast_packet->dest, orig_dest); unicast_packet->ttvn = ttvn; batadv_nc_packet_free(nc_packet, false); return unicast_packet; } /** * batadv_nc_find_decoding_packet() - search through buffered decoding data to * find the data needed to decode the coded packet * @bat_priv: the bat priv with all the soft interface information * @ethhdr: pointer to the ethernet header inside the coded packet * @coded: coded packet we try to find decode data for * * Return: pointer to nc packet if the needed data was found or NULL otherwise. */ static struct batadv_nc_packet * batadv_nc_find_decoding_packet(struct batadv_priv *bat_priv, struct ethhdr *ethhdr, struct batadv_coded_packet *coded) { struct batadv_hashtable *hash = bat_priv->nc.decoding_hash; struct batadv_nc_packet *tmp_nc_packet, *nc_packet = NULL; struct batadv_nc_path *nc_path, nc_path_key; u8 *dest, *source; __be32 packet_id; int index; if (!hash) return NULL; /* Select the correct packet id based on the location of our mac-addr */ dest = ethhdr->h_source; if (!batadv_is_my_mac(bat_priv, coded->second_dest)) { source = coded->second_source; packet_id = coded->second_crc; } else { source = coded->first_source; packet_id = coded->first_crc; } batadv_nc_hash_key_gen(&nc_path_key, source, dest); index = batadv_nc_hash_choose(&nc_path_key, hash->size); /* Search for matching coding path */ rcu_read_lock(); hlist_for_each_entry_rcu(nc_path, &hash->table[index], hash_entry) { /* Find matching nc_packet */ spin_lock_bh(&nc_path->packet_list_lock); list_for_each_entry(tmp_nc_packet, &nc_path->packet_list, list) { if (packet_id == tmp_nc_packet->packet_id) { list_del(&tmp_nc_packet->list); nc_packet = tmp_nc_packet; break; } } spin_unlock_bh(&nc_path->packet_list_lock); if (nc_packet) break; } rcu_read_unlock(); if (!nc_packet) batadv_dbg(BATADV_DBG_NC, bat_priv, "No decoding packet found for %u\n", packet_id); return nc_packet; } /** * batadv_nc_recv_coded_packet() - try to decode coded packet and enqueue the * resulting unicast packet * @skb: incoming coded packet * @recv_if: pointer to interface this packet was received on * * Return: NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP * otherwise. */ static int batadv_nc_recv_coded_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if) { struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); struct batadv_unicast_packet *unicast_packet; struct batadv_coded_packet *coded_packet; struct batadv_nc_packet *nc_packet; struct ethhdr *ethhdr; int hdr_size = sizeof(*coded_packet); /* Check if network coding is enabled */ if (!atomic_read(&bat_priv->network_coding)) goto free_skb; /* Make sure we can access (and remove) header */ if (unlikely(!pskb_may_pull(skb, hdr_size))) goto free_skb; coded_packet = (struct batadv_coded_packet *)skb->data; ethhdr = eth_hdr(skb); /* Verify frame is destined for us */ if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest) && !batadv_is_my_mac(bat_priv, coded_packet->second_dest)) goto free_skb; /* Update stat counter */ if (batadv_is_my_mac(bat_priv, coded_packet->second_dest)) batadv_inc_counter(bat_priv, BATADV_CNT_NC_SNIFFED); nc_packet = batadv_nc_find_decoding_packet(bat_priv, ethhdr, coded_packet); if (!nc_packet) { batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE_FAILED); goto free_skb; } /* Make skb's linear, because decoding accesses the entire buffer */ if (skb_linearize(skb) < 0) goto free_nc_packet; if (skb_linearize(nc_packet->skb) < 0) goto free_nc_packet; /* Decode the packet */ unicast_packet = batadv_nc_skb_decode_packet(bat_priv, skb, nc_packet); if (!unicast_packet) { batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE_FAILED); goto free_nc_packet; } /* Mark packet as decoded to do correct recoding when forwarding */ BATADV_SKB_CB(skb)->decoded = true; batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE); batadv_add_counter(bat_priv, BATADV_CNT_NC_DECODE_BYTES, skb->len + ETH_HLEN); return batadv_recv_unicast_packet(skb, recv_if); free_nc_packet: batadv_nc_packet_free(nc_packet, true); free_skb: kfree_skb(skb); return NET_RX_DROP; } /** * batadv_nc_mesh_free() - clean up network coding memory * @bat_priv: the bat priv with all the soft interface information */ void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_NC, 1); batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_NC, 1); cancel_delayed_work_sync(&bat_priv->nc.work); batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, NULL); batadv_hash_destroy(bat_priv->nc.coding_hash); batadv_nc_purge_paths(bat_priv, bat_priv->nc.decoding_hash, NULL); batadv_hash_destroy(bat_priv->nc.decoding_hash); } |
| 12 12 12 12 5 5 5 11 11 5 5 11 5 5 1 112 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 | // SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> */ #include <linux/module.h> #include <linux/gfp.h> #include <net/tcp.h> static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); u32 elapsed, start_ts; s32 remaining; start_ts = tcp_sk(sk)->retrans_stamp; if (!icsk->icsk_user_timeout) return icsk->icsk_rto; elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; remaining = icsk->icsk_user_timeout - elapsed; if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining)); } u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) { struct inet_connection_sock *icsk = inet_csk(sk); u32 remaining; s32 elapsed; if (!icsk->icsk_user_timeout || !icsk->icsk_probes_tstamp) return when; elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp; if (unlikely(elapsed < 0)) elapsed = 0; remaining = msecs_to_jiffies(icsk->icsk_user_timeout) - elapsed; remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN); return min_t(u32, remaining, when); } /** * tcp_write_err() - close socket and save error info * @sk: The socket the error has appeared on. * * Returns: Nothing (void) */ static void tcp_write_err(struct sock *sk) { tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); } /** * tcp_out_of_resources() - Close socket if out of resources * @sk: pointer to current socket * @do_reset: send a last packet with reset flag * * Do not allow orphaned sockets to eat all our resources. * This is direct violation of TCP specs, but it is required * to prevent DoS attacks. It is called when a retransmission timeout * or zero probe timeout occurs on orphaned socket. * * Also close if our net namespace is exiting; in that case there is no * hope of ever communicating again since all netns interfaces are already * down (or about to be down), and we need to release our dst references, * which have been moved to the netns loopback interface, so the namespace * can finish exiting. This condition is only possible if we are a kernel * socket, as those do not hold references to the namespace. * * Criteria is still not confirmed experimentally and may change. * We kill the socket, if: * 1. If number of orphaned sockets exceeds an administratively configured * limit. * 2. If we have strong memory pressure. * 3. If our net namespace is exiting. */ static int tcp_out_of_resources(struct sock *sk, bool do_reset) { struct tcp_sock *tp = tcp_sk(sk); int shift = 0; /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ if (READ_ONCE(sk->sk_err_soft)) shift++; if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ if ((s32)(tcp_jiffies32 - tp->lsndtime) <= TCP_TIMEWAIT_LEN || /* 2. Window is closed. */ (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) tcp_send_active_reset(sk, GFP_ATOMIC); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; } if (!check_net(sock_net(sk))) { /* Not possible to send reset; just close */ tcp_done(sk); return 1; } return 0; } /** * tcp_orphan_retries() - Returns maximal number of retries on an orphaned socket * @sk: Pointer to the current socket. * @alive: bool, socket alive state */ static int tcp_orphan_retries(struct sock *sk, bool alive) { int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */ /* We know from an ICMP that something is wrong. */ if (READ_ONCE(sk->sk_err_soft) && !alive) retries = 0; /* However, if socket sent something recently, select some safe * number of retries. 8 corresponds to >100 seconds with minimal * RTO of 200msec. */ if (retries == 0 && alive) retries = 8; return retries; } static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) { const struct net *net = sock_net(sk); int mss; /* Black hole detection */ if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing)) return; if (!icsk->icsk_mtup.enabled) { icsk->icsk_mtup.enabled = 1; icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss); mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor)); mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss)); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } static unsigned int tcp_model_timeout(struct sock *sk, unsigned int boundary, unsigned int rto_base) { unsigned int linear_backoff_thresh, timeout; linear_backoff_thresh = ilog2(TCP_RTO_MAX / rto_base); if (boundary <= linear_backoff_thresh) timeout = ((2 << boundary) - 1) * rto_base; else timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; return jiffies_to_msecs(timeout); } /** * retransmits_timed_out() - returns true if this connection has timed out * @sk: The current socket * @boundary: max number of retransmissions * @timeout: A custom timeout value. * If set to 0 the default timeout is calculated and used. * Using TCP_RTO_MIN and the number of unsuccessful retransmits. * * The default "timeout" value this function can calculate and use * is equivalent to the timeout of a TCP Connection * after "boundary" unsuccessful, exponentially backed-off * retransmissions with an initial RTO of TCP_RTO_MIN. */ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { unsigned int start_ts; if (!inet_csk(sk)->icsk_retransmits) return false; start_ts = tcp_sk(sk)->retrans_stamp; if (likely(timeout == 0)) { unsigned int rto_base = TCP_RTO_MIN; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) rto_base = tcp_timeout_init(sk); timeout = tcp_model_timeout(sk, boundary, rto_base); } return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; } /* A write timeout has occurred. Process the after effects. */ static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); bool expired = false, do_reset; int retry_until; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) __dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); expired = icsk->icsk_retransmits >= retry_until; } else { if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); __dst_negative_advice(sk); } retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = icsk->icsk_rto < TCP_RTO_MAX; retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || !retransmits_timed_out(sk, retry_until, 0); if (tcp_out_of_resources(sk, do_reset)) return 1; } } if (!expired) expired = retransmits_timed_out(sk, retry_until, icsk->icsk_user_timeout); tcp_fastopen_active_detect_blackhole(sk, expired); if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB, icsk->icsk_retransmits, icsk->icsk_rto, (int)expired); if (expired) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; } if (sk_rethink_txhash(sk)) { tp->timeout_rehash++; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH); } return 0; } /* Called with BH disabled */ void tcp_delack_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); sk_mem_reclaim_partial(sk); if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) goto out; if (time_after(icsk->icsk_ack.timeout, jiffies)) { sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); goto out; } icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } tcp_mstamp_refresh(tcp_sk(sk)); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } out: if (tcp_under_memory_pressure(sk)) sk_mem_reclaim(sk); } /** * tcp_delack_timer() - The TCP delayed ACK timeout handler * @t: Pointer to the timer. (gets casted to struct sock *) * * This function gets (indirectly) called when the kernel timer for a TCP packet * of this socket expires. Calls tcp_delack_timer_handler() to do the actual work. * * Returns: Nothing (void) */ static void tcp_delack_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_delack_timer); struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_delack_timer_handler(sk); } else { __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk); sock_put(sk); } static void tcp_probe_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb = tcp_send_head(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; if (tp->packets_out || !skb) { icsk->icsk_probes_out = 0; icsk->icsk_probes_tstamp = 0; return; } /* RFC 1122 4.2.2.17 requires the sender to stay open indefinitely as * long as the receiver continues to respond probes. We support this by * default and reset icsk_probes_out with incoming ACKs. But if the * socket is orphaned or the user specifies TCP_USER_TIMEOUT, we * kill the socket when the retry count and the time exceeds the * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ if (!icsk->icsk_probes_tstamp) icsk->icsk_probes_tstamp = tcp_jiffies32; else if (icsk->icsk_user_timeout && (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >= msecs_to_jiffies(icsk->icsk_user_timeout)) goto abort; max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; max_probes = tcp_orphan_retries(sk, alive); if (!alive && icsk->icsk_backoff >= max_probes) goto abort; if (tcp_out_of_resources(sk, true)) return; } if (icsk->icsk_probes_out >= max_probes) { abort: tcp_write_err(sk); } else { /* Only send another probe if we didn't close things up. */ tcp_send_probe0(sk); } } /* * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. */ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int max_retries; req->rsk_ops->syn_ack_timeout(req); /* add one more retry for fastopen */ max_retries = icsk->icsk_syn_retries ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1; if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; } /* Lower cwnd after certain SYNACK timeout like tcp_init_transfer() */ if (icsk->icsk_retransmits == 1) tcp_enter_loss(sk); /* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error * returned from rtx_syn_ack() to make it more persistent like * regular retransmit because if the child socket has been accepted * it's not good to give up too easily. */ inet_rtx_syn_ack(sk, req); req->num_timeout++; icsk->icsk_retransmits++; if (!tp->retrans_stamp) tp->retrans_stamp = tcp_time_stamp(tp); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); } static bool tcp_rtx_probe0_timed_out(const struct sock *sk, const struct sk_buff *skb) { const struct inet_connection_sock *icsk = inet_csk(sk); u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); const struct tcp_sock *tp = tcp_sk(sk); int timeout = TCP_RTO_MAX * 2; u32 rtx_delta; s32 rcv_delta; rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); if (user_timeout) { /* If user application specified a TCP_USER_TIMEOUT, * it does not want win 0 packets to 'reset the timer' * while retransmits are not making progress. */ if (rtx_delta > user_timeout) return true; timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout)); } /* Note: timer interrupt might have been delayed by at least one jiffy, * and tp->rcv_tstamp might very well have been written recently. * rcv_delta can thus be negative. */ rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; return rtx_delta > timeout; } /** * tcp_retransmit_timer() - The TCP retransmit timeout handler * @sk: Pointer to the current socket. * * This function gets called when the kernel timer for a TCP packet * of this socket expires. * * It handles retransmission, timer adjustment and other necessary measures. * * Returns: Nothing (void) */ void tcp_retransmit_timer(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock *req; struct sk_buff *skb; req = rcu_dereference_protected(tp->fastopen_rsk, lockdep_sock_is_held(sk)); if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); tcp_fastopen_synack_timer(sk, req); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). */ return; } if (!tp->packets_out) return; skb = tcp_rtx_queue_head(sk); if (WARN_ON_ONCE(!skb)) return; if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) && !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) { /* Receiver dastardly shrinks window. Our retransmits * become zero probes, but we should not timeout this * connection. If the socket is an orphan, time it out, * we cannot allow such beasts to hang infinitely. */ struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", &inet->inet_daddr, ntohs(inet->inet_dport), inet->inet_num, tp->snd_una, tp->snd_nxt); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", &sk->sk_v6_daddr, ntohs(inet->inet_dport), inet->inet_num, tp->snd_una, tp->snd_nxt); } #endif if (tcp_rtx_probe0_timed_out(sk, skb)) { tcp_write_err(sk); goto out; } tcp_enter_loss(sk); tcp_retransmit_skb(sk, skb, 1); __sk_dst_reset(sk); goto out_reset_timer; } __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); if (tcp_write_timeout(sk)) goto out; if (icsk->icsk_retransmits == 0) { int mib_idx = 0; if (icsk->icsk_ca_state == TCP_CA_Recovery) { if (tcp_is_sack(tp)) mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL; else mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL; } else if (icsk->icsk_ca_state == TCP_CA_Loss) { mib_idx = LINUX_MIB_TCPLOSSFAILURES; } else if ((icsk->icsk_ca_state == TCP_CA_Disorder) || tp->sacked_out) { if (tcp_is_sack(tp)) mib_idx = LINUX_MIB_TCPSACKFAILURES; else mib_idx = LINUX_MIB_TCPRENOFAILURES; } if (mib_idx) __NET_INC_STATS(sock_net(sk), mib_idx); } tcp_enter_loss(sk); icsk->icsk_retransmits++; if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { /* Retransmission failed because of local congestion, * Let senders fight for local resources conservatively. */ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, TCP_RESOURCE_PROBE_INTERVAL, TCP_RTO_MAX); goto out; } /* Increase the timeout each time we retransmit. Note that * we do not increase the rtt estimate. rto is initialized * from rtt, but increases here. Jacobson (SIGCOMM 88) suggests * that doubling rto each time is the least we can get away with. * In KA9Q, Karn uses this for the first few times, and then * goes to quadratic. netBSD doubles, but only goes up to *64, * and clamps at 1 to 64 sec afterwards. Note that 120 sec is * defined in the protocol as the maximum possible RTT. I guess * we'll have to use something other than TCP to talk to the * University of Mars. * * PAWS allows us longer timeouts and large windows, so once * implemented ftp to mars will work nicely. We will have to fix * the 120 second clamps though! */ icsk->icsk_backoff++; out_reset_timer: /* If stream is thin, use linear timeouts. Since 'icsk_backoff' is * used to reset timer, set to 0. Recalculate 'icsk_rto' as this * might be increased if the stream oscillates between thin and thick, * thus the old value might already be too high compared to the value * set by 'tcp_set_rto' in tcp_input.c which resets the rto without * backoff. Limit to TCP_THIN_LINEAR_RETRIES before initiating * exponential backoff behaviour to avoid continue hammering * linear-timeout retransmissions into a black hole */ if (sk->sk_state == TCP_ESTABLISHED && (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) && tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; icsk->icsk_rto = clamp(__tcp_set_rto(tp), tcp_rto_min(sk), TCP_RTO_MAX); } else { /* Use normal (exponential) backoff */ icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX); if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0)) __sk_dst_reset(sk); out:; } /* Called with bottom-half processing disabled. Called by tcp_write_timer() */ void tcp_write_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int event; if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || !icsk->icsk_pending) goto out; if (time_after(icsk->icsk_timeout, jiffies)) { sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); goto out; } tcp_mstamp_refresh(tcp_sk(sk)); event = icsk->icsk_pending; switch (event) { case ICSK_TIME_REO_TIMEOUT: tcp_rack_reo_timeout(sk); break; case ICSK_TIME_LOSS_PROBE: tcp_send_loss_probe(sk); break; case ICSK_TIME_RETRANS: icsk->icsk_pending = 0; tcp_retransmit_timer(sk); break; case ICSK_TIME_PROBE0: icsk->icsk_pending = 0; tcp_probe_timer(sk); break; } out: sk_mem_reclaim(sk); } static void tcp_write_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_retransmit_timer); struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_write_timer_handler(sk); } else { /* delegate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk); sock_put(sk); } void tcp_syn_ack_timeout(const struct request_sock *req) { struct net *net = read_pnet(&inet_rsk(req)->ireq_net); __NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS); } EXPORT_SYMBOL(tcp_syn_ack_timeout); void tcp_set_keepalive(struct sock *sk, int val) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return; if (val && !sock_flag(sk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk))); else if (!val) inet_csk_delete_keepalive_timer(sk); } EXPORT_SYMBOL_GPL(tcp_set_keepalive); static void tcp_keepalive_timer (struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 elapsed; /* Only process if socket is not in use. */ bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later. */ inet_csk_reset_keepalive_timer (sk, HZ/20); goto out; } if (sk->sk_state == TCP_LISTEN) { pr_err("Hmm... keepalive on a LISTEN ???\n"); goto out; } tcp_mstamp_refresh(tp); if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) { if (tp->linger2 >= 0) { const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN; if (tmo > 0) { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto out; } } tcp_send_active_reset(sk, GFP_ATOMIC); goto death; } if (!sock_flag(sk, SOCK_KEEPOPEN) || ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT))) goto out; elapsed = keepalive_time_when(tp); /* It is alive without keepalive 8) */ if (tp->packets_out || !tcp_write_queue_empty(sk)) goto resched; elapsed = keepalive_time_elapsed(tp); if (elapsed >= keepalive_time_when(tp)) { /* If the TCP_USER_TIMEOUT option is enabled, use that * to determine when to timeout instead. */ if ((icsk->icsk_user_timeout != 0 && elapsed >= msecs_to_jiffies(icsk->icsk_user_timeout) && icsk->icsk_probes_out > 0) || (icsk->icsk_user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { tcp_send_active_reset(sk, GFP_ATOMIC); tcp_write_err(sk); goto out; } if (tcp_write_wakeup(sk, LINUX_MIB_TCPKEEPALIVE) <= 0) { icsk->icsk_probes_out++; elapsed = keepalive_intvl_when(tp); } else { /* If keepalive was lost due to local congestion, * try harder. */ elapsed = TCP_RESOURCE_PROBE_INTERVAL; } } else { /* It is tp->rcv_tstamp + keepalive_time_when(tp) */ elapsed = keepalive_time_when(tp) - elapsed; } sk_mem_reclaim(sk); resched: inet_csk_reset_keepalive_timer (sk, elapsed); goto out; death: tcp_done(sk); out: bh_unlock_sock(sk); sock_put(sk); } static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer) { struct tcp_sock *tp = container_of(timer, struct tcp_sock, compressed_ack_timer); struct sock *sk = (struct sock *)tp; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { if (tp->compressed_ack) { /* Since we have to send one ack finally, * subtract one from tp->compressed_ack to keep * LINUX_MIB_TCPACKCOMPRESSED accurate. */ tp->compressed_ack--; tcp_send_ack(sk); } } else { if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk); sock_put(sk); return HRTIMER_NORESTART; } void tcp_init_xmit_timers(struct sock *sk) { inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_SOFT); tcp_sk(sk)->pacing_timer.function = tcp_pace_kick; hrtimer_init(&tcp_sk(sk)->compressed_ack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED_SOFT); tcp_sk(sk)->compressed_ack_timer.function = tcp_compressed_ack_kick; } |
| 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 | // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2010-2011 EIA Electronics, // Pieter Beyens <pieter.beyens@eia.be> // Copyright (c) 2010-2011 EIA Electronics, // Kurt Van Dijck <kurt.van.dijck@eia.be> // Copyright (c) 2018 Protonic, // Robin van der Gracht <robin@protonic.nl> // Copyright (c) 2017-2019 Pengutronix, // Marc Kleine-Budde <kernel@pengutronix.de> // Copyright (c) 2017-2019 Pengutronix, // Oleksij Rempel <kernel@pengutronix.de> #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/can/can-ml.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/errqueue.h> #include <linux/if_arp.h> #include "j1939-priv.h" #define J1939_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.j1939) /* conversion function between struct sock::sk_priority from linux and * j1939 priority field */ static inline priority_t j1939_prio(u32 sk_priority) { sk_priority = min(sk_priority, 7U); return 7 - sk_priority; } static inline u32 j1939_to_sk_priority(priority_t prio) { return 7 - prio; } /* function to see if pgn is to be evaluated */ static inline bool j1939_pgn_is_valid(pgn_t pgn) { return pgn <= J1939_PGN_MAX; } /* test function to avoid non-zero DA placeholder for pdu1 pgn's */ static inline bool j1939_pgn_is_clean_pdu(pgn_t pgn) { if (j1939_pgn_is_pdu1(pgn)) return !(pgn & 0xff); else return true; } static inline void j1939_sock_pending_add(struct sock *sk) { struct j1939_sock *jsk = j1939_sk(sk); atomic_inc(&jsk->skb_pending); } static int j1939_sock_pending_get(struct sock *sk) { struct j1939_sock *jsk = j1939_sk(sk); return atomic_read(&jsk->skb_pending); } void j1939_sock_pending_del(struct sock *sk) { struct j1939_sock *jsk = j1939_sk(sk); /* atomic_dec_return returns the new value */ if (!atomic_dec_return(&jsk->skb_pending)) wake_up(&jsk->waitq); /* no pending SKB's */ } static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk) { jsk->state |= J1939_SOCK_BOUND; j1939_priv_get(priv); write_lock_bh(&priv->j1939_socks_lock); list_add_tail(&jsk->list, &priv->j1939_socks); write_unlock_bh(&priv->j1939_socks_lock); } static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) { write_lock_bh(&priv->j1939_socks_lock); list_del_init(&jsk->list); write_unlock_bh(&priv->j1939_socks_lock); j1939_priv_put(priv); jsk->state &= ~J1939_SOCK_BOUND; } static bool j1939_sk_queue_session(struct j1939_session *session) { struct j1939_sock *jsk = j1939_sk(session->sk); bool empty; spin_lock_bh(&jsk->sk_session_queue_lock); empty = list_empty(&jsk->sk_session_queue); j1939_session_get(session); list_add_tail(&session->sk_session_queue_entry, &jsk->sk_session_queue); spin_unlock_bh(&jsk->sk_session_queue_lock); j1939_sock_pending_add(&jsk->sk); return empty; } static struct j1939_session *j1939_sk_get_incomplete_session(struct j1939_sock *jsk) { struct j1939_session *session = NULL; spin_lock_bh(&jsk->sk_session_queue_lock); if (!list_empty(&jsk->sk_session_queue)) { session = list_last_entry(&jsk->sk_session_queue, struct j1939_session, sk_session_queue_entry); if (session->total_queued_size == session->total_message_size) session = NULL; else j1939_session_get(session); } spin_unlock_bh(&jsk->sk_session_queue_lock); return session; } static void j1939_sk_queue_drop_all(struct j1939_priv *priv, struct j1939_sock *jsk, int err) { struct j1939_session *session, *tmp; netdev_dbg(priv->ndev, "%s: err: %i\n", __func__, err); spin_lock_bh(&jsk->sk_session_queue_lock); list_for_each_entry_safe(session, tmp, &jsk->sk_session_queue, sk_session_queue_entry) { list_del_init(&session->sk_session_queue_entry); session->err = err; j1939_session_put(session); } spin_unlock_bh(&jsk->sk_session_queue_lock); } static void j1939_sk_queue_activate_next_locked(struct j1939_session *session) { struct j1939_sock *jsk; struct j1939_session *first; int err; /* RX-Session don't have a socket (yet) */ if (!session->sk) return; jsk = j1939_sk(session->sk); lockdep_assert_held(&jsk->sk_session_queue_lock); err = session->err; first = list_first_entry_or_null(&jsk->sk_session_queue, struct j1939_session, sk_session_queue_entry); /* Some else has already activated the next session */ if (first != session) return; activate_next: list_del_init(&first->sk_session_queue_entry); j1939_session_put(first); first = list_first_entry_or_null(&jsk->sk_session_queue, struct j1939_session, sk_session_queue_entry); if (!first) return; if (j1939_session_activate(first)) { netdev_warn_once(first->priv->ndev, "%s: 0x%p: Identical session is already activated.\n", __func__, first); first->err = -EBUSY; goto activate_next; } else { /* Give receiver some time (arbitrary chosen) to recover */ int time_ms = 0; if (err) time_ms = 10 + prandom_u32_max(16); j1939_tp_schedule_txtimer(first, time_ms); } } void j1939_sk_queue_activate_next(struct j1939_session *session) { struct j1939_sock *jsk; if (!session->sk) return; jsk = j1939_sk(session->sk); spin_lock_bh(&jsk->sk_session_queue_lock); j1939_sk_queue_activate_next_locked(session); spin_unlock_bh(&jsk->sk_session_queue_lock); } static bool j1939_sk_match_dst(struct j1939_sock *jsk, const struct j1939_sk_buff_cb *skcb) { if ((jsk->state & J1939_SOCK_PROMISC)) return true; /* Destination address filter */ if (jsk->addr.src_name && skcb->addr.dst_name) { if (jsk->addr.src_name != skcb->addr.dst_name) return false; } else { /* receive (all sockets) if * - all packages that match our bind() address * - all broadcast on a socket if SO_BROADCAST * is set */ if (j1939_address_is_unicast(skcb->addr.da)) { if (jsk->addr.sa != skcb->addr.da) return false; } else if (!sock_flag(&jsk->sk, SOCK_BROADCAST)) { /* receiving broadcast without SO_BROADCAST * flag is not allowed */ return false; } } /* Source address filter */ if (jsk->state & J1939_SOCK_CONNECTED) { /* receive (all sockets) if * - all packages that match our connect() name or address */ if (jsk->addr.dst_name && skcb->addr.src_name) { if (jsk->addr.dst_name != skcb->addr.src_name) return false; } else { if (jsk->addr.da != skcb->addr.sa) return false; } } /* PGN filter */ if (j1939_pgn_is_valid(jsk->pgn_rx_filter) && jsk->pgn_rx_filter != skcb->addr.pgn) return false; return true; } /* matches skb control buffer (addr) with a j1939 filter */ static bool j1939_sk_match_filter(struct j1939_sock *jsk, const struct j1939_sk_buff_cb *skcb) { const struct j1939_filter *f; int nfilter; spin_lock_bh(&jsk->filters_lock); f = jsk->filters; nfilter = jsk->nfilters; if (!nfilter) /* receive all when no filters are assigned */ goto filter_match_found; for (; nfilter; ++f, --nfilter) { if ((skcb->addr.pgn & f->pgn_mask) != f->pgn) continue; if ((skcb->addr.sa & f->addr_mask) != f->addr) continue; if ((skcb->addr.src_name & f->name_mask) != f->name) continue; goto filter_match_found; } spin_unlock_bh(&jsk->filters_lock); return false; filter_match_found: spin_unlock_bh(&jsk->filters_lock); return true; } static bool j1939_sk_recv_match_one(struct j1939_sock *jsk, const struct j1939_sk_buff_cb *skcb) { if (!(jsk->state & J1939_SOCK_BOUND)) return false; if (!j1939_sk_match_dst(jsk, skcb)) return false; if (!j1939_sk_match_filter(jsk, skcb)) return false; return true; } static void j1939_sk_recv_one(struct j1939_sock *jsk, struct sk_buff *oskb) { const struct j1939_sk_buff_cb *oskcb = j1939_skb_to_cb(oskb); struct j1939_sk_buff_cb *skcb; struct sk_buff *skb; if (oskb->sk == &jsk->sk) return; if (!j1939_sk_recv_match_one(jsk, oskcb)) return; skb = skb_clone(oskb, GFP_ATOMIC); if (!skb) { pr_warn("skb clone failed\n"); return; } can_skb_set_owner(skb, oskb->sk); skcb = j1939_skb_to_cb(skb); skcb->msg_flags &= ~(MSG_DONTROUTE); if (skb->sk) skcb->msg_flags |= MSG_DONTROUTE; if (sock_queue_rcv_skb(&jsk->sk, skb) < 0) kfree_skb(skb); } bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb) { struct j1939_sock *jsk; bool match = false; read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { match = j1939_sk_recv_match_one(jsk, skcb); if (match) break; } read_unlock_bh(&priv->j1939_socks_lock); return match; } void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sock *jsk; read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { j1939_sk_recv_one(jsk, skb); } read_unlock_bh(&priv->j1939_socks_lock); } static void j1939_sk_sock_destruct(struct sock *sk) { struct j1939_sock *jsk = j1939_sk(sk); /* This function will be called by the generic networking code, when * the socket is ultimately closed (sk->sk_destruct). * * The race between * - processing a received CAN frame * (can_receive -> j1939_can_recv) * and accessing j1939_priv * ... and ... * - closing a socket * (j1939_can_rx_unregister -> can_rx_unregister) * and calling the final j1939_priv_put() * * is avoided by calling the final j1939_priv_put() from this * RCU deferred cleanup call. */ if (jsk->priv) { j1939_priv_put(jsk->priv); jsk->priv = NULL; } /* call generic CAN sock destruct */ can_sock_destruct(sk); } static int j1939_sk_init(struct sock *sk) { struct j1939_sock *jsk = j1939_sk(sk); /* Ensure that "sk" is first member in "struct j1939_sock", so that we * can skip it during memset(). */ BUILD_BUG_ON(offsetof(struct j1939_sock, sk) != 0); memset((void *)jsk + sizeof(jsk->sk), 0x0, sizeof(*jsk) - sizeof(jsk->sk)); INIT_LIST_HEAD(&jsk->list); init_waitqueue_head(&jsk->waitq); jsk->sk.sk_priority = j1939_to_sk_priority(6); jsk->sk.sk_reuse = 1; /* per default */ jsk->addr.sa = J1939_NO_ADDR; jsk->addr.da = J1939_NO_ADDR; jsk->addr.pgn = J1939_NO_PGN; jsk->pgn_rx_filter = J1939_NO_PGN; atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); spin_lock_init(&jsk->filters_lock); /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ sock_set_flag(sk, SOCK_RCU_FREE); sk->sk_destruct = j1939_sk_sock_destruct; sk->sk_protocol = CAN_J1939; return 0; } static int j1939_sk_sanity_check(struct sockaddr_can *addr, int len) { if (!addr) return -EDESTADDRREQ; if (len < J1939_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; if (!addr->can_ifindex) return -ENODEV; if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn) && !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) return -EINVAL; return 0; } static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct j1939_sock *jsk = j1939_sk(sock->sk); struct j1939_priv *priv; struct sock *sk; struct net *net; int ret = 0; ret = j1939_sk_sanity_check(addr, len); if (ret) return ret; lock_sock(sock->sk); priv = jsk->priv; sk = sock->sk; net = sock_net(sk); /* Already bound to an interface? */ if (jsk->state & J1939_SOCK_BOUND) { /* A re-bind() to a different interface is not * supported. */ if (jsk->ifindex != addr->can_ifindex) { ret = -EINVAL; goto out_release_sock; } /* drop old references */ j1939_jsk_del(priv, jsk); j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa); } else { struct can_ml_priv *can_ml; struct net_device *ndev; ndev = dev_get_by_index(net, addr->can_ifindex); if (!ndev) { ret = -ENODEV; goto out_release_sock; } can_ml = can_get_ml_priv(ndev); if (!can_ml) { dev_put(ndev); ret = -ENODEV; goto out_release_sock; } if (!(ndev->flags & IFF_UP)) { dev_put(ndev); ret = -ENETDOWN; goto out_release_sock; } priv = j1939_netdev_start(ndev); dev_put(ndev); if (IS_ERR(priv)) { ret = PTR_ERR(priv); goto out_release_sock; } jsk->ifindex = addr->can_ifindex; /* the corresponding j1939_priv_put() is called via * sk->sk_destruct, which points to j1939_sk_sock_destruct() */ j1939_priv_get(priv); jsk->priv = priv; } /* set default transmit pgn */ if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn)) jsk->pgn_rx_filter = addr->can_addr.j1939.pgn; jsk->addr.src_name = addr->can_addr.j1939.name; jsk->addr.sa = addr->can_addr.j1939.addr; /* get new references */ ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa); if (ret) { j1939_netdev_stop(priv); goto out_release_sock; } j1939_jsk_add(priv, jsk); out_release_sock: /* fall through */ release_sock(sock->sk); return ret; } static int j1939_sk_connect(struct socket *sock, struct sockaddr *uaddr, int len, int flags) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct j1939_sock *jsk = j1939_sk(sock->sk); int ret = 0; ret = j1939_sk_sanity_check(addr, len); if (ret) return ret; lock_sock(sock->sk); /* bind() before connect() is mandatory */ if (!(jsk->state & J1939_SOCK_BOUND)) { ret = -EINVAL; goto out_release_sock; } /* A connect() to a different interface is not supported. */ if (jsk->ifindex != addr->can_ifindex) { ret = -EINVAL; goto out_release_sock; } if (!addr->can_addr.j1939.name && addr->can_addr.j1939.addr == J1939_NO_ADDR && !sock_flag(&jsk->sk, SOCK_BROADCAST)) { /* broadcast, but SO_BROADCAST not set */ ret = -EACCES; goto out_release_sock; } jsk->addr.dst_name = addr->can_addr.j1939.name; jsk->addr.da = addr->can_addr.j1939.addr; if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn)) jsk->addr.pgn = addr->can_addr.j1939.pgn; jsk->state |= J1939_SOCK_CONNECTED; out_release_sock: /* fall through */ release_sock(sock->sk); return ret; } static void j1939_sk_sock2sockaddr_can(struct sockaddr_can *addr, const struct j1939_sock *jsk, int peer) { /* There are two holes (2 bytes and 3 bytes) to clear to avoid * leaking kernel information to user space. */ memset(addr, 0, J1939_MIN_NAMELEN); addr->can_family = AF_CAN; addr->can_ifindex = jsk->ifindex; addr->can_addr.j1939.pgn = jsk->addr.pgn; if (peer) { addr->can_addr.j1939.name = jsk->addr.dst_name; addr->can_addr.j1939.addr = jsk->addr.da; } else { addr->can_addr.j1939.name = jsk->addr.src_name; addr->can_addr.j1939.addr = jsk->addr.sa; } } static int j1939_sk_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct j1939_sock *jsk = j1939_sk(sk); int ret = 0; lock_sock(sk); if (peer && !(jsk->state & J1939_SOCK_CONNECTED)) { ret = -EADDRNOTAVAIL; goto failure; } j1939_sk_sock2sockaddr_can(addr, jsk, peer); ret = J1939_MIN_NAMELEN; failure: release_sock(sk); return ret; } static int j1939_sk_release(struct socket *sock) { struct sock *sk = sock->sk; struct j1939_sock *jsk; if (!sk) return 0; lock_sock(sk); jsk = j1939_sk(sk); if (jsk->state & J1939_SOCK_BOUND) { struct j1939_priv *priv = jsk->priv; if (wait_event_interruptible(jsk->waitq, !j1939_sock_pending_get(&jsk->sk))) { j1939_cancel_active_session(priv, sk); j1939_sk_queue_drop_all(priv, jsk, ESHUTDOWN); } j1939_jsk_del(priv, jsk); j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa); j1939_netdev_stop(priv); } kfree(jsk->filters); sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); return 0; } static int j1939_sk_setsockopt_flag(struct j1939_sock *jsk, sockptr_t optval, unsigned int optlen, int flag) { int tmp; if (optlen != sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, optval, optlen)) return -EFAULT; lock_sock(&jsk->sk); if (tmp) jsk->state |= flag; else jsk->state &= ~flag; release_sock(&jsk->sk); return tmp; } static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct j1939_sock *jsk = j1939_sk(sk); int tmp, count = 0, ret = 0; struct j1939_filter *filters = NULL, *ofilters; if (level != SOL_CAN_J1939) return -EINVAL; switch (optname) { case SO_J1939_FILTER: if (!sockptr_is_null(optval) && optlen != 0) { struct j1939_filter *f; int c; if (optlen % sizeof(*filters) != 0) return -EINVAL; if (optlen > J1939_FILTER_MAX * sizeof(struct j1939_filter)) return -EINVAL; count = optlen / sizeof(*filters); filters = memdup_sockptr(optval, optlen); if (IS_ERR(filters)) return PTR_ERR(filters); for (f = filters, c = count; c; f++, c--) { f->name &= f->name_mask; f->pgn &= f->pgn_mask; f->addr &= f->addr_mask; } } lock_sock(&jsk->sk); spin_lock_bh(&jsk->filters_lock); ofilters = jsk->filters; jsk->filters = filters; jsk->nfilters = count; spin_unlock_bh(&jsk->filters_lock); release_sock(&jsk->sk); kfree(ofilters); return 0; case SO_J1939_PROMISC: return j1939_sk_setsockopt_flag(jsk, optval, optlen, J1939_SOCK_PROMISC); case SO_J1939_ERRQUEUE: ret = j1939_sk_setsockopt_flag(jsk, optval, optlen, J1939_SOCK_ERRQUEUE); if (ret < 0) return ret; if (!(jsk->state & J1939_SOCK_ERRQUEUE)) skb_queue_purge(&sk->sk_error_queue); return ret; case SO_J1939_SEND_PRIO: if (optlen != sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, optval, optlen)) return -EFAULT; if (tmp < 0 || tmp > 7) return -EDOM; if (tmp < 2 && !capable(CAP_NET_ADMIN)) return -EPERM; lock_sock(&jsk->sk); jsk->sk.sk_priority = j1939_to_sk_priority(tmp); release_sock(&jsk->sk); return 0; default: return -ENOPROTOOPT; } } static int j1939_sk_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct j1939_sock *jsk = j1939_sk(sk); int ret, ulen; /* set defaults for using 'int' properties */ int tmp = 0; int len = sizeof(tmp); void *val = &tmp; if (level != SOL_CAN_J1939) return -EINVAL; if (get_user(ulen, optlen)) return -EFAULT; if (ulen < 0) return -EINVAL; lock_sock(&jsk->sk); switch (optname) { case SO_J1939_PROMISC: tmp = (jsk->state & J1939_SOCK_PROMISC) ? 1 : 0; break; case SO_J1939_ERRQUEUE: tmp = (jsk->state & J1939_SOCK_ERRQUEUE) ? 1 : 0; break; case SO_J1939_SEND_PRIO: tmp = j1939_prio(jsk->sk.sk_priority); break; default: ret = -ENOPROTOOPT; goto no_copy; } /* copy to user, based on 'len' & 'val' * but most sockopt's are 'int' properties, and have 'len' & 'val' * left unchanged, but instead modified 'tmp' */ if (len > ulen) ret = -EFAULT; else if (put_user(len, optlen)) ret = -EFAULT; else if (copy_to_user(optval, val, len)) ret = -EFAULT; else ret = 0; no_copy: release_sock(&jsk->sk); return ret; } static int j1939_sk_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; struct j1939_sk_buff_cb *skcb; int ret = 0; if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE | MSG_CMSG_COMPAT)) return -EINVAL; if (flags & MSG_ERRQUEUE) return sock_recv_errqueue(sock->sk, msg, size, SOL_CAN_J1939, SCM_J1939_ERRQUEUE); skb = skb_recv_datagram(sk, flags, 0, &ret); if (!skb) return ret; if (size < skb->len) msg->msg_flags |= MSG_TRUNC; else size = skb->len; ret = memcpy_to_msg(msg, skb->data, size); if (ret < 0) { skb_free_datagram(sk, skb); return ret; } skcb = j1939_skb_to_cb(skb); if (j1939_address_is_valid(skcb->addr.da)) put_cmsg(msg, SOL_CAN_J1939, SCM_J1939_DEST_ADDR, sizeof(skcb->addr.da), &skcb->addr.da); if (skcb->addr.dst_name) put_cmsg(msg, SOL_CAN_J1939, SCM_J1939_DEST_NAME, sizeof(skcb->addr.dst_name), &skcb->addr.dst_name); put_cmsg(msg, SOL_CAN_J1939, SCM_J1939_PRIO, sizeof(skcb->priority), &skcb->priority); if (msg->msg_name) { struct sockaddr_can *paddr = msg->msg_name; msg->msg_namelen = J1939_MIN_NAMELEN; memset(msg->msg_name, 0, msg->msg_namelen); paddr->can_family = AF_CAN; paddr->can_ifindex = skb->skb_iif; paddr->can_addr.j1939.name = skcb->addr.src_name; paddr->can_addr.j1939.addr = skcb->addr.sa; paddr->can_addr.j1939.pgn = skcb->addr.pgn; } sock_recv_ts_and_drops(msg, sk, skb); msg->msg_flags |= skcb->msg_flags; skb_free_datagram(sk, skb); return size; } static struct sk_buff *j1939_sk_alloc_skb(struct net_device *ndev, struct sock *sk, struct msghdr *msg, size_t size, int *errcode) { struct j1939_sock *jsk = j1939_sk(sk); struct j1939_sk_buff_cb *skcb; struct sk_buff *skb; int ret; skb = sock_alloc_send_skb(sk, size + sizeof(struct can_frame) - sizeof(((struct can_frame *)NULL)->data) + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &ret); if (!skb) goto failure; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = ndev->ifindex; can_skb_prv(skb)->skbcnt = 0; skb_reserve(skb, offsetof(struct can_frame, data)); ret = memcpy_from_msg(skb_put(skb, size), msg, size); if (ret < 0) goto free_skb; skb->dev = ndev; skcb = j1939_skb_to_cb(skb); memset(skcb, 0, sizeof(*skcb)); skcb->addr = jsk->addr; skcb->priority = j1939_prio(sk->sk_priority); if (msg->msg_name) { struct sockaddr_can *addr = msg->msg_name; if (addr->can_addr.j1939.name || addr->can_addr.j1939.addr != J1939_NO_ADDR) { skcb->addr.dst_name = addr->can_addr.j1939.name; skcb->addr.da = addr->can_addr.j1939.addr; } if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn)) skcb->addr.pgn = addr->can_addr.j1939.pgn; } *errcode = ret; return skb; free_skb: kfree_skb(skb); failure: *errcode = ret; return NULL; } static size_t j1939_sk_opt_stats_get_size(enum j1939_sk_errqueue_type type) { switch (type) { case J1939_ERRQUEUE_RX_RTS: return nla_total_size(sizeof(u32)) + /* J1939_NLA_TOTAL_SIZE */ nla_total_size(sizeof(u32)) + /* J1939_NLA_PGN */ nla_total_size(sizeof(u64)) + /* J1939_NLA_SRC_NAME */ nla_total_size(sizeof(u64)) + /* J1939_NLA_DEST_NAME */ nla_total_size(sizeof(u8)) + /* J1939_NLA_SRC_ADDR */ nla_total_size(sizeof(u8)) + /* J1939_NLA_DEST_ADDR */ 0; default: return nla_total_size(sizeof(u32)) + /* J1939_NLA_BYTES_ACKED */ 0; } } static struct sk_buff * j1939_sk_get_timestamping_opt_stats(struct j1939_session *session, enum j1939_sk_errqueue_type type) { struct sk_buff *stats; u32 size; stats = alloc_skb(j1939_sk_opt_stats_get_size(type), GFP_ATOMIC); if (!stats) return NULL; if (session->skcb.addr.type == J1939_SIMPLE) size = session->total_message_size; else size = min(session->pkt.tx_acked * 7, session->total_message_size); switch (type) { case J1939_ERRQUEUE_RX_RTS: nla_put_u32(stats, J1939_NLA_TOTAL_SIZE, session->total_message_size); nla_put_u32(stats, J1939_NLA_PGN, session->skcb.addr.pgn); nla_put_u64_64bit(stats, J1939_NLA_SRC_NAME, session->skcb.addr.src_name, J1939_NLA_PAD); nla_put_u64_64bit(stats, J1939_NLA_DEST_NAME, session->skcb.addr.dst_name, J1939_NLA_PAD); nla_put_u8(stats, J1939_NLA_SRC_ADDR, session->skcb.addr.sa); nla_put_u8(stats, J1939_NLA_DEST_ADDR, session->skcb.addr.da); break; default: nla_put_u32(stats, J1939_NLA_BYTES_ACKED, size); } return stats; } static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk, enum j1939_sk_errqueue_type type) { struct j1939_priv *priv = session->priv; struct j1939_sock *jsk; struct sock_exterr_skb *serr; struct sk_buff *skb; char *state = "UNK"; int err; jsk = j1939_sk(sk); if (!(jsk->state & J1939_SOCK_ERRQUEUE)) return; switch (type) { case J1939_ERRQUEUE_TX_ACK: if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) return; break; case J1939_ERRQUEUE_TX_SCHED: if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) return; break; case J1939_ERRQUEUE_TX_ABORT: break; case J1939_ERRQUEUE_RX_RTS: fallthrough; case J1939_ERRQUEUE_RX_DPO: fallthrough; case J1939_ERRQUEUE_RX_ABORT: if (!(sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE)) return; break; default: netdev_err(priv->ndev, "Unknown errqueue type %i\n", type); } skb = j1939_sk_get_timestamping_opt_stats(session, type); if (!skb) return; skb->tstamp = ktime_get_real(); BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb)); serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); switch (type) { case J1939_ERRQUEUE_TX_ACK: serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = SCM_TSTAMP_ACK; state = "TX ACK"; break; case J1939_ERRQUEUE_TX_SCHED: serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = SCM_TSTAMP_SCHED; state = "TX SCH"; break; case J1939_ERRQUEUE_TX_ABORT: serr->ee.ee_errno = session->err; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; serr->ee.ee_info = J1939_EE_INFO_TX_ABORT; state = "TX ABT"; break; case J1939_ERRQUEUE_RX_RTS: serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; serr->ee.ee_info = J1939_EE_INFO_RX_RTS; state = "RX RTS"; break; case J1939_ERRQUEUE_RX_DPO: serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; serr->ee.ee_info = J1939_EE_INFO_RX_DPO; state = "RX DPO"; break; case J1939_ERRQUEUE_RX_ABORT: serr->ee.ee_errno = session->err; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; serr->ee.ee_info = J1939_EE_INFO_RX_ABORT; state = "RX ABT"; break; } serr->opt_stats = true; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) serr->ee.ee_data = session->tskey; netdev_dbg(session->priv->ndev, "%s: 0x%p tskey: %i, state: %s\n", __func__, session, session->tskey, state); err = sock_queue_err_skb(sk, skb); if (err) kfree_skb(skb); }; void j1939_sk_errqueue(struct j1939_session *session, enum j1939_sk_errqueue_type type) { struct j1939_priv *priv = session->priv; struct j1939_sock *jsk; if (session->sk) { /* send TX notifications to the socket of origin */ __j1939_sk_errqueue(session, session->sk, type); return; } /* spread RX notifications to all sockets subscribed to this session */ read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { if (j1939_sk_recv_match_one(jsk, &session->skcb)) __j1939_sk_errqueue(session, &jsk->sk, type); } read_unlock_bh(&priv->j1939_socks_lock); }; void j1939_sk_send_loop_abort(struct sock *sk, int err) { struct j1939_sock *jsk = j1939_sk(sk); if (jsk->state & J1939_SOCK_ERRQUEUE) return; sk->sk_err = err; sk_error_report(sk); } static int j1939_sk_send_loop(struct j1939_priv *priv, struct sock *sk, struct msghdr *msg, size_t size) { struct j1939_sock *jsk = j1939_sk(sk); struct j1939_session *session = j1939_sk_get_incomplete_session(jsk); struct sk_buff *skb; size_t segment_size, todo_size; int ret = 0; if (session && session->total_message_size != session->total_queued_size + size) { j1939_session_put(session); return -EIO; } todo_size = size; while (todo_size) { struct j1939_sk_buff_cb *skcb; segment_size = min_t(size_t, J1939_MAX_TP_PACKET_SIZE, todo_size); /* Allocate skb for one segment */ skb = j1939_sk_alloc_skb(priv->ndev, sk, msg, segment_size, &ret); if (ret) break; skcb = j1939_skb_to_cb(skb); if (!session) { /* at this point the size should be full size * of the session */ skcb->offset = 0; session = j1939_tp_send(priv, skb, size); if (IS_ERR(session)) { ret = PTR_ERR(session); goto kfree_skb; } if (j1939_sk_queue_session(session)) { /* try to activate session if we a * fist in the queue */ if (!j1939_session_activate(session)) { j1939_tp_schedule_txtimer(session, 0); } else { ret = -EBUSY; session->err = ret; j1939_sk_queue_drop_all(priv, jsk, EBUSY); break; } } } else { skcb->offset = session->total_queued_size; j1939_session_skb_queue(session, skb); } todo_size -= segment_size; session->total_queued_size += segment_size; } switch (ret) { case 0: /* OK */ if (todo_size) netdev_warn(priv->ndev, "no error found and not completely queued?! %zu\n", todo_size); ret = size; break; case -ERESTARTSYS: ret = -EINTR; fallthrough; case -EAGAIN: /* OK */ if (todo_size != size) ret = size - todo_size; break; default: /* ERROR */ break; } if (session) j1939_session_put(session); return ret; kfree_skb: kfree_skb(skb); return ret; } static int j1939_sk_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct j1939_sock *jsk = j1939_sk(sk); struct j1939_priv *priv; int ifindex; int ret; lock_sock(sock->sk); /* various socket state tests */ if (!(jsk->state & J1939_SOCK_BOUND)) { ret = -EBADFD; goto sendmsg_done; } priv = jsk->priv; ifindex = jsk->ifindex; if (!jsk->addr.src_name && jsk->addr.sa == J1939_NO_ADDR) { /* no source address assigned yet */ ret = -EBADFD; goto sendmsg_done; } /* deal with provided destination address info */ if (msg->msg_name) { struct sockaddr_can *addr = msg->msg_name; if (msg->msg_namelen < J1939_MIN_NAMELEN) { ret = -EINVAL; goto sendmsg_done; } if (addr->can_family != AF_CAN) { ret = -EINVAL; goto sendmsg_done; } if (addr->can_ifindex && addr->can_ifindex != ifindex) { ret = -EBADFD; goto sendmsg_done; } if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn) && !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) { ret = -EINVAL; goto sendmsg_done; } if (!addr->can_addr.j1939.name && addr->can_addr.j1939.addr == J1939_NO_ADDR && !sock_flag(sk, SOCK_BROADCAST)) { /* broadcast, but SO_BROADCAST not set */ ret = -EACCES; goto sendmsg_done; } } else { if (!jsk->addr.dst_name && jsk->addr.da == J1939_NO_ADDR && !sock_flag(sk, SOCK_BROADCAST)) { /* broadcast, but SO_BROADCAST not set */ ret = -EACCES; goto sendmsg_done; } } ret = j1939_sk_send_loop(priv, sk, msg, size); sendmsg_done: release_sock(sock->sk); return ret; } void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) { struct j1939_sock *jsk; int error_code = ENETDOWN; read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { jsk->sk.sk_err = error_code; if (!sock_flag(&jsk->sk, SOCK_DEAD)) sk_error_report(&jsk->sk); j1939_sk_queue_drop_all(priv, jsk, error_code); } read_unlock_bh(&priv->j1939_socks_lock); } static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { /* no ioctls for socket layer -> hand it down to NIC layer */ return -ENOIOCTLCMD; } static const struct proto_ops j1939_ops = { .family = PF_CAN, .release = j1939_sk_release, .bind = j1939_sk_bind, .connect = j1939_sk_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = j1939_sk_getname, .poll = datagram_poll, .ioctl = j1939_sk_no_ioctlcmd, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = j1939_sk_setsockopt, .getsockopt = j1939_sk_getsockopt, .sendmsg = j1939_sk_sendmsg, .recvmsg = j1939_sk_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; static struct proto j1939_proto __read_mostly = { .name = "CAN_J1939", .owner = THIS_MODULE, .obj_size = sizeof(struct j1939_sock), .init = j1939_sk_init, }; const struct can_proto j1939_can_proto = { .type = SOCK_DGRAM, .protocol = CAN_J1939, .ops = &j1939_ops, .prot = &j1939_proto, }; |
| 103 103 39 134 3012 3 81 108 108 108 14 108 1095 1097 1095 1095 1097 3010 3012 3013 3117 3010 90 682 73 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #ifndef _LINUX_BPF_H #define _LINUX_BPF_H 1 #include <uapi/linux/bpf.h> #include <linux/workqueue.h> #include <linux/file.h> #include <linux/percpu.h> #include <linux/err.h> #include <linux/rbtree_latch.h> #include <linux/numa.h> #include <linux/mm_types.h> #include <linux/wait.h> #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/capability.h> #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> #include <linux/bpfptr.h> struct bpf_verifier_env; struct bpf_verifier_log; struct perf_event; struct bpf_prog; struct bpf_prog_aux; struct bpf_map; struct sock; struct seq_file; struct btf; struct btf_type; struct exception_table_entry; struct seq_operations; struct bpf_iter_aux_info; struct bpf_local_storage; struct bpf_local_storage_map; struct kobject; struct mem_cgroup; struct module; struct bpf_func_state; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; bpf_iter_fini_seq_priv_t fini_seq_private; u32 seq_priv_size; }; /* map is generic key/value storage optionally accessible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ int (*map_alloc_check)(union bpf_attr *attr); struct bpf_map *(*map_alloc)(union bpf_attr *attr); void (*map_release)(struct bpf_map *map, struct file *map_file); void (*map_free)(struct bpf_map *map); int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key); void (*map_release_uref)(struct bpf_map *map); void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_lookup_and_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_map *map, void *key); int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); int (*map_pop_elem)(struct bpf_map *map, void *value); int (*map_peek_elem)(struct bpf_map *map, void *value); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); /* If need_defer is true, the implementation should guarantee that * the to-be-put element is still alive before the bpf program, which * may manipulate it, exists. */ void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); /* Prog poke tracking helpers. */ int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new); /* Direct value access helpers. */ int (*map_direct_value_addr)(const struct bpf_map *map, u64 *imm, u32 off); int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); /* Functions called by bpf_local_storage maps */ int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, void *owner, u32 size); void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, void *owner, u32 size); struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ int (*map_redirect)(struct bpf_map *map, u32 ifindex, u64 flags); /* map_meta_equal must be implemented for maps that can be * used as an inner map. It is a runtime check to ensure * an inner map can be inserted to an outer map. * * Some properties of the inner map has been used during the * verification time. When inserting an inner map at the runtime, * map_meta_equal has to ensure the inserting map has the same * properties that the verifier has used earlier. */ bool (*map_meta_equal)(const struct bpf_map *meta0, const struct bpf_map *meta1); int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); int (*map_for_each_callback)(struct bpf_map *map, void *callback_fn, void *callback_ctx, u64 flags); /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; /* bpf_iter info used to open a seq_file */ const struct bpf_iter_seq_info *iter_seq_info; }; struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). */ const struct bpf_map_ops *ops ____cacheline_aligned; struct bpf_map *inner_map_meta; #ifdef CONFIG_SECURITY void *security; #endif enum bpf_map_type map_type; u32 key_size; u32 value_size; u32 max_entries; u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif char name[BPF_OBJ_NAME_LEN]; u32 btf_vmlinux_value_type_id; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ /* 22 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ atomic64_t refcnt ____cacheline_aligned; atomic64_t usercnt; /* rcu is used before freeing and work is only used during freeing */ union { struct work_struct work; struct rcu_head rcu; }; struct mutex freeze_mutex; atomic64_t writecnt; bool free_after_mult_rcu_gp; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) { return map->spin_lock_off >= 0; } static inline bool map_value_has_timer(const struct bpf_map *map) { return map->timer_off >= 0; } static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { if (unlikely(map_value_has_spin_lock(map))) memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); if (unlikely(map_value_has_timer(map))) memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); } /* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0; if (unlikely(map_value_has_spin_lock(map))) { s_off = map->spin_lock_off; s_sz = sizeof(struct bpf_spin_lock); } if (unlikely(map_value_has_timer(map))) { t_off = map->timer_off; t_sz = sizeof(struct bpf_timer); } if (unlikely(s_sz || t_sz)) { if (s_off < t_off || !s_sz) { swap(s_off, t_off); swap(s_sz, t_sz); } memcpy(dst, src, t_off); memcpy(dst + t_off + t_sz, src + t_off + t_sz, s_off - t_off - t_sz); memcpy(dst + s_off + s_sz, src + s_off + s_sz, map->value_size - s_off - s_sz); } else { memcpy(dst, src, map->value_size); } } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; struct bpf_offloaded_map; struct bpf_map_dev_ops { int (*map_get_next_key)(struct bpf_offloaded_map *map, void *key, void *next_key); int (*map_lookup_elem)(struct bpf_offloaded_map *map, void *key, void *value); int (*map_update_elem)(struct bpf_offloaded_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key); }; struct bpf_offloaded_map { struct bpf_map map; struct net_device *netdev; const struct bpf_map_dev_ops *dev_ops; void *dev_priv; struct list_head offloads; }; static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) { return container_of(map, struct bpf_offloaded_map, map); } static inline bool bpf_map_offload_neutral(const struct bpf_map *map) { return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) && map->ops->map_seq_show_elem; } int map_check_no_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); bool bpf_map_meta_equal(const struct bpf_map *meta0, const struct bpf_map *meta1); extern const struct bpf_map_ops bpf_map_offload_ops; /* bpf_type_flag contains a set of flags that are applicable to the values of * arg_type, ret_type and reg_type. For example, a pointer value may be null, * or a memory is read-only. We classify types into two categories: base types * and extended types. Extended types are base types combined with a type flag. * * Currently there are no more than 32 base types in arg_type, ret_type and * reg_types. */ #define BPF_BASE_TYPE_BITS 8 enum bpf_type_flag { /* PTR may be NULL. */ PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS), /* MEM is read-only. When applied on bpf_arg, it indicates the arg is * compatible with both mutable and immutable memory. */ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), /* MEM was "allocated" from a different helper, and cannot be mixed * with regular non-MEM_ALLOC'ed MEM types. */ MEM_ALLOC = BIT(2 + BPF_BASE_TYPE_BITS), __BPF_TYPE_LAST_FLAG = MEM_ALLOC, }; /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) /* Max number of all types. */ #define BPF_TYPE_LIMIT (__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1)) /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ /* the following constraints used to prototype * bpf_map_lookup/update/delete_elem() functions */ ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized, * helper function must fill all bytes or clear * them in error case. */ ARG_CONST_SIZE, /* number of bytes accessed from memory */ ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ __BPF_ARG_TYPE_MAX, /* Extended arg_types. */ ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE, ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM, ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX, ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_ARG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* type of values returned from helper functions */ enum bpf_return_type { RET_INTEGER, /* function returns integer */ RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_SOCKET, /* returns a pointer to a socket */ RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */ RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */ RET_PTR_TO_ALLOC_MEM, /* returns a pointer to dynamically allocated memory */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ __BPF_RET_TYPE_MAX, /* Extended ret_types. */ RET_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE, RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_RET_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL * instructions after verifying */ struct bpf_func_proto { u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool gpl_only; bool pkt_access; enum bpf_return_type ret_type; union { struct { enum bpf_arg_type arg1_type; enum bpf_arg_type arg2_type; enum bpf_arg_type arg3_type; enum bpf_arg_type arg4_type; enum bpf_arg_type arg5_type; }; enum bpf_arg_type arg_type[5]; }; union { struct { u32 *arg1_btf_id; u32 *arg2_btf_id; u32 *arg3_btf_id; u32 *arg4_btf_id; u32 *arg5_btf_id; }; u32 *arg_btf_id[5]; }; int *ret_btf_id; /* return value btf_id */ bool (*allowed)(const struct bpf_prog *prog); }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is * the first argument to eBPF programs. * For socket filters: 'struct bpf_context *' == 'struct sk_buff *' */ struct bpf_context; enum bpf_access_type { BPF_READ = 1, BPF_WRITE = 2 }; /* types of values stored in eBPF registers */ /* Pointer types represent: * pointer * pointer + imm * pointer + (u16) var * pointer + (u16) var + imm * if (range > 0) then [ptr, ptr + range - off) is safe to access * if (id > 0) means that some 'var' was added * if (off > 0) means that 'imm' was added */ enum bpf_reg_type { NOT_INIT = 0, /* nothing was written into register */ SCALAR_VALUE, /* reg doesn't contain a valid pointer */ PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_KEY, /* reg points to a map element key */ PTR_TO_STACK, /* reg == frame_pointer + offset */ PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ PTR_TO_SOCKET, /* reg points to struct bpf_sock */ PTR_TO_SOCK_COMMON, /* reg points to sock_common */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ /* PTR_TO_BTF_ID points to a kernel struct that does not need * to be null checked by the BPF program. This does not imply the * pointer is _not_ null and in practice this can easily be a null * pointer when reading pointer chains. The assumption is program * context will handle null pointer dereference typically via fault * handling. The verifier must keep this in mind and can make no * assumptions about null or non-null when doing branch analysis. * Further, when passed into helpers the helpers can not, without * additional context, assume the value is non-null. */ PTR_TO_BTF_ID, /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not * been checked for null. Used primarily to inform the verifier * an explicit null check is required for this struct. */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ PTR_TO_FUNC, /* reg points to a bpf program function */ __BPF_REG_TYPE_MAX, /* Extended reg_types. */ PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_REG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* The information passed from prog-specific *_is_valid_access * back to the verifier. */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; union { int ctx_field_size; struct { struct btf *btf; u32 btf_id; }; }; struct bpf_verifier_log *log; /* for verbose logs */ }; static inline void bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) { aux->ctx_field_size = size; } static inline bool bpf_pseudo_func(const struct bpf_insn *insn) { return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && insn->src_reg == BPF_PSEUDO_FUNC; } struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); }; struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto * (*get_func_proto)(enum bpf_func_id func_id, const struct bpf_prog *prog); /* return true if 'size' wide access at offset 'off' within bpf_context * with 'type' (read or write) is allowed */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); int (*gen_ld_abs)(const struct bpf_insn *orig, struct bpf_insn *insn_buf); u32 (*convert_ctx_access)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); bool (*check_kfunc_call)(u32 kfunc_btf_id); }; struct bpf_prog_offload_ops { /* verifier basic callbacks */ int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); /* verifier optimization callbacks (called after .finalize) */ int (*replace_insn)(struct bpf_verifier_env *env, u32 off, struct bpf_insn *insn); int (*remove_insns)(struct bpf_verifier_env *env, u32 off, u32 cnt); /* program management callbacks */ int (*prepare)(struct bpf_prog *prog); int (*translate)(struct bpf_prog *prog); void (*destroy)(struct bpf_prog *prog); }; struct bpf_prog_offload { struct bpf_prog *prog; struct net_device *netdev; struct bpf_offload_dev *offdev; void *dev_priv; struct list_head offloads; bool dev_state; bool opt_failed; void *jited_image; u32 jited_len; }; enum bpf_cgroup_storage_type { BPF_CGROUP_STORAGE_SHARED, BPF_CGROUP_STORAGE_PERCPU, __BPF_CGROUP_STORAGE_MAX }; #define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX /* The longest tracepoint has 12 args. * See include/trace/bpf_probe.h */ #define MAX_BPF_FUNC_ARGS 12 /* The maximum number of arguments passed through registers * a single function may have. */ #define MAX_BPF_FUNC_REG_ARGS 5 struct btf_func_model { u8 ret_size; u8 nr_args; u8 arg_size[MAX_BPF_FUNC_ARGS]; }; /* Restore arguments before returning from trampoline to let original function * continue executing. This flag is used for fentry progs when there are no * fexit progs. */ #define BPF_TRAMP_F_RESTORE_REGS BIT(0) /* Call original function after fentry progs, but before fexit progs. * Makes sense for fentry/fexit, normal calls and indirect calls. */ #define BPF_TRAMP_F_CALL_ORIG BIT(1) /* Skip current frame and return to parent. Makes sense for fentry/fexit * programs only. Should not be used with normal calls and indirect calls. */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) /* Store IP address of the caller on the trampoline stack, * so it's available for trampoline's programs. */ #define BPF_TRAMP_F_IP_ARG BIT(3) /* Return the return value of fentry prog. Only used by bpf_struct_ops. */ #define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ #define BPF_MAX_TRAMP_PROGS 38 struct bpf_tramp_progs { struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS]; int nr_progs; }; /* Different use cases for BPF trampoline: * 1. replace nop at the function entry (kprobe equivalent) * flags = BPF_TRAMP_F_RESTORE_REGS * fentry = a set of programs to run before returning from trampoline * * 2. replace nop at the function entry (kprobe + kretprobe equivalent) * flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME * orig_call = fentry_ip + MCOUNT_INSN_SIZE * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function * * 3. replace direct call instruction anywhere in the function body * or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid) * With flags = 0 * fentry = a set of programs to run before returning from trampoline * With flags = BPF_TRAMP_F_CALL_ORIG * orig_call = original callback addr or direct function addr * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function */ struct bpf_tramp_image; int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_progs *tprogs, void *orig_call); /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(struct bpf_prog *prog); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); struct bpf_ksym { unsigned long start; unsigned long end; char name[KSYM_NAME_LEN]; struct list_head lnode; struct latch_tree_node tnode; bool prog; }; enum bpf_tramp_prog_type { BPF_TRAMP_FENTRY, BPF_TRAMP_FEXIT, BPF_TRAMP_MODIFY_RETURN, BPF_TRAMP_MAX, BPF_TRAMP_REPLACE, /* more than MAX */ }; struct bpf_tramp_image { void *image; struct bpf_ksym ksym; struct percpu_ref pcref; void *ip_after_call; void *ip_epilogue; union { struct rcu_head rcu; struct work_struct work; }; }; struct bpf_trampoline { /* hlist for trampoline_table */ struct hlist_node hlist; /* serializes access to fields of this trampoline */ struct mutex mutex; refcount_t refcnt; u64 key; struct { struct btf_func_model model; void *addr; bool ftrace_managed; } func; /* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF * program by replacing one of its functions. func.addr is the address * of the function it replaced. */ struct bpf_prog *extension_prog; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; /* Number of attached programs. A counter per kind. */ int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ struct bpf_tramp_image *cur_image; u64 selector; struct module *mod; }; struct bpf_attach_target_info { struct btf_func_model fmodel; long tgt_addr; const char *tgt_name; const struct btf_type *tgt_type; }; #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */ struct bpf_dispatcher_prog { struct bpf_prog *prog; refcount_t users; }; struct bpf_dispatcher { /* dispatcher mutex */ struct mutex mutex; void *func; struct bpf_dispatcher_prog progs[BPF_DISPATCHER_MAX]; int num_progs; void *image; u32 image_off; struct bpf_ksym ksym; }; static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, const struct bpf_insn *)) { return bpf_func(ctx, insnsi); } #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs); #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ .progs = {}, \ .num_progs = 0, \ .image = NULL, \ .image_off = 0, \ .ksym = { \ .name = #_name, \ .lnode = LIST_HEAD_INIT(_name.ksym.lnode), \ }, \ } #define DEFINE_BPF_DISPATCHER(name) \ noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ unsigned int (*bpf_func)(const void *, \ const struct bpf_insn *)) \ { \ return bpf_func(ctx, insnsi); \ } \ EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ struct bpf_dispatcher bpf_dispatcher_##name = \ BPF_DISPATCHER_INIT(bpf_dispatcher_##name); #define DECLARE_BPF_DISPATCHER(name) \ unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ unsigned int (*bpf_func)(const void *, \ const struct bpf_insn *)); \ extern struct bpf_dispatcher bpf_dispatcher_##name; #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ void *bpf_jit_alloc_exec_page(void); void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); int bpf_jit_charge_modmem(u32 pages); void bpf_jit_uncharge_modmem(u32 pages); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) { return -ENOTSUPP; } static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) { return -ENOTSUPP; } static inline struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info) { return NULL; } static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) #define DECLARE_BPF_DISPATCHER(name) #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nop_func #define BPF_DISPATCHER_PTR(name) NULL static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to) {} static inline bool is_bpf_image_address(unsigned long address) { return false; } #endif struct bpf_func_info_aux { u16 linkage; bool unreliable; }; enum bpf_jit_poke_reason { BPF_POKE_REASON_TAIL_CALL, }; /* Descriptor of pokes pointing /into/ the JITed image. */ struct bpf_jit_poke_descriptor { void *tailcall_target; void *tailcall_bypass; void *bypass_addr; void *aux; union { struct { struct bpf_map *map; u32 key; } tail_call; }; bool tailcall_target_stable; u8 adj_off; u16 reason; u32 insn_idx; }; /* reg_type info for ctx arguments */ struct bpf_ctx_arg_aux { u32 offset; enum bpf_reg_type reg_type; u32 btf_id; }; struct btf_mod_pair { struct btf *btf; struct module *module; }; struct bpf_kfunc_desc_tab; struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; u32 used_btf_cnt; u32 max_ctx_offset; u32 max_pkt_offset; u32 max_tp_access; u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 ctx_arg_info_size; u32 max_rdonly_access; u32 max_rdwr_access; struct btf *attach_btf; const struct bpf_ctx_arg_aux *ctx_arg_info; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; struct bpf_trampoline *dst_trampoline; enum bpf_prog_type saved_dst_prog_type; enum bpf_attach_type saved_dst_attach_type; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ const char *attach_func_name; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ struct bpf_jit_poke_descriptor *poke_tab; struct bpf_kfunc_desc_tab *kfunc_tab; u32 size_poke_tab; struct bpf_ksym ksym; const struct bpf_prog_ops *ops; struct bpf_map **used_maps; struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ struct btf_mod_pair *used_btfs; struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY void *security; #endif struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; struct bpf_func_info_aux *func_info_aux; /* bpf_line_info loaded from userspace. linfo->insn_off * has the xlated insn offset. * Both the main and sub prog share the same linfo. * The subprog can access its first linfo by * using the linfo_idx. */ struct bpf_line_info *linfo; /* jited_linfo is the jited addr of the linfo. It has a * one to one mapping to linfo: * jited_linfo[i] is the jited addr for the linfo[i]->insn_off. * Both the main and sub prog share the same jited_linfo. * The subprog can access its first jited_linfo by * using the linfo_idx. */ void **jited_linfo; u32 func_info_cnt; u32 nr_linfo; /* subprog can use linfo_idx to access its first linfo and * jited_linfo. * main prog always has linfo_idx == 0 */ u32 linfo_idx; u32 num_exentries; struct exception_table_entry *extable; union { struct work_struct work; struct rcu_head rcu; }; }; struct bpf_array_aux { /* 'Ownership' of prog array is claimed by the first program that * is going to use this map or by the first program which FD is * stored in the map to make sure that all callers and callees have * the same prog type and JITed flag. */ struct { spinlock_t lock; enum bpf_prog_type type; bool jited; } owner; /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; struct mutex poke_mutex; struct work_struct work; }; struct bpf_link { atomic64_t refcnt; u32 id; enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; struct work_struct work; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); int (*fill_link_info)(const struct bpf_link *link, struct bpf_link_info *info); }; struct bpf_link_primer { struct bpf_link *link; struct file *file; int fd; u32 id; }; struct bpf_struct_ops_value; struct btf_member; #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 struct bpf_struct_ops { const struct bpf_verifier_ops *verifier_ops; int (*init)(struct btf *btf); int (*check_member)(const struct btf_type *t, const struct btf_member *member); int (*init_member)(const struct btf_type *t, const struct btf_member *member, void *kdata, const void *udata); int (*reg)(void *kdata); void (*unreg)(void *kdata); const struct btf_type *type; const struct btf_type *value_type; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; u32 type_id; u32 value_id; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); static inline bool bpf_try_module_get(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) return bpf_struct_ops_get(data); else return try_module_get(owner); } static inline void bpf_module_put(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) bpf_struct_ops_put(data); else module_put(owner); } #else static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { return NULL; } static inline void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) { } static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); } static inline void bpf_module_put(const void *data, struct module *owner) { module_put(owner); } static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value) { return -EINVAL; } #endif struct bpf_array { struct bpf_map map; u32 elem_size; u32 index_mask; struct bpf_array_aux *aux; union { char value[0] __aligned(8); void *ptrs[0] __aligned(8); void __percpu *pptrs[0] __aligned(8); }; }; #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 32 #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ BPF_F_WRONLY | \ BPF_F_WRONLY_PROG) #define BPF_MAP_CAN_READ BIT(0) #define BPF_MAP_CAN_WRITE BIT(1) static inline u32 bpf_map_flags_to_cap(struct bpf_map *map) { u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); /* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is * not possible. */ if (access_flags & BPF_F_RDONLY_PROG) return BPF_MAP_CAN_READ; else if (access_flags & BPF_F_WRONLY_PROG) return BPF_MAP_CAN_WRITE; else return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE; } static inline bool bpf_map_flags_access_ok(u32 access_flags) { return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) != (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); } struct bpf_event_entry { struct perf_event *event; struct file *perf_file; struct file *map_file; struct rcu_head rcu; }; bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); /* an array of programs to be executed under rcu_lock. * * Typical usage: * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, bpf_prog_run); * * the structure returned by bpf_prog_array_alloc() should be populated * with program pointers and the last pointer must be NULL. * The user has to keep refcnt on the program and make sure the program * is removed from the array before bpf_prog_put(). * The 'struct bpf_prog_array *' should only be replaced with xchg() * since other cpus are walking the array of pointers in parallel. */ struct bpf_prog_array_item { struct bpf_prog *prog; union { struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; u64 bpf_cookie; }; }; struct bpf_prog_array { struct rcu_head rcu; struct bpf_prog_array_item items[]; }; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); bool bpf_prog_array_is_empty(struct bpf_prog_array *array); int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, __u32 __user *prog_ids, u32 cnt); void bpf_prog_array_delete_safe(struct bpf_prog_array *progs, struct bpf_prog *old_prog); int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index); int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, struct bpf_prog *prog); int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt); int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, u64 bpf_cookie, struct bpf_prog_array **new_array); struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; }; struct bpf_trace_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; }; static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) { struct bpf_run_ctx *old_ctx = NULL; #ifdef CONFIG_BPF_SYSCALL old_ctx = current->bpf_ctx; current->bpf_ctx = new_ctx; #endif return old_ctx; } static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) { #ifdef CONFIG_BPF_SYSCALL current->bpf_ctx = old_ctx; #endif } /* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ #define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) /* BPF program asks to set CN on the packet. */ #define BPF_RET_SET_CN (1 << 0) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); static __always_inline u32 BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog, u32 *ret_flags) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; u32 ret = 1; u32 func_ret; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); item = &array->items[0]; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); ret &= (func_ret & 1); *(ret_flags) |= (func_ret >> 1); item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); return ret; } static __always_inline u32 BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; u32 ret = 1; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); item = &array->items[0]; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; ret &= run_prog(prog, ctx); item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); return ret; } static __always_inline u32 BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); if (unlikely(!array)) goto out; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; } bpf_reset_run_ctx(old_run_ctx); out: rcu_read_unlock(); migrate_enable(); return ret; } /* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs * so BPF programs can request cwr for TCP packets. * * Current cgroup skb programs can only return 0 or 1 (0 to drop the * packet. This macro changes the behavior so the low order bit * indicates whether the packet should be dropped (0) or not (1) * and the next bit is a congestion notification bit. This could be * used by TCP to call tcp_enter_cwr() * * Hence, new allowed return values of CGROUP EGRESS BPF programs are: * 0: drop packet * 1: keep packet * 2: drop packet and cn * 3: keep packet and cn * * This macro then converts it to one of the NET_XMIT or an error * code that is then interpreted as drop packet (and no cn): * 0: NET_XMIT_SUCCESS skb should be transmitted * 1: NET_XMIT_DROP skb should be dropped and cn * 2: NET_XMIT_CN skb should be transmitted and cn * 3: -EPERM skb should be dropped */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ u32 _flags = 0; \ bool _cn; \ u32 _ret; \ _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ if (_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ _ret; \ }) #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; /* * Block execution of BPF programs attached to instrumentation (perf, * kprobes, tracepoints) to prevent deadlocks on map operations as any of * these events can happen inside a region which holds a map bucket lock * and can deadlock on it. */ static inline void bpf_disable_instrumentation(void) { migrate_disable(); this_cpu_inc(bpf_prog_active); } static inline void bpf_enable_instrumentation(void) { this_cpu_dec(bpf_prog_active); migrate_enable(); } extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE extern const struct bpf_prog_ops bpf_offload_prog_ops; extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv); void bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_update_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); struct bpf_map *bpf_map_get_curr_or_next(u32 *id); struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); #ifdef CONFIG_MEMCG_KMEM void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags); #else static inline void * bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node) { return kmalloc_node(size, flags, node); } static inline void * bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { return kzalloc(size, flags); } static inline void __percpu * bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { return __alloc_percpu_gfp(size, align, flags); } #endif extern int sysctl_unprivileged_bpf_disabled; static inline bool bpf_allow_ptr_leaks(void) { return perfmon_capable(); } static inline bool bpf_allow_uninit_stack(void) { return perfmon_capable(); } static inline bool bpf_allow_ptr_to_map_access(void) { return perfmon_capable(); } static inline bool bpf_bypass_spec_v1(void) { return perfmon_capable(); } static inline bool bpf_bypass_spec_v4(void) { return perfmon_capable(); } int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); struct bpf_link *bpf_link_get_from_fd(u32 ufd); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } struct bpf_iter_aux_info { struct bpf_map *map; }; typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux, struct seq_file *seq); typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); typedef const struct bpf_func_proto * (*bpf_iter_get_func_proto_t)(enum bpf_func_id func_id, const struct bpf_prog *prog); enum bpf_iter_feature { BPF_ITER_RESCHED = BIT(0), }; #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; bpf_iter_attach_target_t attach_target; bpf_iter_detach_target_t detach_target; bpf_iter_show_fdinfo_t show_fdinfo; bpf_iter_fill_link_info_t fill_link_info; bpf_iter_get_func_proto_t get_func_proto; u32 ctx_arg_info_size; u32 feature; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; }; struct bpf_iter_meta { __bpf_md_ptr(struct seq_file *, seq); u64 session_id; u64 seq_num; }; struct bpf_iter__bpf_map_elem { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(void *, key); __bpf_md_ptr(void *, value); }; int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); const struct bpf_func_proto * bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx); void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, struct seq_file *seq); int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); int map_set_for_each_callback_args(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent * updates from BPF programs. Called from bpf syscall and mostly used with * size 8 or 16 bytes, so ask compiler to inline it. */ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) { const long *lsrc = src; long *ldst = dst; size /= sizeof(long); while (size--) *ldst++ = *lsrc++; } /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); #endif struct btf *bpf_get_btf_vmlinux(void); /* Map specifics */ struct xdp_frame; struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; void __dev_flush(void); int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) { return (attr->map_flags & BPF_F_NUMA_NODE) ? attr->numa_node : NUMA_NO_NODE; } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); int array_map_alloc_check(union bpf_attr *attr); int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); bool bpf_prog_test_check_kfunc_call(u32 kfunc_id); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func_proto, const char *func_name, struct btf_func_model *m); struct bpf_reg_state; int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *reg); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); void bpf_task_storage_free(struct task_struct *task); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); static inline bool unprivileged_ebpf_enabled(void) { return !sysctl_unprivileged_bpf_disabled; } #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); } static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_prog_add(struct bpf_prog *prog, int i) { } static inline void bpf_prog_sub(struct bpf_prog *prog, int i) { } static inline void bpf_prog_put(struct bpf_prog *prog) { } static inline void bpf_prog_inc(struct bpf_prog *prog) { } static inline struct bpf_prog *__must_check bpf_prog_inc_not_zero(struct bpf_prog *prog) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) { } static inline int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { return -EOPNOTSUPP; } static inline int bpf_link_settle(struct bpf_link_primer *primer) { return -EOPNOTSUPP; } static inline void bpf_link_cleanup(struct bpf_link_primer *primer) { } static inline void bpf_link_inc(struct bpf_link *link) { } static inline void bpf_link_put(struct bpf_link *link) { } static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; } static inline bool dev_map_can_have_prog(struct bpf_map *map) { return false; } static inline void __dev_flush(void) { } struct xdp_frame; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; static inline int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { return 0; } struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { return 0; } static inline int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { return 0; } static inline void __cpu_map_flush(void) { } static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb) { return -EOPNOTSUPP; } static inline bool cpu_map_prog_allowed(struct bpf_map *map) { return false; } static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { return ERR_PTR(-EOPNOTSUPP); } static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id) { return false; } static inline void bpf_map_put(struct bpf_map *map) { } static inline struct bpf_prog *bpf_prog_by_id(u32 id) { return ERR_PTR(-ENOTSUPP); } static inline const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { return NULL; } static inline void bpf_task_storage_free(struct task_struct *task) { } static inline bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog) { return false; } static inline const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn) { return NULL; } static inline bool unprivileged_ebpf_enabled(void) { return false; } #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, struct btf_mod_pair *used_btfs, u32 len); static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { return bpf_prog_get_type_dev(ufd, type, false); } void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len); bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_offload_destroy(struct bpf_prog *prog); int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct bpf_prog *prog); int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map); int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_map_offload_update_elem(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key); bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); struct bpf_offload_dev * bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv); void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev); int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); void unpriv_ebpf_notify(int new_state); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return aux->offload_requested; } static inline bool bpf_map_is_dev_bound(struct bpf_map *map) { return unlikely(map->ops == &bpf_map_offload_ops); } struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) { return -EOPNOTSUPP; } static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) { return false; } static inline bool bpf_map_is_dev_bound(struct bpf_map *map) { return false; } static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_map_offload_map_free(struct bpf_map *map) { } static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } #ifdef CONFIG_BPF_SYSCALL static inline int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { return -EOPNOTSUPP; } static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags) { return -EOPNOTSUPP; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags); #else static inline void bpf_sk_reuseport_detach(struct sock *sk) { } #ifdef CONFIG_BPF_SYSCALL static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { return -EOPNOTSUPP; } static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return -EOPNOTSUPP; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */ /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_map_push_elem_proto; extern const struct bpf_func_proto bpf_map_pop_elem_proto; extern const struct bpf_func_proto bpf_map_peek_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_get_task_stack_proto; extern const struct bpf_func_proto bpf_get_stackid_proto_pe; extern const struct bpf_func_proto bpf_get_stack_proto_pe; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_spin_lock_proto; extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_event_output_data_proto; extern const struct bpf_func_proto bpf_ringbuf_output_proto; extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #if defined(CONFIG_NET) bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); #else static inline bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } #endif #ifdef CONFIG_INET struct sk_reuseport_kern { struct sk_buff *skb; struct sock *sk; struct sock *selected_sk; struct sock *migrating_sk; void *data_end; u32 hash; u32 reuseport_id; bool bind_inany; }; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); #else static inline bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } static inline bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } #endif /* CONFIG_INET */ enum bpf_text_poke_type { BPF_MOD_CALL, BPF_MOD_JUMP, }; int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, struct bpf_prog *new, struct bpf_prog *old); struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); #define MAX_BPRINTF_VARARGS 12 #define MAX_BPRINTF_BUF 1024 struct bpf_bprintf_data { u32 *bin_args; char *buf; bool get_bin_args; bool get_buf; }; int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 num_args, struct bpf_bprintf_data *data); void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); #endif /* _LINUX_BPF_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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2020 Google LLC. */ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/binfmts.h> #include <linux/lsm_hooks.h> #include <linux/bpf_lsm.h> #include <linux/kallsyms.h> #include <linux/bpf_verifier.h> #include <net/bpf_sk_storage.h> #include <linux/bpf_local_storage.h> #include <linux/btf_ids.h> #include <linux/ima.h> /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. */ #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ noinline RET bpf_lsm_##NAME(__VA_ARGS__) \ { \ return DEFAULT; \ } #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME) BTF_SET_START(bpf_lsm_hooks) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK BTF_SET_END(bpf_lsm_hooks) int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) { if (!prog->gpl_compatible) { bpf_log(vlog, "LSM programs must have a GPL compatible license\n"); return -EINVAL; } if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) { bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", prog->aux->attach_btf_id, prog->aux->attach_func_name); return -EINVAL; } return 0; } /* Mask for all the currently supported BPRM option flags */ #define BPF_F_BRPM_OPTS_MASK BPF_F_BPRM_SECUREEXEC BPF_CALL_2(bpf_bprm_opts_set, struct linux_binprm *, bprm, u64, flags) { if (flags & ~BPF_F_BRPM_OPTS_MASK) return -EINVAL; bprm->secureexec = (flags & BPF_F_BPRM_SECUREEXEC); return 0; } BTF_ID_LIST_SINGLE(bpf_bprm_opts_set_btf_ids, struct, linux_binprm) static const struct bpf_func_proto bpf_bprm_opts_set_proto = { .func = bpf_bprm_opts_set, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_bprm_opts_set_btf_ids[0], .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_ima_inode_hash, struct inode *, inode, void *, dst, u32, size) { return ima_inode_hash(inode, dst, size); } static bool bpf_ima_inode_hash_allowed(const struct bpf_prog *prog) { return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); } BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode) static const struct bpf_func_proto bpf_ima_inode_hash_proto = { .func = bpf_ima_inode_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0], .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, .allowed = bpf_ima_inode_hash_allowed, }; static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_inode_storage_get: return &bpf_inode_storage_get_proto; case BPF_FUNC_inode_storage_delete: return &bpf_inode_storage_delete_proto; #ifdef CONFIG_NET case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #endif /* CONFIG_NET */ case BPF_FUNC_spin_lock: return &bpf_spin_lock_proto; case BPF_FUNC_spin_unlock: return &bpf_spin_unlock_proto; case BPF_FUNC_bprm_opts_set: return &bpf_bprm_opts_set_proto; case BPF_FUNC_ima_inode_hash: return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL; default: return tracing_prog_func_proto(func_id, prog); } } /* The set of hooks which are called without pagefaults disabled and are allowed * to "sleep" and thus can be used for sleepable BPF programs. */ BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) BTF_ID(func, bpf_lsm_bpf_map) BTF_ID(func, bpf_lsm_bpf_map_alloc_security) BTF_ID(func, bpf_lsm_bpf_map_free_security) BTF_ID(func, bpf_lsm_bpf_prog) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) BTF_ID(func, bpf_lsm_bprm_creds_for_exec) BTF_ID(func, bpf_lsm_bprm_creds_from_file) BTF_ID(func, bpf_lsm_capget) BTF_ID(func, bpf_lsm_capset) BTF_ID(func, bpf_lsm_cred_prepare) BTF_ID(func, bpf_lsm_file_ioctl) BTF_ID(func, bpf_lsm_file_lock) BTF_ID(func, bpf_lsm_file_open) BTF_ID(func, bpf_lsm_file_receive) #ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_inet_conn_established) #endif /* CONFIG_SECURITY_NETWORK */ BTF_ID(func, bpf_lsm_inode_create) BTF_ID(func, bpf_lsm_inode_free_security) BTF_ID(func, bpf_lsm_inode_getattr) BTF_ID(func, bpf_lsm_inode_getxattr) BTF_ID(func, bpf_lsm_inode_mknod) BTF_ID(func, bpf_lsm_inode_need_killpriv) BTF_ID(func, bpf_lsm_inode_post_setxattr) BTF_ID(func, bpf_lsm_inode_readlink) BTF_ID(func, bpf_lsm_inode_rename) BTF_ID(func, bpf_lsm_inode_rmdir) BTF_ID(func, bpf_lsm_inode_setattr) BTF_ID(func, bpf_lsm_inode_setxattr) BTF_ID(func, bpf_lsm_inode_symlink) BTF_ID(func, bpf_lsm_inode_unlink) BTF_ID(func, bpf_lsm_kernel_module_request) BTF_ID(func, bpf_lsm_kernfs_init_security) #ifdef CONFIG_KEYS BTF_ID(func, bpf_lsm_key_free) #endif /* CONFIG_KEYS */ BTF_ID(func, bpf_lsm_mmap_file) BTF_ID(func, bpf_lsm_netlink_send) BTF_ID(func, bpf_lsm_path_notify) BTF_ID(func, bpf_lsm_release_secctx) BTF_ID(func, bpf_lsm_sb_alloc_security) BTF_ID(func, bpf_lsm_sb_eat_lsm_opts) BTF_ID(func, bpf_lsm_sb_kern_mount) BTF_ID(func, bpf_lsm_sb_mount) BTF_ID(func, bpf_lsm_sb_remount) BTF_ID(func, bpf_lsm_sb_set_mnt_opts) BTF_ID(func, bpf_lsm_sb_show_options) BTF_ID(func, bpf_lsm_sb_statfs) BTF_ID(func, bpf_lsm_sb_umount) BTF_ID(func, bpf_lsm_settime) #ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_socket_accept) BTF_ID(func, bpf_lsm_socket_bind) BTF_ID(func, bpf_lsm_socket_connect) BTF_ID(func, bpf_lsm_socket_create) BTF_ID(func, bpf_lsm_socket_getpeername) BTF_ID(func, bpf_lsm_socket_getpeersec_dgram) BTF_ID(func, bpf_lsm_socket_getsockname) BTF_ID(func, bpf_lsm_socket_getsockopt) BTF_ID(func, bpf_lsm_socket_listen) BTF_ID(func, bpf_lsm_socket_post_create) BTF_ID(func, bpf_lsm_socket_recvmsg) BTF_ID(func, bpf_lsm_socket_sendmsg) BTF_ID(func, bpf_lsm_socket_shutdown) BTF_ID(func, bpf_lsm_socket_socketpair) #endif /* CONFIG_SECURITY_NETWORK */ BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) BTF_ID(func, bpf_lsm_task_getsecid_subj) BTF_ID(func, bpf_lsm_task_getsecid_obj) BTF_ID(func, bpf_lsm_task_prctl) BTF_ID(func, bpf_lsm_task_setscheduler) BTF_ID(func, bpf_lsm_task_to_inode) BTF_SET_END(sleepable_lsm_hooks) bool bpf_lsm_is_sleepable_hook(u32 btf_id) { return btf_id_set_contains(&sleepable_lsm_hooks, btf_id); } const struct bpf_prog_ops lsm_prog_ops = { }; const struct bpf_verifier_ops lsm_verifier_ops = { .get_func_proto = bpf_lsm_func_proto, .is_valid_access = btf_ctx_access, }; |
| 74 74 18 18 18 18 18 18 56 57 57 57 57 57 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/random.h> #include <linux/hrtimer.h> #include <linux/ktime.h> #include <linux/string.h> #include <linux/net.h> #include <linux/siphash.h> #include <net/secure_seq.h> #if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET) #include <linux/in6.h> #include <net/tcp.h> static siphash_key_t net_secret __read_mostly; static siphash_key_t ts_secret __read_mostly; #define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ) static __always_inline void net_secret_init(void) { net_get_random_once(&net_secret, sizeof(net_secret)); } static __always_inline void ts_secret_init(void) { net_get_random_once(&ts_secret, sizeof(ts_secret)); } #endif #ifdef CONFIG_INET static u32 seq_scale(u32 seq) { /* * As close as possible to RFC 793, which * suggests using a 250 kHz clock. * Further reading shows this assumes 2 Mb/s networks. * For 10 Mb/s Ethernet, a 1 MHz clock is appropriate. * For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but * we also need to limit the resolution so that the u32 seq * overlaps less than one time per MSL (2 minutes). * Choosing a clock of 64 ns period is OK. (period of 274 s) */ return seq + (ktime_get_real_ns() >> 6); } #endif #if IS_ENABLED(CONFIG_IPV6) u32 secure_tcpv6_ts_off(const struct net *net, const __be32 *saddr, const __be32 *daddr) { const struct { struct in6_addr saddr; struct in6_addr daddr; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, }; if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) return 0; ts_secret_init(); return siphash(&combined, offsetofend(typeof(combined), daddr), &ts_secret); } EXPORT_SYMBOL(secure_tcpv6_ts_off); u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport) { const struct { struct in6_addr saddr; struct in6_addr daddr; __be16 sport; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, .sport = sport, .dport = dport }; u32 hash; net_secret_init(); hash = siphash(&combined, offsetofend(typeof(combined), dport), &net_secret); return seq_scale(hash); } EXPORT_SYMBOL(secure_tcpv6_seq); u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) { const struct { struct in6_addr saddr; struct in6_addr daddr; unsigned int timeseed; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, .timeseed = jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, .dport = dport, }; net_secret_init(); return siphash(&combined, offsetofend(typeof(combined), dport), &net_secret); } EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) { if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) return 0; ts_secret_init(); return siphash_2u32((__force u32)saddr, (__force u32)daddr, &ts_secret); } /* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, * it would be easy enough to have the former function use siphash_4u32, passing * the arguments as separate u32. */ u32 secure_tcp_seq(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport) { u32 hash; net_secret_init(); hash = siphash_3u32((__force u32)saddr, (__force u32)daddr, (__force u32)sport << 16 | (__force u32)dport, &net_secret); return seq_scale(hash); } EXPORT_SYMBOL_GPL(secure_tcp_seq); u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { net_secret_init(); return siphash_4u32((__force u32)saddr, (__force u32)daddr, (__force u16)dport, jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, &net_secret); } EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); #endif #if IS_ENABLED(CONFIG_IP_DCCP) u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport) { u64 seq; net_secret_init(); seq = siphash_3u32((__force u32)saddr, (__force u32)daddr, (__force u32)sport << 16 | (__force u32)dport, &net_secret); seq += ktime_get_real_ns(); seq &= (1ull << 48) - 1; return seq; } EXPORT_SYMBOL(secure_dccp_sequence_number); #if IS_ENABLED(CONFIG_IPV6) u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, __be16 sport, __be16 dport) { const struct { struct in6_addr saddr; struct in6_addr daddr; __be16 sport; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, .sport = sport, .dport = dport }; u64 seq; net_secret_init(); seq = siphash(&combined, offsetofend(typeof(combined), dport), &net_secret); seq += ktime_get_real_ns(); seq &= (1ull << 48) - 1; return seq; } EXPORT_SYMBOL(secure_dccpv6_sequence_number); #endif #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _INET_COMMON_H #define _INET_COMMON_H #include <linux/indirect_call_wrapper.h> extern const struct proto_ops inet_stream_ops; extern const struct proto_ops inet_dgram_ops; /* * INET4 prototypes used by INET6 */ struct msghdr; struct sock; struct sockaddr; struct socket; int inet_release(struct socket *sock); int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags, int is_sendmsg); int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); int inet_accept(struct socket *sock, struct socket *newsock, int flags, bool kern); int inet_send_prepare(struct sock *sk); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); void inet_sock_destruct(struct sock *sk); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); /* Don't allocate port at this moment, defer to connect. */ #define BIND_FORCE_ADDRESS_NO_PORT (1 << 0) /* Grab and release socket lock. */ #define BIND_WITH_LOCK (1 << 1) /* Called from BPF program. */ #define BIND_FROM_BPF (1 << 2) /* Skip CAP_NET_BIND_SERVICE check. */ #define BIND_NO_CAP_NET_BIND_SERVICE (1 << 3) int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags); int inet_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet_ctl_sock_create(struct sock **sk, unsigned short family, unsigned short type, unsigned char protocol, struct net *net); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb); int inet_gro_complete(struct sk_buff *skb, int nhoff); struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features); static inline void inet_ctl_sock_destroy(struct sock *sk) { if (sk) sock_release(sk->sk_socket); } #define indirect_call_gro_receive(f2, f1, cb, head, skb) \ ({ \ unlikely(gro_recursion_inc_test(skb)) ? \ NAPI_GRO_CB(skb)->flush |= 1, NULL : \ INDIRECT_CALL_2(cb, f2, f1, head, skb); \ }) #endif |
| 34 26 3 3 7 31 3195 3204 3200 3205 3200 120 1626 119 1635 1637 1629 8 115 117 2 2 2941 2947 2942 1661 646 2 1 2945 56 7 56 56 368 97 367 404 628 630 361 630 193 57 405 488 682 249 487 487 488 187 187 1520 11 1521 1520 1523 1517 1 130 1492 1536 1536 1537 1538 15 33 37 37 1487 1514 1514 1517 1514 1487 37 16116 7 7 7 7 7 16040 16035 16116 16041 33 33 1636 1653 1635 1634 1636 1633 1634 1637 6 2900 18 44 2 14 1621 343 46 1624 111 1516 1518 1518 1626 62 34 30 87 69 16 17 7 7 3 3 5 3 3 3 27 20 9 4 8 2 24 20 7 2 7 2 22 8 4 2 4 2592 2594 212 11 2951 2955 1564 1561 3 70 70 311 311 310 31 117 1537 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <uapi/linux/btf.h> #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/random.h> #include <linux/moduleloader.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/objtool.h> #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/perf_event.h> #include <linux/extable.h> #include <linux/log2.h> #include <linux/nospec.h> #include <asm/barrier.h> #include <asm/unaligned.h> /* Registers */ #define BPF_R0 regs[BPF_REG_0] #define BPF_R1 regs[BPF_REG_1] #define BPF_R2 regs[BPF_REG_2] #define BPF_R3 regs[BPF_REG_3] #define BPF_R4 regs[BPF_REG_4] #define BPF_R5 regs[BPF_REG_5] #define BPF_R6 regs[BPF_REG_6] #define BPF_R7 regs[BPF_REG_7] #define BPF_R8 regs[BPF_REG_8] #define BPF_R9 regs[BPF_REG_9] #define BPF_R10 regs[BPF_REG_10] /* Named registers */ #define DST regs[insn->dst_reg] #define SRC regs[insn->src_reg] #define FP regs[BPF_REG_FP] #define AX regs[BPF_REG_AX] #define ARG1 regs[BPF_REG_ARG1] #define CTX regs[BPF_REG_CTX] #define IMM insn->imm /* No hurry in this branch * * Exported for the bpf jit load helper. */ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; if (k >= SKF_NET_OFF) { ptr = skb_network_header(skb) + k - SKF_NET_OFF; } else if (k >= SKF_LL_OFF) { if (unlikely(!skb_mac_header_was_set(skb))) return NULL; ptr = skb_mac_header(skb) + k - SKF_LL_OFF; } if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; return NULL; } struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog_aux *aux; struct bpf_prog *fp; size = round_up(size, PAGE_SIZE); fp = __vmalloc(size, gfp_flags); if (fp == NULL) return NULL; aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags); if (aux == NULL) { vfree(fp); return NULL; } fp->active = alloc_percpu_gfp(int, GFP_KERNEL_ACCOUNT | gfp_extra_flags); if (!fp->active) { vfree(fp); kfree(aux); return NULL; } fp->pages = size / PAGE_SIZE; fp->aux = aux; fp->aux->prog = fp; fp->jit_requested = ebpf_jit_enabled(); INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode); mutex_init(&fp->aux->used_maps_mutex); mutex_init(&fp->aux->dst_mutex); return fp; } struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *prog; int cpu; prog = bpf_prog_alloc_no_stats(size, gfp_extra_flags); if (!prog) return NULL; prog->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags); if (!prog->stats) { free_percpu(prog->active); kfree(prog->aux); vfree(prog); return NULL; } for_each_possible_cpu(cpu) { struct bpf_prog_stats *pstats; pstats = per_cpu_ptr(prog->stats, cpu); u64_stats_init(&pstats->syncp); } return prog; } EXPORT_SYMBOL_GPL(bpf_prog_alloc); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) { if (!prog->aux->nr_linfo || !prog->jit_requested) return 0; prog->aux->jited_linfo = kvcalloc(prog->aux->nr_linfo, sizeof(*prog->aux->jited_linfo), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!prog->aux->jited_linfo) return -ENOMEM; return 0; } void bpf_prog_jit_attempt_done(struct bpf_prog *prog) { if (prog->aux->jited_linfo && (!prog->jited || !prog->aux->jited_linfo[0])) { kvfree(prog->aux->jited_linfo); prog->aux->jited_linfo = NULL; } kfree(prog->aux->kfunc_tab); prog->aux->kfunc_tab = NULL; } /* The jit engine is responsible to provide an array * for insn_off to the jited_off mapping (insn_to_jit_off). * * The idx to this array is the insn_off. Hence, the insn_off * here is relative to the prog itself instead of the main prog. * This array has one entry for each xlated bpf insn. * * jited_off is the byte off to the last byte of the jited insn. * * Hence, with * insn_start: * The first bpf insn off of the prog. The insn off * here is relative to the main prog. * e.g. if prog is a subprog, insn_start > 0 * linfo_idx: * The prog's idx to prog->aux->linfo and jited_linfo * * jited_linfo[linfo_idx] = prog->bpf_func * * For i > linfo_idx, * * jited_linfo[i] = prog->bpf_func + * insn_to_jit_off[linfo[i].insn_off - insn_start - 1] */ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off) { u32 linfo_idx, insn_start, insn_end, nr_linfo, i; const struct bpf_line_info *linfo; void **jited_linfo; if (!prog->aux->jited_linfo) /* Userspace did not provide linfo */ return; linfo_idx = prog->aux->linfo_idx; linfo = &prog->aux->linfo[linfo_idx]; insn_start = linfo[0].insn_off; insn_end = insn_start + prog->len; jited_linfo = &prog->aux->jited_linfo[linfo_idx]; jited_linfo[0] = prog->bpf_func; nr_linfo = prog->aux->nr_linfo - linfo_idx; for (i = 1; i < nr_linfo && linfo[i].insn_off < insn_end; i++) /* The verifier ensures that linfo[i].insn_off is * strictly increasing */ jited_linfo[i] = prog->bpf_func + insn_to_jit_off[linfo[i].insn_off - insn_start - 1]; } struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; u32 pages; size = round_up(size, PAGE_SIZE); pages = size / PAGE_SIZE; if (pages <= fp_old->pages) return fp_old; fp = __vmalloc(size, gfp_flags); if (fp) { memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); fp->pages = pages; fp->aux->prog = fp; /* We keep fp->aux from fp_old around in the new * reallocated structure. */ fp_old->aux = NULL; fp_old->stats = NULL; fp_old->active = NULL; __bpf_prog_free(fp_old); } return fp; } void __bpf_prog_free(struct bpf_prog *fp) { if (fp->aux) { mutex_destroy(&fp->aux->used_maps_mutex); mutex_destroy(&fp->aux->dst_mutex); kfree(fp->aux->poke_tab); kfree(fp->aux); } free_percpu(fp->stats); free_percpu(fp->active); vfree(fp); } int bpf_prog_calc_tag(struct bpf_prog *fp) { const u32 bits_offset = SHA1_BLOCK_SIZE - sizeof(__be64); u32 raw_size = bpf_prog_tag_scratch_size(fp); u32 digest[SHA1_DIGEST_WORDS]; u32 ws[SHA1_WORKSPACE_WORDS]; u32 i, bsize, psize, blocks; struct bpf_insn *dst; bool was_ld_map; u8 *raw, *todo; __be32 *result; __be64 *bits; raw = vmalloc(raw_size); if (!raw) return -ENOMEM; sha1_init(digest); memset(ws, 0, sizeof(ws)); /* We need to take out the map fd for the digest calculation * since they are unstable from user space side. */ dst = (void *)raw; for (i = 0, was_ld_map = false; i < fp->len; i++) { dst[i] = fp->insnsi[i]; if (!was_ld_map && dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) && (dst[i].src_reg == BPF_PSEUDO_MAP_FD || dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) { was_ld_map = true; dst[i].imm = 0; } else if (was_ld_map && dst[i].code == 0 && dst[i].dst_reg == 0 && dst[i].src_reg == 0 && dst[i].off == 0) { was_ld_map = false; dst[i].imm = 0; } else { was_ld_map = false; } } psize = bpf_prog_insn_size(fp); memset(&raw[psize], 0, raw_size - psize); raw[psize++] = 0x80; bsize = round_up(psize, SHA1_BLOCK_SIZE); blocks = bsize / SHA1_BLOCK_SIZE; todo = raw; if (bsize - psize >= sizeof(__be64)) { bits = (__be64 *)(todo + bsize - sizeof(__be64)); } else { bits = (__be64 *)(todo + bsize + bits_offset); blocks++; } *bits = cpu_to_be64((psize - 1) << 3); while (blocks--) { sha1_transform(digest, todo, ws); todo += SHA1_BLOCK_SIZE; } result = (__force __be32 *)digest; for (i = 0; i < SHA1_DIGEST_WORDS; i++) result[i] = cpu_to_be32(digest[i]); memcpy(fp->tag, result, sizeof(fp->tag)); vfree(raw); return 0; } static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { const s64 imm_min = S32_MIN, imm_max = S32_MAX; s32 delta = end_new - end_old; s64 imm = insn->imm; if (curr < pos && curr + imm + 1 >= end_old) imm += delta; else if (curr >= end_new && curr + imm + 1 < end_new) imm -= delta; if (imm < imm_min || imm > imm_max) return -ERANGE; if (!probe_pass) insn->imm = imm; return 0; } static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { const s32 off_min = S16_MIN, off_max = S16_MAX; s32 delta = end_new - end_old; s32 off = insn->off; if (curr < pos && curr + off + 1 >= end_old) off += delta; else if (curr >= end_new && curr + off + 1 < end_new) off -= delta; if (off < off_min || off > off_max) return -ERANGE; if (!probe_pass) insn->off = off; return 0; } static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old, s32 end_new, const bool probe_pass) { u32 i, insn_cnt = prog->len + (probe_pass ? end_new - end_old : 0); struct bpf_insn *insn = prog->insnsi; int ret = 0; for (i = 0; i < insn_cnt; i++, insn++) { u8 code; /* In the probing pass we still operate on the original, * unpatched image in order to check overflows before we * do any other adjustments. Therefore skip the patchlet. */ if (probe_pass && i == pos) { i = end_new; insn = prog->insnsi + end_old; } if (bpf_pseudo_func(insn)) { ret = bpf_adj_delta_to_imm(insn, pos, end_old, end_new, i, probe_pass); if (ret) return ret; continue; } code = insn->code; if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || BPF_OP(code) == BPF_EXIT) continue; /* Adjust offset of jmps if we cross patch boundaries. */ if (BPF_OP(code) == BPF_CALL) { if (insn->src_reg != BPF_PSEUDO_CALL) continue; ret = bpf_adj_delta_to_imm(insn, pos, end_old, end_new, i, probe_pass); } else { ret = bpf_adj_delta_to_off(insn, pos, end_old, end_new, i, probe_pass); } if (ret) break; } return ret; } static void bpf_adj_linfo(struct bpf_prog *prog, u32 off, u32 delta) { struct bpf_line_info *linfo; u32 i, nr_linfo; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo || !delta) return; linfo = prog->aux->linfo; for (i = 0; i < nr_linfo; i++) if (off < linfo[i].insn_off) break; /* Push all off < linfo[i].insn_off by delta */ for (; i < nr_linfo; i++) linfo[i].insn_off += delta; } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len) { u32 insn_adj_cnt, insn_rest, insn_delta = len - 1; const u32 cnt_max = S16_MAX; struct bpf_prog *prog_adj; int err; /* Since our patchlet doesn't expand the image, we're done. */ if (insn_delta == 0) { memcpy(prog->insnsi + off, patch, sizeof(*patch)); return prog; } insn_adj_cnt = prog->len + insn_delta; /* Reject anything that would potentially let the insn->off * target overflow when we have excessive program expansions. * We need to probe here before we do any reallocation where * we afterwards may not fail anymore. */ if (insn_adj_cnt > cnt_max && (err = bpf_adj_branches(prog, off, off + 1, off + len, true))) return ERR_PTR(err); /* Several new instructions need to be inserted. Make room * for them. Likely, there's no need for a new allocation as * last page could have large enough tailroom. */ prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt), GFP_USER); if (!prog_adj) return ERR_PTR(-ENOMEM); prog_adj->len = insn_adj_cnt; /* Patching happens in 3 steps: * * 1) Move over tail of insnsi from next instruction onwards, * so we can patch the single target insn with one or more * new ones (patching is always from 1 to n insns, n > 0). * 2) Inject new instructions at the target location. * 3) Adjust branch offsets if necessary. */ insn_rest = insn_adj_cnt - off - len; memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1, sizeof(*patch) * insn_rest); memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len); /* We are guaranteed to not fail at this point, otherwise * the ship has sailed to reverse to the original state. An * overflow cannot happen at this point. */ BUG_ON(bpf_adj_branches(prog_adj, off, off + 1, off + len, false)); bpf_adj_linfo(prog_adj, off, insn_delta); return prog_adj; } int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) { int err; /* Branch offsets can't overflow when program is shrinking, no need * to call bpf_adj_branches(..., true) here */ memmove(prog->insnsi + off, prog->insnsi + off + cnt, sizeof(struct bpf_insn) * (prog->len - off - cnt)); prog->len -= cnt; err = bpf_adj_branches(prog, off, off + cnt, off, false); WARN_ON_ONCE(err); return err; } static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) { int i; for (i = 0; i < fp->aux->func_cnt; i++) bpf_prog_kallsyms_del(fp->aux->func[i]); } void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) { bpf_prog_kallsyms_del_subprogs(fp); bpf_prog_kallsyms_del(fp); } #ifdef CONFIG_BPF_JIT /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; long bpf_jit_limit __read_mostly; long bpf_jit_limit_max __read_mostly; static void bpf_prog_ksym_set_addr(struct bpf_prog *prog) { const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog); unsigned long addr = (unsigned long)hdr; WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog)); prog->aux->ksym.start = (unsigned long) prog->bpf_func; prog->aux->ksym.end = addr + hdr->pages * PAGE_SIZE; } static void bpf_prog_ksym_set_name(struct bpf_prog *prog) { char *sym = prog->aux->ksym.name; const char *end = sym + KSYM_NAME_LEN; const struct btf_type *type; const char *func_name; BUILD_BUG_ON(sizeof("bpf_prog_") + sizeof(prog->tag) * 2 + /* name has been null terminated. * We should need +1 for the '_' preceding * the name. However, the null character * is double counted between the name and the * sizeof("bpf_prog_") above, so we omit * the +1 here. */ sizeof(prog->aux->name) > KSYM_NAME_LEN); sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_"); sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); /* prog->aux->name will be ignored if full btf name is available */ if (prog->aux->func_info_cnt) { type = btf_type_by_id(prog->aux->btf, prog->aux->func_info[prog->aux->func_idx].type_id); func_name = btf_name_by_offset(prog->aux->btf, type->name_off); snprintf(sym, (size_t)(end - sym), "_%s", func_name); return; } if (prog->aux->name[0]) snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name); else *sym = 0; } static unsigned long bpf_get_ksym_start(struct latch_tree_node *n) { return container_of(n, struct bpf_ksym, tnode)->start; } static __always_inline bool bpf_tree_less(struct latch_tree_node *a, struct latch_tree_node *b) { return bpf_get_ksym_start(a) < bpf_get_ksym_start(b); } static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n) { unsigned long val = (unsigned long)key; const struct bpf_ksym *ksym; ksym = container_of(n, struct bpf_ksym, tnode); if (val < ksym->start) return -1; /* Ensure that we detect return addresses as part of the program, when * the final instruction is a call for a program part of the stack * trace. Therefore, do val > ksym->end instead of val >= ksym->end. */ if (val > ksym->end) return 1; return 0; } static const struct latch_tree_ops bpf_tree_ops = { .less = bpf_tree_less, .comp = bpf_tree_comp, }; static DEFINE_SPINLOCK(bpf_lock); static LIST_HEAD(bpf_kallsyms); static struct latch_tree_root bpf_tree __cacheline_aligned; void bpf_ksym_add(struct bpf_ksym *ksym) { spin_lock_bh(&bpf_lock); WARN_ON_ONCE(!list_empty(&ksym->lnode)); list_add_tail_rcu(&ksym->lnode, &bpf_kallsyms); latch_tree_insert(&ksym->tnode, &bpf_tree, &bpf_tree_ops); spin_unlock_bh(&bpf_lock); } static void __bpf_ksym_del(struct bpf_ksym *ksym) { if (list_empty(&ksym->lnode)) return; latch_tree_erase(&ksym->tnode, &bpf_tree, &bpf_tree_ops); list_del_rcu(&ksym->lnode); } void bpf_ksym_del(struct bpf_ksym *ksym) { spin_lock_bh(&bpf_lock); __bpf_ksym_del(ksym); spin_unlock_bh(&bpf_lock); } static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) { return fp->jited && !bpf_prog_was_classic(fp); } static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { return list_empty(&fp->aux->ksym.lnode) || fp->aux->ksym.lnode.prev == LIST_POISON2; } void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || !bpf_capable()) return; bpf_prog_ksym_set_addr(fp); bpf_prog_ksym_set_name(fp); fp->aux->ksym.prog = true; bpf_ksym_add(&fp->aux->ksym); } void bpf_prog_kallsyms_del(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp)) return; bpf_ksym_del(&fp->aux->ksym); } static struct bpf_ksym *bpf_ksym_find(unsigned long addr) { struct latch_tree_node *n; n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops); return n ? container_of(n, struct bpf_ksym, tnode) : NULL; } const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { struct bpf_ksym *ksym; char *ret = NULL; rcu_read_lock(); ksym = bpf_ksym_find(addr); if (ksym) { unsigned long symbol_start = ksym->start; unsigned long symbol_end = ksym->end; strncpy(sym, ksym->name, KSYM_NAME_LEN); ret = sym; if (size) *size = symbol_end - symbol_start; if (off) *off = addr - symbol_start; } rcu_read_unlock(); return ret; } bool is_bpf_text_address(unsigned long addr) { bool ret; rcu_read_lock(); ret = bpf_ksym_find(addr) != NULL; rcu_read_unlock(); return ret; } static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { struct bpf_ksym *ksym = bpf_ksym_find(addr); return ksym && ksym->prog ? container_of(ksym, struct bpf_prog_aux, ksym)->prog : NULL; } const struct exception_table_entry *search_bpf_extables(unsigned long addr) { const struct exception_table_entry *e = NULL; struct bpf_prog *prog; rcu_read_lock(); prog = bpf_prog_ksym_find(addr); if (!prog) goto out; if (!prog->aux->num_exentries) goto out; e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr); out: rcu_read_unlock(); return e; } int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { struct bpf_ksym *ksym; unsigned int it = 0; int ret = -ERANGE; if (!bpf_jit_kallsyms_enabled()) return ret; rcu_read_lock(); list_for_each_entry_rcu(ksym, &bpf_kallsyms, lnode) { if (it++ != symnum) continue; strncpy(sym, ksym->name, KSYM_NAME_LEN); *value = ksym->start; *type = BPF_SYM_ELF_TYPE; ret = 0; break; } rcu_read_unlock(); return ret; } int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; static const u32 poke_tab_max = 1024; u32 slot = prog->aux->size_poke_tab; u32 size = slot + 1; if (size > poke_tab_max) return -ENOSPC; if (poke->tailcall_target || poke->tailcall_target_stable || poke->tailcall_bypass || poke->adj_off || poke->bypass_addr) return -EINVAL; switch (poke->reason) { case BPF_POKE_REASON_TAIL_CALL: if (!poke->tail_call.map) return -EINVAL; break; default: return -EINVAL; } tab = krealloc(tab, size * sizeof(*poke), GFP_KERNEL); if (!tab) return -ENOMEM; memcpy(&tab[slot], poke, sizeof(*poke)); prog->aux->size_poke_tab = size; prog->aux->poke_tab = tab; return slot; } static atomic_long_t bpf_jit_current; /* Can be overridden by an arch's JIT compiler if it has a custom, * dedicated BPF backend memory area, or if neither of the two * below apply. */ u64 __weak bpf_jit_alloc_exec_limit(void) { #if defined(MODULES_VADDR) return MODULES_END - MODULES_VADDR; #else return VMALLOC_END - VMALLOC_START; #endif } static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 1, PAGE_SIZE), LONG_MAX); return 0; } pure_initcall(bpf_jit_charge_init); int bpf_jit_charge_modmem(u32 pages) { if (atomic_long_add_return(pages, &bpf_jit_current) > (bpf_jit_limit >> PAGE_SHIFT)) { if (!bpf_capable()) { atomic_long_sub(pages, &bpf_jit_current); return -EPERM; } } return 0; } void bpf_jit_uncharge_modmem(u32 pages) { atomic_long_sub(pages, &bpf_jit_current); } void *__weak bpf_jit_alloc_exec(unsigned long size) { return module_alloc(size); } void __weak bpf_jit_free_exec(void *addr) { module_memfree(addr); } struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *hdr; u32 size, hole, start, pages; WARN_ON_ONCE(!is_power_of_2(alignment) || alignment > BPF_IMAGE_ALIGNMENT); /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); pages = size / PAGE_SIZE; if (bpf_jit_charge_modmem(pages)) return NULL; hdr = bpf_jit_alloc_exec(size); if (!hdr) { bpf_jit_uncharge_modmem(pages); return NULL; } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); hdr->pages = pages; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); /* Leave a random number of instructions before BPF code. */ *image_ptr = &hdr->image[start]; return hdr; } void bpf_jit_binary_free(struct bpf_binary_header *hdr) { u32 pages = hdr->pages; bpf_jit_free_exec(hdr); bpf_jit_uncharge_modmem(pages); } /* This symbol is only overridden by archs that have different * requirements than the usual eBPF JITs, f.e. when they only * implement cBPF JIT, do not set images read-only, etc. */ void __weak bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) { struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); bpf_jit_binary_free(hdr); WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp)); } bpf_prog_unlock_free(fp); } int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed) { s16 off = insn->off; s32 imm = insn->imm; u8 *addr; *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; if (!*func_addr_fixed) { /* Place-holder address till the last pass has collected * all addresses for JITed subprograms in which case we * can pick them up from prog->aux. */ if (!extra_pass) addr = NULL; else if (prog->aux->func && off >= 0 && off < prog->aux->func_cnt) addr = (u8 *)prog->aux->func[off]->bpf_func; else return -EINVAL; } else { /* Address of a BPF helper call. Since part of the core * kernel, it's always at a fixed location. __bpf_call_base * and the helper with imm relative to it are both in core * kernel. */ addr = (u8 *)__bpf_call_base + imm; } *func_addr = (unsigned long)addr; return 0; } static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff, bool emit_zext) { struct bpf_insn *to = to_buff; u32 imm_rnd = get_random_int(); s16 off; BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG); /* Constraints on AX register: * * AX register is inaccessible from user space. It is mapped in * all JITs, and used here for constant blinding rewrites. It is * typically "stateless" meaning its contents are only valid within * the executed instruction, but not across several instructions. * There are a few exceptions however which are further detailed * below. * * Constant blinding is only used by JITs, not in the interpreter. * The interpreter uses AX in some occasions as a local temporary * register e.g. in DIV or MOD instructions. * * In restricted circumstances, the verifier can also use the AX * register for rewrites as long as they do not interfere with * the above cases! */ if (from->dst_reg == BPF_REG_AX || from->src_reg == BPF_REG_AX) goto out; if (from->imm == 0 && (from->code == (BPF_ALU | BPF_MOV | BPF_K) || from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) { *to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg); goto out; } switch (from->code) { case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MOV | BPF_K: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX); break; case BPF_ALU64 | BPF_ADD | BPF_K: case BPF_ALU64 | BPF_SUB | BPF_K: case BPF_ALU64 | BPF_AND | BPF_K: case BPF_ALU64 | BPF_OR | BPF_K: case BPF_ALU64 | BPF_XOR | BPF_K: case BPF_ALU64 | BPF_MUL | BPF_K: case BPF_ALU64 | BPF_MOV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_MOD | BPF_K: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX); break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSLE | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; if (off < 0) off -= 2; *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; case BPF_JMP32 | BPF_JEQ | BPF_K: case BPF_JMP32 | BPF_JNE | BPF_K: case BPF_JMP32 | BPF_JGT | BPF_K: case BPF_JMP32 | BPF_JLT | BPF_K: case BPF_JMP32 | BPF_JGE | BPF_K: case BPF_JMP32 | BPF_JLE | BPF_K: case BPF_JMP32 | BPF_JSGT | BPF_K: case BPF_JMP32 | BPF_JSLT | BPF_K: case BPF_JMP32 | BPF_JSGE | BPF_K: case BPF_JMP32 | BPF_JSLE | BPF_K: case BPF_JMP32 | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; if (off < 0) off -= 2; *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; case BPF_LD | BPF_IMM | BPF_DW: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); *to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX); break; case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); if (emit_zext) *to++ = BPF_ZEXT_REG(BPF_REG_AX); *to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX); break; case BPF_ST | BPF_MEM | BPF_DW: case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off); break; } out: return to - to_buff; } static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags); if (fp != NULL) { /* aux->prog still points to the fp_other one, so * when promoting the clone to the real program, * this still needs to be adapted. */ memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE); } return fp; } static void bpf_prog_clone_free(struct bpf_prog *fp) { /* aux was stolen by the other clone, so we cannot free * it from this path! It will be freed eventually by the * other program on release. * * At this point, we don't need a deferred release since * clone is guaranteed to not be locked. */ fp->aux = NULL; fp->stats = NULL; fp->active = NULL; __bpf_prog_free(fp); } void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other) { /* We have to repoint aux->prog to self, as we don't * know whether fp here is the clone or the original. */ fp->aux->prog = fp; bpf_prog_clone_free(fp_other); } struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) { struct bpf_insn insn_buff[16], aux[2]; struct bpf_prog *clone, *tmp; int insn_delta, insn_cnt; struct bpf_insn *insn; int i, rewritten; if (!bpf_jit_blinding_enabled(prog) || prog->blinded) return prog; clone = bpf_prog_clone_create(prog, GFP_USER); if (!clone) return ERR_PTR(-ENOMEM); insn_cnt = clone->len; insn = clone->insnsi; for (i = 0; i < insn_cnt; i++, insn++) { /* We temporarily need to hold the original ld64 insn * so that we can still access the first part in the * second blinding run. */ if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) && insn[1].code == 0) memcpy(aux, insn, sizeof(aux)); rewritten = bpf_jit_blind_insn(insn, aux, insn_buff, clone->aux->verifier_zext); if (!rewritten) continue; tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten); if (IS_ERR(tmp)) { /* Patching may have repointed aux->prog during * realloc from the original one, so we need to * fix it up here on error. */ bpf_jit_prog_release_other(prog, clone); return tmp; } clone = tmp; insn_delta = rewritten - 1; /* Walk new program and skip insns we just inserted. */ insn = clone->insnsi + i + insn_delta; insn_cnt += insn_delta; i += insn_delta; } clone->blinded = 1; return clone; } #endif /* CONFIG_BPF_JIT */ /* Base function for offset calculation. Needs to go into .text section, * therefore keeping it non-static as well; will also be used by JITs * anyway later on, so do not let the compiler omit it. This also needs * to go into kallsyms for correlation from e.g. bpftool, so naming * must not change. */ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return 0; } EXPORT_SYMBOL_GPL(__bpf_call_base); /* All UAPI available opcodes. */ #define BPF_INSN_MAP(INSN_2, INSN_3) \ /* 32 bit ALU operations. */ \ /* Register based. */ \ INSN_3(ALU, ADD, X), \ INSN_3(ALU, SUB, X), \ INSN_3(ALU, AND, X), \ INSN_3(ALU, OR, X), \ INSN_3(ALU, LSH, X), \ INSN_3(ALU, RSH, X), \ INSN_3(ALU, XOR, X), \ INSN_3(ALU, MUL, X), \ INSN_3(ALU, MOV, X), \ INSN_3(ALU, ARSH, X), \ INSN_3(ALU, DIV, X), \ INSN_3(ALU, MOD, X), \ INSN_2(ALU, NEG), \ INSN_3(ALU, END, TO_BE), \ INSN_3(ALU, END, TO_LE), \ /* Immediate based. */ \ INSN_3(ALU, ADD, K), \ INSN_3(ALU, SUB, K), \ INSN_3(ALU, AND, K), \ INSN_3(ALU, OR, K), \ INSN_3(ALU, LSH, K), \ INSN_3(ALU, RSH, K), \ INSN_3(ALU, XOR, K), \ INSN_3(ALU, MUL, K), \ INSN_3(ALU, MOV, K), \ INSN_3(ALU, ARSH, K), \ INSN_3(ALU, DIV, K), \ INSN_3(ALU, MOD, K), \ /* 64 bit ALU operations. */ \ /* Register based. */ \ INSN_3(ALU64, ADD, X), \ INSN_3(ALU64, SUB, X), \ INSN_3(ALU64, AND, X), \ INSN_3(ALU64, OR, X), \ INSN_3(ALU64, LSH, X), \ INSN_3(ALU64, RSH, X), \ INSN_3(ALU64, XOR, X), \ INSN_3(ALU64, MUL, X), \ INSN_3(ALU64, MOV, X), \ INSN_3(ALU64, ARSH, X), \ INSN_3(ALU64, DIV, X), \ INSN_3(ALU64, MOD, X), \ INSN_2(ALU64, NEG), \ /* Immediate based. */ \ INSN_3(ALU64, ADD, K), \ INSN_3(ALU64, SUB, K), \ INSN_3(ALU64, AND, K), \ INSN_3(ALU64, OR, K), \ INSN_3(ALU64, LSH, K), \ INSN_3(ALU64, RSH, K), \ INSN_3(ALU64, XOR, K), \ INSN_3(ALU64, MUL, K), \ INSN_3(ALU64, MOV, K), \ INSN_3(ALU64, ARSH, K), \ INSN_3(ALU64, DIV, K), \ INSN_3(ALU64, MOD, K), \ /* Call instruction. */ \ INSN_2(JMP, CALL), \ /* Exit instruction. */ \ INSN_2(JMP, EXIT), \ /* 32-bit Jump instructions. */ \ /* Register based. */ \ INSN_3(JMP32, JEQ, X), \ INSN_3(JMP32, JNE, X), \ INSN_3(JMP32, JGT, X), \ INSN_3(JMP32, JLT, X), \ INSN_3(JMP32, JGE, X), \ INSN_3(JMP32, JLE, X), \ INSN_3(JMP32, JSGT, X), \ INSN_3(JMP32, JSLT, X), \ INSN_3(JMP32, JSGE, X), \ INSN_3(JMP32, JSLE, X), \ INSN_3(JMP32, JSET, X), \ /* Immediate based. */ \ INSN_3(JMP32, JEQ, K), \ INSN_3(JMP32, JNE, K), \ INSN_3(JMP32, JGT, K), \ INSN_3(JMP32, JLT, K), \ INSN_3(JMP32, JGE, K), \ INSN_3(JMP32, JLE, K), \ INSN_3(JMP32, JSGT, K), \ INSN_3(JMP32, JSLT, K), \ INSN_3(JMP32, JSGE, K), \ INSN_3(JMP32, JSLE, K), \ INSN_3(JMP32, JSET, K), \ /* Jump instructions. */ \ /* Register based. */ \ INSN_3(JMP, JEQ, X), \ INSN_3(JMP, JNE, X), \ INSN_3(JMP, JGT, X), \ INSN_3(JMP, JLT, X), \ INSN_3(JMP, JGE, X), \ INSN_3(JMP, JLE, X), \ INSN_3(JMP, JSGT, X), \ INSN_3(JMP, JSLT, X), \ INSN_3(JMP, JSGE, X), \ INSN_3(JMP, JSLE, X), \ INSN_3(JMP, JSET, X), \ /* Immediate based. */ \ INSN_3(JMP, JEQ, K), \ INSN_3(JMP, JNE, K), \ INSN_3(JMP, JGT, K), \ INSN_3(JMP, JLT, K), \ INSN_3(JMP, JGE, K), \ INSN_3(JMP, JLE, K), \ INSN_3(JMP, JSGT, K), \ INSN_3(JMP, JSLT, K), \ INSN_3(JMP, JSGE, K), \ INSN_3(JMP, JSLE, K), \ INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ /* Store instructions. */ \ /* Register based. */ \ INSN_3(STX, MEM, B), \ INSN_3(STX, MEM, H), \ INSN_3(STX, MEM, W), \ INSN_3(STX, MEM, DW), \ INSN_3(STX, ATOMIC, W), \ INSN_3(STX, ATOMIC, DW), \ /* Immediate based. */ \ INSN_3(ST, MEM, B), \ INSN_3(ST, MEM, H), \ INSN_3(ST, MEM, W), \ INSN_3(ST, MEM, DW), \ /* Load instructions. */ \ /* Register based. */ \ INSN_3(LDX, MEM, B), \ INSN_3(LDX, MEM, H), \ INSN_3(LDX, MEM, W), \ INSN_3(LDX, MEM, DW), \ /* Immediate based. */ \ INSN_3(LD, IMM, DW) bool bpf_opcode_in_insntable(u8 code) { #define BPF_INSN_2_TBL(x, y) [BPF_##x | BPF_##y] = true #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true static const bool public_insntable[256] = { [0 ... 255] = false, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL), /* UAPI exposed, but rewritten opcodes. cBPF carry-over. */ [BPF_LD | BPF_ABS | BPF_B] = true, [BPF_LD | BPF_ABS | BPF_H] = true, [BPF_LD | BPF_ABS | BPF_W] = true, [BPF_LD | BPF_IND | BPF_B] = true, [BPF_LD | BPF_IND | BPF_H] = true, [BPF_LD | BPF_IND | BPF_W] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL return public_insntable[code]; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) { memset(dst, 0, size); return -EFAULT; } /** * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers * @insn: is the array of eBPF instructions * * Decode and execute eBPF instructions. * * Return: whatever value is in %BPF_R0 at program exit */ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) { #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z static const void * const jumptable[256] __annotate_jump_table = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL), /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC, [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW, }; #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL u32 tail_call_cnt = 0; #define CONT ({ insn++; goto select_insn; }) #define CONT_JMP ({ insn++; goto select_insn; }) select_insn: goto *jumptable[insn->code]; /* Explicitly mask the register-based shift amounts with 63 or 31 * to avoid undefined behavior. Normally this won't affect the * generated code, for example, in case of native 64 bit archs such * as x86-64 or arm64, the compiler is optimizing the AND away for * the interpreter. In case of JITs, each of the JIT backends compiles * the BPF shift operations to machine instructions which produce * implementation-defined results in such a case; the resulting * contents of the register may be arbitrary, but program behaviour * as a whole remains defined. In other words, in case of JIT backends, * the AND must /not/ be added to the emitted LSH/RSH/ARSH translation. */ /* ALU (shifts) */ #define SHT(OPCODE, OP) \ ALU64_##OPCODE##_X: \ DST = DST OP (SRC & 63); \ CONT; \ ALU_##OPCODE##_X: \ DST = (u32) DST OP ((u32) SRC & 31); \ CONT; \ ALU64_##OPCODE##_K: \ DST = DST OP IMM; \ CONT; \ ALU_##OPCODE##_K: \ DST = (u32) DST OP (u32) IMM; \ CONT; /* ALU (rest) */ #define ALU(OPCODE, OP) \ ALU64_##OPCODE##_X: \ DST = DST OP SRC; \ CONT; \ ALU_##OPCODE##_X: \ DST = (u32) DST OP (u32) SRC; \ CONT; \ ALU64_##OPCODE##_K: \ DST = DST OP IMM; \ CONT; \ ALU_##OPCODE##_K: \ DST = (u32) DST OP (u32) IMM; \ CONT; ALU(ADD, +) ALU(SUB, -) ALU(AND, &) ALU(OR, |) ALU(XOR, ^) ALU(MUL, *) SHT(LSH, <<) SHT(RSH, >>) #undef SHT #undef ALU ALU_NEG: DST = (u32) -DST; CONT; ALU64_NEG: DST = -DST; CONT; ALU_MOV_X: DST = (u32) SRC; CONT; ALU_MOV_K: DST = (u32) IMM; CONT; ALU64_MOV_X: DST = SRC; CONT; ALU64_MOV_K: DST = IMM; CONT; LD_IMM_DW: DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32; insn++; CONT; ALU_ARSH_X: DST = (u64) (u32) (((s32) DST) >> (SRC & 31)); CONT; ALU_ARSH_K: DST = (u64) (u32) (((s32) DST) >> IMM); CONT; ALU64_ARSH_X: (*(s64 *) &DST) >>= (SRC & 63); CONT; ALU64_ARSH_K: (*(s64 *) &DST) >>= IMM; CONT; ALU64_MOD_X: div64_u64_rem(DST, SRC, &AX); DST = AX; CONT; ALU_MOD_X: AX = (u32) DST; DST = do_div(AX, (u32) SRC); CONT; ALU64_MOD_K: div64_u64_rem(DST, IMM, &AX); DST = AX; CONT; ALU_MOD_K: AX = (u32) DST; DST = do_div(AX, (u32) IMM); CONT; ALU64_DIV_X: DST = div64_u64(DST, SRC); CONT; ALU_DIV_X: AX = (u32) DST; do_div(AX, (u32) SRC); DST = (u32) AX; CONT; ALU64_DIV_K: DST = div64_u64(DST, IMM); CONT; ALU_DIV_K: AX = (u32) DST; do_div(AX, (u32) IMM); DST = (u32) AX; CONT; ALU_END_TO_BE: switch (IMM) { case 16: DST = (__force u16) cpu_to_be16(DST); break; case 32: DST = (__force u32) cpu_to_be32(DST); break; case 64: DST = (__force u64) cpu_to_be64(DST); break; } CONT; ALU_END_TO_LE: switch (IMM) { case 16: DST = (__force u16) cpu_to_le16(DST); break; case 32: DST = (__force u32) cpu_to_le32(DST); break; case 64: DST = (__force u64) cpu_to_le64(DST); break; } CONT; /* CALL */ JMP_CALL: /* Function call scratches BPF_R1-BPF_R5 registers, * preserves BPF_R6-BPF_R9, and stores return value * into BPF_R0. */ BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, BPF_R4, BPF_R5); CONT; JMP_CALL_ARGS: BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2, BPF_R3, BPF_R4, BPF_R5, insn + insn->off + 1); CONT; JMP_TAIL_CALL: { struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; prog = READ_ONCE(array->ptrs[index]); if (!prog) goto out; /* ARG1 at this point is guaranteed to point to CTX from * the verifier side due to the fact that the tail call is * handled like a helper, that is, bpf_tail_call_proto, * where arg1_type is ARG_PTR_TO_CTX. */ insn = prog->insnsi; goto select_insn; out: CONT; } JMP_JA: insn += insn->off; CONT; JMP_EXIT: return BPF_R0; /* JMP */ #define COND_JMP(SIGN, OPCODE, CMP_OP) \ JMP_##OPCODE##_X: \ if ((SIGN##64) DST CMP_OP (SIGN##64) SRC) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP32_##OPCODE##_X: \ if ((SIGN##32) DST CMP_OP (SIGN##32) SRC) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP_##OPCODE##_K: \ if ((SIGN##64) DST CMP_OP (SIGN##64) IMM) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP32_##OPCODE##_K: \ if ((SIGN##32) DST CMP_OP (SIGN##32) IMM) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; COND_JMP(u, JEQ, ==) COND_JMP(u, JNE, !=) COND_JMP(u, JGT, >) COND_JMP(u, JLT, <) COND_JMP(u, JGE, >=) COND_JMP(u, JLE, <=) COND_JMP(u, JSET, &) COND_JMP(s, JSGT, >) COND_JMP(s, JSLT, <) COND_JMP(s, JSGE, >=) COND_JMP(s, JSLE, <=) #undef COND_JMP /* ST, STX and LDX*/ ST_NOSPEC: /* Speculation barrier for mitigating Speculative Store Bypass. * In case of arm64, we rely on the firmware mitigation as * controlled via the ssbd kernel parameter. Whenever the * mitigation is enabled, it works for all of the kernel code * with no need to provide any additional instructions here. * In case of x86, we use 'lfence' insn for mitigation. We * reuse preexisting logic from Spectre v1 mitigation that * happens to produce the required code on x86 for v4 as well. */ barrier_nospec(); CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ CONT; \ ST_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \ CONT; \ LDX_MEM_##SIZEOP: \ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ CONT; \ LDX_PROBE_MEM_##SIZEOP: \ bpf_probe_read_kernel(&DST, sizeof(SIZE), \ (const void *)(long) (SRC + insn->off)); \ DST = *((SIZE *)&DST); \ CONT; LDST(B, u8) LDST(H, u16) LDST(W, u32) LDST(DW, u64) #undef LDST #define ATOMIC_ALU_OP(BOP, KOP) \ case BOP: \ if (BPF_SIZE(insn->code) == BPF_W) \ atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \ (DST + insn->off)); \ else \ atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \ (DST + insn->off)); \ break; \ case BOP | BPF_FETCH: \ if (BPF_SIZE(insn->code) == BPF_W) \ SRC = (u32) atomic_fetch_##KOP( \ (u32) SRC, \ (atomic_t *)(unsigned long) (DST + insn->off)); \ else \ SRC = (u64) atomic64_fetch_##KOP( \ (u64) SRC, \ (atomic64_t *)(unsigned long) (DST + insn->off)); \ break; STX_ATOMIC_DW: STX_ATOMIC_W: switch (IMM) { ATOMIC_ALU_OP(BPF_ADD, add) ATOMIC_ALU_OP(BPF_AND, and) ATOMIC_ALU_OP(BPF_OR, or) ATOMIC_ALU_OP(BPF_XOR, xor) #undef ATOMIC_ALU_OP case BPF_XCHG: if (BPF_SIZE(insn->code) == BPF_W) SRC = (u32) atomic_xchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) SRC); else SRC = (u64) atomic64_xchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) SRC); break; case BPF_CMPXCHG: if (BPF_SIZE(insn->code) == BPF_W) BPF_R0 = (u32) atomic_cmpxchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) BPF_R0, (u32) SRC); else BPF_R0 = (u64) atomic64_cmpxchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) BPF_R0, (u64) SRC); break; default: goto default_label; } CONT; default_label: /* If we ever reach this, we have a bug somewhere. Die hard here * instead of just returning 0; we could be somewhere in a subprog, * so execution could continue otherwise which we do /not/ want. * * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable(). */ pr_warn("BPF interpreter: unknown opcode %02x (imm: 0x%x)\n", insn->code, insn->imm); BUG_ON(1); return 0; } #define PROG_NAME(stack_size) __bpf_prog_run##stack_size #define DEFINE_BPF_PROG_RUN(stack_size) \ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ u64 regs[MAX_BPF_EXT_REG]; \ \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ ARG1 = (u64) (unsigned long) ctx; \ return ___bpf_prog_run(regs, insn); \ } #define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size #define DEFINE_BPF_PROG_RUN_ARGS(stack_size) \ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \ const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ u64 regs[MAX_BPF_EXT_REG]; \ \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ BPF_R1 = r1; \ BPF_R2 = r2; \ BPF_R3 = r3; \ BPF_R4 = r4; \ BPF_R5 = r5; \ return ___bpf_prog_run(regs, insn); \ } #define EVAL1(FN, X) FN(X) #define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y) #define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y) #define EVAL4(FN, X, Y...) FN(X) EVAL3(FN, Y) #define EVAL5(FN, X, Y...) FN(X) EVAL4(FN, Y) #define EVAL6(FN, X, Y...) FN(X) EVAL5(FN, Y) EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512); EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512); #define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size), static unsigned int (*interpreters[])(const void *ctx, const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST #define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size), static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) { stack_depth = max_t(u32, stack_depth, 1); insn->off = (s16) insn->imm; insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] - __bpf_call_base_args; insn->code = BPF_JMP | BPF_CALL_ARGS; } #else static unsigned int __bpf_prog_ret0_warn(const void *ctx, const struct bpf_insn *insn) { /* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON * is not working properly, so warn about it! */ WARN_ON_ONCE(1); return 0; } #endif bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) { bool ret; if (fp->kprobe_override) return false; spin_lock(&array->aux->owner.lock); if (!array->aux->owner.type) { /* There's no owner yet where we could check for * compatibility. */ array->aux->owner.type = fp->type; array->aux->owner.jited = fp->jited; ret = true; } else { ret = array->aux->owner.type == fp->type && array->aux->owner.jited == fp->jited; } spin_unlock(&array->aux->owner.lock); return ret; } static int bpf_check_tail_call(const struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; int i, ret = 0; mutex_lock(&aux->used_maps_mutex); for (i = 0; i < aux->used_map_cnt; i++) { struct bpf_map *map = aux->used_maps[i]; struct bpf_array *array; if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) continue; array = container_of(map, struct bpf_array, map); if (!bpf_prog_array_compatible(array, fp)) { ret = -EINVAL; goto out; } } out: mutex_unlock(&aux->used_maps_mutex); return ret; } static void bpf_prog_select_func(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; #else fp->bpf_func = __bpf_prog_ret0_warn; #endif } /** * bpf_prog_select_runtime - select exec runtime for BPF program * @fp: bpf_prog populated with internal BPF program * @err: pointer to error variable * * Try to JIT eBPF program, if JIT is not available, use interpreter. * The BPF program will be executed via bpf_prog_run() function. * * Return: the &fp argument along with &err set to 0 for success or * a negative errno code on failure */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { /* In case of BPF to BPF calls, verifier did all the prep * work with regards to JITing, etc. */ bool jit_needed = false; if (fp->bpf_func) goto finalize; if (IS_ENABLED(CONFIG_BPF_JIT_ALWAYS_ON) || bpf_prog_has_kfunc_call(fp)) jit_needed = true; bpf_prog_select_func(fp); /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during * blinding, bpf_int_jit_compile() must always return a * valid program, which in this case would simply not * be JITed, but falls back to the interpreter. */ if (!bpf_prog_is_dev_bound(fp->aux)) { *err = bpf_prog_alloc_jited_linfo(fp); if (*err) return fp; fp = bpf_int_jit_compile(fp); bpf_prog_jit_attempt_done(fp); if (!fp->jited && jit_needed) { *err = -ENOTSUPP; return fp; } } else { *err = bpf_prog_offload_compile(fp); if (*err) return fp; } finalize: *err = bpf_prog_lock_ro(fp); if (*err) return fp; /* The tail call compatibility check can only be done at * this late stage as we need to determine, if we deal * with JITed or non JITed program concatenations and not * all eBPF JITs might immediately support all features. */ *err = bpf_check_tail_call(fp); return fp; } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); static unsigned int __bpf_prog_ret1(const void *ctx, const struct bpf_insn *insn) { return 1; } static struct bpf_prog_dummy { struct bpf_prog prog; } dummy_bpf_prog = { .prog = { .bpf_func = __bpf_prog_ret1, }, }; /* to avoid allocating empty bpf_prog_array for cgroups that * don't have bpf program attached use one global 'empty_prog_array' * It will not be modified the caller of bpf_prog_array_alloc() * (since caller requested prog_cnt == 0) * that pointer should be 'freed' by bpf_prog_array_free() */ static struct { struct bpf_prog_array hdr; struct bpf_prog *null_prog; } empty_prog_array = { .null_prog = NULL, }; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { if (prog_cnt) return kzalloc(sizeof(struct bpf_prog_array) + sizeof(struct bpf_prog_array_item) * (prog_cnt + 1), flags); return &empty_prog_array.hdr; } void bpf_prog_array_free(struct bpf_prog_array *progs) { if (!progs || progs == &empty_prog_array.hdr) return; kfree_rcu(progs, rcu); } int bpf_prog_array_length(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; u32 cnt = 0; for (item = array->items; item->prog; item++) if (item->prog != &dummy_bpf_prog.prog) cnt++; return cnt; } bool bpf_prog_array_is_empty(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; for (item = array->items; item->prog; item++) if (item->prog != &dummy_bpf_prog.prog) return false; return true; } static bool bpf_prog_array_copy_core(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt) { struct bpf_prog_array_item *item; int i = 0; for (item = array->items; item->prog; item++) { if (item->prog == &dummy_bpf_prog.prog) continue; prog_ids[i] = item->prog->aux->id; if (++i == request_cnt) { item++; break; } } return !!(item->prog); } int bpf_prog_array_copy_to_user(struct bpf_prog_array *array, __u32 __user *prog_ids, u32 cnt) { unsigned long err = 0; bool nospc; u32 *ids; /* users of this function are doing: * cnt = bpf_prog_array_length(); * if (cnt > 0) * bpf_prog_array_copy_to_user(..., cnt); * so below kcalloc doesn't need extra cnt > 0 check. */ ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN); if (!ids) return -ENOMEM; nospc = bpf_prog_array_copy_core(array, ids, cnt); err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); kfree(ids); if (err) return -EFAULT; if (nospc) return -ENOSPC; return 0; } void bpf_prog_array_delete_safe(struct bpf_prog_array *array, struct bpf_prog *old_prog) { struct bpf_prog_array_item *item; for (item = array->items; item->prog; item++) if (item->prog == old_prog) { WRITE_ONCE(item->prog, &dummy_bpf_prog.prog); break; } } /** * bpf_prog_array_delete_safe_at() - Replaces the program at the given * index into the program array with * a dummy no-op program. * @array: a bpf_prog_array * @index: the index of the program to replace * * Skips over dummy programs, by not counting them, when calculating * the position of the program to replace. * * Return: * * 0 - Success * * -EINVAL - Invalid index value. Must be a non-negative integer. * * -ENOENT - Index out of range */ int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index) { return bpf_prog_array_update_at(array, index, &dummy_bpf_prog.prog); } /** * bpf_prog_array_update_at() - Updates the program at the given index * into the program array. * @array: a bpf_prog_array * @index: the index of the program to update * @prog: the program to insert into the array * * Skips over dummy programs, by not counting them, when calculating * the position of the program to update. * * Return: * * 0 - Success * * -EINVAL - Invalid index value. Must be a non-negative integer. * * -ENOENT - Index out of range */ int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, struct bpf_prog *prog) { struct bpf_prog_array_item *item; if (unlikely(index < 0)) return -EINVAL; for (item = array->items; item->prog; item++) { if (item->prog == &dummy_bpf_prog.prog) continue; if (!index) { WRITE_ONCE(item->prog, prog); return 0; } index--; } return -ENOENT; } int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, u64 bpf_cookie, struct bpf_prog_array **new_array) { int new_prog_cnt, carry_prog_cnt = 0; struct bpf_prog_array_item *existing, *new; struct bpf_prog_array *array; bool found_exclude = false; /* Figure out how many existing progs we need to carry over to * the new array. */ if (old_array) { existing = old_array->items; for (; existing->prog; existing++) { if (existing->prog == exclude_prog) { found_exclude = true; continue; } if (existing->prog != &dummy_bpf_prog.prog) carry_prog_cnt++; if (existing->prog == include_prog) return -EEXIST; } } if (exclude_prog && !found_exclude) return -ENOENT; /* How many progs (not NULL) will be in the new array? */ new_prog_cnt = carry_prog_cnt; if (include_prog) new_prog_cnt += 1; /* Do we have any prog (not NULL) in the new array? */ if (!new_prog_cnt) { *new_array = NULL; return 0; } /* +1 as the end of prog_array is marked with NULL */ array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL); if (!array) return -ENOMEM; new = array->items; /* Fill in the new prog array */ if (carry_prog_cnt) { existing = old_array->items; for (; existing->prog; existing++) { if (existing->prog == exclude_prog || existing->prog == &dummy_bpf_prog.prog) continue; new->prog = existing->prog; new->bpf_cookie = existing->bpf_cookie; new++; } } if (include_prog) { new->prog = include_prog; new->bpf_cookie = bpf_cookie; new++; } new->prog = NULL; *new_array = array; return 0; } int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt) { u32 cnt = 0; if (array) cnt = bpf_prog_array_length(array); *prog_cnt = cnt; /* return early if user requested only program count or nothing to copy */ if (!request_cnt || !cnt) return 0; /* this function is called under trace/bpf_trace.c: bpf_event_mutex */ return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC : 0; } void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len) { struct bpf_map *map; u32 i; for (i = 0; i < len; i++) { map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); bpf_map_put(map); } } static void bpf_free_used_maps(struct bpf_prog_aux *aux) { __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt); kfree(aux->used_maps); } void __bpf_free_used_btfs(struct bpf_prog_aux *aux, struct btf_mod_pair *used_btfs, u32 len) { #ifdef CONFIG_BPF_SYSCALL struct btf_mod_pair *btf_mod; u32 i; for (i = 0; i < len; i++) { btf_mod = &used_btfs[i]; if (btf_mod->module) module_put(btf_mod->module); btf_put(btf_mod->btf); } #endif } static void bpf_free_used_btfs(struct bpf_prog_aux *aux) { __bpf_free_used_btfs(aux, aux->used_btfs, aux->used_btf_cnt); kfree(aux->used_btfs); } static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; int i; aux = container_of(work, struct bpf_prog_aux, work); bpf_free_used_maps(aux); bpf_free_used_btfs(aux); if (bpf_prog_is_dev_bound(aux)) bpf_prog_offload_destroy(aux->prog); #ifdef CONFIG_PERF_EVENTS if (aux->prog->has_callchain_buf) put_callchain_buffers(); #endif if (aux->dst_trampoline) bpf_trampoline_put(aux->dst_trampoline); for (i = 0; i < aux->func_cnt; i++) { /* We can just unlink the subprog poke descriptor table as * it was originally linked to the main program and is also * released along with it. */ aux->func[i]->aux->poke_tab = NULL; bpf_jit_free(aux->func[i]); } if (aux->func_cnt) { kfree(aux->func); bpf_prog_unlock_free(aux->prog); } else { bpf_jit_free(aux->prog); } } /* Free internal BPF program */ void bpf_prog_free(struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; if (aux->dst_prog) bpf_prog_put(aux->dst_prog); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } EXPORT_SYMBOL_GPL(bpf_prog_free); /* RNG for unpriviledged user space with separated state from prandom_u32(). */ static DEFINE_PER_CPU(struct rnd_state, bpf_user_rnd_state); void bpf_user_rnd_init_once(void) { prandom_init_once(&bpf_user_rnd_state); } BPF_CALL_0(bpf_user_rnd_u32) { /* Should someone ever have the rather unwise idea to use some * of the registers passed into this function, then note that * this function is called from native eBPF and classic-to-eBPF * transformations. Register assignments from both sides are * different, f.e. classic always sets fn(ctx, A, X) here. */ struct rnd_state *state; u32 res; state = &get_cpu_var(bpf_user_rnd_state); res = prandom_u32_state(state); put_cpu_var(bpf_user_rnd_state); return res; } BPF_CALL_0(bpf_get_raw_cpu_id) { return raw_smp_processor_id(); } /* Weak definitions of helper functions in case we don't have bpf syscall. */ const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_map_push_elem_proto __weak; const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; const struct bpf_func_proto bpf_spin_lock_proto __weak; const struct bpf_func_proto bpf_spin_unlock_proto __weak; const struct bpf_func_proto bpf_jiffies64_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_snprintf_btf_proto __weak; const struct bpf_func_proto bpf_seq_printf_btf_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { return NULL; } u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { return -ENOTSUPP; } EXPORT_SYMBOL_GPL(bpf_event_output); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = { .func = NULL, .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; /* Stub for JITs that only support cBPF. eBPF programs are interpreted. * It is encouraged to implement bpf_int_jit_compile() instead, so that * eBPF and implicitly also cBPF can get JITed! */ struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog) { return prog; } /* Stub for JITs that support eBPF. All cBPF code gets transformed into * eBPF by the kernel and is later compiled by bpf_int_jit_compile(). */ void __weak bpf_jit_compile(struct bpf_prog *prog) { } bool __weak bpf_helper_changes_pkt_data(void *func) { return false; } /* Return TRUE if the JIT backend wants verifier to enable sub-register usage * analysis code and wants explicit zero extension inserted by verifier. * Otherwise, return FALSE. * * The verifier inserts an explicit zero extension after BPF_CMPXCHGs even if * you don't override this. JITs that don't want these extra insns can detect * them using insn_is_zext. */ bool __weak bpf_jit_needs_zext(void) { return false; } bool __weak bpf_jit_supports_kfunc_call(void) { return false; } /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { return -EFAULT; } int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2) { return -ENOTSUPP; } DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); /* All definitions of tracepoints related to BPF. */ #define CREATE_TRACE_POINTS #include <linux/bpf_trace.h> EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx); |
| 964 965 4 3 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * * Authors: * (C) 2015 Pengutronix, Alexander Aring <aar@pengutronix.de> */ #include <linux/module.h> #include <net/6lowpan.h> #include <net/addrconf.h> #include "6lowpan_i.h" int lowpan_register_netdevice(struct net_device *dev, enum lowpan_lltypes lltype) { int i, ret; switch (lltype) { case LOWPAN_LLTYPE_IEEE802154: dev->addr_len = EUI64_ADDR_LEN; break; case LOWPAN_LLTYPE_BTLE: dev->addr_len = ETH_ALEN; break; } dev->type = ARPHRD_6LOWPAN; dev->mtu = IPV6_MIN_MTU; lowpan_dev(dev)->lltype = lltype; spin_lock_init(&lowpan_dev(dev)->ctx.lock); for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) lowpan_dev(dev)->ctx.table[i].id = i; dev->ndisc_ops = &lowpan_ndisc_ops; ret = register_netdevice(dev); if (ret < 0) return ret; lowpan_dev_debugfs_init(dev); return ret; } EXPORT_SYMBOL(lowpan_register_netdevice); int lowpan_register_netdev(struct net_device *dev, enum lowpan_lltypes lltype) { int ret; rtnl_lock(); ret = lowpan_register_netdevice(dev, lltype); rtnl_unlock(); return ret; } EXPORT_SYMBOL(lowpan_register_netdev); void lowpan_unregister_netdevice(struct net_device *dev) { unregister_netdevice(dev); lowpan_dev_debugfs_exit(dev); } EXPORT_SYMBOL(lowpan_unregister_netdevice); void lowpan_unregister_netdev(struct net_device *dev) { rtnl_lock(); lowpan_unregister_netdevice(dev); rtnl_unlock(); } EXPORT_SYMBOL(lowpan_unregister_netdev); int addrconf_ifid_802154_6lowpan(u8 *eui, struct net_device *dev) { struct wpan_dev *wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr; /* Set short_addr autoconfiguration if short_addr is present only */ if (!lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr)) return -1; /* For either address format, all zero addresses MUST NOT be used */ if (wpan_dev->pan_id == cpu_to_le16(0x0000) && wpan_dev->short_addr == cpu_to_le16(0x0000)) return -1; /* Alternatively, if no PAN ID is known, 16 zero bits may be used */ if (wpan_dev->pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST)) memset(eui, 0, 2); else ieee802154_le16_to_be16(eui, &wpan_dev->pan_id); /* The "Universal/Local" (U/L) bit shall be set to zero */ eui[0] &= ~2; eui[2] = 0; eui[3] = 0xFF; eui[4] = 0xFE; eui[5] = 0; ieee802154_le16_to_be16(&eui[6], &wpan_dev->short_addr); return 0; } static int lowpan_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev; struct in6_addr addr; int i; if (dev->type != ARPHRD_6LOWPAN) return NOTIFY_DONE; idev = __in6_dev_get(dev); if (!idev) return NOTIFY_DONE; switch (event) { case NETDEV_UP: case NETDEV_CHANGE: /* (802.15.4 6LoWPAN short address slaac handling */ if (lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154) && addrconf_ifid_802154_6lowpan(addr.s6_addr + 8, dev) == 0) { __ipv6_addr_set_half(&addr.s6_addr32[0], htonl(0xFE800000), 0); addrconf_add_linklocal(idev, &addr, 0); } break; case NETDEV_DOWN: for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) clear_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, &lowpan_dev(dev)->ctx.table[i].flags); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block lowpan_notifier = { .notifier_call = lowpan_event, }; static int __init lowpan_module_init(void) { int ret; lowpan_debugfs_init(); ret = register_netdevice_notifier(&lowpan_notifier); if (ret < 0) { lowpan_debugfs_exit(); return ret; } request_module_nowait("nhc_dest"); request_module_nowait("nhc_fragment"); request_module_nowait("nhc_hop"); request_module_nowait("nhc_ipv6"); request_module_nowait("nhc_mobility"); request_module_nowait("nhc_routing"); request_module_nowait("nhc_udp"); return 0; } static void __exit lowpan_module_exit(void) { lowpan_debugfs_exit(); unregister_netdevice_notifier(&lowpan_notifier); } module_init(lowpan_module_init); module_exit(lowpan_module_exit); MODULE_LICENSE("GPL"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DAX_H #define _LINUX_DAX_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/radix-tree.h> /* Flag for synchronous flush */ #define DAXDEV_F_SYNC (1UL << 0) typedef unsigned long dax_entry_t; struct iomap_ops; struct iomap; struct dax_device; struct dax_operations { /* * direct_access: translate a device-relative * logical-page-offset into an absolute physical pfn. Return the * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, void **, pfn_t *); /* * Validate whether this device is usable as an fsdax backing * device. */ bool (*dax_supported)(struct dax_device *, struct block_device *, int, sector_t, sector_t); /* copy_from_iter: required operation for fs-dax direct-i/o */ size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, struct iov_iter *); /* copy_to_iter: required operation for fs-dax direct-i/o */ size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t, struct iov_iter *); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); }; extern struct attribute_group dax_attribute_group; #if IS_ENABLED(CONFIG_DAX) struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool __dax_synchronous(struct dax_device *dax_dev); static inline bool dax_synchronous(struct dax_device *dax_dev) { return __dax_synchronous(dax_dev); } void __set_dax_synchronous(struct dax_device *dax_dev); static inline void set_dax_synchronous(struct dax_device *dax_dev) { __set_dax_synchronous(dax_dev); } /* * Check if given mapping is supported by the file / underlying device. */ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { if (!(vma->vm_flags & VM_SYNC)) return true; if (!IS_DAX(file_inode(vma->vm_file))) return false; return dax_synchronous(dax_dev); } #else static inline struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags) { /* * Callers should check IS_ENABLED(CONFIG_DAX) to know if this * NULL is an error or expected. */ return NULL; } static inline void put_dax(struct dax_device *dax_dev) { } static inline void kill_dax(struct dax_device *dax_dev) { } static inline void dax_write_cache(struct dax_device *dax_dev, bool wc) { } static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) { return false; } static inline bool dax_synchronous(struct dax_device *dax_dev) { return true; } static inline void set_dax_synchronous(struct dax_device *dax_dev) { } static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { return !(vma->vm_flags & VM_SYNC); } #endif struct writeback_control; int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors); bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t len); static inline void fs_put_dax(struct dax_device *dax_dev) { put_dax(dax_dev); } struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); #else #define generic_fsdax_supported NULL static inline bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t len) { return false; } static inline void fs_put_dax(struct dax_device *dax_dev) { } static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { return NULL; } static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; } static inline struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t start, pgoff_t nr_pages) { return NULL; } static inline int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc) { return -EOPNOTSUPP; } static inline dax_entry_t dax_lock_page(struct page *page) { if (IS_DAX(page->mapping->host)) return ~0UL; return 0; } static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) { } #endif #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); #else static inline int dax_read_lock(void) { return 0; } static inline void dax_read_unlock(int id) { } #endif /* CONFIG_DAX */ bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t *pfnp, int *errp, const struct iomap_ops *ops); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } #ifdef CONFIG_DEV_DAX_HMEM_DEVICES void hmem_register_device(int target_nid, struct resource *r); #else static inline void hmem_register_device(int target_nid, struct resource *r) { } #endif #endif |
| 6 1 1 4 4 4 3 1 2 1 1 1 2 7 1 1 5 5 2 4 2 9 9 5 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ #include <linux/skmsg.h> #include <linux/filter.h> #include <linux/bpf.h> #include <linux/init.h> #include <linux/wait.h> #include <linux/util_macros.h> #include <net/inet_common.h> #include <net/tls.h> static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, u32 apply_bytes, int flags) { bool apply = apply_bytes; struct scatterlist *sge; u32 size, copied = 0; struct sk_msg *tmp; int i, ret = 0; tmp = kzalloc(sizeof(*tmp), __GFP_NOWARN | GFP_KERNEL); if (unlikely(!tmp)) return -ENOMEM; lock_sock(sk); tmp->sg.start = msg->sg.start; i = msg->sg.start; do { sge = sk_msg_elem(msg, i); size = (apply && apply_bytes < sge->length) ? apply_bytes : sge->length; if (!__sk_rmem_schedule(sk, size, false)) { if (!copied) ret = -ENOMEM; break; } sk_mem_charge(sk, size); atomic_add(size, &sk->sk_rmem_alloc); sk_msg_xfer(tmp, msg, i, size); copied += size; if (sge->length) get_page(sk_msg_page(tmp, i)); sk_msg_iter_var_next(i); tmp->sg.end = i; if (apply) { apply_bytes -= size; if (!apply_bytes) { if (sge->length) sk_msg_iter_var_prev(i); break; } } } while (i != msg->sg.end); if (!ret) { msg->sg.start = i; if (!sk_psock_queue_msg(psock, tmp)) atomic_sub(copied, &sk->sk_rmem_alloc); sk_psock_data_ready(sk, psock); } else { sk_msg_free(sk, tmp); kfree(tmp); } release_sock(sk); return ret; } static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes, int flags, bool uncharge) { bool apply = apply_bytes; struct scatterlist *sge; struct page *page; int size, ret = 0; u32 off; while (1) { bool has_tx_ulp; sge = sk_msg_elem(msg, msg->sg.start); size = (apply && apply_bytes < sge->length) ? apply_bytes : sge->length; off = sge->offset; page = sg_page(sge); tcp_rate_check_app_limited(sk); retry: has_tx_ulp = tls_sw_has_ctx_tx(sk); if (has_tx_ulp) { flags |= MSG_SENDPAGE_NOPOLICY; ret = kernel_sendpage_locked(sk, page, off, size, flags); } else { ret = do_tcp_sendpages(sk, page, off, size, flags); } if (ret <= 0) return ret; if (apply) apply_bytes -= ret; msg->sg.size -= ret; sge->offset += ret; sge->length -= ret; if (uncharge) sk_mem_uncharge(sk, ret); if (ret != size) { size -= ret; off += ret; goto retry; } if (!sge->length) { put_page(page); sk_msg_iter_next(msg, start); sg_init_table(sge, 1); if (msg->sg.start == msg->sg.end) break; } if (apply && !apply_bytes) break; } return 0; } static int tcp_bpf_push_locked(struct sock *sk, struct sk_msg *msg, u32 apply_bytes, int flags, bool uncharge) { int ret; lock_sock(sk); ret = tcp_bpf_push(sk, msg, apply_bytes, flags, uncharge); release_sock(sk); return ret; } int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, struct sk_msg *msg, u32 bytes, int flags) { struct sk_psock *psock = sk_psock_get(sk); int ret; if (unlikely(!psock)) return -EPIPE; ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes, flags) : tcp_bpf_push_locked(sk, msg, bytes, flags, false); sk_psock_put(sk, psock); return ret; } EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); #ifdef CONFIG_BPF_SYSCALL static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int ret = 0; if (sk->sk_shutdown & RCV_SHUTDOWN) return 1; if (!timeo) return ret; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); ret = sk_wait_event(sk, &timeo, !list_empty(&psock->ingress_msg) || !skb_queue_empty_lockless(&sk->sk_receive_queue), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return ret; } static bool is_next_msg_fin(struct sk_psock *psock) { struct scatterlist *sge; struct sk_msg *msg_rx; int i; msg_rx = sk_psock_peek_msg(psock); i = msg_rx->sg.start; sge = sk_msg_elem(msg_rx, i); if (!sge->length) { struct sk_buff *skb = msg_rx->skb; if (skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) return true; } return false; } static int tcp_bpf_recvmsg_parser(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { struct sk_psock *psock; int copied; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); if (!len) return 0; psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); lock_sock(sk); /* We may have received data on the sk_receive_queue pre-accept and * then we can not use read_skb in this context because we haven't * assigned a sk_socket yet so have no link to the ops. The work-around * is to check the sk_receive_queue and in these cases read skbs off * queue again. The read_skb hook is not running at this point because * of lock_sock so we avoid having multiple runners in read_skb. */ if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { tcp_data_ready(sk); /* This handles the ENOMEM errors if we both receive data * pre accept and are already under memory pressure. At least * let user know to retry. */ if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { copied = -EAGAIN; goto out; } } msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); /* The typical case for EFAULT is the socket was gracefully * shutdown with a FIN pkt. So check here the other case is * some error on copy_page_to_iter which would be unexpected. * On fin return correct return code to zero. */ if (copied == -EFAULT) { bool is_fin = is_next_msg_fin(psock); if (is_fin) { copied = 0; goto out; } } if (!copied) { long timeo; int data; if (sock_flag(sk, SOCK_DONE)) goto out; if (sk->sk_err) { copied = sock_error(sk); goto out; } if (sk->sk_shutdown & RCV_SHUTDOWN) goto out; if (sk->sk_state == TCP_CLOSE) { copied = -ENOTCONN; goto out; } timeo = sock_rcvtimeo(sk, nonblock); if (!timeo) { copied = -EAGAIN; goto out; } if (signal_pending(current)) { copied = sock_intr_errno(timeo); goto out; } data = tcp_msg_wait_data(sk, psock, timeo); if (data && !sk_psock_queue_empty(psock)) goto msg_bytes_ready; copied = -EAGAIN; } out: release_sock(sk); sk_psock_put(sk, psock); return copied; } static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { struct sk_psock *psock; int copied, ret; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); if (!len) return 0; psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); if (!skb_queue_empty(&sk->sk_receive_queue) && sk_psock_queue_empty(psock)) { sk_psock_put(sk, psock); return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); } lock_sock(sk); msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { long timeo; int data; timeo = sock_rcvtimeo(sk, nonblock); data = tcp_msg_wait_data(sk, psock, timeo); if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; release_sock(sk); sk_psock_put(sk, psock); return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); } copied = -EAGAIN; } ret = copied; release_sock(sk); sk_psock_put(sk, psock); return ret; } static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, int *copied, int flags) { bool cork = false, enospc = sk_msg_full(msg), redir_ingress; struct sock *sk_redir; u32 tosend, origsize, sent, delta = 0; u32 eval; int ret; more_data: if (psock->eval == __SK_NONE) { /* Track delta in msg size to add/subtract it on SK_DROP from * returned to user copied size. This ensures user doesn't * get a positive return code with msg_cut_data and SK_DROP * verdict. */ delta = msg->sg.size; psock->eval = sk_psock_msg_verdict(sk, psock, msg); delta -= msg->sg.size; } if (msg->cork_bytes && msg->cork_bytes > msg->sg.size && !enospc) { psock->cork_bytes = msg->cork_bytes - msg->sg.size; if (!psock->cork) { psock->cork = kzalloc(sizeof(*psock->cork), GFP_ATOMIC | __GFP_NOWARN); if (!psock->cork) return -ENOMEM; } memcpy(psock->cork, msg, sizeof(*msg)); return 0; } tosend = msg->sg.size; if (psock->apply_bytes && psock->apply_bytes < tosend) tosend = psock->apply_bytes; eval = __SK_NONE; switch (psock->eval) { case __SK_PASS: ret = tcp_bpf_push(sk, msg, tosend, flags, true); if (unlikely(ret)) { *copied -= sk_msg_free(sk, msg); break; } sk_msg_apply_bytes(psock, tosend); break; case __SK_REDIRECT: redir_ingress = psock->redir_ingress; sk_redir = psock->sk_redir; sk_msg_apply_bytes(psock, tosend); if (!psock->apply_bytes) { /* Clean up before releasing the sock lock. */ eval = psock->eval; psock->eval = __SK_NONE; psock->sk_redir = NULL; } if (psock->cork) { cork = true; psock->cork = NULL; } release_sock(sk); origsize = msg->sg.size; ret = tcp_bpf_sendmsg_redir(sk_redir, redir_ingress, msg, tosend, flags); sent = origsize - msg->sg.size; if (eval == __SK_REDIRECT) sock_put(sk_redir); lock_sock(sk); sk_mem_uncharge(sk, sent); if (unlikely(ret < 0)) { int free = sk_msg_free(sk, msg); if (!cork) *copied -= free; } if (cork) { sk_msg_free(sk, msg); kfree(msg); msg = NULL; ret = 0; } break; case __SK_DROP: default: sk_msg_free(sk, msg); sk_msg_apply_bytes(psock, tosend); *copied -= (tosend + delta); return -EACCES; } if (likely(!ret)) { if (!psock->apply_bytes) { psock->eval = __SK_NONE; if (psock->sk_redir) { sock_put(psock->sk_redir); psock->sk_redir = NULL; } } if (msg && msg->sg.data[msg->sg.start].page_link && msg->sg.data[msg->sg.start].length) goto more_data; } return ret; } static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_msg tmp, *msg_tx = NULL; int copied = 0, err = 0; struct sk_psock *psock; long timeo; int flags; /* Don't let internal do_tcp_sendpages() flags through */ flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED); flags |= MSG_NO_SHARED_FRAGS; psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_sendmsg(sk, msg, size); lock_sock(sk); timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); while (msg_data_left(msg)) { bool enospc = false; u32 copy, osize; if (sk->sk_err) { err = -sk->sk_err; goto out_err; } copy = msg_data_left(msg); if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; if (psock->cork) { msg_tx = psock->cork; } else { msg_tx = &tmp; sk_msg_init(msg_tx); } osize = msg_tx->sg.size; err = sk_msg_alloc(sk, msg_tx, msg_tx->sg.size + copy, msg_tx->sg.end - 1); if (err) { if (err != -ENOSPC) goto wait_for_memory; enospc = true; copy = msg_tx->sg.size - osize; } err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, copy); if (err < 0) { sk_msg_trim(sk, msg_tx, osize); goto out_err; } copied += copy; if (psock->cork_bytes) { if (size > psock->cork_bytes) psock->cork_bytes = 0; else psock->cork_bytes -= size; if (psock->cork_bytes && !enospc) goto out_err; /* All cork bytes are accounted, rerun the prog. */ psock->eval = __SK_NONE; psock->cork_bytes = 0; } err = tcp_bpf_send_verdict(sk, psock, msg_tx, &copied, flags); if (unlikely(err < 0)) goto out_err; continue; wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: err = sk_stream_wait_memory(sk, &timeo); if (err) { if (msg_tx && msg_tx != psock->cork) sk_msg_free(sk, msg_tx); goto out_err; } } out_err: if (err < 0) err = sk_stream_error(sk, msg->msg_flags, err); release_sock(sk); sk_psock_put(sk, psock); return copied > 0 ? copied : err; } static int tcp_bpf_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { struct sk_msg tmp, *msg = NULL; int err = 0, copied = 0; struct sk_psock *psock; bool enospc = false; psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_sendpage(sk, page, offset, size, flags); lock_sock(sk); if (psock->cork) { msg = psock->cork; } else { msg = &tmp; sk_msg_init(msg); } /* Catch case where ring is full and sendpage is stalled. */ if (unlikely(sk_msg_full(msg))) goto out_err; sk_msg_page_add(msg, page, size, offset); sk_mem_charge(sk, size); copied = size; if (sk_msg_full(msg)) enospc = true; if (psock->cork_bytes) { if (size > psock->cork_bytes) psock->cork_bytes = 0; else psock->cork_bytes -= size; if (psock->cork_bytes && !enospc) goto out_err; /* All cork bytes are accounted, rerun the prog. */ psock->eval = __SK_NONE; psock->cork_bytes = 0; } err = tcp_bpf_send_verdict(sk, psock, msg, &copied, flags); out_err: release_sock(sk); sk_psock_put(sk, psock); return copied ? copied : err; } enum { TCP_BPF_IPV4, TCP_BPF_IPV6, TCP_BPF_NUM_PROTS, }; enum { TCP_BPF_BASE, TCP_BPF_TX, TCP_BPF_RX, TCP_BPF_TXRX, TCP_BPF_NUM_CFGS, }; static struct proto *tcpv6_prot_saved __read_mostly; static DEFINE_SPINLOCK(tcpv6_prot_lock); static struct proto tcp_bpf_prots[TCP_BPF_NUM_PROTS][TCP_BPF_NUM_CFGS]; static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], struct proto *base) { prot[TCP_BPF_BASE] = *base; prot[TCP_BPF_BASE].destroy = sock_map_destroy; prot[TCP_BPF_BASE].close = sock_map_close; prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg; prot[TCP_BPF_BASE].sock_is_readable = sk_msg_is_readable; prot[TCP_BPF_TX] = prot[TCP_BPF_BASE]; prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg; prot[TCP_BPF_TX].sendpage = tcp_bpf_sendpage; prot[TCP_BPF_RX] = prot[TCP_BPF_BASE]; prot[TCP_BPF_RX].recvmsg = tcp_bpf_recvmsg_parser; prot[TCP_BPF_TXRX] = prot[TCP_BPF_TX]; prot[TCP_BPF_TXRX].recvmsg = tcp_bpf_recvmsg_parser; } static void tcp_bpf_check_v6_needs_rebuild(struct proto *ops) { if (unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) { spin_lock_bh(&tcpv6_prot_lock); if (likely(ops != tcpv6_prot_saved)) { tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV6], ops); smp_store_release(&tcpv6_prot_saved, ops); } spin_unlock_bh(&tcpv6_prot_lock); } } static int __init tcp_bpf_v4_build_proto(void) { tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot); return 0; } late_initcall(tcp_bpf_v4_build_proto); static int tcp_bpf_assert_proto_ops(struct proto *ops) { /* In order to avoid retpoline, we make assumptions when we call * into ops if e.g. a psock is not present. Make sure they are * indeed valid assumptions. */ return ops->recvmsg == tcp_recvmsg && ops->sendmsg == tcp_sendmsg && ops->sendpage == tcp_sendpage ? 0 : -ENOTSUPP; } int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE; if (psock->progs.stream_verdict || psock->progs.skb_verdict) { config = (config == TCP_BPF_TX) ? TCP_BPF_TXRX : TCP_BPF_RX; } if (restore) { if (inet_csk_has_ulp(sk)) { /* TLS does not have an unhash proto in SW cases, * but we need to ensure we stop using the sock_map * unhash routine because the associated psock is being * removed. So use the original unhash handler. */ WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash); tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space); } else { sk->sk_write_space = psock->saved_write_space; /* Pairs with lockless read in sk_clone_lock() */ WRITE_ONCE(sk->sk_prot, psock->sk_proto); } return 0; } if (sk->sk_family == AF_INET6) { if (tcp_bpf_assert_proto_ops(psock->sk_proto)) return -EINVAL; tcp_bpf_check_v6_needs_rebuild(psock->sk_proto); } /* Pairs with lockless read in sk_clone_lock() */ WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]); return 0; } EXPORT_SYMBOL_GPL(tcp_bpf_update_proto); /* If a child got cloned from a listening socket that had tcp_bpf * protocol callbacks installed, we need to restore the callbacks to * the default ones because the child does not inherit the psock state * that tcp_bpf callbacks expect. */ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { struct proto *prot = newsk->sk_prot; if (is_insidevar(prot, tcp_bpf_prots)) newsk->sk_prot = sk->sk_prot_creator; } #endif /* CONFIG_BPF_SYSCALL */ |
| 491 489 21 14 14 14 1 1 11 491 431 432 59 59 491 11 492 488 489 3 487 239 1 2 2 2 2 6 6 4 3 2 6 6 6 6 174 22 1 27 8 84 85 24 24 128 1 1 1 17 1 16 11 69 44 3 10 2 184 182 4 180 2 250 251 2 1 236 2 1 227 226 10 55 4 145 32 117 61 110 110 109 171 166 1 4 169 58 13 99 54 43 11 79 37 117 28 147 134 130 12 10 119 3 6 6 10 11 1 120 61 145 59 7 7 14 16 16 15 16 16 16 3 161 3 3 3 3 3 7 3 13 14 14 14 13 3 3 11 9 1 8 7 6 6 6 6 111 72 37 2 39 39 39 15 10 5 4 4 12 28 28 28 11 17 10 18 23 2 1 20 1 2 1 1 2 4 2 2 1 1 1 99 12 87 49 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The User Datagram Protocol (UDP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Alan Cox, <alan@lxorguk.ukuu.org.uk> * Hirokazu Takahashi, <taka@valinux.co.jp> * * Fixes: * Alan Cox : verify_area() calls * Alan Cox : stopped close while in use off icmp * messages. Not a fix but a botch that * for udp at least is 'valid'. * Alan Cox : Fixed icmp handling properly * Alan Cox : Correct error for oversized datagrams * Alan Cox : Tidied select() semantics. * Alan Cox : udp_err() fixed properly, also now * select and read wake correctly on errors * Alan Cox : udp_send verify_area moved to avoid mem leak * Alan Cox : UDP can count its memory * Alan Cox : send to an unknown connection causes * an ECONNREFUSED off the icmp, but * does NOT close. * Alan Cox : Switched to new sk_buff handlers. No more backlog! * Alan Cox : Using generic datagram code. Even smaller and the PEEK * bug no longer crashes it. * Fred Van Kempen : Net2e support for sk->broadcast. * Alan Cox : Uses skb_free_datagram * Alan Cox : Added get/set sockopt support. * Alan Cox : Broadcasting without option set returns EACCES. * Alan Cox : No wakeup calls. Instead we now use the callbacks. * Alan Cox : Use ip_tos and ip_ttl * Alan Cox : SNMP Mibs * Alan Cox : MSG_DONTROUTE, and 0.0.0.0 support. * Matt Dillon : UDP length checks. * Alan Cox : Smarter af_inet used properly. * Alan Cox : Use new kernel side addressing. * Alan Cox : Incorrect return on truncated datagram receive. * Arnt Gulbrandsen : New udp_send and stuff * Alan Cox : Cache last socket * Alan Cox : Route cache * Jon Peatfield : Minor efficiency fix to sendto(). * Mike Shaver : RFC1122 checks. * Alan Cox : Nonblocking error fix. * Willy Konynenberg : Transparent proxying support. * Mike McLagan : Routing by source * David S. Miller : New socket lookup architecture. * Last socket cache retained as it * does have a high hit rate. * Olaf Kirch : Don't linearise iovec on sendmsg. * Andi Kleen : Some cleanups, cache destination entry * for connect. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Melvin Smith : Check msg_name not msg_namelen in sendto(), * return ENOTCONN for unconnected sockets (POSIX) * Janos Farkas : don't deliver multi/broadcasts to a different * bound-to-device socket * Hirokazu Takahashi : HW checksumming for outgoing UDP * datagrams. * Hirokazu Takahashi : sendfile() on UDP works now. * Arnaldo C. Melo : convert /proc/net/udp to seq_file * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov: allow both IPv4 and IPv6 sockets to bind * a single port at the same time. * Derek Atkins <derek@ihtfp.com>: Add Encapulation Support * James Chapman : Add L2TP encapsulation type. */ #define pr_fmt(fmt) "UDP: " fmt #include <linux/uaccess.h> #include <asm/ioctls.h> #include <linux/memblock.h> #include <linux/highmem.h> #include <linux/swap.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/igmp.h> #include <linux/inetdevice.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <net/tcp_states.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/net_namespace.h> #include <net/icmp.h> #include <net/inet_hashtables.h> #include <net/ip_tunnels.h> #include <net/route.h> #include <net/checksum.h> #include <net/xfrm.h> #include <trace/events/udp.h> #include <linux/static_key.h> #include <linux/btf_ids.h> #include <trace/events/skb.h> #include <net/busy_poll.h> #include "udp_impl.h" #include <net/sock_reuseport.h> #include <net/addrconf.h> #include <net/udp_tunnel.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6_stubs.h> #endif struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); long sysctl_udp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_udp_mem); atomic_long_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); #define MAX_UDP_PORTS 65536 #define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) static int udp_lib_lport_inuse(struct net *net, __u16 num, const struct udp_hslot *hslot, unsigned long *bitmap, struct sock *sk, unsigned int log) { struct sock *sk2; kuid_t uid = sock_i_uid(sk); sk_for_each(sk2, &hslot->head) { if (net_eq(sock_net(sk2), net) && sk2 != sk && (bitmap || udp_sk(sk2)->udp_port_hash == num) && (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && inet_rcv_saddr_equal(sk, sk2, true)) { if (sk2->sk_reuseport && sk->sk_reuseport && !rcu_access_pointer(sk->sk_reuseport_cb) && uid_eq(uid, sock_i_uid(sk2))) { if (!bitmap) return 0; } else { if (!bitmap) return 1; __set_bit(udp_sk(sk2)->udp_port_hash >> log, bitmap); } } } return 0; } /* * Note: we still hold spinlock of primary hash chain, so no other writer * can insert/delete a socket with local_port == num */ static int udp_lib_lport_inuse2(struct net *net, __u16 num, struct udp_hslot *hslot2, struct sock *sk) { struct sock *sk2; kuid_t uid = sock_i_uid(sk); int res = 0; spin_lock(&hslot2->lock); udp_portaddr_for_each_entry(sk2, &hslot2->head) { if (net_eq(sock_net(sk2), net) && sk2 != sk && (udp_sk(sk2)->udp_port_hash == num) && (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && inet_rcv_saddr_equal(sk, sk2, true)) { if (sk2->sk_reuseport && sk->sk_reuseport && !rcu_access_pointer(sk->sk_reuseport_cb) && uid_eq(uid, sock_i_uid(sk2))) { res = 0; } else { res = 1; } break; } } spin_unlock(&hslot2->lock); return res; } static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) { struct net *net = sock_net(sk); kuid_t uid = sock_i_uid(sk); struct sock *sk2; sk_for_each(sk2, &hslot->head) { if (net_eq(sock_net(sk2), net) && sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && (udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) && (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && inet_rcv_saddr_equal(sk, sk2, false)) { return reuseport_add_sock(sk, sk2, inet_rcv_saddr_any(sk)); } } return reuseport_alloc(sk, inet_rcv_saddr_any(sk)); } /** * udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6 * * @sk: socket struct in question * @snum: port number to look up * @hash2_nulladdr: AF-dependent hash value in secondary hash chains, * with NULL address */ int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned int hash2_nulladdr) { struct udp_hslot *hslot, *hslot2; struct udp_table *udptable = sk->sk_prot->h.udp_table; int error = 1; struct net *net = sock_net(sk); if (!snum) { int low, high, remaining; unsigned int rand; unsigned short first, last; DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rand = prandom_u32(); first = reciprocal_scale(rand, remaining) + low; /* * force rand to be an odd multiple of UDP_HTABLE_SIZE */ rand = (rand | 1) * (udptable->mask + 1); last = first + udptable->mask + 1; do { hslot = udp_hashslot(udptable, net, first); bitmap_zero(bitmap, PORTS_PER_CHAIN); spin_lock_bh(&hslot->lock); udp_lib_lport_inuse(net, snum, hslot, bitmap, sk, udptable->log); snum = first; /* * Iterate on all possible values of snum for this hash. * Using steps of an odd multiple of UDP_HTABLE_SIZE * give us randomization and full range coverage. */ do { if (low <= snum && snum <= high && !test_bit(snum >> udptable->log, bitmap) && !inet_is_local_reserved_port(net, snum)) goto found; snum += rand; } while (snum != first); spin_unlock_bh(&hslot->lock); cond_resched(); } while (++first != last); goto fail; } else { hslot = udp_hashslot(udptable, net, snum); spin_lock_bh(&hslot->lock); if (hslot->count > 10) { int exist; unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum; slot2 &= udptable->mask; hash2_nulladdr &= udptable->mask; hslot2 = udp_hashslot2(udptable, slot2); if (hslot->count < hslot2->count) goto scan_primary_hash; exist = udp_lib_lport_inuse2(net, snum, hslot2, sk); if (!exist && (hash2_nulladdr != slot2)) { hslot2 = udp_hashslot2(udptable, hash2_nulladdr); exist = udp_lib_lport_inuse2(net, snum, hslot2, sk); } if (exist) goto fail_unlock; else goto found; } scan_primary_hash: if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, 0)) goto fail_unlock; } found: inet_sk(sk)->inet_num = snum; udp_sk(sk)->udp_port_hash = snum; udp_sk(sk)->udp_portaddr_hash ^= snum; if (sk_unhashed(sk)) { if (sk->sk_reuseport && udp_reuseport_add_sock(sk, hslot)) { inet_sk(sk)->inet_num = 0; udp_sk(sk)->udp_port_hash = 0; udp_sk(sk)->udp_portaddr_hash ^= snum; goto fail_unlock; } sock_set_flag(sk, SOCK_RCU_FREE); sk_add_node_rcu(sk, &hslot->head); hslot->count++; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); spin_lock(&hslot2->lock); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) hlist_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node, &hslot2->head); else hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, &hslot2->head); hslot2->count++; spin_unlock(&hslot2->lock); } error = 0; fail_unlock: spin_unlock_bh(&hslot->lock); fail: return error; } EXPORT_SYMBOL(udp_lib_get_port); int udp_v4_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = ipv4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum); unsigned int hash2_partial = ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0); /* precompute partial secondary hash */ udp_sk(sk)->udp_portaddr_hash = hash2_partial; return udp_lib_get_port(sk, snum, hash2_nulladdr); } static int compute_score(struct sock *sk, struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, int dif, int sdif) { int score; struct inet_sock *inet; bool dev_match; if (!net_eq(sock_net(sk), net) || udp_sk(sk)->udp_port_hash != hnum || ipv6_only_sock(sk)) return -1; if (sk->sk_rcv_saddr != daddr) return -1; score = (sk->sk_family == PF_INET) ? 2 : 1; inet = inet_sk(sk); if (inet->inet_daddr) { if (inet->inet_daddr != saddr) return -1; score += 4; } if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; score += 4; } dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif); if (!dev_match) return -1; if (sk->sk_bound_dev_if) score += 4; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; } INDIRECT_CALLABLE_SCOPE u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { static u32 udp_ehash_secret __read_mostly; net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, udp_ehash_secret + net_hash_mix(net)); } /* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif, int sdif, struct udp_hslot *hslot2, struct sk_buff *skb) { struct sock *sk, *result; int score, badness; bool need_rescore; result = NULL; badness = 0; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { need_rescore = false; rescore: score = compute_score(need_rescore ? result : sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { badness = score; if (need_rescore) continue; if (sk->sk_state == TCP_ESTABLISHED) { result = sk; continue; } result = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), saddr, sport, daddr, hnum, udp_ehashfn); if (!result) { result = sk; continue; } /* Fall back to scoring if group has connections */ if (!reuseport_has_conns(sk)) return result; /* Reuseport logic returned an error, keep original score. */ if (IS_ERR(result)) continue; /* compute_score is too long of a function to be * inlined, and calling it again here yields * measureable overhead for some * workloads. Work around it by jumping * backwards to rescore 'result'. */ need_rescore = true; goto rescore; } } return result; } static struct sock *udp4_lookup_run_bpf(struct net *net, struct udp_table *udptable, struct sk_buff *skb, __be32 saddr, __be16 sport, __be32 daddr, u16 hnum) { struct sock *sk, *reuse_sk; bool no_reuseport; if (udptable != &udp_table) return NULL; /* only UDP is supported */ no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport, daddr, hnum, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), saddr, sport, daddr, hnum, udp_ehashfn); if (reuse_sk) sk = reuse_sk; return sk; } /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, struct sk_buff *skb) { unsigned short hnum = ntohs(dport); unsigned int hash2, slot2; struct udp_hslot *hslot2; struct sock *result, *sk; hash2 = ipv4_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; /* Lookup connected or non-wildcard socket */ result = udp4_lib_lookup2(net, saddr, sport, daddr, hnum, dif, sdif, hslot2, skb); if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED) goto done; /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { sk = udp4_lookup_run_bpf(net, udptable, skb, saddr, sport, daddr, hnum); if (sk) { result = sk; goto done; } } /* Got non-wildcard socket or error on first lookup */ if (result) goto done; /* Lookup wildcard sockets */ hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; result = udp4_lib_lookup2(net, saddr, sport, htonl(INADDR_ANY), hnum, dif, sdif, hslot2, skb); done: if (IS_ERR(result)) return NULL; return result; } EXPORT_SYMBOL_GPL(__udp4_lib_lookup); static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, struct udp_table *udptable) { const struct iphdr *iph = ip_hdr(skb); return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), inet_sdif(skb), udptable, skb); } struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = ip_hdr(skb); return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), inet_sdif(skb), &udp_table, NULL); } /* Must be called under rcu_read_lock(). * Does increment socket refcount. */ #if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4) struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { struct sock *sk; sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, 0, &udp_table, NULL); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } EXPORT_SYMBOL_GPL(udp4_lib_lookup); #endif static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif, unsigned short hnum) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net) || udp_sk(sk)->udp_port_hash != hnum || (inet->inet_daddr && inet->inet_daddr != rmt_addr) || (inet->inet_dport != rmt_port && inet->inet_dport) || (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) || ipv6_only_sock(sk) || !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return false; if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif, sdif)) return false; return true; } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); EXPORT_SYMBOL(udp_encap_needed_key); #if IS_ENABLED(CONFIG_IPV6) DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); EXPORT_SYMBOL(udpv6_encap_needed_key); #endif void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); } EXPORT_SYMBOL(udp_encap_enable); void udp_encap_disable(void) { static_branch_dec(&udp_encap_needed_key); } EXPORT_SYMBOL(udp_encap_disable); /* Handler for tunnels with arbitrary destination ports: no socket lookup, go * through error handlers in encapsulations looking for a match. */ static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info) { int i; for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, u32 info); const struct ip_tunnel_encap_ops *encap; encap = rcu_dereference(iptun_encaps[i]); if (!encap) continue; handler = encap->err_handler; if (handler && !handler(skb, info)) return 0; } return -ENOENT; } /* Try to match ICMP errors to UDP tunnels by looking up a socket without * reversing source and destination port: this will match tunnels that force the * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that * lwtunnels might actually break this assumption by being configured with * different destination ports on endpoints, in this case we won't be able to * trace ICMP messages back to them. * * If this doesn't match any socket, probe tunnels with arbitrary destination * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port * we've sent packets to won't necessarily match the local destination port. * * Then ask the tunnel implementation to match the error against a valid * association. * * Return an error if we can't find a match, the socket if we need further * processing, zero otherwise. */ static struct sock *__udp4_lib_err_encap(struct net *net, const struct iphdr *iph, struct udphdr *uh, struct udp_table *udptable, struct sock *sk, struct sk_buff *skb, u32 info) { int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); /* Network header needs to point to the outer IPv4 header inside ICMP */ skb_reset_network_header(skb); /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, iph->ihl << 2); if (sk) { up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (lookup && lookup(sk, skb)) sk = NULL; goto out; } sk = __udp4_lib_lookup(net, iph->daddr, uh->source, iph->saddr, uh->dest, skb->dev->ifindex, 0, udptable, NULL); if (sk) { up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; } out: if (!sk) sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info)); skb_set_transport_header(skb, transport_offset); skb_set_network_header(skb, network_offset); return sk; } /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should * be closed and the error returned to the user. If err > 0 * it's just the icmp type << 8 | icmp code. * Header points to the ip header of the error packet. We move * on past this. Then (as it used to claim before adjustment) * header points to the first 8 bytes of the udp header. We need * to find the appropriate port. */ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) { struct inet_sock *inet; const struct iphdr *iph = (const struct iphdr *)skb->data; struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2)); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; bool tunnel = false; struct sock *sk; int harderr; int err; struct net *net = dev_net(skb->dev); sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, inet_sdif(skb), udptable, NULL); if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ if (static_branch_unlikely(&udp_encap_needed_key)) { sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb, info); if (!sk) return 0; } else sk = ERR_PTR(-ENOENT); if (IS_ERR(sk)) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return PTR_ERR(sk); } tunnel = true; } err = 0; harderr = 0; inet = inet_sk(sk); switch (type) { default: case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; case ICMP_SOURCE_QUENCH: goto out; case ICMP_PARAMETERPROB: err = EPROTO; harderr = 1; break; case ICMP_DEST_UNREACH: if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ ipv4_sk_update_pmtu(skb, sk, info); if (inet->pmtudisc != IP_PMTUDISC_DONT) { err = EMSGSIZE; harderr = 1; break; } goto out; } err = EHOSTUNREACH; if (code <= NR_ICMP_UNREACH) { harderr = icmp_err_convert[code].fatal; err = icmp_err_convert[code].errno; } break; case ICMP_REDIRECT: ipv4_sk_redirect(skb, sk); goto out; } /* * RFC1122: OK. Passes ICMP errors back to application, as per * 4.1.3.3. */ if (tunnel) { /* ...not for tunnels though: we don't have a sending socket */ if (udp_sk(sk)->encap_err_rcv) udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2); goto out; } if (!inet->recverr) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1)); sk->sk_err = err; sk_error_report(sk); out: return 0; } int udp_err(struct sk_buff *skb, u32 info) { return __udp4_lib_err(skb, info, &udp_table); } /* * Throw away all pending data and cancel the corking. Socket is locked. */ void udp_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); if (up->pending) { up->len = 0; up->pending = 0; ip_flush_pending_frames(sk); } } EXPORT_SYMBOL(udp_flush_pending_frames); /** * udp4_hwcsum - handle outgoing HW checksumming * @skb: sk_buff containing the filled-in UDP header * (checksum field must be zeroed out) * @src: source IP address * @dst: destination IP address */ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) { struct udphdr *uh = udp_hdr(skb); int offset = skb_transport_offset(skb); int len = skb->len - offset; int hlen = len; __wsum csum = 0; if (!skb_has_frag_list(skb)) { /* * Only one fragment on the socket. */ skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0); } else { struct sk_buff *frags; /* * HW-checksum won't work as there are two or more * fragments on the socket so that all csums of sk_buffs * should be together */ skb_walk_frags(skb, frags) { csum = csum_add(csum, frags->csum); hlen -= frags->len; } csum = skb_checksum(skb, offset, hlen, csum); skb->ip_summed = CHECKSUM_NONE; uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } } EXPORT_SYMBOL_GPL(udp4_hwcsum); /* Function to set UDP checksum for an IPv4 UDP packet. This is intended * for the simple case like when setting the checksum for a UDP tunnel. */ void udp_set_csum(bool nocheck, struct sk_buff *skb, __be32 saddr, __be32 daddr, int len) { struct udphdr *uh = udp_hdr(skb); if (nocheck) { uh->check = 0; } else if (skb_is_gso(skb)) { uh->check = ~udp_v4_check(len, saddr, daddr, 0); } else if (skb->ip_summed == CHECKSUM_PARTIAL) { uh->check = 0; uh->check = udp_v4_check(len, saddr, daddr, lco_csum(skb)); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); uh->check = ~udp_v4_check(len, saddr, daddr, 0); } } EXPORT_SYMBOL(udp_set_csum); static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, struct inet_cork *cork) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct udphdr *uh; int err; int is_udplite = IS_UDPLITE(sk); int offset = skb_transport_offset(skb); int len = skb->len - offset; int datalen = len - sizeof(*uh); __wsum csum = 0; /* * Create a UDP header */ uh = udp_hdr(skb); uh->source = inet->inet_sport; uh->dest = fl4->fl4_dport; uh->len = htons(len); uh->check = 0; if (cork->gso_size) { const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); if (hlen + cork->gso_size > cork->fragsize) { kfree_skb(skb); return -EINVAL; } if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); return -EINVAL; } if (sk->sk_no_check_tx) { kfree_skb(skb); return -EINVAL; } if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || dst_xfrm(skb_dst(skb))) { kfree_skb(skb); return -EIO; } if (datalen > cork->gso_size) { skb_shinfo(skb)->gso_size = cork->gso_size; skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, cork->gso_size); } goto csum_partial; } if (is_udplite) /* UDP-Lite */ csum = udplite_csum(skb); else if (sk->sk_no_check_tx) { /* UDP csum off */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ csum_partial: udp4_hwcsum(skb, fl4->saddr, fl4->daddr); goto send; } else csum = udp_csum(skb); /* add protocol-dependent pseudo-header */ uh->check = csum_tcpudp_magic(fl4->saddr, fl4->daddr, len, sk->sk_protocol, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; send: err = ip_send_skb(sock_net(sk), skb); if (err) { if (err == -ENOBUFS && !inet->recverr) { UDP_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); err = 0; } } else UDP_INC_STATS(sock_net(sk), UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } /* * Push out all pending data as one UDP datagram. Socket is locked. */ int udp_push_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct flowi4 *fl4 = &inet->cork.fl.u.ip4; struct sk_buff *skb; int err = 0; skb = ip_finish_skb(sk, fl4); if (!skb) goto out; err = udp_send_skb(skb, fl4, &inet->cork.base); out: up->len = 0; up->pending = 0; return err; } EXPORT_SYMBOL(udp_push_pending_frames); static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size) { switch (cmsg->cmsg_type) { case UDP_SEGMENT: if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u16))) return -EINVAL; *gso_size = *(__u16 *)CMSG_DATA(cmsg); return 0; default: return -EINVAL; } } int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size) { struct cmsghdr *cmsg; bool need_ip = false; int err; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_UDP) { need_ip = true; continue; } err = __udp_cmsg_send(cmsg, gso_size); if (err) return err; } return need_ip; } EXPORT_SYMBOL_GPL(udp_cmsg_send); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); struct flowi4 fl4_stack; struct flowi4 *fl4; int ulen = len; struct ipcm_cookie ipc; struct rtable *rt = NULL; int free = 0; int connected = 0; __be32 daddr, faddr, saddr; __be16 dport; u8 tos; int err, is_udplite = IS_UDPLITE(sk); int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; struct ip_options_data opt_copy; if (len > 0xFFFF) return -EMSGSIZE; /* * Check the flags. */ if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */ return -EOPNOTSUPP; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; fl4 = &inet->cork.fl.u.ip4; if (up->pending) { /* * There are pending frames. * The socket lock must be held while it's corked. */ lock_sock(sk); if (likely(up->pending)) { if (unlikely(up->pending != AF_INET)) { release_sock(sk); return -EINVAL; } goto do_append_data; } release_sock(sk); } ulen += sizeof(struct udphdr); /* * Get and verify the address. */ if (usin) { if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { if (usin->sin_family != AF_UNSPEC) return -EAFNOSUPPORT; } daddr = usin->sin_addr.s_addr; dport = usin->sin_port; if (dport == 0) return -EINVAL; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = inet->inet_daddr; dport = inet->inet_dport; /* Open fast path for connected socket. Route will not be used, if at least one option is set. */ connected = 1; } ipcm_init_sk(&ipc, inet); ipc.gso_size = READ_ONCE(up->gso_size); if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); if (err > 0) { err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); connected = 0; } if (unlikely(err < 0)) { kfree(ipc.opt); return err; } if (ipc.opt) free = 1; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { memcpy(&opt_copy, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen); ipc.opt = &opt_copy.opt; } rcu_read_unlock(); } if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, (struct sockaddr *)usin, &ipc.addr); if (err) goto out_free; if (usin) { if (usin->sin_port == 0) { /* BPF program set invalid port. Reject it. */ err = -EINVAL; goto out_free; } daddr = usin->sin_addr.s_addr; dport = usin->sin_port; } } saddr = ipc.addr; ipc.addr = faddr = daddr; if (ipc.opt && ipc.opt->opt.srr) { if (!daddr) { err = -EINVAL; goto out_free; } faddr = ipc.opt->opt.faddr; connected = 0; } tos = get_rttos(&ipc, inet); if (sock_flag(sk, SOCK_LOCALROUTE) || (msg->msg_flags & MSG_DONTROUTE) || (ipc.opt && ipc.opt->opt.is_strictroute)) { tos |= RTO_ONLINK; connected = 0; } if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) ipc.oif = inet->mc_index; if (!saddr) saddr = inet->mc_addr; connected = 0; } else if (!ipc.oif) { ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { /* oif is set, packet is to local broadcast and * uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. * If so, we want to allow the send using the uc_index. */ if (ipc.oif != inet->uc_index && ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk), inet->uc_index)) { ipc.oif = inet->uc_index; } } if (connected) rt = (struct rtable *)sk_dst_check(sk, 0); if (!rt) { struct net *net = sock_net(sk); __u8 flow_flags = inet_sk_flowi_flags(sk); fl4 = &fl4_stack; flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, flow_flags, faddr, saddr, dport, inet->inet_sport, sk->sk_uid); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } err = -EACCES; if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) goto out; if (connected) sk_dst_set(sk, dst_clone(&rt->dst)); } if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: saddr = fl4->saddr; if (!ipc.addr) daddr = ipc.addr = fl4->daddr; /* Lockless fast path for the non-corking case. */ if (!corkreq) { struct inet_cork cork; skb = ip_make_skb(sk, fl4, getfrag, msg, ulen, sizeof(struct udphdr), &ipc, &rt, &cork, msg->msg_flags); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) err = udp_send_skb(skb, fl4, &cork); goto out; } lock_sock(sk); if (unlikely(up->pending)) { /* The socket is already corked while preparing it. */ /* ... which is an evident application bug. --ANK */ release_sock(sk); net_dbg_ratelimited("socket already corked\n"); err = -EINVAL; goto out; } /* * Now cork the socket to pend data. */ fl4 = &inet->cork.fl.u.ip4; fl4->daddr = daddr; fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = inet->inet_sport; up->pending = AF_INET; do_append_data: up->len += ulen; err = ip_append_data(sk, fl4, getfrag, msg, ulen, sizeof(struct udphdr), &ipc, &rt, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_flush_pending_frames(sk); else if (!corkreq) err = udp_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) up->pending = 0; release_sock(sk); out: ip_rt_put(rt); out_free: if (free) kfree(ipc.opt); if (!err) return len; /* * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting * ENOBUFS might not be good (it's not tunable per se), but otherwise * we don't have a good statistic (IpOutDiscards but it can be too many * things). We could add another new stat but at least for now that * seems like overkill. */ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { UDP_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); } return err; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(&rt->dst, &fl4->daddr); if (!(msg->msg_flags&MSG_PROBE) || len) goto back_from_confirm; err = 0; goto out; } EXPORT_SYMBOL(udp_sendmsg); int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); int ret; if (flags & MSG_SENDPAGE_NOTLAST) flags |= MSG_MORE; if (!up->pending) { struct msghdr msg = { .msg_flags = flags|MSG_MORE }; /* Call udp_sendmsg to specify destination address which * sendpage interface can't pass. * This will succeed only when the socket is connected. */ ret = udp_sendmsg(sk, &msg, 0); if (ret < 0) return ret; } lock_sock(sk); if (unlikely(!up->pending)) { release_sock(sk); net_dbg_ratelimited("cork failed\n"); return -EINVAL; } ret = ip_append_page(sk, &inet->cork.fl.u.ip4, page, offset, size, flags); if (ret == -EOPNOTSUPP) { release_sock(sk); return sock_no_sendpage(sk->sk_socket, page, offset, size, flags); } if (ret < 0) { udp_flush_pending_frames(sk); goto out; } up->len += size; if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE))) ret = udp_push_pending_frames(sk); if (!ret) ret = size; out: release_sock(sk); return ret; } #define UDP_SKB_IS_STATELESS 0x80000000 /* all head states (dst, sk, nf conntrack) except skb extensions are * cleared by udp_rcv(). * * We need to preserve secpath, if present, to eventually process * IP_CMSG_PASSSEC at recvmsg() time. * * Other extensions can be cleared. */ static bool udp_try_make_stateless(struct sk_buff *skb) { if (!skb_has_extensions(skb)) return true; if (!secpath_exists(skb)) { skb_ext_reset(skb); return true; } return false; } static void udp_set_dev_scratch(struct sk_buff *skb) { struct udp_dev_scratch *scratch = udp_skb_scratch(skb); BUILD_BUG_ON(sizeof(struct udp_dev_scratch) > sizeof(long)); scratch->_tsize_state = skb->truesize; #if BITS_PER_LONG == 64 scratch->len = skb->len; scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); scratch->is_linear = !skb_is_nonlinear(skb); #endif if (udp_try_make_stateless(skb)) scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } static void udp_skb_csum_unnecessary_set(struct sk_buff *skb) { /* We come here after udp_lib_checksum_complete() returned 0. * This means that __skb_checksum_complete() might have * set skb->csum_valid to 1. * On 64bit platforms, we can set csum_unnecessary * to true, but only if the skb is not shared. */ #if BITS_PER_LONG == 64 if (!skb_shared(skb)) udp_skb_scratch(skb)->csum_unnecessary = true; #endif } static int udp_skb_truesize(struct sk_buff *skb) { return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS; } static bool udp_skb_has_head_state(struct sk_buff *skb) { return !(udp_skb_scratch(skb)->_tsize_state & UDP_SKB_IS_STATELESS); } /* fully reclaim rmem/fwd memory allocated for skb */ static void udp_rmem_release(struct sock *sk, int size, int partial, bool rx_queue_lock_held) { struct udp_sock *up = udp_sk(sk); struct sk_buff_head *sk_queue; int amt; if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; if (size < (sk->sk_rcvbuf >> 2) && !skb_queue_empty(&up->reader_queue)) return; } else { size += up->forward_deficit; } up->forward_deficit = 0; /* acquire the sk_receive_queue for fwd allocated memory scheduling, * if the called don't held it already */ sk_queue = &sk->sk_receive_queue; if (!rx_queue_lock_held) spin_lock(&sk_queue->lock); sk->sk_forward_alloc += size; amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1); sk->sk_forward_alloc -= amt; if (amt) __sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT); atomic_sub(size, &sk->sk_rmem_alloc); /* this can save us from acquiring the rx queue lock on next receive */ skb_queue_splice_tail_init(sk_queue, &up->reader_queue); if (!rx_queue_lock_held) spin_unlock(&sk_queue->lock); } /* Note: called with reader_queue.lock held. * Instead of using skb->truesize here, find a copy of it in skb->dev_scratch * This avoids a cache line miss while receive_queue lock is held. * Look at __udp_enqueue_schedule_skb() to find where this copy is done. */ void udp_skb_destructor(struct sock *sk, struct sk_buff *skb) { prefetch(&skb->data); udp_rmem_release(sk, udp_skb_truesize(skb), 1, false); } EXPORT_SYMBOL(udp_skb_destructor); /* as above, but the caller held the rx queue lock, too */ static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb) { prefetch(&skb->data); udp_rmem_release(sk, udp_skb_truesize(skb), 1, true); } /* Idea of busylocks is to let producers grab an extra spinlock * to relieve pressure on the receive_queue spinlock shared by consumer. * Under flood, this means that only one producer can be in line * trying to acquire the receive_queue spinlock. * These busylock can be allocated on a per cpu manner, instead of a * per socket one (that would consume a cache line per socket) */ static int udp_busylocks_log __read_mostly; static spinlock_t *udp_busylocks __read_mostly; static spinlock_t *busylock_acquire(void *ptr) { spinlock_t *busy; busy = udp_busylocks + hash_ptr(ptr, udp_busylocks_log); spin_lock(busy); return busy; } static void busylock_release(spinlock_t *busy) { if (busy) spin_unlock(busy); } int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff_head *list = &sk->sk_receive_queue; int rmem, delta, amt, err = -ENOMEM; spinlock_t *busy = NULL; int size; /* try to avoid the costly atomic add/sub pair when the receive * queue is full; always allow at least a packet */ rmem = atomic_read(&sk->sk_rmem_alloc); if (rmem > sk->sk_rcvbuf) goto drop; /* Under mem pressure, it might be helpful to help udp_recvmsg() * having linear skbs : * - Reduce memory overhead and thus increase receive queue capacity * - Less cache line misses at copyout() time * - Less work at consume_skb() (less alien page frag freeing) */ if (rmem > (sk->sk_rcvbuf >> 1)) { skb_condense(skb); busy = busylock_acquire(sk); } size = skb->truesize; udp_set_dev_scratch(skb); /* we drop only if the receive buf is full and the receive * queue contains some other skb */ rmem = atomic_add_return(size, &sk->sk_rmem_alloc); if (rmem > (size + (unsigned int)sk->sk_rcvbuf)) goto uncharge_drop; spin_lock(&list->lock); if (size >= sk->sk_forward_alloc) { amt = sk_mem_pages(size); delta = amt << SK_MEM_QUANTUM_SHIFT; if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) { err = -ENOBUFS; spin_unlock(&list->lock); goto uncharge_drop; } sk->sk_forward_alloc += delta; } sk->sk_forward_alloc -= size; /* no need to setup a destructor, we will explicitly release the * forward allocated memory on dequeue */ sock_skb_set_dropcount(sk, skb); __skb_queue_tail(list, skb); spin_unlock(&list->lock); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); busylock_release(busy); return 0; uncharge_drop: atomic_sub(skb->truesize, &sk->sk_rmem_alloc); drop: atomic_inc(&sk->sk_drops); busylock_release(busy); return err; } EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb); void udp_destruct_common(struct sock *sk) { /* reclaim completely the forward allocated memory */ struct udp_sock *up = udp_sk(sk); unsigned int total = 0; struct sk_buff *skb; skb_queue_splice_tail_init(&sk->sk_receive_queue, &up->reader_queue); while ((skb = __skb_dequeue(&up->reader_queue)) != NULL) { total += skb->truesize; kfree_skb(skb); } udp_rmem_release(sk, total, 0, true); } EXPORT_SYMBOL_GPL(udp_destruct_common); static void udp_destruct_sock(struct sock *sk) { udp_destruct_common(sk); inet_sock_destruct(sk); } int udp_init_sock(struct sock *sk) { skb_queue_head_init(&udp_sk(sk)->reader_queue); sk->sk_destruct = udp_destruct_sock; return 0; } void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) { bool slow = lock_sock_fast(sk); sk_peek_offset_bwd(sk, len); unlock_sock_fast(sk, slow); } if (!skb_unref(skb)) return; /* In the more common cases we cleared the head states previously, * see __udp_queue_rcv_skb(). */ if (unlikely(udp_skb_has_head_state(skb))) skb_release_head_state(skb); __consume_stateless_skb(skb); } EXPORT_SYMBOL_GPL(skb_consume_udp); static struct sk_buff *__first_packet_length(struct sock *sk, struct sk_buff_head *rcvq, int *total) { struct sk_buff *skb; while ((skb = skb_peek(rcvq)) != NULL) { if (udp_lib_checksum_complete(skb)) { __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, IS_UDPLITE(sk)); __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, IS_UDPLITE(sk)); atomic_inc(&sk->sk_drops); __skb_unlink(skb, rcvq); *total += skb->truesize; kfree_skb(skb); } else { udp_skb_csum_unnecessary_set(skb); break; } } return skb; } /** * first_packet_length - return length of first packet in receive queue * @sk: socket * * Drops all bad checksum frames, until a valid one is found. * Returns the length of found skb, or -1 if none is found. */ static int first_packet_length(struct sock *sk) { struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; struct sk_buff_head *sk_queue = &sk->sk_receive_queue; struct sk_buff *skb; int total = 0; int res; spin_lock_bh(&rcvq->lock); skb = __first_packet_length(sk, rcvq, &total); if (!skb && !skb_queue_empty_lockless(sk_queue)) { spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, rcvq); spin_unlock(&sk_queue->lock); skb = __first_packet_length(sk, rcvq, &total); } res = skb ? skb->len : -1; if (total) udp_rmem_release(sk, total, 1, false); spin_unlock_bh(&rcvq->lock); return res; } /* * IOCTL requests applicable to the UDP protocol */ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { int amount = max_t(int, 0, first_packet_length(sk)); return put_user(amount, (int __user *)arg); } default: return -ENOIOCTLCMD; } return 0; } EXPORT_SYMBOL(udp_ioctl); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *off, int *err) { struct sk_buff_head *sk_queue = &sk->sk_receive_queue; struct sk_buff_head *queue; struct sk_buff *last; long timeo; int error; queue = &udp_sk(sk)->reader_queue; flags |= noblock ? MSG_DONTWAIT : 0; timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { struct sk_buff *skb; error = sock_error(sk); if (error) break; error = -EAGAIN; do { spin_lock_bh(&queue->lock); skb = __skb_try_recv_from_queue(sk, queue, flags, off, err, &last); if (skb) { if (!(flags & MSG_PEEK)) udp_skb_destructor(sk, skb); spin_unlock_bh(&queue->lock); return skb; } if (skb_queue_empty_lockless(sk_queue)) { spin_unlock_bh(&queue->lock); goto busy_check; } /* refill the reader queue and walk it again * keep both queues locked to avoid re-acquiring * the sk_receive_queue lock if fwd memory scheduling * is needed. */ spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, queue); skb = __skb_try_recv_from_queue(sk, queue, flags, off, err, &last); if (skb && !(flags & MSG_PEEK)) udp_skb_dtor_locked(sk, skb); spin_unlock(&sk_queue->lock); spin_unlock_bh(&queue->lock); if (skb) return skb; busy_check: if (!sk_can_busy_loop(sk)) break; sk_busy_loop(sk, flags & MSG_DONTWAIT); } while (!skb_queue_empty_lockless(sk_queue)); /* sk_queue is empty, reader_queue may contain peeked packets */ } while (timeo && !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue, &error, &timeo, (struct sk_buff *)sk_queue)); *err = error; return NULL; } EXPORT_SYMBOL(__skb_recv_udp); int udp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor) { int copied = 0; while (1) { struct sk_buff *skb; int err, used; skb = skb_recv_udp(sk, 0, 1, &err); if (!skb) return err; if (udp_lib_checksum_complete(skb)) { __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, IS_UDPLITE(sk)); __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, IS_UDPLITE(sk)); atomic_inc(&sk->sk_drops); kfree_skb(skb); continue; } used = recv_actor(desc, skb, 0, skb->len); if (used <= 0) { if (!copied) copied = used; kfree_skb(skb); break; } else if (used <= skb->len) { copied += used; } kfree_skb(skb); if (!desc->count) break; } return copied; } EXPORT_SYMBOL(udp_read_sock); /* * This should be easy, if there is something there we * return it, otherwise we block. */ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; unsigned int ulen, copied; int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); bool checksum_valid = false; if (flags & MSG_ERRQUEUE) return ip_recv_error(sk, msg, len, addr_len); try_again: off = sk_peek_offset(sk, flags); skb = __skb_recv_udp(sk, flags, noblock, &off, &err); if (!skb) return err; ulen = udp_skb_len(skb); copied = len; if (copied > ulen - off) copied = ulen - off; else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; /* * If checksum is needed at all, try to do it while copying the * data. If the data is truncated, or if we only want a partial * coverage checksum (UDP-Lite), do it before the copy. */ if (copied < ulen || peeking || (is_udplite && UDP_SKB_CB(skb)->partial_cov)) { checksum_valid = udp_skb_csum_unnecessary(skb) || !__udp_lib_checksum_complete(skb); if (!checksum_valid) goto csum_copy_err; } if (checksum_valid || udp_skb_csum_unnecessary(skb)) { if (udp_skb_is_linear(skb)) err = copy_linear_skb(skb, copied, off, &msg->msg_iter); else err = skb_copy_datagram_msg(skb, off, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) goto csum_copy_err; } if (unlikely(err)) { if (!peeking) { atomic_inc(&sk->sk_drops); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } kfree_skb(skb); return err; } if (!peeking) UDP_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS, is_udplite); sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ if (sin) { sin->sin_family = AF_INET; sin->sin_port = udp_hdr(skb)->source; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, (struct sockaddr *)sin); } if (udp_sk(sk)->gro_enabled) udp_cmsg_recv(msg, sk, skb); if (inet->cmsg_flags) ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off); err = copied; if (flags & MSG_TRUNC) err = ulen; skb_consume_udp(sk, skb, peeking ? -err : err); return err; csum_copy_err: if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, udp_skb_destructor)) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } kfree_skb(skb); /* starting over for a new packet, but check if we need to yield */ cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from __ip4_datagram_connect() and * intended to prevent BPF program called below from accessing bytes * that are out of the bound specified by user in addr_len. */ if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr); } EXPORT_SYMBOL(udp_pre_connect); int __udp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); /* * 1003.1g - break association. */ sk->sk_state = TCP_CLOSE; inet->inet_daddr = 0; inet->inet_dport = 0; sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); if (sk->sk_prot->rehash && (sk->sk_userlocks & SOCK_BINDPORT_LOCK)) sk->sk_prot->rehash(sk); } if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); inet->inet_sport = 0; } sk_dst_reset(sk); return 0; } EXPORT_SYMBOL(__udp_disconnect); int udp_disconnect(struct sock *sk, int flags) { lock_sock(sk); __udp_disconnect(sk, flags); release_sock(sk); return 0; } EXPORT_SYMBOL(udp_disconnect); void udp_lib_unhash(struct sock *sk) { if (sk_hashed(sk)) { struct udp_table *udptable = sk->sk_prot->h.udp_table; struct udp_hslot *hslot, *hslot2; hslot = udp_hashslot(udptable, sock_net(sk), udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); spin_lock_bh(&hslot->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); if (sk_del_node_init_rcu(sk)) { hslot->count--; inet_sk(sk)->inet_num = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_lock(&hslot2->lock); hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); hslot2->count--; spin_unlock(&hslot2->lock); } spin_unlock_bh(&hslot->lock); } } EXPORT_SYMBOL(udp_lib_unhash); /* * inet_rcv_saddr was changed, we must rehash secondary hash */ void udp_lib_rehash(struct sock *sk, u16 newhash) { if (sk_hashed(sk)) { struct udp_table *udptable = sk->sk_prot->h.udp_table; struct udp_hslot *hslot, *hslot2, *nhslot2; hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); udp_sk(sk)->udp_portaddr_hash = newhash; if (hslot2 != nhslot2 || rcu_access_pointer(sk->sk_reuseport_cb)) { hslot = udp_hashslot(udptable, sock_net(sk), udp_sk(sk)->udp_port_hash); /* we must lock primary chain too */ spin_lock_bh(&hslot->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); if (hslot2 != nhslot2) { spin_lock(&hslot2->lock); hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); hslot2->count--; spin_unlock(&hslot2->lock); spin_lock(&nhslot2->lock); hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, &nhslot2->head); nhslot2->count++; spin_unlock(&nhslot2->lock); } spin_unlock_bh(&hslot->lock); } } } EXPORT_SYMBOL(udp_lib_rehash); void udp_v4_rehash(struct sock *sk) { u16 new_hash = ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, inet_sk(sk)->inet_num); udp_lib_rehash(sk, new_hash); } static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; if (inet_sk(sk)->inet_daddr) { sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); sk_incoming_cpu_update(sk); } else { sk_mark_napi_id_once(sk, skb); } rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); else UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS, is_udplite); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } return 0; } /* returns: * -1: error * 0: success * >0: "udp encap" protocol resubmission * * Note that in the success and error cases, the skb is assumed to * have either been requeued or freed. */ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); /* * Charge it to the socket, dropping if the queue is full. */ if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; nf_reset_ct(skb); if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* * This is an encapsulation socket so pass the skb to * the socket's udp_encap_rcv() hook. Otherwise, just * fall through and pass this up the UDP socket. * up->encap_rcv() returns the following value: * =0 if skb was successfully passed to the encap * handler or was discarded by it. * >0 if skb should be passed on to UDP. * <0 if skb should be resubmitted as proto -N */ /* if we're overly short, let UDP handle it */ encap_rcv = READ_ONCE(up->encap_rcv); if (encap_rcv) { int ret; /* Verify checksum before giving to encap */ if (udp_lib_checksum_complete(skb)) goto csum_error; ret = encap_rcv(sk, skb); if (ret <= 0) { __UDP_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS, is_udplite); return -ret; } } /* FALLTHROUGH -- it's a UDP Packet */ } /* * UDP-Lite specific tests, ignored on UDP sockets */ if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { /* * MIB statistics other than incrementing the error count are * disabled for the following two types of errors: these depend * on the application settings, not on the functioning of the * protocol stack as such. * * RFC 3828 here recommends (sec 3.3): "There should also be a * way ... to ... at least let the receiving application block * delivery of packets with coverage values less than a value * provided by the application." */ if (up->pcrlen == 0) { /* full coverage was set */ net_dbg_ratelimited("UDPLite: partial coverage %d while full coverage %d requested\n", UDP_SKB_CB(skb)->cscov, skb->len); goto drop; } /* The next case involves violating the min. coverage requested * by the receiver. This is subtle: if receiver wants x and x is * greater than the buffersize/MTU then receiver will complain * that it wants x while sender emits packets of smaller size y. * Therefore the above ...()->partial_cov statement is essential. */ if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { net_dbg_ratelimited("UDPLite: coverage %d too small, need min %d\n", UDP_SKB_CB(skb)->cscov, up->pcrlen); goto drop; } } prefetch(&sk->sk_rmem_alloc); if (rcu_access_pointer(sk->sk_filter) && udp_lib_checksum_complete(skb)) goto csum_error; if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) goto drop; udp_csum_pull_header(skb); ipv4_pktinfo_prepare(sk, skb); return __udp_queue_rcv_skb(sk, skb); csum_error: __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); kfree_skb(skb); return -1; } static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff *next, *segs; int ret; if (likely(!udp_unexpected_gso(sk, skb))) return udp_queue_rcv_one_skb(sk, skb); BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_GSO_CB_OFFSET); __skb_push(skb, -skb_mac_offset(skb)); segs = udp_rcv_segment(sk, skb, true); skb_list_walk_safe(segs, skb, next) { __skb_pull(skb, skb_transport_offset(skb)); udp_post_segment_fix_csum(skb); ret = udp_queue_rcv_one_skb(sk, skb); if (ret > 0) ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret); } return 0; } /* For TCP sockets, sk_rx_dst is protected by socket lock * For UDP, we use xchg() to guard against concurrent changes. */ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old; if (dst_hold_safe(dst)) { old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst); dst_release(old); return old != dst; } return false; } EXPORT_SYMBOL(udp_sk_rx_dst_set); /* * Multicasts and broadcasts go to each listener. * * Note: called only from the BH handler context. */ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udphdr *uh, __be32 saddr, __be32 daddr, struct udp_table *udptable, int proto) { struct sock *sk, *first = NULL; unsigned short hnum = ntohs(uh->dest); struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); unsigned int offset = offsetof(typeof(*sk), sk_node); int dif = skb->dev->ifindex; int sdif = inet_sdif(skb); struct hlist_node *node; struct sk_buff *nskb; if (use_hash2) { hash2_any = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & udptable->mask; hash2 = ipv4_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) { if (!__udp_is_mcast_sock(net, sk, uh->dest, daddr, uh->source, saddr, dif, sdif, hnum)) continue; if (!first) { first = sk; continue; } nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) { atomic_inc(&sk->sk_drops); __UDP_INC_STATS(net, UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk)); __UDP_INC_STATS(net, UDP_MIB_INERRORS, IS_UDPLITE(sk)); continue; } if (udp_queue_rcv_skb(sk, nskb) > 0) consume_skb(nskb); } /* Also lookup *:port if we are using hash2 and haven't done so yet. */ if (use_hash2 && hash2 != hash2_any) { hash2 = hash2_any; goto start_lookup; } if (first) { if (udp_queue_rcv_skb(first, skb) > 0) consume_skb(skb); } else { kfree_skb(skb); __UDP_INC_STATS(net, UDP_MIB_IGNOREDMULTI, proto == IPPROTO_UDPLITE); } return 0; } /* Initialize UDP checksum. If exited with zero value (success), * CHECKSUM_UNNECESSARY means, that no more checks are required. * Otherwise, csum completion requires checksumming packet body, * including udp header and folding it to skb->csum. */ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) { int err; UDP_SKB_CB(skb)->partial_cov = 0; UDP_SKB_CB(skb)->cscov = skb->len; if (proto == IPPROTO_UDPLITE) { err = udplite_checksum_init(skb, uh); if (err) return err; if (UDP_SKB_CB(skb)->partial_cov) { skb->csum = inet_compute_pseudo(skb, proto); return 0; } } /* Note, we are only interested in != 0 or == 0, thus the * force to int. */ err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check, inet_compute_pseudo); if (err) return err; if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) { /* If SW calculated the value, we know it's bad */ if (skb->csum_complete_sw) return 1; /* HW says the value is bad. Let's validate that. * skb->csum is no longer the full packet checksum, * so don't treat it as such. */ skb_checksum_complete_unset(skb); } return 0; } /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and * return code conversion for ip layer consumption */ static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, struct udphdr *uh) { int ret; if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) skb_checksum_try_convert(skb, IPPROTO_UDP, inet_compute_pseudo); ret = udp_queue_rcv_skb(sk, skb); /* a return value > 0 means to resubmit the input, but * it wants the return to be -protocol, or 0 */ if (ret > 0) return -ret; return 0; } /* * All we need to do is get the socket, and then do a checksum. */ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { struct sock *sk; struct udphdr *uh; unsigned short ulen; struct rtable *rt = skb_rtable(skb); __be32 saddr, daddr; struct net *net = dev_net(skb->dev); bool refcounted; int drop_reason; drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; /* * Validate the packet. */ if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto drop; /* No space for header. */ uh = udp_hdr(skb); ulen = ntohs(uh->len); saddr = ip_hdr(skb)->saddr; daddr = ip_hdr(skb)->daddr; if (ulen > skb->len) goto short_packet; if (proto == IPPROTO_UDP) { /* UDP validates ulen. */ if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen)) goto short_packet; uh = udp_hdr(skb); } if (udp4_csum_init(skb, uh, proto)) goto csum_error; sk = skb_steal_sock(skb, &refcounted); if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp_sk_rx_dst_set(sk, dst); ret = udp_unicast_rcv_skb(sk, skb, uh); if (refcounted) sock_put(sk); return ret; } if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) return __udp4_lib_mcast_deliver(net, skb, uh, saddr, daddr, udptable, proto); sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) return udp_unicast_rcv_skb(sk, skb, uh); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; nf_reset_ct(skb); /* No socket. Drop packet silently, if checksum is wrong */ if (udp_lib_checksum_complete(skb)) goto csum_error; drop_reason = SKB_DROP_REASON_NO_SOCKET; __UDP_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); /* * Hmm. We got an UDP packet to a port to which we * don't wanna listen. Ignore it. */ kfree_skb_reason(skb, drop_reason); return 0; short_packet: drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; net_dbg_ratelimited("UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n", proto == IPPROTO_UDPLITE ? "Lite" : "", &saddr, ntohs(uh->source), ulen, skb->len, &daddr, ntohs(uh->dest)); goto drop; csum_error: /* * RFC1122: OK. Discards the bad packet silently (as far as * the network is concerned, anyway) as per 4.1.3.4 (MUST). */ drop_reason = SKB_DROP_REASON_UDP_CSUM; net_dbg_ratelimited("UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n", proto == IPPROTO_UDPLITE ? "Lite" : "", &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest), ulen); __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); drop: __UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); kfree_skb_reason(skb, drop_reason); return 0; } /* We can only early demux multicast if there is a single matching socket. * If more than one socket found returns NULL */ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif) { struct sock *sk, *result; unsigned short hnum = ntohs(loc_port); unsigned int slot = udp_hashfn(net, hnum, udp_table.mask); struct udp_hslot *hslot = &udp_table.hash[slot]; /* Do not bother scanning a too big list */ if (hslot->count > 10) return NULL; result = NULL; sk_for_each_rcu(sk, &hslot->head) { if (__udp_is_mcast_sock(net, sk, loc_port, loc_addr, rmt_port, rmt_addr, dif, sdif, hnum)) { if (result) return NULL; result = sk; } } return result; } /* For unicast we should only early demux connected sockets or we can * break forwarding setups. The chains here can be long so only check * if the first socket is an exact match and if not move on. */ static struct sock *__udp4_lib_demux_lookup(struct net *net, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif) { unsigned short hnum = ntohs(loc_port); unsigned int hash2 = ipv4_portaddr_hash(net, loc_addr, hnum); unsigned int slot2 = hash2 & udp_table.mask; struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr); const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum); struct sock *sk; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { if (INET_MATCH(net, sk, acookie, ports, dif, sdif)) return sk; /* Only check first socket in chain */ break; } return NULL; } int udp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct in_device *in_dev = NULL; const struct iphdr *iph; const struct udphdr *uh; struct sock *sk = NULL; struct dst_entry *dst; int dif = skb->dev->ifindex; int sdif = inet_sdif(skb); int ours; /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) return 0; iph = ip_hdr(skb); uh = udp_hdr(skb); if (skb->pkt_type == PACKET_MULTICAST) { in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) return 0; ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, iph->protocol); if (!ours) return 0; sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif, sdif); } else if (skb->pkt_type == PACKET_HOST) { sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif, sdif); } if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return 0; skb->sk = sk; skb->destructor = sock_efree; dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); if (dst) { u32 itag = 0; /* set noref for now. * any place which wants to hold dst has to call * dst_hold_safe() */ skb_dst_set_noref(skb, dst); /* for unconnected multicast sockets we need to validate * the source on each packet */ if (!inet_sk(sk)->inet_daddr && in_dev) return ip_mc_validate_source(skb, iph->daddr, iph->saddr, iph->tos & IPTOS_RT_MASK, skb->dev, in_dev, &itag); } return 0; } int udp_rcv(struct sk_buff *skb) { return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP); } void udp_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); /* protects from races with udp_abort() */ sock_set_flag(sk, SOCK_DEAD); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); if (static_branch_unlikely(&udp_encap_needed_key)) { if (up->encap_type) { void (*encap_destroy)(struct sock *sk); encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) encap_destroy(sk); } if (up->encap_enabled) static_branch_dec(&udp_encap_needed_key); } } /* * Socket option code for UDP */ int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)) { struct udp_sock *up = udp_sk(sk); int val, valbool; int err = 0; int is_udplite = IS_UDPLITE(sk); if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; valbool = val ? 1 : 0; switch (optname) { case UDP_CORK: if (val != 0) { WRITE_ONCE(up->corkflag, 1); } else { WRITE_ONCE(up->corkflag, 0); lock_sock(sk); push_pending_frames(sk); release_sock(sk); } break; case UDP_ENCAP: switch (val) { case 0: #ifdef CONFIG_XFRM case UDP_ENCAP_ESPINUDP: case UDP_ENCAP_ESPINUDP_NON_IKE: #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) WRITE_ONCE(up->encap_rcv, ipv6_stub->xfrm6_udp_encap_rcv); else #endif WRITE_ONCE(up->encap_rcv, xfrm4_udp_encap_rcv); #endif fallthrough; case UDP_ENCAP_L2TPINUDP: up->encap_type = val; lock_sock(sk); udp_tunnel_encap_enable(sk->sk_socket); release_sock(sk); break; default: err = -ENOPROTOOPT; break; } break; case UDP_NO_CHECK6_TX: up->no_check6_tx = valbool; break; case UDP_NO_CHECK6_RX: up->no_check6_rx = valbool; break; case UDP_SEGMENT: if (val < 0 || val > USHRT_MAX) return -EINVAL; WRITE_ONCE(up->gso_size, val); break; case UDP_GRO: lock_sock(sk); /* when enabling GRO, accept the related GSO packet type */ if (valbool) udp_tunnel_encap_enable(sk->sk_socket); up->gro_enabled = valbool; up->accept_udp_l4 = valbool; release_sock(sk); break; /* * UDP-Lite's partial checksum coverage (RFC 3828). */ /* The sender sets actual checksum coverage length via this option. * The case coverage > packet length is handled by send module. */ case UDPLITE_SEND_CSCOV: if (!is_udplite) /* Disable the option on UDP sockets */ return -ENOPROTOOPT; if (val != 0 && val < 8) /* Illegal coverage: use default (8) */ val = 8; else if (val > USHRT_MAX) val = USHRT_MAX; up->pcslen = val; up->pcflag |= UDPLITE_SEND_CC; break; /* The receiver specifies a minimum checksum coverage value. To make * sense, this should be set to at least 8 (as done below). If zero is * used, this again means full checksum coverage. */ case UDPLITE_RECV_CSCOV: if (!is_udplite) /* Disable the option on UDP sockets */ return -ENOPROTOOPT; if (val != 0 && val < 8) /* Avoid silly minimal values. */ val = 8; else if (val > USHRT_MAX) val = USHRT_MAX; up->pcrlen = val; up->pcflag |= UDPLITE_RECV_CC; break; default: err = -ENOPROTOOPT; break; } return err; } EXPORT_SYMBOL(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_push_pending_frames); return ip_setsockopt(sk, level, optname, optval, optlen); } int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct udp_sock *up = udp_sk(sk); int val, len; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; len = min_t(unsigned int, len, sizeof(int)); switch (optname) { case UDP_CORK: val = READ_ONCE(up->corkflag); break; case UDP_ENCAP: val = up->encap_type; break; case UDP_NO_CHECK6_TX: val = up->no_check6_tx; break; case UDP_NO_CHECK6_RX: val = up->no_check6_rx; break; case UDP_SEGMENT: val = READ_ONCE(up->gso_size); break; case UDP_GRO: val = up->gro_enabled; break; /* The following two cannot be changed on UDP sockets, the return is * always 0 (which corresponds to the full checksum coverage of UDP). */ case UDPLITE_SEND_CSCOV: val = up->pcslen; break; case UDPLITE_RECV_CSCOV: val = up->pcrlen; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } EXPORT_SYMBOL(udp_lib_getsockopt); int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_getsockopt(sk, level, optname, optval, optlen); return ip_getsockopt(sk, level, optname, optval, optlen); } /** * udp_poll - wait for a UDP event. * @file: - file struct * @sock: - socket * @wait: - poll table * * This is same as datagram poll, except for the special case of * blocking sockets. If application is using a blocking fd * and a packet with checksum error is in the queue; * then it could get return from select indicating data available * but then block when reading it. Add special case code * to work around these arguably broken applications. */ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) { __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Check for false positives due to checksum errors */ if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) && !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) mask &= ~(EPOLLIN | EPOLLRDNORM); /* psock ingress_msg queue should not contain any bad checksum frames */ if (sk_is_readable(sk)) mask |= EPOLLIN | EPOLLRDNORM; return mask; } EXPORT_SYMBOL(udp_poll); int udp_abort(struct sock *sk, int err) { lock_sock(sk); /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing * with close() */ if (sock_flag(sk, SOCK_DEAD)) goto out; sk->sk_err = err; sk_error_report(sk); __udp_disconnect(sk, 0); out: release_sock(sk); return 0; } EXPORT_SYMBOL_GPL(udp_abort); struct proto udp_prot = { .name = "UDP", .owner = THIS_MODULE, .close = udp_lib_close, .pre_connect = udp_pre_connect, .connect = ip4_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, .init = udp_init_sock, .destroy = udp_destroy_sock, .setsockopt = udp_setsockopt, .getsockopt = udp_getsockopt, .sendmsg = udp_sendmsg, .recvmsg = udp_recvmsg, .sendpage = udp_sendpage, .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp_sock), .h.udp_table = &udp_table, .diag_destroy = udp_abort, }; EXPORT_SYMBOL(udp_prot); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS static struct sock *udp_get_first(struct seq_file *seq, int start) { struct sock *sk; struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else afinfo = PDE_DATA(file_inode(seq->file)); for (state->bucket = start; state->bucket <= afinfo->udp_table->mask; ++state->bucket) { struct udp_hslot *hslot = &afinfo->udp_table->hash[state->bucket]; if (hlist_empty(&hslot->head)) continue; spin_lock_bh(&hslot->lock); sk_for_each(sk, &hslot->head) { if (!net_eq(sock_net(sk), net)) continue; if (afinfo->family == AF_UNSPEC || sk->sk_family == afinfo->family) goto found; } spin_unlock_bh(&hslot->lock); } sk = NULL; found: return sk; } static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) { struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else afinfo = PDE_DATA(file_inode(seq->file)); do { sk = sk_next(sk); } while (sk && (!net_eq(sock_net(sk), net) || (afinfo->family != AF_UNSPEC && sk->sk_family != afinfo->family))); if (!sk) { if (state->bucket <= afinfo->udp_table->mask) spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); return udp_get_first(seq, state->bucket + 1); } return sk; } static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) { struct sock *sk = udp_get_first(seq, 0); if (sk) while (pos && (sk = udp_get_next(seq, sk)) != NULL) --pos; return pos ? NULL : sk; } void *udp_seq_start(struct seq_file *seq, loff_t *pos) { struct udp_iter_state *state = seq->private; state->bucket = MAX_UDP_PORTS; return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } EXPORT_SYMBOL(udp_seq_start); void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock *sk; if (v == SEQ_START_TOKEN) sk = udp_get_idx(seq, 0); else sk = udp_get_next(seq, v); ++*pos; return sk; } EXPORT_SYMBOL(udp_seq_next); void udp_seq_stop(struct seq_file *seq, void *v) { struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else afinfo = PDE_DATA(file_inode(seq->file)); if (state->bucket <= afinfo->udp_table->mask) spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); } EXPORT_SYMBOL(udp_seq_stop); /* ------------------------------------------------------------------------ */ static void udp4_format_sock(struct sock *sp, struct seq_file *f, int bucket) { struct inet_sock *inet = inet_sk(sp); __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); seq_printf(f, "%5d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u", bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), udp_rqueue_get(sp), 0, 0L, 0, from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 0, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } int udp4_seq_show(struct seq_file *seq, void *v) { seq_setwidth(seq, 127); if (v == SEQ_START_TOKEN) seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode ref pointer drops"); else { struct udp_iter_state *state = seq->private; udp4_format_sock(v, seq, state->bucket); } seq_pad(seq, '\n'); return 0; } #ifdef CONFIG_BPF_SYSCALL struct bpf_iter__udp { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct udp_sock *, udp_sk); uid_t uid __aligned(8); int bucket __aligned(8); }; static int udp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, struct udp_sock *udp_sk, uid_t uid, int bucket) { struct bpf_iter__udp ctx; meta->seq_num--; /* skip SEQ_START_TOKEN */ ctx.meta = meta; ctx.udp_sk = udp_sk; ctx.uid = uid; ctx.bucket = bucket; return bpf_iter_run_prog(prog, &ctx); } static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v) { struct udp_iter_state *state = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; struct sock *sk = v; uid_t uid; if (v == SEQ_START_TOKEN) return 0; uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); meta.seq = seq; prog = bpf_iter_get_info(&meta, false); return udp_prog_seq_show(prog, &meta, v, uid, state->bucket); } static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)udp_prog_seq_show(prog, &meta, v, 0, 0); } udp_seq_stop(seq, v); } static const struct seq_operations bpf_iter_udp_seq_ops = { .start = udp_seq_start, .next = udp_seq_next, .stop = bpf_iter_udp_seq_stop, .show = bpf_iter_udp_seq_show, }; #endif const struct seq_operations udp_seq_ops = { .start = udp_seq_start, .next = udp_seq_next, .stop = udp_seq_stop, .show = udp4_seq_show, }; EXPORT_SYMBOL(udp_seq_ops); static struct udp_seq_afinfo udp4_seq_afinfo = { .family = AF_INET, .udp_table = &udp_table, }; static int __net_init udp4_proc_init_net(struct net *net) { if (!proc_create_net_data("udp", 0444, net->proc_net, &udp_seq_ops, sizeof(struct udp_iter_state), &udp4_seq_afinfo)) return -ENOMEM; return 0; } static void __net_exit udp4_proc_exit_net(struct net *net) { remove_proc_entry("udp", net->proc_net); } static struct pernet_operations udp4_net_ops = { .init = udp4_proc_init_net, .exit = udp4_proc_exit_net, }; int __init udp4_proc_init(void) { return register_pernet_subsys(&udp4_net_ops); } void udp4_proc_exit(void) { unregister_pernet_subsys(&udp4_net_ops); } #endif /* CONFIG_PROC_FS */ static __initdata unsigned long uhash_entries; static int __init set_uhash_entries(char *str) { ssize_t ret; if (!str) return 0; ret = kstrtoul(str, 0, &uhash_entries); if (ret) return 0; if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN) uhash_entries = UDP_HTABLE_SIZE_MIN; return 1; } __setup("uhash_entries=", set_uhash_entries); void __init udp_table_init(struct udp_table *table, const char *name) { unsigned int i; table->hash = alloc_large_system_hash(name, 2 * sizeof(struct udp_hslot), uhash_entries, 21, /* one slot per 2 MB */ 0, &table->log, &table->mask, UDP_HTABLE_SIZE_MIN, 64 * 1024); table->hash2 = table->hash + (table->mask + 1); for (i = 0; i <= table->mask; i++) { INIT_HLIST_HEAD(&table->hash[i].head); table->hash[i].count = 0; spin_lock_init(&table->hash[i].lock); } for (i = 0; i <= table->mask; i++) { INIT_HLIST_HEAD(&table->hash2[i].head); table->hash2[i].count = 0; spin_lock_init(&table->hash2[i].lock); } } u32 udp_flow_hashrnd(void) { static u32 hashrnd __read_mostly; net_get_random_once(&hashrnd, sizeof(hashrnd)); return hashrnd; } EXPORT_SYMBOL(udp_flow_hashrnd); static void __udp_sysctl_init(struct net *net) { net->ipv4.sysctl_udp_rmem_min = SK_MEM_QUANTUM; net->ipv4.sysctl_udp_wmem_min = SK_MEM_QUANTUM; #ifdef CONFIG_NET_L3_MASTER_DEV net->ipv4.sysctl_udp_l3mdev_accept = 0; #endif } static int __net_init udp_sysctl_init(struct net *net) { __udp_sysctl_init(net); return 0; } static struct pernet_operations __net_initdata udp_sysctl_ops = { .init = udp_sysctl_init, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta, struct udp_sock *udp_sk, uid_t uid, int bucket) static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux) { struct udp_iter_state *st = priv_data; struct udp_seq_afinfo *afinfo; int ret; afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN); if (!afinfo) return -ENOMEM; afinfo->family = AF_UNSPEC; afinfo->udp_table = &udp_table; st->bpf_seq_afinfo = afinfo; ret = bpf_iter_init_seq_net(priv_data, aux); if (ret) kfree(afinfo); return ret; } static void bpf_iter_fini_udp(void *priv_data) { struct udp_iter_state *st = priv_data; kfree(st->bpf_seq_afinfo); bpf_iter_fini_seq_net(priv_data); } static const struct bpf_iter_seq_info udp_seq_info = { .seq_ops = &bpf_iter_udp_seq_ops, .init_seq_private = bpf_iter_init_udp, .fini_seq_private = bpf_iter_fini_udp, .seq_priv_size = sizeof(struct udp_iter_state), }; static struct bpf_iter_reg udp_reg_info = { .target = "udp", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__udp, udp_sk), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &udp_seq_info, }; static void __init bpf_iter_register(void) { udp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UDP]; if (bpf_iter_reg_target(&udp_reg_info)) pr_warn("Warning: could not register bpf iterator udp\n"); } #endif void __init udp_init(void) { unsigned long limit; unsigned int i; udp_table_init(&udp_table, "UDP"); limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_udp_mem[0] = limit / 4 * 3; sysctl_udp_mem[1] = limit; sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2; __udp_sysctl_init(&init_net); /* 16 spinlocks per cpu */ udp_busylocks_log = ilog2(nr_cpu_ids) + 4; udp_busylocks = kmalloc(sizeof(spinlock_t) << udp_busylocks_log, GFP_KERNEL); if (!udp_busylocks) panic("UDP: failed to alloc udp_busylocks\n"); for (i = 0; i < (1U << udp_busylocks_log); i++) spin_lock_init(udp_busylocks + i); if (register_pernet_subsys(&udp_sysctl_ops)) panic("UDP: failed to init sysctl parameters.\n"); #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_register(); #endif } |
| 71 79 1226 261 122 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs */ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/dax.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> struct mm_struct; #ifdef CONFIG_NUMA /* * Describe a memory policy. * * A mempolicy can be either associated with a process or with a VMA. * For VMA related allocations the VMA policy is preferred, otherwise * the process policy is used. Interrupts ignore the memory policy * of the current process. * * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when * mpol_put() decrements the reference count to zero. * * Duplicating policy objects: * mpol_dup() allocates a new mempolicy and copies the specified mempolicy * to the new storage. The reference count of the new object is initialized * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/perfer */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; }; /* * Support for managing mempolicy data objects (clone, copy, destroy) * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ extern void __mpol_put(struct mempolicy *pol); static inline void mpol_put(struct mempolicy *pol) { if (pol) __mpol_put(pol); } /* * Does mempolicy pol need explicit unref after use? * Currently only needed for shared policies. */ static inline int mpol_needs_cond_ref(struct mempolicy *pol) { return (pol && (pol->flags & MPOL_F_SHARED)); } static inline void mpol_cond_put(struct mempolicy *pol) { if (mpol_needs_cond_ref(pol)) __mpol_put(pol); } extern struct mempolicy *__mpol_dup(struct mempolicy *pol); static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) pol = __mpol_dup(pol); return pol; } #define vma_policy(vma) ((vma)->vm_policy) static inline void mpol_get(struct mempolicy *pol) { if (pol) atomic_inc(&pol->refcnt); } extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b); static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (a == b) return true; return __mpol_equal(a, b); } /* * Tree of shared policies for a shared memory region. * Maintain the policies in a pseudo mm that contains vmas. The vmas * carry the policy. As a special twist the pseudo mm is indexed in pages, not * bytes, so that we can work with shared memory segments bigger than * unsigned long. */ struct sp_node { struct rb_node nd; unsigned long start, end; struct mempolicy *policy; }; struct shared_policy { struct rb_root root; rwlock_t lock; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *info, struct vm_area_struct *vma, struct mempolicy *new); void mpol_free_shared_policy(struct shared_policy *p); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); static inline nodemask_t *policy_nodemask_current(gfp_t gfp) { struct mempolicy *mpol = get_task_policy(current); return policy_nodemask(gfp, mpol); } extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone && k != ZONE_MOVABLE) policy_zone = k; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS extern int mpol_parse_str(char *str, struct mempolicy **mpol); #endif extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); extern bool numa_demotion_enabled; static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); } #else struct mempolicy {}; static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } static inline void mpol_put(struct mempolicy *p) { } static inline void mpol_cond_put(struct mempolicy *pol) { } static inline void mpol_get(struct mempolicy *pol) { } struct shared_policy {}; static inline void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { } static inline void mpol_free_shared_policy(struct shared_policy *p) { } static inline struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) { return NULL; } #define vma_policy(vma) NULL static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { return 0; } static inline void numa_policy_init(void) { } static inline void numa_default_policy(void) { } static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { } static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return 0; } static inline void check_highest_zone(int k) { } #ifdef CONFIG_TMPFS static inline int mpol_parse_str(char *str, struct mempolicy **mpol) { return 1; /* error */ } #endif static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long address) { return -1; /* no node preference */ } static inline void mpol_put_task_policy(struct task_struct *task) { } static inline nodemask_t *policy_nodemask_current(gfp_t gfp) { return NULL; } #define numa_demotion_enabled false static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; } #endif /* CONFIG_NUMA */ #endif |
| 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to segment and merge handling */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/scatterlist.h> #include <linux/blk-cgroup.h> #include <trace/events/block.h> #include "blk.h" #include "blk-rq-qos.h" static inline bool bio_will_gap(struct request_queue *q, struct request *prev_rq, struct bio *prev, struct bio *next) { struct bio_vec pb, nb; if (!bio_has_data(prev) || !queue_virt_boundary(q)) return false; /* * Don't merge if the 1st bio starts with non-zero offset, otherwise it * is quite difficult to respect the sg gap limit. We work hard to * merge a huge number of small single bios in case of mkfs. */ if (prev_rq) bio_get_first_bvec(prev_rq->bio, &pb); else bio_get_first_bvec(prev, &pb); if (pb.bv_offset & queue_virt_boundary(q)) return true; /* * We don't need to worry about the situation that the merged segment * ends in unaligned virt boundary: * * - if 'pb' ends aligned, the merged segment ends aligned * - if 'pb' ends unaligned, the next bio must include * one single bvec of 'nb', otherwise the 'nb' can't * merge with 'pb' */ bio_get_last_bvec(prev, &pb); bio_get_first_bvec(next, &nb); if (biovec_phys_mergeable(q, &pb, &nb)) return false; return __bvec_gap_to_prev(q, &pb, nb.bv_offset); } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) { return bio_will_gap(req->q, req, req->biotail, bio); } static inline bool req_gap_front_merge(struct request *req, struct bio *bio) { return bio_will_gap(req->q, NULL, bio, req->bio); } static struct bio *blk_bio_discard_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *nsegs) { unsigned int max_discard_sectors, granularity; int alignment; sector_t tmp; unsigned split_sectors; *nsegs = 1; /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); max_discard_sectors = min(q->limits.max_discard_sectors, bio_allowed_max_sectors(q)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) { /* XXX: warn */ return NULL; } if (bio_sectors(bio) <= max_discard_sectors) return NULL; split_sectors = max_discard_sectors; /* * If the next starting sector would be misaligned, stop the discard at * the previous aligned sector. */ alignment = (q->limits.discard_alignment >> 9) % granularity; tmp = bio->bi_iter.bi_sector + split_sectors - alignment; tmp = sector_div(tmp, granularity); if (split_sectors > tmp) split_sectors -= tmp; return bio_split(bio, split_sectors, GFP_NOIO, bs); } static struct bio *blk_bio_write_zeroes_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *nsegs) { *nsegs = 0; if (!q->limits.max_write_zeroes_sectors) return NULL; if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors) return NULL; return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs); } static struct bio *blk_bio_write_same_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *nsegs) { *nsegs = 1; if (!q->limits.max_write_same_sectors) return NULL; if (bio_sectors(bio) <= q->limits.max_write_same_sectors) return NULL; return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs); } /* * Return the maximum number of sectors from the start of a bio that may be * submitted as a single request to a block device. If enough sectors remain, * align the end to the physical block size. Otherwise align the end to the * logical block size. This approach minimizes the number of non-aligned * requests that are submitted to a block device if the start of a bio is not * aligned to a physical block boundary. */ static inline unsigned get_max_io_size(struct request_queue *q, struct bio *bio) { unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0); unsigned max_sectors = sectors; unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT; unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT; unsigned start_offset = bio->bi_iter.bi_sector & (pbs - 1); max_sectors += start_offset; max_sectors &= ~(pbs - 1); if (max_sectors > start_offset) return max_sectors - start_offset; return sectors & ~(lbs - 1); } static inline unsigned get_max_segment_size(const struct request_queue *q, struct page *start_page, unsigned long offset) { unsigned long mask = queue_segment_boundary(q); offset = mask & (page_to_phys(start_page) + offset); /* * overflow may be triggered in case of zero page physical address * on 32bit arch, use queue's max segment size when that happens. */ return min_not_zero(mask - offset + 1, (unsigned long)queue_max_segment_size(q)); } /** * bvec_split_segs - verify whether or not a bvec should be split in the middle * @q: [in] request queue associated with the bio associated with @bv * @bv: [in] bvec to examine * @nsegs: [in,out] Number of segments in the bio being built. Incremented * by the number of segments from @bv that may be appended to that * bio without exceeding @max_segs * @sectors: [in,out] Number of sectors in the bio being built. Incremented * by the number of sectors from @bv that may be appended to that * bio without exceeding @max_sectors * @max_segs: [in] upper bound for *@nsegs * @max_sectors: [in] upper bound for *@sectors * * When splitting a bio, it can happen that a bvec is encountered that is too * big to fit in a single segment and hence that it has to be split in the * middle. This function verifies whether or not that should happen. The value * %true is returned if and only if appending the entire @bv to a bio with * *@nsegs segments and *@sectors sectors would make that bio unacceptable for * the block driver. */ static bool bvec_split_segs(const struct request_queue *q, const struct bio_vec *bv, unsigned *nsegs, unsigned *sectors, unsigned max_segs, unsigned max_sectors) { unsigned max_len = (min(max_sectors, UINT_MAX >> 9) - *sectors) << 9; unsigned len = min(bv->bv_len, max_len); unsigned total_len = 0; unsigned seg_size = 0; while (len && *nsegs < max_segs) { seg_size = get_max_segment_size(q, bv->bv_page, bv->bv_offset + total_len); seg_size = min(seg_size, len); (*nsegs)++; total_len += seg_size; len -= seg_size; if ((bv->bv_offset + total_len) & queue_virt_boundary(q)) break; } *sectors += total_len >> 9; /* tell the caller to split the bvec if it is too big to fit */ return len > 0 || bv->bv_len > max_len; } /** * blk_bio_segment_split - split a bio in two bios * @q: [in] request queue pointer * @bio: [in] bio to be split * @bs: [in] bio set to allocate the clone from * @segs: [out] number of segments in the bio with the first half of the sectors * * Clone @bio, update the bi_iter of the clone to represent the first sectors * of @bio and update @bio->bi_iter to represent the remaining sectors. The * following is guaranteed for the cloned bio: * - That it has at most get_max_io_size(@q, @bio) sectors. * - That it has at most queue_max_segments(@q) segments. * * Except for discard requests the cloned bio will point at the bi_io_vec of * the original bio. It is the responsibility of the caller to ensure that the * original bio is not freed before the cloned bio. The caller is also * responsible for ensuring that @bs is only destroyed after processing of the * split bio has finished. */ static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *segs) { struct bio_vec bv, bvprv, *bvprvp = NULL; struct bvec_iter iter; unsigned nsegs = 0, sectors = 0; const unsigned max_sectors = get_max_io_size(q, bio); const unsigned max_segs = queue_max_segments(q); bio_for_each_bvec(bv, bio, iter) { /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; if (nsegs < max_segs && sectors + (bv.bv_len >> 9) <= max_sectors && bv.bv_offset + bv.bv_len <= PAGE_SIZE) { nsegs++; sectors += bv.bv_len >> 9; } else if (bvec_split_segs(q, &bv, &nsegs, §ors, max_segs, max_sectors)) { goto split; } bvprv = bv; bvprvp = &bvprv; } *segs = nsegs; return NULL; split: /* * We can't sanely support splitting for a REQ_NOWAIT bio. End it * with EAGAIN if splitting is required and return an error pointer. */ if (bio->bi_opf & REQ_NOWAIT) { bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); return ERR_PTR(-EAGAIN); } *segs = nsegs; /* * Bio splitting may cause subtle trouble such as hang when doing sync * iopoll in direct IO routine. Given performance gain of iopoll for * big IO can be trival, disable iopoll when split needed. */ bio_clear_hipri(bio); return bio_split(bio, sectors, GFP_NOIO, bs); } /** * __blk_queue_split - split a bio and submit the second half * @bio: [in, out] bio to be split * @nr_segs: [out] number of segments in the first bio * * Split a bio into two bios, chain the two bios, submit the second half and * store a pointer to the first half in *@bio. If the second bio is still too * big it will be split by a recursive call to this function. Since this * function may allocate a new bio from q->bio_split, it is the responsibility * of the caller to ensure that q->bio_split is only released after processing * of the split bio has finished. */ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs) { struct request_queue *q = (*bio)->bi_bdev->bd_disk->queue; struct bio *split = NULL; switch (bio_op(*bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, &q->bio_split, nr_segs); break; case REQ_OP_WRITE_ZEROES: split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split, nr_segs); break; case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, &q->bio_split, nr_segs); break; default: /* * All drivers must accept single-segments bios that are <= * PAGE_SIZE. This is a quick and dirty check that relies on * the fact that bi_io_vec[0] is always valid if a bio has data. * The check might lead to occasional false negatives when bios * are cloned, but compared to the performance impact of cloned * bios themselves the loop below doesn't matter anyway. */ if (!q->limits.chunk_sectors && (*bio)->bi_vcnt == 1 && ((*bio)->bi_io_vec[0].bv_len + (*bio)->bi_io_vec[0].bv_offset) <= PAGE_SIZE) { *nr_segs = 1; break; } split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs); if (IS_ERR(split)) *bio = split = NULL; break; } if (split) { /* there isn't chance to merge the split bio */ split->bi_opf |= REQ_NOMERGE; bio_chain(split, *bio); trace_block_split(split, (*bio)->bi_iter.bi_sector); submit_bio_noacct(*bio); *bio = split; blk_throtl_charge_bio_split(*bio); } } /** * blk_queue_split - split a bio and submit the second half * @bio: [in, out] bio to be split * * Split a bio into two bios, chains the two bios, submit the second half and * store a pointer to the first half in *@bio. Since this function may allocate * a new bio from q->bio_split, it is the responsibility of the caller to ensure * that q->bio_split is only released after processing of the split bio has * finished. */ void blk_queue_split(struct bio **bio) { unsigned int nr_segs; __blk_queue_split(bio, &nr_segs); } EXPORT_SYMBOL(blk_queue_split); unsigned int blk_recalc_rq_segments(struct request *rq) { unsigned int nr_phys_segs = 0; unsigned int nr_sectors = 0; struct req_iterator iter; struct bio_vec bv; if (!rq->bio) return 0; switch (bio_op(rq->bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: if (queue_max_discard_segments(rq->q) > 1) { struct bio *bio = rq->bio; for_each_bio(bio) nr_phys_segs++; return nr_phys_segs; } return 1; case REQ_OP_WRITE_ZEROES: return 0; case REQ_OP_WRITE_SAME: return 1; } rq_for_each_bvec(bv, rq, iter) bvec_split_segs(rq->q, &bv, &nr_phys_segs, &nr_sectors, UINT_MAX, UINT_MAX); return nr_phys_segs; } static inline struct scatterlist *blk_next_sg(struct scatterlist **sg, struct scatterlist *sglist) { if (!*sg) return sglist; /* * If the driver previously mapped a shorter list, we could see a * termination bit prematurely unless it fully inits the sg table * on each mapping. We KNOW that there must be more entries here * or the driver would be buggy, so force clear the termination bit * to avoid doing a full sg_init_table() in drivers for each command. */ sg_unmark_end(*sg); return sg_next(*sg); } static unsigned blk_bvec_map_sg(struct request_queue *q, struct bio_vec *bvec, struct scatterlist *sglist, struct scatterlist **sg) { unsigned nbytes = bvec->bv_len; unsigned nsegs = 0, total = 0; while (nbytes > 0) { unsigned offset = bvec->bv_offset + total; unsigned len = min(get_max_segment_size(q, bvec->bv_page, offset), nbytes); struct page *page = bvec->bv_page; /* * Unfortunately a fair number of drivers barf on scatterlists * that have an offset larger than PAGE_SIZE, despite other * subsystems dealing with that invariant just fine. For now * stick to the legacy format where we never present those from * the block layer, but the code below should be removed once * these offenders (mostly MMC/SD drivers) are fixed. */ page += (offset >> PAGE_SHIFT); offset &= ~PAGE_MASK; *sg = blk_next_sg(sg, sglist); sg_set_page(*sg, page, len, offset); total += len; nbytes -= len; nsegs++; } return nsegs; } static inline int __blk_bvec_map_sg(struct bio_vec bv, struct scatterlist *sglist, struct scatterlist **sg) { *sg = blk_next_sg(sg, sglist); sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset); return 1; } /* only try to merge bvecs into one sg if they are from two bios */ static inline bool __blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec, struct bio_vec *bvprv, struct scatterlist **sg) { int nbytes = bvec->bv_len; if (!*sg) return false; if ((*sg)->length + nbytes > queue_max_segment_size(q)) return false; if (!biovec_phys_mergeable(q, bvprv, bvec)) return false; (*sg)->length += nbytes; return true; } static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist, struct scatterlist **sg) { struct bio_vec bvec, bvprv = { NULL }; struct bvec_iter iter; int nsegs = 0; bool new_bio = false; for_each_bio(bio) { bio_for_each_bvec(bvec, bio, iter) { /* * Only try to merge bvecs from two bios given we * have done bio internal merge when adding pages * to bio */ if (new_bio && __blk_segment_map_sg_merge(q, &bvec, &bvprv, sg)) goto next_bvec; if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE) nsegs += __blk_bvec_map_sg(bvec, sglist, sg); else nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg); next_bvec: new_bio = false; } if (likely(bio->bi_iter.bi_size)) { bvprv = bvec; new_bio = true; } } return nsegs; } /* * map a request to scatterlist, return number of sg entries setup. Caller * must make sure sg can hold rq->nr_phys_segments entries */ int __blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg) { int nsegs = 0; if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, last_sg); else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME) nsegs = __blk_bvec_map_sg(bio_iovec(rq->bio), sglist, last_sg); else if (rq->bio) nsegs = __blk_bios_map_sg(q, rq->bio, sglist, last_sg); if (*last_sg) sg_mark_end(*last_sg); /* * Something must have been wrong if the figured number of * segment is bigger than number of req's physical segments */ WARN_ON(nsegs > blk_rq_nr_phys_segments(rq)); return nsegs; } EXPORT_SYMBOL(__blk_rq_map_sg); static inline unsigned int blk_rq_get_max_segments(struct request *rq) { if (req_op(rq) == REQ_OP_DISCARD) return queue_max_discard_segments(rq->q); return queue_max_segments(rq->q); } static inline int ll_new_hw_segment(struct request *req, struct bio *bio, unsigned int nr_phys_segs) { if (!blk_cgroup_mergeable(req, bio)) goto no_merge; if (blk_integrity_merge_bio(req->q, req, bio) == false) goto no_merge; /* discard request merge won't add new segment */ if (req_op(req) == REQ_OP_DISCARD) return 1; if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req)) goto no_merge; /* * This will form the start of a new hw segment. Bump both * counters. */ req->nr_phys_segments += nr_phys_segs; return 1; no_merge: req_set_nomerge(req->q, req); return 0; } int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) { if (req_gap_back_merge(req, bio)) return 0; if (blk_integrity_rq(req) && integrity_req_gap_back_merge(req, bio)) return 0; if (!bio_crypt_ctx_back_mergeable(req, bio)) return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) { req_set_nomerge(req->q, req); return 0; } return ll_new_hw_segment(req, bio, nr_segs); } static int ll_front_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) { if (req_gap_front_merge(req, bio)) return 0; if (blk_integrity_rq(req) && integrity_req_gap_front_merge(req, bio)) return 0; if (!bio_crypt_ctx_front_mergeable(req, bio)) return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) { req_set_nomerge(req->q, req); return 0; } return ll_new_hw_segment(req, bio, nr_segs); } static bool req_attempt_discard_merge(struct request_queue *q, struct request *req, struct request *next) { unsigned short segments = blk_rq_nr_discard_segments(req); if (segments >= queue_max_discard_segments(q)) goto no_merge; if (blk_rq_sectors(req) + bio_sectors(next->bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) goto no_merge; req->nr_phys_segments = segments + blk_rq_nr_discard_segments(next); return true; no_merge: req_set_nomerge(q, req); return false; } static int ll_merge_requests_fn(struct request_queue *q, struct request *req, struct request *next) { int total_phys_segments; if (req_gap_back_merge(req, next->bio)) return 0; /* * Will it become too large? */ if ((blk_rq_sectors(req) + blk_rq_sectors(next)) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) return 0; total_phys_segments = req->nr_phys_segments + next->nr_phys_segments; if (total_phys_segments > blk_rq_get_max_segments(req)) return 0; if (!blk_cgroup_mergeable(req, next->bio)) return 0; if (blk_integrity_merge_rq(q, req, next) == false) return 0; if (!bio_crypt_ctx_merge_rq(req, next)) return 0; /* Merge is OK... */ req->nr_phys_segments = total_phys_segments; return 1; } /** * blk_rq_set_mixed_merge - mark a request as mixed merge * @rq: request to mark as mixed merge * * Description: * @rq is about to be mixed merged. Make sure the attributes * which can be mixed are set in each bio and mark @rq as mixed * merged. */ void blk_rq_set_mixed_merge(struct request *rq) { unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; struct bio *bio; if (rq->rq_flags & RQF_MIXED_MERGE) return; /* * @rq will no longer represent mixable attributes for all the * contained bios. It will just track those of the first one. * Distributes the attributs to each bio. */ for (bio = rq->bio; bio; bio = bio->bi_next) { WARN_ON_ONCE((bio->bi_opf & REQ_FAILFAST_MASK) && (bio->bi_opf & REQ_FAILFAST_MASK) != ff); bio->bi_opf |= ff; } rq->rq_flags |= RQF_MIXED_MERGE; } static void blk_account_io_merge_request(struct request *req) { if (blk_do_io_stat(req)) { part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_unlock(); } } static enum elv_merge blk_try_req_merge(struct request *req, struct request *next) { if (blk_discard_mergable(req)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) return ELEVATOR_BACK_MERGE; return ELEVATOR_NO_MERGE; } /* * For non-mq, this has to be called with the request spinlock acquired. * For mq with scheduling, the appropriate queue wide lock should be held. */ static struct request *attempt_merge(struct request_queue *q, struct request *req, struct request *next) { if (!rq_mergeable(req) || !rq_mergeable(next)) return NULL; if (req_op(req) != req_op(next)) return NULL; if (rq_data_dir(req) != rq_data_dir(next) || req->rq_disk != next->rq_disk) return NULL; if (req_op(req) == REQ_OP_WRITE_SAME && !blk_write_same_mergeable(req->bio, next->bio)) return NULL; /* * Don't allow merge of different write hints, or for a hint with * non-hint IO. */ if (req->write_hint != next->write_hint) return NULL; if (req->ioprio != next->ioprio) return NULL; /* * If we are allowed to merge, then append bio list * from next to rq and release next. merge_requests_fn * will have updated segment counts, update sector * counts here. Handle DISCARDs separately, as they * have separate settings. */ switch (blk_try_req_merge(req, next)) { case ELEVATOR_DISCARD_MERGE: if (!req_attempt_discard_merge(q, req, next)) return NULL; break; case ELEVATOR_BACK_MERGE: if (!ll_merge_requests_fn(q, req, next)) return NULL; break; default: return NULL; } /* * If failfast settings disagree or any of the two is already * a mixed merge, mark both as mixed before proceeding. This * makes sure that all involved bios have mixable attributes * set properly. */ if (((req->rq_flags | next->rq_flags) & RQF_MIXED_MERGE) || (req->cmd_flags & REQ_FAILFAST_MASK) != (next->cmd_flags & REQ_FAILFAST_MASK)) { blk_rq_set_mixed_merge(req); blk_rq_set_mixed_merge(next); } /* * At this point we have either done a back merge or front merge. We * need the smaller start_time_ns of the merged requests to be the * current request for accounting purposes. */ if (next->start_time_ns < req->start_time_ns) req->start_time_ns = next->start_time_ns; req->biotail->bi_next = next->bio; req->biotail = next->biotail; req->__data_len += blk_rq_bytes(next); if (!blk_discard_mergable(req)) elv_merge_requests(q, req, next); blk_crypto_rq_put_keyslot(next); /* * 'next' is going away, so update stats accordingly */ blk_account_io_merge_request(next); trace_block_rq_merge(next); /* * ownership of bio passed from next to req, return 'next' for * the caller to free */ next->bio = NULL; return next; } static struct request *attempt_back_merge(struct request_queue *q, struct request *rq) { struct request *next = elv_latter_request(q, rq); if (next) return attempt_merge(q, rq, next); return NULL; } static struct request *attempt_front_merge(struct request_queue *q, struct request *rq) { struct request *prev = elv_former_request(q, rq); if (prev) return attempt_merge(q, prev, rq); return NULL; } /* * Try to merge 'next' into 'rq'. Return true if the merge happened, false * otherwise. The caller is responsible for freeing 'next' if the merge * happened. */ bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next) { return attempt_merge(q, rq, next); } bool blk_rq_merge_ok(struct request *rq, struct bio *bio) { if (!rq_mergeable(rq) || !bio_mergeable(bio)) return false; if (req_op(rq) != bio_op(bio)) return false; /* different data direction or already started, don't merge */ if (bio_data_dir(bio) != rq_data_dir(rq)) return false; /* must be same device */ if (rq->rq_disk != bio->bi_bdev->bd_disk) return false; /* don't merge across cgroup boundaries */ if (!blk_cgroup_mergeable(rq, bio)) return false; /* only merge integrity protected bio into ditto rq */ if (blk_integrity_merge_bio(rq->q, rq, bio) == false) return false; /* Only merge if the crypt contexts are compatible */ if (!bio_crypt_rq_ctx_compatible(rq, bio)) return false; /* must be using the same buffer */ if (req_op(rq) == REQ_OP_WRITE_SAME && !blk_write_same_mergeable(rq->bio, bio)) return false; /* * Don't allow merge of different write hints, or for a hint with * non-hint IO. */ if (rq->write_hint != bio->bi_write_hint) return false; if (rq->ioprio != bio_prio(bio)) return false; return true; } enum elv_merge blk_try_merge(struct request *rq, struct bio *bio) { if (blk_discard_mergable(rq)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) return ELEVATOR_BACK_MERGE; else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector) return ELEVATOR_FRONT_MERGE; return ELEVATOR_NO_MERGE; } static void blk_account_io_merge_bio(struct request *req) { if (!blk_do_io_stat(req)) return; part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_unlock(); } enum bio_merge_status { BIO_MERGE_OK, BIO_MERGE_NONE, BIO_MERGE_FAILED, }; static enum bio_merge_status bio_attempt_back_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { const int ff = bio->bi_opf & REQ_FAILFAST_MASK; if (!ll_back_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; trace_block_bio_backmerge(bio); rq_qos_merge(req->q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); req->biotail->bi_next = bio; req->biotail = bio; req->__data_len += bio->bi_iter.bi_size; bio_crypt_free_ctx(bio); blk_account_io_merge_bio(req); return BIO_MERGE_OK; } static enum bio_merge_status bio_attempt_front_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { const int ff = bio->bi_opf & REQ_FAILFAST_MASK; if (!ll_front_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; trace_block_bio_frontmerge(bio); rq_qos_merge(req->q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); bio->bi_next = req->bio; req->bio = bio; req->__sector = bio->bi_iter.bi_sector; req->__data_len += bio->bi_iter.bi_size; bio_crypt_do_front_merge(req, bio); blk_account_io_merge_bio(req); return BIO_MERGE_OK; } static enum bio_merge_status bio_attempt_discard_merge(struct request_queue *q, struct request *req, struct bio *bio) { unsigned short segments = blk_rq_nr_discard_segments(req); if (segments >= queue_max_discard_segments(q)) goto no_merge; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) goto no_merge; rq_qos_merge(q, req, bio); req->biotail->bi_next = bio; req->biotail = bio; req->__data_len += bio->bi_iter.bi_size; req->nr_phys_segments = segments + 1; blk_account_io_merge_bio(req); return BIO_MERGE_OK; no_merge: req_set_nomerge(q, req); return BIO_MERGE_FAILED; } static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q, struct request *rq, struct bio *bio, unsigned int nr_segs, bool sched_allow_merge) { if (!blk_rq_merge_ok(rq, bio)) return BIO_MERGE_NONE; switch (blk_try_merge(rq, bio)) { case ELEVATOR_BACK_MERGE: if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio)) return bio_attempt_back_merge(rq, bio, nr_segs); break; case ELEVATOR_FRONT_MERGE: if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio)) return bio_attempt_front_merge(rq, bio, nr_segs); break; case ELEVATOR_DISCARD_MERGE: return bio_attempt_discard_merge(q, rq, bio); default: return BIO_MERGE_NONE; } return BIO_MERGE_FAILED; } /** * blk_attempt_plug_merge - try to merge with %current's plugged list * @q: request_queue new bio is being queued at * @bio: new bio being queued * @nr_segs: number of segments in @bio * @same_queue_rq: pointer to &struct request that gets filled in when * another request associated with @q is found on the plug list * (optional, may be %NULL) * * Determine whether @bio being queued on @q can be merged with a request * on %current's plugged list. Returns %true if merge was successful, * otherwise %false. * * Plugging coalesces IOs from the same issuer for the same purpose without * going through @q->queue_lock. As such it's more of an issuing mechanism * than scheduling, and the request, while may have elvpriv data, is not * added on the elevator at this point. In addition, we don't have * reliable access to the elevator outside queue lock. Only check basic * merging parameters without querying the elevator. * * Caller must ensure !blk_queue_nomerges(q) beforehand. */ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **same_queue_rq) { struct blk_plug *plug; struct request *rq; struct list_head *plug_list; plug = blk_mq_plug(q, bio); if (!plug) return false; plug_list = &plug->mq_list; list_for_each_entry_reverse(rq, plug_list, queuelist) { if (rq->q == q && same_queue_rq) { /* * Only blk-mq multiple hardware queues case checks the * rq in the same queue, there should be only one such * rq in a queue **/ *same_queue_rq = rq; } if (rq->q != q) continue; if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == BIO_MERGE_OK) return true; } return false; } /* * Iterate list of requests and see if we can merge this bio with any * of them. */ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs) { struct request *rq; int checked = 8; list_for_each_entry_reverse(rq, list, queuelist) { if (!checked--) break; switch (blk_attempt_bio_merge(q, rq, bio, nr_segs, true)) { case BIO_MERGE_NONE: continue; case BIO_MERGE_OK: return true; case BIO_MERGE_FAILED: return false; } } return false; } EXPORT_SYMBOL_GPL(blk_bio_list_merge); bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **merged_request) { struct request *rq; switch (elv_merge(q, &rq, bio)) { case ELEVATOR_BACK_MERGE: if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; if (bio_attempt_back_merge(rq, bio, nr_segs) != BIO_MERGE_OK) return false; *merged_request = attempt_back_merge(q, rq); if (!*merged_request) elv_merged_request(q, rq, ELEVATOR_BACK_MERGE); return true; case ELEVATOR_FRONT_MERGE: if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; if (bio_attempt_front_merge(rq, bio, nr_segs) != BIO_MERGE_OK) return false; *merged_request = attempt_front_merge(q, rq); if (!*merged_request) elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE); return true; case ELEVATOR_DISCARD_MERGE: return bio_attempt_discard_merge(q, rq, bio) == BIO_MERGE_OK; default: return false; } } EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge); |
| 105 104 105 174 174 174 7 7 7 7 7 11 11 11 11 11 24 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/module.h> #include <linux/errno.h> #include <linux/socket.h> #include <linux/udp.h> #include <linux/types.h> #include <linux/kernel.h> #include <net/dst_metadata.h> #include <net/net_namespace.h> #include <net/udp.h> #include <net/udp_tunnel.h> int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { int err; struct socket *sock = NULL; struct sockaddr_in udp_addr; err = sock_create_kern(net, AF_INET, SOCK_DGRAM, 0, &sock); if (err < 0) goto error; if (cfg->bind_ifindex) { err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true); if (err < 0) goto error; } udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->local_ip; udp_addr.sin_port = cfg->local_udp_port; err = kernel_bind(sock, (struct sockaddr *)&udp_addr, sizeof(udp_addr)); if (err < 0) goto error; if (cfg->peer_udp_port) { udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->peer_ip; udp_addr.sin_port = cfg->peer_udp_port; err = kernel_connect(sock, (struct sockaddr *)&udp_addr, sizeof(udp_addr), 0); if (err < 0) goto error; } sock->sk->sk_no_check_tx = !cfg->use_udp_checksums; *sockp = sock; return 0; error: if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } *sockp = NULL; return err; } EXPORT_SYMBOL(udp_sock_create4); void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *cfg) { struct sock *sk = sock->sk; /* Disable multicast loopback */ inet_sk(sk)->mc_loop = 0; /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */ inet_inc_convert_csum(sk); rcu_assign_sk_user_data(sk, cfg->sk_user_data); udp_sk(sk)->encap_type = cfg->encap_type; udp_sk(sk)->encap_rcv = cfg->encap_rcv; udp_sk(sk)->encap_err_rcv = cfg->encap_err_rcv; udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup; udp_sk(sk)->encap_destroy = cfg->encap_destroy; udp_sk(sk)->gro_receive = cfg->gro_receive; udp_sk(sk)->gro_complete = cfg->gro_complete; udp_tunnel_encap_enable(sock); } EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock); void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct udp_tunnel_info ti; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; udp_tunnel_nic_add_port(dev, &ti); } EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port); void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct udp_tunnel_info ti; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; udp_tunnel_nic_del_port(dev, &ti); } EXPORT_SYMBOL_GPL(udp_tunnel_drop_rx_port); /* Notify netdevs that UDP port started listening */ void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct udp_tunnel_info ti; struct net_device *dev; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; rcu_read_lock(); for_each_netdev_rcu(net, dev) { udp_tunnel_nic_add_port(dev, &ti); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port); /* Notify netdevs that UDP port is no more listening */ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct udp_tunnel_info ti; struct net_device *dev; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; rcu_read_lock(); for_each_netdev_rcu(net, dev) { udp_tunnel_nic_del_port(dev, &ti); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port); void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck) { struct udphdr *uh; __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = dst_port; uh->source = src_port; uh->len = htons(skb->len); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); udp_set_csum(nocheck, skb, src, dst, skb->len); iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); } EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); void udp_tunnel_sock_release(struct socket *sock) { rcu_assign_sk_user_data(sock->sk, NULL); synchronize_rcu(); kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } EXPORT_SYMBOL_GPL(udp_tunnel_sock_release); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, __be16 flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; if (family == AF_INET) tun_dst = ip_tun_rx_dst(skb, flags, tunnel_id, md_size); else tun_dst = ipv6_tun_rx_dst(skb, flags, tunnel_id, md_size); if (!tun_dst) return NULL; info = &tun_dst->u.tun_info; info->key.tp_src = udp_hdr(skb)->source; info->key.tp_dst = udp_hdr(skb)->dest; if (udp_hdr(skb)->check) info->key.tun_flags |= TUNNEL_CSUM; return tun_dst; } EXPORT_SYMBOL_GPL(udp_tun_rx_dst); MODULE_LICENSE("GPL"); |
| 178 25 177 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _TRACE_SYSCALL_H #define _TRACE_SYSCALL_H #include <linux/tracepoint.h> #include <linux/unistd.h> #include <linux/trace_events.h> #include <linux/thread_info.h> #include <asm/ptrace.h> /* * A syscall entry in the ftrace syscalls array. * * @name: name of the syscall * @syscall_nr: number of the syscall * @nb_args: number of parameters it takes * @types: list of types as strings * @args: list of args as strings (args[i] matches types[i]) * @enter_fields: list of fields for syscall_enter trace event * @enter_event: associated syscall_enter trace event * @exit_event: associated syscall_exit trace event */ struct syscall_metadata { const char *name; int syscall_nr; int nb_args; const char **types; const char **args; struct list_head enter_fields; struct trace_event_call *enter_event; struct trace_event_call *exit_event; }; #if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS) static inline void syscall_tracepoint_update(struct task_struct *p) { if (test_syscall_work(SYSCALL_TRACEPOINT)) set_task_syscall_work(p, SYSCALL_TRACEPOINT); else clear_task_syscall_work(p, SYSCALL_TRACEPOINT); } #else static inline void syscall_tracepoint_update(struct task_struct *p) { } #endif #endif /* _TRACE_SYSCALL_H */ |
| 164 167 35 35 35 35 35 35 35 35 35 2 35 35 2 1 2 2 2 2 2 2 2 2 2 2 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/dd.c - The core device/driver interactions. * * This file contains the (sometimes tricky) code that controls the * interactions between devices and drivers, which primarily includes * driver binding and unbinding. * * All of this code used to exist in drivers/base/bus.c, but was * relocated to here in the name of compartmentalization (since it wasn't * strictly code just for the 'struct bus_type'. * * Copyright (c) 2002-5 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2007-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2007-2009 Novell Inc. */ #include <linux/debugfs.h> #include <linux/device.h> #include <linux/delay.h> #include <linux/dma-map-ops.h> #include <linux/init.h> #include <linux/module.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/async.h> #include <linux/pm_runtime.h> #include <linux/pinctrl/devinfo.h> #include <linux/slab.h> #include "base.h" #include "power/power.h" /* * Deferred Probe infrastructure. * * Sometimes driver probe order matters, but the kernel doesn't always have * dependency information which means some drivers will get probed before a * resource it depends on is available. For example, an SDHCI driver may * first need a GPIO line from an i2c GPIO controller before it can be * initialized. If a required resource is not available yet, a driver can * request probing to be deferred by returning -EPROBE_DEFER from its probe hook * * Deferred probe maintains two lists of devices, a pending list and an active * list. A driver returning -EPROBE_DEFER causes the device to be added to the * pending list. A successful driver probe will trigger moving all devices * from the pending to the active list so that the workqueue will eventually * retry them. * * The deferred_probe_mutex must be held any time the deferred_probe_*_list * of the (struct device*)->p->deferred_probe pointers are manipulated */ static DEFINE_MUTEX(deferred_probe_mutex); static LIST_HEAD(deferred_probe_pending_list); static LIST_HEAD(deferred_probe_active_list); static atomic_t deferred_trigger_count = ATOMIC_INIT(0); static bool initcalls_done; /* Save the async probe drivers' name from kernel cmdline */ #define ASYNC_DRV_NAMES_MAX_LEN 256 static char async_probe_drv_names[ASYNC_DRV_NAMES_MAX_LEN]; /* * In some cases, like suspend to RAM or hibernation, It might be reasonable * to prohibit probing of devices as it could be unsafe. * Once defer_all_probes is true all drivers probes will be forcibly deferred. */ static bool defer_all_probes; static void __device_set_deferred_probe_reason(const struct device *dev, char *reason) { kfree(dev->p->deferred_probe_reason); dev->p->deferred_probe_reason = reason; } /* * deferred_probe_work_func() - Retry probing devices in the active list. */ static void deferred_probe_work_func(struct work_struct *work) { struct device *dev; struct device_private *private; /* * This block processes every device in the deferred 'active' list. * Each device is removed from the active list and passed to * bus_probe_device() to re-attempt the probe. The loop continues * until every device in the active list is removed and retried. * * Note: Once the device is removed from the list and the mutex is * released, it is possible for the device get freed by another thread * and cause a illegal pointer dereference. This code uses * get/put_device() to ensure the device structure cannot disappear * from under our feet. */ mutex_lock(&deferred_probe_mutex); while (!list_empty(&deferred_probe_active_list)) { private = list_first_entry(&deferred_probe_active_list, typeof(*dev->p), deferred_probe); dev = private->device; list_del_init(&private->deferred_probe); get_device(dev); __device_set_deferred_probe_reason(dev, NULL); /* * Drop the mutex while probing each device; the probe path may * manipulate the deferred list */ mutex_unlock(&deferred_probe_mutex); /* * Force the device to the end of the dpm_list since * the PM code assumes that the order we add things to * the list is a good order for suspend but deferred * probe makes that very unsafe. */ device_pm_move_to_tail(dev); dev_dbg(dev, "Retrying from deferred list\n"); bus_probe_device(dev); mutex_lock(&deferred_probe_mutex); put_device(dev); } mutex_unlock(&deferred_probe_mutex); } static DECLARE_WORK(deferred_probe_work, deferred_probe_work_func); void driver_deferred_probe_add(struct device *dev) { if (!dev->can_match) return; mutex_lock(&deferred_probe_mutex); if (list_empty(&dev->p->deferred_probe)) { dev_dbg(dev, "Added to deferred list\n"); list_add_tail(&dev->p->deferred_probe, &deferred_probe_pending_list); } mutex_unlock(&deferred_probe_mutex); } void driver_deferred_probe_del(struct device *dev) { mutex_lock(&deferred_probe_mutex); if (!list_empty(&dev->p->deferred_probe)) { dev_dbg(dev, "Removed from deferred list\n"); list_del_init(&dev->p->deferred_probe); __device_set_deferred_probe_reason(dev, NULL); } mutex_unlock(&deferred_probe_mutex); } static bool driver_deferred_probe_enable = false; /** * driver_deferred_probe_trigger() - Kick off re-probing deferred devices * * This functions moves all devices from the pending list to the active * list and schedules the deferred probe workqueue to process them. It * should be called anytime a driver is successfully bound to a device. * * Note, there is a race condition in multi-threaded probe. In the case where * more than one device is probing at the same time, it is possible for one * probe to complete successfully while another is about to defer. If the second * depends on the first, then it will get put on the pending list after the * trigger event has already occurred and will be stuck there. * * The atomic 'deferred_trigger_count' is used to determine if a successful * trigger has occurred in the midst of probing a driver. If the trigger count * changes in the midst of a probe, then deferred processing should be triggered * again. */ static void driver_deferred_probe_trigger(void) { if (!driver_deferred_probe_enable) return; /* * A successful probe means that all the devices in the pending list * should be triggered to be reprobed. Move all the deferred devices * into the active list so they can be retried by the workqueue */ mutex_lock(&deferred_probe_mutex); atomic_inc(&deferred_trigger_count); list_splice_tail_init(&deferred_probe_pending_list, &deferred_probe_active_list); mutex_unlock(&deferred_probe_mutex); /* * Kick the re-probe thread. It may already be scheduled, but it is * safe to kick it again. */ queue_work(system_unbound_wq, &deferred_probe_work); } /** * device_block_probing() - Block/defer device's probes * * It will disable probing of devices and defer their probes instead. */ void device_block_probing(void) { defer_all_probes = true; /* sync with probes to avoid races. */ wait_for_device_probe(); } /** * device_unblock_probing() - Unblock/enable device's probes * * It will restore normal behavior and trigger re-probing of deferred * devices. */ void device_unblock_probing(void) { defer_all_probes = false; driver_deferred_probe_trigger(); } /** * device_set_deferred_probe_reason() - Set defer probe reason message for device * @dev: the pointer to the struct device * @vaf: the pointer to va_format structure with message */ void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf) { const char *drv = dev_driver_string(dev); char *reason; mutex_lock(&deferred_probe_mutex); reason = kasprintf(GFP_KERNEL, "%s: %pV", drv, vaf); __device_set_deferred_probe_reason(dev, reason); mutex_unlock(&deferred_probe_mutex); } /* * deferred_devs_show() - Show the devices in the deferred probe pending list. */ static int deferred_devs_show(struct seq_file *s, void *data) { struct device_private *curr; mutex_lock(&deferred_probe_mutex); list_for_each_entry(curr, &deferred_probe_pending_list, deferred_probe) seq_printf(s, "%s\t%s", dev_name(curr->device), curr->device->p->deferred_probe_reason ?: "\n"); mutex_unlock(&deferred_probe_mutex); return 0; } DEFINE_SHOW_ATTRIBUTE(deferred_devs); int driver_deferred_probe_timeout; EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout); static int __init deferred_probe_timeout_setup(char *str) { int timeout; if (!kstrtoint(str, 10, &timeout)) driver_deferred_probe_timeout = timeout; return 1; } __setup("deferred_probe_timeout=", deferred_probe_timeout_setup); /** * driver_deferred_probe_check_state() - Check deferred probe state * @dev: device to check * * Return: * -ENODEV if initcalls have completed and modules are disabled. * -ETIMEDOUT if the deferred probe timeout was set and has expired * and modules are enabled. * -EPROBE_DEFER in other cases. * * Drivers or subsystems can opt-in to calling this function instead of directly * returning -EPROBE_DEFER. */ int driver_deferred_probe_check_state(struct device *dev) { if (!IS_ENABLED(CONFIG_MODULES) && initcalls_done) { dev_warn(dev, "ignoring dependency for device, assuming no driver\n"); return -ENODEV; } if (!driver_deferred_probe_timeout && initcalls_done) { dev_warn(dev, "deferred probe timeout, ignoring dependency\n"); return -ETIMEDOUT; } return -EPROBE_DEFER; } EXPORT_SYMBOL_GPL(driver_deferred_probe_check_state); static void deferred_probe_timeout_work_func(struct work_struct *work) { struct device_private *p; fw_devlink_drivers_done(); driver_deferred_probe_timeout = 0; driver_deferred_probe_trigger(); flush_work(&deferred_probe_work); mutex_lock(&deferred_probe_mutex); list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe) dev_info(p->device, "deferred probe pending\n"); mutex_unlock(&deferred_probe_mutex); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); /** * deferred_probe_initcall() - Enable probing of deferred devices * * We don't want to get in the way when the bulk of drivers are getting probed. * Instead, this initcall makes sure that deferred probing is delayed until * late_initcall time. */ static int deferred_probe_initcall(void) { debugfs_create_file("devices_deferred", 0444, NULL, NULL, &deferred_devs_fops); driver_deferred_probe_enable = true; driver_deferred_probe_trigger(); /* Sort as many dependencies as possible before exiting initcalls */ flush_work(&deferred_probe_work); initcalls_done = true; if (!IS_ENABLED(CONFIG_MODULES)) fw_devlink_drivers_done(); /* * Trigger deferred probe again, this time we won't defer anything * that is optional */ driver_deferred_probe_trigger(); flush_work(&deferred_probe_work); if (driver_deferred_probe_timeout > 0) { schedule_delayed_work(&deferred_probe_timeout_work, driver_deferred_probe_timeout * HZ); } return 0; } late_initcall(deferred_probe_initcall); static void __exit deferred_probe_exit(void) { debugfs_lookup_and_remove("devices_deferred", NULL); } __exitcall(deferred_probe_exit); /** * device_is_bound() - Check if device is bound to a driver * @dev: device to check * * Returns true if passed device has already finished probing successfully * against a driver. * * This function must be called with the device lock held. */ bool device_is_bound(struct device *dev) { return dev->p && klist_node_attached(&dev->p->knode_driver); } static void driver_bound(struct device *dev) { if (device_is_bound(dev)) { pr_warn("%s: device %s already bound\n", __func__, kobject_name(&dev->kobj)); return; } pr_debug("driver: '%s': %s: bound to device '%s'\n", dev->driver->name, __func__, dev_name(dev)); klist_add_tail(&dev->p->knode_driver, &dev->driver->p->klist_devices); device_links_driver_bound(dev); device_pm_check_callbacks(dev); /* * Make sure the device is no longer in one of the deferred lists and * kick off retrying all pending devices */ driver_deferred_probe_del(dev); driver_deferred_probe_trigger(); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_BOUND_DRIVER, dev); kobject_uevent(&dev->kobj, KOBJ_BIND); } static ssize_t coredump_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { device_lock(dev); dev->driver->coredump(dev); device_unlock(dev); return count; } static DEVICE_ATTR_WO(coredump); static int driver_sysfs_add(struct device *dev) { int ret; if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_BIND_DRIVER, dev); ret = sysfs_create_link(&dev->driver->p->kobj, &dev->kobj, kobject_name(&dev->kobj)); if (ret) goto fail; ret = sysfs_create_link(&dev->kobj, &dev->driver->p->kobj, "driver"); if (ret) goto rm_dev; if (!IS_ENABLED(CONFIG_DEV_COREDUMP) || !dev->driver->coredump) return 0; ret = device_create_file(dev, &dev_attr_coredump); if (!ret) return 0; sysfs_remove_link(&dev->kobj, "driver"); rm_dev: sysfs_remove_link(&dev->driver->p->kobj, kobject_name(&dev->kobj)); fail: return ret; } static void driver_sysfs_remove(struct device *dev) { struct device_driver *drv = dev->driver; if (drv) { if (drv->coredump) device_remove_file(dev, &dev_attr_coredump); sysfs_remove_link(&drv->p->kobj, kobject_name(&dev->kobj)); sysfs_remove_link(&dev->kobj, "driver"); } } /** * device_bind_driver - bind a driver to one device. * @dev: device. * * Allow manual attachment of a driver to a device. * Caller must have already set @dev->driver. * * Note that this does not modify the bus reference count. * Please verify that is accounted for before calling this. * (It is ok to call with no other effort from a driver's probe() method.) * * This function must be called with the device lock held. * * Callers should prefer to use device_driver_attach() instead. */ int device_bind_driver(struct device *dev) { int ret; ret = driver_sysfs_add(dev); if (!ret) { device_links_force_bind(dev); driver_bound(dev); } else if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DRIVER_NOT_BOUND, dev); return ret; } EXPORT_SYMBOL_GPL(device_bind_driver); static atomic_t probe_count = ATOMIC_INIT(0); static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue); static ssize_t state_synced_show(struct device *dev, struct device_attribute *attr, char *buf) { bool val; device_lock(dev); val = dev->state_synced; device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } static DEVICE_ATTR_RO(state_synced); static int call_driver_probe(struct device *dev, struct device_driver *drv) { int ret = 0; if (dev->bus->probe) ret = dev->bus->probe(dev); else if (drv->probe) ret = drv->probe(dev); switch (ret) { case 0: break; case -EPROBE_DEFER: /* Driver requested deferred probing */ dev_dbg(dev, "Driver %s requests probe deferral\n", drv->name); break; case -ENODEV: case -ENXIO: pr_debug("%s: probe of %s rejects match %d\n", drv->name, dev_name(dev), ret); break; default: /* driver matched but the probe failed */ pr_warn("%s: probe of %s failed with error %d\n", drv->name, dev_name(dev), ret); break; } return ret; } static int really_probe(struct device *dev, struct device_driver *drv) { bool test_remove = IS_ENABLED(CONFIG_DEBUG_TEST_DRIVER_REMOVE) && !drv->suppress_bind_attrs; int ret; if (defer_all_probes) { /* * Value of defer_all_probes can be set only by * device_block_probing() which, in turn, will call * wait_for_device_probe() right after that to avoid any races. */ dev_dbg(dev, "Driver %s force probe deferral\n", drv->name); return -EPROBE_DEFER; } ret = device_links_check_suppliers(dev); if (ret) return ret; pr_debug("bus: '%s': %s: probing driver %s with device %s\n", drv->bus->name, __func__, drv->name, dev_name(dev)); if (!list_empty(&dev->devres_head)) { dev_crit(dev, "Resources present before probing\n"); ret = -EBUSY; goto done; } re_probe: dev->driver = drv; /* If using pinctrl, bind pins now before probing */ ret = pinctrl_bind_pins(dev); if (ret) goto pinctrl_bind_failed; if (dev->bus->dma_configure) { ret = dev->bus->dma_configure(dev); if (ret) goto probe_failed; } ret = driver_sysfs_add(dev); if (ret) { pr_err("%s: driver_sysfs_add(%s) failed\n", __func__, dev_name(dev)); goto probe_failed; } if (dev->pm_domain && dev->pm_domain->activate) { ret = dev->pm_domain->activate(dev); if (ret) goto probe_failed; } ret = call_driver_probe(dev, drv); if (ret) { /* * Return probe errors as positive values so that the callers * can distinguish them from other errors. */ ret = -ret; goto probe_failed; } ret = device_add_groups(dev, drv->dev_groups); if (ret) { dev_err(dev, "device_add_groups() failed\n"); goto dev_groups_failed; } if (dev_has_sync_state(dev)) { ret = device_create_file(dev, &dev_attr_state_synced); if (ret) { dev_err(dev, "state_synced sysfs add failed\n"); goto dev_sysfs_state_synced_failed; } } if (test_remove) { test_remove = false; device_remove_file(dev, &dev_attr_state_synced); device_remove_groups(dev, drv->dev_groups); if (dev->bus->remove) dev->bus->remove(dev); else if (drv->remove) drv->remove(dev); devres_release_all(dev); arch_teardown_dma_ops(dev); kfree(dev->dma_range_map); dev->dma_range_map = NULL; driver_sysfs_remove(dev); dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) dev->pm_domain->dismiss(dev); pm_runtime_reinit(dev); goto re_probe; } pinctrl_init_done(dev); if (dev->pm_domain && dev->pm_domain->sync) dev->pm_domain->sync(dev); driver_bound(dev); pr_debug("bus: '%s': %s: bound device %s to driver %s\n", drv->bus->name, __func__, dev_name(dev), drv->name); goto done; dev_sysfs_state_synced_failed: device_remove_groups(dev, drv->dev_groups); dev_groups_failed: if (dev->bus->remove) dev->bus->remove(dev); else if (drv->remove) drv->remove(dev); probe_failed: if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DRIVER_NOT_BOUND, dev); pinctrl_bind_failed: device_links_no_driver(dev); devres_release_all(dev); arch_teardown_dma_ops(dev); kfree(dev->dma_range_map); dev->dma_range_map = NULL; driver_sysfs_remove(dev); dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) dev->pm_domain->dismiss(dev); pm_runtime_reinit(dev); dev_pm_set_driver_flags(dev, 0); done: return ret; } /* * For initcall_debug, show the driver probe time. */ static int really_probe_debug(struct device *dev, struct device_driver *drv) { ktime_t calltime, rettime; int ret; calltime = ktime_get(); ret = really_probe(dev, drv); rettime = ktime_get(); /* * Don't change this to pr_debug() because that requires * CONFIG_DYNAMIC_DEBUG and we want a simple 'initcall_debug' on the * kernel commandline to print this all the time at the debug level. */ printk(KERN_DEBUG "probe of %s returned %d after %lld usecs\n", dev_name(dev), ret, ktime_us_delta(rettime, calltime)); return ret; } /** * driver_probe_done * Determine if the probe sequence is finished or not. * * Should somehow figure out how to use a semaphore, not an atomic variable... */ int driver_probe_done(void) { int local_probe_count = atomic_read(&probe_count); pr_debug("%s: probe_count = %d\n", __func__, local_probe_count); if (local_probe_count) return -EBUSY; return 0; } /** * wait_for_device_probe * Wait for device probing to be completed. */ void wait_for_device_probe(void) { /* wait for the deferred probe workqueue to finish */ flush_work(&deferred_probe_work); /* wait for the known devices to complete their probing */ wait_event(probe_waitqueue, atomic_read(&probe_count) == 0); async_synchronize_full(); } EXPORT_SYMBOL_GPL(wait_for_device_probe); static int __driver_probe_device(struct device_driver *drv, struct device *dev) { int ret = 0; if (dev->p->dead || !device_is_registered(dev)) return -ENODEV; if (dev->driver) return -EBUSY; dev->can_match = true; pr_debug("bus: '%s': %s: matched device %s with driver %s\n", drv->bus->name, __func__, dev_name(dev), drv->name); pm_runtime_get_suppliers(dev); if (dev->parent) pm_runtime_get_sync(dev->parent); pm_runtime_barrier(dev); if (initcall_debug) ret = really_probe_debug(dev, drv); else ret = really_probe(dev, drv); pm_request_idle(dev); if (dev->parent) pm_runtime_put(dev->parent); pm_runtime_put_suppliers(dev); return ret; } /** * driver_probe_device - attempt to bind device & driver together * @drv: driver to bind a device to * @dev: device to try to bind to the driver * * This function returns -ENODEV if the device is not registered, -EBUSY if it * already has a driver, 0 if the device is bound successfully and a positive * (inverted) error code for failures from the ->probe method. * * This function must be called with @dev lock held. When called for a * USB interface, @dev->parent lock must be held as well. * * If the device has a parent, runtime-resume the parent before driver probing. */ static int driver_probe_device(struct device_driver *drv, struct device *dev) { int trigger_count = atomic_read(&deferred_trigger_count); int ret; atomic_inc(&probe_count); ret = __driver_probe_device(drv, dev); if (ret == -EPROBE_DEFER || ret == EPROBE_DEFER) { driver_deferred_probe_add(dev); /* * Did a trigger occur while probing? Need to re-trigger if yes */ if (trigger_count != atomic_read(&deferred_trigger_count) && !defer_all_probes) driver_deferred_probe_trigger(); } atomic_dec(&probe_count); wake_up_all(&probe_waitqueue); return ret; } static inline bool cmdline_requested_async_probing(const char *drv_name) { return parse_option_str(async_probe_drv_names, drv_name); } /* The option format is "driver_async_probe=drv_name1,drv_name2,..." */ static int __init save_async_options(char *buf) { if (strlen(buf) >= ASYNC_DRV_NAMES_MAX_LEN) pr_warn("Too long list of driver names for 'driver_async_probe'!\n"); strlcpy(async_probe_drv_names, buf, ASYNC_DRV_NAMES_MAX_LEN); return 1; } __setup("driver_async_probe=", save_async_options); bool driver_allows_async_probing(struct device_driver *drv) { switch (drv->probe_type) { case PROBE_PREFER_ASYNCHRONOUS: return true; case PROBE_FORCE_SYNCHRONOUS: return false; default: if (cmdline_requested_async_probing(drv->name)) return true; if (module_requested_async_probing(drv->owner)) return true; return false; } } struct device_attach_data { struct device *dev; /* * Indicates whether we are are considering asynchronous probing or * not. Only initial binding after device or driver registration * (including deferral processing) may be done asynchronously, the * rest is always synchronous, as we expect it is being done by * request from userspace. */ bool check_async; /* * Indicates if we are binding synchronous or asynchronous drivers. * When asynchronous probing is enabled we'll execute 2 passes * over drivers: first pass doing synchronous probing and second * doing asynchronous probing (if synchronous did not succeed - * most likely because there was no driver requiring synchronous * probing - and we found asynchronous driver during first pass). * The 2 passes are done because we can't shoot asynchronous * probe for given device and driver from bus_for_each_drv() since * driver pointer is not guaranteed to stay valid once * bus_for_each_drv() iterates to the next driver on the bus. */ bool want_async; /* * We'll set have_async to 'true' if, while scanning for matching * driver, we'll encounter one that requests asynchronous probing. */ bool have_async; }; static int __device_attach_driver(struct device_driver *drv, void *_data) { struct device_attach_data *data = _data; struct device *dev = data->dev; bool async_allowed; int ret; ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ return 0; } else if (ret == -EPROBE_DEFER) { dev_dbg(dev, "Device match requests probe deferral\n"); dev->can_match = true; driver_deferred_probe_add(dev); /* * Device can't match with a driver right now, so don't attempt * to match or bind with other drivers on the bus. */ return ret; } else if (ret < 0) { dev_dbg(dev, "Bus failed to match device: %d\n", ret); return ret; } /* ret > 0 means positive match */ async_allowed = driver_allows_async_probing(drv); if (async_allowed) data->have_async = true; if (data->check_async && async_allowed != data->want_async) return 0; /* * Ignore errors returned by ->probe so that the next driver can try * its luck. */ ret = driver_probe_device(drv, dev); if (ret < 0) return ret; return ret == 0; } static void __device_attach_async_helper(void *_dev, async_cookie_t cookie) { struct device *dev = _dev; struct device_attach_data data = { .dev = dev, .check_async = true, .want_async = true, }; device_lock(dev); /* * Check if device has already been removed or claimed. This may * happen with driver loading, device discovery/registration, * and deferred probe processing happens all at once with * multiple threads. */ if (dev->p->dead || dev->driver) goto out_unlock; if (dev->parent) pm_runtime_get_sync(dev->parent); bus_for_each_drv(dev->bus, NULL, &data, __device_attach_driver); dev_dbg(dev, "async probe completed\n"); pm_request_idle(dev); if (dev->parent) pm_runtime_put(dev->parent); out_unlock: device_unlock(dev); put_device(dev); } static int __device_attach(struct device *dev, bool allow_async) { int ret = 0; bool async = false; device_lock(dev); if (dev->p->dead) { goto out_unlock; } else if (dev->driver) { if (device_is_bound(dev)) { ret = 1; goto out_unlock; } ret = device_bind_driver(dev); if (ret == 0) ret = 1; else { dev->driver = NULL; ret = 0; } } else { struct device_attach_data data = { .dev = dev, .check_async = allow_async, .want_async = false, }; if (dev->parent) pm_runtime_get_sync(dev->parent); ret = bus_for_each_drv(dev->bus, NULL, &data, __device_attach_driver); if (!ret && allow_async && data.have_async) { /* * If we could not find appropriate driver * synchronously and we are allowed to do * async probes and there are drivers that * want to probe asynchronously, we'll * try them. */ dev_dbg(dev, "scheduling asynchronous probe\n"); get_device(dev); async = true; } else { pm_request_idle(dev); } if (dev->parent) pm_runtime_put(dev->parent); } out_unlock: device_unlock(dev); if (async) async_schedule_dev(__device_attach_async_helper, dev); return ret; } /** * device_attach - try to attach device to a driver. * @dev: device. * * Walk the list of drivers that the bus has and call * driver_probe_device() for each pair. If a compatible * pair is found, break out and return. * * Returns 1 if the device was bound to a driver; * 0 if no matching driver was found; * -ENODEV if the device is not registered. * * When called for a USB interface, @dev->parent lock must be held. */ int device_attach(struct device *dev) { return __device_attach(dev, false); } EXPORT_SYMBOL_GPL(device_attach); void device_initial_probe(struct device *dev) { __device_attach(dev, true); } /* * __device_driver_lock - acquire locks needed to manipulate dev->drv * @dev: Device we will update driver info for * @parent: Parent device. Needed if the bus requires parent lock * * This function will take the required locks for manipulating dev->drv. * Normally this will just be the @dev lock, but when called for a USB * interface, @parent lock will be held as well. */ static void __device_driver_lock(struct device *dev, struct device *parent) { if (parent && dev->bus->need_parent_lock) device_lock(parent); device_lock(dev); } /* * __device_driver_unlock - release locks needed to manipulate dev->drv * @dev: Device we will update driver info for * @parent: Parent device. Needed if the bus requires parent lock * * This function will release the required locks for manipulating dev->drv. * Normally this will just be the the @dev lock, but when called for a * USB interface, @parent lock will be released as well. */ static void __device_driver_unlock(struct device *dev, struct device *parent) { device_unlock(dev); if (parent && dev->bus->need_parent_lock) device_unlock(parent); } /** * device_driver_attach - attach a specific driver to a specific device * @drv: Driver to attach * @dev: Device to attach it to * * Manually attach driver to a device. Will acquire both @dev lock and * @dev->parent lock if needed. Returns 0 on success, -ERR on failure. */ int device_driver_attach(struct device_driver *drv, struct device *dev) { int ret; __device_driver_lock(dev, dev->parent); ret = __driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); /* also return probe errors as normal negative errnos */ if (ret > 0) ret = -ret; if (ret == -EPROBE_DEFER) return -EAGAIN; return ret; } EXPORT_SYMBOL_GPL(device_driver_attach); static void __driver_attach_async_helper(void *_dev, async_cookie_t cookie) { struct device *dev = _dev; struct device_driver *drv; int ret; __device_driver_lock(dev, dev->parent); drv = dev->p->async_driver; ret = driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); dev_dbg(dev, "driver %s async attach completed: %d\n", drv->name, ret); put_device(dev); } static int __driver_attach(struct device *dev, void *data) { struct device_driver *drv = data; bool async = false; int ret; /* * Lock device and try to bind to it. We drop the error * here and always return 0, because we need to keep trying * to bind to devices and some drivers will return an error * simply if it didn't support the device. * * driver_probe_device() will spit a warning if there * is an error. */ ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ return 0; } else if (ret == -EPROBE_DEFER) { dev_dbg(dev, "Device match requests probe deferral\n"); dev->can_match = true; driver_deferred_probe_add(dev); /* * Driver could not match with device, but may match with * another device on the bus. */ return 0; } else if (ret < 0) { dev_dbg(dev, "Bus failed to match device: %d\n", ret); /* * Driver could not match with device, but may match with * another device on the bus. */ return 0; } /* ret > 0 means positive match */ if (driver_allows_async_probing(drv)) { /* * Instead of probing the device synchronously we will * probe it asynchronously to allow for more parallelism. * * We only take the device lock here in order to guarantee * that the dev->driver and async_driver fields are protected */ dev_dbg(dev, "probing driver %s asynchronously\n", drv->name); device_lock(dev); if (!dev->driver) { get_device(dev); dev->p->async_driver = drv; async = true; } device_unlock(dev); if (async) async_schedule_dev(__driver_attach_async_helper, dev); return 0; } __device_driver_lock(dev, dev->parent); driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); return 0; } /** * driver_attach - try to bind driver to devices. * @drv: driver. * * Walk the list of devices that the bus has on it and try to * match the driver with each one. If driver_probe_device() * returns 0 and the @dev->driver is set, we've found a * compatible pair. */ int driver_attach(struct device_driver *drv) { return bus_for_each_dev(drv->bus, NULL, drv, __driver_attach); } EXPORT_SYMBOL_GPL(driver_attach); /* * __device_release_driver() must be called with @dev lock held. * When called for a USB interface, @dev->parent lock must be held as well. */ static void __device_release_driver(struct device *dev, struct device *parent) { struct device_driver *drv; drv = dev->driver; if (drv) { pm_runtime_get_sync(dev); while (device_links_busy(dev)) { __device_driver_unlock(dev, parent); device_links_unbind_consumers(dev); __device_driver_lock(dev, parent); /* * A concurrent invocation of the same function might * have released the driver successfully while this one * was waiting, so check for that. */ if (dev->driver != drv) { pm_runtime_put(dev); return; } } driver_sysfs_remove(dev); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_UNBIND_DRIVER, dev); pm_runtime_put_sync(dev); device_remove_file(dev, &dev_attr_state_synced); device_remove_groups(dev, drv->dev_groups); if (dev->bus && dev->bus->remove) dev->bus->remove(dev); else if (drv->remove) drv->remove(dev); devres_release_all(dev); arch_teardown_dma_ops(dev); kfree(dev->dma_range_map); dev->dma_range_map = NULL; dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) dev->pm_domain->dismiss(dev); pm_runtime_reinit(dev); dev_pm_set_driver_flags(dev, 0); device_links_driver_cleanup(dev); klist_remove(&dev->p->knode_driver); device_pm_check_callbacks(dev); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_UNBOUND_DRIVER, dev); kobject_uevent(&dev->kobj, KOBJ_UNBIND); } } void device_release_driver_internal(struct device *dev, struct device_driver *drv, struct device *parent) { __device_driver_lock(dev, parent); if (!drv || drv == dev->driver) __device_release_driver(dev, parent); __device_driver_unlock(dev, parent); } /** * device_release_driver - manually detach device from driver. * @dev: device. * * Manually detach device from driver. * When called for a USB interface, @dev->parent lock must be held. * * If this function is to be called with @dev->parent lock held, ensure that * the device's consumers are unbound in advance or that their locks can be * acquired under the @dev->parent lock. */ void device_release_driver(struct device *dev) { /* * If anyone calls device_release_driver() recursively from * within their ->remove callback for the same device, they * will deadlock right here. */ device_release_driver_internal(dev, NULL, NULL); } EXPORT_SYMBOL_GPL(device_release_driver); /** * device_driver_detach - detach driver from a specific device * @dev: device to detach driver from * * Detach driver from device. Will acquire both @dev lock and @dev->parent * lock if needed. */ void device_driver_detach(struct device *dev) { device_release_driver_internal(dev, NULL, dev->parent); } /** * driver_detach - detach driver from all devices it controls. * @drv: driver. */ void driver_detach(struct device_driver *drv) { struct device_private *dev_prv; struct device *dev; if (driver_allows_async_probing(drv)) async_synchronize_full(); for (;;) { spin_lock(&drv->p->klist_devices.k_lock); if (list_empty(&drv->p->klist_devices.k_list)) { spin_unlock(&drv->p->klist_devices.k_lock); break; } dev_prv = list_last_entry(&drv->p->klist_devices.k_list, struct device_private, knode_driver.n_node); dev = dev_prv->device; get_device(dev); spin_unlock(&drv->p->klist_devices.k_lock); device_release_driver_internal(dev, drv, dev->parent); put_device(dev); } } |
| 5 5 1 1 1 1 3 3 3 2 1 1 1 3 1 1 2 5 5 2 1 1 2 2 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing */ #include "multicast.h" #include "main.h" #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/icmpv6.h> #include <linux/if_bridge.h> #include <linux/if_ether.h> #include <linux/igmp.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> #include <linux/workqueue.h> #include <net/addrconf.h> #include <net/genetlink.h> #include <net/if_inet6.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <net/sock.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> #include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" #include "netlink.h" #include "send.h" #include "soft-interface.h" #include "translation-table.h" #include "tvlv.h" static void batadv_mcast_mla_update(struct work_struct *work); /** * batadv_mcast_start_timer() - schedule the multicast periodic worker * @bat_priv: the bat priv with all the soft interface information */ static void batadv_mcast_start_timer(struct batadv_priv *bat_priv) { queue_delayed_work(batadv_event_workqueue, &bat_priv->mcast.work, msecs_to_jiffies(BATADV_MCAST_WORK_PERIOD)); } /** * batadv_mcast_get_bridge() - get the bridge on top of the softif if it exists * @soft_iface: netdev struct of the mesh interface * * If the given soft interface has a bridge on top then the refcount * of the according net device is increased. * * Return: NULL if no such bridge exists. Otherwise the net device of the * bridge. */ static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface) { struct net_device *upper = soft_iface; rcu_read_lock(); do { upper = netdev_master_upper_dev_get_rcu(upper); } while (upper && !(upper->priv_flags & IFF_EBRIDGE)); dev_hold(upper); rcu_read_unlock(); return upper; } /** * batadv_mcast_mla_rtr_flags_softif_get_ipv4() - get mcast router flags from * node for IPv4 * @dev: the interface to check * * Checks the presence of an IPv4 multicast router on this node. * * Caller needs to hold rcu read lock. * * Return: BATADV_NO_FLAGS if present, BATADV_MCAST_WANT_NO_RTR4 otherwise. */ static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv4(struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); if (in_dev && IN_DEV_MFORWARD(in_dev)) return BATADV_NO_FLAGS; else return BATADV_MCAST_WANT_NO_RTR4; } /** * batadv_mcast_mla_rtr_flags_softif_get_ipv6() - get mcast router flags from * node for IPv6 * @dev: the interface to check * * Checks the presence of an IPv6 multicast router on this node. * * Caller needs to hold rcu read lock. * * Return: BATADV_NO_FLAGS if present, BATADV_MCAST_WANT_NO_RTR6 otherwise. */ #if IS_ENABLED(CONFIG_IPV6_MROUTE) static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev) { struct inet6_dev *in6_dev = __in6_dev_get(dev); if (in6_dev && atomic_read(&in6_dev->cnf.mc_forwarding)) return BATADV_NO_FLAGS; else return BATADV_MCAST_WANT_NO_RTR6; } #else static inline u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev) { return BATADV_MCAST_WANT_NO_RTR6; } #endif /** * batadv_mcast_mla_rtr_flags_softif_get() - get mcast router flags from node * @bat_priv: the bat priv with all the soft interface information * @bridge: bridge interface on top of the soft_iface if present, * otherwise pass NULL * * Checks the presence of IPv4 and IPv6 multicast routers on this * node. * * Return: * BATADV_NO_FLAGS: Both an IPv4 and IPv6 multicast router is present * BATADV_MCAST_WANT_NO_RTR4: No IPv4 multicast router is present * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present * The former two OR'd: no multicast router is present */ static u8 batadv_mcast_mla_rtr_flags_softif_get(struct batadv_priv *bat_priv, struct net_device *bridge) { struct net_device *dev = bridge ? bridge : bat_priv->soft_iface; u8 flags = BATADV_NO_FLAGS; rcu_read_lock(); flags |= batadv_mcast_mla_rtr_flags_softif_get_ipv4(dev); flags |= batadv_mcast_mla_rtr_flags_softif_get_ipv6(dev); rcu_read_unlock(); return flags; } /** * batadv_mcast_mla_rtr_flags_bridge_get() - get mcast router flags from bridge * @bat_priv: the bat priv with all the soft interface information * @bridge: bridge interface on top of the soft_iface if present, * otherwise pass NULL * * Checks the presence of IPv4 and IPv6 multicast routers behind a bridge. * * Return: * BATADV_NO_FLAGS: Both an IPv4 and IPv6 multicast router is present * BATADV_MCAST_WANT_NO_RTR4: No IPv4 multicast router is present * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present * The former two OR'd: no multicast router is present */ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv, struct net_device *bridge) { struct net_device *dev = bat_priv->soft_iface; u8 flags = BATADV_NO_FLAGS; if (!bridge) return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; if (!br_multicast_has_router_adjacent(dev, ETH_P_IP)) flags |= BATADV_MCAST_WANT_NO_RTR4; if (!br_multicast_has_router_adjacent(dev, ETH_P_IPV6)) flags |= BATADV_MCAST_WANT_NO_RTR6; return flags; } /** * batadv_mcast_mla_rtr_flags_get() - get multicast router flags * @bat_priv: the bat priv with all the soft interface information * @bridge: bridge interface on top of the soft_iface if present, * otherwise pass NULL * * Checks the presence of IPv4 and IPv6 multicast routers on this * node or behind its bridge. * * Return: * BATADV_NO_FLAGS: Both an IPv4 and IPv6 multicast router is present * BATADV_MCAST_WANT_NO_RTR4: No IPv4 multicast router is present * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present * The former two OR'd: no multicast router is present */ static u8 batadv_mcast_mla_rtr_flags_get(struct batadv_priv *bat_priv, struct net_device *bridge) { u8 flags = BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; flags &= batadv_mcast_mla_rtr_flags_softif_get(bat_priv, bridge); flags &= batadv_mcast_mla_rtr_flags_bridge_get(bat_priv, bridge); return flags; } /** * batadv_mcast_mla_flags_get() - get the new multicast flags * @bat_priv: the bat priv with all the soft interface information * * Return: A set of flags for the current/next TVLV, querier and * bridge state. */ static struct batadv_mcast_mla_flags batadv_mcast_mla_flags_get(struct batadv_priv *bat_priv) { struct net_device *dev = bat_priv->soft_iface; struct batadv_mcast_querier_state *qr4, *qr6; struct batadv_mcast_mla_flags mla_flags; struct net_device *bridge; bridge = batadv_mcast_get_bridge(dev); memset(&mla_flags, 0, sizeof(mla_flags)); mla_flags.enabled = 1; mla_flags.tvlv_flags |= batadv_mcast_mla_rtr_flags_get(bat_priv, bridge); if (!bridge) return mla_flags; dev_put(bridge); mla_flags.bridged = 1; qr4 = &mla_flags.querier_ipv4; qr6 = &mla_flags.querier_ipv6; if (!IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)) pr_warn_once("No bridge IGMP snooping compiled - multicast optimizations disabled\n"); qr4->exists = br_multicast_has_querier_anywhere(dev, ETH_P_IP); qr4->shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IP); qr6->exists = br_multicast_has_querier_anywhere(dev, ETH_P_IPV6); qr6->shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IPV6); mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_UNSNOOPABLES; /* 1) If no querier exists at all, then multicast listeners on * our local TT clients behind the bridge will keep silent. * 2) If the selected querier is on one of our local TT clients, * behind the bridge, then this querier might shadow multicast * listeners on our local TT clients, behind this bridge. * * In both cases, we will signalize other batman nodes that * we need all multicast traffic of the according protocol. */ if (!qr4->exists || qr4->shadowing) { mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_IPV4; mla_flags.tvlv_flags &= ~BATADV_MCAST_WANT_NO_RTR4; } if (!qr6->exists || qr6->shadowing) { mla_flags.tvlv_flags |= BATADV_MCAST_WANT_ALL_IPV6; mla_flags.tvlv_flags &= ~BATADV_MCAST_WANT_NO_RTR6; } return mla_flags; } /** * batadv_mcast_mla_is_duplicate() - check whether an address is in a list * @mcast_addr: the multicast address to check * @mcast_list: the list with multicast addresses to search in * * Return: true if the given address is already in the given list. * Otherwise returns false. */ static bool batadv_mcast_mla_is_duplicate(u8 *mcast_addr, struct hlist_head *mcast_list) { struct batadv_hw_addr *mcast_entry; hlist_for_each_entry(mcast_entry, mcast_list, list) if (batadv_compare_eth(mcast_entry->addr, mcast_addr)) return true; return false; } /** * batadv_mcast_mla_softif_get_ipv4() - get softif IPv4 multicast listeners * @dev: the device to collect multicast addresses from * @mcast_list: a list to put found addresses into * @flags: flags indicating the new multicast state * * Collects multicast addresses of IPv4 multicast listeners residing * on this kernel on the given soft interface, dev, in * the given mcast_list. In general, multicast listeners provided by * your multicast receiving applications run directly on this node. * * Return: -ENOMEM on memory allocation error or the number of * items added to the mcast_list otherwise. */ static int batadv_mcast_mla_softif_get_ipv4(struct net_device *dev, struct hlist_head *mcast_list, struct batadv_mcast_mla_flags *flags) { struct batadv_hw_addr *new; struct in_device *in_dev; u8 mcast_addr[ETH_ALEN]; struct ip_mc_list *pmc; int ret = 0; if (flags->tvlv_flags & BATADV_MCAST_WANT_ALL_IPV4) return 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { rcu_read_unlock(); return 0; } for (pmc = rcu_dereference(in_dev->mc_list); pmc; pmc = rcu_dereference(pmc->next_rcu)) { if (flags->tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && ipv4_is_local_multicast(pmc->multiaddr)) continue; if (!(flags->tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) && !ipv4_is_local_multicast(pmc->multiaddr)) continue; ip_eth_mc_map(pmc->multiaddr, mcast_addr); if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list)) continue; new = kmalloc(sizeof(*new), GFP_ATOMIC); if (!new) { ret = -ENOMEM; break; } ether_addr_copy(new->addr, mcast_addr); hlist_add_head(&new->list, mcast_list); ret++; } rcu_read_unlock(); return ret; } /** * batadv_mcast_mla_softif_get_ipv6() - get softif IPv6 multicast listeners * @dev: the device to collect multicast addresses from * @mcast_list: a list to put found addresses into * @flags: flags indicating the new multicast state * * Collects multicast addresses of IPv6 multicast listeners residing * on this kernel on the given soft interface, dev, in * the given mcast_list. In general, multicast listeners provided by * your multicast receiving applications run directly on this node. * * Return: -ENOMEM on memory allocation error or the number of * items added to the mcast_list otherwise. */ #if IS_ENABLED(CONFIG_IPV6) static int batadv_mcast_mla_softif_get_ipv6(struct net_device *dev, struct hlist_head *mcast_list, struct batadv_mcast_mla_flags *flags) { struct batadv_hw_addr *new; struct inet6_dev *in6_dev; u8 mcast_addr[ETH_ALEN]; struct ifmcaddr6 *pmc6; int ret = 0; if (flags->tvlv_flags & BATADV_MCAST_WANT_ALL_IPV6) return 0; rcu_read_lock(); in6_dev = __in6_dev_get(dev); if (!in6_dev) { rcu_read_unlock(); return 0; } for (pmc6 = rcu_dereference(in6_dev->mc_list); pmc6; pmc6 = rcu_dereference(pmc6->next)) { if (IPV6_ADDR_MC_SCOPE(&pmc6->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) continue; if (flags->tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && ipv6_addr_is_ll_all_nodes(&pmc6->mca_addr)) continue; if (!(flags->tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) && IPV6_ADDR_MC_SCOPE(&pmc6->mca_addr) > IPV6_ADDR_SCOPE_LINKLOCAL) continue; ipv6_eth_mc_map(&pmc6->mca_addr, mcast_addr); if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list)) continue; new = kmalloc(sizeof(*new), GFP_ATOMIC); if (!new) { ret = -ENOMEM; break; } ether_addr_copy(new->addr, mcast_addr); hlist_add_head(&new->list, mcast_list); ret++; } rcu_read_unlock(); return ret; } #else static inline int batadv_mcast_mla_softif_get_ipv6(struct net_device *dev, struct hlist_head *mcast_list, struct batadv_mcast_mla_flags *flags) { return 0; } #endif /** * batadv_mcast_mla_softif_get() - get softif multicast listeners * @dev: the device to collect multicast addresses from * @mcast_list: a list to put found addresses into * @flags: flags indicating the new multicast state * * Collects multicast addresses of multicast listeners residing * on this kernel on the given soft interface, dev, in * the given mcast_list. In general, multicast listeners provided by * your multicast receiving applications run directly on this node. * * If there is a bridge interface on top of dev, collect from that one * instead. Just like with IP addresses and routes, multicast listeners * will(/should) register to the bridge interface instead of an * enslaved bat0. * * Return: -ENOMEM on memory allocation error or the number of * items added to the mcast_list otherwise. */ static int batadv_mcast_mla_softif_get(struct net_device *dev, struct hlist_head *mcast_list, struct batadv_mcast_mla_flags *flags) { struct net_device *bridge = batadv_mcast_get_bridge(dev); int ret4, ret6 = 0; if (bridge) dev = bridge; ret4 = batadv_mcast_mla_softif_get_ipv4(dev, mcast_list, flags); if (ret4 < 0) goto out; ret6 = batadv_mcast_mla_softif_get_ipv6(dev, mcast_list, flags); if (ret6 < 0) { ret4 = 0; goto out; } out: dev_put(bridge); return ret4 + ret6; } /** * batadv_mcast_mla_br_addr_cpy() - copy a bridge multicast address * @dst: destination to write to - a multicast MAC address * @src: source to read from - a multicast IP address * * Converts a given multicast IPv4/IPv6 address from a bridge * to its matching multicast MAC address and copies it into the given * destination buffer. * * Caller needs to make sure the destination buffer can hold * at least ETH_ALEN bytes. */ static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src) { if (src->proto == htons(ETH_P_IP)) ip_eth_mc_map(src->dst.ip4, dst); #if IS_ENABLED(CONFIG_IPV6) else if (src->proto == htons(ETH_P_IPV6)) ipv6_eth_mc_map(&src->dst.ip6, dst); #endif else eth_zero_addr(dst); } /** * batadv_mcast_mla_bridge_get() - get bridged-in multicast listeners * @dev: a bridge slave whose bridge to collect multicast addresses from * @mcast_list: a list to put found addresses into * @flags: flags indicating the new multicast state * * Collects multicast addresses of multicast listeners residing * on foreign, non-mesh devices which we gave access to our mesh via * a bridge on top of the given soft interface, dev, in the given * mcast_list. * * Return: -ENOMEM on memory allocation error or the number of * items added to the mcast_list otherwise. */ static int batadv_mcast_mla_bridge_get(struct net_device *dev, struct hlist_head *mcast_list, struct batadv_mcast_mla_flags *flags) { struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list); struct br_ip_list *br_ip_entry, *tmp; u8 tvlv_flags = flags->tvlv_flags; struct batadv_hw_addr *new; u8 mcast_addr[ETH_ALEN]; int ret; /* we don't need to detect these devices/listeners, the IGMP/MLD * snooping code of the Linux bridge already does that for us */ ret = br_multicast_list_adjacent(dev, &bridge_mcast_list); if (ret < 0) goto out; list_for_each_entry(br_ip_entry, &bridge_mcast_list, list) { if (br_ip_entry->addr.proto == htons(ETH_P_IP)) { if (tvlv_flags & BATADV_MCAST_WANT_ALL_IPV4) continue; if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4)) continue; if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) && !ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4)) continue; } #if IS_ENABLED(CONFIG_IPV6) if (br_ip_entry->addr.proto == htons(ETH_P_IPV6)) { if (tvlv_flags & BATADV_MCAST_WANT_ALL_IPV6) continue; if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.dst.ip6)) continue; if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) && IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.dst.ip6) > IPV6_ADDR_SCOPE_LINKLOCAL) continue; } #endif batadv_mcast_mla_br_addr_cpy(mcast_addr, &br_ip_entry->addr); if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list)) continue; new = kmalloc(sizeof(*new), GFP_ATOMIC); if (!new) { ret = -ENOMEM; break; } ether_addr_copy(new->addr, mcast_addr); hlist_add_head(&new->list, mcast_list); } out: list_for_each_entry_safe(br_ip_entry, tmp, &bridge_mcast_list, list) { list_del(&br_ip_entry->list); kfree(br_ip_entry); } return ret; } /** * batadv_mcast_mla_list_free() - free a list of multicast addresses * @mcast_list: the list to free * * Removes and frees all items in the given mcast_list. */ static void batadv_mcast_mla_list_free(struct hlist_head *mcast_list) { struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) { hlist_del(&mcast_entry->list); kfree(mcast_entry); } } /** * batadv_mcast_mla_tt_retract() - clean up multicast listener announcements * @bat_priv: the bat priv with all the soft interface information * @mcast_list: a list of addresses which should _not_ be removed * * Retracts the announcement of any multicast listener from the * translation table except the ones listed in the given mcast_list. * * If mcast_list is NULL then all are retracted. */ static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv, struct hlist_head *mcast_list) { struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; hlist_for_each_entry_safe(mcast_entry, tmp, &bat_priv->mcast.mla_list, list) { if (mcast_list && batadv_mcast_mla_is_duplicate(mcast_entry->addr, mcast_list)) continue; batadv_tt_local_remove(bat_priv, mcast_entry->addr, BATADV_NO_FLAGS, "mcast TT outdated", false); hlist_del(&mcast_entry->list); kfree(mcast_entry); } } /** * batadv_mcast_mla_tt_add() - add multicast listener announcements * @bat_priv: the bat priv with all the soft interface information * @mcast_list: a list of addresses which are going to get added * * Adds multicast listener announcements from the given mcast_list to the * translation table if they have not been added yet. */ static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv, struct hlist_head *mcast_list) { struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; if (!mcast_list) return; hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) { if (batadv_mcast_mla_is_duplicate(mcast_entry->addr, &bat_priv->mcast.mla_list)) continue; if (!batadv_tt_local_add(bat_priv->soft_iface, mcast_entry->addr, BATADV_NO_FLAGS, BATADV_NULL_IFINDEX, BATADV_NO_MARK)) continue; hlist_del(&mcast_entry->list); hlist_add_head(&mcast_entry->list, &bat_priv->mcast.mla_list); } } /** * batadv_mcast_querier_log() - debug output regarding the querier status on * link * @bat_priv: the bat priv with all the soft interface information * @str_proto: a string for the querier protocol (e.g. "IGMP" or "MLD") * @old_state: the previous querier state on our link * @new_state: the new querier state on our link * * Outputs debug messages to the logging facility with log level 'mcast' * regarding changes to the querier status on the link which are relevant * to our multicast optimizations. * * Usually this is about whether a querier appeared or vanished in * our mesh or whether the querier is in the suboptimal position of being * behind our local bridge segment: Snooping switches will directly * forward listener reports to the querier, therefore batman-adv and * the bridge will potentially not see these listeners - the querier is * potentially shadowing listeners from us then. * * This is only interesting for nodes with a bridge on top of their * soft interface. */ static void batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto, struct batadv_mcast_querier_state *old_state, struct batadv_mcast_querier_state *new_state) { if (!old_state->exists && new_state->exists) batadv_info(bat_priv->soft_iface, "%s Querier appeared\n", str_proto); else if (old_state->exists && !new_state->exists) batadv_info(bat_priv->soft_iface, "%s Querier disappeared - multicast optimizations disabled\n", str_proto); else if (!bat_priv->mcast.mla_flags.bridged && !new_state->exists) batadv_info(bat_priv->soft_iface, "No %s Querier present - multicast optimizations disabled\n", str_proto); if (new_state->exists) { if ((!old_state->shadowing && new_state->shadowing) || (!old_state->exists && new_state->shadowing)) batadv_dbg(BATADV_DBG_MCAST, bat_priv, "%s Querier is behind our bridged segment: Might shadow listeners\n", str_proto); else if (old_state->shadowing && !new_state->shadowing) batadv_dbg(BATADV_DBG_MCAST, bat_priv, "%s Querier is not behind our bridged segment\n", str_proto); } } /** * batadv_mcast_bridge_log() - debug output for topology changes in bridged * setups * @bat_priv: the bat priv with all the soft interface information * @new_flags: flags indicating the new multicast state * * If no bridges are ever used on this node, then this function does nothing. * * Otherwise this function outputs debug information to the 'mcast' log level * which might be relevant to our multicast optimizations. * * More precisely, it outputs information when a bridge interface is added or * removed from a soft interface. And when a bridge is present, it further * outputs information about the querier state which is relevant for the * multicast flags this node is going to set. */ static void batadv_mcast_bridge_log(struct batadv_priv *bat_priv, struct batadv_mcast_mla_flags *new_flags) { struct batadv_mcast_mla_flags *old_flags = &bat_priv->mcast.mla_flags; if (!old_flags->bridged && new_flags->bridged) batadv_dbg(BATADV_DBG_MCAST, bat_priv, "Bridge added: Setting Unsnoopables(U)-flag\n"); else if (old_flags->bridged && !new_flags->bridged) batadv_dbg(BATADV_DBG_MCAST, bat_priv, "Bridge removed: Unsetting Unsnoopables(U)-flag\n"); if (new_flags->bridged) { batadv_mcast_querier_log(bat_priv, "IGMP", &old_flags->querier_ipv4, &new_flags->querier_ipv4); batadv_mcast_querier_log(bat_priv, "MLD", &old_flags->querier_ipv6, &new_flags->querier_ipv6); } } /** * batadv_mcast_flags_log() - output debug information about mcast flag changes * @bat_priv: the bat priv with all the soft interface information * @flags: TVLV flags indicating the new multicast state * * Whenever the multicast TVLV flags this node announces change, this function * should be used to notify userspace about the change. */ static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags) { bool old_enabled = bat_priv->mcast.mla_flags.enabled; u8 old_flags = bat_priv->mcast.mla_flags.tvlv_flags; char str_old_flags[] = "[.... . ]"; sprintf(str_old_flags, "[%c%c%c%s%s]", (old_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.', (old_flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.', (old_flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.', !(old_flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ", !(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". "); batadv_dbg(BATADV_DBG_MCAST, bat_priv, "Changing multicast flags from '%s' to '[%c%c%c%s%s]'\n", old_enabled ? str_old_flags : "<undefined>", (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.', (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.', (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.', !(flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ", !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". "); } /** * batadv_mcast_mla_flags_update() - update multicast flags * @bat_priv: the bat priv with all the soft interface information * @flags: flags indicating the new multicast state * * Updates the own multicast tvlv with our current multicast related settings, * capabilities and inabilities. */ static void batadv_mcast_mla_flags_update(struct batadv_priv *bat_priv, struct batadv_mcast_mla_flags *flags) { struct batadv_tvlv_mcast_data mcast_data; if (!memcmp(flags, &bat_priv->mcast.mla_flags, sizeof(*flags))) return; batadv_mcast_bridge_log(bat_priv, flags); batadv_mcast_flags_log(bat_priv, flags->tvlv_flags); mcast_data.flags = flags->tvlv_flags; memset(mcast_data.reserved, 0, sizeof(mcast_data.reserved)); batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 2, &mcast_data, sizeof(mcast_data)); bat_priv->mcast.mla_flags = *flags; } /** * __batadv_mcast_mla_update() - update the own MLAs * @bat_priv: the bat priv with all the soft interface information * * Updates the own multicast listener announcements in the translation * table as well as the own, announced multicast tvlv container. * * Note that non-conflicting reads and writes to bat_priv->mcast.mla_list * in batadv_mcast_mla_tt_retract() and batadv_mcast_mla_tt_add() are * ensured by the non-parallel execution of the worker this function * belongs to. */ static void __batadv_mcast_mla_update(struct batadv_priv *bat_priv) { struct net_device *soft_iface = bat_priv->soft_iface; struct hlist_head mcast_list = HLIST_HEAD_INIT; struct batadv_mcast_mla_flags flags; int ret; flags = batadv_mcast_mla_flags_get(bat_priv); ret = batadv_mcast_mla_softif_get(soft_iface, &mcast_list, &flags); if (ret < 0) goto out; ret = batadv_mcast_mla_bridge_get(soft_iface, &mcast_list, &flags); if (ret < 0) goto out; spin_lock(&bat_priv->mcast.mla_lock); batadv_mcast_mla_tt_retract(bat_priv, &mcast_list); batadv_mcast_mla_tt_add(bat_priv, &mcast_list); batadv_mcast_mla_flags_update(bat_priv, &flags); spin_unlock(&bat_priv->mcast.mla_lock); out: batadv_mcast_mla_list_free(&mcast_list); } /** * batadv_mcast_mla_update() - update the own MLAs * @work: kernel work struct * * Updates the own multicast listener announcements in the translation * table as well as the own, announced multicast tvlv container. * * In the end, reschedules the work timer. */ static void batadv_mcast_mla_update(struct work_struct *work) { struct delayed_work *delayed_work; struct batadv_priv_mcast *priv_mcast; struct batadv_priv *bat_priv; delayed_work = to_delayed_work(work); priv_mcast = container_of(delayed_work, struct batadv_priv_mcast, work); bat_priv = container_of(priv_mcast, struct batadv_priv, mcast); __batadv_mcast_mla_update(bat_priv); batadv_mcast_start_timer(bat_priv); } /** * batadv_mcast_is_report_ipv4() - check for IGMP reports * @skb: the ethernet frame destined for the mesh * * This call might reallocate skb data. * * Checks whether the given frame is a valid IGMP report. * * Return: If so then true, otherwise false. */ static bool batadv_mcast_is_report_ipv4(struct sk_buff *skb) { if (ip_mc_check_igmp(skb) < 0) return false; switch (igmp_hdr(skb)->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: case IGMPV3_HOST_MEMBERSHIP_REPORT: return true; } return false; } /** * batadv_mcast_forw_mode_check_ipv4() - check for optimized forwarding * potential * @bat_priv: the bat priv with all the soft interface information * @skb: the IPv4 packet to check * @is_unsnoopable: stores whether the destination is snoopable * @is_routable: stores whether the destination is routable * * Checks whether the given IPv4 packet has the potential to be forwarded with a * mode more optimal than classic flooding. * * Return: If so then 0. Otherwise -EINVAL or -ENOMEM in case of memory * allocation failure. */ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv, struct sk_buff *skb, bool *is_unsnoopable, int *is_routable) { struct iphdr *iphdr; /* We might fail due to out-of-memory -> drop it */ if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*iphdr))) return -ENOMEM; if (batadv_mcast_is_report_ipv4(skb)) return -EINVAL; iphdr = ip_hdr(skb); /* link-local multicast listeners behind a bridge are * not snoopable (see RFC4541, section 2.1.2.2) */ if (ipv4_is_local_multicast(iphdr->daddr)) *is_unsnoopable = true; else *is_routable = ETH_P_IP; return 0; } /** * batadv_mcast_is_report_ipv6() - check for MLD reports * @skb: the ethernet frame destined for the mesh * * This call might reallocate skb data. * * Checks whether the given frame is a valid MLD report. * * Return: If so then true, otherwise false. */ static bool batadv_mcast_is_report_ipv6(struct sk_buff *skb) { if (ipv6_mc_check_mld(skb) < 0) return false; switch (icmp6_hdr(skb)->icmp6_type) { case ICMPV6_MGM_REPORT: case ICMPV6_MLD2_REPORT: return true; } return false; } /** * batadv_mcast_forw_mode_check_ipv6() - check for optimized forwarding * potential * @bat_priv: the bat priv with all the soft interface information * @skb: the IPv6 packet to check * @is_unsnoopable: stores whether the destination is snoopable * @is_routable: stores whether the destination is routable * * Checks whether the given IPv6 packet has the potential to be forwarded with a * mode more optimal than classic flooding. * * Return: If so then 0. Otherwise -EINVAL is or -ENOMEM if we are out of memory */ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv, struct sk_buff *skb, bool *is_unsnoopable, int *is_routable) { struct ipv6hdr *ip6hdr; /* We might fail due to out-of-memory -> drop it */ if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*ip6hdr))) return -ENOMEM; if (batadv_mcast_is_report_ipv6(skb)) return -EINVAL; ip6hdr = ipv6_hdr(skb); if (IPV6_ADDR_MC_SCOPE(&ip6hdr->daddr) < IPV6_ADDR_SCOPE_LINKLOCAL) return -EINVAL; /* link-local-all-nodes multicast listeners behind a bridge are * not snoopable (see RFC4541, section 3, paragraph 3) */ if (ipv6_addr_is_ll_all_nodes(&ip6hdr->daddr)) *is_unsnoopable = true; else if (IPV6_ADDR_MC_SCOPE(&ip6hdr->daddr) > IPV6_ADDR_SCOPE_LINKLOCAL) *is_routable = ETH_P_IPV6; return 0; } /** * batadv_mcast_forw_mode_check() - check for optimized forwarding potential * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast frame to check * @is_unsnoopable: stores whether the destination is snoopable * @is_routable: stores whether the destination is routable * * Checks whether the given multicast ethernet frame has the potential to be * forwarded with a mode more optimal than classic flooding. * * Return: If so then 0. Otherwise -EINVAL is or -ENOMEM if we are out of memory */ static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv, struct sk_buff *skb, bool *is_unsnoopable, int *is_routable) { struct ethhdr *ethhdr = eth_hdr(skb); if (!atomic_read(&bat_priv->multicast_mode)) return -EINVAL; switch (ntohs(ethhdr->h_proto)) { case ETH_P_IP: return batadv_mcast_forw_mode_check_ipv4(bat_priv, skb, is_unsnoopable, is_routable); case ETH_P_IPV6: if (!IS_ENABLED(CONFIG_IPV6)) return -EINVAL; return batadv_mcast_forw_mode_check_ipv6(bat_priv, skb, is_unsnoopable, is_routable); default: return -EINVAL; } } /** * batadv_mcast_forw_want_all_ip_count() - count nodes with unspecific mcast * interest * @bat_priv: the bat priv with all the soft interface information * @ethhdr: ethernet header of a packet * * Return: the number of nodes which want all IPv4 multicast traffic if the * given ethhdr is from an IPv4 packet or the number of nodes which want all * IPv6 traffic if it matches an IPv6 packet. */ static int batadv_mcast_forw_want_all_ip_count(struct batadv_priv *bat_priv, struct ethhdr *ethhdr) { switch (ntohs(ethhdr->h_proto)) { case ETH_P_IP: return atomic_read(&bat_priv->mcast.num_want_all_ipv4); case ETH_P_IPV6: return atomic_read(&bat_priv->mcast.num_want_all_ipv6); default: /* we shouldn't be here... */ return 0; } } /** * batadv_mcast_forw_rtr_count() - count nodes with a multicast router * @bat_priv: the bat priv with all the soft interface information * @protocol: the ethernet protocol type to count multicast routers for * * Return: the number of nodes which want all routable IPv4 multicast traffic * if the protocol is ETH_P_IP or the number of nodes which want all routable * IPv6 traffic if the protocol is ETH_P_IPV6. Otherwise returns 0. */ static int batadv_mcast_forw_rtr_count(struct batadv_priv *bat_priv, int protocol) { switch (protocol) { case ETH_P_IP: return atomic_read(&bat_priv->mcast.num_want_all_rtr4); case ETH_P_IPV6: return atomic_read(&bat_priv->mcast.num_want_all_rtr6); default: return 0; } } /** * batadv_mcast_forw_tt_node_get() - get a multicast tt node * @bat_priv: the bat priv with all the soft interface information * @ethhdr: the ether header containing the multicast destination * * Return: an orig_node matching the multicast address provided by ethhdr * via a translation table lookup. This increases the returned nodes refcount. */ static struct batadv_orig_node * batadv_mcast_forw_tt_node_get(struct batadv_priv *bat_priv, struct ethhdr *ethhdr) { return batadv_transtable_search(bat_priv, NULL, ethhdr->h_dest, BATADV_NO_FLAGS); } /** * batadv_mcast_forw_ipv4_node_get() - get a node with an ipv4 flag * @bat_priv: the bat priv with all the soft interface information * * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 flag set and * increases its refcount. */ static struct batadv_orig_node * batadv_mcast_forw_ipv4_node_get(struct batadv_priv *bat_priv) { struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_orig_node, &bat_priv->mcast.want_all_ipv4_list, mcast_want_all_ipv4_node) { if (!kref_get_unless_zero(&tmp_orig_node->refcount)) continue; orig_node = tmp_orig_node; break; } rcu_read_unlock(); return orig_node; } /** * batadv_mcast_forw_ipv6_node_get() - get a node with an ipv6 flag * @bat_priv: the bat priv with all the soft interface information * * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_IPV6 flag set * and increases its refcount. */ static struct batadv_orig_node * batadv_mcast_forw_ipv6_node_get(struct batadv_priv *bat_priv) { struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_orig_node, &bat_priv->mcast.want_all_ipv6_list, mcast_want_all_ipv6_node) { if (!kref_get_unless_zero(&tmp_orig_node->refcount)) continue; orig_node = tmp_orig_node; break; } rcu_read_unlock(); return orig_node; } /** * batadv_mcast_forw_ip_node_get() - get a node with an ipv4/ipv6 flag * @bat_priv: the bat priv with all the soft interface information * @ethhdr: an ethernet header to determine the protocol family from * * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 or * BATADV_MCAST_WANT_ALL_IPV6 flag, depending on the provided ethhdr, sets and * increases its refcount. */ static struct batadv_orig_node * batadv_mcast_forw_ip_node_get(struct batadv_priv *bat_priv, struct ethhdr *ethhdr) { switch (ntohs(ethhdr->h_proto)) { case ETH_P_IP: return batadv_mcast_forw_ipv4_node_get(bat_priv); case ETH_P_IPV6: return batadv_mcast_forw_ipv6_node_get(bat_priv); default: /* we shouldn't be here... */ return NULL; } } /** * batadv_mcast_forw_unsnoop_node_get() - get a node with an unsnoopable flag * @bat_priv: the bat priv with all the soft interface information * * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag * set and increases its refcount. */ static struct batadv_orig_node * batadv_mcast_forw_unsnoop_node_get(struct batadv_priv *bat_priv) { struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_orig_node, &bat_priv->mcast.want_all_unsnoopables_list, mcast_want_all_unsnoopables_node) { if (!kref_get_unless_zero(&tmp_orig_node->refcount)) continue; orig_node = tmp_orig_node; break; } rcu_read_unlock(); return orig_node; } /** * batadv_mcast_forw_rtr4_node_get() - get a node with an ipv4 mcast router flag * @bat_priv: the bat priv with all the soft interface information * * Return: an orig_node which has the BATADV_MCAST_WANT_NO_RTR4 flag unset and * increases its refcount. */ static struct batadv_orig_node * batadv_mcast_forw_rtr4_node_get(struct batadv_priv *bat_priv) { struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_orig_node, &bat_priv->mcast.want_all_rtr4_list, mcast_want_all_rtr4_node) { if (!kref_get_unless_zero(&tmp_orig_node->refcount)) continue; orig_node = tmp_orig_node; break; } rcu_read_unlock(); return orig_node; } /** * batadv_mcast_forw_rtr6_node_get() - get a node with an ipv6 mcast router flag * @bat_priv: the bat priv with all the soft interface information * * Return: an orig_node which has the BATADV_MCAST_WANT_NO_RTR6 flag unset * and increases its refcount. */ static struct batadv_orig_node * batadv_mcast_forw_rtr6_node_get(struct batadv_priv *bat_priv) { struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_orig_node, &bat_priv->mcast.want_all_rtr6_list, mcast_want_all_rtr6_node) { if (!kref_get_unless_zero(&tmp_orig_node->refcount)) continue; orig_node = tmp_orig_node; break; } rcu_read_unlock(); return orig_node; } /** * batadv_mcast_forw_rtr_node_get() - get a node with an ipv4/ipv6 router flag * @bat_priv: the bat priv with all the soft interface information * @ethhdr: an ethernet header to determine the protocol family from * * Return: an orig_node which has no BATADV_MCAST_WANT_NO_RTR4 or * BATADV_MCAST_WANT_NO_RTR6 flag, depending on the provided ethhdr, set and * increases its refcount. */ static struct batadv_orig_node * batadv_mcast_forw_rtr_node_get(struct batadv_priv *bat_priv, struct ethhdr *ethhdr) { switch (ntohs(ethhdr->h_proto)) { case ETH_P_IP: return batadv_mcast_forw_rtr4_node_get(bat_priv); case ETH_P_IPV6: return batadv_mcast_forw_rtr6_node_get(bat_priv); default: /* we shouldn't be here... */ return NULL; } } /** * batadv_mcast_forw_mode() - check on how to forward a multicast packet * @bat_priv: the bat priv with all the soft interface information * @skb: The multicast packet to check * @orig: an originator to be set to forward the skb to * @is_routable: stores whether the destination is routable * * Return: the forwarding mode as enum batadv_forw_mode and in case of * BATADV_FORW_SINGLE set the orig to the single originator the skb * should be forwarded to. */ enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node **orig, int *is_routable) { int ret, tt_count, ip_count, unsnoop_count, total_count; bool is_unsnoopable = false; unsigned int mcast_fanout; struct ethhdr *ethhdr; int rtr_count = 0; ret = batadv_mcast_forw_mode_check(bat_priv, skb, &is_unsnoopable, is_routable); if (ret == -ENOMEM) return BATADV_FORW_NONE; else if (ret < 0) return BATADV_FORW_ALL; ethhdr = eth_hdr(skb); tt_count = batadv_tt_global_hash_count(bat_priv, ethhdr->h_dest, BATADV_NO_FLAGS); ip_count = batadv_mcast_forw_want_all_ip_count(bat_priv, ethhdr); unsnoop_count = !is_unsnoopable ? 0 : atomic_read(&bat_priv->mcast.num_want_all_unsnoopables); rtr_count = batadv_mcast_forw_rtr_count(bat_priv, *is_routable); total_count = tt_count + ip_count + unsnoop_count + rtr_count; switch (total_count) { case 1: if (tt_count) *orig = batadv_mcast_forw_tt_node_get(bat_priv, ethhdr); else if (ip_count) *orig = batadv_mcast_forw_ip_node_get(bat_priv, ethhdr); else if (unsnoop_count) *orig = batadv_mcast_forw_unsnoop_node_get(bat_priv); else if (rtr_count) *orig = batadv_mcast_forw_rtr_node_get(bat_priv, ethhdr); if (*orig) return BATADV_FORW_SINGLE; fallthrough; case 0: return BATADV_FORW_NONE; default: mcast_fanout = atomic_read(&bat_priv->multicast_fanout); if (!unsnoop_count && total_count <= mcast_fanout) return BATADV_FORW_SOME; } return BATADV_FORW_ALL; } /** * batadv_mcast_forw_send_orig() - send a multicast packet to an originator * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to send * @vid: the vlan identifier * @orig_node: the originator to send the packet to * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, struct batadv_orig_node *orig_node) { /* Avoid sending multicast-in-unicast packets to other BLA * gateways - they already got the frame from the LAN side * we share with them. * TODO: Refactor to take BLA into account earlier, to avoid * reducing the mcast_fanout count. */ if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) { dev_kfree_skb(skb); return NET_XMIT_SUCCESS; } return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0, orig_node, vid); } /** * batadv_mcast_forw_tt() - forwards a packet to multicast listeners * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any multicast * listener registered in the translation table. A transmission is performed * via a batman-adv unicast packet for each such destination node. * * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS * otherwise. */ static int batadv_mcast_forw_tt(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { int ret = NET_XMIT_SUCCESS; struct sk_buff *newskb; struct batadv_tt_orig_list_entry *orig_entry; struct batadv_tt_global_entry *tt_global; const u8 *addr = eth_hdr(skb)->h_dest; tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid); if (!tt_global) goto out; rcu_read_lock(); hlist_for_each_entry_rcu(orig_entry, &tt_global->orig_list, list) { newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) { ret = NET_XMIT_DROP; break; } batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_entry->orig_node); } rcu_read_unlock(); batadv_tt_global_entry_put(tt_global); out: return ret; } /** * batadv_mcast_forw_want_all_ipv4() - forward to nodes with want-all-ipv4 * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_ALL_IPV4 flag set. A transmission is performed via a * batman-adv unicast packet for each such destination node. * * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS * otherwise. */ static int batadv_mcast_forw_want_all_ipv4(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret = NET_XMIT_SUCCESS; struct sk_buff *newskb; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, &bat_priv->mcast.want_all_ipv4_list, mcast_want_all_ipv4_node) { newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) { ret = NET_XMIT_DROP; break; } batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; } /** * batadv_mcast_forw_want_all_ipv6() - forward to nodes with want-all-ipv6 * @bat_priv: the bat priv with all the soft interface information * @skb: The multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_ALL_IPV6 flag set. A transmission is performed via a * batman-adv unicast packet for each such destination node. * * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS * otherwise. */ static int batadv_mcast_forw_want_all_ipv6(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret = NET_XMIT_SUCCESS; struct sk_buff *newskb; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, &bat_priv->mcast.want_all_ipv6_list, mcast_want_all_ipv6_node) { newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) { ret = NET_XMIT_DROP; break; } batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; } /** * batadv_mcast_forw_want_all() - forward packet to nodes in a want-all list * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_ALL_IPV4 or BATADV_MCAST_WANT_ALL_IPV6 flag set. A * transmission is performed via a batman-adv unicast packet for each such * destination node. * * Return: NET_XMIT_DROP on memory allocation failure or if the protocol family * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise. */ static int batadv_mcast_forw_want_all(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { switch (ntohs(eth_hdr(skb)->h_proto)) { case ETH_P_IP: return batadv_mcast_forw_want_all_ipv4(bat_priv, skb, vid); case ETH_P_IPV6: return batadv_mcast_forw_want_all_ipv6(bat_priv, skb, vid); default: /* we shouldn't be here... */ return NET_XMIT_DROP; } } /** * batadv_mcast_forw_want_all_rtr4() - forward to nodes with want-all-rtr4 * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_NO_RTR4 flag unset. A transmission is performed via a * batman-adv unicast packet for each such destination node. * * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS * otherwise. */ static int batadv_mcast_forw_want_all_rtr4(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret = NET_XMIT_SUCCESS; struct sk_buff *newskb; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, &bat_priv->mcast.want_all_rtr4_list, mcast_want_all_rtr4_node) { newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) { ret = NET_XMIT_DROP; break; } batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; } /** * batadv_mcast_forw_want_all_rtr6() - forward to nodes with want-all-rtr6 * @bat_priv: the bat priv with all the soft interface information * @skb: The multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_NO_RTR6 flag unset. A transmission is performed via a * batman-adv unicast packet for each such destination node. * * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS * otherwise. */ static int batadv_mcast_forw_want_all_rtr6(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret = NET_XMIT_SUCCESS; struct sk_buff *newskb; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, &bat_priv->mcast.want_all_rtr6_list, mcast_want_all_rtr6_node) { newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) { ret = NET_XMIT_DROP; break; } batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; } /** * batadv_mcast_forw_want_rtr() - forward packet to nodes in a want-all-rtr list * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * * Sends copies of a frame with multicast destination to any node with a * BATADV_MCAST_WANT_NO_RTR4 or BATADV_MCAST_WANT_NO_RTR6 flag unset. A * transmission is performed via a batman-adv unicast packet for each such * destination node. * * Return: NET_XMIT_DROP on memory allocation failure or if the protocol family * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise. */ static int batadv_mcast_forw_want_rtr(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { switch (ntohs(eth_hdr(skb)->h_proto)) { case ETH_P_IP: return batadv_mcast_forw_want_all_rtr4(bat_priv, skb, vid); case ETH_P_IPV6: return batadv_mcast_forw_want_all_rtr6(bat_priv, skb, vid); default: /* we shouldn't be here... */ return NET_XMIT_DROP; } } /** * batadv_mcast_forw_send() - send packet to any detected multicast recipient * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier * @is_routable: stores whether the destination is routable * * Sends copies of a frame with multicast destination to any node that signaled * interest in it, that is either via the translation table or the according * want-all flags. A transmission is performed via a batman-adv unicast packet * for each such destination node. * * The given skb is consumed/freed. * * Return: NET_XMIT_DROP on memory allocation failure or if the protocol family * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise. */ int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, int is_routable) { int ret; ret = batadv_mcast_forw_tt(bat_priv, skb, vid); if (ret != NET_XMIT_SUCCESS) { kfree_skb(skb); return ret; } ret = batadv_mcast_forw_want_all(bat_priv, skb, vid); if (ret != NET_XMIT_SUCCESS) { kfree_skb(skb); return ret; } if (!is_routable) goto skip_mc_router; ret = batadv_mcast_forw_want_rtr(bat_priv, skb, vid); if (ret != NET_XMIT_SUCCESS) { kfree_skb(skb); return ret; } skip_mc_router: consume_skb(skb); return ret; } /** * batadv_mcast_want_unsnoop_update() - update unsnoop counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag of this originator, * orig, has toggled then this method updates the counter and the list * accordingly. * * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { struct hlist_node *node = &orig->mcast_want_all_unsnoopables_node; struct hlist_head *head = &bat_priv->mcast.want_all_unsnoopables_list; lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag unset to set */ if (mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)) { atomic_inc(&bat_priv->mcast.num_want_all_unsnoopables); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(!hlist_unhashed(node)); hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag set to unset */ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) && orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) { atomic_dec(&bat_priv->mcast.num_want_all_unsnoopables); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(hlist_unhashed(node)); hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } /** * batadv_mcast_want_ipv4_update() - update want-all-ipv4 counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_WANT_ALL_IPV4 flag of this originator, orig, has * toggled then this method updates the counter and the list accordingly. * * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { struct hlist_node *node = &orig->mcast_want_all_ipv4_node; struct hlist_head *head = &bat_priv->mcast.want_all_ipv4_list; lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag unset to set */ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV4 && !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4)) { atomic_inc(&bat_priv->mcast.num_want_all_ipv4); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(!hlist_unhashed(node)); hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag set to unset */ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) && orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) { atomic_dec(&bat_priv->mcast.num_want_all_ipv4); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(hlist_unhashed(node)); hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } /** * batadv_mcast_want_ipv6_update() - update want-all-ipv6 counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_WANT_ALL_IPV6 flag of this originator, orig, has * toggled then this method updates the counter and the list accordingly. * * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { struct hlist_node *node = &orig->mcast_want_all_ipv6_node; struct hlist_head *head = &bat_priv->mcast.want_all_ipv6_list; lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag unset to set */ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV6 && !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6)) { atomic_inc(&bat_priv->mcast.num_want_all_ipv6); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(!hlist_unhashed(node)); hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag set to unset */ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) && orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) { atomic_dec(&bat_priv->mcast.num_want_all_ipv6); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(hlist_unhashed(node)); hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } /** * batadv_mcast_want_rtr4_update() - update want-all-rtr4 counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_WANT_NO_RTR4 flag of this originator, orig, has * toggled then this method updates the counter and the list accordingly. * * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_rtr4_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { struct hlist_node *node = &orig->mcast_want_all_rtr4_node; struct hlist_head *head = &bat_priv->mcast.want_all_rtr4_list; lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag set to unset */ if (!(mcast_flags & BATADV_MCAST_WANT_NO_RTR4) && orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR4) { atomic_inc(&bat_priv->mcast.num_want_all_rtr4); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(!hlist_unhashed(node)); hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag unset to set */ } else if (mcast_flags & BATADV_MCAST_WANT_NO_RTR4 && !(orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR4)) { atomic_dec(&bat_priv->mcast.num_want_all_rtr4); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(hlist_unhashed(node)); hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } /** * batadv_mcast_want_rtr6_update() - update want-all-rtr6 counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of * @mcast_flags: flags indicating the new multicast state * * If the BATADV_MCAST_WANT_NO_RTR6 flag of this originator, orig, has * toggled then this method updates the counter and the list accordingly. * * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_rtr6_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 mcast_flags) { struct hlist_node *node = &orig->mcast_want_all_rtr6_node; struct hlist_head *head = &bat_priv->mcast.want_all_rtr6_list; lockdep_assert_held(&orig->mcast_handler_lock); /* switched from flag set to unset */ if (!(mcast_flags & BATADV_MCAST_WANT_NO_RTR6) && orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR6) { atomic_inc(&bat_priv->mcast.num_want_all_rtr6); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(!hlist_unhashed(node)); hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag unset to set */ } else if (mcast_flags & BATADV_MCAST_WANT_NO_RTR6 && !(orig->mcast_flags & BATADV_MCAST_WANT_NO_RTR6)) { atomic_dec(&bat_priv->mcast.num_want_all_rtr6); spin_lock_bh(&bat_priv->mcast.want_lists_lock); /* flag checks above + mcast_handler_lock prevents this */ WARN_ON(hlist_unhashed(node)); hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } /** * batadv_mcast_tvlv_flags_get() - get multicast flags from an OGM TVLV * @enabled: whether the originator has multicast TVLV support enabled * @tvlv_value: tvlv buffer containing the multicast flags * @tvlv_value_len: tvlv buffer length * * Return: multicast flags for the given tvlv buffer */ static u8 batadv_mcast_tvlv_flags_get(bool enabled, void *tvlv_value, u16 tvlv_value_len) { u8 mcast_flags = BATADV_NO_FLAGS; if (enabled && tvlv_value && tvlv_value_len >= sizeof(mcast_flags)) mcast_flags = *(u8 *)tvlv_value; if (!enabled) { mcast_flags |= BATADV_MCAST_WANT_ALL_IPV4; mcast_flags |= BATADV_MCAST_WANT_ALL_IPV6; } /* remove redundant flags to avoid sending duplicate packets later */ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) mcast_flags |= BATADV_MCAST_WANT_NO_RTR4; if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) mcast_flags |= BATADV_MCAST_WANT_NO_RTR6; return mcast_flags; } /** * batadv_mcast_tvlv_ogm_handler() - process incoming multicast tvlv container * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node of the ogm * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags) * @tvlv_value: tvlv buffer containing the multicast data * @tvlv_value_len: tvlv buffer length */ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 flags, void *tvlv_value, u16 tvlv_value_len) { bool orig_mcast_enabled = !(flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND); u8 mcast_flags; mcast_flags = batadv_mcast_tvlv_flags_get(orig_mcast_enabled, tvlv_value, tvlv_value_len); spin_lock_bh(&orig->mcast_handler_lock); if (orig_mcast_enabled && !test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities)) { set_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities); } else if (!orig_mcast_enabled && test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities)) { clear_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities); } set_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capa_initialized); batadv_mcast_want_unsnoop_update(bat_priv, orig, mcast_flags); batadv_mcast_want_ipv4_update(bat_priv, orig, mcast_flags); batadv_mcast_want_ipv6_update(bat_priv, orig, mcast_flags); batadv_mcast_want_rtr4_update(bat_priv, orig, mcast_flags); batadv_mcast_want_rtr6_update(bat_priv, orig, mcast_flags); orig->mcast_flags = mcast_flags; spin_unlock_bh(&orig->mcast_handler_lock); } /** * batadv_mcast_init() - initialize the multicast optimizations structures * @bat_priv: the bat priv with all the soft interface information */ void batadv_mcast_init(struct batadv_priv *bat_priv) { batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler, NULL, BATADV_TVLV_MCAST, 2, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); INIT_DELAYED_WORK(&bat_priv->mcast.work, batadv_mcast_mla_update); batadv_mcast_start_timer(bat_priv); } /** * batadv_mcast_mesh_info_put() - put multicast info into a netlink message * @msg: buffer for the message * @bat_priv: the bat priv with all the soft interface information * * Return: 0 or error code. */ int batadv_mcast_mesh_info_put(struct sk_buff *msg, struct batadv_priv *bat_priv) { u32 flags = bat_priv->mcast.mla_flags.tvlv_flags; u32 flags_priv = BATADV_NO_FLAGS; if (bat_priv->mcast.mla_flags.bridged) { flags_priv |= BATADV_MCAST_FLAGS_BRIDGED; if (bat_priv->mcast.mla_flags.querier_ipv4.exists) flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV4_EXISTS; if (bat_priv->mcast.mla_flags.querier_ipv6.exists) flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV6_EXISTS; if (bat_priv->mcast.mla_flags.querier_ipv4.shadowing) flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV4_SHADOWING; if (bat_priv->mcast.mla_flags.querier_ipv6.shadowing) flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV6_SHADOWING; } if (nla_put_u32(msg, BATADV_ATTR_MCAST_FLAGS, flags) || nla_put_u32(msg, BATADV_ATTR_MCAST_FLAGS_PRIV, flags_priv)) return -EMSGSIZE; return 0; } /** * batadv_mcast_flags_dump_entry() - dump one entry of the multicast flags table * to a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @orig_node: originator to dump the multicast flags of * * Return: 0 or error code. */ static int batadv_mcast_flags_dump_entry(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_orig_node *orig_node) { void *hdr; hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_MCAST_FLAGS); if (!hdr) return -ENOBUFS; genl_dump_check_consistent(cb, hdr); if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, orig_node->orig)) { genlmsg_cancel(msg, hdr); return -EMSGSIZE; } if (test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig_node->capabilities)) { if (nla_put_u32(msg, BATADV_ATTR_MCAST_FLAGS, orig_node->mcast_flags)) { genlmsg_cancel(msg, hdr); return -EMSGSIZE; } } genlmsg_end(msg, hdr); return 0; } /** * batadv_mcast_flags_dump_bucket() - dump one bucket of the multicast flags * table to a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @hash: hash to dump * @bucket: bucket index to dump * @idx_skip: How many entries to skip * * Return: 0 or error code. */ static int batadv_mcast_flags_dump_bucket(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hashtable *hash, unsigned int bucket, long *idx_skip) { struct batadv_orig_node *orig_node; long idx = 0; spin_lock_bh(&hash->list_locks[bucket]); cb->seq = atomic_read(&hash->generation) << 1 | 1; hlist_for_each_entry(orig_node, &hash->table[bucket], hash_entry) { if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig_node->capa_initialized)) continue; if (idx < *idx_skip) goto skip; if (batadv_mcast_flags_dump_entry(msg, portid, cb, orig_node)) { spin_unlock_bh(&hash->list_locks[bucket]); *idx_skip = idx; return -EMSGSIZE; } skip: idx++; } spin_unlock_bh(&hash->list_locks[bucket]); return 0; } /** * __batadv_mcast_flags_dump() - dump multicast flags table to a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @bat_priv: the bat priv with all the soft interface information * @bucket: current bucket to dump * @idx: index in current bucket to the next entry to dump * * Return: 0 or error code. */ static int __batadv_mcast_flags_dump(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_priv *bat_priv, long *bucket, long *idx) { struct batadv_hashtable *hash = bat_priv->orig_hash; long bucket_tmp = *bucket; long idx_tmp = *idx; while (bucket_tmp < hash->size) { if (batadv_mcast_flags_dump_bucket(msg, portid, cb, hash, bucket_tmp, &idx_tmp)) break; bucket_tmp++; idx_tmp = 0; } *bucket = bucket_tmp; *idx = idx_tmp; return msg->len; } /** * batadv_mcast_netlink_get_primary() - get primary interface from netlink * callback * @cb: netlink callback structure * @primary_if: the primary interface pointer to return the result in * * Return: 0 or error code. */ static int batadv_mcast_netlink_get_primary(struct netlink_callback *cb, struct batadv_hard_iface **primary_if) { struct batadv_hard_iface *hard_iface = NULL; struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_priv *bat_priv; int ifindex; int ret = 0; ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); if (!ifindex) return -EINVAL; soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { ret = -ENODEV; goto out; } bat_priv = netdev_priv(soft_iface); hard_iface = batadv_primary_if_get_selected(bat_priv); if (!hard_iface || hard_iface->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out; } out: dev_put(soft_iface); if (!ret && primary_if) *primary_if = hard_iface; else batadv_hardif_put(hard_iface); return ret; } /** * batadv_mcast_flags_dump() - dump multicast flags table to a netlink socket * @msg: buffer for the message * @cb: callback structure containing arguments * * Return: message length. */ int batadv_mcast_flags_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; int portid = NETLINK_CB(cb->skb).portid; struct batadv_priv *bat_priv; long *bucket = &cb->args[0]; long *idx = &cb->args[1]; int ret; ret = batadv_mcast_netlink_get_primary(cb, &primary_if); if (ret) return ret; bat_priv = netdev_priv(primary_if->soft_iface); ret = __batadv_mcast_flags_dump(msg, portid, cb, bat_priv, bucket, idx); batadv_hardif_put(primary_if); return ret; } /** * batadv_mcast_free() - free the multicast optimizations structures * @bat_priv: the bat priv with all the soft interface information */ void batadv_mcast_free(struct batadv_priv *bat_priv) { cancel_delayed_work_sync(&bat_priv->mcast.work); batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 2); batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 2); /* safely calling outside of worker, as worker was canceled above */ batadv_mcast_mla_tt_retract(bat_priv, NULL); } /** * batadv_mcast_purge_orig() - reset originator global mcast state modifications * @orig: the originator which is going to get purged */ void batadv_mcast_purge_orig(struct batadv_orig_node *orig) { struct batadv_priv *bat_priv = orig->bat_priv; spin_lock_bh(&orig->mcast_handler_lock); batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS); batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS); batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS); batadv_mcast_want_rtr4_update(bat_priv, orig, BATADV_MCAST_WANT_NO_RTR4); batadv_mcast_want_rtr6_update(bat_priv, orig, BATADV_MCAST_WANT_NO_RTR6); spin_unlock_bh(&orig->mcast_handler_lock); } |
| 5 40 75 75 75 75 22 53 129 5 124 124 123 119 5 5 5 5 5 5 99 92 14 78 2 12 27 27 27 27 27 27 385 369 17 17 16 17 136 123 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * lwtunnel Infrastructure for light weight tunnels like mpls * * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com> */ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/lwtunnel.h> #include <linux/in.h> #include <linux/init.h> #include <linux/err.h> #include <net/lwtunnel.h> #include <net/rtnetlink.h> #include <net/ip6_fib.h> #include <net/rtnh.h> DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled); EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled); #ifdef CONFIG_MODULES static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) { /* Only lwt encaps implemented without using an interface for * the encap need to return a string here. */ switch (encap_type) { case LWTUNNEL_ENCAP_MPLS: return "MPLS"; case LWTUNNEL_ENCAP_ILA: return "ILA"; case LWTUNNEL_ENCAP_SEG6: return "SEG6"; case LWTUNNEL_ENCAP_BPF: return "BPF"; case LWTUNNEL_ENCAP_SEG6_LOCAL: return "SEG6LOCAL"; case LWTUNNEL_ENCAP_RPL: return "RPL"; case LWTUNNEL_ENCAP_IOAM6: return "IOAM6"; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: case LWTUNNEL_ENCAP_NONE: case __LWTUNNEL_ENCAP_MAX: /* should not have got here */ WARN_ON(1); break; } return NULL; } #endif /* CONFIG_MODULES */ struct lwtunnel_state *lwtunnel_state_alloc(int encap_len) { struct lwtunnel_state *lws; lws = kzalloc(sizeof(*lws) + encap_len, GFP_ATOMIC); return lws; } EXPORT_SYMBOL_GPL(lwtunnel_state_alloc); static const struct lwtunnel_encap_ops __rcu * lwtun_encaps[LWTUNNEL_ENCAP_MAX + 1] __read_mostly; int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *ops, unsigned int num) { if (num > LWTUNNEL_ENCAP_MAX) return -ERANGE; return !cmpxchg((const struct lwtunnel_encap_ops **) &lwtun_encaps[num], NULL, ops) ? 0 : -1; } EXPORT_SYMBOL_GPL(lwtunnel_encap_add_ops); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops, unsigned int encap_type) { int ret; if (encap_type == LWTUNNEL_ENCAP_NONE || encap_type > LWTUNNEL_ENCAP_MAX) return -ERANGE; ret = (cmpxchg((const struct lwtunnel_encap_ops **) &lwtun_encaps[encap_type], ops, NULL) == ops) ? 0 : -1; synchronize_net(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_encap_del_ops); int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; bool found = false; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || encap_type > LWTUNNEL_ENCAP_MAX) { NL_SET_ERR_MSG_ATTR(extack, encap, "Unknown LWT encapsulation type"); return ret; } ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); if (likely(ops && ops->build_state && try_module_get(ops->owner))) found = true; rcu_read_unlock(); if (found) { ret = ops->build_state(net, encap, family, cfg, lws, extack); if (ret) module_put(ops->owner); } else { /* don't rely on -EOPNOTSUPP to detect match as build_state * handlers could return it */ NL_SET_ERR_MSG_ATTR(extack, encap, "LWT encapsulation type not supported"); } return ret; } EXPORT_SYMBOL_GPL(lwtunnel_build_state); int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || encap_type > LWTUNNEL_ENCAP_MAX) { NL_SET_ERR_MSG(extack, "Unknown lwt encapsulation type"); return ret; } rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); rcu_read_unlock(); #ifdef CONFIG_MODULES if (!ops) { const char *encap_type_str = lwtunnel_encap_str(encap_type); if (encap_type_str) { __rtnl_unlock(); request_module("rtnl-lwt-%s", encap_type_str); rtnl_lock(); rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); rcu_read_unlock(); } } #endif ret = ops ? 0 : -EOPNOTSUPP; if (ret < 0) NL_SET_ERR_MSG(extack, "lwt encapsulation type not supported"); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, struct netlink_ext_ack *extack) { struct rtnexthop *rtnh = (struct rtnexthop *)attr; struct nlattr *nla_entype; struct nlattr *attrs; u16 encap_type; int attrlen; while (rtnh_ok(rtnh, remaining)) { attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { attrs = rtnh_attrs(rtnh); nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla_entype) { if (nla_len(nla_entype) < sizeof(u16)) { NL_SET_ERR_MSG(extack, "Invalid RTA_ENCAP_TYPE"); return -EINVAL; } encap_type = nla_get_u16(nla_entype); if (lwtunnel_valid_encap_type(encap_type, extack) != 0) return -EOPNOTSUPP; } } rtnh = rtnh_next(rtnh, &remaining); } return 0; } EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type_attr); void lwtstate_free(struct lwtunnel_state *lws) { const struct lwtunnel_encap_ops *ops = lwtun_encaps[lws->type]; if (ops->destroy_state) { ops->destroy_state(lws); kfree_rcu(lws, rcu); } else { kfree(lws); } module_put(ops->owner); } EXPORT_SYMBOL_GPL(lwtstate_free); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr) { const struct lwtunnel_encap_ops *ops; struct nlattr *nest; int ret; if (!lwtstate) return 0; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; nest = nla_nest_start_noflag(skb, encap_attr); if (!nest) return -EMSGSIZE; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->fill_encap)) ret = ops->fill_encap(skb, lwtstate); rcu_read_unlock(); if (ret) goto nla_put_failure; nla_nest_end(skb, nest); ret = nla_put_u16(skb, encap_type_attr, lwtstate->type); if (ret) goto nla_put_failure; return 0; nla_put_failure: nla_nest_cancel(skb, nest); return (ret == -EOPNOTSUPP ? 0 : ret); } EXPORT_SYMBOL_GPL(lwtunnel_fill_encap); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) { const struct lwtunnel_encap_ops *ops; int ret = 0; if (!lwtstate) return 0; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->get_encap_size)) ret = nla_total_size(ops->get_encap_size(lwtstate)); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_get_encap_size); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) { const struct lwtunnel_encap_ops *ops; int ret = 0; if (!a && !b) return 0; if (!a || !b) return 1; if (a->type != b->type) return 1; if (a->type == LWTUNNEL_ENCAP_NONE || a->type > LWTUNNEL_ENCAP_MAX) return 0; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[a->type]); if (likely(ops && ops->cmp_encap)) ret = ops->cmp_encap(a, b); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_cmp_encap); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; int ret = -EINVAL; if (!dst) goto drop; lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->output)) ret = ops->output(net, sk, skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; return ret; drop: kfree_skb(skb); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_output); int lwtunnel_xmit(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; int ret = -EINVAL; if (!dst) goto drop; lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->xmit)) ret = ops->xmit(skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; return ret; drop: kfree_skb(skb); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_xmit); int lwtunnel_input(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; int ret = -EINVAL; if (!dst) goto drop; lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->input)) ret = ops->input(skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; return ret; drop: kfree_skb(skb); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_input); |
| 2 2 1 5 5 2 3 8 2 6 3 2 1 1 4 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2017 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/if.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/kernel.h> #include <linux/openvswitch.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <linux/swap.h> #include <net/netlink.h> #include <net/genetlink.h> #include "datapath.h" #include "meter.h" static const struct nla_policy meter_policy[OVS_METER_ATTR_MAX + 1] = { [OVS_METER_ATTR_ID] = { .type = NLA_U32, }, [OVS_METER_ATTR_KBPS] = { .type = NLA_FLAG }, [OVS_METER_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) }, [OVS_METER_ATTR_BANDS] = { .type = NLA_NESTED }, [OVS_METER_ATTR_USED] = { .type = NLA_U64 }, [OVS_METER_ATTR_CLEAR] = { .type = NLA_FLAG }, [OVS_METER_ATTR_MAX_METERS] = { .type = NLA_U32 }, [OVS_METER_ATTR_MAX_BANDS] = { .type = NLA_U32 }, }; static const struct nla_policy band_policy[OVS_BAND_ATTR_MAX + 1] = { [OVS_BAND_ATTR_TYPE] = { .type = NLA_U32, }, [OVS_BAND_ATTR_RATE] = { .type = NLA_U32, }, [OVS_BAND_ATTR_BURST] = { .type = NLA_U32, }, [OVS_BAND_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) }, }; static u32 meter_hash(struct dp_meter_instance *ti, u32 id) { return id % ti->n_meters; } static void ovs_meter_free(struct dp_meter *meter) { if (!meter) return; kfree_rcu(meter, rcu); } /* Call with ovs_mutex or RCU read lock. */ static struct dp_meter *lookup_meter(const struct dp_meter_table *tbl, u32 meter_id) { struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti); u32 hash = meter_hash(ti, meter_id); struct dp_meter *meter; meter = rcu_dereference_ovsl(ti->dp_meters[hash]); if (meter && likely(meter->id == meter_id)) return meter; return NULL; } static struct dp_meter_instance *dp_meter_instance_alloc(const u32 size) { struct dp_meter_instance *ti; ti = kvzalloc(sizeof(*ti) + sizeof(struct dp_meter *) * size, GFP_KERNEL); if (!ti) return NULL; ti->n_meters = size; return ti; } static void dp_meter_instance_free(struct dp_meter_instance *ti) { kvfree(ti); } static void dp_meter_instance_free_rcu(struct rcu_head *rcu) { struct dp_meter_instance *ti; ti = container_of(rcu, struct dp_meter_instance, rcu); kvfree(ti); } static int dp_meter_instance_realloc(struct dp_meter_table *tbl, u32 size) { struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti); int n_meters = min(size, ti->n_meters); struct dp_meter_instance *new_ti; int i; new_ti = dp_meter_instance_alloc(size); if (!new_ti) return -ENOMEM; for (i = 0; i < n_meters; i++) if (rcu_dereference_ovsl(ti->dp_meters[i])) new_ti->dp_meters[i] = ti->dp_meters[i]; rcu_assign_pointer(tbl->ti, new_ti); call_rcu(&ti->rcu, dp_meter_instance_free_rcu); return 0; } static void dp_meter_instance_insert(struct dp_meter_instance *ti, struct dp_meter *meter) { u32 hash; hash = meter_hash(ti, meter->id); rcu_assign_pointer(ti->dp_meters[hash], meter); } static void dp_meter_instance_remove(struct dp_meter_instance *ti, struct dp_meter *meter) { u32 hash; hash = meter_hash(ti, meter->id); RCU_INIT_POINTER(ti->dp_meters[hash], NULL); } static int attach_meter(struct dp_meter_table *tbl, struct dp_meter *meter) { struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti); u32 hash = meter_hash(ti, meter->id); int err; /* In generally, slots selected should be empty, because * OvS uses id-pool to fetch a available id. */ if (unlikely(rcu_dereference_ovsl(ti->dp_meters[hash]))) return -EBUSY; dp_meter_instance_insert(ti, meter); /* That function is thread-safe. */ tbl->count++; if (tbl->count >= tbl->max_meters_allowed) { err = -EFBIG; goto attach_err; } if (tbl->count >= ti->n_meters && dp_meter_instance_realloc(tbl, ti->n_meters * 2)) { err = -ENOMEM; goto attach_err; } return 0; attach_err: dp_meter_instance_remove(ti, meter); tbl->count--; return err; } static int detach_meter(struct dp_meter_table *tbl, struct dp_meter *meter) { struct dp_meter_instance *ti; ASSERT_OVSL(); if (!meter) return 0; ti = rcu_dereference_ovsl(tbl->ti); dp_meter_instance_remove(ti, meter); tbl->count--; /* Shrink the meter array if necessary. */ if (ti->n_meters > DP_METER_ARRAY_SIZE_MIN && tbl->count <= (ti->n_meters / 4)) { int half_size = ti->n_meters / 2; int i; /* Avoid hash collision, don't move slots to other place. * Make sure there are no references of meters in array * which will be released. */ for (i = half_size; i < ti->n_meters; i++) if (rcu_dereference_ovsl(ti->dp_meters[i])) goto out; if (dp_meter_instance_realloc(tbl, half_size)) goto shrink_err; } out: return 0; shrink_err: dp_meter_instance_insert(ti, meter); tbl->count++; return -ENOMEM; } static struct sk_buff * ovs_meter_cmd_reply_start(struct genl_info *info, u8 cmd, struct ovs_header **ovs_reply_header) { struct sk_buff *skb; struct ovs_header *ovs_header = info->userhdr; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return ERR_PTR(-ENOMEM); *ovs_reply_header = genlmsg_put(skb, info->snd_portid, info->snd_seq, &dp_meter_genl_family, 0, cmd); if (!*ovs_reply_header) { nlmsg_free(skb); return ERR_PTR(-EMSGSIZE); } (*ovs_reply_header)->dp_ifindex = ovs_header->dp_ifindex; return skb; } static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id, struct dp_meter *meter) { struct nlattr *nla; struct dp_meter_band *band; u16 i; if (nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id)) goto error; if (nla_put(reply, OVS_METER_ATTR_STATS, sizeof(struct ovs_flow_stats), &meter->stats)) goto error; if (nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used, OVS_METER_ATTR_PAD)) goto error; nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS); if (!nla) goto error; band = meter->bands; for (i = 0; i < meter->n_bands; ++i, ++band) { struct nlattr *band_nla; band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC); if (!band_nla || nla_put(reply, OVS_BAND_ATTR_STATS, sizeof(struct ovs_flow_stats), &band->stats)) goto error; nla_nest_end(reply, band_nla); } nla_nest_end(reply, nla); return 0; error: return -EMSGSIZE; } static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info) { struct ovs_header *ovs_header = info->userhdr; struct ovs_header *ovs_reply_header; struct nlattr *nla, *band_nla; struct sk_buff *reply; struct datapath *dp; int err = -EMSGSIZE; reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_FEATURES, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply); ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { err = -ENODEV; goto exit_unlock; } if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS, dp->meter_tbl.max_meters_allowed)) goto exit_unlock; ovs_unlock(); if (nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS)) goto nla_put_failure; nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS); if (!nla) goto nla_put_failure; band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC); if (!band_nla) goto nla_put_failure; /* Currently only DROP band type is supported. */ if (nla_put_u32(reply, OVS_BAND_ATTR_TYPE, OVS_METER_BAND_TYPE_DROP)) goto nla_put_failure; nla_nest_end(reply, band_nla); nla_nest_end(reply, nla); genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_unlock: ovs_unlock(); nla_put_failure: nlmsg_free(reply); return err; } static struct dp_meter *dp_meter_create(struct nlattr **a) { struct nlattr *nla; int rem; u16 n_bands = 0; struct dp_meter *meter; struct dp_meter_band *band; int err; /* Validate attributes, count the bands. */ if (!a[OVS_METER_ATTR_BANDS]) return ERR_PTR(-EINVAL); nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem) if (++n_bands > DP_MAX_BANDS) return ERR_PTR(-EINVAL); /* Allocate and set up the meter before locking anything. */ meter = kzalloc(struct_size(meter, bands, n_bands), GFP_KERNEL); if (!meter) return ERR_PTR(-ENOMEM); meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]); meter->used = div_u64(ktime_get_ns(), 1000 * 1000); meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0; meter->keep_stats = !a[OVS_METER_ATTR_CLEAR]; spin_lock_init(&meter->lock); if (meter->keep_stats && a[OVS_METER_ATTR_STATS]) { meter->stats = *(struct ovs_flow_stats *) nla_data(a[OVS_METER_ATTR_STATS]); } meter->n_bands = n_bands; /* Set up meter bands. */ band = meter->bands; nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem) { struct nlattr *attr[OVS_BAND_ATTR_MAX + 1]; u32 band_max_delta_t; err = nla_parse_deprecated((struct nlattr **)&attr, OVS_BAND_ATTR_MAX, nla_data(nla), nla_len(nla), band_policy, NULL); if (err) goto exit_free_meter; if (!attr[OVS_BAND_ATTR_TYPE] || !attr[OVS_BAND_ATTR_RATE] || !attr[OVS_BAND_ATTR_BURST]) { err = -EINVAL; goto exit_free_meter; } band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]); band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]); if (band->rate == 0) { err = -EINVAL; goto exit_free_meter; } band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]); /* Figure out max delta_t that is enough to fill any bucket. * Keep max_delta_t size to the bucket units: * pkts => 1/1000 packets, kilobits => bits. * * Start with a full bucket. */ band->bucket = band->burst_size * 1000ULL; band_max_delta_t = div_u64(band->bucket, band->rate); if (band_max_delta_t > meter->max_delta_t) meter->max_delta_t = band_max_delta_t; band++; } return meter; exit_free_meter: kfree(meter); return ERR_PTR(err); } static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct dp_meter *meter, *old_meter; struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_header *ovs_header = info->userhdr; struct dp_meter_table *meter_tbl; struct datapath *dp; int err; u32 meter_id; bool failed; if (!a[OVS_METER_ATTR_ID]) return -EINVAL; meter = dp_meter_create(a); if (IS_ERR(meter)) return PTR_ERR(meter); reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET, &ovs_reply_header); if (IS_ERR(reply)) { err = PTR_ERR(reply); goto exit_free_meter; } ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { err = -ENODEV; goto exit_unlock; } meter_tbl = &dp->meter_tbl; meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); old_meter = lookup_meter(meter_tbl, meter_id); err = detach_meter(meter_tbl, old_meter); if (err) goto exit_unlock; err = attach_meter(meter_tbl, meter); if (err) goto exit_free_old_meter; ovs_unlock(); /* Build response with the meter_id and stats from * the old meter, if any. */ failed = nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id); WARN_ON(failed); if (old_meter) { spin_lock_bh(&old_meter->lock); if (old_meter->keep_stats) { err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter); WARN_ON(err); } spin_unlock_bh(&old_meter->lock); ovs_meter_free(old_meter); } genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_free_old_meter: ovs_meter_free(old_meter); exit_unlock: ovs_unlock(); nlmsg_free(reply); exit_free_meter: kfree(meter); return err; } static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct ovs_header *ovs_header = info->userhdr; struct ovs_header *ovs_reply_header; struct nlattr **a = info->attrs; struct dp_meter *meter; struct sk_buff *reply; struct datapath *dp; u32 meter_id; int err; if (!a[OVS_METER_ATTR_ID]) return -EINVAL; meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_GET, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply); ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { err = -ENODEV; goto exit_unlock; } /* Locate meter, copy stats. */ meter = lookup_meter(&dp->meter_tbl, meter_id); if (!meter) { err = -ENOENT; goto exit_unlock; } spin_lock_bh(&meter->lock); err = ovs_meter_cmd_reply_stats(reply, meter_id, meter); spin_unlock_bh(&meter->lock); if (err) goto exit_unlock; ovs_unlock(); genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_unlock: ovs_unlock(); nlmsg_free(reply); return err; } static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info) { struct ovs_header *ovs_header = info->userhdr; struct ovs_header *ovs_reply_header; struct nlattr **a = info->attrs; struct dp_meter *old_meter; struct sk_buff *reply; struct datapath *dp; u32 meter_id; int err; if (!a[OVS_METER_ATTR_ID]) return -EINVAL; reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_DEL, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply); ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { err = -ENODEV; goto exit_unlock; } meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); old_meter = lookup_meter(&dp->meter_tbl, meter_id); if (old_meter) { spin_lock_bh(&old_meter->lock); err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter); WARN_ON(err); spin_unlock_bh(&old_meter->lock); err = detach_meter(&dp->meter_tbl, old_meter); if (err) goto exit_unlock; } ovs_unlock(); ovs_meter_free(old_meter); genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_unlock: ovs_unlock(); nlmsg_free(reply); return err; } /* Meter action execution. * * Return true 'meter_id' drop band is triggered. The 'skb' should be * dropped by the caller'. */ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, u32 meter_id) { long long int now_ms = div_u64(ktime_get_ns(), 1000 * 1000); long long int long_delta_ms; struct dp_meter_band *band; struct dp_meter *meter; int i, band_exceeded_max = -1; u32 band_exceeded_rate = 0; u32 delta_ms; u32 cost; meter = lookup_meter(&dp->meter_tbl, meter_id); /* Do not drop the packet when there is no meter. */ if (!meter) return false; /* Lock the meter while using it. */ spin_lock(&meter->lock); long_delta_ms = (now_ms - meter->used); /* ms */ if (long_delta_ms < 0) { /* This condition means that we have several threads fighting * for a meter lock, and the one who received the packets a * bit later wins. Assuming that all racing threads received * packets at the same time to avoid overflow. */ long_delta_ms = 0; } /* Make sure delta_ms will not be too large, so that bucket will not * wrap around below. */ delta_ms = (long_delta_ms > (long long int)meter->max_delta_t) ? meter->max_delta_t : (u32)long_delta_ms; /* Update meter statistics. */ meter->used = now_ms; meter->stats.n_packets += 1; meter->stats.n_bytes += skb->len; /* Bucket rate is either in kilobits per second, or in packets per * second. We maintain the bucket in the units of either bits or * 1/1000th of a packet, correspondingly. * Then, when rate is multiplied with milliseconds, we get the * bucket units: * msec * kbps = bits, and * msec * packets/sec = 1/1000 packets. * * 'cost' is the number of bucket units in this packet. */ cost = (meter->kbps) ? skb->len * 8 : 1000; /* Update all bands and find the one hit with the highest rate. */ for (i = 0; i < meter->n_bands; ++i) { long long int max_bucket_size; band = &meter->bands[i]; max_bucket_size = band->burst_size * 1000LL; band->bucket += delta_ms * band->rate; if (band->bucket > max_bucket_size) band->bucket = max_bucket_size; if (band->bucket >= cost) { band->bucket -= cost; } else if (band->rate > band_exceeded_rate) { band_exceeded_rate = band->rate; band_exceeded_max = i; } } if (band_exceeded_max >= 0) { /* Update band statistics. */ band = &meter->bands[band_exceeded_max]; band->stats.n_packets += 1; band->stats.n_bytes += skb->len; /* Drop band triggered, let the caller drop the 'skb'. */ if (band->type == OVS_METER_BAND_TYPE_DROP) { spin_unlock(&meter->lock); return true; } } spin_unlock(&meter->lock); return false; } static const struct genl_small_ops dp_meter_genl_ops[] = { { .cmd = OVS_METER_CMD_FEATURES, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, /* OK for unprivileged users. */ .doit = ovs_meter_cmd_features }, { .cmd = OVS_METER_CMD_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ .doit = ovs_meter_cmd_set, }, { .cmd = OVS_METER_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, /* OK for unprivileged users. */ .doit = ovs_meter_cmd_get, }, { .cmd = OVS_METER_CMD_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ .doit = ovs_meter_cmd_del }, }; static const struct genl_multicast_group ovs_meter_multicast_group = { .name = OVS_METER_MCGROUP, }; struct genl_family dp_meter_genl_family __ro_after_init = { .hdrsize = sizeof(struct ovs_header), .name = OVS_METER_FAMILY, .version = OVS_METER_VERSION, .maxattr = OVS_METER_ATTR_MAX, .policy = meter_policy, .netnsok = true, .parallel_ops = true, .small_ops = dp_meter_genl_ops, .n_small_ops = ARRAY_SIZE(dp_meter_genl_ops), .mcgrps = &ovs_meter_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, }; int ovs_meters_init(struct datapath *dp) { struct dp_meter_table *tbl = &dp->meter_tbl; struct dp_meter_instance *ti; unsigned long free_mem_bytes; ti = dp_meter_instance_alloc(DP_METER_ARRAY_SIZE_MIN); if (!ti) return -ENOMEM; /* Allow meters in a datapath to use ~3.12% of physical memory. */ free_mem_bytes = nr_free_buffer_pages() * (PAGE_SIZE >> 5); tbl->max_meters_allowed = min(free_mem_bytes / sizeof(struct dp_meter), DP_METER_NUM_MAX); if (!tbl->max_meters_allowed) goto out_err; rcu_assign_pointer(tbl->ti, ti); tbl->count = 0; return 0; out_err: dp_meter_instance_free(ti); return -ENOMEM; } void ovs_meters_exit(struct datapath *dp) { struct dp_meter_table *tbl = &dp->meter_tbl; struct dp_meter_instance *ti = rcu_dereference_raw(tbl->ti); int i; for (i = 0; i < ti->n_meters; i++) ovs_meter_free(rcu_dereference_raw(ti->dp_meters[i])); dp_meter_instance_free(ti); } |
| 72 72 72 71 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2020 Facebook * Copyright 2020 Google LLC. */ #include <linux/pid.h> #include <linux/sched.h> #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/bpf_local_storage.h> #include <linux/filter.h> #include <uapi/linux/btf.h> #include <linux/btf_ids.h> #include <linux/fdtable.h> DEFINE_BPF_STORAGE_CACHE(task_cache); static DEFINE_PER_CPU(int, bpf_task_storage_busy); static void bpf_task_storage_lock(void) { migrate_disable(); this_cpu_inc(bpf_task_storage_busy); } static void bpf_task_storage_unlock(void) { this_cpu_dec(bpf_task_storage_busy); migrate_enable(); } static bool bpf_task_storage_trylock(void) { migrate_disable(); if (unlikely(this_cpu_inc_return(bpf_task_storage_busy) != 1)) { this_cpu_dec(bpf_task_storage_busy); migrate_enable(); return false; } return true; } static struct bpf_local_storage __rcu **task_storage_ptr(void *owner) { struct task_struct *task = owner; return &task->bpf_storage; } static struct bpf_local_storage_data * task_storage_lookup(struct task_struct *task, struct bpf_map *map, bool cacheit_lockit) { struct bpf_local_storage *task_storage; struct bpf_local_storage_map *smap; task_storage = rcu_dereference(task->bpf_storage); if (!task_storage) return NULL; smap = (struct bpf_local_storage_map *)map; return bpf_local_storage_lookup(task_storage, smap, cacheit_lockit); } void bpf_task_storage_free(struct task_struct *task) { struct bpf_local_storage_elem *selem; struct bpf_local_storage *local_storage; bool free_task_storage = false; struct hlist_node *n; unsigned long flags; rcu_read_lock(); local_storage = rcu_dereference(task->bpf_storage); if (!local_storage) { rcu_read_unlock(); return; } /* Neither the bpf_prog nor the bpf-map's syscall * could be modifying the local_storage->list now. * Thus, no elem can be added-to or deleted-from the * local_storage->list by the bpf_prog or by the bpf-map's syscall. * * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the local_storage->list and * the map's bucket->list. */ bpf_task_storage_lock(); raw_spin_lock_irqsave(&local_storage->lock, flags); hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { /* Always unlink from map before unlinking from * local_storage. */ bpf_selem_unlink_map(selem); free_task_storage = bpf_selem_unlink_storage_nolock( local_storage, selem, false); } raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_task_storage_unlock(); rcu_read_unlock(); /* free_task_storage should always be true as long as * local_storage->list was non-empty. */ if (free_task_storage) kfree_rcu(local_storage, rcu); } static void *bpf_pid_task_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; struct task_struct *task; unsigned int f_flags; struct pid *pid; int fd, err; fd = *(int *)key; pid = pidfd_get_pid(fd, &f_flags); if (IS_ERR(pid)) return ERR_CAST(pid); /* We should be in an RCU read side critical section, it should be safe * to call pid_task. */ WARN_ON_ONCE(!rcu_read_lock_held()); task = pid_task(pid, PIDTYPE_PID); if (!task) { err = -ENOENT; goto out; } bpf_task_storage_lock(); sdata = task_storage_lookup(task, map, true); bpf_task_storage_unlock(); put_pid(pid); return sdata ? sdata->data : NULL; out: put_pid(pid); return ERR_PTR(err); } static int bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct task_struct *task; unsigned int f_flags; struct pid *pid; int fd, err; fd = *(int *)key; pid = pidfd_get_pid(fd, &f_flags); if (IS_ERR(pid)) return PTR_ERR(pid); /* We should be in an RCU read side critical section, it should be safe * to call pid_task. */ WARN_ON_ONCE(!rcu_read_lock_held()); task = pid_task(pid, PIDTYPE_PID); if (!task) { err = -ENOENT; goto out; } bpf_task_storage_lock(); sdata = bpf_local_storage_update( task, (struct bpf_local_storage_map *)map, value, map_flags); bpf_task_storage_unlock(); err = PTR_ERR_OR_ZERO(sdata); out: put_pid(pid); return err; } static int task_storage_delete(struct task_struct *task, struct bpf_map *map) { struct bpf_local_storage_data *sdata; sdata = task_storage_lookup(task, map, false); if (!sdata) return -ENOENT; bpf_selem_unlink(SELEM(sdata)); return 0; } static int bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key) { struct task_struct *task; unsigned int f_flags; struct pid *pid; int fd, err; fd = *(int *)key; pid = pidfd_get_pid(fd, &f_flags); if (IS_ERR(pid)) return PTR_ERR(pid); /* We should be in an RCU read side critical section, it should be safe * to call pid_task. */ WARN_ON_ONCE(!rcu_read_lock_held()); task = pid_task(pid, PIDTYPE_PID); if (!task) { err = -ENOENT; goto out; } bpf_task_storage_lock(); err = task_storage_delete(task, map); bpf_task_storage_unlock(); out: put_pid(pid); return err; } BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, task, void *, value, u64, flags) { struct bpf_local_storage_data *sdata; if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) return (unsigned long)NULL; if (!task) return (unsigned long)NULL; if (!bpf_task_storage_trylock()) return (unsigned long)NULL; sdata = task_storage_lookup(task, map, true); if (sdata) goto unlock; /* only allocate new storage, when the task is refcounted */ if (refcount_read(&task->usage) && (flags & BPF_LOCAL_STORAGE_GET_F_CREATE)) sdata = bpf_local_storage_update( task, (struct bpf_local_storage_map *)map, value, BPF_NOEXIST); unlock: bpf_task_storage_unlock(); return IS_ERR_OR_NULL(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *, task) { int ret; if (!task) return -EINVAL; if (!bpf_task_storage_trylock()) return -EBUSY; /* This helper must only be called from places where the lifetime of the task * is guaranteed. Either by being refcounted or by being protected * by an RCU read-side critical section. */ ret = task_storage_delete(task, map); bpf_task_storage_unlock(); return ret; } static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr) { struct bpf_local_storage_map *smap; smap = bpf_local_storage_map_alloc(attr); if (IS_ERR(smap)) return ERR_CAST(smap); smap->cache_idx = bpf_local_storage_cache_idx_get(&task_cache); return &smap->map; } static void task_storage_map_free(struct bpf_map *map) { struct bpf_local_storage_map *smap; smap = (struct bpf_local_storage_map *)map; bpf_local_storage_cache_idx_free(&task_cache, smap->cache_idx); bpf_local_storage_map_free(smap, &bpf_task_storage_busy); } static int task_storage_map_btf_id; const struct bpf_map_ops task_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, .map_alloc = task_storage_map_alloc, .map_free = task_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_pid_task_storage_lookup_elem, .map_update_elem = bpf_pid_task_storage_update_elem, .map_delete_elem = bpf_pid_task_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, .map_btf_name = "bpf_local_storage_map", .map_btf_id = &task_storage_map_btf_id, .map_owner_storage_ptr = task_storage_ptr, }; const struct bpf_func_proto bpf_task_storage_get_proto = { .func = bpf_task_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, .arg2_btf_id = &btf_task_struct_ids[0], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_task_storage_delete_proto = { .func = bpf_task_storage_delete, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, .arg2_btf_id = &btf_task_struct_ids[0], }; |
| 334 97 117 20 1 74 113 113 145 632 1499 298 633 632 474 228 261 262 54 27 27 346 262 261 3938 3935 540 95 386 77 78 8 270 270 8 663 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_H #define _LINUX_MM_H #include <linux/errno.h> #ifdef __KERNEL__ #include <linux/mmdebug.h> #include <linux/gfp.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/percpu-refcount.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> #include <linux/resource.h> #include <linux/page_ext.h> #include <linux/err.h> #include <linux/page-flags.h> #include <linux/page_ref.h> #include <linux/memremap.h> #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> #include <linux/pgtable.h> #include <linux/kasan.h> struct mempolicy; struct anon_vma; struct anon_vma_chain; struct file_ra_state; struct user_struct; struct writeback_control; struct bdi_writeback; struct pt_regs; extern int sysctl_page_lock_unfairness; void init_mm_internals(void); #ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; static inline void set_max_mapnr(unsigned long limit) { max_mapnr = limit; } #else static inline void set_max_mapnr(unsigned long limit) { } #endif extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { return (unsigned long)atomic_long_read(&_totalram_pages); } static inline void totalram_pages_inc(void) { atomic_long_inc(&_totalram_pages); } static inline void totalram_pages_dec(void) { atomic_long_dec(&_totalram_pages); } static inline void totalram_pages_add(long count) { atomic_long_add(count, &_totalram_pages); } extern void * high_memory; extern int page_cluster; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else #define sysctl_legacy_va_layout 0 #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; extern const int mmap_rnd_bits_max; extern int mmap_rnd_bits __read_mostly; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS extern const int mmap_rnd_compat_bits_min; extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif #include <asm/page.h> #include <asm/processor.h> /* * Architectures that support memory tagging (assigning tags to memory regions, * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. * It's defined as noop for architectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) #endif #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif #ifndef page_to_virt #define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x))) #endif #ifndef lm_alias #define lm_alias(x) __va(__pa_symbol(x)) #endif /* * To prevent common memory management code establishing * a zero page mapping on a read fault. * This macro should be defined within <asm/pgtable.h>. * s390 does this to prevent multiplexing of hardware bits * related to the physical page in case of virtualization. */ #ifndef mm_forbids_zeropage #define mm_forbids_zeropage(X) (0) #endif /* * On some architectures it is expensive to call memset() for small sizes. * If an architecture decides to implement their own version of * mm_zero_struct_page they should wrap the defines below in a #ifndef and * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 /* This function must be updated when the size of struct page grows above 80 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statements if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) static inline void __mm_zero_struct_page(struct page *page) { unsigned long *_pp = (void *)page; /* Check that struct page is either 56, 64, 72, or 80 bytes */ BUILD_BUG_ON(sizeof(struct page) & 7); BUILD_BUG_ON(sizeof(struct page) < 56); BUILD_BUG_ON(sizeof(struct page) > 80); switch (sizeof(struct page)) { case 80: _pp[9] = 0; fallthrough; case 72: _pp[8] = 0; fallthrough; case 64: _pp[7] = 0; fallthrough; case 56: _pp[6] = 0; _pp[5] = 0; _pp[4] = 0; _pp[3] = 0; _pp[2] = 0; _pp[1] = 0; _pp[0] = 0; } } #else #define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page))) #endif /* * Default maximum number of active map areas, this limits the number of vmas * per mm struct. Users can overwrite this number by sysctl but there is a * problem. * * When a program's coredump is generated as ELF format, a section is created * per a vma. In ELF, the number of sections is represented in unsigned short. * This means the number of sections should be smaller than 65535 at coredump. * Because the kernel adds some informative sections to a image of program at * generating coredump, we need some margin. The number of extra sections is * 1-3 now and depends on arch. We use "5" as safe margin, here. * * ELF extended numbering allows more than 65535 sections, so 16-bit bound is * not a hard limit any more. Although some userspace tools can be surprised by * that. */ #define MAPCOUNT_ELF_CORE_MARGIN (5) #define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, loff_t *); /* * Any attempt to mark this function as static leads to build failure * when CONFIG_DEBUG_INFO_BTF is enabled because __add_to_page_cache_locked() * is referred to by BPF code. This must be visible for error injection. */ int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp, void **shadowp); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) #else #define nth_page(page,n) ((page) + (n)) #endif /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) void setup_initial_init_mm(void *start_code, void *end_code, void *end_data, void *brk); /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way * we have a virtual fs - giving a cleaner interface to the * mm details, and allowing different kinds of memory mappings * (from shared memory to executable loading to arbitrary * mmap() functions). */ struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif /* * vm_flags in vm_area_struct, see mm_types.h. * When changing, update also include/trace/events/mmflags.h */ #define VM_NONE 0x00000000 #define VM_READ 0x00000001 /* currently active flags */ #define VM_WRITE 0x00000002 #define VM_EXEC 0x00000004 #define VM_SHARED 0x00000008 /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ #define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */ #define VM_MAYWRITE 0x00000020 #define VM_MAYEXEC 0x00000040 #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ /* Used by sys_madvise() */ #define VM_SEQ_READ 0x00008000 /* App will access data sequentially */ #define VM_RAND_READ 0x00010000 /* App will not benefit from clustered reads */ #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_SYNC 0x00800000 /* Synchronous page faults */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #ifdef CONFIG_MEM_SOFT_DIRTY # define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */ #else # define VM_SOFTDIRTY 0 #endif #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ #ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS #define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) #define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS # define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 # define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ # define VM_PKEY_BIT1 VM_HIGH_ARCH_1 /* on x86 and 5-bit value on ppc64 */ # define VM_PKEY_BIT2 VM_HIGH_ARCH_2 # define VM_PKEY_BIT3 VM_HIGH_ARCH_3 #ifdef CONFIG_PPC # define VM_PKEY_BIT4 VM_HIGH_ARCH_4 #else # define VM_PKEY_BIT4 0 #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ #elif defined(CONFIG_PPC) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_IA64) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI #elif defined(CONFIG_ARM64) # define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */ # define VM_ARCH_CLEAR VM_ARM64_BTI #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif #if defined(CONFIG_ARM64_MTE) # define VM_MTE VM_HIGH_ARCH_0 /* Use Tagged memory for access control */ # define VM_MTE_ALLOWED VM_HIGH_ARCH_1 /* Tagged memory permitted */ #else # define VM_MTE VM_NONE # define VM_MTE_ALLOWED VM_NONE #endif #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR # define VM_UFFD_MINOR_BIT 37 # define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ # define VM_UFFD_MINOR VM_NONE #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) #define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) /* Common data flag combinations */ #define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \ VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */ #define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC #endif #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif #ifdef CONFIG_STACK_GROWSUP #define VM_STACK VM_GROWSUP #else #define VM_STACK VM_GROWSDOWN #endif #define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) /* VMA basic access permission flags */ #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) /* * Special vmas that are non-mergable, non-mlock()able. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) /* This mask prevents VMA from being scanned with khugepaged */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE /* This mask is used to clear all the VMA flags used by mlock */ #define VM_LOCKED_CLEAR_MASK (~(VM_LOCKED | VM_LOCKONFAULT)) /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR # define VM_ARCH_CLEAR VM_NONE #endif #define VM_FLAGS_CLEAR (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR) /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ extern pgprot_t protection_map[16]; /** * enum fault_flag - Fault flag definitions. * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. * @FAULT_FLAG_TRIED: The fault has been tried once. * @FAULT_FLAG_USER: The fault originated in userspace. * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two * fault flags correctly. Currently there can be three legal combinations: * * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and * this is the first try * * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and * we've already tried at least once * * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry * * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never * be used. Note that page faults can be allowed to retry for multiple times, * in which case we'll have an initial fault with flags (a) then later on * continuous faults with flags (b). We should always try to detect pending * signals before a retry to make sure the continuous page faults can still be * interrupted if necessary. */ enum fault_flag { FAULT_FLAG_WRITE = 1 << 0, FAULT_FLAG_MKWRITE = 1 << 1, FAULT_FLAG_ALLOW_RETRY = 1 << 2, FAULT_FLAG_RETRY_NOWAIT = 1 << 3, FAULT_FLAG_KILLABLE = 1 << 4, FAULT_FLAG_TRIED = 1 << 5, FAULT_FLAG_USER = 1 << 6, FAULT_FLAG_REMOTE = 1 << 7, FAULT_FLAG_INSTRUCTION = 1 << 8, FAULT_FLAG_INTERRUPTIBLE = 1 << 9, }; /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. */ #define FAULT_FLAG_DEFAULT (FAULT_FLAG_ALLOW_RETRY | \ FAULT_FLAG_KILLABLE | \ FAULT_FLAG_INTERRUPTIBLE) /** * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * @flags: Fault flags. * * This is mostly used for places where we want to try to avoid taking * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the * mmap_lock in the first round to avoid potential starvation of other * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. */ static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { return (flags & FAULT_FLAG_ALLOW_RETRY) && (!(flags & FAULT_FLAG_TRIED)); } #define FAULT_FLAG_TRACE \ { FAULT_FLAG_WRITE, "WRITE" }, \ { FAULT_FLAG_MKWRITE, "MKWRITE" }, \ { FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \ { FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \ { FAULT_FLAG_KILLABLE, "KILLABLE" }, \ { FAULT_FLAG_TRIED, "TRIED" }, \ { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } /* * vm_fault is filled by the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * * MM layer fills up gfp_mask for page allocations but fault handler might * alter it if its implementation requires a different allocation context. * * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { const struct { struct vm_area_struct *vma; /* Target VMA */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address */ }; enum fault_flag flags; /* FAULT_FLAG_xxx flags * XXX: should really be 'const' */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ pud_t *pud; /* Pointer to pud entry matching * the 'address' */ union { pte_t orig_pte; /* Value of PTE at the time of fault */ pmd_t orig_pmd; /* Value of PMD at the time of fault, * used by PMD fault only. */ }; struct page *cow_page; /* Page handler may use for COW fault */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by * VM_FAULT_ERROR). */ /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page * table hasn't been allocated. */ spinlock_t *ptl; /* Page table lock. * Protects pte page table if 'pte' * is not NULL, otherwise pmd. */ pgtable_t prealloc_pte; /* Pre-allocated pte page table. * vm_ops->map_pages() sets up a page * table from atomic context. * do_fault_around() pre-allocates * page table to avoid allocation from * atomic context. */ }; /* page entry size for vm->huge_fault() */ enum page_entry_size { PE_SIZE_PTE = 0, PE_SIZE_PMD, PE_SIZE_PUD, }; /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); /* Called any time before splitting to check if it's allowed */ int (*may_split)(struct vm_area_struct *area, unsigned long addr); int (*mremap)(struct vm_area_struct *area); /* * Called by mprotect() to make driver-specific permission * checks before mprotect() is finalised. The VMA must not * be modified. Returns 0 if eprotect() can proceed. */ int (*mprotect)(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long newflags); vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size); vm_fault_t (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ vm_fault_t (*page_mkwrite)(struct vm_fault *vmf); /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs. See also generic_access_phys() for a generic * implementation useful for any iomem mapping. */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); /* Called by the /proc/PID/maps code to ask the vma whether it * has a special name. Returning non-NULL will also cause this * vma to be dumped unconditionally. */ const char *(*name)(struct vm_area_struct *vma); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy * to hold the policy upon return. Caller should pass NULL @new to * remove a policy and fall back to surrounding context--i.e. do not * install a MPOL_DEFAULT policy, nor the task or system default * mempolicy. */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); /* * get_policy() op must add reference [mpol_get()] to any policy at * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); #endif /* * Called by vm_normal_page() for special PTEs to find the * page for @addr. This is useful if the default behavior * (using pte_page()) would not find the correct page. */ struct page *(*find_special_page)(struct vm_area_struct *vma, unsigned long addr); }; static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); } static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; } static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; } static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); if (!maybe_stack) return false; if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == VM_STACK_INCOMPLETE_SETUP) return true; return false; } static inline bool vma_is_foreign(struct vm_area_struct *vma) { if (!current->mm) return true; if (current->mm != vma->vm_mm) return true; return false; } static inline bool vma_is_accessible(struct vm_area_struct *vma) { return vma->vm_flags & VM_ACCESS_FLAGS; } #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow * paths in userfault. */ bool vma_is_shmem(struct vm_area_struct *vma); #else static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } #endif int vma_is_stack_for_current(struct vm_area_struct *vma); /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } struct mmu_gather; struct inode; #include <linux/huge_mm.h> /* * Methods to modify the page usage count. * * What counts for a page usage: * - cache mapping (page->mapping) * - private data (page->private) * - page mapped in a task's page tables, each mapping * is counted separately * * Also, many kernel routines increase the page count before a critical * routine so they can be sure the page doesn't go away from under them. */ /* * Drop a ref, return true if the refcount fell to zero (the page has no users) */ static inline int put_page_testzero(struct page *page) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); return page_ref_dec_and_test(page); } /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. * This can be called when MMU is off so it must not access * any of the virtual mappings. */ static inline int get_page_unless_zero(struct page *page) { return page_ref_add_unless(page, 1, 0); } extern int page_is_ram(unsigned long pfn); enum { REGION_INTERSECTS, REGION_DISJOINT, REGION_MIXED, }; int region_intersects(resource_size_t offset, size_t size, unsigned long flags, unsigned long desc); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); unsigned long vmalloc_to_pfn(const void *addr); /* * Determine if an address is within the vmalloc range * * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ #ifndef is_ioremap_addr #define is_ioremap_addr(x) is_vmalloc_addr(x) #endif #ifdef CONFIG_MMU extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); #else static inline bool is_vmalloc_addr(const void *x) { return false; } static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } #endif extern void *kvmalloc_node(size_t size, gfp_t flags, int node); static inline void *kvmalloc(size_t size, gfp_t flags) { return kvmalloc_node(size, flags, NUMA_NO_NODE); } static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) { return kvmalloc_node(size, flags | __GFP_ZERO, node); } static inline void *kvzalloc(size_t size, gfp_t flags) { return kvmalloc(size, flags | __GFP_ZERO); } static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kvmalloc(bytes, flags); } static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) { return kvmalloc_array(n, size, flags | __GFP_ZERO); } extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags); extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); static inline int head_compound_mapcount(struct page *head) { return atomic_read(compound_mapcount_ptr(head)) + 1; } /* * Mapcount of compound page as a whole, does not include mapped sub-pages. * * Must be called only for compound pages or any their tail sub-pages. */ static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); page = compound_head(page); return head_compound_mapcount(page); } /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). */ static inline void page_mapcount_reset(struct page *page) { atomic_set(&(page)->_mapcount, -1); } int __page_mapcount(struct page *page); /* * Mapcount of 0-order page; when compound sub-page, includes * compound_mapcount(). * * Result is undefined for pages which cannot be mapped into userspace. * For example SLAB or special types of pages. See function page_has_type(). * They use this place in struct page differently. */ static inline int page_mapcount(struct page *page) { if (unlikely(PageCompound(page))) return __page_mapcount(page); return atomic_read(&page->_mapcount) + 1; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int total_mapcount(struct page *page); int page_trans_huge_mapcount(struct page *page, int *total_mapcount); #else static inline int total_mapcount(struct page *page) { return page_mapcount(page); } static inline int page_trans_huge_mapcount(struct page *page, int *total_mapcount) { int mapcount = page_mapcount(page); if (total_mapcount) *total_mapcount = mapcount; return mapcount; } #endif static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); return compound_head(page); } void __put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); void copy_huge_page(struct page *dst, struct page *src); /* * Compound pages have a destructor function. Provide a * prototype for that function and accessor functions. * These are _only_ valid on the head of a compound page. */ typedef void compound_page_dtor(struct page *); /* Keep the enum in sync with compound_page_dtors array in mm/page_alloc.c */ enum compound_dtor_id { NULL_COMPOUND_DTOR, COMPOUND_PAGE_DTOR, #ifdef CONFIG_HUGETLB_PAGE HUGETLB_PAGE_DTOR, #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE TRANSHUGE_PAGE_DTOR, #endif NR_COMPOUND_DTORS, }; extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS]; static inline void set_compound_page_dtor(struct page *page, enum compound_dtor_id compound_dtor) { VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page); page[1].compound_dtor = compound_dtor; } static inline void destroy_compound_page(struct page *page) { VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); compound_page_dtors[page[1].compound_dtor](page); } static inline unsigned int compound_order(struct page *page) { if (!PageHead(page)) return 0; return page[1].compound_order; } static inline bool hpage_pincount_available(struct page *page) { /* * Can the page->hpage_pinned_refcount field be used? That field is in * the 3rd page of the compound page, so the smallest (2-page) compound * pages cannot support it. */ page = compound_head(page); return PageCompound(page) && compound_order(page) > 1; } static inline int head_compound_pincount(struct page *head) { return atomic_read(compound_pincount_ptr(head)); } static inline int compound_pincount(struct page *page) { VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); page = compound_head(page); return head_compound_pincount(page); } static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; page[1].compound_nr = 1U << order; } /* Returns the number of pages in this potentially compound page. */ static inline unsigned long compound_nr(struct page *page) { if (!PageHead(page)) return 1; return page[1].compound_nr; } /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { return PAGE_SIZE << compound_order(page); } /* Returns the number of bits needed for the number of bytes in a page */ static inline unsigned int page_shift(struct page *page) { return PAGE_SHIFT + compound_order(page); } void free_compound_page(struct page *page); #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pte = pte_mkwrite(pte); return pte; } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr); vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of * zeroes, and text pages of executables and shared libraries have * only one copy in memory, at most, normally. * * For the non-reserved pages, page_count(page) denotes a reference count. * page_count() == 0 means the page is free. page->lru is then used for * freelist management in the buddy allocator. * page_count() > 0 means the page has been allocated. * * Pages are allocated by the slab allocator in order to provide memory * to kmalloc and kmem_cache_alloc. In this case, the management of the * page, and the fields in 'struct page' are the responsibility of mm/slab.c * unless a particular usage is carefully commented. (the responsibility of * freeing the kmalloc memory is the caller's, of course). * * A page may be used by anyone else who does a __get_free_page(). * In this case, page_count still tracks the references, and should only * be used through the normal accessor functions. The top bits of page->flags * and page->virtual store page management information, but all other fields * are unused and could be used privately, carefully. The management of this * page is the responsibility of the one who allocated it, and those who have * subsequently been given references to it. * * The other pages (we may call them "pagecache pages") are completely * managed by the Linux memory manager: I/O, buffers, swapping etc. * The following discussion applies only to them. * * A pagecache page contains an opaque `private' member, which belongs to the * page's address_space. Usually, this is the address of a circular list of * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * * A page may belong to an inode's memory mapping. In this case, page->mapping * is the pointer to the inode, and page->index is the file offset of the page, * in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that * case PG_swapcache is set, and page->private is an offset into the swapcache. * * In either case (swapcache or inode backed), the pagecache itself holds one * reference to the page. Setting PG_private should also increment the * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is * rooted at mapping->i_pages, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * * All pagecache pages may be subject to I/O: * - inode pages may need to be read from disk, * - inode pages which have been modified and are MAP_SHARED may need * to be written back to the inode on disk, * - anonymous pages (including MAP_PRIVATE file mappings) which have been * modified may need to be swapped out to swap space and (later) to be read * back into memory. */ /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF)? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF)? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { return false; } #endif static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; } #ifdef CONFIG_DEV_PAGEMAP_OPS void free_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); static inline bool page_is_devmap_managed(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; if (!is_zone_device_page(page)) return false; switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_FS_DAX: return true; default: break; } return false; } void put_devmap_managed_page(struct page *page); #else /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool page_is_devmap_managed(struct page *page) { return false; } static inline void put_devmap_managed_page(struct page *page) { } #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && IS_ENABLED(CONFIG_DEVICE_PRIVATE) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && IS_ENABLED(CONFIG_PCI_P2PDMA) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } /* 127: arbitrary random number, small enough to assemble well */ #define page_ref_zero_or_close_to_overflow(page) \ ((unsigned int) page_ref_count(page) + 127u <= 127u) static inline void get_page(struct page *page) { page = compound_head(page); /* * Getting a normal page or the head of a compound page * requires to already have an elevated page->_refcount. */ VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); page_ref_inc(page); } bool __must_check try_grab_page(struct page *page, unsigned int flags); struct page *try_grab_compound_head(struct page *page, int refs, unsigned int flags); static inline __must_check bool try_get_page(struct page *page) { page = compound_head(page); if (WARN_ON_ONCE(page_ref_count(page) <= 0)) return false; page_ref_inc(page); return true; } static inline void put_page(struct page *page) { page = compound_head(page); /* * For devmap managed pages we need to catch refcount transition from * 2 to 1, when refcount reach one it means the page is free and we * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ if (page_is_devmap_managed(page)) { put_devmap_managed_page(page); return; } if (put_page_testzero(page)) __put_page(page); } /* * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload * the page's refcount so that two separate items are tracked: the original page * reference count, and also a new count of how many pin_user_pages() calls were * made against the page. ("gup-pinned" is another term for the latter). * * With this scheme, pin_user_pages() becomes special: such pages are marked as * distinct from normal pages. As such, the unpin_user_page() call (and its * variants) must be used in order to release gup-pinned pages. * * Choice of value: * * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference * counts with respect to pin_user_pages() and unpin_user_page() becomes * simpler, due to the fact that adding an even power of two to the page * refcount has the effect of using only the upper N bits, for the code that * counts up using the bias value. This means that the lower bits are left for * the exclusive use of the original code that increments and decrements by one * (or at least, by much smaller values than the bias value). * * Of course, once the lower bits overflow into the upper bits (and this is * OK, because subtraction recovers the original values), then visual inspection * no longer suffices to directly view the separate counts. However, for normal * applications that don't have huge page reference counts, this won't be an * issue. * * Locking: the lockless algorithm described in page_cache_get_speculative() * and page_cache_gup_pin_speculative() provides safe operation for * get_user_pages and page_mkclean and other calls that race to set up page * table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) void unpin_user_page(struct page *page); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); /** * page_maybe_dma_pinned - Report if a page is pinned for DMA. * @page: The page. * * This function checks if a page has been pinned via a call to * a function in the pin_user_pages() family. * * For non-huge pages, the return value is partially fuzzy: false is not fuzzy, * because it means "definitely not pinned for DMA", but true means "probably * pinned for DMA, but possibly a false positive due to having at least * GUP_PIN_COUNTING_BIAS worth of normal page references". * * False positives are OK, because: a) it's unlikely for a page to get that many * refcounts, and b) all the callers of this routine are expected to be able to * deal gracefully with a false positive. * * For huge pages, the result will be exactly correct. That's because we have * more tracking data available: the 3rd struct page in the compound page is * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS * scheme). * * For more information, please see Documentation/core-api/pin_user_pages.rst. * * Return: True, if it is likely that the page has been "dma-pinned". * False, if the page is definitely not dma-pinned. */ static inline bool page_maybe_dma_pinned(struct page *page) { if (hpage_pincount_available(page)) return compound_pincount(page) > 0; /* * page_ref_count() is signed. If that refcount overflows, then * page_ref_count() returns a negative value, and callers will avoid * further incrementing the refcount. * * Here, for that overflow case, use the signed bit to count a little * bit higher via unsigned math, and thus still get an accurate result. */ return ((unsigned int)page_ref_count(compound_head(page))) >= GUP_PIN_COUNTING_BIAS; } static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for a page on the src mm. */ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, struct page *page) { if (!is_cow_mapping(vma->vm_flags)) return false; if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; return page_maybe_dma_pinned(page); } #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif /* * The identification function is mainly used by the buddy allocator for * determining if two pages could be buddies. We are not really identifying * the zone since we could be using the section number id if we do not have * node id available in page flags. * We only guarantee that it will return the same value for two combinable * pages in a zone. */ static inline int page_zone_id(struct page *page) { return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } #ifdef NODE_NOT_IN_PAGE_FLAGS extern int page_to_nid(const struct page *page); #else static inline int page_to_nid(const struct page *page) { struct page *p = (struct page *)page; return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK; } #endif #ifdef CONFIG_NUMA_BALANCING static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); } static inline int cpupid_to_pid(int cpupid) { return cpupid & LAST__PID_MASK; } static inline int cpupid_to_cpu(int cpupid) { return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK; } static inline int cpupid_to_nid(int cpupid) { return cpu_to_node(cpupid_to_cpu(cpupid)); } static inline bool cpupid_pid_unset(int cpupid) { return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK); } static inline bool cpupid_cpu_unset(int cpupid) { return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK); } static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) { return (task_pid & LAST__PID_MASK) == cpupid_to_pid(cpupid); } #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int page_cpupid_last(struct page *page) { return page->_last_cpupid; } static inline void page_cpupid_reset_last(struct page *page) { page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else static inline int page_cpupid_last(struct page *page) { return (page->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } extern int page_cpupid_xchg_last(struct page *page, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return page_to_nid(page); /* XXX */ } static inline int page_cpupid_last(struct page *page) { return page_to_nid(page); /* XXX */ } static inline int cpupid_to_nid(int cpupid) { return -1; } static inline int cpupid_to_pid(int cpupid) { return -1; } static inline int cpupid_to_cpu(int cpupid) { return -1; } static inline int cpu_pid_to_cpupid(int nid, int pid) { return -1; } static inline bool cpupid_pid_unset(int cpupid) { return true; } static inline void page_cpupid_reset_last(struct page *page) { } static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) /* * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid * setting tags for all pages to native kernel tag value 0xff, as the default * value 0x00 maps to 0xff. */ static inline u8 page_kasan_tag(const struct page *page) { u8 tag = 0xff; if (kasan_enabled()) { tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; tag ^= 0xff; } return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { unsigned long old_flags, flags; if (!kasan_enabled()) return; tag ^= 0xff; old_flags = READ_ONCE(page->flags); do { flags = old_flags; flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) { if (kasan_enabled()) page_kasan_tag_set(page, 0xff); } #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline u8 page_kasan_tag(const struct page *page) { return 0xff; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { } static inline void page_kasan_tag_reset(struct page *page) { } #endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline struct zone *page_zone(const struct page *page) { return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } static inline pg_data_t *page_pgdat(const struct page *page) { return NODE_DATA(page_to_nid(page)); } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } static inline unsigned long page_to_section(const struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } #endif /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION static inline bool is_pinnable_page(struct page *page) { return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) || is_zero_pfn(page_to_pfn(page)); } #else static inline bool is_pinnable_page(struct page *page) { return true; } #endif static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { page->flags &= ~(NODES_MASK << NODES_PGSHIFT); page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); set_page_node(page, node); #ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } /* * Some inline functions in vmstat.h depend on page_zone() */ #include <linux/vmstat.h> static __always_inline void *lowmem_page_address(const struct page *page) { return page_to_virt(page); } #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif #if defined(WANT_PAGE_VIRTUAL) static inline void *page_address(const struct page *page) { return page->virtual; } static inline void set_page_address(struct page *page, void *address) { page->virtual = address; } #define page_address_init() do { } while(0) #endif #if defined(HASHED_PAGE_VIRTUAL) void *page_address(const struct page *page); void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) #define page_address_init() do { } while(0) #endif extern void *page_rmapping(struct page *page); extern struct anon_vma *page_anon_vma(struct page *page); extern struct address_space *page_mapping(struct page *page); extern struct address_space *__page_file_mapping(struct page *); static inline struct address_space *page_file_mapping(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_mapping(page); return page->mapping; } extern pgoff_t __page_file_index(struct page *page); /* * Return the pagecache index of the passed page. Regular pagecache pages * use ->index whereas swapcache pages use swp_offset(->private) */ static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_index(page); return page->index; } bool page_mapped(struct page *page); struct address_space *page_mapping(struct page *page); /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool page_is_pfmemalloc(const struct page *page) { /* * lru.next has bit 1 set if the page is allocated from the * pfmemalloc reserves. Callers may simply overwrite it if * they do not need to preserve that information. */ return (uintptr_t)page->lru.next & BIT(1); } /* * Only to be called by the page allocator on a freshly allocated * page. */ static inline void set_page_pfmemalloc(struct page *page) { page->lru.next = (void *)BIT(1); } static inline void clear_page_pfmemalloc(struct page *page) { page->lru.next = NULL; } /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. */ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) #define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) /* * Flags passed to show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else static inline bool can_do_mlock(void) { return false; } #endif extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); /* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ struct page *single_page; /* Locked page to be unmapped */ }; struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned long *prot, resource_size_t *phys); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs); extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* should never happen if there's no MMU */ BUG(); return VM_FAULT_SIGBUS; } static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); return -EFAULT; } static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { } #endif static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) { unmap_mapping_range(mapping, holebegin, holelen, 0); } extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); void __cancel_dirty_page(struct page *page); static inline void cancel_dirty_page(struct page *page) { /* Avoid atomic ops, locking, etc. when not actually needed. */ if (PageDirty(page)) __cancel_dirty_page(page); } int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, bool need_rmap_locks); /* * Flags used by change_protection(). For now we make it a bitmap so * that we can pass in multiple flags just like parameters. However * for now all the callers are only use one of the flags at the same * time. */ /* Whether we should allow dirty bit accounting */ #define MM_CP_DIRTY_ACCT (1UL << 0) /* Whether this protection change is for NUMA hints */ #define MM_CP_PROT_NUMA (1UL << 1) /* Whether this change is for write protecting */ #define MM_CP_UFFD_WP (1UL << 2) /* do wp */ #define MM_CP_UFFD_WP_RESOLVE (1UL << 3) /* Resolve wp */ #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, unsigned long cp_flags); extern int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); /* * doesn't attempt to fault and will return short. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); static inline bool get_user_page_fast_only(unsigned long addr, unsigned int gup_flags, struct page **pagep) { return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1; } /* * per-process(per-mm_struct) statistics. */ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) { long val = atomic_long_read(&mm->rss_stat.count[member]); #ifdef SPLIT_RSS_COUNTING /* * counter is updated in asynchronous manner and may go to minus. * But it's never be expected number for users. */ if (val < 0) val = 0; #endif return (unsigned long)val; } void mm_trace_rss_stat(struct mm_struct *mm, int member, long count); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { long count = atomic_long_add_return(value, &mm->rss_stat.count[member]); mm_trace_rss_stat(mm, member, count); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { long count = atomic_long_inc_return(&mm->rss_stat.count[member]); mm_trace_rss_stat(mm, member, count); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { long count = atomic_long_dec_return(&mm->rss_stat.count[member]); mm_trace_rss_stat(mm, member, count); } /* Optimized variant when page is already known not to be PageAnon */ static inline int mm_counter_file(struct page *page) { if (PageSwapBacked(page)) return MM_SHMEMPAGES; return MM_FILEPAGES; } static inline int mm_counter(struct page *page) { if (PageAnon(page)) return MM_ANONPAGES; return mm_counter_file(page); } static inline unsigned long get_mm_rss(struct mm_struct *mm) { return get_mm_counter(mm, MM_FILEPAGES) + get_mm_counter(mm, MM_ANONPAGES) + get_mm_counter(mm, MM_SHMEMPAGES); } static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) { return max(mm->hiwater_rss, get_mm_rss(mm)); } static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) { return max(mm->hiwater_vm, mm->total_vm); } static inline void update_hiwater_rss(struct mm_struct *mm) { unsigned long _rss = get_mm_rss(mm); if ((mm)->hiwater_rss < _rss) (mm)->hiwater_rss = _rss; } static inline void update_hiwater_vm(struct mm_struct *mm) { if (mm->hiwater_vm < mm->total_vm) mm->hiwater_vm = mm->total_vm; } static inline void reset_mm_hiwater_rss(struct mm_struct *mm) { mm->hiwater_rss = get_mm_rss(mm); } static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, struct mm_struct *mm) { unsigned long hiwater_rss = get_mm_hiwater_rss(mm); if (*maxrss < hiwater_rss) *maxrss = hiwater_rss; } #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm); #else static inline void sync_mm_rss(struct mm_struct *mm) { } #endif #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_mkspecial(pte_t pte) { return pte; } #endif #ifndef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t pte) { return 0; } #endif int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pte_t *ptep; __cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl)); return ptep; } #ifdef __PAGETABLE_P4D_FOLDED static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return 0; } #else int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); #endif #if defined(__PAGETABLE_PUD_FOLDED) || !defined(CONFIG_MMU) static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return 0; } static inline void mm_inc_nr_puds(struct mm_struct *mm) {} static inline void mm_dec_nr_puds(struct mm_struct *mm) {} #else int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return 0; } static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif #ifdef CONFIG_MMU static inline void mm_pgtables_bytes_init(struct mm_struct *mm) { atomic_long_set(&mm->pgtables_bytes, 0); } static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return atomic_long_read(&mm->pgtables_bytes); } static inline void mm_inc_nr_ptes(struct mm_struct *mm) { atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_ptes(struct mm_struct *mm) { atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } #else static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {} static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return 0; } static inline void mm_inc_nr_ptes(struct mm_struct *mm) {} static inline void mm_dec_nr_ptes(struct mm_struct *mm) {} #endif int __pte_alloc(struct mm_struct *mm, pmd_t *pmd); int __pte_alloc_kernel(pmd_t *pmd); #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? NULL : p4d_offset(pgd, address); } static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } #endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); extern bool ptlock_alloc(struct page *page); extern void ptlock_free(struct page *page); static inline spinlock_t *ptlock_ptr(struct page *page) { return page->ptl; } #else /* ALLOC_SPLIT_PTLOCKS */ static inline void ptlock_cache_init(void) { } static inline bool ptlock_alloc(struct page *page) { return true; } static inline void ptlock_free(struct page *page) { } static inline spinlock_t *ptlock_ptr(struct page *page) { return &page->ptl; } #endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_page(*pmd)); } static inline bool ptlock_init(struct page *page) { /* * prep_new_page() initialize page->private (and therefore page->ptl) * with 0. Make sure nobody took it in use in between. * * It can happen if arch try to use slab for page table allocation: * slab code uses page->slab_cache, which share storage with page->ptl. */ VM_BUG_ON_PAGE(*(unsigned long *)&page->ptl, page); if (!ptlock_alloc(page)) return false; spin_lock_init(ptlock_ptr(page)); return true; } #else /* !USE_SPLIT_PTE_PTLOCKS */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct page *page) { return true; } static inline void ptlock_free(struct page *page) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ static inline void pgtable_init(void) { ptlock_cache_init(); pgtable_cache_init(); } static inline bool pgtable_pte_page_ctor(struct page *page) { if (!ptlock_init(page)) return false; __SetPageTable(page); inc_lruvec_page_state(page, NR_PAGETABLE); return true; } static inline void pgtable_pte_page_dtor(struct page *page) { ptlock_free(page); __ClearPageTable(page); dec_lruvec_page_state(page, NR_PAGETABLE); } #define pte_offset_map_lock(mm, pmd, address, ptlp) \ ({ \ spinlock_t *__ptl = pte_lockptr(mm, pmd); \ pte_t *__pte = pte_offset_map(pmd, address); \ *(ptlp) = __ptl; \ spin_lock(__ptl); \ __pte; \ }) #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ pte_unmap(pte); \ } while (0) #define pte_alloc(mm, pmd) (unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd)) #define pte_alloc_map(mm, pmd, address) \ (pte_alloc(mm, pmd) ? NULL : pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ (pte_alloc(mm, pmd) ? \ NULL : pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) #if USE_SPLIT_PMD_PTLOCKS static struct page *pmd_to_page(pmd_t *pmd) { unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1); return virt_to_page((void *)((unsigned long) pmd & mask)); } static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_to_page(pmd)); } static inline bool pmd_ptlock_init(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE page->pmd_huge_pte = NULL; #endif return ptlock_init(page); } static inline void pmd_ptlock_free(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE VM_BUG_ON_PAGE(page->pmd_huge_pte, page); #endif ptlock_free(page); } #define pmd_huge_pte(mm, pmd) (pmd_to_page(pmd)->pmd_huge_pte) #else static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline bool pmd_ptlock_init(struct page *page) { return true; } static inline void pmd_ptlock_free(struct page *page) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) #endif static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); return ptl; } static inline bool pgtable_pmd_page_ctor(struct page *page) { if (!pmd_ptlock_init(page)) return false; __SetPageTable(page); inc_lruvec_page_state(page, NR_PAGETABLE); return true; } static inline void pgtable_pmd_page_dtor(struct page *page) { pmd_ptlock_free(page); __ClearPageTable(page); dec_lruvec_page_state(page, NR_PAGETABLE); } /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be * considered ready to switch to split PUD locks yet; there may be places * which need to be converted from page_table_lock. */ static inline spinlock_t *pud_lockptr(struct mm_struct *mm, pud_t *pud) { return &mm->page_table_lock; } static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) { spinlock_t *ptl = pud_lockptr(mm, pud); spin_lock(ptl); return ptl; } extern void __init pagecache_init(void); extern void __init free_area_init_memoryless_node(int nid); extern void free_initmem(void); /* * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK) * into the buddy system. The freed pages will be poisoned with pattern * "poison" if it's within range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); extern void adjust_managed_page_count(struct page *page, long count); extern void mem_init_print_info(void); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); /* Free the reserved page into the buddy system, so it gets managed. */ static inline void free_reserved_page(struct page *page) { ClearPageReserved(page); init_page_count(page); __free_page(page); adjust_managed_page_count(page, 1); } #define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) { SetPageReserved(page); adjust_managed_page_count(page, -1); } /* * Default method to free all the __init memory into the buddy system. * The freed pages will be poisoned with pattern "poison" if it's within * range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ static inline unsigned long free_initmem_default(int poison) { extern char __init_begin[], __init_end[]; return free_reserved_area(&__init_begin, &__init_end, poison, "unused kernel image (initmem)"); } static inline unsigned long get_num_physpages(void) { int nid; unsigned long phys_pages = 0; for_each_online_node(nid) phys_pages += node_present_pages(nid); return phys_pages; } /* * Using memblock node mappings, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in an * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid, MEMBLOCK_NONE) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, unsigned long end_pfn); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); #ifndef CONFIG_NUMA static inline int early_pfn_to_nid(unsigned long pfn) { return 0; } #else /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); extern void show_mem(unsigned int flags, nodemask_t *nodemask); extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); #ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES extern unsigned long arch_reserved_kernel_pages(void); #endif extern __printf(3, 4) void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); /* page_alloc.c */ extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, struct rb_root_cached *root); void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, struct rb_root_cached *root); struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, unsigned long start, unsigned long last); #define vma_interval_tree_foreach(vma, root, start, last) \ for (vma = vma_interval_tree_iter_first(root, start, last); \ vma; vma = vma_interval_tree_iter_next(vma, start, last)) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root); struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct anon_vma_chain *anon_vma_interval_tree_iter_next( struct anon_vma_chain *node, unsigned long start, unsigned long last); #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node); #endif #define anon_vma_interval_tree_foreach(avc, root, start, last) \ for (avc = anon_vma_interval_tree_iter_first(root, start, last); \ avc; avc = anon_vma_interval_tree_iter_next(avc, start, last)) /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, struct vm_area_struct *expand); static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { return __vma_adjust(vma, start, end, pgoff, insert, NULL); } extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); extern int split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *, struct rb_node **, struct rb_node *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, unsigned long end_data, unsigned long start_data) { if (rlim < RLIM_INFINITY) { if (((new - start) + (end_data - start_data)) > rlim) return -ENOSPC; } return 0; } extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); extern int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); extern struct file *get_task_exe_file(struct task_struct *task); extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); extern bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm); extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, const struct vm_special_mapping *spec); /* This is an obsolete alternative to _install_special_mapping. */ extern int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, struct page **pages); unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); extern int __do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) { /* Ignore errors */ (void) __mm_populate(addr, len, 1); } #else static inline void mm_populate(unsigned long addr, unsigned long len) {} #endif /* These take the mm semaphore themselves */ extern int __must_check vm_brk(unsigned long, unsigned long); extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); extern unsigned long __must_check vm_mmap(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); struct vm_unmapped_area_info { #define VM_UNMAPPED_AREA_TOPDOWN 1 unsigned long flags; unsigned long length; unsigned long low_limit; unsigned long high_limit; unsigned long align_mask; unsigned long align_offset; }; extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ extern void truncate_inode_pages(struct address_space *, loff_t); extern void truncate_inode_pages_range(struct address_space *, loff_t lstart, loff_t lend); extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); /* mm/page-writeback.c */ int __must_check write_one_page(struct page *page); void task_dirty_inc(struct task_struct *tsk); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); /* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ extern int expand_downwards(struct vm_area_struct *vma, unsigned long address); #if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #else #define expand_upwards(vma, address) (0) #endif /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); /** * find_vma_intersection() - Look up the first VMA which intersects the interval * @mm: The process address space. * @start_addr: The inclusive start user address. * @end_addr: The exclusive end user address. * * Returns: The first VMA within the provided range, %NULL otherwise. Assumes * start_addr < end_addr. */ static inline struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr) { struct vm_area_struct *vma = find_vma(mm, start_addr); if (vma && end_addr <= vma->vm_start) vma = NULL; return vma; } /** * vma_lookup() - Find a VMA at a specific address * @mm: The process address space. * @addr: The user address. * * Return: The vm_area_struct at the given address, %NULL otherwise. */ static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma = find_vma(mm, addr); if (vma && addr < vma->vm_start) vma = NULL; return vma; } static inline unsigned long vm_start_gap(struct vm_area_struct *vma) { unsigned long vm_start = vma->vm_start; if (vma->vm_flags & VM_GROWSDOWN) { vm_start -= stack_guard_gap; if (vm_start > vma->vm_start) vm_start = 0; } return vm_start; } static inline unsigned long vm_end_gap(struct vm_area_struct *vma) { unsigned long vm_end = vma->vm_end; if (vma->vm_flags & VM_GROWSUP) { vm_end += stack_guard_gap; if (vm_end < vma->vm_end) vm_end = -PAGE_SIZE; } return vm_end; } static inline unsigned long vma_pages(struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) { struct vm_area_struct *vma = find_vma(mm, vm_start); if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end)) vma = NULL; return vma; } static inline bool range_in_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { return (vma && vma->vm_start <= start && end <= vma->vm_end); } #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); #else static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) { return __pgprot(0); } static inline void vma_set_page_prot(struct vm_area_struct *vma) { vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); } #endif void vma_set_file(struct vm_area_struct *vma, struct file *file); #ifdef CONFIG_NUMA_BALANCING unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long start, unsigned long end); #endif struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num); int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num); int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { int err = vm_insert_page(vma, addr, page); if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } #ifndef io_remap_pfn_range static inline int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot)); } #endif static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) return VM_FAULT_OOM; return VM_FAULT_SIGBUS; } struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ #define FOLL_GET 0x04 /* do get_page on page */ #define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ #define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO * and return without waiting upon it */ #define FOLL_POPULATE 0x40 /* fault in pages (with FOLL_MLOCK) */ #define FOLL_NOFAULT 0x80 /* do not fault in pages */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ #define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ #define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: * * FOLL_LONGTERM indicates that the page will be held for an indefinite time * period _often_ under userspace control. This is in contrast to * iov_iter_get_pages(), whose usages are transient. * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm * users like RDMA and V4L2 only establish mappings which coordinate usage with * the filesystem. Ideas for this coordination include revoking the longterm * pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was * added after the problem with filesystems was found FS DAX VMAs are * specifically failed. Filesystem pages are still subject to bugs and use of * FOLL_LONGTERM should be avoided on those pages. * * FIXME: Also NOTE that FOLL_LONGTERM is not supported in every GUP call. * Currently only get_user_pages() and get_user_pages_fast() support this flag * and calls to get_user_pages_[un]locked are specifically not allowed. This * is due to an incompatibility with the FS DAX check and * FAULT_FLAG_ALLOW_RETRY. * * In the CMA case: long term pins in a CMA region would unnecessarily fragment * that region. And so, CMA attempts to migrate the page before pinning, when * FOLL_LONGTERM is specified. * * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, * but an additional pin counting system) will be invoked. This is intended for * anything that gets a page reference and then touches page data (for example, * Direct IO). This lets the filesystem know that some non-file-system entity is * potentially changing the pages' data. In contrast to FOLL_GET (whose pages * are released via put_page()), FOLL_PIN pages must be released, ultimately, by * a call to unpin_user_page(). * * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different * and separate refcounting mechanisms, however, and that means that each has * its own acquire and release mechanisms: * * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. * * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. * * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based * calls applied to them, and that's perfectly OK. This is a constraint on the * callers, not on the pages.) * * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never * directly by the caller. That's in order to help avoid mismatches when * releasing pages: get_user_pages*() pages must be released via put_page(), * while pin_user_pages*() pages must be released via unpin_user_page(). * * Please see Documentation/core-api/pin_user_pages.rst for more information. */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) return -ENOMEM; if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT; if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; return 0; } typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); extern void init_mem_debugging_and_hardening(void); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); extern bool _page_poisoning_enabled_early; DECLARE_STATIC_KEY_FALSE(_page_poisoning_enabled); static inline bool page_poisoning_enabled(void) { return _page_poisoning_enabled_early; } /* * For use in fast paths after init_mem_debugging() has run, or when a * false negative result is not harmful when called too early. */ static inline bool page_poisoning_enabled_static(void) { return static_branch_unlikely(&_page_poisoning_enabled); } static inline void kernel_poison_pages(struct page *page, int numpages) { if (page_poisoning_enabled_static()) __kernel_poison_pages(page, numpages); } static inline void kernel_unpoison_pages(struct page *page, int numpages) { if (page_poisoning_enabled_static()) __kernel_unpoison_pages(page, numpages); } #else static inline bool page_poisoning_enabled(void) { return false; } static inline bool page_poisoning_enabled_static(void) { return false; } static inline void __kernel_poison_pages(struct page *page, int nunmpages) { } static inline void kernel_poison_pages(struct page *page, int numpages) { } static inline void kernel_unpoison_pages(struct page *page, int numpages) { } #endif DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc); static inline bool want_init_on_alloc(gfp_t flags) { if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, &init_on_alloc)) return true; return flags & __GFP_ZERO; } DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); static inline bool want_init_on_free(void) { return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, &init_on_free); } extern bool _debug_pagealloc_enabled_early; DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) { return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled_early; } /* * For use in fast paths after init_debug_pagealloc() has run, or when a * false negative result is not harmful when called too early. */ static inline bool debug_pagealloc_enabled_static(void) { if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) return false; return static_branch_unlikely(&_debug_pagealloc_enabled); } #ifdef CONFIG_DEBUG_PAGEALLOC /* * To support DEBUG_PAGEALLOC architecture must ensure that * __kernel_map_pages() never fails */ extern void __kernel_map_pages(struct page *page, int numpages, int enable); static inline void debug_pagealloc_map_pages(struct page *page, int numpages) { if (debug_pagealloc_enabled_static()) __kernel_map_pages(page, numpages, 1); } static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) { if (debug_pagealloc_enabled_static()) __kernel_map_pages(page, numpages, 0); } #else /* CONFIG_DEBUG_PAGEALLOC */ static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {} static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {} #endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); extern int in_gate_area_no_mm(unsigned long addr); extern int in_gate_area(struct mm_struct *mm, unsigned long addr); #else static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { return NULL; } static inline int in_gate_area_no_mm(unsigned long addr) { return 0; } static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) { return 0; } #endif /* __HAVE_ARCH_GATE_AREA */ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); #ifdef CONFIG_SYSCTL extern int sysctl_drop_caches; int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); #endif void drop_slab(void); void drop_slab_node(int nid); #ifndef CONFIG_MMU #define randomize_va_space 0 #else extern int randomize_va_space; #endif const char * arch_vma_name(struct vm_area_struct *vma); #ifdef CONFIG_MMU void print_vma_addr(char *prefix, unsigned long rip); #else static inline void print_vma_addr(char *prefix, unsigned long rip) { } #endif int vmemmap_remap_free(unsigned long start, unsigned long end, unsigned long reuse); int vmemmap_remap_alloc(unsigned long start, unsigned long end, unsigned long reuse, gfp_t gfp_mask); void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, struct vmem_altmap *altmap); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE extern void memory_failure_queue(unsigned long pfn, int flags); extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { } static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) { return 0; } #endif /* * Error handlers for various types of pages. */ enum mf_result { MF_IGNORED, /* Error: cannot be handled */ MF_FAILED, /* Error: handling failed */ MF_DELAYED, /* Will be handled later */ MF_RECOVERED, /* Successfully recovered */ }; enum mf_action_page_type { MF_MSG_KERNEL, MF_MSG_KERNEL_HIGH_ORDER, MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, MF_MSG_POISONED_HUGE, MF_MSG_HUGE, MF_MSG_FREE_HUGE, MF_MSG_NON_PMD_HUGE, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, MF_MSG_DIRTY_MLOCKED_LRU, MF_MSG_CLEAN_MLOCKED_LRU, MF_MSG_DIRTY_UNEVICTABLE_LRU, MF_MSG_CLEAN_UNEVICTABLE_LRU, MF_MSG_DIRTY_LRU, MF_MSG_CLEAN_LRU, MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, MF_MSG_BUDDY_2ND, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_UNKNOWN, }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); extern void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int pages_per_huge_page); extern long copy_huge_page_from_user(struct page *dst_page, const void __user *usr_src, unsigned int pages_per_huge_page, bool allow_pagefault); /** * vma_is_special_huge - Are transhuge page-table entries considered special? * @vma: Pointer to the struct vm_area_struct to consider * * Whether transhuge page-table entries are considered "special" following * the definition in vm_normal_page(). * * Return: true if transhuge page-table entries should be considered special, * false otherwise. */ static inline bool vma_is_special_huge(const struct vm_area_struct *vma) { return vma_is_dax(vma) || (vma->vm_file && (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #ifdef CONFIG_DEBUG_PAGEALLOC extern unsigned int _debug_guardpage_minorder; DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static inline unsigned int debug_guardpage_minorder(void) { return _debug_guardpage_minorder; } static inline bool debug_guardpage_enabled(void) { return static_branch_unlikely(&_debug_guardpage_enabled); } static inline bool page_is_guard(struct page *page) { if (!debug_guardpage_enabled()) return false; return PageGuard(page); } #else static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } static inline bool page_is_guard(struct page *page) { return false; } #endif /* CONFIG_DEBUG_PAGEALLOC */ #if MAX_NUMNODES > 1 void __init setup_nr_node_ids(void); #else static inline void setup_nr_node_ids(void) {} #endif extern int memcmp_pages(struct page *page1, struct page *page2); static inline int pages_identical(struct page *page1, struct page *page2) { return !memcmp_pages(page1, page2); } #ifdef CONFIG_MAPPING_DIRTY_HELPERS unsigned long clean_record_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, pgoff_t bitmap_pgoff, unsigned long *bitmap, pgoff_t *start, pgoff_t *end); unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif extern int sysctl_nr_trim_pages; #ifdef CONFIG_PRINTK void mem_dump_obj(void *object); #else static inline void mem_dump_obj(void *object) {} #endif /** * seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it * @seals: the seals to check * @vma: the vma to operate on * * Check whether F_SEAL_FUTURE_WRITE is set; if so, do proper check/handling on * the vma flags. Return 0 if check pass, or <0 for errors. */ static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) { if (seals & F_SEAL_FUTURE_WRITE) { /* * New PROT_WRITE and MAP_SHARED mmaps are not allowed when * "future write" seal active. */ if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) return -EPERM; /* * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as * MAP_SHARED and read-only, take care to not allow mprotect to * revert protections on such mappings. Do this only for shared * mappings. For private mappings, don't need to mask * VM_MAYWRITE as we still want them to be COW-writable. */ if (vma->vm_flags & VM_SHARED) vma->vm_flags &= ~(VM_MAYWRITE); } return 0; } #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ |
| 49 49 49 49 49 49 49 49 49 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_proto.c: transport protocol load balancing support for IPVS * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Julian Anastasov <ja@ssi.bg> * * Changes: */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/gfp.h> #include <linux/in.h> #include <linux/ip.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/udp.h> #include <linux/stat.h> #include <linux/proc_fs.h> #include <net/ip_vs.h> /* * IPVS protocols can only be registered/unregistered when the ipvs * module is loaded/unloaded, so no lock is needed in accessing the * ipvs protocol table. */ #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */ #define IP_VS_PROTO_HASH(proto) ((proto) & (IP_VS_PROTO_TAB_SIZE-1)) static struct ip_vs_protocol *ip_vs_proto_table[IP_VS_PROTO_TAB_SIZE]; /* States for conn templates: NONE or words separated with ",", max 15 chars */ static const char *ip_vs_ctpl_state_name_table[IP_VS_CTPL_S_LAST] = { [IP_VS_CTPL_S_NONE] = "NONE", [IP_VS_CTPL_S_ASSURED] = "ASSURED", }; /* * register an ipvs protocol */ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) { unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); pp->next = ip_vs_proto_table[hash]; ip_vs_proto_table[hash] = pp; if (pp->init != NULL) pp->init(pp); return 0; } /* * register an ipvs protocols netns related data */ static int register_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_protocol *pp) { unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); struct ip_vs_proto_data *pd = kzalloc(sizeof(struct ip_vs_proto_data), GFP_KERNEL); if (!pd) return -ENOMEM; pd->pp = pp; /* For speed issues */ pd->next = ipvs->proto_data_table[hash]; ipvs->proto_data_table[hash] = pd; atomic_set(&pd->appcnt, 0); /* Init app counter */ if (pp->init_netns != NULL) { int ret = pp->init_netns(ipvs, pd); if (ret) { /* unlink an free proto data */ ipvs->proto_data_table[hash] = pd->next; kfree(pd); return ret; } } return 0; } /* * unregister an ipvs protocol */ static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp) { struct ip_vs_protocol **pp_p; unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); pp_p = &ip_vs_proto_table[hash]; for (; *pp_p; pp_p = &(*pp_p)->next) { if (*pp_p == pp) { *pp_p = pp->next; if (pp->exit != NULL) pp->exit(pp); return 0; } } return -ESRCH; } /* * unregister an ipvs protocols netns data */ static int unregister_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { struct ip_vs_proto_data **pd_p; unsigned int hash = IP_VS_PROTO_HASH(pd->pp->protocol); pd_p = &ipvs->proto_data_table[hash]; for (; *pd_p; pd_p = &(*pd_p)->next) { if (*pd_p == pd) { *pd_p = pd->next; if (pd->pp->exit_netns != NULL) pd->pp->exit_netns(ipvs, pd); kfree(pd); return 0; } } return -ESRCH; } /* * get ip_vs_protocol object by its proto. */ struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto) { struct ip_vs_protocol *pp; unsigned int hash = IP_VS_PROTO_HASH(proto); for (pp = ip_vs_proto_table[hash]; pp; pp = pp->next) { if (pp->protocol == proto) return pp; } return NULL; } EXPORT_SYMBOL(ip_vs_proto_get); /* * get ip_vs_protocol object data by netns and proto */ struct ip_vs_proto_data * ip_vs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) { struct ip_vs_proto_data *pd; unsigned int hash = IP_VS_PROTO_HASH(proto); for (pd = ipvs->proto_data_table[hash]; pd; pd = pd->next) { if (pd->pp->protocol == proto) return pd; } return NULL; } EXPORT_SYMBOL(ip_vs_proto_data_get); /* * Propagate event for state change to all protocols */ void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags) { struct ip_vs_proto_data *pd; int i; for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { for (pd = ipvs->proto_data_table[i]; pd; pd = pd->next) { if (pd->pp->timeout_change) pd->pp->timeout_change(pd, flags); } } } int * ip_vs_create_timeout_table(int *table, int size) { return kmemdup(table, size, GFP_KERNEL); } const char *ip_vs_state_name(const struct ip_vs_conn *cp) { unsigned int state = cp->state; struct ip_vs_protocol *pp; if (cp->flags & IP_VS_CONN_F_TEMPLATE) { if (state >= IP_VS_CTPL_S_LAST) return "ERR!"; return ip_vs_ctpl_state_name_table[state] ? : "?"; } pp = ip_vs_proto_get(cp->protocol); if (pp == NULL || pp->state_name == NULL) return (cp->protocol == IPPROTO_IP) ? "NONE" : "ERR!"; return pp->state_name(state); } static void ip_vs_tcpudp_debug_packet_v4(struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg) { char buf[128]; struct iphdr _iph, *ih; ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) sprintf(buf, "TRUNCATED"); else if (ih->frag_off & htons(IP_OFFSET)) sprintf(buf, "%pI4->%pI4 frag", &ih->saddr, &ih->daddr); else { __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, offset + ih->ihl*4, sizeof(_ports), _ports); if (pptr == NULL) sprintf(buf, "TRUNCATED %pI4->%pI4", &ih->saddr, &ih->daddr); else sprintf(buf, "%pI4:%u->%pI4:%u", &ih->saddr, ntohs(pptr[0]), &ih->daddr, ntohs(pptr[1])); } pr_debug("%s: %s %s\n", msg, pp->name, buf); } #ifdef CONFIG_IP_VS_IPV6 static void ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg) { char buf[192]; struct ipv6hdr _iph, *ih; ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) sprintf(buf, "TRUNCATED"); else if (ih->nexthdr == IPPROTO_FRAGMENT) sprintf(buf, "%pI6c->%pI6c frag", &ih->saddr, &ih->daddr); else { __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, offset + sizeof(struct ipv6hdr), sizeof(_ports), _ports); if (pptr == NULL) sprintf(buf, "TRUNCATED %pI6c->%pI6c", &ih->saddr, &ih->daddr); else sprintf(buf, "%pI6c:%u->%pI6c:%u", &ih->saddr, ntohs(pptr[0]), &ih->daddr, ntohs(pptr[1])); } pr_debug("%s: %s %s\n", msg, pp->name, buf); } #endif void ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_tcpudp_debug_packet_v6(pp, skb, offset, msg); else #endif ip_vs_tcpudp_debug_packet_v4(pp, skb, offset, msg); } /* * per network name-space init */ int __net_init ip_vs_protocol_net_init(struct netns_ipvs *ipvs) { int i, ret; static struct ip_vs_protocol *protos[] = { #ifdef CONFIG_IP_VS_PROTO_TCP &ip_vs_protocol_tcp, #endif #ifdef CONFIG_IP_VS_PROTO_UDP &ip_vs_protocol_udp, #endif #ifdef CONFIG_IP_VS_PROTO_SCTP &ip_vs_protocol_sctp, #endif #ifdef CONFIG_IP_VS_PROTO_AH &ip_vs_protocol_ah, #endif #ifdef CONFIG_IP_VS_PROTO_ESP &ip_vs_protocol_esp, #endif }; for (i = 0; i < ARRAY_SIZE(protos); i++) { ret = register_ip_vs_proto_netns(ipvs, protos[i]); if (ret < 0) goto cleanup; } return 0; cleanup: ip_vs_protocol_net_cleanup(ipvs); return ret; } void __net_exit ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs) { struct ip_vs_proto_data *pd; int i; /* unregister all the ipvs proto data for this netns */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pd = ipvs->proto_data_table[i]) != NULL) unregister_ip_vs_proto_netns(ipvs, pd); } } int __init ip_vs_protocol_init(void) { char protocols[64] = { 0 }; #define REGISTER_PROTOCOL(p) \ do { \ register_ip_vs_protocol(p); \ strcat(protocols, ", "); \ strcat(protocols, (p)->name); \ } while (0) #ifdef CONFIG_IP_VS_PROTO_TCP REGISTER_PROTOCOL(&ip_vs_protocol_tcp); #endif #ifdef CONFIG_IP_VS_PROTO_UDP REGISTER_PROTOCOL(&ip_vs_protocol_udp); #endif #ifdef CONFIG_IP_VS_PROTO_SCTP REGISTER_PROTOCOL(&ip_vs_protocol_sctp); #endif #ifdef CONFIG_IP_VS_PROTO_AH REGISTER_PROTOCOL(&ip_vs_protocol_ah); #endif #ifdef CONFIG_IP_VS_PROTO_ESP REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); return 0; } void ip_vs_protocol_cleanup(void) { struct ip_vs_protocol *pp; int i; /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) unregister_ip_vs_protocol(pp); } } |
| 1319 1320 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c. * * Copyright (C) 2004 Paul Mackerras, IBM Corp. */ #include <linux/bsearch.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sort.h> #include <linux/uaccess.h> #include <linux/extable.h> #ifndef ARCH_HAS_RELATIVE_EXTABLE #define ex_to_insn(x) ((x)->insn) #else static inline unsigned long ex_to_insn(const struct exception_table_entry *x) { return (unsigned long)&x->insn + x->insn; } #endif #ifndef ARCH_HAS_RELATIVE_EXTABLE #define swap_ex NULL #else static void swap_ex(void *a, void *b, int size) { struct exception_table_entry *x = a, *y = b, tmp; int delta = b - a; tmp = *x; x->insn = y->insn + delta; y->insn = tmp.insn - delta; #ifdef swap_ex_entry_fixup swap_ex_entry_fixup(x, y, tmp, delta); #else x->fixup = y->fixup + delta; y->fixup = tmp.fixup - delta; #endif } #endif /* ARCH_HAS_RELATIVE_EXTABLE */ /* * The exception table needs to be sorted so that the binary * search that we use to find entries in it works properly. * This is used both for the kernel exception table and for * the exception tables of modules that get loaded. */ static int cmp_ex_sort(const void *a, const void *b) { const struct exception_table_entry *x = a, *y = b; /* avoid overflow */ if (ex_to_insn(x) > ex_to_insn(y)) return 1; if (ex_to_insn(x) < ex_to_insn(y)) return -1; return 0; } void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish) { sort(start, finish - start, sizeof(struct exception_table_entry), cmp_ex_sort, swap_ex); } #ifdef CONFIG_MODULES /* * If the exception table is sorted, any referring to the module init * will be at the beginning or the end. */ void trim_init_extable(struct module *m) { /*trim the beginning*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[0]), m)) { m->extable++; m->num_exentries--; } /*trim the end*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[m->num_exentries - 1]), m)) m->num_exentries--; } #endif /* CONFIG_MODULES */ static int cmp_ex_search(const void *key, const void *elt) { const struct exception_table_entry *_elt = elt; unsigned long _key = *(unsigned long *)key; /* avoid overflow */ if (_key > ex_to_insn(_elt)) return 1; if (_key < ex_to_insn(_elt)) return -1; return 0; } /* * Search one exception table for an entry corresponding to the * given instruction address, and return the address of the entry, * or NULL if none is found. * We use a binary search, and thus we assume that the table is * already sorted. */ const struct exception_table_entry * search_extable(const struct exception_table_entry *base, const size_t num, unsigned long value) { return bsearch(&value, base, num, sizeof(struct exception_table_entry), cmp_ex_search); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef INT_BLK_MQ_H #define INT_BLK_MQ_H #include "blk-stat.h" #include "blk-mq-tag.h" struct blk_mq_tag_set; struct blk_mq_ctxs { struct kobject kobj; struct blk_mq_ctx __percpu *queue_ctx; }; /** * struct blk_mq_ctx - State for a software queue facing the submitting CPUs */ struct blk_mq_ctx { struct { spinlock_t lock; struct list_head rq_lists[HCTX_MAX_TYPES]; } ____cacheline_aligned_in_smp; unsigned int cpu; unsigned short index_hw[HCTX_MAX_TYPES]; struct blk_mq_hw_ctx *hctxs[HCTX_MAX_TYPES]; /* incremented at dispatch time */ unsigned long rq_dispatched[2]; unsigned long rq_merged; /* incremented at completion time */ unsigned long ____cacheline_aligned_in_smp rq_completed[2]; struct request_queue *queue; struct blk_mq_ctxs *ctxs; struct kobject kobj; } ____cacheline_aligned_in_smp; void blk_mq_exit_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *, unsigned int); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, bool kick_requeue_list); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start); void blk_mq_put_rq_ref(struct request *rq); /* * Internal helpers for allocating/freeing the request map */ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx); void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags); struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, unsigned int reserved_tags, unsigned int flags); int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx, unsigned int depth); /* * Internal helpers for request insertion into sw queues */ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head); void blk_mq_request_bypass_insert(struct request *rq, bool at_head, bool run_queue); void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list); /* Used by blk_insert_cloned_request() to issue request directly */ blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last); void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list); /* * CPU -> queue mappings */ extern int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int); /* * blk_mq_map_queue_type() - map (hctx_type,cpu) to hardware queue * @q: request queue * @type: the hctx type index * @cpu: CPU */ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *q, enum hctx_type type, unsigned int cpu) { return q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]]; } /* * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue * @q: request queue * @flags: request command flags * @ctx: software queue cpu ctx */ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, unsigned int flags, struct blk_mq_ctx *ctx) { enum hctx_type type = HCTX_TYPE_DEFAULT; /* * The caller ensure that if REQ_HIPRI, poll must be enabled. */ if (flags & REQ_HIPRI) type = HCTX_TYPE_POLL; else if ((flags & REQ_OP_MASK) == REQ_OP_READ) type = HCTX_TYPE_READ; return ctx->hctxs[type]; } /* * sysfs helpers */ extern void blk_mq_sysfs_init(struct request_queue *q); extern void blk_mq_sysfs_deinit(struct request_queue *q); extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q); extern int blk_mq_sysfs_register(struct request_queue *q); extern void blk_mq_sysfs_unregister(struct request_queue *q); extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); void blk_mq_cancel_work_sync(struct request_queue *q); void blk_mq_release(struct request_queue *q); static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, unsigned int cpu) { return per_cpu_ptr(q->queue_ctx, cpu); } /* * This assumes per-cpu software queueing queues. They could be per-node * as well, for instance. For now this is hardcoded as-is. Note that we don't * care about preemption, since we know the ctx's are persistent. This does * mean that we can't rely on ctx always matching the currently running CPU. */ static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) { return __blk_mq_get_ctx(q, raw_smp_processor_id()); } struct blk_mq_alloc_data { /* input parameter */ struct request_queue *q; blk_mq_req_flags_t flags; unsigned int shallow_depth; unsigned int cmd_flags; /* input & output parameter */ struct blk_mq_ctx *ctx; struct blk_mq_hw_ctx *hctx; }; static inline bool blk_mq_is_sbitmap_shared(unsigned int flags) { return flags & BLK_MQ_F_TAG_HCTX_SHARED; } static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data) { if (data->q->elevator) return data->hctx->sched_tags; return data->hctx->tags; } static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx) { /* Fast path: hardware queue is not stopped most of the time. */ if (likely(!test_bit(BLK_MQ_S_STOPPED, &hctx->state))) return false; /* * This barrier is used to order adding of dispatch list before and * the test of BLK_MQ_S_STOPPED below. Pairs with the memory barrier * in blk_mq_start_stopped_hw_queue() so that dispatch code could * either see BLK_MQ_S_STOPPED is cleared or dispatch list is not * empty to avoid missing dispatching requests. */ smp_mb(); return test_bit(BLK_MQ_S_STOPPED, &hctx->state); } static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) { return hctx->nr_ctx && hctx->tags; } unsigned int blk_mq_in_flight(struct request_queue *q, struct block_device *part); void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, unsigned int inflight[2]); static inline void blk_mq_put_dispatch_budget(struct request_queue *q, int budget_token) { if (q->mq_ops->put_budget) q->mq_ops->put_budget(q, budget_token); } static inline int blk_mq_get_dispatch_budget(struct request_queue *q) { if (q->mq_ops->get_budget) return q->mq_ops->get_budget(q); return 0; } static inline void blk_mq_set_rq_budget_token(struct request *rq, int token) { if (token < 0) return; if (rq->q->mq_ops->set_rq_budget_token) rq->q->mq_ops->set_rq_budget_token(rq, token); } static inline int blk_mq_get_rq_budget_token(struct request *rq) { if (rq->q->mq_ops->get_rq_budget_token) return rq->q->mq_ops->get_rq_budget_token(rq); return -1; } static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap); else atomic_inc(&hctx->nr_active); } static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap); else atomic_dec(&hctx->nr_active); } static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap); return atomic_read(&hctx->nr_active); } static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq) { blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag); rq->tag = BLK_MQ_NO_TAG; if (rq->rq_flags & RQF_MQ_INFLIGHT) { rq->rq_flags &= ~RQF_MQ_INFLIGHT; __blk_mq_dec_active_requests(hctx); } } static inline void blk_mq_put_driver_tag(struct request *rq) { if (rq->tag == BLK_MQ_NO_TAG || rq->internal_tag == BLK_MQ_NO_TAG) return; __blk_mq_put_driver_tag(rq->mq_hctx, rq); } bool blk_mq_get_driver_tag(struct request *rq); static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) { int cpu; for_each_possible_cpu(cpu) qmap->mq_map[cpu] = 0; } /* * blk_mq_plug() - Get caller context plug * @q: request queue * @bio : the bio being submitted by the caller context * * Plugging, by design, may delay the insertion of BIOs into the elevator in * order to increase BIO merging opportunities. This however can cause BIO * insertion order to change from the order in which submit_bio() is being * executed in the case of multiple contexts concurrently issuing BIOs to a * device, even if these context are synchronized to tightly control BIO issuing * order. While this is not a problem with regular block devices, this ordering * change can cause write BIO failures with zoned block devices as these * require sequential write patterns to zones. Prevent this from happening by * ignoring the plug state of a BIO issuing context if the target request queue * is for a zoned block device and the BIO to plug is a write operation. * * Return current->plug if the bio can be plugged and NULL otherwise */ static inline struct blk_plug *blk_mq_plug(struct request_queue *q, struct bio *bio) { /* * For regular block devices or read operations, use the context plug * which may be NULL if blk_start_plug() was not executed. */ if (!blk_queue_is_zoned(q) || !op_is_write(bio_op(bio))) return current->plug; /* Zoned block device write operation case: do not plug the BIO */ return NULL; } /* Free all requests on the list */ static inline void blk_mq_free_requests(struct list_head *list) { while (!list_empty(list)) { struct request *rq = list_entry_rq(list->next); list_del_init(&rq->queuelist); blk_mq_free_request(rq); } } /* * For shared tag users, we track the number of currently active users * and attempt to provide a fair share of the tag depth for each of them. */ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt) { unsigned int depth, users; if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return true; /* * Don't try dividing an ant */ if (bt->sb.depth == 1) return true; if (blk_mq_is_sbitmap_shared(hctx->flags)) { struct request_queue *q = hctx->queue; struct blk_mq_tag_set *set = q->tag_set; if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return true; users = atomic_read(&set->active_queues_shared_sbitmap); } else { if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return true; users = atomic_read(&hctx->tags->active_queues); } if (!users) return true; /* * Allow at least some tags */ depth = max((bt->sb.depth + users - 1) / users, 4U); return __blk_mq_active_requests(hctx) < depth; } #endif |
| 431 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 | // SPDX-License-Identifier: GPL-2.0 /* * Dynamic byte queue limits. See include/linux/dynamic_queue_limits.h * * Copyright (c) 2011, Tom Herbert <therbert@google.com> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/dynamic_queue_limits.h> #include <linux/compiler.h> #include <linux/export.h> #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0) #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0) /* Records completed count and recalculates the queue limit */ void dql_completed(struct dql *dql, unsigned int count) { unsigned int inprogress, prev_inprogress, limit; unsigned int ovlimit, completed, num_queued; bool all_prev_completed; num_queued = READ_ONCE(dql->num_queued); /* Can't complete more than what's in queue */ BUG_ON(count > num_queued - dql->num_completed); completed = dql->num_completed + count; limit = dql->limit; ovlimit = POSDIFF(num_queued - dql->num_completed, limit); inprogress = num_queued - completed; prev_inprogress = dql->prev_num_queued - dql->num_completed; all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued); if ((ovlimit && !inprogress) || (dql->prev_ovlimit && all_prev_completed)) { /* * Queue considered starved if: * - The queue was over-limit in the last interval, * and there is no more data in the queue. * OR * - The queue was over-limit in the previous interval and * when enqueuing it was possible that all queued data * had been consumed. This covers the case when queue * may have becomes starved between completion processing * running and next time enqueue was scheduled. * * When queue is starved increase the limit by the amount * of bytes both sent and completed in the last interval, * plus any previous over-limit. */ limit += POSDIFF(completed, dql->prev_num_queued) + dql->prev_ovlimit; dql->slack_start_time = jiffies; dql->lowest_slack = UINT_MAX; } else if (inprogress && prev_inprogress && !all_prev_completed) { /* * Queue was not starved, check if the limit can be decreased. * A decrease is only considered if the queue has been busy in * the whole interval (the check above). * * If there is slack, the amount of excess data queued above * the amount needed to prevent starvation, the queue limit * can be decreased. To avoid hysteresis we consider the * minimum amount of slack found over several iterations of the * completion routine. */ unsigned int slack, slack_last_objs; /* * Slack is the maximum of * - The queue limit plus previous over-limit minus twice * the number of objects completed. Note that two times * number of completed bytes is a basis for an upper bound * of the limit. * - Portion of objects in the last queuing operation that * was not part of non-zero previous over-limit. That is * "round down" by non-overlimit portion of the last * queueing operation. */ slack = POSDIFF(limit + dql->prev_ovlimit, 2 * (completed - dql->num_completed)); slack_last_objs = dql->prev_ovlimit ? POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0; slack = max(slack, slack_last_objs); if (slack < dql->lowest_slack) dql->lowest_slack = slack; if (time_after(jiffies, dql->slack_start_time + dql->slack_hold_time)) { limit = POSDIFF(limit, dql->lowest_slack); dql->slack_start_time = jiffies; dql->lowest_slack = UINT_MAX; } } /* Enforce bounds on limit */ limit = clamp(limit, dql->min_limit, dql->max_limit); if (limit != dql->limit) { dql->limit = limit; ovlimit = 0; } dql->adj_limit = limit + completed; dql->prev_ovlimit = ovlimit; dql->prev_last_obj_cnt = dql->last_obj_cnt; dql->num_completed = completed; dql->prev_num_queued = num_queued; } EXPORT_SYMBOL(dql_completed); void dql_reset(struct dql *dql) { /* Reset all dynamic values */ dql->limit = 0; dql->num_queued = 0; dql->num_completed = 0; dql->last_obj_cnt = 0; dql->prev_num_queued = 0; dql->prev_last_obj_cnt = 0; dql->prev_ovlimit = 0; dql->lowest_slack = UINT_MAX; dql->slack_start_time = jiffies; } EXPORT_SYMBOL(dql_reset); void dql_init(struct dql *dql, unsigned int hold_time) { dql->max_limit = DQL_MAX_LIMIT; dql->min_limit = 0; dql->slack_hold_time = hold_time; dql_reset(dql); } EXPORT_SYMBOL(dql_init); |
| 5158 2415 3040 63 63 63 35 63 237 237 236 236 237 238 44 68 461 3242 177 178 177 211 35 225 121 121 121 45 45 304 304 305 305 196 196 15 183 197 24 24 24 24 29 83 3384 1 3060 3067 3198 3206 316 2925 3216 3201 875 3897 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic pidhash and scalable, time-bounded PID allocator * * (C) 2002-2003 Nadia Yvette Chambers, IBM * (C) 2004 Nadia Yvette Chambers, Oracle * (C) 2002-2004 Ingo Molnar, Red Hat * * pid-structures are backing objects for tasks sharing a given ID to chain * against. There is very little to them aside from hashing them and * parking tasks using given ID's on a list. * * The hash is always changed with the tasklist_lock write-acquired, * and the hash is only accessed with the tasklist_lock at least * read-acquired, so there's no additional SMP locking needed here. * * We have a list of bitmap pages, which bitmaps represent the PID space. * Allocating and freeing PIDs is completely lockless. The worst-case * allocation scenario when all but one out of 1 million PIDs possible are * allocated already: the scanning of 32 list entries and at most PAGE_SIZE * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). * * Pid namespaces: * (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. * (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM * Many thanks to Oleg Nesterov for comments and help * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/memblock.h> #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/anon_inodes.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> #include <net/sock.h> #include <uapi/linux/pidfd.h> struct pid init_struct_pid = { .count = REFCOUNT_INIT(1), .tasks = { { .first = NULL }, { .first = NULL }, { .first = NULL }, }, .level = 0, .numbers = { { .nr = 0, .ns = &init_pid_ns, }, } }; int pid_max = PID_MAX_DEFAULT; #define RESERVED_PIDS 300 int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; /* * PID-map pages start out as NULL, they get allocated upon * first use and are never deallocated. This way a low pid_max * value does not cause lots of bitmaps to be allocated, but * the scheme scales to up to 4 million PIDs, runtime. */ struct pid_namespace init_pid_ns = { .ns.count = REFCOUNT_INIT(2), .idr = IDR_INIT(init_pid_ns.idr), .pid_allocated = PIDNS_ADDING, .level = 0, .child_reaper = &init_task, .user_ns = &init_user_ns, .ns.inum = PROC_PID_INIT_INO, #ifdef CONFIG_PID_NS .ns.ops = &pidns_operations, #endif }; EXPORT_SYMBOL_GPL(init_pid_ns); /* * Note: disable interrupts while the pidmap_lock is held as an * interrupt might come in and do read_lock(&tasklist_lock). * * If we don't disable interrupts there is a nasty deadlock between * detach_pid()->free_pid() and another cpu that does * spin_lock(&pidmap_lock) followed by an interrupt routine that does * read_lock(&tasklist_lock); * * After we clean up the tasklist_lock and know there are no * irq handlers that take it we can leave the interrupts enabled. * For now it is easier to be safe than to prove it can't happen. */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); void put_pid(struct pid *pid) { struct pid_namespace *ns; if (!pid) return; ns = pid->numbers[pid->level].ns; if (refcount_dec_and_test(&pid->count)) { kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } } EXPORT_SYMBOL_GPL(put_pid); static void delayed_put_pid(struct rcu_head *rhp) { struct pid *pid = container_of(rhp, struct pid, rcu); put_pid(pid); } void free_pid(struct pid *pid) { /* We can be called with write_lock_irq(&tasklist_lock) held */ int i; unsigned long flags; spin_lock_irqsave(&pidmap_lock, flags); for (i = 0; i <= pid->level; i++) { struct upid *upid = pid->numbers + i; struct pid_namespace *ns = upid->ns; switch (--ns->pid_allocated) { case 2: case 1: /* When all that is left in the pid namespace * is the reaper wake up the reaper. The reaper * may be sleeping in zap_pid_ns_processes(). */ wake_up_process(ns->child_reaper); break; case PIDNS_ADDING: /* Handle a fork failure of the first process */ WARN_ON(ns->child_reaper); ns->pid_allocated = 0; break; } idr_remove(&ns->idr, upid->nr); } spin_unlock_irqrestore(&pidmap_lock, flags); call_rcu(&pid->rcu, delayed_put_pid); } struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size) { struct pid *pid; enum pid_type type; int i, nr; struct pid_namespace *tmp; struct upid *upid; int retval = -ENOMEM; /* * set_tid_size contains the size of the set_tid array. Starting at * the most nested currently active PID namespace it tells alloc_pid() * which PID to set for a process in that most nested PID namespace * up to set_tid_size PID namespaces. It does not have to set the PID * for a process in all nested PID namespaces but set_tid_size must * never be greater than the current ns->level + 1. */ if (set_tid_size > ns->level + 1) return ERR_PTR(-EINVAL); pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); tmp = ns; pid->level = ns->level; for (i = ns->level; i >= 0; i--) { int tid = 0; if (set_tid_size) { tid = set_tid[ns->level - i]; retval = -EINVAL; if (tid < 1 || tid >= pid_max) goto out_free; /* * Also fail if a PID != 1 is requested and * no PID 1 exists. */ if (tid != 1 && !tmp->child_reaper) goto out_free; retval = -EPERM; if (!checkpoint_restore_ns_capable(tmp->user_ns)) goto out_free; set_tid_size--; } idr_preload(GFP_KERNEL); spin_lock_irq(&pidmap_lock); if (tid) { nr = idr_alloc(&tmp->idr, NULL, tid, tid + 1, GFP_ATOMIC); /* * If ENOSPC is returned it means that the PID is * alreay in use. Return EEXIST in that case. */ if (nr == -ENOSPC) nr = -EEXIST; } else { int pid_min = 1; /* * init really needs pid 1, but after reaching the * maximum wrap back to RESERVED_PIDS */ if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) pid_min = RESERVED_PIDS; /* * Store a null pointer so find_pid_ns does not find * a partially initialized PID (see below). */ nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, pid_max, GFP_ATOMIC); } spin_unlock_irq(&pidmap_lock); idr_preload_end(); if (nr < 0) { retval = (nr == -ENOSPC) ? -EAGAIN : nr; goto out_free; } pid->numbers[i].nr = nr; pid->numbers[i].ns = tmp; tmp = tmp->parent; } /* * ENOMEM is not the most obvious choice especially for the case * where the child subreaper has already exited and the pid * namespace denies the creation of any new processes. But ENOMEM * is what we have exposed to userspace for a long time and it is * documented behavior for pid namespaces. So we can't easily * change it even if there were an error code better suited. */ retval = -ENOMEM; get_pid_ns(ns); refcount_set(&pid->count, 1); spin_lock_init(&pid->lock); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); init_waitqueue_head(&pid->wait_pidfd); INIT_HLIST_HEAD(&pid->inodes); upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); upid->ns->pid_allocated++; } spin_unlock_irq(&pidmap_lock); return pid; out_unlock: spin_unlock_irq(&pidmap_lock); put_pid_ns(ns); out_free: spin_lock_irq(&pidmap_lock); while (++i <= ns->level) { upid = pid->numbers + i; idr_remove(&upid->ns->idr, upid->nr); } /* On failure to allocate the first pid, reset the state */ if (ns->pid_allocated == PIDNS_ADDING) idr_set_cursor(&ns->idr, 0); spin_unlock_irq(&pidmap_lock); kmem_cache_free(ns->pid_cachep, pid); return ERR_PTR(retval); } void disable_pid_allocation(struct pid_namespace *ns) { spin_lock_irq(&pidmap_lock); ns->pid_allocated &= ~PIDNS_ADDING; spin_unlock_irq(&pidmap_lock); } struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { return idr_find(&ns->idr, nr); } EXPORT_SYMBOL_GPL(find_pid_ns); struct pid *find_vpid(int nr) { return find_pid_ns(nr, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(find_vpid); static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type) { return (type == PIDTYPE_PID) ? &task->thread_pid : &task->signal->pids[type]; } /* * attach_pid() must be called with the tasklist_lock write-held. */ void attach_pid(struct task_struct *task, enum pid_type type) { struct pid *pid = *task_pid_ptr(task, type); hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]); } static void __change_pid(struct task_struct *task, enum pid_type type, struct pid *new) { struct pid **pid_ptr = task_pid_ptr(task, type); struct pid *pid; int tmp; pid = *pid_ptr; hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; free_pid(pid); } void detach_pid(struct task_struct *task, enum pid_type type) { __change_pid(task, type, NULL); } void change_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { __change_pid(task, type, pid); attach_pid(task, type); } void exchange_tids(struct task_struct *left, struct task_struct *right) { struct pid *pid1 = left->thread_pid; struct pid *pid2 = right->thread_pid; struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID]; struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID]; /* Swap the single entry tid lists */ hlists_swap_heads_rcu(head1, head2); /* Swap the per task_struct pid */ rcu_assign_pointer(left->thread_pid, pid2); rcu_assign_pointer(right->thread_pid, pid1); /* Swap the cached value */ WRITE_ONCE(left->pid, pid_nr(pid2)); WRITE_ONCE(right->pid, pid_nr(pid1)); } /* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type type) { if (type == PIDTYPE_PID) new->thread_pid = old->thread_pid; hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]); } struct task_struct *pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pid_links[(type)]); } return result; } EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock(). */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "find_task_by_pid_ns() needs rcu_read_lock() protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } struct task_struct *find_task_by_vpid(pid_t vnr) { return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } struct task_struct *find_get_task_by_vpid(pid_t nr) { struct task_struct *task; rcu_read_lock(); task = find_task_by_vpid(nr); if (task) get_task_struct(task); rcu_read_unlock(); return task; } struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; rcu_read_lock(); pid = get_pid(rcu_dereference(*task_pid_ptr(task, type))); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(get_task_pid); struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; rcu_read_lock(); result = pid_task(pid, type); if (result) get_task_struct(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(get_pid_task); struct pid *find_get_pid(pid_t nr) { struct pid *pid; rcu_read_lock(); pid = get_pid(find_vpid(nr)); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(find_get_pid); pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) { struct upid *upid; pid_t nr = 0; if (pid && ns->level <= pid->level) { upid = &pid->numbers[ns->level]; if (upid->ns == ns) nr = upid->nr; } return nr; } EXPORT_SYMBOL_GPL(pid_nr_ns); pid_t pid_vnr(struct pid *pid) { return pid_nr_ns(pid, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(pid_vnr); pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns) { pid_t nr = 0; rcu_read_lock(); if (!ns) ns = task_active_pid_ns(current); nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns); rcu_read_unlock(); return nr; } EXPORT_SYMBOL(__task_pid_nr_ns); struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); } EXPORT_SYMBOL_GPL(task_active_pid_ns); /* * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) { return idr_get_next(&ns->idr, &nr); } struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) { struct fd f; struct pid *pid; f = fdget(fd); if (!f.file) return ERR_PTR(-EBADF); pid = pidfd_pid(f.file); if (!IS_ERR(pid)) { get_pid(pid); *flags = f.file->f_flags; } fdput(f); return pid; } /** * pidfd_create() - Create a new pid file descriptor. * * @pid: struct pid that the pidfd will reference * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set. * * Note, that this function can only be called after the fd table has * been unshared to avoid leaking the pidfd to the new process. * * This symbol should not be explicitly exported to loadable modules. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ int pidfd_create(struct pid *pid, unsigned int flags) { int fd; if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) return -EINVAL; if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) return -EINVAL; fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid), flags | O_RDWR | O_CLOEXEC); if (fd < 0) put_pid(pid); return fd; } /** * pidfd_open() - Open new pid file descriptor. * * @pid: pid for which to retrieve a pidfd * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for * the process identified by @pid. Currently, the process identified by * @pid must be a thread-group leader. This restriction currently exists * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot * be used with CLONE_THREAD) and pidfd polling (only supports thread group * leaders). * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; struct pid *p; if (flags & ~PIDFD_NONBLOCK) return -EINVAL; if (pid <= 0) return -EINVAL; p = find_get_pid(pid); if (!p) return -ESRCH; fd = pidfd_create(p, flags); put_pid(p); return fd; } void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ pid_max = min(pid_max_max, max_t(int, pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min); idr_init(&init_pid_ns.idr); init_pid_ns.pid_cachep = KMEM_CACHE(pid, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); } static struct file *__pidfd_fget(struct task_struct *task, int fd) { struct file *file; int ret; ret = down_read_killable(&task->signal->exec_update_lock); if (ret) return ERR_PTR(ret); if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) file = fget_task(task, fd); else file = ERR_PTR(-EPERM); up_read(&task->signal->exec_update_lock); return file ?: ERR_PTR(-EBADF); } static int pidfd_getfd(struct pid *pid, int fd) { struct task_struct *task; struct file *file; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; file = __pidfd_fget(task, fd); put_task_struct(task); if (IS_ERR(file)) return PTR_ERR(file); ret = receive_fd(file, O_CLOEXEC); fput(file); return ret; } /** * sys_pidfd_getfd() - Get a file descriptor from another process * * @pidfd: the pidfd file descriptor of the process * @fd: the file descriptor number to get * @flags: flags on how to get the fd (reserved) * * This syscall gets a copy of a file descriptor from another process * based on the pidfd, and file descriptor number. It requires that * the calling process has the ability to ptrace the process represented * by the pidfd. The process which is having its file descriptor copied * is otherwise unaffected. * * Return: On success, a cloexec file descriptor is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd, unsigned int, flags) { struct pid *pid; struct fd f; int ret; /* flags is currently unused - make sure it's unset */ if (flags) return -EINVAL; f = fdget(pidfd); if (!f.file) return -EBADF; pid = pidfd_pid(f.file); if (IS_ERR(pid)) ret = PTR_ERR(pid); else ret = pidfd_getfd(pid, fd); fdput(f); return ret; } |
| 2577 2063 2061 10 2059 2003 2070 2038 2039 2038 2044 92 92 93 1690 1691 10 1694 1392 1700 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Percpu refcounts: * (C) 2012 Google, Inc. * Author: Kent Overstreet <koverstreet@google.com> * * This implements a refcount with similar semantics to atomic_t - atomic_inc(), * atomic_dec_and_test() - but percpu. * * There's one important difference between percpu refs and normal atomic_t * refcounts; you have to keep track of your initial refcount, and then when you * start shutting down you call percpu_ref_kill() _before_ dropping the initial * refcount. * * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less * than an atomic_t - this is because of the way shutdown works, see * percpu_ref_kill()/PERCPU_COUNT_BIAS. * * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill() * puts the ref back in single atomic_t mode, collecting the per cpu refs and * issuing the appropriate barriers, and then marks the ref as shutting down so * that percpu_ref_put() will check for the ref hitting 0. After it returns, * it's safe to drop the initial ref. * * USAGE: * * See fs/aio.c for some example usage; it's used there for struct kioctx, which * is created when userspaces calls io_setup(), and destroyed when userspace * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. * After that, there can't be any new users of the kioctx (from lookup_ioctx()) * and it's then safe to drop the initial ref with percpu_ref_put(). * * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't * imply RCU grace periods of any kind and if a user wants to combine percpu_ref * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped * once - percpu_ref_kill() does this for you, it returns true once and false if * someone else already called it. The aio code uses it this way, but it's not * necessary if the code has some other mechanism to synchronize teardown. * around. */ #ifndef _LINUX_PERCPU_REFCOUNT_H #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/gfp.h> struct percpu_ref; typedef void (percpu_ref_func_t)(struct percpu_ref *); /* flags set in the lower bits of percpu_ref->percpu_count_ptr */ enum { __PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */ __PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */ __PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD, __PERCPU_REF_FLAG_BITS = 2, }; /* @flags for percpu_ref_init() */ enum { /* * Start w/ ref == 1 in atomic mode. Can be switched to percpu * operation using percpu_ref_switch_to_percpu(). If initialized * with this flag, the ref will stay in atomic mode until * percpu_ref_switch_to_percpu() is invoked on it. * Implies ALLOW_REINIT. */ PERCPU_REF_INIT_ATOMIC = 1 << 0, /* * Start dead w/ ref == 0 in atomic mode. Must be revived with * percpu_ref_reinit() before used. Implies INIT_ATOMIC and * ALLOW_REINIT. */ PERCPU_REF_INIT_DEAD = 1 << 1, /* * Allow switching from atomic mode to percpu mode. */ PERCPU_REF_ALLOW_REINIT = 1 << 2, }; struct percpu_ref_data { atomic_long_t count; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; struct percpu_ref *ref; }; struct percpu_ref { /* * The low bit of the pointer indicates whether the ref is in percpu * mode; if set, then get/put will manipulate the atomic_t. */ unsigned long percpu_count_ptr; /* * 'percpu_ref' is often embedded into user structure, and only * 'percpu_count_ptr' is required in fast path, move other fields * into 'percpu_ref_data', so we can reduce memory footprint in * fast path. */ struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp); void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch); void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref * @ref: percpu_ref to kill * * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * * Switches @ref into atomic mode before gathering up the percpu counters * and dropping the initial ref. * * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { percpu_ref_kill_and_confirm(ref, NULL); } /* * Internal helper. Don't use outside percpu-refcount proper. The * function doesn't return the pointer and let the caller test it for NULL * because doing so forces the compiler to generate two conditional * branches as it can't assume that @ref->percpu_count is not NULL. */ static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { unsigned long percpu_ptr; /* * The value of @ref->percpu_count_ptr is tested for * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then * used as a pointer. If the compiler generates a separate fetch * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in * between contaminating the pointer value, meaning that * READ_ONCE() is required when fetching it. * * The dependency ordering from the READ_ONCE() pairs * with smp_store_release() in __percpu_ref_switch_to_percpu(). */ percpu_ptr = READ_ONCE(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, * then we'd have to mask off DEAD separately as DEAD may be * visible without ATOMIC if we race with percpu_ref_kill(). DEAD * implies ATOMIC anyway. Test them together. */ if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD)) return false; *percpu_countp = (unsigned long __percpu *)percpu_ptr; return true; } /** * percpu_ref_get_many - increment a percpu refcount * @ref: percpu_ref to get * @nr: number of references to get * * Analogous to atomic_long_add(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } /** * percpu_ref_get - increment a percpu refcount * @ref: percpu_ref to get * * Analogous to atomic_long_inc(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get(struct percpu_ref *ref) { percpu_ref_get_many(ref, 1); } /** * percpu_ref_tryget_many - try to increment a percpu refcount * @ref: percpu_ref to try-get * @nr: number of references to get * * Increment a percpu refcount by @nr unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; bool ret; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_add(*percpu_count, nr); ret = true; } else { ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); return ret; } /** * percpu_ref_tryget - try to increment a percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget(struct percpu_ref *ref) { return percpu_ref_tryget_many(ref, 1); } /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless it has already been killed. Returns * %true on success; %false on failure. * * Completion of percpu_ref_kill() in itself doesn't guarantee that this * function will fail. For such guarantee, percpu_ref_kill_and_confirm() * should be used. After the confirm_kill callback is invoked, it's * guaranteed that no new reference will be given out by * percpu_ref_tryget_live(). * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; bool ret = false; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->data->count); } rcu_read_unlock(); return ret; } /** * percpu_ref_put_many - decrement a percpu refcount * @ref: percpu_ref to put * @nr: number of references to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) ref->data->release(ref); rcu_read_unlock(); } /** * percpu_ref_put - decrement a percpu refcount * @ref: percpu_ref to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put(struct percpu_ref *ref) { percpu_ref_put_many(ref, 1); } /** * percpu_ref_is_dying - test whether a percpu refcount is dying or dead * @ref: percpu_ref to test * * Returns %true if @ref is dying or dead. * * This function is safe to call as long as @ref is between init and exit * and the caller is responsible for synchronizing against state changes. */ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) { return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } #endif |
| 25 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains the procedures for the handling of select and poll * * Created for Linux based loosely upon Mathius Lattner's minix * patches by Peter MacDonald. Heavily edited by Linus. * * 4 February 1994 * COFF/ELF binary emulation. If the process has the STICKY_TIMEOUTS * flag set in its personality we do *not* modify the given timeout * parameter to reflect time remaining. * * 24 January 2000 * Changed sys_poll()/do_poll() to use PAGE_SIZE chunk-based allocation * of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian). */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/sched/rt.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/personality.h> /* for STICKY_TIMEOUTS */ #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/rcupdate.h> #include <linux/hrtimer.h> #include <linux/freezer.h> #include <net/busy_poll.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> /* * Estimate expected accuracy in ns from a timeval. * * After quite a bit of churning around, we've settled on * a simple thing of taking 0.1% of the timeout as the * slack, with a cap of 100 msec. * "nice" tasks get a 0.5% slack instead. * * Consider this comment an open invitation to come up with even * better solutions.. */ #define MAX_SLACK (100 * NSEC_PER_MSEC) static long __estimate_accuracy(struct timespec64 *tv) { long slack; int divfactor = 1000; if (tv->tv_sec < 0) return 0; if (task_nice(current) > 0) divfactor = divfactor / 5; if (tv->tv_sec > MAX_SLACK / (NSEC_PER_SEC/divfactor)) return MAX_SLACK; slack = tv->tv_nsec / divfactor; slack += tv->tv_sec * (NSEC_PER_SEC/divfactor); if (slack > MAX_SLACK) return MAX_SLACK; return slack; } u64 select_estimate_accuracy(struct timespec64 *tv) { u64 ret; struct timespec64 now; /* * Realtime tasks get a slack of 0 for obvious reasons. */ if (rt_task(current)) return 0; ktime_get_ts64(&now); now = timespec64_sub(*tv, now); ret = __estimate_accuracy(&now); if (ret < current->timer_slack_ns) return current->timer_slack_ns; return ret; } struct poll_table_page { struct poll_table_page * next; struct poll_table_entry * entry; struct poll_table_entry entries[]; }; #define POLL_TABLE_FULL(table) \ ((unsigned long)((table)->entry+1) > PAGE_SIZE + (unsigned long)(table)) /* * Ok, Peter made a complicated, but straightforward multiple_wait() function. * I have rewritten this, taking some shortcuts: This code may not be easy to * follow, but it should be free of race-conditions, and it's practical. If you * understand what I'm doing here, then you understand how the linux * sleep/wakeup mechanism works. * * Two very simple procedures, poll_wait() and poll_freewait() make all the * work. poll_wait() is an inline-function defined in <linux/poll.h>, * as all select/poll functions have to call it to add an entry to the * poll table. */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p); void poll_initwait(struct poll_wqueues *pwq) { init_poll_funcptr(&pwq->pt, __pollwait); pwq->polling_task = current; pwq->triggered = 0; pwq->error = 0; pwq->table = NULL; pwq->inline_index = 0; } EXPORT_SYMBOL(poll_initwait); static void free_poll_entry(struct poll_table_entry *entry) { remove_wait_queue(entry->wait_address, &entry->wait); fput(entry->filp); } void poll_freewait(struct poll_wqueues *pwq) { struct poll_table_page * p = pwq->table; int i; for (i = 0; i < pwq->inline_index; i++) free_poll_entry(pwq->inline_entries + i); while (p) { struct poll_table_entry * entry; struct poll_table_page *old; entry = p->entry; do { entry--; free_poll_entry(entry); } while (entry > p->entries); old = p; p = p->next; free_page((unsigned long) old); } } EXPORT_SYMBOL(poll_freewait); static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) { struct poll_table_page *table = p->table; if (p->inline_index < N_INLINE_POLL_ENTRIES) return p->inline_entries + p->inline_index++; if (!table || POLL_TABLE_FULL(table)) { struct poll_table_page *new_table; new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL); if (!new_table) { p->error = -ENOMEM; return NULL; } new_table->entry = new_table->entries; new_table->next = table; p->table = new_table; table = new_table; } return table->entry++; } static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_wqueues *pwq = wait->private; DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); /* * Although this function is called under waitqueue lock, LOCK * doesn't imply write barrier and the users expect write * barrier semantics on wakeup functions. The following * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() * and is paired with smp_store_mb() in poll_schedule_timeout. */ smp_wmb(); pwq->triggered = 1; /* * Perform the default wake up operation using a dummy * waitqueue. * * TODO: This is hacky but there currently is no interface to * pass in @sync. @sync is scheduled to be removed and once * that happens, wake_up_process() can be used directly. */ return default_wake_function(&dummy_wait, mode, sync, key); } static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_table_entry *entry; entry = container_of(wait, struct poll_table_entry, wait); if (key && !(key_to_poll(key) & entry->key)) return 0; return __pollwake(wait, mode, sync, key); } /* Add a new entry */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt); struct poll_table_entry *entry = poll_get_entry(pwq); if (!entry) return; entry->filp = get_file(filp); entry->wait_address = wait_address; entry->key = p->_key; init_waitqueue_func_entry(&entry->wait, pollwake); entry->wait.private = pwq; add_wait_queue(wait_address, &entry->wait); } static int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack) { int rc = -EINTR; set_current_state(state); if (!pwq->triggered) rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * Prepare for the next iteration. * * The following smp_store_mb() serves two purposes. First, it's * the counterpart rmb of the wmb in pollwake() such that data * written before wake up is always visible after wake up. * Second, the full barrier guarantees that triggered clearing * doesn't pass event check of the next iteration. Note that * this problem doesn't exist for the first iteration as * add_wait_queue() has full barrier semantics. */ smp_store_mb(pwq->triggered, 0); return rc; } /** * poll_select_set_timeout - helper function to setup the timeout value * @to: pointer to timespec64 variable for the final timeout * @sec: seconds (from user space) * @nsec: nanoseconds (from user space) * * Note, we do not use a timespec for the user space value here, That * way we can use the function for timeval and compat interfaces as well. * * Returns -EINVAL if sec/nsec are not normalized. Otherwise 0. */ int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec) { struct timespec64 ts = {.tv_sec = sec, .tv_nsec = nsec}; if (!timespec64_valid(&ts)) return -EINVAL; /* Optimize for the zero timeout value here */ if (!sec && !nsec) { to->tv_sec = to->tv_nsec = 0; } else { ktime_get_ts64(to); *to = timespec64_add_safe(*to, ts); } return 0; } enum poll_time_type { PT_TIMEVAL = 0, PT_OLD_TIMEVAL = 1, PT_TIMESPEC = 2, PT_OLD_TIMESPEC = 3, }; static int poll_select_finish(struct timespec64 *end_time, void __user *p, enum poll_time_type pt_type, int ret) { struct timespec64 rts; restore_saved_sigmask_unless(ret == -ERESTARTNOHAND); if (!p) return ret; if (current->personality & STICKY_TIMEOUTS) goto sticky; /* No update for zero timeout */ if (!end_time->tv_sec && !end_time->tv_nsec) return ret; ktime_get_ts64(&rts); rts = timespec64_sub(*end_time, rts); if (rts.tv_sec < 0) rts.tv_sec = rts.tv_nsec = 0; switch (pt_type) { case PT_TIMEVAL: { struct __kernel_old_timeval rtv; if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec)) memset(&rtv, 0, sizeof(rtv)); rtv.tv_sec = rts.tv_sec; rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } break; case PT_OLD_TIMEVAL: { struct old_timeval32 rtv; rtv.tv_sec = rts.tv_sec; rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } break; case PT_TIMESPEC: if (!put_timespec64(&rts, p)) return ret; break; case PT_OLD_TIMESPEC: if (!put_old_timespec32(&rts, p)) return ret; break; default: BUG(); } /* * If an application puts its timeval in read-only memory, we * don't want the Linux-specific update to the timeval to * cause a fault after the select has completed * successfully. However, because we're not updating the * timeval, we can't restart the system call. */ sticky: if (ret == -ERESTARTNOHAND) ret = -EINTR; return ret; } /* * Scalable version of the fd_set. */ typedef struct { unsigned long *in, *out, *ex; unsigned long *res_in, *res_out, *res_ex; } fd_set_bits; /* * How many longwords for "nr" bits? */ #define FDS_BITPERLONG (8*sizeof(long)) #define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG) #define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long)) /* * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned. */ static inline int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { nr = FDS_BYTES(nr); if (ufdset) return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0; memset(fdset, 0, nr); return 0; } static inline unsigned long __must_check set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { if (ufdset) return __copy_to_user(ufdset, fdset, FDS_BYTES(nr)); return 0; } static inline void zero_fd_set(unsigned long nr, unsigned long *fdset) { memset(fdset, 0, FDS_BYTES(nr)); } #define FDS_IN(fds, n) (fds->in + n) #define FDS_OUT(fds, n) (fds->out + n) #define FDS_EX(fds, n) (fds->ex + n) #define BITS(fds, n) (*FDS_IN(fds, n)|*FDS_OUT(fds, n)|*FDS_EX(fds, n)) static int max_select_fd(unsigned long n, fd_set_bits *fds) { unsigned long *open_fds; unsigned long set; int max; struct fdtable *fdt; /* handle last in-complete long-word first */ set = ~(~0UL << (n & (BITS_PER_LONG-1))); n /= BITS_PER_LONG; fdt = files_fdtable(current->files); open_fds = fdt->open_fds + n; max = 0; if (set) { set &= BITS(fds, n); if (set) { if (!(set & ~*open_fds)) goto get_max; return -EBADF; } } while (n) { open_fds--; n--; set = BITS(fds, n); if (!set) continue; if (set & ~*open_fds) return -EBADF; if (max) continue; get_max: do { max++; set >>= 1; } while (set); max += n * BITS_PER_LONG; } return max; } #define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR |\ EPOLLNVAL) #define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR |\ EPOLLNVAL) #define POLLEX_SET (EPOLLPRI | EPOLLNVAL) static inline void wait_key_set(poll_table *wait, unsigned long in, unsigned long out, unsigned long bit, __poll_t ll_flag) { wait->_key = POLLEX_SET | ll_flag; if (in & bit) wait->_key |= POLLIN_SET; if (out & bit) wait->_key |= POLLOUT_SET; } static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; poll_table *wait; int retval, i, timed_out = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; rcu_read_lock(); retval = max_select_fd(n, fds); rcu_read_unlock(); if (retval < 0) return retval; n = retval; poll_initwait(&table); wait = &table.pt; if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { wait->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(end_time); retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; bool can_busy_loop = false; inp = fds->in; outp = fds->out; exp = fds->ex; rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex; for (i = 0; i < n; ++rinp, ++routp, ++rexp) { unsigned long in, out, ex, all_bits, bit = 1, j; unsigned long res_in = 0, res_out = 0, res_ex = 0; __poll_t mask; in = *inp++; out = *outp++; ex = *exp++; all_bits = in | out | ex; if (all_bits == 0) { i += BITS_PER_LONG; continue; } for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) { struct fd f; if (i >= n) break; if (!(bit & all_bits)) continue; mask = EPOLLNVAL; f = fdget(i); if (f.file) { wait_key_set(wait, in, out, bit, busy_flag); mask = vfs_poll(f.file, wait); fdput(f); } if ((mask & POLLIN_SET) && (in & bit)) { res_in |= bit; retval++; wait->_qproc = NULL; } if ((mask & POLLOUT_SET) && (out & bit)) { res_out |= bit; retval++; wait->_qproc = NULL; } if ((mask & POLLEX_SET) && (ex & bit)) { res_ex |= bit; retval++; wait->_qproc = NULL; } /* got something, stop busy polling */ if (retval) { can_busy_loop = false; busy_flag = 0; /* * only remember a returned * POLL_BUSY_LOOP if we asked for it */ } else if (busy_flag & mask) can_busy_loop = true; } if (res_in) *rinp = res_in; if (res_out) *routp = res_out; if (res_ex) *rexp = res_ex; cond_resched(); } wait->_qproc = NULL; if (retval || timed_out || signal_pending(current)) break; if (table.error) { retval = table.error; break; } /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } poll_freewait(&table); return retval; } /* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int ret, max_fds; size_t size, alloc_size; struct fdtable *fdt; /* Allocate small arguments on the stack to save memory and be faster */ long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; ret = -EINVAL; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { /* Not enough space in on-stack array; must use kmalloc */ ret = -ENOMEM; if (size > (SIZE_MAX / 6)) goto out_nofds; alloc_size = 6 * size; bits = kvmalloc(alloc_size, GFP_KERNEL); if (!bits) goto out_nofds; } fds.in = bits; fds.out = bits + size; fds.ex = bits + 2*size; fds.res_in = bits + 3*size; fds.res_out = bits + 4*size; fds.res_ex = bits + 5*size; if ((ret = get_fd_set(n, inp, fds.in)) || (ret = get_fd_set(n, outp, fds.out)) || (ret = get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (set_fd_set(n, inp, fds.res_in) || set_fd_set(n, outp, fds.res_out) || set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kvfree(bits); out_nofds: return ret; } static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp) { struct timespec64 end_time, *to = NULL; struct __kernel_old_timeval tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; } ret = core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tvp, PT_TIMEVAL, ret); } SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_old_timeval __user *, tvp) { return kern_select(n, inp, outp, exp, tvp); } static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, void __user *tsp, const sigset_t __user *sigmask, size_t sigsetsize, enum poll_time_type type) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { switch (type) { case PT_TIMESPEC: if (get_timespec64(&ts, tsp)) return -EFAULT; break; case PT_OLD_TIMESPEC: if (get_old_timespec32(&ts, tsp)) return -EFAULT; break; default: BUG(); } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tsp, type, ret); } /* * Most architectures can't handle 7-argument syscalls. So we provide a * 6-argument version where the sixth argument is a pointer to a structure * which has a pointer to the sigset_t itself followed by a size_t containing * the sigset size. */ struct sigset_argpack { sigset_t __user *p; size_t size; }; static inline int get_sigset_argpack(struct sigset_argpack *to, struct sigset_argpack __user *from) { // the path is hot enough for overhead of copy_from_user() to matter if (from) { if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); user_read_access_end(); } return 0; Efault: user_access_end(); return -EFAULT; } SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_TIMESPEC); } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE6(pselect6_time32, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_OLD_TIMESPEC); } #endif #ifdef __ARCH_WANT_SYS_OLD_SELECT struct sel_arg_struct { unsigned long n; fd_set __user *inp, *outp, *exp; struct __kernel_old_timeval __user *tvp; }; SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) { struct sel_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; return kern_select(a.n, a.inp, a.outp, a.exp, a.tvp); } #endif struct poll_list { struct poll_list *next; int len; struct pollfd entries[]; }; #define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd)) /* * Fish for pollable events on the pollfd->fd file descriptor. We're only * interested in events matching the pollfd->events mask, and the result * matching that mask is both recorded in pollfd->revents and returned. The * pwait poll_table will be used by the fd-provided poll handler for waiting, * if pwait->_qproc is non-NULL. */ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait, bool *can_busy_poll, __poll_t busy_flag) { int fd = pollfd->fd; __poll_t mask = 0, filter; struct fd f; if (fd < 0) goto out; mask = EPOLLNVAL; f = fdget(fd); if (!f.file) goto out; /* userland u16 ->events contains POLL... bitmap */ filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP; pwait->_key = filter | busy_flag; mask = vfs_poll(f.file, pwait); if (mask & busy_flag) *can_busy_poll = true; mask &= filter; /* Mask out unneeded events. */ fdput(f); out: /* ... and so does ->revents */ pollfd->revents = mangle_poll(mask); return mask; } static int do_poll(struct poll_list *list, struct poll_wqueues *wait, struct timespec64 *end_time) { poll_table* pt = &wait->pt; ktime_t expire, *to = NULL; int timed_out = 0, count = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; /* Optimise the no-wait case */ if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { pt->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(end_time); for (;;) { struct poll_list *walk; bool can_busy_loop = false; for (walk = list; walk != NULL; walk = walk->next) { struct pollfd * pfd, * pfd_end; pfd = walk->entries; pfd_end = pfd + walk->len; for (; pfd != pfd_end; pfd++) { /* * Fish for events. If we found one, record it * and kill poll_table->_qproc, so we don't * needlessly register any other waiters after * this. They'll get immediately deregistered * when we break out and return. */ if (do_pollfd(pfd, pt, &can_busy_loop, busy_flag)) { count++; pt->_qproc = NULL; /* found something, stop busy polling */ busy_flag = 0; can_busy_loop = false; } } } /* * All waiters have already been registered, so don't provide * a poll_table->_qproc to them on the next loop iteration. */ pt->_qproc = NULL; if (!count) { count = wait->error; if (signal_pending(current)) count = -ERESTARTNOHAND; } if (count || timed_out) break; /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } return count; } #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \ sizeof(struct pollfd)) static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, struct timespec64 *end_time) { struct poll_wqueues table; int err = -EFAULT, fdcount, len; /* Allocate small arguments on the stack to save memory and be faster - use long to make sure the buffer is aligned properly on 64 bit archs to avoid unaligned access */ long stack_pps[POLL_STACK_ALLOC/sizeof(long)]; struct poll_list *const head = (struct poll_list *)stack_pps; struct poll_list *walk = head; unsigned long todo = nfds; if (nfds > rlimit(RLIMIT_NOFILE)) return -EINVAL; len = min_t(unsigned int, nfds, N_STACK_PPS); for (;;) { walk->next = NULL; walk->len = len; if (!len) break; if (copy_from_user(walk->entries, ufds + nfds-todo, sizeof(struct pollfd) * walk->len)) goto out_fds; todo -= walk->len; if (!todo) break; len = min(todo, POLLFD_PER_PAGE); walk = walk->next = kmalloc(struct_size(walk, entries, len), GFP_KERNEL); if (!walk) { err = -ENOMEM; goto out_fds; } } poll_initwait(&table); fdcount = do_poll(head, &table, end_time); poll_freewait(&table); if (!user_write_access_begin(ufds, nfds * sizeof(*ufds))) goto out_fds; for (walk = head; walk; walk = walk->next) { struct pollfd *fds = walk->entries; int j; for (j = walk->len; j; fds++, ufds++, j--) unsafe_put_user(fds->revents, &ufds->revents, Efault); } user_write_access_end(); err = fdcount; out_fds: walk = head->next; while (walk) { struct poll_list *pos = walk; walk = walk->next; kfree(pos); } return err; Efault: user_write_access_end(); err = -EFAULT; goto out_fds; } static long do_restart_poll(struct restart_block *restart_block) { struct pollfd __user *ufds = restart_block->poll.ufds; int nfds = restart_block->poll.nfds; struct timespec64 *to = NULL, end_time; int ret; if (restart_block->poll.has_timeout) { end_time.tv_sec = restart_block->poll.tv_sec; end_time.tv_nsec = restart_block->poll.tv_nsec; to = &end_time; } ret = do_sys_poll(ufds, nfds, to); if (ret == -ERESTARTNOHAND) ret = set_restart_fn(restart_block, do_restart_poll); return ret; } SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout_msecs) { struct timespec64 end_time, *to = NULL; int ret; if (timeout_msecs >= 0) { to = &end_time; poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC, NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC)); } ret = do_sys_poll(ufds, nfds, to); if (ret == -ERESTARTNOHAND) { struct restart_block *restart_block; restart_block = ¤t->restart_block; restart_block->poll.ufds = ufds; restart_block->poll.nfds = nfds; if (timeout_msecs >= 0) { restart_block->poll.tv_sec = end_time.tv_sec; restart_block->poll.tv_nsec = end_time.tv_nsec; restart_block->poll.has_timeout = 1; } else restart_block->poll.has_timeout = 0; ret = set_restart_fn(restart_block, do_restart_poll); } return ret; } SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_timespec64(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif #ifdef CONFIG_COMPAT #define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to * 64-bit unsigned longs. */ static int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { if (ufdset) { return compat_get_bitmap(fdset, ufdset, nr); } else { zero_fd_set(nr, fdset); return 0; } } static int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { if (!ufdset) return 0; return compat_put_bitmap(ufdset, fdset, nr); } /* * This is a virtual copy of sys_select from fs/select.c and probably * should be compared to it from time to time */ /* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ static int compat_core_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int size, max_fds, ret = -EINVAL; struct fdtable *fdt; long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { bits = kmalloc_array(6, size, GFP_KERNEL); ret = -ENOMEM; if (!bits) goto out_nofds; } fds.in = (unsigned long *) bits; fds.out = (unsigned long *) (bits + size); fds.ex = (unsigned long *) (bits + 2*size); fds.res_in = (unsigned long *) (bits + 3*size); fds.res_out = (unsigned long *) (bits + 4*size); fds.res_ex = (unsigned long *) (bits + 5*size); if ((ret = compat_get_fd_set(n, inp, fds.in)) || (ret = compat_get_fd_set(n, outp, fds.out)) || (ret = compat_get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (compat_set_fd_set(n, inp, fds.res_in) || compat_set_fd_set(n, outp, fds.res_out) || compat_set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kfree(bits); out_nofds: return ret; } static int do_compat_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timeval32 __user *tvp) { struct timespec64 end_time, *to = NULL; struct old_timeval32 tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; } ret = compat_core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tvp, PT_OLD_TIMEVAL, ret); } COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timeval32 __user *, tvp) { return do_compat_select(n, inp, outp, exp, tvp); } struct compat_sel_arg_struct { compat_ulong_t n; compat_uptr_t inp; compat_uptr_t outp; compat_uptr_t exp; compat_uptr_t tvp; }; COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) { struct compat_sel_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; return do_compat_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), compat_ptr(a.exp), compat_ptr(a.tvp)); } static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, void __user *tsp, compat_sigset_t __user *sigmask, compat_size_t sigsetsize, enum poll_time_type type) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { switch (type) { case PT_OLD_TIMESPEC: if (get_old_timespec32(&ts, tsp)) return -EFAULT; break; case PT_TIMESPEC: if (get_timespec64(&ts, tsp)) return -EFAULT; break; default: BUG(); } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = compat_core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tsp, type, ret); } struct compat_sigset_argpack { compat_uptr_t p; compat_size_t size; }; static inline int get_compat_sigset_argpack(struct compat_sigset_argpack *to, struct compat_sigset_argpack __user *from) { if (from) { if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); user_read_access_end(); } return 0; Efault: user_access_end(); return -EFAULT; } COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { struct compat_sigset_argpack x = {0, 0}; if (get_compat_sigset_argpack(&x, sig)) return -EFAULT; return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), x.size, PT_TIMESPEC); } #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE6(pselect6_time32, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct compat_sigset_argpack x = {0, 0}; if (get_compat_sigset_argpack(&x, sig)) return -EFAULT; return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), x.size, PT_OLD_TIMESPEC); } #endif #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif /* New compat syscall for 64 bit time_t*/ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_timespec64(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } #endif |
| 49 49 49 49 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | // SPDX-License-Identifier: GPL-2.0 /* * procfs-based user access to knfsd statistics * * /proc/net/rpc/nfsd * * Format: * rc <hits> <misses> <nocache> * Statistsics for the reply cache * fh <stale> <deprecated filehandle cache stats> * statistics for filehandle lookup * io <bytes-read> <bytes-written> * statistics for IO throughput * th <threads> <deprecated thread usage histogram stats> * number of threads * ra <deprecated ra-cache stats> * * plus generic RPC stats (see net/sunrpc/stats.c) * * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ #include <linux/seq_file.h> #include <linux/module.h> #include <linux/sunrpc/stats.h> #include <net/net_namespace.h> #include "nfsd.h" static int nfsd_show(struct seq_file *seq, void *v) { struct net *net = PDE_DATA(file_inode(seq->file)); struct nfsd_net *nn = net_generic(net, nfsd_net_id); int i; seq_printf(seq, "rc %lld %lld %lld\nfh %lld 0 0 0 0\nio %lld %lld\n", percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_HITS]), percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_MISSES]), percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_NOCACHE]), percpu_counter_sum_positive(&nn->counter[NFSD_STATS_FH_STALE]), percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_READ]), percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_WRITE])); /* thread usage: */ seq_printf(seq, "th %u 0", atomic_read(&nfsd_th_cnt)); /* deprecated thread usage histogram stats */ for (i = 0; i < 10; i++) seq_puts(seq, " 0.000"); /* deprecated ra-cache stats */ seq_puts(seq, "\nra 0 0 0 0 0 0 0 0 0 0 0 0\n"); /* show my rpc info */ svc_seq_show(seq, &nn->nfsd_svcstats); #ifdef CONFIG_NFSD_V4 /* Show count for individual nfsv4 operations */ /* Writing operation numbers 0 1 2 also for maintaining uniformity */ seq_printf(seq,"proc4ops %u", LAST_NFS4_OP + 1); for (i = 0; i <= LAST_NFS4_OP; i++) { seq_printf(seq, " %lld", percpu_counter_sum_positive(&nn->counter[NFSD_STATS_NFS4_OP(i)])); } seq_putc(seq, '\n'); #endif return 0; } DEFINE_PROC_SHOW_ATTRIBUTE(nfsd); int nfsd_percpu_counters_init(struct percpu_counter *counters, int num) { int i, err = 0; for (i = 0; !err && i < num; i++) err = percpu_counter_init(&counters[i], 0, GFP_KERNEL); if (!err) return 0; for (; i > 0; i--) percpu_counter_destroy(&counters[i-1]); return err; } void nfsd_percpu_counters_reset(struct percpu_counter counters[], int num) { int i; for (i = 0; i < num; i++) percpu_counter_set(&counters[i], 0); } void nfsd_percpu_counters_destroy(struct percpu_counter counters[], int num) { int i; for (i = 0; i < num; i++) percpu_counter_destroy(&counters[i]); } int nfsd_stat_counters_init(struct nfsd_net *nn) { return nfsd_percpu_counters_init(nn->counter, NFSD_STATS_COUNTERS_NUM); } void nfsd_stat_counters_destroy(struct nfsd_net *nn) { nfsd_percpu_counters_destroy(nn->counter, NFSD_STATS_COUNTERS_NUM); } void nfsd_proc_stat_init(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); svc_proc_register(net, &nn->nfsd_svcstats, &nfsd_proc_ops); } void nfsd_proc_stat_shutdown(struct net *net) { svc_proc_unregister(net, "nfsd"); } |
| 1 1 3 1 3 8 8 7 1 1 1 5 4 3 3 4 2 1 7 7 7 1 6 7 7 7 1151 952 937 12 1504 47 10 40 7 47 18 2 4 19 1 23 189 170 7 291 8 1 6 5 440 982 983 1445 14 17 77 2121 221 1973 2031 486 13 41 1551 188 1366 868 573 1255 1258 208 1973 176 150 130 28 28 125 125 6 6 4 4 3 1 1095 1094 1092 1084 1087 1086 1860 1865 1864 1222 1216 1216 41 40 41 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 | // SPDX-License-Identifier: GPL-2.0 /* * NETLINK Netlink attributes * * Authors: Thomas Graf <tgraf@suug.ch> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/nospec.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h> #include <net/netlink.h> /* For these data types, attribute length should be exactly the given * size. However, to maintain compatibility with broken commands, if the * attribute length does not match the expected size a warning is emitted * to the user that the command is sending invalid data and needs to be fixed. */ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = { [NLA_U8] = sizeof(u8), [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), [NLA_S8] = sizeof(s8), [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), }; static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = { [NLA_U8] = sizeof(u8), [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), [NLA_MSECS] = sizeof(u64), [NLA_NESTED] = NLA_HDRLEN, [NLA_S8] = sizeof(s8), [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), }; /* * Nested policies might refer back to the original * policy in some cases, and userspace could try to * abuse that and recurse by nesting in the right * ways. Limit recursion to avoid this problem. */ #define MAX_POLICY_RECURSION_DEPTH 10 static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, struct nlattr **tb, unsigned int depth); static int validate_nla_bitfield32(const struct nlattr *nla, const u32 valid_flags_mask) { const struct nla_bitfield32 *bf = nla_data(nla); if (!valid_flags_mask) return -EINVAL; /*disallow invalid bit selector */ if (bf->selector & ~valid_flags_mask) return -EINVAL; /*disallow invalid bit values */ if (bf->value & ~valid_flags_mask) return -EINVAL; /*disallow valid bit values that are not selected*/ if (bf->value & ~bf->selector) return -EINVAL; return 0; } static int nla_validate_array(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack, unsigned int validate, unsigned int depth) { const struct nlattr *entry; int rem; nla_for_each_attr(entry, head, len, rem) { int ret; if (nla_len(entry) == 0) continue; if (nla_len(entry) < NLA_HDRLEN) { NL_SET_ERR_MSG_ATTR_POL(extack, entry, policy, "Array element too short"); return -ERANGE; } ret = __nla_validate_parse(nla_data(entry), nla_len(entry), maxtype, policy, validate, extack, NULL, depth + 1); if (ret < 0) return ret; } return 0; } void nla_get_range_unsigned(const struct nla_policy *pt, struct netlink_range_validation *range) { WARN_ON_ONCE(pt->validation_type != NLA_VALIDATE_RANGE_PTR && (pt->min < 0 || pt->max < 0)); range->min = 0; switch (pt->type) { case NLA_U8: range->max = U8_MAX; break; case NLA_U16: case NLA_BINARY: range->max = U16_MAX; break; case NLA_U32: range->max = U32_MAX; break; case NLA_U64: case NLA_MSECS: range->max = U64_MAX; break; default: WARN_ON_ONCE(1); return; } switch (pt->validation_type) { case NLA_VALIDATE_RANGE: case NLA_VALIDATE_RANGE_WARN_TOO_LONG: range->min = pt->min; range->max = pt->max; break; case NLA_VALIDATE_RANGE_PTR: *range = *pt->range; break; case NLA_VALIDATE_MIN: range->min = pt->min; break; case NLA_VALIDATE_MAX: range->max = pt->max; break; default: break; } } static int nla_validate_range_unsigned(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, unsigned int validate) { struct netlink_range_validation range; u64 value; switch (pt->type) { case NLA_U8: value = nla_get_u8(nla); break; case NLA_U16: value = nla_get_u16(nla); break; case NLA_U32: value = nla_get_u32(nla); break; case NLA_U64: case NLA_MSECS: value = nla_get_u64(nla); break; case NLA_BINARY: value = nla_len(nla); break; default: return -EINVAL; } nla_get_range_unsigned(pt, &range); if (pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG && pt->type == NLA_BINARY && value > range.max) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, pt->type); if (validate & NL_VALIDATE_STRICT_ATTRS) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } /* this assumes min <= max (don't validate against min) */ return 0; } if (value < range.min || value > range.max) { bool binary = pt->type == NLA_BINARY; if (binary) NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "binary attribute size out of range"); else NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "integer out of range"); return -ERANGE; } return 0; } void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range) { switch (pt->type) { case NLA_S8: range->min = S8_MIN; range->max = S8_MAX; break; case NLA_S16: range->min = S16_MIN; range->max = S16_MAX; break; case NLA_S32: range->min = S32_MIN; range->max = S32_MAX; break; case NLA_S64: range->min = S64_MIN; range->max = S64_MAX; break; default: WARN_ON_ONCE(1); return; } switch (pt->validation_type) { case NLA_VALIDATE_RANGE: range->min = pt->min; range->max = pt->max; break; case NLA_VALIDATE_RANGE_PTR: *range = *pt->range_signed; break; case NLA_VALIDATE_MIN: range->min = pt->min; break; case NLA_VALIDATE_MAX: range->max = pt->max; break; default: break; } } static int nla_validate_int_range_signed(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct netlink_range_validation_signed range; s64 value; switch (pt->type) { case NLA_S8: value = nla_get_s8(nla); break; case NLA_S16: value = nla_get_s16(nla); break; case NLA_S32: value = nla_get_s32(nla); break; case NLA_S64: value = nla_get_s64(nla); break; default: return -EINVAL; } nla_get_range_signed(pt, &range); if (value < range.min || value > range.max) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "integer out of range"); return -ERANGE; } return 0; } static int nla_validate_int_range(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, unsigned int validate) { switch (pt->type) { case NLA_U8: case NLA_U16: case NLA_U32: case NLA_U64: case NLA_MSECS: case NLA_BINARY: return nla_validate_range_unsigned(pt, nla, extack, validate); case NLA_S8: case NLA_S16: case NLA_S32: case NLA_S64: return nla_validate_int_range_signed(pt, nla, extack); default: WARN_ON(1); return -EINVAL; } } static int nla_validate_mask(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack) { u64 value; switch (pt->type) { case NLA_U8: value = nla_get_u8(nla); break; case NLA_U16: value = nla_get_u16(nla); break; case NLA_U32: value = nla_get_u32(nla); break; case NLA_U64: value = nla_get_u64(nla); break; default: return -EINVAL; } if (value & ~(u64)pt->mask) { NL_SET_ERR_MSG_ATTR(extack, nla, "reserved bit set"); return -EINVAL; } return 0; } static int validate_nla(const struct nlattr *nla, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, unsigned int depth) { u16 strict_start_type = policy[0].strict_start_type; const struct nla_policy *pt; int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla); int err = -ERANGE; if (strict_start_type && type >= strict_start_type) validate |= NL_VALIDATE_STRICT; if (type <= 0 || type > maxtype) return 0; type = array_index_nospec(type, maxtype + 1); pt = &policy[type]; BUG_ON(pt->type > NLA_TYPE_MAX); if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, type); if (validate & NL_VALIDATE_STRICT_ATTRS) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } } if (validate & NL_VALIDATE_NESTED) { if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) && !(nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "NLA_F_NESTED is missing"); return -EINVAL; } if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY && pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "NLA_F_NESTED not expected"); return -EINVAL; } } switch (pt->type) { case NLA_REJECT: if (extack && pt->reject_message) { NL_SET_BAD_ATTR(extack, nla); extack->_msg = pt->reject_message; return -EINVAL; } err = -EINVAL; goto out_err; case NLA_FLAG: if (attrlen > 0) goto out_err; break; case NLA_BITFIELD32: if (attrlen != sizeof(struct nla_bitfield32)) goto out_err; err = validate_nla_bitfield32(nla, pt->bitfield32_valid); if (err) goto out_err; break; case NLA_NUL_STRING: if (pt->len) minlen = min_t(int, attrlen, pt->len + 1); else minlen = attrlen; if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL) { err = -EINVAL; goto out_err; } fallthrough; case NLA_STRING: if (attrlen < 1) goto out_err; if (pt->len) { char *buf = nla_data(nla); if (buf[attrlen - 1] == '\0') attrlen--; if (attrlen > pt->len) goto out_err; } break; case NLA_BINARY: if (pt->len && attrlen > pt->len) goto out_err; break; case NLA_NESTED: /* a nested attributes is allowed to be empty; if its not, * it must have a size of at least NLA_HDRLEN. */ if (attrlen == 0) break; if (attrlen < NLA_HDRLEN) goto out_err; if (pt->nested_policy) { err = __nla_validate_parse(nla_data(nla), nla_len(nla), pt->len, pt->nested_policy, validate, extack, NULL, depth + 1); if (err < 0) { /* * return directly to preserve the inner * error message/attribute pointer */ return err; } } break; case NLA_NESTED_ARRAY: /* a nested array attribute is allowed to be empty; if its not, * it must have a size of at least NLA_HDRLEN. */ if (attrlen == 0) break; if (attrlen < NLA_HDRLEN) goto out_err; if (pt->nested_policy) { int err; err = nla_validate_array(nla_data(nla), nla_len(nla), pt->len, pt->nested_policy, extack, validate, depth); if (err < 0) { /* * return directly to preserve the inner * error message/attribute pointer */ return err; } } break; case NLA_UNSPEC: if (validate & NL_VALIDATE_UNSPEC) { NL_SET_ERR_MSG_ATTR(extack, nla, "Unsupported attribute"); return -EINVAL; } if (attrlen < pt->len) goto out_err; break; default: if (pt->len) minlen = pt->len; else minlen = nla_attr_minlen[pt->type]; if (attrlen < minlen) goto out_err; } /* further validation */ switch (pt->validation_type) { case NLA_VALIDATE_NONE: /* nothing to do */ break; case NLA_VALIDATE_RANGE_PTR: case NLA_VALIDATE_RANGE: case NLA_VALIDATE_RANGE_WARN_TOO_LONG: case NLA_VALIDATE_MIN: case NLA_VALIDATE_MAX: err = nla_validate_int_range(pt, nla, extack, validate); if (err) return err; break; case NLA_VALIDATE_MASK: err = nla_validate_mask(pt, nla, extack); if (err) return err; break; case NLA_VALIDATE_FUNCTION: if (pt->validate) { err = pt->validate(nla, extack); if (err) return err; } break; } return 0; out_err: NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "Attribute failed policy validation"); return err; } static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, struct nlattr **tb, unsigned int depth) { const struct nlattr *nla; int rem; if (depth >= MAX_POLICY_RECURSION_DEPTH) { NL_SET_ERR_MSG(extack, "allowed policy recursion depth exceeded"); return -EINVAL; } if (tb) memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); nla_for_each_attr(nla, head, len, rem) { u16 type = nla_type(nla); if (type == 0 || type > maxtype) { if (validate & NL_VALIDATE_MAXTYPE) { NL_SET_ERR_MSG_ATTR(extack, nla, "Unknown attribute type"); return -EINVAL; } continue; } type = array_index_nospec(type, maxtype + 1); if (policy) { int err = validate_nla(nla, maxtype, policy, validate, extack, depth); if (err < 0) return err; } if (tb) tb[type] = (struct nlattr *)nla; } if (unlikely(rem > 0)) { pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n", rem, current->comm); NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes"); if (validate & NL_VALIDATE_TRAILING) return -EINVAL; } return 0; } /** * __nla_validate - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation depends on the validate flags passed, see * &enum netlink_validation for more details on that. * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ int __nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate_parse(head, len, maxtype, policy, validate, extack, NULL, 0); } EXPORT_SYMBOL(__nla_validate); /** * nla_policy_len - Determine the max. length of a policy * @policy: policy to use * @n: number of policies * * Determines the max. length of the policy. It is currently used * to allocated Netlink buffers roughly the size of the actual * message. * * Returns 0 on success or a negative error code. */ int nla_policy_len(const struct nla_policy *p, int n) { int i, len = 0; for (i = 0; i < n; i++, p++) { if (p->len) len += nla_total_size(p->len); else if (nla_attr_len[p->type]) len += nla_total_size(nla_attr_len[p->type]); else if (nla_attr_minlen[p->type]) len += nla_total_size(nla_attr_minlen[p->type]); } return len; } EXPORT_SYMBOL(nla_policy_len); /** * __nla_parse - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @validate: validation strictness * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. * Validation is controlled by the @validate parameter. * * Returns 0 on success or a negative error code. */ int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate_parse(head, len, maxtype, policy, validate, extack, tb, 0); } EXPORT_SYMBOL(__nla_parse); /** * nla_find - Find a specific attribute in a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @attrtype: type of attribute to look for * * Returns the first attribute in the stream matching the specified type. */ struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype) { const struct nlattr *nla; int rem; nla_for_each_attr(nla, head, len, rem) if (nla_type(nla) == attrtype) return (struct nlattr *)nla; return NULL; } EXPORT_SYMBOL(nla_find); /** * nla_strscpy - Copy string attribute payload into a sized buffer * @dst: Where to copy the string to. * @nla: Attribute to copy the string from. * @dstsize: Size of destination buffer. * * Copies at most dstsize - 1 bytes into the destination buffer. * Unlike strlcpy the destination buffer is always padded out. * * Return: * * srclen - Returns @nla length (not including the trailing %NUL). * * -E2BIG - If @dstsize is 0 or greater than U16_MAX or @nla length greater * than @dstsize. */ ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize) { size_t srclen = nla_len(nla); char *src = nla_data(nla); ssize_t ret; size_t len; if (dstsize == 0 || WARN_ON_ONCE(dstsize > U16_MAX)) return -E2BIG; if (srclen > 0 && src[srclen - 1] == '\0') srclen--; if (srclen >= dstsize) { len = dstsize - 1; ret = -E2BIG; } else { len = srclen; ret = len; } memcpy(dst, src, len); /* Zero pad end of dst. */ memset(dst + len, 0, dstsize - len); return ret; } EXPORT_SYMBOL(nla_strscpy); /** * nla_strdup - Copy string attribute payload into a newly allocated buffer * @nla: attribute to copy the string from * @flags: the type of memory to allocate (see kmalloc). * * Returns a pointer to the allocated buffer or NULL on error. */ char *nla_strdup(const struct nlattr *nla, gfp_t flags) { size_t srclen = nla_len(nla); char *src = nla_data(nla), *dst; if (srclen > 0 && src[srclen - 1] == '\0') srclen--; dst = kmalloc(srclen + 1, flags); if (dst != NULL) { memcpy(dst, src, srclen); dst[srclen] = '\0'; } return dst; } EXPORT_SYMBOL(nla_strdup); /** * nla_memcpy - Copy a netlink attribute into another memory area * @dest: where to copy to memcpy * @src: netlink attribute to copy from * @count: size of the destination area * * Note: The number of bytes copied is limited by the length of * attribute's payload. memcpy * * Returns the number of bytes copied. */ int nla_memcpy(void *dest, const struct nlattr *src, int count) { int minlen = min_t(int, count, nla_len(src)); memcpy(dest, nla_data(src), minlen); if (count > minlen) memset(dest + minlen, 0, count - minlen); return minlen; } EXPORT_SYMBOL(nla_memcpy); /** * nla_memcmp - Compare an attribute with sized memory area * @nla: netlink attribute * @data: memory area * @size: size of memory area */ int nla_memcmp(const struct nlattr *nla, const void *data, size_t size) { int d = nla_len(nla) - size; if (d == 0) d = memcmp(nla_data(nla), data, size); return d; } EXPORT_SYMBOL(nla_memcmp); /** * nla_strcmp - Compare a string attribute against a string * @nla: netlink string attribute * @str: another string */ int nla_strcmp(const struct nlattr *nla, const char *str) { int len = strlen(str); char *buf = nla_data(nla); int attrlen = nla_len(nla); int d; while (attrlen > 0 && buf[attrlen - 1] == '\0') attrlen--; d = attrlen - len; if (d == 0) d = memcmp(nla_data(nla), str, len); return d; } EXPORT_SYMBOL(nla_strcmp); #ifdef CONFIG_NET /** * __nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { struct nlattr *nla; nla = skb_put(skb, nla_total_size(attrlen)); nla->nla_type = attrtype; nla->nla_len = nla_attr_size(attrlen); memset((unsigned char *) nla + nla->nla_len, 0, nla_padlen(attrlen)); return nla; } EXPORT_SYMBOL(__nla_reserve); /** * __nla_reserve_64bit - reserve room for attribute on the skb and align it * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * @padattr: attribute type for the padding * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. It also ensure that this * attribute will have a 64-bit aligned nla_data() area. * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { nla_align_64bit(skb, padattr); return __nla_reserve(skb, attrtype, attrlen); } EXPORT_SYMBOL(__nla_reserve_64bit); /** * __nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * * The caller is responsible to ensure that the skb provides enough * tailroom for the payload. */ void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { return skb_put_zero(skb, NLA_ALIGN(attrlen)); } EXPORT_SYMBOL(__nla_reserve_nohdr); /** * nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute header and payload. */ struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) return NULL; return __nla_reserve(skb, attrtype, attrlen); } EXPORT_SYMBOL(nla_reserve); /** * nla_reserve_64bit - reserve room for attribute on the skb and align it * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * @padattr: attribute type for the padding * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. It also ensure that this * attribute will have a 64-bit aligned nla_data() area. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute header and payload. */ struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { size_t len; if (nla_need_padding_for_64bit(skb)) len = nla_total_size_64bit(attrlen); else len = nla_total_size(attrlen); if (unlikely(skb_tailroom(skb) < len)) return NULL; return __nla_reserve_64bit(skb, attrtype, attrlen, padattr); } EXPORT_SYMBOL(nla_reserve_64bit); /** * nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute payload. */ void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return NULL; return __nla_reserve_nohdr(skb, attrlen); } EXPORT_SYMBOL(nla_reserve_nohdr); /** * __nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { struct nlattr *nla; nla = __nla_reserve(skb, attrtype, attrlen); memcpy(nla_data(nla), data, attrlen); } EXPORT_SYMBOL(__nla_put); /** * __nla_put_64bit - Add a netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * @padattr: attribute type for the padding * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr) { struct nlattr *nla; nla = __nla_reserve_64bit(skb, attrtype, attrlen, padattr); memcpy(nla_data(nla), data, attrlen); } EXPORT_SYMBOL(__nla_put_64bit); /** * __nla_put_nohdr - Add a netlink attribute without header * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute payload. */ void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { void *start; start = __nla_reserve_nohdr(skb, attrlen); memcpy(start, data, attrlen); } EXPORT_SYMBOL(__nla_put_nohdr); /** * nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) return -EMSGSIZE; __nla_put(skb, attrtype, attrlen, data); return 0; } EXPORT_SYMBOL(nla_put); /** * nla_put_64bit - Add a netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * @padattr: attribute type for the padding * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr) { size_t len; if (nla_need_padding_for_64bit(skb)) len = nla_total_size_64bit(attrlen); else len = nla_total_size(attrlen); if (unlikely(skb_tailroom(skb) < len)) return -EMSGSIZE; __nla_put_64bit(skb, attrtype, attrlen, data, padattr); return 0; } EXPORT_SYMBOL(nla_put_64bit); /** * nla_put_nohdr - Add a netlink attribute without header * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; __nla_put_nohdr(skb, attrlen, data); return 0; } EXPORT_SYMBOL(nla_put_nohdr); /** * nla_append - Add a netlink attribute without header or padding * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_append(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; skb_put_data(skb, data, attrlen); return 0; } EXPORT_SYMBOL(nla_append); #endif |
| 97 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_64_H #define _ASM_X86_PGTABLE_64_H #include <linux/const.h> #include <asm/pgtable_64_types.h> #ifndef __ASSEMBLY__ /* * This file contains the functions and defines necessary to modify and use * the x86-64 page table tree. */ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> #include <asm/fixmap.h> extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt extern void paging_init(void); static inline void sync_initial_page_table(void) { } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pmd_val(e)) #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pud_val(e)) #if CONFIG_PGTABLE_LEVELS >= 5 #define p4d_ERROR(e) \ pr_err("%s:%d: bad p4d %p(%016lx)\n", \ __FILE__, __LINE__, &(e), p4d_val(e)) #endif #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) struct mm_struct; #define mm_p4d_folded mm_p4d_folded static inline bool mm_p4d_folded(struct mm_struct *mm) { return !pgtable_l5_enabled(); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); static inline void native_set_pte(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); } static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { native_set_pte(ptep, pte); } static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) { native_set_pmd(pmd, native_make_pmd(0)); } static inline pte_t native_ptep_get_and_clear(pte_t *xp) { #ifdef CONFIG_SMP return native_make_pte(xchg(&xp->pte, 0)); #else /* native_local_ptep_get_and_clear, but duplicated because of cyclic dependency */ pte_t ret = *xp; native_pte_clear(NULL, 0, xp); return ret; #endif } static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { #ifdef CONFIG_SMP return native_make_pmd(xchg(&xp->pmd, 0)); #else /* native_local_pmdp_get_and_clear, but duplicated because of cyclic dependency */ pmd_t ret = *xp; native_pmd_clear(xp); return ret; #endif } static inline void native_set_pud(pud_t *pudp, pud_t pud) { WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) { native_set_pud(pud, native_make_pud(0)); } static inline pud_t native_pudp_get_and_clear(pud_t *xp) { #ifdef CONFIG_SMP return native_make_pud(xchg(&xp->pud, 0)); #else /* native_local_pudp_get_and_clear, * but duplicated because of cyclic dependency */ pud_t ret = *xp; native_pud_clear(xp); return ret; #endif } static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) { native_set_p4d(p4d, native_make_p4d(0)); } static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) { native_set_pgd(pgd, native_make_pgd(0)); } /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ /* PGD - Level 4 access */ /* PUD - Level 3 access */ /* PMD - Level 2 access */ /* PTE - Level 1 access */ /* * Encode and de-code a swap entry * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| X|F|SD|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above * there. We also need to avoid using A and D because of an * erratum where they can be incorrectly set by hardware on * non-present PTEs. * * SD Bits 1-4 are not used in non-present format and available for * special use described below: * * SD (1) in swp entry is used to store soft dirty bit, which helps us * remember soft dirty over page migration * * F (2) in swp entry is used to record when a pagetable is * writeprotected by userfaultfd WP support. * * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. * * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define SWP_TYPE_BITS 5 #define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) /* We always extract/encode the offset by shifting it all the way up, and then down again */ #define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) /* Extract the high bits for type */ #define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS)) /* Shift up (to get rid of type), then down to get value */ #define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT) /* * Shift the offset up "too far" by TYPE bits, then down again * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define __swp_entry(type, offset) ((swp_entry_t) { \ (~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val((pmd)) }) #define __swp_entry_to_pte(x) (__pte((x).val)) #define __swp_entry_to_pmd(x) (__pmd((x).val)) extern int kern_addr_valid(unsigned long addr); extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 /* fs/proc/kcore.c */ #define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK) #define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK) #define __HAVE_ARCH_PTE_SAME #define vmemmap ((struct page *)VMEMMAP_START) extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); #define gup_fast_permitted gup_fast_permitted static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { if (end >> __VIRTUAL_MASK_SHIFT) return false; return true; } #include <asm/pgtable-invert.h> #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ |
| 60 2 12 64 180 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* AF_RXRPC internal definitions * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/atomic.h> #include <linux/seqlock.h> #include <linux/win_minmax.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <keys/rxrpc-type.h> #include "protocol.h" #define FCRYPT_BSIZE 8 struct rxrpc_crypt { union { u8 x[FCRYPT_BSIZE]; __be32 n[2]; }; } __attribute__((aligned(8))); #define rxrpc_queue_work(WS) queue_work(rxrpc_workqueue, (WS)) #define rxrpc_queue_delayed_work(WS,D) \ queue_delayed_work(rxrpc_workqueue, (WS), (D)) struct key_preparsed_payload; struct rxrpc_connection; /* * Mark applied to socket buffers in skb->mark. skb->priority is used * to pass supplementary information. */ enum rxrpc_skb_mark { RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */ RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */ }; /* * sk_state for RxRPC sockets */ enum { RXRPC_UNBOUND = 0, RXRPC_CLIENT_UNBOUND, /* Unbound socket used as client */ RXRPC_CLIENT_BOUND, /* client local address bound */ RXRPC_SERVER_BOUND, /* server local address bound */ RXRPC_SERVER_BOUND2, /* second server local address bound */ RXRPC_SERVER_LISTENING, /* server listening for connections */ RXRPC_SERVER_LISTEN_DISABLED, /* server listening disabled */ RXRPC_CLOSE, /* socket is being closed */ }; /* * Per-network namespace data. */ struct rxrpc_net { struct proc_dir_entry *proc_net; /* Subdir in /proc/net */ u32 epoch; /* Local epoch for detecting local-end reset */ struct list_head calls; /* List of calls active in this namespace */ spinlock_t call_lock; /* Lock for ->calls */ atomic_t nr_calls; /* Count of allocated calls */ atomic_t nr_conns; struct list_head conn_proc_list; /* List of conns in this namespace for proc */ struct list_head service_conns; /* Service conns in this namespace */ rwlock_t conn_lock; /* Lock for ->conn_proc_list, ->service_conns */ struct work_struct service_conn_reaper; struct timer_list service_conn_reap_timer; bool live; bool kill_all_client_conns; atomic_t nr_client_conns; spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */ spinlock_t client_conn_discard_lock; /* Prevent multiple discarders */ struct list_head idle_client_conns; struct work_struct client_conn_reaper; struct timer_list client_conn_reap_timer; struct hlist_head local_endpoints; struct mutex local_mutex; /* Lock for ->local_endpoints */ DECLARE_HASHTABLE (peer_hash, 10); spinlock_t peer_hash_lock; /* Lock for ->peer_hash */ #define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */ u8 peer_keepalive_cursor; time64_t peer_keepalive_base; struct list_head peer_keepalive[32]; struct list_head peer_keepalive_new; struct timer_list peer_keepalive_timer; struct work_struct peer_keepalive_work; }; /* * Service backlog preallocation. * * This contains circular buffers of preallocated peers, connections and calls * for incoming service calls and their head and tail pointers. This allows * calls to be set up in the data_ready handler, thereby avoiding the need to * shuffle packets around so much. */ struct rxrpc_backlog { unsigned short peer_backlog_head; unsigned short peer_backlog_tail; unsigned short conn_backlog_head; unsigned short conn_backlog_tail; unsigned short call_backlog_head; unsigned short call_backlog_tail; #define RXRPC_BACKLOG_MAX 32 struct rxrpc_peer *peer_backlog[RXRPC_BACKLOG_MAX]; struct rxrpc_connection *conn_backlog[RXRPC_BACKLOG_MAX]; struct rxrpc_call *call_backlog[RXRPC_BACKLOG_MAX]; }; /* * RxRPC socket definition */ struct rxrpc_sock { /* WARNING: sk has to be the first member */ struct sock sk; rxrpc_notify_new_call_t notify_new_call; /* Func to notify of new call */ rxrpc_discard_new_call_t discard_new_call; /* Func to discard a new call */ struct rxrpc_local *local; /* local endpoint */ struct rxrpc_backlog *backlog; /* Preallocation for services */ spinlock_t incoming_lock; /* Incoming call vs service shutdown lock */ struct list_head sock_calls; /* List of calls owned by this socket */ struct list_head to_be_accepted; /* calls awaiting acceptance */ struct list_head recvmsg_q; /* Calls awaiting recvmsg's attention */ rwlock_t recvmsg_lock; /* Lock for recvmsg_q */ struct key *key; /* security for this socket */ struct key *securities; /* list of server security descriptors */ struct rb_root calls; /* User ID -> call mapping */ unsigned long flags; #define RXRPC_SOCK_CONNECTED 0 /* connect_srx is set */ rwlock_t call_lock; /* lock for calls */ u32 min_sec_level; /* minimum security level */ #define RXRPC_SECURITY_MAX RXRPC_SECURITY_ENCRYPT bool exclusive; /* Exclusive connection for a client socket */ u16 second_service; /* Additional service bound to the endpoint */ struct { /* Service upgrade information */ u16 from; /* Service ID to upgrade (if not 0) */ u16 to; /* service ID to upgrade to */ } service_upgrade; sa_family_t family; /* Protocol family created with */ struct sockaddr_rxrpc srx; /* Primary Service/local addresses */ struct sockaddr_rxrpc connect_srx; /* Default client address from connect() */ }; #define rxrpc_sk(__sk) container_of((__sk), struct rxrpc_sock, sk) /* * CPU-byteorder normalised Rx packet header. */ struct rxrpc_host_header { u32 epoch; /* client boot timestamp */ u32 cid; /* connection and channel ID */ u32 callNumber; /* call ID (0 for connection-level packets) */ u32 seq; /* sequence number of pkt in call stream */ u32 serial; /* serial number of pkt sent to network */ u8 type; /* packet type */ u8 flags; /* packet flags */ u8 userStatus; /* app-layer defined status */ u8 securityIndex; /* security protocol ID */ union { u16 _rsvd; /* reserved */ u16 cksum; /* kerberos security checksum */ }; u16 serviceId; /* service ID */ } __packed; /* * RxRPC socket buffer private variables * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { atomic_t nr_ring_pins; /* Number of rxtx ring pins */ u8 nr_subpackets; /* Number of subpackets */ u8 rx_flags; /* Received packet flags */ #define RXRPC_SKB_INCL_LAST 0x01 /* - Includes last packet */ #define RXRPC_SKB_TX_BUFFER 0x02 /* - Is transmit buffer */ union { int remain; /* amount of space remaining for next write */ /* List of requested ACKs on subpackets */ unsigned long rx_req_ack[(RXRPC_MAX_NR_JUMBO + BITS_PER_LONG - 1) / BITS_PER_LONG]; }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; #define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb) /* * RxRPC security module interface */ struct rxrpc_security { const char *name; /* name of this service */ u8 security_index; /* security type provided */ u32 no_key_abort; /* Abort code indicating no key */ /* Initialise a security service */ int (*init)(void); /* Clean up a security service */ void (*exit)(void); /* Parse the information from a server key */ int (*preparse_server_key)(struct key_preparsed_payload *); /* Clean up the preparse buffer after parsing a server key */ void (*free_preparse_server_key)(struct key_preparsed_payload *); /* Destroy the payload of a server key */ void (*destroy_server_key)(struct key *); /* Describe a server key */ void (*describe_server_key)(const struct key *, struct seq_file *); /* initialise a connection's security */ int (*init_connection_security)(struct rxrpc_connection *, struct rxrpc_key_token *); /* Work out how much data we can store in a packet, given an estimate * of the amount of data remaining. */ int (*how_much_data)(struct rxrpc_call *, size_t, size_t *, size_t *, size_t *); /* impose security on a packet */ int (*secure_packet)(struct rxrpc_call *, struct sk_buff *, size_t); /* verify the security on a received packet */ int (*verify_packet)(struct rxrpc_call *, struct sk_buff *, unsigned int, unsigned int, rxrpc_seq_t, u16); /* Free crypto request on a call */ void (*free_call_crypto)(struct rxrpc_call *); /* Locate the data in a received packet that has been verified. */ void (*locate_data)(struct rxrpc_call *, struct sk_buff *, unsigned int *, unsigned int *); /* issue a challenge */ int (*issue_challenge)(struct rxrpc_connection *); /* respond to a challenge */ int (*respond_to_challenge)(struct rxrpc_connection *, struct sk_buff *, u32 *); /* verify a response */ int (*verify_response)(struct rxrpc_connection *, struct sk_buff *, u32 *); /* clear connection security */ void (*clear)(struct rxrpc_connection *); }; /* * RxRPC local transport endpoint description * - owned by a single AF_RXRPC socket * - pointed to by transport socket struct sk_user_data */ struct rxrpc_local { struct rcu_head rcu; atomic_t active_users; /* Number of users of the local endpoint */ refcount_t ref; /* Number of references to the structure */ struct rxrpc_net *rxnet; /* The network ns in which this resides */ struct hlist_node link; struct socket *socket; /* my UDP socket */ struct work_struct processor; struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head reject_queue; /* packets awaiting rejection */ struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */ struct rb_root client_bundles; /* Client connection bundles by socket params */ spinlock_t client_bundles_lock; /* Lock for client_bundles */ spinlock_t lock; /* access lock */ rwlock_t services_lock; /* lock for services list */ int debug_id; /* debug ID for printks */ bool dead; bool service_closed; /* Service socket closed */ struct sockaddr_rxrpc srx; /* local address */ }; /* * RxRPC remote transport endpoint definition * - matched by local endpoint, remote port, address and protocol type */ struct rxrpc_peer { struct rcu_head rcu; /* This must be first */ refcount_t ref; unsigned long hash_key; struct hlist_node hash_link; struct rxrpc_local *local; struct hlist_head error_targets; /* targets for net error distribution */ struct rb_root service_conns; /* Service connections */ struct list_head keepalive_link; /* Link in net->peer_keepalive[] */ time64_t last_tx_at; /* Last time packet sent here */ seqlock_t service_conn_lock; spinlock_t lock; /* access lock */ unsigned int if_mtu; /* interface MTU for this peer */ unsigned int mtu; /* network MTU for this peer */ unsigned int maxdata; /* data size (MTU - hdrsize) */ unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ int debug_id; /* debug ID for printks */ struct sockaddr_rxrpc srx; /* remote address */ /* calculated RTT cache */ #define RXRPC_RTT_CACHE_SIZE 32 spinlock_t rtt_input_lock; /* RTT lock for input routine */ ktime_t rtt_last_req; /* Time of last RTT request */ unsigned int rtt_count; /* Number of samples we've got */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ u32 rto_j; /* Retransmission timeout in jiffies */ u8 backoff; /* Backoff timeout */ u8 cong_cwnd; /* Congestion window size */ }; /* * Keys for matching a connection. */ struct rxrpc_conn_proto { union { struct { u32 epoch; /* epoch of this connection */ u32 cid; /* connection ID */ }; u64 index_key; }; }; struct rxrpc_conn_parameters { struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Remote endpoint */ struct key *key; /* Security details */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ u16 service_id; /* Service ID for this connection */ u32 security_level; /* Security level selected */ }; /* * Bits in the connection flags. */ enum rxrpc_conn_flag { RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */ RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */ RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */ RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */ RXRPC_CONN_FINAL_ACK_0, /* Need final ACK for channel 0 */ RXRPC_CONN_FINAL_ACK_1, /* Need final ACK for channel 1 */ RXRPC_CONN_FINAL_ACK_2, /* Need final ACK for channel 2 */ RXRPC_CONN_FINAL_ACK_3, /* Need final ACK for channel 3 */ }; #define RXRPC_CONN_FINAL_ACK_MASK ((1UL << RXRPC_CONN_FINAL_ACK_0) | \ (1UL << RXRPC_CONN_FINAL_ACK_1) | \ (1UL << RXRPC_CONN_FINAL_ACK_2) | \ (1UL << RXRPC_CONN_FINAL_ACK_3)) /* * Events that can be raised upon a connection. */ enum rxrpc_conn_event { RXRPC_CONN_EV_CHALLENGE, /* Send challenge packet */ }; /* * The connection protocol state. */ enum rxrpc_conn_proto_state { RXRPC_CONN_UNUSED, /* Connection not yet attempted */ RXRPC_CONN_CLIENT, /* Client connection */ RXRPC_CONN_SERVICE_PREALLOC, /* Service connection preallocation */ RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */ RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */ RXRPC_CONN_SERVICE, /* Service secured connection */ RXRPC_CONN_REMOTELY_ABORTED, /* Conn aborted by peer */ RXRPC_CONN_LOCALLY_ABORTED, /* Conn aborted locally */ RXRPC_CONN__NR_STATES }; /* * RxRPC client connection bundle. */ struct rxrpc_bundle { struct rxrpc_conn_parameters params; refcount_t ref; atomic_t active; /* Number of active users */ unsigned int debug_id; bool try_upgrade; /* True if the bundle is attempting upgrade */ bool alloc_conn; /* True if someone's getting a conn */ short alloc_error; /* Error from last conn allocation */ spinlock_t channel_lock; struct rb_node local_node; /* Node in local->client_conns */ struct list_head waiting_calls; /* Calls waiting for channels */ unsigned long avail_chans; /* Mask of available channels */ struct rxrpc_connection *conns[4]; /* The connections in the bundle (max 4) */ }; /* * RxRPC connection definition * - matched by { local, peer, epoch, conn_id, direction } * - each connection can only handle four simultaneous calls */ struct rxrpc_connection { struct rxrpc_conn_proto proto; struct rxrpc_conn_parameters params; refcount_t ref; struct rcu_head rcu; struct list_head cache_link; unsigned char act_chans; /* Mask of active channels */ struct rxrpc_channel { unsigned long final_ack_at; /* Time at which to issue final ACK */ struct rxrpc_call __rcu *call; /* Active call */ unsigned int call_debug_id; /* call->debug_id */ u32 call_id; /* ID of current call */ u32 call_counter; /* Call ID counter */ u32 last_call; /* ID of last call */ u8 last_type; /* Type of last packet */ union { u32 last_seq; u32 last_abort; }; } channels[RXRPC_MAXCALLS]; struct timer_list timer; /* Conn event timer */ struct work_struct processor; /* connection event processor */ struct rxrpc_bundle *bundle; /* Client connection bundle */ struct rb_node service_node; /* Node in peer->service_conns */ struct list_head proc_link; /* link in procfs list */ struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ const struct rxrpc_security *security; /* applied security module */ union { struct { struct crypto_sync_skcipher *cipher; /* encryption handle */ struct rxrpc_crypt csum_iv; /* packet checksum base */ u32 nonce; /* response re-use preventer */ } rxkad; }; unsigned long flags; unsigned long events; unsigned long idle_timestamp; /* Time at which last became idle */ spinlock_t state_lock; /* state-change lock */ enum rxrpc_conn_proto_state state; /* current state of connection */ u32 abort_code; /* Abort code of connection abort */ int debug_id; /* debug ID for printks */ atomic_t serial; /* packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ u32 service_id; /* Service ID, possibly upgraded */ u8 security_ix; /* security type */ u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */ u8 bundle_shift; /* Index into bundle->avail_chans */ short error; /* Local error code */ }; static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp) { return sp->hdr.flags & RXRPC_CLIENT_INITIATED; } static inline bool rxrpc_to_client(const struct rxrpc_skb_priv *sp) { return !rxrpc_to_server(sp); } /* * Flags in call->flags. */ enum rxrpc_call_flag { RXRPC_CALL_RELEASED, /* call has been released - no more message to userspace */ RXRPC_CALL_HAS_USERID, /* has a user ID attached */ RXRPC_CALL_IS_SERVICE, /* Call is service call */ RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ RXRPC_CALL_RX_UNDERRUN, /* Got data underrun */ RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ }; /* * Events that can be raised on a call. */ enum rxrpc_call_event { RXRPC_CALL_EV_ACK, /* need to generate ACK */ RXRPC_CALL_EV_ABORT, /* need to generate abort */ RXRPC_CALL_EV_RESEND, /* Tx resend required */ RXRPC_CALL_EV_PING, /* Ping send required */ RXRPC_CALL_EV_EXPIRED, /* Expiry occurred */ RXRPC_CALL_EV_ACK_LOST, /* ACK may be lost, send ping */ }; /* * The states that a call can be in. */ enum rxrpc_call_state { RXRPC_CALL_UNINITIALISED, RXRPC_CALL_CLIENT_AWAIT_CONN, /* - client waiting for connection to become available */ RXRPC_CALL_CLIENT_SEND_REQUEST, /* - client sending request phase */ RXRPC_CALL_CLIENT_AWAIT_REPLY, /* - client awaiting reply */ RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */ RXRPC_CALL_SERVER_PREALLOC, /* - service preallocation */ RXRPC_CALL_SERVER_SECURING, /* - server securing request connection */ RXRPC_CALL_SERVER_RECV_REQUEST, /* - server receiving request */ RXRPC_CALL_SERVER_ACK_REQUEST, /* - server pending ACK of request */ RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */ RXRPC_CALL_SERVER_AWAIT_ACK, /* - server awaiting final ACK */ RXRPC_CALL_COMPLETE, /* - call complete */ NR__RXRPC_CALL_STATES }; /* * Call completion condition (state == RXRPC_CALL_COMPLETE). */ enum rxrpc_call_completion { RXRPC_CALL_SUCCEEDED, /* - Normal termination */ RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ NR__RXRPC_CALL_COMPLETIONS }; /* * Call Tx congestion management modes. */ enum rxrpc_congest_mode { RXRPC_CALL_SLOW_START, RXRPC_CALL_CONGEST_AVOIDANCE, RXRPC_CALL_PACKET_LOSS, RXRPC_CALL_FAST_RETRANSMIT, NR__RXRPC_CONGEST_MODES }; /* * RxRPC call definition * - matched by { connection, call_id } */ struct rxrpc_call { struct rcu_head rcu; struct rxrpc_connection *conn; /* connection carrying call */ struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_sock __rcu *socket; /* socket responsible */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ unsigned long ack_at; /* When deferred ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ unsigned long resend_at; /* When next resend needs to happen */ unsigned long ping_at; /* When next to send a ping */ unsigned long keepalive_at; /* When next to send a keepalive ping */ unsigned long expect_rx_by; /* When we expect to get a packet by */ unsigned long expect_req_by; /* When we expect to get a request DATA packet by */ unsigned long expect_term_by; /* When we expect call termination by */ u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ struct skcipher_request *cipher_req; /* Packet cipher request buffer */ struct timer_list timer; /* Combined event timer */ struct work_struct processor; /* Event processor */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ struct list_head chan_wait_link; /* Link in conn->bundle->waiting_calls */ struct hlist_node error_link; /* link in error distribution list */ struct list_head accept_link; /* Link in rx->acceptq */ struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ struct list_head sock_link; /* Link in rx->sock_calls */ struct rb_node sock_node; /* Node in rx->calls */ struct sk_buff *tx_pending; /* Tx socket buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ s64 tx_total_len; /* Total length left to be transmitted (or -1) */ __be32 crypto_buf[2]; /* Temporary packet crypto buffer */ unsigned long user_call_ID; /* user-defined call ID */ unsigned long flags; unsigned long events; spinlock_t lock; spinlock_t notify_lock; /* Kernel notification lock */ rwlock_t state_lock; /* lock for state transition */ u32 abort_code; /* Local/remote abort code */ int error; /* Local error incurred */ enum rxrpc_call_state state; /* current state of call */ enum rxrpc_call_completion completion; /* Call completion condition */ refcount_t ref; u16 service_id; /* service ID */ u8 security_ix; /* Security type */ enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */ u32 call_id; /* call ID on connection */ u32 cid; /* connection ID plus channel index */ int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ bool rx_pkt_last; /* Current recvmsg packet is last */ /* Rx/Tx circular buffer, depending on phase. * * In the Rx phase, packets are annotated with 0 or the number of the * segment of a jumbo packet each buffer refers to. There can be up to * 47 segments in a maximum-size UDP packet. * * In the Tx phase, packets are annotated with which buffers have been * acked. */ #define RXRPC_RXTX_BUFF_SIZE 64 #define RXRPC_RXTX_BUFF_MASK (RXRPC_RXTX_BUFF_SIZE - 1) #define RXRPC_INIT_RX_WINDOW_SIZE 63 struct sk_buff **rxtx_buffer; u8 *rxtx_annotations; #define RXRPC_TX_ANNO_ACK 0 #define RXRPC_TX_ANNO_UNACK 1 #define RXRPC_TX_ANNO_NAK 2 #define RXRPC_TX_ANNO_RETRANS 3 #define RXRPC_TX_ANNO_MASK 0x03 #define RXRPC_TX_ANNO_LAST 0x04 #define RXRPC_TX_ANNO_RESENT 0x08 #define RXRPC_RX_ANNO_SUBPACKET 0x3f /* Subpacket number in jumbogram */ #define RXRPC_RX_ANNO_VERIFIED 0x80 /* Set if verified and decrypted */ rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but * not hard-ACK'd packet follows this. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ u16 tx_backoff; /* Delay to insert due to Tx failure */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA * packets) rather than bytes. */ #define RXRPC_TX_SMSS RXRPC_JUMBO_DATALEN u8 cong_cwnd; /* Congestion window size */ u8 cong_extra; /* Extra to send for congestion management */ u8 cong_ssthresh; /* Slow-start threshold */ enum rxrpc_congest_mode cong_mode:8; /* Congestion management mode */ u8 cong_dup_acks; /* Count of ACKs showing missing packets */ u8 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ rxrpc_seq_t rx_hard_ack; /* Dead slot in buffer; the first received but not * consumed packet follows this. */ rxrpc_seq_t rx_top; /* Highest Rx slot allocated. */ rxrpc_seq_t rx_expect_next; /* Expected next packet sequence number */ rxrpc_serial_t rx_serial; /* Highest serial received for this call */ u8 rx_winsize; /* Size of Rx window */ u8 tx_winsize; /* Maximum size of Tx window */ bool tx_phase; /* T if transmission phase, F if receive phase */ u8 nr_jumbo_bad; /* Number of jumbo dups/exceeds-windows */ spinlock_t input_lock; /* Lock for packet input to this call */ /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ rxrpc_seq_t ackr_highest_seq; /* Higest sequence number received */ atomic_t ackr_nr_unacked; /* Number of unacked packets */ atomic_t ackr_nr_consumed; /* Number of packets needing hard ACK */ /* RTT management */ rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ ktime_t rtt_sent_at[4]; /* Time packet sent */ unsigned long rtt_avail; /* Mask of available slots in bits 0-3, * Mask of pending samples in 8-11 */ #define RXRPC_CALL_RTT_AVAIL_MASK 0xf #define RXRPC_CALL_RTT_PEND_SHIFT 8 /* Transmission-phase ACK management (ACKs we've received). */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ rxrpc_seq_t acks_first_seq; /* first sequence number received */ rxrpc_seq_t acks_prev_seq; /* Highest previousPacket received */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ }; /* * Summary of a new ACK and the changes it made to the Tx buffer packet states. */ struct rxrpc_ack_summary { u8 ack_reason; u8 nr_acks; /* Number of ACKs in packet */ u8 nr_nacks; /* Number of NACKs in packet */ u8 nr_new_acks; /* Number of new ACKs in packet */ u8 nr_new_nacks; /* Number of new NACKs in packet */ u8 nr_rot_new_acks; /* Number of rotated new ACKs */ bool new_low_nack; /* T if new low NACK found */ bool retrans_timeo; /* T if reTx due to timeout happened */ u8 flight_size; /* Number of unreceived transmissions */ /* Place to stash values for tracing */ enum rxrpc_congest_mode mode:8; u8 cwnd; u8 ssthresh; u8 dup_acks; u8 cumulative_acks; }; /* * sendmsg() cmsg-specified parameters. */ enum rxrpc_command { RXRPC_CMD_SEND_DATA, /* send data message */ RXRPC_CMD_SEND_ABORT, /* request abort generation */ RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */ RXRPC_CMD_CHARGE_ACCEPT, /* [server] charge accept preallocation */ }; struct rxrpc_call_params { s64 tx_total_len; /* Total Tx data length (if send data) */ unsigned long user_call_ID; /* User's call ID */ struct { u32 hard; /* Maximum lifetime (sec) */ u32 idle; /* Max time since last data packet (msec) */ u32 normal; /* Max time since last call packet (msec) */ } timeouts; u8 nr_timeouts; /* Number of timeouts specified */ bool kernel; /* T if kernel is making the call */ enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */ }; struct rxrpc_send_params { struct rxrpc_call_params call; u32 abort_code; /* Abort code to Tx (if abort) */ enum rxrpc_command command : 8; /* The command to implement */ bool exclusive; /* Shared or exclusive call */ bool upgrade; /* If the connection is upgradeable */ }; #include <trace/events/rxrpc.h> /* * af_rxrpc.c */ extern atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; extern struct workqueue_struct *rxrpc_workqueue; /* * call_accept.c */ int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); void rxrpc_discard_prealloc(struct rxrpc_sock *); struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_sock *, struct sk_buff *); void rxrpc_accept_incoming_calls(struct rxrpc_local *); int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* * call_event.c */ void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool, enum rxrpc_propose_ack_trace); void rxrpc_process_call(struct work_struct *); void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long expire_at, unsigned long now, enum rxrpc_timer_trace why); void rxrpc_delete_call_timer(struct rxrpc_call *call); /* * call_object.c */ extern const char *const rxrpc_call_states[]; extern const char *const rxrpc_call_completions[]; extern unsigned int rxrpc_max_call_lifetime; extern struct kmem_cache *rxrpc_call_jar; struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long); struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int); struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, struct rxrpc_call_params *, gfp_t, unsigned int); void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); bool __rxrpc_queue_call(struct rxrpc_call *); bool rxrpc_queue_call(struct rxrpc_call *); void rxrpc_see_call(struct rxrpc_call *); bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op); void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_cleanup_call(struct rxrpc_call *); void rxrpc_destroy_all_calls(struct rxrpc_net *); static inline bool rxrpc_is_service_call(const struct rxrpc_call *call) { return test_bit(RXRPC_CALL_IS_SERVICE, &call->flags); } static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) { return !rxrpc_is_service_call(call); } /* * conn_client.c */ extern unsigned int rxrpc_reap_client_connections; extern unsigned long rxrpc_conn_idle_client_expiry; extern unsigned long rxrpc_conn_idle_client_fast_expiry; extern struct idr rxrpc_client_conn_ids; void rxrpc_destroy_client_conn_ids(void); struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *); void rxrpc_put_bundle(struct rxrpc_bundle *); int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, gfp_t); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); void rxrpc_put_client_conn(struct rxrpc_connection *); void rxrpc_discard_expired_client_conns(struct work_struct *); void rxrpc_destroy_all_client_connections(struct rxrpc_net *); void rxrpc_clean_up_local_conns(struct rxrpc_local *); /* * conn_event.c */ void rxrpc_process_connection(struct work_struct *); void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); /* * conn_object.c */ extern unsigned int rxrpc_connection_expiry; extern unsigned int rxrpc_closed_conn_expiry; struct rxrpc_connection *rxrpc_alloc_connection(gfp_t); struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, struct sk_buff *, struct rxrpc_peer **); void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_connection(struct rxrpc_connection *); bool rxrpc_queue_conn(struct rxrpc_connection *); void rxrpc_see_connection(struct rxrpc_connection *); struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *); struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *); void rxrpc_put_service_conn(struct rxrpc_connection *); void rxrpc_service_connection_reaper(struct work_struct *); void rxrpc_destroy_all_connections(struct rxrpc_net *); static inline bool rxrpc_conn_is_client(const struct rxrpc_connection *conn) { return conn->out_clientflag; } static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn) { return !rxrpc_conn_is_client(conn); } static inline void rxrpc_put_connection(struct rxrpc_connection *conn) { if (!conn) return; if (rxrpc_conn_is_client(conn)) rxrpc_put_client_conn(conn); else rxrpc_put_service_conn(conn); } static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, unsigned long expire_at) { timer_reduce(&conn->timer, expire_at); } /* * conn_service.c */ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *, struct sk_buff *); struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t); void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *, const struct rxrpc_security *, struct sk_buff *); void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* * input.c */ int rxrpc_input_packet(struct sock *, struct sk_buff *); /* * insecure.c */ extern const struct rxrpc_security rxrpc_no_security; /* * key.c */ extern struct key_type key_type_rxrpc; int rxrpc_request_key(struct rxrpc_sock *, sockptr_t , int); int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t, u32); /* * local_event.c */ extern void rxrpc_process_local_events(struct rxrpc_local *); /* * local_object.c */ struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *); struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *); struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *); void rxrpc_put_local(struct rxrpc_local *); struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *); void rxrpc_unuse_local(struct rxrpc_local *); void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_all_locals(struct rxrpc_net *); static inline bool __rxrpc_unuse_local(struct rxrpc_local *local) { return atomic_dec_return(&local->active_users) == 0; } static inline bool __rxrpc_use_local(struct rxrpc_local *local) { return atomic_fetch_add_unless(&local->active_users, 1, 0) != 0; } /* * misc.c */ extern unsigned int rxrpc_max_backlog __read_mostly; extern unsigned long rxrpc_requested_ack_delay; extern unsigned long rxrpc_soft_ack_delay; extern unsigned long rxrpc_idle_ack_delay; extern unsigned int rxrpc_rx_window_size; extern unsigned int rxrpc_rx_mtu; extern unsigned int rxrpc_rx_jumbo_max; extern const s8 rxrpc_ack_priority[]; /* * net_ns.c */ extern unsigned int rxrpc_net_id; extern struct pernet_operations rxrpc_net_ops; static inline struct rxrpc_net *rxrpc_net(struct net *net) { return net_generic(net, rxrpc_net_id); } /* * output.c */ int rxrpc_send_ack_packet(struct rxrpc_call *, bool, rxrpc_serial_t *); int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool); void rxrpc_reject_packets(struct rxrpc_local *); void rxrpc_send_keepalive(struct rxrpc_peer *); /* * peer_event.c */ void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); void rxrpc_error_report(struct sock *); void rxrpc_peer_keepalive_worker(struct work_struct *); /* * peer_object.c */ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *, struct sockaddr_rxrpc *, gfp_t); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t); void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *, struct rxrpc_peer *); void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); void rxrpc_put_peer(struct rxrpc_peer *); void rxrpc_put_peer_locked(struct rxrpc_peer *); /* * proc.c */ extern const struct seq_operations rxrpc_call_seq_ops; extern const struct seq_operations rxrpc_connection_seq_ops; extern const struct seq_operations rxrpc_peer_seq_ops; extern const struct seq_operations rxrpc_local_seq_ops; /* * recvmsg.c */ void rxrpc_notify_socket(struct rxrpc_call *); bool __rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int); bool rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int); bool __rxrpc_call_completed(struct rxrpc_call *); bool rxrpc_call_completed(struct rxrpc_call *); bool __rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int); bool rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int); int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* * Abort a call due to a protocol error. */ static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call, struct sk_buff *skb, const char *eproto_why, const char *why, u32 abort_code) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); trace_rxrpc_rx_eproto(call, sp->hdr.serial, eproto_why); return rxrpc_abort_call(why, call, sp->hdr.seq, abort_code, -EPROTO); } #define rxrpc_abort_eproto(call, skb, eproto_why, abort_why, abort_code) \ __rxrpc_abort_eproto((call), (skb), tracepoint_string(eproto_why), \ (abort_why), (abort_code)) /* * rtt.c */ void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool); void rxrpc_peer_init_rtt(struct rxrpc_peer *); /* * rxkad.c */ #ifdef CONFIG_RXKAD extern const struct rxrpc_security rxkad; #endif /* * security.c */ int __init rxrpc_init_security(void); const struct rxrpc_security *rxrpc_security_lookup(u8); void rxrpc_exit_security(void); int rxrpc_init_client_conn_security(struct rxrpc_connection *); const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *, struct sk_buff *); struct key *rxrpc_look_up_server_security(struct rxrpc_connection *, struct sk_buff *, u32, u32); /* * sendmsg.c */ int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); /* * server_key.c */ extern struct key_type key_type_rxrpc_s; int rxrpc_server_keyring(struct rxrpc_sock *, sockptr_t, int); /* * skbuff.c */ void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); void rxrpc_packet_destructor(struct sk_buff *); void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_eaten_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_get_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_purge_queue(struct sk_buff_head *); /* * sysctl.c */ #ifdef CONFIG_SYSCTL extern int __init rxrpc_sysctl_init(void); extern void rxrpc_sysctl_exit(void); #else static inline int __init rxrpc_sysctl_init(void) { return 0; } static inline void rxrpc_sysctl_exit(void) {} #endif /* * utils.c */ int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); static inline bool before(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) < 0; } static inline bool before_eq(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) <= 0; } static inline bool after(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) > 0; } static inline bool after_eq(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) >= 0; } /* * debug tracing */ extern unsigned int rxrpc_debug; #define dbgprintk(FMT,...) \ printk("[%-6.6s] "FMT"\n", current->comm ,##__VA_ARGS__) #define kenter(FMT,...) dbgprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__) #define kleave(FMT,...) dbgprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__) #define kdebug(FMT,...) dbgprintk(" "FMT ,##__VA_ARGS__) #define kproto(FMT,...) dbgprintk("### "FMT ,##__VA_ARGS__) #define knet(FMT,...) dbgprintk("@@@ "FMT ,##__VA_ARGS__) #if defined(__KDEBUG) #define _enter(FMT,...) kenter(FMT,##__VA_ARGS__) #define _leave(FMT,...) kleave(FMT,##__VA_ARGS__) #define _debug(FMT,...) kdebug(FMT,##__VA_ARGS__) #define _proto(FMT,...) kproto(FMT,##__VA_ARGS__) #define _net(FMT,...) knet(FMT,##__VA_ARGS__) #elif defined(CONFIG_AF_RXRPC_DEBUG) #define RXRPC_DEBUG_KENTER 0x01 #define RXRPC_DEBUG_KLEAVE 0x02 #define RXRPC_DEBUG_KDEBUG 0x04 #define RXRPC_DEBUG_KPROTO 0x08 #define RXRPC_DEBUG_KNET 0x10 #define _enter(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KENTER)) \ kenter(FMT,##__VA_ARGS__); \ } while (0) #define _leave(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KLEAVE)) \ kleave(FMT,##__VA_ARGS__); \ } while (0) #define _debug(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KDEBUG)) \ kdebug(FMT,##__VA_ARGS__); \ } while (0) #define _proto(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KPROTO)) \ kproto(FMT,##__VA_ARGS__); \ } while (0) #define _net(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KNET)) \ knet(FMT,##__VA_ARGS__); \ } while (0) #else #define _enter(FMT,...) no_printk("==> %s("FMT")",__func__ ,##__VA_ARGS__) #define _leave(FMT,...) no_printk("<== %s()"FMT"",__func__ ,##__VA_ARGS__) #define _debug(FMT,...) no_printk(" "FMT ,##__VA_ARGS__) #define _proto(FMT,...) no_printk("### "FMT ,##__VA_ARGS__) #define _net(FMT,...) no_printk("@@@ "FMT ,##__VA_ARGS__) #endif /* * debug assertion checking */ #if 1 // defined(__KDEBUGALL) #define ASSERT(X) \ do { \ if (unlikely(!(X))) { \ pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) #define ASSERTCMP(X, OP, Y) \ do { \ __typeof__(X) _x = (X); \ __typeof__(Y) _y = (__typeof__(X))(Y); \ if (unlikely(!(_x OP _y))) { \ pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ (unsigned long)_x, (unsigned long)_x, #OP, \ (unsigned long)_y, (unsigned long)_y); \ BUG(); \ } \ } while (0) #define ASSERTIF(C, X) \ do { \ if (unlikely((C) && !(X))) { \ pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) #define ASSERTIFCMP(C, X, OP, Y) \ do { \ __typeof__(X) _x = (X); \ __typeof__(Y) _y = (__typeof__(X))(Y); \ if (unlikely((C) && !(_x OP _y))) { \ pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ (unsigned long)_x, (unsigned long)_x, #OP, \ (unsigned long)_y, (unsigned long)_y); \ BUG(); \ } \ } while (0) #else #define ASSERT(X) \ do { \ } while (0) #define ASSERTCMP(X, OP, Y) \ do { \ } while (0) #define ASSERTIF(C, X) \ do { \ } while (0) #define ASSERTIFCMP(C, X, OP, Y) \ do { \ } while (0) #endif /* __KDEBUGALL */ |
| 8 8 8 2 1 1 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 | /* * Copyright (c) 2007, 2020 Oracle and/or its affiliates. * * 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. * */ #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/dma-mapping.h> /* for DMA_*_DEVICE */ #include "rds.h" /* * XXX * - build with sparse * - should we detect duplicate keys on a socket? hmm. * - an rdma is an mlock, apply rlimit? */ /* * get the number of pages by looking at the page indices that the start and * end addresses fall in. * * Returns 0 if the vec is invalid. It is invalid if the number of bytes * causes the address to wrap or overflows an unsigned int. This comes * from being stored in the 'length' member of 'struct scatterlist'. */ static unsigned int rds_pages_in_vec(struct rds_iovec *vec) { if ((vec->addr + vec->bytes <= vec->addr) || (vec->bytes > (u64)UINT_MAX)) return 0; return ((vec->addr + vec->bytes + PAGE_SIZE - 1) >> PAGE_SHIFT) - (vec->addr >> PAGE_SHIFT); } static struct rds_mr *rds_mr_tree_walk(struct rb_root *root, u64 key, struct rds_mr *insert) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct rds_mr *mr; while (*p) { parent = *p; mr = rb_entry(parent, struct rds_mr, r_rb_node); if (key < mr->r_key) p = &(*p)->rb_left; else if (key > mr->r_key) p = &(*p)->rb_right; else return mr; } if (insert) { rb_link_node(&insert->r_rb_node, parent, p); rb_insert_color(&insert->r_rb_node, root); kref_get(&insert->r_kref); } return NULL; } /* * Destroy the transport-specific part of a MR. */ static void rds_destroy_mr(struct rds_mr *mr) { struct rds_sock *rs = mr->r_sock; void *trans_private = NULL; unsigned long flags; rdsdebug("RDS: destroy mr key is %x refcnt %u\n", mr->r_key, kref_read(&mr->r_kref)); spin_lock_irqsave(&rs->rs_rdma_lock, flags); if (!RB_EMPTY_NODE(&mr->r_rb_node)) rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); trans_private = mr->r_trans_private; mr->r_trans_private = NULL; spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (trans_private) mr->r_trans->free_mr(trans_private, mr->r_invalidate); } void __rds_put_mr_final(struct kref *kref) { struct rds_mr *mr = container_of(kref, struct rds_mr, r_kref); rds_destroy_mr(mr); kfree(mr); } /* * By the time this is called we can't have any more ioctls called on * the socket so we don't need to worry about racing with others. */ void rds_rdma_drop_keys(struct rds_sock *rs) { struct rds_mr *mr; struct rb_node *node; unsigned long flags; /* Release any MRs associated with this socket */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); while ((node = rb_first(&rs->rs_rdma_keys))) { mr = rb_entry(node, struct rds_mr, r_rb_node); if (mr->r_trans == rs->rs_transport) mr->r_invalidate = 0; rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); kref_put(&mr->r_kref, __rds_put_mr_final); spin_lock_irqsave(&rs->rs_rdma_lock, flags); } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (rs->rs_transport && rs->rs_transport->flush_mrs) rs->rs_transport->flush_mrs(); } /* * Helper function to pin user pages. */ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, struct page **pages, int write) { unsigned int gup_flags = FOLL_LONGTERM; int ret; if (write) gup_flags |= FOLL_WRITE; ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages); if (ret >= 0 && ret < nr_pages) { unpin_user_pages(pages, ret); ret = -EFAULT; } return ret; } static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, u64 *cookie_ret, struct rds_mr **mr_ret, struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; struct scatterlist *sg = NULL; unsigned int nr_pages; struct page **pages = NULL; void *trans_private; unsigned long flags; rds_rdma_cookie_t cookie; unsigned int nents = 0; int need_odp = 0; long i; int ret; if (ipv6_addr_any(&rs->rs_bound_addr) || !rs->rs_transport) { ret = -ENOTCONN; /* XXX not a great errno */ goto out; } if (!rs->rs_transport->get_mr) { ret = -EOPNOTSUPP; goto out; } /* If the combination of the addr and size requested for this memory * region causes an integer overflow, return error. */ if (((args->vec.addr + args->vec.bytes) < args->vec.addr) || PAGE_ALIGN(args->vec.addr + args->vec.bytes) < (args->vec.addr + args->vec.bytes)) { ret = -EINVAL; goto out; } if (!can_do_mlock()) { ret = -EPERM; goto out; } nr_pages = rds_pages_in_vec(&args->vec); if (nr_pages == 0) { ret = -EINVAL; goto out; } /* Restrict the size of mr irrespective of underlying transport * To account for unaligned mr regions, subtract one from nr_pages */ if ((nr_pages - 1) > (RDS_MAX_MSG_SIZE >> PAGE_SHIFT)) { ret = -EMSGSIZE; goto out; } rdsdebug("RDS: get_mr addr %llx len %llu nr_pages %u\n", args->vec.addr, args->vec.bytes, nr_pages); /* XXX clamp nr_pages to limit the size of this alloc? */ pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; goto out; } mr = kzalloc(sizeof(struct rds_mr), GFP_KERNEL); if (!mr) { ret = -ENOMEM; goto out; } kref_init(&mr->r_kref); RB_CLEAR_NODE(&mr->r_rb_node); mr->r_trans = rs->rs_transport; mr->r_sock = rs; if (args->flags & RDS_RDMA_USE_ONCE) mr->r_use_once = 1; if (args->flags & RDS_RDMA_INVALIDATE) mr->r_invalidate = 1; if (args->flags & RDS_RDMA_READWRITE) mr->r_write = 1; /* * Pin the pages that make up the user buffer and transfer the page * pointers to the mr's sg array. We check to see if we've mapped * the whole region after transferring the partial page references * to the sg array so that we can have one page ref cleanup path. * * For now we have no flag that tells us whether the mapping is * r/o or r/w. We need to assume r/w, or we'll do a lot of RDMA to * the zero page. */ ret = rds_pin_pages(args->vec.addr, nr_pages, pages, 1); if (ret == -EOPNOTSUPP) { need_odp = 1; } else if (ret <= 0) { goto out; } else { nents = ret; sg = kmalloc_array(nents, sizeof(*sg), GFP_KERNEL); if (!sg) { ret = -ENOMEM; goto out; } WARN_ON(!nents); sg_init_table(sg, nents); /* Stick all pages into the scatterlist */ for (i = 0 ; i < nents; i++) sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0); rdsdebug("RDS: trans_private nents is %u\n", nents); } /* Obtain a transport specific MR. If this succeeds, the * s/g list is now owned by the MR. * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ trans_private = rs->rs_transport->get_mr( sg, nents, rs, &mr->r_key, cp ? cp->cp_conn : NULL, args->vec.addr, args->vec.bytes, need_odp ? ODP_ZEROBASED : ODP_NOT_NEEDED); if (IS_ERR(trans_private)) { /* In ODP case, we don't GUP pages, so don't need * to release anything. */ if (!need_odp) { unpin_user_pages(pages, nr_pages); kfree(sg); } ret = PTR_ERR(trans_private); /* Trigger connection so that its ready for the next retry */ if (ret == -ENODEV && cp) rds_conn_connect_if_down(cp->cp_conn); goto out; } mr->r_trans_private = trans_private; rdsdebug("RDS: get_mr put_user key is %x cookie_addr %p\n", mr->r_key, (void *)(unsigned long) args->cookie_addr); /* The user may pass us an unaligned address, but we can only * map page aligned regions. So we keep the offset, and build * a 64bit cookie containing <R_Key, offset> and pass that * around. */ if (need_odp) cookie = rds_rdma_make_cookie(mr->r_key, 0); else cookie = rds_rdma_make_cookie(mr->r_key, args->vec.addr & ~PAGE_MASK); if (cookie_ret) *cookie_ret = cookie; if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) { if (!need_odp) { unpin_user_pages(pages, nr_pages); kfree(sg); } ret = -EFAULT; goto out; } /* Inserting the new MR into the rbtree bumps its * reference count. */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); found = rds_mr_tree_walk(&rs->rs_rdma_keys, mr->r_key, mr); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); BUG_ON(found && found != mr); rdsdebug("RDS: get_mr key is %x\n", mr->r_key); if (mr_ret) { kref_get(&mr->r_kref); *mr_ret = mr; } ret = 0; out: kfree(pages); if (mr) kref_put(&mr->r_kref, __rds_put_mr_final); return ret; } int rds_get_mr(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_get_mr_args args; if (optlen != sizeof(struct rds_get_mr_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_get_mr_args))) return -EFAULT; return __rds_rdma_map(rs, &args, NULL, NULL, NULL); } int rds_get_mr_for_dest(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_get_mr_for_dest_args args; struct rds_get_mr_args new_args; if (optlen != sizeof(struct rds_get_mr_for_dest_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_get_mr_for_dest_args))) return -EFAULT; /* * Initially, just behave like get_mr(). * TODO: Implement get_mr as wrapper around this * and deprecate it. */ new_args.vec = args.vec; new_args.cookie_addr = args.cookie_addr; new_args.flags = args.flags; return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL); } /* * Free the MR indicated by the given R_Key */ int rds_free_mr(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_free_mr_args args; struct rds_mr *mr; unsigned long flags; if (optlen != sizeof(struct rds_free_mr_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_free_mr_args))) return -EFAULT; /* Special case - a null cookie means flush all unused MRs */ if (args.cookie == 0) { if (!rs->rs_transport || !rs->rs_transport->flush_mrs) return -EINVAL; rs->rs_transport->flush_mrs(); return 0; } /* Look up the MR given its R_key and remove it from the rbtree * so nobody else finds it. * This should also prevent races with rds_rdma_unuse. */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, rds_rdma_cookie_key(args.cookie), NULL); if (mr) { rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); if (args.flags & RDS_RDMA_INVALIDATE) mr->r_invalidate = 1; } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (!mr) return -EINVAL; kref_put(&mr->r_kref, __rds_put_mr_final); return 0; } /* * This is called when we receive an extension header that * tells us this MR was used. It allows us to implement * use_once semantics */ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force) { struct rds_mr *mr; unsigned long flags; int zot_me = 0; spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, r_key, NULL); if (!mr) { pr_debug("rds: trying to unuse MR with unknown r_key %u!\n", r_key); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); return; } /* Get a reference so that the MR won't go away before calling * sync_mr() below. */ kref_get(&mr->r_kref); /* If it is going to be freed, remove it from the tree now so * that no other thread can find it and free it. */ if (mr->r_use_once || force) { rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); zot_me = 1; } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); /* May have to issue a dma_sync on this memory region. * Note we could avoid this if the operation was a RDMA READ, * but at this point we can't tell. */ if (mr->r_trans->sync_mr) mr->r_trans->sync_mr(mr->r_trans_private, DMA_FROM_DEVICE); /* Release the reference held above. */ kref_put(&mr->r_kref, __rds_put_mr_final); /* If the MR was marked as invalidate, this will * trigger an async flush. */ if (zot_me) kref_put(&mr->r_kref, __rds_put_mr_final); } void rds_rdma_free_op(struct rm_rdma_op *ro) { unsigned int i; if (ro->op_odp_mr) { kref_put(&ro->op_odp_mr->r_kref, __rds_put_mr_final); } else { for (i = 0; i < ro->op_nents; i++) { struct page *page = sg_page(&ro->op_sg[i]); /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ unpin_user_pages_dirty_lock(&page, 1, !ro->op_write); } } kfree(ro->op_notifier); ro->op_notifier = NULL; ro->op_active = 0; ro->op_odp_mr = NULL; } void rds_atomic_free_op(struct rm_atomic_op *ao) { struct page *page = sg_page(ao->op_sg); /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ unpin_user_pages_dirty_lock(&page, 1, true); kfree(ao->op_notifier); ao->op_notifier = NULL; ao->op_active = 0; } /* * Count the number of pages needed to describe an incoming iovec array. */ static int rds_rdma_pages(struct rds_iovec iov[], int nr_iovecs) { int tot_pages = 0; unsigned int nr_pages; unsigned int i; /* figure out the number of pages in the vector */ for (i = 0; i < nr_iovecs; i++) { nr_pages = rds_pages_in_vec(&iov[i]); if (nr_pages == 0) return -EINVAL; tot_pages += nr_pages; /* * nr_pages for one entry is limited to (UINT_MAX>>PAGE_SHIFT)+1, * so tot_pages cannot overflow without first going negative. */ if (tot_pages < 0) return -EINVAL; } return tot_pages; } int rds_rdma_extra_size(struct rds_rdma_args *args, struct rds_iov_vector *iov) { struct rds_iovec *vec; struct rds_iovec __user *local_vec; int tot_pages = 0; unsigned int nr_pages; unsigned int i; local_vec = (struct rds_iovec __user *)(unsigned long) args->local_vec_addr; if (args->nr_local == 0) return -EINVAL; if (args->nr_local > UIO_MAXIOV) return -EMSGSIZE; iov->iov = kcalloc(args->nr_local, sizeof(struct rds_iovec), GFP_KERNEL); if (!iov->iov) return -ENOMEM; vec = &iov->iov[0]; if (copy_from_user(vec, local_vec, args->nr_local * sizeof(struct rds_iovec))) return -EFAULT; iov->len = args->nr_local; /* figure out the number of pages in the vector */ for (i = 0; i < args->nr_local; i++, vec++) { nr_pages = rds_pages_in_vec(vec); if (nr_pages == 0) return -EINVAL; tot_pages += nr_pages; /* * nr_pages for one entry is limited to (UINT_MAX>>PAGE_SHIFT)+1, * so tot_pages cannot overflow without first going negative. */ if (tot_pages < 0) return -EINVAL; } return tot_pages * sizeof(struct scatterlist); } /* * The application asks for a RDMA transfer. * Extract all arguments and set up the rdma_op */ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg, struct rds_iov_vector *vec) { struct rds_rdma_args *args; struct rm_rdma_op *op = &rm->rdma; int nr_pages; unsigned int nr_bytes; struct page **pages = NULL; struct rds_iovec *iovs; unsigned int i, j; int ret = 0; bool odp_supported = true; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args)) || rm->rdma.op_active) return -EINVAL; args = CMSG_DATA(cmsg); if (ipv6_addr_any(&rs->rs_bound_addr)) { ret = -ENOTCONN; /* XXX not a great errno */ goto out_ret; } if (args->nr_local > UIO_MAXIOV) { ret = -EMSGSIZE; goto out_ret; } if (vec->len != args->nr_local) { ret = -EINVAL; goto out_ret; } /* odp-mr is not supported for multiple requests within one message */ if (args->nr_local != 1) odp_supported = false; iovs = vec->iov; nr_pages = rds_rdma_pages(iovs, args->nr_local); if (nr_pages < 0) { ret = -EINVAL; goto out_ret; } pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; goto out_ret; } op->op_write = !!(args->flags & RDS_RDMA_READWRITE); op->op_fence = !!(args->flags & RDS_RDMA_FENCE); op->op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME); op->op_silent = !!(args->flags & RDS_RDMA_SILENT); op->op_active = 1; op->op_recverr = rs->rs_recverr; op->op_odp_mr = NULL; WARN_ON(!nr_pages); op->op_sg = rds_message_alloc_sgs(rm, nr_pages); if (IS_ERR(op->op_sg)) { ret = PTR_ERR(op->op_sg); goto out_pages; } if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because * we don't want to do that in the completion handler. We * would have to use GFP_ATOMIC there, and don't want to deal * with failed allocations. */ op->op_notifier = kmalloc(sizeof(struct rds_notifier), GFP_KERNEL); if (!op->op_notifier) { ret = -ENOMEM; goto out_pages; } op->op_notifier->n_user_token = args->user_token; op->op_notifier->n_status = RDS_RDMA_SUCCESS; } /* The cookie contains the R_Key of the remote memory region, and * optionally an offset into it. This is how we implement RDMA into * unaligned memory. * When setting up the RDMA, we need to add that offset to the * destination address (which is really an offset into the MR) * FIXME: We may want to move this into ib_rdma.c */ op->op_rkey = rds_rdma_cookie_key(args->cookie); op->op_remote_addr = args->remote_vec.addr + rds_rdma_cookie_offset(args->cookie); nr_bytes = 0; rdsdebug("RDS: rdma prepare nr_local %llu rva %llx rkey %x\n", (unsigned long long)args->nr_local, (unsigned long long)args->remote_vec.addr, op->op_rkey); for (i = 0; i < args->nr_local; i++) { struct rds_iovec *iov = &iovs[i]; /* don't need to check, rds_rdma_pages() verified nr will be +nonzero */ unsigned int nr = rds_pages_in_vec(iov); rs->rs_user_addr = iov->addr; rs->rs_user_bytes = iov->bytes; /* If it's a WRITE operation, we want to pin the pages for reading. * If it's a READ operation, we need to pin the pages for writing. */ ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); if ((!odp_supported && ret <= 0) || (odp_supported && ret <= 0 && ret != -EOPNOTSUPP)) goto out_pages; if (ret == -EOPNOTSUPP) { struct rds_mr *local_odp_mr; if (!rs->rs_transport->get_mr) { ret = -EOPNOTSUPP; goto out_pages; } local_odp_mr = kzalloc(sizeof(*local_odp_mr), GFP_KERNEL); if (!local_odp_mr) { ret = -ENOMEM; goto out_pages; } RB_CLEAR_NODE(&local_odp_mr->r_rb_node); kref_init(&local_odp_mr->r_kref); local_odp_mr->r_trans = rs->rs_transport; local_odp_mr->r_sock = rs; local_odp_mr->r_trans_private = rs->rs_transport->get_mr( NULL, 0, rs, &local_odp_mr->r_key, NULL, iov->addr, iov->bytes, ODP_VIRTUAL); if (IS_ERR(local_odp_mr->r_trans_private)) { ret = IS_ERR(local_odp_mr->r_trans_private); rdsdebug("get_mr ret %d %p\"", ret, local_odp_mr->r_trans_private); kfree(local_odp_mr); ret = -EOPNOTSUPP; goto out_pages; } rdsdebug("Need odp; local_odp_mr %p trans_private %p\n", local_odp_mr, local_odp_mr->r_trans_private); op->op_odp_mr = local_odp_mr; op->op_odp_addr = iov->addr; } rdsdebug("RDS: nr_bytes %u nr %u iov->bytes %llu iov->addr %llx\n", nr_bytes, nr, iov->bytes, iov->addr); nr_bytes += iov->bytes; for (j = 0; j < nr; j++) { unsigned int offset = iov->addr & ~PAGE_MASK; struct scatterlist *sg; sg = &op->op_sg[op->op_nents + j]; sg_set_page(sg, pages[j], min_t(unsigned int, iov->bytes, PAGE_SIZE - offset), offset); sg_dma_len(sg) = sg->length; rdsdebug("RDS: sg->offset %x sg->len %x iov->addr %llx iov->bytes %llu\n", sg->offset, sg->length, iov->addr, iov->bytes); iov->addr += sg->length; iov->bytes -= sg->length; } op->op_nents += nr; } if (nr_bytes > args->remote_vec.bytes) { rdsdebug("RDS nr_bytes %u remote_bytes %u do not match\n", nr_bytes, (unsigned int) args->remote_vec.bytes); ret = -EINVAL; goto out_pages; } op->op_bytes = nr_bytes; ret = 0; out_pages: kfree(pages); out_ret: if (ret) rds_rdma_free_op(op); else rds_stats_inc(s_send_rdma); return ret; } /* * The application wants us to pass an RDMA destination (aka MR) * to the remote */ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { unsigned long flags; struct rds_mr *mr; u32 r_key; int err = 0; if (cmsg->cmsg_len < CMSG_LEN(sizeof(rds_rdma_cookie_t)) || rm->m_rdma_cookie != 0) return -EINVAL; memcpy(&rm->m_rdma_cookie, CMSG_DATA(cmsg), sizeof(rm->m_rdma_cookie)); /* We are reusing a previously mapped MR here. Most likely, the * application has written to the buffer, so we need to explicitly * flush those writes to RAM. Otherwise the HCA may not see them * when doing a DMA from that buffer. */ r_key = rds_rdma_cookie_key(rm->m_rdma_cookie); spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, r_key, NULL); if (!mr) err = -EINVAL; /* invalid r_key */ else kref_get(&mr->r_kref); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (mr) { mr->r_trans->sync_mr(mr->r_trans_private, DMA_TO_DEVICE); rm->rdma.op_rdma_mr = mr; } return err; } /* * The application passes us an address range it wants to enable RDMA * to/from. We map the area, and save the <R_Key,offset> pair * in rm->m_rdma_cookie. This causes it to be sent along to the peer * in an extension header. */ int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_get_mr_args)) || rm->m_rdma_cookie != 0) return -EINVAL; return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr, rm->m_conn_path); } /* * Fill in rds_message for an atomic request. */ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { struct page *page = NULL; struct rds_atomic_args *args; int ret = 0; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_atomic_args)) || rm->atomic.op_active) return -EINVAL; args = CMSG_DATA(cmsg); /* Nonmasked & masked cmsg ops converted to masked hw ops */ switch (cmsg->cmsg_type) { case RDS_CMSG_ATOMIC_FADD: rm->atomic.op_type = RDS_ATOMIC_TYPE_FADD; rm->atomic.op_m_fadd.add = args->fadd.add; rm->atomic.op_m_fadd.nocarry_mask = 0; break; case RDS_CMSG_MASKED_ATOMIC_FADD: rm->atomic.op_type = RDS_ATOMIC_TYPE_FADD; rm->atomic.op_m_fadd.add = args->m_fadd.add; rm->atomic.op_m_fadd.nocarry_mask = args->m_fadd.nocarry_mask; break; case RDS_CMSG_ATOMIC_CSWP: rm->atomic.op_type = RDS_ATOMIC_TYPE_CSWP; rm->atomic.op_m_cswp.compare = args->cswp.compare; rm->atomic.op_m_cswp.swap = args->cswp.swap; rm->atomic.op_m_cswp.compare_mask = ~0; rm->atomic.op_m_cswp.swap_mask = ~0; break; case RDS_CMSG_MASKED_ATOMIC_CSWP: rm->atomic.op_type = RDS_ATOMIC_TYPE_CSWP; rm->atomic.op_m_cswp.compare = args->m_cswp.compare; rm->atomic.op_m_cswp.swap = args->m_cswp.swap; rm->atomic.op_m_cswp.compare_mask = args->m_cswp.compare_mask; rm->atomic.op_m_cswp.swap_mask = args->m_cswp.swap_mask; break; default: BUG(); /* should never happen */ } rm->atomic.op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME); rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT); rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); if (IS_ERR(rm->atomic.op_sg)) { ret = PTR_ERR(rm->atomic.op_sg); goto err; } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { ret = -EFAULT; goto err; } ret = rds_pin_pages(args->local_addr, 1, &page, 1); if (ret != 1) goto err; ret = 0; sg_set_page(rm->atomic.op_sg, page, 8, offset_in_page(args->local_addr)); if (rm->atomic.op_notify || rm->atomic.op_recverr) { /* We allocate an uninitialized notifier here, because * we don't want to do that in the completion handler. We * would have to use GFP_ATOMIC there, and don't want to deal * with failed allocations. */ rm->atomic.op_notifier = kmalloc(sizeof(*rm->atomic.op_notifier), GFP_KERNEL); if (!rm->atomic.op_notifier) { ret = -ENOMEM; goto err; } rm->atomic.op_notifier->n_user_token = args->user_token; rm->atomic.op_notifier->n_status = RDS_RDMA_SUCCESS; } rm->atomic.op_rkey = rds_rdma_cookie_key(args->cookie); rm->atomic.op_remote_addr = args->remote_addr + rds_rdma_cookie_offset(args->cookie); return ret; err: if (page) unpin_user_page(page); rm->atomic.op_active = 0; kfree(rm->atomic.op_notifier); return ret; } |
| 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | // SPDX-License-Identifier: GPL-2.0-only /* * Common code for control of lockd and nfsv4 grace periods. * * Transplanted from lockd code */ #include <linux/module.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/fs.h> static unsigned int grace_net_id; static DEFINE_SPINLOCK(grace_lock); /** * locks_start_grace * @net: net namespace that this lock manager belongs to * @lm: who this grace period is for * * A grace period is a period during which locks should not be given * out. Currently grace periods are only enforced by the two lock * managers (lockd and nfsd), using the locks_in_grace() function to * check when they are in a grace period. * * This function is called to start a grace period. */ void locks_start_grace(struct net *net, struct lock_manager *lm) { struct list_head *grace_list = net_generic(net, grace_net_id); spin_lock(&grace_lock); if (list_empty(&lm->list)) list_add(&lm->list, grace_list); else WARN(1, "double list_add attempt detected in net %x %s\n", net->ns.inum, (net == &init_net) ? "(init_net)" : ""); spin_unlock(&grace_lock); } EXPORT_SYMBOL_GPL(locks_start_grace); /** * locks_end_grace * @lm: who this grace period is for * * Call this function to state that the given lock manager is ready to * resume regular locking. The grace period will not end until all lock * managers that called locks_start_grace() also call locks_end_grace(). * Note that callers count on it being safe to call this more than once, * and the second call should be a no-op. */ void locks_end_grace(struct lock_manager *lm) { spin_lock(&grace_lock); list_del_init(&lm->list); spin_unlock(&grace_lock); } EXPORT_SYMBOL_GPL(locks_end_grace); static bool __state_in_grace(struct net *net, bool open) { struct list_head *grace_list = net_generic(net, grace_net_id); struct lock_manager *lm; if (!open) return !list_empty(grace_list); spin_lock(&grace_lock); list_for_each_entry(lm, grace_list, list) { if (lm->block_opens) { spin_unlock(&grace_lock); return true; } } spin_unlock(&grace_lock); return false; } /** * locks_in_grace * @net: network namespace * * Lock managers call this function to determine when it is OK for them * to answer ordinary lock requests, and when they should accept only * lock reclaims. */ bool locks_in_grace(struct net *net) { return __state_in_grace(net, false); } EXPORT_SYMBOL_GPL(locks_in_grace); bool opens_in_grace(struct net *net) { return __state_in_grace(net, true); } EXPORT_SYMBOL_GPL(opens_in_grace); static int __net_init grace_init_net(struct net *net) { struct list_head *grace_list = net_generic(net, grace_net_id); INIT_LIST_HEAD(grace_list); return 0; } static void __net_exit grace_exit_net(struct net *net) { struct list_head *grace_list = net_generic(net, grace_net_id); WARN_ONCE(!list_empty(grace_list), "net %x %s: grace_list is not empty\n", net->ns.inum, __func__); } static struct pernet_operations grace_net_ops = { .init = grace_init_net, .exit = grace_exit_net, .id = &grace_net_id, .size = sizeof(struct list_head), }; static int __init init_grace(void) { return register_pernet_subsys(&grace_net_ops); } static void __exit exit_grace(void) { unregister_pernet_subsys(&grace_net_ops); } MODULE_AUTHOR("Jeff Layton <jlayton@primarydata.com>"); MODULE_LICENSE("GPL"); module_init(init_grace) module_exit(exit_grace) |
| 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | // SPDX-License-Identifier: GPL-2.0-only /* * crc16.c */ #include <linux/types.h> #include <linux/module.h> #include <linux/crc16.h> /** CRC table for the CRC-16. The poly is 0x8005 (x^16 + x^15 + x^2 + 1) */ u16 const crc16_table[256] = { 0x0000, 0xC0C1, 0xC181, 0x0140, 0xC301, 0x03C0, 0x0280, 0xC241, 0xC601, 0x06C0, 0x0780, 0xC741, 0x0500, 0xC5C1, 0xC481, 0x0440, 0xCC01, 0x0CC0, 0x0D80, 0xCD41, 0x0F00, 0xCFC1, 0xCE81, 0x0E40, 0x0A00, 0xCAC1, 0xCB81, 0x0B40, 0xC901, 0x09C0, 0x0880, 0xC841, 0xD801, 0x18C0, 0x1980, 0xD941, 0x1B00, 0xDBC1, 0xDA81, 0x1A40, 0x1E00, 0xDEC1, 0xDF81, 0x1F40, 0xDD01, 0x1DC0, 0x1C80, 0xDC41, 0x1400, 0xD4C1, 0xD581, 0x1540, 0xD701, 0x17C0, 0x1680, 0xD641, 0xD201, 0x12C0, 0x1380, 0xD341, 0x1100, 0xD1C1, 0xD081, 0x1040, 0xF001, 0x30C0, 0x3180, 0xF141, 0x3300, 0xF3C1, 0xF281, 0x3240, 0x3600, 0xF6C1, 0xF781, 0x3740, 0xF501, 0x35C0, 0x3480, 0xF441, 0x3C00, 0xFCC1, 0xFD81, 0x3D40, 0xFF01, 0x3FC0, 0x3E80, 0xFE41, 0xFA01, 0x3AC0, 0x3B80, 0xFB41, 0x3900, 0xF9C1, 0xF881, 0x3840, 0x2800, 0xE8C1, 0xE981, 0x2940, 0xEB01, 0x2BC0, 0x2A80, 0xEA41, 0xEE01, 0x2EC0, 0x2F80, 0xEF41, 0x2D00, 0xEDC1, 0xEC81, 0x2C40, 0xE401, 0x24C0, 0x2580, 0xE541, 0x2700, 0xE7C1, 0xE681, 0x2640, 0x2200, 0xE2C1, 0xE381, 0x2340, 0xE101, 0x21C0, 0x2080, 0xE041, 0xA001, 0x60C0, 0x6180, 0xA141, 0x6300, 0xA3C1, 0xA281, 0x6240, 0x6600, 0xA6C1, 0xA781, 0x6740, 0xA501, 0x65C0, 0x6480, 0xA441, 0x6C00, 0xACC1, 0xAD81, 0x6D40, 0xAF01, 0x6FC0, 0x6E80, 0xAE41, 0xAA01, 0x6AC0, 0x6B80, 0xAB41, 0x6900, 0xA9C1, 0xA881, 0x6840, 0x7800, 0xB8C1, 0xB981, 0x7940, 0xBB01, 0x7BC0, 0x7A80, 0xBA41, 0xBE01, 0x7EC0, 0x7F80, 0xBF41, 0x7D00, 0xBDC1, 0xBC81, 0x7C40, 0xB401, 0x74C0, 0x7580, 0xB541, 0x7700, 0xB7C1, 0xB681, 0x7640, 0x7200, 0xB2C1, 0xB381, 0x7340, 0xB101, 0x71C0, 0x7080, 0xB041, 0x5000, 0x90C1, 0x9181, 0x5140, 0x9301, 0x53C0, 0x5280, 0x9241, 0x9601, 0x56C0, 0x5780, 0x9741, 0x5500, 0x95C1, 0x9481, 0x5440, 0x9C01, 0x5CC0, 0x5D80, 0x9D41, 0x5F00, 0x9FC1, 0x9E81, 0x5E40, 0x5A00, 0x9AC1, 0x9B81, 0x5B40, 0x9901, 0x59C0, 0x5880, 0x9841, 0x8801, 0x48C0, 0x4980, 0x8941, 0x4B00, 0x8BC1, 0x8A81, 0x4A40, 0x4E00, 0x8EC1, 0x8F81, 0x4F40, 0x8D01, 0x4DC0, 0x4C80, 0x8C41, 0x4400, 0x84C1, 0x8581, 0x4540, 0x8701, 0x47C0, 0x4680, 0x8641, 0x8201, 0x42C0, 0x4380, 0x8341, 0x4100, 0x81C1, 0x8081, 0x4040 }; EXPORT_SYMBOL(crc16_table); /** * crc16 - compute the CRC-16 for the data buffer * @crc: previous CRC value * @buffer: data pointer * @len: number of bytes in the buffer * * Returns the updated CRC value. */ u16 crc16(u16 crc, u8 const *buffer, size_t len) { while (len--) crc = crc16_byte(crc, *buffer++); return crc; } EXPORT_SYMBOL(crc16); MODULE_DESCRIPTION("CRC16 calculations"); MODULE_LICENSE("GPL"); |
| 8 8 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/mm_inline.h> #include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/mman.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" enum scan_result { SCAN_FAIL, SCAN_SUCCEED, SCAN_PMD_NULL, SCAN_EXCEED_NONE_PTE, SCAN_EXCEED_SWAP_PTE, SCAN_EXCEED_SHARED_PTE, SCAN_PTE_NON_PRESENT, SCAN_PTE_UFFD_WP, SCAN_PAGE_RO, SCAN_LACK_REFERENCED_PAGE, SCAN_PAGE_NULL, SCAN_SCAN_ABORT, SCAN_PAGE_COUNT, SCAN_PAGE_LRU, SCAN_PAGE_LOCK, SCAN_PAGE_ANON, SCAN_PAGE_COMPOUND, SCAN_ANY_PROCESS, SCAN_VMA_NULL, SCAN_VMA_CHECK, SCAN_ADDRESS_RANGE, SCAN_SWAP_CACHE_PAGE, SCAN_DEL_PAGE_LRU, SCAN_ALLOC_HUGE_PAGE_FAIL, SCAN_CGROUP_CHARGE_FAIL, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, }; #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> static struct task_struct *khugepaged_thread __read_mostly; static DEFINE_MUTEX(khugepaged_mutex); /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; static unsigned int khugepaged_full_scans; static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; /* during fragmentation poll the hugepage allocator once every minute */ static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; static unsigned long khugepaged_sleep_expire; static DEFINE_SPINLOCK(khugepaged_mm_lock); static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); /* * default collapse hugepages if there is at least one pte mapped like * it would have happened if the vma was large enough during page * fault. */ static unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct kmem_cache *mm_slot_cache __read_mostly; #define MAX_PTE_MAPPED_THP 8 /** * struct mm_slot - hash lookup from mm to mm_slot * @hash: hash collision list * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head * @mm: the mm that this information is valid for * @nr_pte_mapped_thp: number of pte mapped THP * @pte_mapped_thp: address array corresponding pte mapped THP */ struct mm_slot { struct hlist_node hash; struct list_head mm_node; struct mm_struct *mm; /* pte-mapped THP in this mm */ int nr_pte_mapped_thp; unsigned long pte_mapped_thp[MAX_PTE_MAPPED_THP]; }; /** * struct khugepaged_scan - cursor for scanning * @mm_head: the head of the mm list to scan * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * * There is only the one khugepaged_scan instance of this cursor structure. */ struct khugepaged_scan { struct list_head mm_head; struct mm_slot *mm_slot; unsigned long address; }; static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; #ifdef CONFIG_SYSFS static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_scan_sleep_millisecs); } static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_scan_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute scan_sleep_millisecs_attr = __ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show, scan_sleep_millisecs_store); static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_alloc_sleep_millisecs); } static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_alloc_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute alloc_sleep_millisecs_attr = __ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show, alloc_sleep_millisecs_store); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int pages; int err; err = kstrtouint(buf, 10, &pages); if (err || !pages) return -EINVAL; khugepaged_pages_to_scan = pages; return count; } static struct kobj_attribute pages_to_scan_attr = __ATTR(pages_to_scan, 0644, pages_to_scan_show, pages_to_scan_store); static ssize_t pages_collapsed_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_collapsed); } static struct kobj_attribute pages_collapsed_attr = __ATTR_RO(pages_collapsed); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_full_scans); } static struct kobj_attribute full_scans_attr = __ATTR_RO(full_scans); static ssize_t khugepaged_defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static ssize_t khugepaged_defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static struct kobj_attribute khugepaged_defrag_attr = __ATTR(defrag, 0644, khugepaged_defrag_show, khugepaged_defrag_store); /* * max_ptes_none controls if khugepaged should collapse hugepages over * any unmapped ptes in turn potentially increasing the memory * footprint of the vmas. When max_ptes_none is 0 khugepaged will not * reduce the available free memory in the system as it * runs. Increasing max_ptes_none will instead potentially reduce the * free memory in the system during the khugepaged scan. */ static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none); } static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_none; err = kstrtoul(buf, 10, &max_ptes_none); if (err || max_ptes_none > HPAGE_PMD_NR-1) return -EINVAL; khugepaged_max_ptes_none = max_ptes_none; return count; } static struct kobj_attribute khugepaged_max_ptes_none_attr = __ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show, khugepaged_max_ptes_none_store); static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap); } static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_swap; err = kstrtoul(buf, 10, &max_ptes_swap); if (err || max_ptes_swap > HPAGE_PMD_NR-1) return -EINVAL; khugepaged_max_ptes_swap = max_ptes_swap; return count; } static struct kobj_attribute khugepaged_max_ptes_swap_attr = __ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show, khugepaged_max_ptes_swap_store); static ssize_t khugepaged_max_ptes_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared); } static ssize_t khugepaged_max_ptes_shared_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_shared; err = kstrtoul(buf, 10, &max_ptes_shared); if (err || max_ptes_shared > HPAGE_PMD_NR-1) return -EINVAL; khugepaged_max_ptes_shared = max_ptes_shared; return count; } static struct kobj_attribute khugepaged_max_ptes_shared_attr = __ATTR(max_ptes_shared, 0644, khugepaged_max_ptes_shared_show, khugepaged_max_ptes_shared_store); static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, &khugepaged_max_ptes_none_attr.attr, &khugepaged_max_ptes_swap_attr.attr, &khugepaged_max_ptes_shared_attr.attr, &pages_to_scan_attr.attr, &pages_collapsed_attr.attr, &full_scans_attr.attr, &scan_sleep_millisecs_attr.attr, &alloc_sleep_millisecs_attr.attr, NULL, }; struct attribute_group khugepaged_attr_group = { .attrs = khugepaged_attr, .name = "khugepaged", }; #endif /* CONFIG_SYSFS */ int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { switch (advice) { case MADV_HUGEPAGE: #ifdef CONFIG_S390 /* * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 * can't handle this properly after s390_enable_sie, so we simply * ignore the madvise to prevent qemu from causing a SIGSEGV. */ if (mm_has_pgste(vma->vm_mm)) return 0; #endif *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* * If the vma become good for khugepaged to scan, * register it here without waiting a page fault that * may not happen any time soon. */ if (!(*vm_flags & VM_NO_KHUGEPAGED) && khugepaged_enter_vma_merge(vma, *vm_flags)) return -ENOMEM; break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; /* * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning * this vma even if we leave the mm registered in khugepaged if * it got registered before VM_NOHUGEPAGE was set. */ break; } return 0; } int __init khugepaged_init(void) { mm_slot_cache = kmem_cache_create("khugepaged_mm_slot", sizeof(struct mm_slot), __alignof__(struct mm_slot), 0, NULL); if (!mm_slot_cache) return -ENOMEM; khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; return 0; } void __init khugepaged_destroy(void) { kmem_cache_destroy(mm_slot_cache); } static inline struct mm_slot *alloc_mm_slot(void) { if (!mm_slot_cache) /* initialization failed */ return NULL; return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); } static inline void free_mm_slot(struct mm_slot *mm_slot) { kmem_cache_free(mm_slot_cache, mm_slot); } static struct mm_slot *get_mm_slot(struct mm_struct *mm) { struct mm_slot *mm_slot; hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm) if (mm == mm_slot->mm) return mm_slot; return NULL; } static void insert_to_mm_slots_hash(struct mm_struct *mm, struct mm_slot *mm_slot) { mm_slot->mm = mm; hash_add(mm_slots_hash, &mm_slot->hash, (long)mm); } static inline int khugepaged_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } static bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags) { if (!transhuge_vma_enabled(vma, vm_flags)) return false; if (vma->vm_file && !IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR)) return false; /* Enabled via shmem mount options or sysfs settings. */ if (shmem_file(vma->vm_file)) return shmem_huge_enabled(vma); /* THP settings require madvise. */ if (!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) return false; /* Only regular file is valid */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file && (vm_flags & VM_EXEC)) { struct inode *inode = vma->vm_file->f_inode; return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); } if (!vma->anon_vma || vma->vm_ops) return false; if (vma_is_temporary_stack(vma)) return false; return !(vm_flags & VM_NO_KHUGEPAGED); } int __khugepaged_enter(struct mm_struct *mm) { struct mm_slot *mm_slot; int wakeup; mm_slot = alloc_mm_slot(); if (!mm_slot) return -ENOMEM; /* __khugepaged_exit() must not run from under us */ VM_BUG_ON_MM(khugepaged_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { free_mm_slot(mm_slot); return 0; } spin_lock(&khugepaged_mm_lock); insert_to_mm_slots_hash(mm, mm_slot); /* * Insert just behind the scanning cursor, to let the area settle * down a little. */ wakeup = list_empty(&khugepaged_scan.mm_head); list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head); spin_unlock(&khugepaged_mm_lock); mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); return 0; } int khugepaged_enter_vma_merge(struct vm_area_struct *vma, unsigned long vm_flags) { unsigned long hstart, hend; /* * khugepaged only supports read-only files for non-shmem files. * khugepaged does not yet work on special mappings. And * file-private shmem THP is not supported. */ if (!hugepage_vma_check(vma, vm_flags)) return 0; hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart < hend) return khugepaged_enter(vma, vm_flags); return 0; } void __khugepaged_exit(struct mm_struct *mm) { struct mm_slot *mm_slot; int free = 0; spin_lock(&khugepaged_mm_lock); mm_slot = get_mm_slot(mm); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { hash_del(&mm_slot->hash); list_del(&mm_slot->mm_node); free = 1; } spin_unlock(&khugepaged_mm_lock); if (free) { clear_bit(MMF_VM_HUGEPAGE, &mm->flags); free_mm_slot(mm_slot); mmdrop(mm); } else if (mm_slot) { /* * This is required to serialize against * khugepaged_test_exit() (which is guaranteed to run * under mmap sem read mode). Stop here (after we * return all pagetables will be destroyed) until * khugepaged has finished working on the pagetables * under the mmap_lock. */ mmap_write_lock(mm); mmap_write_unlock(mm); } } static void release_pte_page(struct page *page) { mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page), -compound_nr(page)); unlock_page(page); putback_lru_page(page); } static void release_pte_pages(pte_t *pte, pte_t *_pte, struct list_head *compound_pagelist) { struct page *page, *tmp; while (--_pte >= pte) { pte_t pteval = *_pte; page = pte_page(pteval); if (!pte_none(pteval) && !is_zero_pfn(pte_pfn(pteval)) && !PageCompound(page)) release_pte_page(page); } list_for_each_entry_safe(page, tmp, compound_pagelist, lru) { list_del(&page->lru); release_pte_page(page); } } static bool is_refcount_suitable(struct page *page) { int expected_refcount; expected_refcount = total_mapcount(page); if (PageSwapCache(page)) expected_refcount += compound_nr(page); return page_count(page) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte, struct list_head *compound_pagelist) { struct page *page = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = 0, referenced = 0; bool writable = false; for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = *_pte; if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { if (!userfaultfd_armed(vma) && ++none_or_zero <= khugepaged_max_ptes_none) { continue; } else { result = SCAN_EXCEED_NONE_PTE; goto out; } } if (!pte_present(pteval)) { result = SCAN_PTE_NON_PRESENT; goto out; } if (pte_uffd_wp(pteval)) { result = SCAN_PTE_UFFD_WP; goto out; } page = vm_normal_page(vma, address, pteval); if (unlikely(!page)) { result = SCAN_PAGE_NULL; goto out; } VM_BUG_ON_PAGE(!PageAnon(page), page); if (page_mapcount(page) > 1 && ++shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; goto out; } if (PageCompound(page)) { struct page *p; page = compound_head(page); /* * Check if we have dealt with the compound page * already */ list_for_each_entry(p, compound_pagelist, lru) { if (page == p) goto next; } } /* * We can do it before isolate_lru_page because the * page can't be freed from under us. NOTE: PG_lock * is needed to serialize against split_huge_page * when invoked from the VM. */ if (!trylock_page(page)) { result = SCAN_PAGE_LOCK; goto out; } /* * Check if the page has any GUP (or other external) pins. * * The page table that maps the page has been already unlinked * from the page table tree and this process cannot get * an additional pin on the page. * * New pins can come later if the page is shared across fork, * but not from this process. The other process cannot write to * the page, only trigger CoW. */ if (!is_refcount_suitable(page)) { unlock_page(page); result = SCAN_PAGE_COUNT; goto out; } if (!pte_write(pteval) && PageSwapCache(page) && !reuse_swap_page(page, NULL)) { /* * Page is in the swap cache and cannot be re-used. * It cannot be collapsed into a THP. */ unlock_page(page); result = SCAN_SWAP_CACHE_PAGE; goto out; } /* * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ if (isolate_lru_page(page)) { unlock_page(page); result = SCAN_DEL_PAGE_LRU; goto out; } mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page), compound_nr(page)); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageLRU(page), page); if (PageCompound(page)) list_add_tail(&page->lru, compound_pagelist); next: /* There should be enough young pte to collapse the page */ if (pte_young(pteval) || page_is_young(page) || PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, address)) referenced++; if (pte_write(pteval)) writable = true; } if (unlikely(!writable)) { result = SCAN_PAGE_RO; } else if (unlikely(!referenced)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; trace_mm_collapse_huge_page_isolate(page, none_or_zero, referenced, writable, result); return 1; } out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(page, none_or_zero, referenced, writable, result); return 0; } static void __collapse_huge_page_copy(pte_t *pte, struct page *page, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { struct page *src_page, *tmp; pte_t *_pte; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, page++, address += PAGE_SIZE) { pte_t pteval = *_pte; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, address); add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { /* * ptl mostly unnecessary. */ spin_lock(ptl); /* * paravirt calls inside pte_clear here are * superfluous. */ pte_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); } } else { src_page = pte_page(pteval); copy_user_highpage(page, src_page, address, vma); if (!PageCompound(src_page)) release_pte_page(src_page); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats * inside page_remove_rmap(). */ spin_lock(ptl); /* * paravirt calls inside pte_clear here are * superfluous. */ pte_clear(vma->vm_mm, address, _pte); page_remove_rmap(src_page, false); spin_unlock(ptl); free_page_and_swap_cache(src_page); } } list_for_each_entry_safe(src_page, tmp, compound_pagelist, lru) { list_del(&src_page->lru); release_pte_page(src_page); } } static void khugepaged_alloc_sleep(void) { DEFINE_WAIT(wait); add_wait_queue(&khugepaged_wait, &wait); freezable_schedule_timeout_interruptible( msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); remove_wait_queue(&khugepaged_wait, &wait); } static int khugepaged_node_load[MAX_NUMNODES]; static bool khugepaged_scan_abort(int nid) { int i; /* * If node_reclaim_mode is disabled, then no extra effort is made to * allocate memory locally. */ if (!node_reclaim_enabled()) return false; /* If there is a count for this node already, it must be acceptable */ if (khugepaged_node_load[nid]) return false; for (i = 0; i < MAX_NUMNODES; i++) { if (!khugepaged_node_load[i]) continue; if (node_distance(nid, i) > node_reclaim_distance) return true; } return false; } /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) { return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT; } #ifdef CONFIG_NUMA static int khugepaged_find_target_node(void) { static int last_khugepaged_target_node = NUMA_NO_NODE; int nid, target_node = 0, max_value = 0; /* find first node with max normal pages hit */ for (nid = 0; nid < MAX_NUMNODES; nid++) if (khugepaged_node_load[nid] > max_value) { max_value = khugepaged_node_load[nid]; target_node = nid; } /* do some balance if several nodes have the same hit record */ if (target_node <= last_khugepaged_target_node) for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES; nid++) if (max_value == khugepaged_node_load[nid]) { target_node = nid; break; } last_khugepaged_target_node = target_node; return target_node; } static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { if (IS_ERR(*hpage)) { if (!*wait) return false; *wait = false; *hpage = NULL; khugepaged_alloc_sleep(); } else if (*hpage) { put_page(*hpage); *hpage = NULL; } return true; } static struct page * khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node) { VM_BUG_ON_PAGE(*hpage, *hpage); *hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER); if (unlikely(!*hpage)) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); *hpage = ERR_PTR(-ENOMEM); return NULL; } prep_transhuge_page(*hpage); count_vm_event(THP_COLLAPSE_ALLOC); return *hpage; } #else static int khugepaged_find_target_node(void) { return 0; } static inline struct page *alloc_khugepaged_hugepage(void) { struct page *page; page = alloc_pages(alloc_hugepage_khugepaged_gfpmask(), HPAGE_PMD_ORDER); if (page) prep_transhuge_page(page); return page; } static struct page *khugepaged_alloc_hugepage(bool *wait) { struct page *hpage; do { hpage = alloc_khugepaged_hugepage(); if (!hpage) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); if (!*wait) return NULL; *wait = false; khugepaged_alloc_sleep(); } else count_vm_event(THP_COLLAPSE_ALLOC); } while (unlikely(!hpage) && likely(khugepaged_enabled())); return hpage; } static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { /* * If the hpage allocated earlier was briefly exposed in page cache * before collapse_file() failed, it is possible that racing lookups * have not yet completed, and would then be unpleasantly surprised by * finding the hpage reused for the same mapping at a different offset. * Just release the previous allocation if there is any danger of that. */ if (*hpage && page_count(*hpage) > 1) { put_page(*hpage); *hpage = NULL; } if (!*hpage) *hpage = khugepaged_alloc_hugepage(wait); if (unlikely(!*hpage)) return false; return true; } static struct page * khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node) { VM_BUG_ON(!*hpage); return *hpage; } #endif /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. * Return 0 if succeeds, otherwise return none-zero * value (scan code). */ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, struct vm_area_struct **vmap) { struct vm_area_struct *vma; unsigned long hstart, hend; if (unlikely(khugepaged_test_exit(mm))) return SCAN_ANY_PROCESS; *vmap = vma = find_vma(mm, address); if (!vma) return SCAN_VMA_NULL; hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (address < hstart || address + HPAGE_PMD_SIZE > hend) return SCAN_ADDRESS_RANGE; if (!hugepage_vma_check(vma, vma->vm_flags)) return SCAN_VMA_CHECK; /* Anon VMA expected */ if (!vma->anon_vma || vma->vm_ops) return SCAN_VMA_CHECK; return 0; } /* * Bring missing pages in from swap, to complete THP collapse. * Only done if khugepaged_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held, * but with mmap_lock held to protect against vma changes. */ static bool __collapse_huge_page_swapin(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, int referenced) { int swapped_in = 0; vm_fault_t ret = 0; unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE); for (address = haddr; address < end; address += PAGE_SIZE) { struct vm_fault vmf = { .vma = vma, .address = address, .pgoff = linear_page_index(vma, haddr), .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, }; vmf.pte = pte_offset_map(pmd, address); vmf.orig_pte = *vmf.pte; if (!is_swap_pte(vmf.orig_pte)) { pte_unmap(vmf.pte); continue; } swapped_in++; ret = do_swap_page(&vmf); /* do_swap_page returns VM_FAULT_RETRY with released mmap_lock */ if (ret & VM_FAULT_RETRY) { mmap_read_lock(mm); if (hugepage_vma_revalidate(mm, haddr, &vma)) { /* vma is no longer available, don't continue to swapin */ trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); return false; } /* check if the pmd is still valid */ if (mm_find_pmd(mm, haddr) != pmd) { trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); return false; } } if (ret & VM_FAULT_ERROR) { trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); return false; } } /* Drain LRU add pagevec to remove extra pin on the swapped in pages */ if (swapped_in) lru_add_drain(); trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 1); return true; } static void collapse_huge_page(struct mm_struct *mm, unsigned long address, struct page **hpage, int node, int referenced, int unmapped) { LIST_HEAD(compound_pagelist); pmd_t *pmd, _pmd; pte_t *pte; pgtable_t pgtable; struct page *new_page; spinlock_t *pmd_ptl, *pte_ptl; int isolated = 0, result = 0; struct vm_area_struct *vma; struct mmu_notifier_range range; gfp_t gfp; VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* Only allocate from the target node */ gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; /* * Before allocating the hugepage, release the mmap_lock read lock. * The allocation can take potentially a long time if it involves * sync compaction, and we do not need to hold the mmap_lock during * that. We will recheck the vma after taking it again in write mode. */ mmap_read_unlock(mm); new_page = khugepaged_alloc_page(hpage, gfp, node); if (!new_page) { result = SCAN_ALLOC_HUGE_PAGE_FAIL; goto out_nolock; } if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); mmap_read_lock(mm); result = hugepage_vma_revalidate(mm, address, &vma); if (result) { mmap_read_unlock(mm); goto out_nolock; } pmd = mm_find_pmd(mm, address); if (!pmd) { result = SCAN_PMD_NULL; mmap_read_unlock(mm); goto out_nolock; } /* * __collapse_huge_page_swapin always returns with mmap_lock locked. * If it fails, we release mmap_lock and jump out_nolock. * Continuing to collapse causes inconsistency. */ if (unmapped && !__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) { mmap_read_unlock(mm); goto out_nolock; } mmap_read_unlock(mm); /* * Prevent all access to pagetables with the exception of * gup_fast later handled by the ptep_clear_flush and the VM * handled by the anon_vma lock + PG_lock. */ mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, &vma); if (result) goto out_up_write; /* check if the pmd is still valid */ if (mm_find_pmd(mm, address) != pmd) goto out_up_write; anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pte = pte_offset_map(pmd, address); pte_ptl = pte_lockptr(mm, pmd); pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * This removes any huge TLB entry from the CPU so we won't allow * huge and small TLB entries for the same virtual address to * avoid the risk of CPU bugs in that area. * * Parallel fast GUP is fine since fast GUP will back off when * it detects PMD is changed. */ _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(&range); tlb_remove_table_sync_one(); spin_lock(pte_ptl); isolated = __collapse_huge_page_isolate(vma, address, pte, &compound_pagelist); spin_unlock(pte_ptl); if (unlikely(!isolated)) { pte_unmap(pte); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); /* * We can only use set_pmd_at when establishing * hugepmds and never for establishing regular pmds that * points to regular pagetables. Use pmd_populate for that */ pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); result = SCAN_FAIL; goto out_up_write; } /* * All pages are isolated and locked so anon_vma rmap * can't run anymore. */ anon_vma_unlock_write(vma->anon_vma); __collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); /* * spin_lock() below is not the equivalent of smp_wmb(), but * the smp_wmb() inside __SetPageUptodate() can be reused to * avoid the copy_huge_page writes to become visible after * the set_pmd_at() write. */ __SetPageUptodate(new_page); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(new_page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address, true); lru_cache_add_inactive_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); spin_unlock(pmd_ptl); *hpage = NULL; khugepaged_pages_collapsed++; result = SCAN_SUCCEED; out_up_write: mmap_write_unlock(mm); out_nolock: if (!IS_ERR_OR_NULL(*hpage)) mem_cgroup_uncharge(*hpage); trace_mm_collapse_huge_page(mm, isolated, result); return; } static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, struct page **hpage) { pmd_t *pmd; pte_t *pte, *_pte; int ret = 0, result = 0, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; bool writable = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); pmd = mm_find_pmd(mm, address); if (!pmd) { result = SCAN_PMD_NULL; goto out; } memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); pte = pte_offset_map_lock(mm, pmd, address, &ptl); for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = *_pte; if (is_swap_pte(pteval)) { if (++unmapped <= khugepaged_max_ptes_swap) { /* * Always be strict with uffd-wp * enabled swap entries. Please see * comment below for pte_uffd_wp(). */ if (pte_swp_uffd_wp(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } continue; } else { result = SCAN_EXCEED_SWAP_PTE; goto out_unmap; } } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { if (!userfaultfd_armed(vma) && ++none_or_zero <= khugepaged_max_ptes_none) { continue; } else { result = SCAN_EXCEED_NONE_PTE; goto out_unmap; } } if (pte_uffd_wp(pteval)) { /* * Don't collapse the page if any of the small * PTEs are armed with uffd write protection. * Here we can also mark the new huge pmd as * write protected if any of the small ones is * marked but that could bring unknown * userfault messages that falls outside of * the registered range. So, just be simple. */ result = SCAN_PTE_UFFD_WP; goto out_unmap; } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); if (unlikely(!page)) { result = SCAN_PAGE_NULL; goto out_unmap; } if (page_mapcount(page) > 1 && ++shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; goto out_unmap; } page = compound_head(page); /* * Record which node the original page is from and save this * information to khugepaged_node_load[]. * Khupaged will allocate hugepage from the node has the max * hit record. */ node = page_to_nid(page); if (khugepaged_scan_abort(node)) { result = SCAN_SCAN_ABORT; goto out_unmap; } khugepaged_node_load[node]++; if (!PageLRU(page)) { result = SCAN_PAGE_LRU; goto out_unmap; } if (PageLocked(page)) { result = SCAN_PAGE_LOCK; goto out_unmap; } if (!PageAnon(page)) { result = SCAN_PAGE_ANON; goto out_unmap; } /* * Check if the page has any GUP (or other external) pins. * * Here the check is racy it may see totmal_mapcount > refcount * in some cases. * For example, one process with one forked child process. * The parent has the PMD split due to MADV_DONTNEED, then * the child is trying unmap the whole PMD, but khugepaged * may be scanning the parent between the child has * PageDoubleMap flag cleared and dec the mapcount. So * khugepaged may see total_mapcount > refcount. * * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ if (!is_refcount_suitable(page)) { result = SCAN_PAGE_COUNT; goto out_unmap; } if (pte_young(pteval) || page_is_young(page) || PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, address)) referenced++; } if (!writable) { result = SCAN_PAGE_RO; } else if (!referenced || (unmapped && referenced < HPAGE_PMD_NR/2)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; ret = 1; } out_unmap: pte_unmap_unlock(pte, ptl); if (ret) { node = khugepaged_find_target_node(); /* collapse_huge_page will return with the mmap_lock released */ collapse_huge_page(mm, address, hpage, node, referenced, unmapped); } out: trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced, none_or_zero, result, unmapped); return ret; } static void collect_mm_slot(struct mm_slot *mm_slot) { struct mm_struct *mm = mm_slot->mm; lockdep_assert_held(&khugepaged_mm_lock); if (khugepaged_test_exit(mm)) { /* free mm_slot */ hash_del(&mm_slot->hash); list_del(&mm_slot->mm_node); /* * Not strictly needed because the mm exited already. * * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); */ /* khugepaged_mm_lock actually not necessary for the below */ free_mm_slot(mm_slot); mmdrop(mm); } } #ifdef CONFIG_SHMEM /* * Notify khugepaged that given addr of the mm is pte-mapped THP. Then * khugepaged should try to collapse the page table. */ static int khugepaged_add_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) { struct mm_slot *mm_slot; VM_BUG_ON(addr & ~HPAGE_PMD_MASK); spin_lock(&khugepaged_mm_lock); mm_slot = get_mm_slot(mm); if (likely(mm_slot && mm_slot->nr_pte_mapped_thp < MAX_PTE_MAPPED_THP)) mm_slot->pte_mapped_thp[mm_slot->nr_pte_mapped_thp++] = addr; spin_unlock(&khugepaged_mm_lock); return 0; } /** * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at * address haddr. * * @mm: process address space where collapse happens * @addr: THP collapse address * * This function checks whether all the PTEs in the PMD are pointing to the * right THP. If so, retract the page table so the THP can refault in with * as pmd-mapped. */ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) { unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = find_vma(mm, haddr); struct page *hpage; pte_t *start_pte, *pte; pmd_t *pmd, _pmd; spinlock_t *ptl; int count = 0; int i; struct mmu_notifier_range range; if (!vma || !vma->vm_file || !range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE)) return; /* * This vm_flags may not have VM_HUGEPAGE if the page was not * collapsed by this mm. But we can still collapse if the page is * the valid THP. Add extra VM_HUGEPAGE so hugepage_vma_check() * will not fail the vma for missing VM_HUGEPAGE */ if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE)) return; hpage = find_lock_page(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (!hpage) return; if (!PageHead(hpage)) goto drop_hpage; pmd = mm_find_pmd(mm, haddr); if (!pmd) goto drop_hpage; /* * We need to lock the mapping so that from here on, only GUP-fast and * hardware page walks can access the parts of the page tables that * we're operating on. */ i_mmap_lock_write(vma->vm_file->f_mapping); /* * This spinlock should be unnecessary: Nobody else should be accessing * the page tables under spinlock protection here, only * lockless_pages_from_mm() and the hardware page walker can access page * tables while all the high-level locks are held in write mode. */ start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; /* empty pte, skip */ if (pte_none(*pte)) continue; /* page swapped out, abort */ if (!pte_present(*pte)) goto abort; page = vm_normal_page(vma, addr, *pte); /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ if (hpage + i != page) goto abort; count++; } /* step 2: adjust rmap */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; if (pte_none(*pte)) continue; page = vm_normal_page(vma, addr, *pte); page_remove_rmap(page, false); } pte_unmap_unlock(start_pte, ptl); /* step 3: set proper refcount and mm_counters. */ if (count) { page_ref_sub(hpage, count); add_mm_counter(vma->vm_mm, mm_counter_file(hpage), -count); } /* step 4: collapse pmd */ /* we make no change to anon, but protect concurrent anon page lookup */ if (vma->anon_vma) anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); _pmd = pmdp_collapse_flush(vma, haddr, pmd); mm_dec_nr_ptes(mm); tlb_remove_table_sync_one(); mmu_notifier_invalidate_range_end(&range); pte_free(mm, pmd_pgtable(_pmd)); if (vma->anon_vma) anon_vma_unlock_write(vma->anon_vma); i_mmap_unlock_write(vma->vm_file->f_mapping); drop_hpage: unlock_page(hpage); put_page(hpage); return; abort: pte_unmap_unlock(start_pte, ptl); i_mmap_unlock_write(vma->vm_file->f_mapping); goto drop_hpage; } static void khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) { struct mm_struct *mm = mm_slot->mm; int i; if (likely(mm_slot->nr_pte_mapped_thp == 0)) return; if (!mmap_write_trylock(mm)) return; if (unlikely(khugepaged_test_exit(mm))) goto out; for (i = 0; i < mm_slot->nr_pte_mapped_thp; i++) collapse_pte_mapped_thp(mm, mm_slot->pte_mapped_thp[i]); out: mm_slot->nr_pte_mapped_thp = 0; mmap_write_unlock(mm); } static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) { struct vm_area_struct *vma; struct mm_struct *mm; unsigned long addr; pmd_t *pmd, _pmd; i_mmap_lock_write(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that * got written to. These VMAs are likely not worth investing * mmap_write_lock(mm) as PMD-mapping is likely to be split * later. * * Not that vma->anon_vma check is racy: it can be set up after * the check but before we took mmap_lock by the fault path. * But page lock would prevent establishing any new ptes of the * page, so we are safe. * * An alternative would be drop the check, but check that page * table is clear before calling pmdp_collapse_flush() under * ptl. It has higher chance to recover THP for the VMA, but * has higher cost too. It would also probably require locking * the anon_vma. */ if (vma->anon_vma) continue; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (addr & ~HPAGE_PMD_MASK) continue; if (vma->vm_end < addr + HPAGE_PMD_SIZE) continue; mm = vma->vm_mm; pmd = mm_find_pmd(mm, addr); if (!pmd) continue; /* * We need exclusive mmap_lock to retract page table. * * We use trylock due to lock inversion: we need to acquire * mmap_lock while holding page lock. Fault path does it in * reverse order. Trylock is a way to avoid deadlock. */ if (mmap_write_trylock(mm)) { if (!khugepaged_test_exit(mm)) { struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, addr, addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); /* assume page table is clear */ _pmd = pmdp_collapse_flush(vma, addr, pmd); mm_dec_nr_ptes(mm); tlb_remove_table_sync_one(); pte_free(mm, pmd_pgtable(_pmd)); mmu_notifier_invalidate_range_end(&range); } mmap_write_unlock(mm); } else { /* Try again later */ khugepaged_add_pte_mapped_thp(mm, addr); } } i_mmap_unlock_write(mapping); } /** * collapse_file - collapse filemap/tmpfs/shmem pages into huge one. * * @mm: process address space where collapse happens * @file: file that collapse on * @start: collapse start address * @hpage: new allocated huge page for collapse * @node: appointed node the new huge page allocate from * * Basic scheme is simple, details are more complex: * - allocate and lock a new huge page; * - scan page cache replacing old pages with the new one * + swap/gup in pages if necessary; * + fill in gaps; * + keep old pages around in case rollback is required; * - if replacing succeeds: * + copy data over; * + free old pages; * + unlock huge page; * - if replacing failed; * + put all pages back and unfreeze them; * + restore gaps in the page cache; * + unlock and free huge page; */ static void collapse_file(struct mm_struct *mm, struct file *file, pgoff_t start, struct page **hpage, int node) { struct address_space *mapping = file->f_mapping; gfp_t gfp; struct page *new_page; pgoff_t index, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); int nr; VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); /* Only allocate from the target node */ gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; new_page = khugepaged_alloc_page(hpage, gfp, node); if (!new_page) { result = SCAN_ALLOC_HUGE_PAGE_FAIL; goto out; } if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); /* This will be less messy when we use multi-index entries */ do { xas_lock_irq(&xas); xas_create_range(&xas); if (!xas_error(&xas)) break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { result = SCAN_FAIL; goto out; } } while (1); __SetPageLocked(new_page); if (is_shmem) __SetPageSwapBacked(new_page); new_page->index = start; new_page->mapping = mapping; /* * At this point the new_page is locked and not up-to-date. * It's safe to insert it into the page cache, because nobody would * be able to map it or use it in another way until we unlock it. */ xas_set(&xas, start); for (index = start; index < end; index++) { struct page *page = xas_next(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { if (!page) { /* * Stop if extent has been truncated or * hole-punched, and is now completely * empty. */ if (index == start) { if (!xas_next_entry(&xas, end - 1)) { result = SCAN_TRUNCATED; goto xa_locked; } xas_set(&xas, index); } if (!shmem_charge(mapping->host, 1)) { result = SCAN_FAIL; goto xa_locked; } xas_store(&xas, new_page); nr_none++; continue; } if (xa_is_value(page) || !PageUptodate(page)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_getpage(mapping->host, index, &page, SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (trylock_page(page)) { get_page(page); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } else { /* !is_shmem */ if (!page || xa_is_value(page)) { xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); /* drain pagevecs to help isolate_lru_page() */ lru_add_drain(); page = find_lock_page(mapping, index); if (unlikely(page == NULL)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (PageDirty(page)) { /* * khugepaged only works on read-only fd, * so this page is dirty because it hasn't * been flushed since first write. There * won't be new dirty pages. * * Trigger async flush here and hope the * writeback is done when khugepaged * revisits this page. * * This is a one-off situation. We are not * forcing writeback in loop. */ xas_unlock_irq(&xas); filemap_flush(mapping); result = SCAN_FAIL; goto xa_unlocked; } else if (PageWriteback(page)) { xas_unlock_irq(&xas); result = SCAN_FAIL; goto xa_unlocked; } else if (trylock_page(page)) { get_page(page); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } /* * The page must be locked, so we can drop the i_pages lock * without racing with truncate. */ VM_BUG_ON_PAGE(!PageLocked(page), page); /* make sure the page is up to date */ if (unlikely(!PageUptodate(page))) { result = SCAN_FAIL; goto out_unlock; } /* * If file was truncated then extended, or hole-punched, before * we locked the first page, then a THP might be there already. */ if (PageTransCompound(page)) { result = SCAN_PAGE_COMPOUND; goto out_unlock; } if (page_mapping(page) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } if (!is_shmem && (PageDirty(page) || PageWriteback(page))) { /* * khugepaged only works on read-only fd, so this * page is dirty because it hasn't been flushed * since first write. */ result = SCAN_FAIL; goto out_unlock; } if (isolate_lru_page(page)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; putback_lru_page(page); goto out_unlock; } if (page_mapped(page)) unmap_mapping_pages(mapping, index, 1, false); xas_lock_irq(&xas); xas_set(&xas, index); VM_BUG_ON_PAGE(page != xas_load(&xas), page); VM_BUG_ON_PAGE(page_mapped(page), page); /* * The page is expected to have page_count() == 3: * - we hold a pin on it; * - one reference from page cache; * - one from isolate_lru_page; */ if (!page_ref_freeze(page, 3)) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); putback_lru_page(page); goto out_unlock; } /* * Add the page to the list to be able to undo the collapse if * something go wrong. */ list_add_tail(&page->lru, &pagelist); /* Finally, replace with the new page. */ xas_store(&xas, new_page); continue; out_unlock: unlock_page(page); put_page(page); goto xa_unlocked; } nr = thp_nr_pages(new_page); if (is_shmem) __mod_lruvec_page_state(new_page, NR_SHMEM_THPS, nr); else { __mod_lruvec_page_state(new_page, NR_FILE_THPS, nr); filemap_nr_thps_inc(mapping); /* * Paired with smp_mb() in do_dentry_open() to ensure * i_writecount is up to date and the update to nr_thps is * visible. Ensures the page cache will be truncated if the * file is opened writable. */ smp_mb(); if (inode_is_open_for_write(mapping->host)) { result = SCAN_FAIL; __mod_lruvec_page_state(new_page, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); goto xa_locked; } } if (nr_none) { __mod_lruvec_page_state(new_page, NR_FILE_PAGES, nr_none); if (is_shmem) __mod_lruvec_page_state(new_page, NR_SHMEM, nr_none); } xa_locked: xas_unlock_irq(&xas); xa_unlocked: if (result == SCAN_SUCCEED) { struct page *page, *tmp; /* * Replacing old pages with new one has succeeded, now we * need to copy the content and free the old pages. */ index = start; list_for_each_entry_safe(page, tmp, &pagelist, lru) { while (index < page->index) { clear_highpage(new_page + (index % HPAGE_PMD_NR)); index++; } copy_highpage(new_page + (page->index % HPAGE_PMD_NR), page); list_del(&page->lru); page->mapping = NULL; page_ref_unfreeze(page, 1); ClearPageActive(page); ClearPageUnevictable(page); unlock_page(page); put_page(page); index++; } while (index < end) { clear_highpage(new_page + (index % HPAGE_PMD_NR)); index++; } SetPageUptodate(new_page); page_ref_add(new_page, HPAGE_PMD_NR - 1); if (is_shmem) set_page_dirty(new_page); lru_cache_add(new_page); /* * Remove pte page tables, so we can re-fault the page as huge. */ retract_page_tables(mapping, start); *hpage = NULL; khugepaged_pages_collapsed++; } else { struct page *page; /* Something went wrong: roll back page cache changes */ xas_lock_irq(&xas); mapping->nrpages -= nr_none; if (is_shmem) shmem_uncharge(mapping->host, nr_none); xas_set(&xas, start); xas_for_each(&xas, page, end - 1) { page = list_first_entry_or_null(&pagelist, struct page, lru); if (!page || xas.xa_index < page->index) { if (!nr_none) break; nr_none--; /* Put holes back where they were */ xas_store(&xas, NULL); continue; } VM_BUG_ON_PAGE(page->index != xas.xa_index, page); /* Unfreeze the page. */ list_del(&page->lru); page_ref_unfreeze(page, 2); xas_store(&xas, page); xas_pause(&xas); xas_unlock_irq(&xas); unlock_page(page); putback_lru_page(page); xas_lock_irq(&xas); } VM_BUG_ON(nr_none); xas_unlock_irq(&xas); new_page->mapping = NULL; } unlock_page(new_page); out: VM_BUG_ON(!list_empty(&pagelist)); if (!IS_ERR_OR_NULL(*hpage)) mem_cgroup_uncharge(*hpage); /* TODO: tracepoints */ } static void khugepaged_scan_file(struct mm_struct *mm, struct file *file, pgoff_t start, struct page **hpage) { struct page *page = NULL; struct address_space *mapping = file->f_mapping; XA_STATE(xas, &mapping->i_pages, start); int present, swap; int node = NUMA_NO_NODE; int result = SCAN_SUCCEED; present = 0; swap = 0; memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); rcu_read_lock(); xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, page)) continue; if (xa_is_value(page)) { if (++swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; break; } continue; } if (PageTransCompound(page)) { result = SCAN_PAGE_COMPOUND; break; } node = page_to_nid(page); if (khugepaged_scan_abort(node)) { result = SCAN_SCAN_ABORT; break; } khugepaged_node_load[node]++; if (!PageLRU(page)) { result = SCAN_PAGE_LRU; break; } if (page_count(page) != 1 + page_mapcount(page) + page_has_private(page)) { result = SCAN_PAGE_COUNT; break; } /* * We probably should check if the page is referenced here, but * nobody would transfer pte_young() to PageReferenced() for us. * And rmap walk here is just too costly... */ present++; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); if (result == SCAN_SUCCEED) { if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; } else { node = khugepaged_find_target_node(); collapse_file(mm, file, start, hpage, node); } } /* TODO: tracepoints */ } #else static void khugepaged_scan_file(struct mm_struct *mm, struct file *file, pgoff_t start, struct page **hpage) { BUILD_BUG(); } static void khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) { } #endif static unsigned int khugepaged_scan_mm_slot(unsigned int pages, struct page **hpage) __releases(&khugepaged_mm_lock) __acquires(&khugepaged_mm_lock) { struct mm_slot *mm_slot; struct mm_struct *mm; struct vm_area_struct *vma; int progress = 0; VM_BUG_ON(!pages); lockdep_assert_held(&khugepaged_mm_lock); if (khugepaged_scan.mm_slot) mm_slot = khugepaged_scan.mm_slot; else { mm_slot = list_entry(khugepaged_scan.mm_head.next, struct mm_slot, mm_node); khugepaged_scan.address = 0; khugepaged_scan.mm_slot = mm_slot; } spin_unlock(&khugepaged_mm_lock); khugepaged_collapse_pte_mapped_thps(mm_slot); mm = mm_slot->mm; /* * Don't wait for semaphore (to avoid long wait times). Just move to * the next mm on the list. */ vma = NULL; if (unlikely(!mmap_read_trylock(mm))) goto breakouterloop_mmap_lock; if (likely(!khugepaged_test_exit(mm))) vma = find_vma(mm, khugepaged_scan.address); progress++; for (; vma; vma = vma->vm_next) { unsigned long hstart, hend; cond_resched(); if (unlikely(khugepaged_test_exit(mm))) { progress++; break; } if (!hugepage_vma_check(vma, vma->vm_flags)) { skip: progress++; continue; } hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart >= hend) goto skip; if (khugepaged_scan.address > hend) goto skip; if (khugepaged_scan.address < hstart) khugepaged_scan.address = hstart; VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); if (shmem_file(vma->vm_file) && !shmem_huge_enabled(vma)) goto skip; while (khugepaged_scan.address < hend) { int ret; cond_resched(); if (unlikely(khugepaged_test_exit(mm))) goto breakouterloop; VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, khugepaged_scan.address); mmap_read_unlock(mm); ret = 1; khugepaged_scan_file(mm, file, pgoff, hpage); fput(file); } else { ret = khugepaged_scan_pmd(mm, vma, khugepaged_scan.address, hpage); } /* move to next address */ khugepaged_scan.address += HPAGE_PMD_SIZE; progress += HPAGE_PMD_NR; if (ret) /* we released mmap_lock so break loop */ goto breakouterloop_mmap_lock; if (progress >= pages) goto breakouterloop; } } breakouterloop: mmap_read_unlock(mm); /* exit_mmap will destroy ptes after this */ breakouterloop_mmap_lock: spin_lock(&khugepaged_mm_lock); VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); /* * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm. */ if (khugepaged_test_exit(mm) || !vma) { /* * Make sure that if mm_users is reaching zero while * khugepaged runs here, khugepaged_exit will find * mm_slot not pointing to the exiting mm. */ if (mm_slot->mm_node.next != &khugepaged_scan.mm_head) { khugepaged_scan.mm_slot = list_entry( mm_slot->mm_node.next, struct mm_slot, mm_node); khugepaged_scan.address = 0; } else { khugepaged_scan.mm_slot = NULL; khugepaged_full_scans++; } collect_mm_slot(mm_slot); } return progress; } static int khugepaged_has_work(void) { return !list_empty(&khugepaged_scan.mm_head) && khugepaged_enabled(); } static int khugepaged_wait_event(void) { return !list_empty(&khugepaged_scan.mm_head) || kthread_should_stop(); } static void khugepaged_do_scan(void) { struct page *hpage = NULL; unsigned int progress = 0, pass_through_head = 0; unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); bool wait = true; lru_add_drain_all(); while (progress < pages) { if (!khugepaged_prealloc_page(&hpage, &wait)) break; cond_resched(); if (unlikely(kthread_should_stop() || try_to_freeze())) break; spin_lock(&khugepaged_mm_lock); if (!khugepaged_scan.mm_slot) pass_through_head++; if (khugepaged_has_work() && pass_through_head < 2) progress += khugepaged_scan_mm_slot(pages - progress, &hpage); else progress = pages; spin_unlock(&khugepaged_mm_lock); } if (!IS_ERR_OR_NULL(hpage)) put_page(hpage); } static bool khugepaged_should_wakeup(void) { return kthread_should_stop() || time_after_eq(jiffies, khugepaged_sleep_expire); } static void khugepaged_wait_work(void) { if (khugepaged_has_work()) { const unsigned long scan_sleep_jiffies = msecs_to_jiffies(khugepaged_scan_sleep_millisecs); if (!scan_sleep_jiffies) return; khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; wait_event_freezable_timeout(khugepaged_wait, khugepaged_should_wakeup(), scan_sleep_jiffies); return; } if (khugepaged_enabled()) wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); } static int khugepaged(void *none) { struct mm_slot *mm_slot; set_freezable(); set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(); khugepaged_wait_work(); } spin_lock(&khugepaged_mm_lock); mm_slot = khugepaged_scan.mm_slot; khugepaged_scan.mm_slot = NULL; if (mm_slot) collect_mm_slot(mm_slot); spin_unlock(&khugepaged_mm_lock); return 0; } static void set_recommended_min_free_kbytes(void) { struct zone *zone; int nr_zones = 0; unsigned long recommended_min; for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of * ZONE_MOVABLE since it only has movable pages. */ if (zone_idx(zone) > gfp_zone(GFP_USER)) continue; nr_zones++; } /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ recommended_min = pageblock_nr_pages * nr_zones * 2; /* * Make sure that on average at least two pageblocks are almost free * of another type, one for a migratetype to fall back to and a * second to avoid subsequent fallbacks of other types There are 3 * MIGRATE_TYPES we care about. */ recommended_min += pageblock_nr_pages * nr_zones * MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; /* don't ever allow to reserve more than 5% of the lowmem */ recommended_min = min(recommended_min, (unsigned long) nr_free_buffer_pages() / 20); recommended_min <<= (PAGE_SHIFT-10); if (recommended_min > min_free_kbytes) { if (user_min_free_kbytes >= 0) pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", min_free_kbytes, recommended_min); min_free_kbytes = recommended_min; } setup_per_zone_wmarks(); } int start_stop_khugepaged(void) { int err = 0; mutex_lock(&khugepaged_mutex); if (khugepaged_enabled()) { if (!khugepaged_thread) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); if (IS_ERR(khugepaged_thread)) { pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; goto fail; } if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); set_recommended_min_free_kbytes(); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } fail: mutex_unlock(&khugepaged_mutex); return err; } void khugepaged_min_free_kbytes_update(void) { mutex_lock(&khugepaged_mutex); if (khugepaged_enabled() && khugepaged_thread) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } |
| 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 | /* 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, RQ_QOS_IOPRIO, }; struct rq_wait { wait_queue_head_t wait; atomic_t inflight; }; struct rq_qos { struct rq_qos_ops *ops; struct request_queue *q; 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 *blkcg_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); } static inline int rq_qos_add(struct request_queue *q, struct rq_qos *rqos) { /* * No IO can be in-flight when adding rqos, so freeze queue, which * is fine since we only support rq_qos for blk-mq queue. * * Reuse ->queue_lock for protecting against other concurrent * rq_qos adding/deleting */ blk_mq_freeze_queue(q); spin_lock_irq(&q->queue_lock); if (rq_qos_id(q, rqos->id)) goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; spin_unlock_irq(&q->queue_lock); blk_mq_unfreeze_queue(q); if (rqos->ops->debugfs_attrs) blk_mq_debugfs_register_rqos(rqos); return 0; ebusy: spin_unlock_irq(&q->queue_lock); blk_mq_unfreeze_queue(q); return -EBUSY; } static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) { struct rq_qos **cur; /* * See comment in rq_qos_add() about freezing queue & using * ->queue_lock. */ blk_mq_freeze_queue(q); spin_lock_irq(&q->queue_lock); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } spin_unlock_irq(&q->queue_lock); blk_mq_unfreeze_queue(q); blk_mq_debugfs_unregister_rqos(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 |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/panic.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * This function is used through-out the kernel (including mm and fs) * to indicate a major problem. */ #include <linux/debug_locks.h> #include <linux/sched/debug.h> #include <linux/interrupt.h> #include <linux/kgdb.h> #include <linux/kmsg_dump.h> #include <linux/kallsyms.h> #include <linux/notifier.h> #include <linux/vt_kern.h> #include <linux/module.h> #include <linux/random.h> #include <linux/ftrace.h> #include <linux/reboot.h> #include <linux/delay.h> #include <linux/kexec.h> #include <linux/panic_notifier.h> #include <linux/sched.h> #include <linux/sysrq.h> #include <linux/init.h> #include <linux/nmi.h> #include <linux/console.h> #include <linux/bug.h> #include <linux/ratelimit.h> #include <linux/debugfs.h> #include <linux/sysfs.h> #include <asm/sections.h> #define PANIC_TIMER_STEP 100 #define PANIC_BLINK_SPD 18 #ifdef CONFIG_SMP /* * Should we dump all CPUs backtraces in an oops event? * Defaults to 0, can be changed via sysctl. */ static unsigned int __read_mostly sysctl_oops_all_cpu_backtrace; #else #define sysctl_oops_all_cpu_backtrace 0 #endif /* CONFIG_SMP */ int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE; static unsigned long tainted_mask = IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0; static int pause_on_oops; static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); bool crash_kexec_post_notifiers; int panic_on_warn __read_mostly; unsigned long panic_on_taint; bool panic_on_taint_nousertaint = false; static unsigned int warn_limit __read_mostly; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); #define PANIC_PRINT_TASK_INFO 0x00000001 #define PANIC_PRINT_MEM_INFO 0x00000002 #define PANIC_PRINT_TIMER_INFO 0x00000004 #define PANIC_PRINT_LOCK_INFO 0x00000008 #define PANIC_PRINT_FTRACE_INFO 0x00000010 #define PANIC_PRINT_ALL_PRINTK_MSG 0x00000020 unsigned long panic_print; ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); #ifdef CONFIG_SYSCTL static struct ctl_table kern_panic_table[] = { #ifdef CONFIG_SMP { .procname = "oops_all_cpu_backtrace", .data = &sysctl_oops_all_cpu_backtrace, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "warn_limit", .data = &warn_limit, .maxlen = sizeof(warn_limit), .mode = 0644, .proc_handler = proc_douintvec, }, { } }; static __init int kernel_panic_sysctls_init(void) { register_sysctl_init("kernel", kern_panic_table); return 0; } late_initcall(kernel_panic_sysctls_init); #endif static atomic_t warn_count = ATOMIC_INIT(0); #ifdef CONFIG_SYSFS static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return sysfs_emit(page, "%d\n", atomic_read(&warn_count)); } static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count); static __init int kernel_panic_sysfs_init(void) { sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL); return 0; } late_initcall(kernel_panic_sysfs_init); #endif static long no_blink(int state) { return 0; } /* Returns how long it waited in ms */ long (*panic_blink)(int state); EXPORT_SYMBOL(panic_blink); /* * Stop ourself in panic -- architecture code may override this */ void __weak panic_smp_self_stop(void) { while (1) cpu_relax(); } /* * Stop ourselves in NMI context if another CPU has already panicked. Arch code * may override this to prepare for crash dumping, e.g. save regs info. */ void __weak nmi_panic_self_stop(struct pt_regs *regs) { panic_smp_self_stop(); } /* * Stop other CPUs in panic. Architecture dependent code may override this * with more suitable version. For example, if the architecture supports * crash dump, it should save registers of each stopped CPU and disable * per-CPU features such as virtualization extensions. */ void __weak crash_smp_send_stop(void) { static int cpus_stopped; /* * This function can be called twice in panic path, but obviously * we execute this only once. */ if (cpus_stopped) return; /* * Note smp_send_stop is the usual smp shutdown function, which * unfortunately means it may not be hardened to work in a panic * situation. */ smp_send_stop(); cpus_stopped = 1; } atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); /* * A variant of panic() called from NMI context. We return if we've already * panicked on this CPU. If another CPU already panicked, loop in * nmi_panic_self_stop() which can provide architecture dependent code such * as saving register state for crash dump. */ void nmi_panic(struct pt_regs *regs, const char *msg) { int old_cpu, cpu; cpu = raw_smp_processor_id(); old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); if (old_cpu == PANIC_CPU_INVALID) panic("%s", msg); else if (old_cpu != cpu) nmi_panic_self_stop(regs); } EXPORT_SYMBOL(nmi_panic); static void panic_print_sys_info(void) { if (panic_print & PANIC_PRINT_ALL_PRINTK_MSG) console_flush_on_panic(CONSOLE_REPLAY_ALL); if (panic_print & PANIC_PRINT_TASK_INFO) show_state(); if (panic_print & PANIC_PRINT_MEM_INFO) show_mem(0, NULL); if (panic_print & PANIC_PRINT_TIMER_INFO) sysrq_timer_list_show(); if (panic_print & PANIC_PRINT_LOCK_INFO) debug_show_all_locks(); if (panic_print & PANIC_PRINT_FTRACE_INFO) ftrace_dump(DUMP_ALL); } void check_panic_on_warn(const char *origin) { unsigned int limit; if (panic_on_warn) panic("%s: panic_on_warn set ...\n", origin); limit = READ_ONCE(warn_limit); if (atomic_inc_return(&warn_count) >= limit && limit) panic("%s: system warned too often (kernel.warn_limit is %d)", origin, limit); } /** * panic - halt the system * @fmt: The text string to print * * Display a message, then perform cleanups. * * This function never returns. */ void panic(const char *fmt, ...) { static char buf[1024]; va_list args; long i, i_next = 0, len; int state = 0; int old_cpu, this_cpu; bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers; if (panic_on_warn) { /* * This thread may hit another WARN() in the panic path. * Resetting this prevents additional WARN() from panicking the * system on this thread. Other threads are blocked by the * panic_mutex in panic(). */ panic_on_warn = 0; } /* * Disable local interrupts. This will prevent panic_smp_self_stop * from deadlocking the first cpu that invokes the panic, since * there is nothing to prevent an interrupt handler (that runs * after setting panic_cpu) from invoking panic() again. */ local_irq_disable(); preempt_disable_notrace(); /* * It's possible to come here directly from a panic-assertion and * not have preempt disabled. Some functions called from here want * preempt to be disabled. No point enabling it later though... * * Only one CPU is allowed to execute the panic code from here. For * multiple parallel invocations of panic, all other CPUs either * stop themself or will wait until they are stopped by the 1st CPU * with smp_send_stop(). * * `old_cpu == PANIC_CPU_INVALID' means this is the 1st CPU which * comes here, so go ahead. * `old_cpu == this_cpu' means we came from nmi_panic() which sets * panic_cpu to this CPU. In this case, this is also the 1st CPU. */ this_cpu = raw_smp_processor_id(); old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu); if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu) panic_smp_self_stop(); console_verbose(); bust_spinlocks(1); va_start(args, fmt); len = vscnprintf(buf, sizeof(buf), fmt, args); va_end(args); if (len && buf[len - 1] == '\n') buf[len - 1] = '\0'; pr_emerg("Kernel panic - not syncing: %s\n", buf); #ifdef CONFIG_DEBUG_BUGVERBOSE /* * Avoid nested stack-dumping if a panic occurs during oops processing */ if (!test_taint(TAINT_DIE) && oops_in_progress <= 1) dump_stack(); #endif /* * If kgdb is enabled, give it a chance to run before we stop all * the other CPUs or else we won't be able to debug processes left * running on them. */ kgdb_panic(buf); /* * If we have crashed and we have a crash kernel loaded let it handle * everything else. * If we want to run this after calling panic_notifiers, pass * the "crash_kexec_post_notifiers" option to the kernel. * * Bypass the panic_cpu check and call __crash_kexec directly. */ if (!_crash_kexec_post_notifiers) { __crash_kexec(NULL); /* * Note smp_send_stop is the usual smp shutdown function, which * unfortunately means it may not be hardened to work in a * panic situation. */ smp_send_stop(); } else { /* * If we want to do crash dump after notifier calls and * kmsg_dump, we will need architecture dependent extra * works in addition to stopping other CPUs. */ crash_smp_send_stop(); } /* * Run any panic handlers, including those that might need to * add information to the kmsg dump output. */ atomic_notifier_call_chain(&panic_notifier_list, 0, buf); kmsg_dump(KMSG_DUMP_PANIC); /* * If you doubt kdump always works fine in any situation, * "crash_kexec_post_notifiers" offers you a chance to run * panic_notifiers and dumping kmsg before kdump. * Note: since some panic_notifiers can make crashed kernel * more unstable, it can increase risks of the kdump failure too. * * Bypass the panic_cpu check and call __crash_kexec directly. */ if (_crash_kexec_post_notifiers) __crash_kexec(NULL); #ifdef CONFIG_VT unblank_screen(); #endif console_unblank(); /* * We may have ended up stopping the CPU holding the lock (in * smp_send_stop()) while still having some valuable data in the console * buffer. Try to acquire the lock then release it regardless of the * result. The release will also print the buffers out. Locks debug * should be disabled to avoid reporting bad unlock balance when * panic() is not being callled from OOPS. */ debug_locks_off(); console_flush_on_panic(CONSOLE_FLUSH_PENDING); panic_print_sys_info(); if (!panic_blink) panic_blink = no_blink; if (panic_timeout > 0) { /* * Delay timeout seconds before rebooting the machine. * We can't use the "normal" timers since we just panicked. */ pr_emerg("Rebooting in %d seconds..\n", panic_timeout); for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); if (i >= i_next) { i += panic_blink(state ^= 1); i_next = i + 3600 / PANIC_BLINK_SPD; } mdelay(PANIC_TIMER_STEP); } } if (panic_timeout != 0) { /* * This will not be a clean reboot, with everything * shutting down. But if there is a chance of * rebooting the system it will be rebooted. */ if (panic_reboot_mode != REBOOT_UNDEFINED) reboot_mode = panic_reboot_mode; emergency_restart(); } #ifdef __sparc__ { extern int stop_a_enabled; /* Make sure the user can actually press Stop-A (L1-A) */ stop_a_enabled = 1; pr_emerg("Press Stop-A (L1-A) from sun keyboard or send break\n" "twice on console to return to the boot prom\n"); } #endif #if defined(CONFIG_S390) disabled_wait(); #endif pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf); /* Do not scroll important messages printed above */ suppress_printk = 1; /* * The final messages may not have been printed if in a context that * defers printing (such as NMI) and irq_work is not available. * Explicitly flush the kernel log buffer one last time. */ console_flush_on_panic(CONSOLE_FLUSH_PENDING); local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); if (i >= i_next) { i += panic_blink(state ^= 1); i_next = i + 3600 / PANIC_BLINK_SPD; } mdelay(PANIC_TIMER_STEP); } } EXPORT_SYMBOL(panic); /* * TAINT_FORCED_RMMOD could be a per-module flag but the module * is being removed anyway. */ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = { [ TAINT_PROPRIETARY_MODULE ] = { 'P', 'G', true }, [ TAINT_FORCED_MODULE ] = { 'F', ' ', true }, [ TAINT_CPU_OUT_OF_SPEC ] = { 'S', ' ', false }, [ TAINT_FORCED_RMMOD ] = { 'R', ' ', false }, [ TAINT_MACHINE_CHECK ] = { 'M', ' ', false }, [ TAINT_BAD_PAGE ] = { 'B', ' ', false }, [ TAINT_USER ] = { 'U', ' ', false }, [ TAINT_DIE ] = { 'D', ' ', false }, [ TAINT_OVERRIDDEN_ACPI_TABLE ] = { 'A', ' ', false }, [ TAINT_WARN ] = { 'W', ' ', false }, [ TAINT_CRAP ] = { 'C', ' ', true }, [ TAINT_FIRMWARE_WORKAROUND ] = { 'I', ' ', false }, [ TAINT_OOT_MODULE ] = { 'O', ' ', true }, [ TAINT_UNSIGNED_MODULE ] = { 'E', ' ', true }, [ TAINT_SOFTLOCKUP ] = { 'L', ' ', false }, [ TAINT_LIVEPATCH ] = { 'K', ' ', true }, [ TAINT_AUX ] = { 'X', ' ', true }, [ TAINT_RANDSTRUCT ] = { 'T', ' ', true }, }; /** * print_tainted - return a string to represent the kernel taint state. * * For individual taint flag meanings, see Documentation/admin-guide/sysctl/kernel.rst * * The string is overwritten by the next call to print_tainted(), * but is always NULL terminated. */ const char *print_tainted(void) { static char buf[TAINT_FLAGS_COUNT + sizeof("Tainted: ")]; BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT); if (tainted_mask) { char *s; int i; s = buf + sprintf(buf, "Tainted: "); for (i = 0; i < TAINT_FLAGS_COUNT; i++) { const struct taint_flag *t = &taint_flags[i]; *s++ = test_bit(i, &tainted_mask) ? t->c_true : t->c_false; } *s = 0; } else snprintf(buf, sizeof(buf), "Not tainted"); return buf; } int test_taint(unsigned flag) { return test_bit(flag, &tainted_mask); } EXPORT_SYMBOL(test_taint); unsigned long get_taint(void) { return tainted_mask; } /** * add_taint: add a taint flag if not already set. * @flag: one of the TAINT_* constants. * @lockdep_ok: whether lock debugging is still OK. * * If something bad has gone wrong, you'll want @lockdebug_ok = false, but for * some notewortht-but-not-corrupting cases, it can be set to true. */ void add_taint(unsigned flag, enum lockdep_ok lockdep_ok) { if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off()) pr_warn("Disabling lock debugging due to kernel taint\n"); set_bit(flag, &tainted_mask); if (tainted_mask & panic_on_taint) { panic_on_taint = 0; panic("panic_on_taint set ..."); } } EXPORT_SYMBOL(add_taint); static void spin_msec(int msecs) { int i; for (i = 0; i < msecs; i++) { touch_nmi_watchdog(); mdelay(1); } } /* * It just happens that oops_enter() and oops_exit() are identically * implemented... */ static void do_oops_enter_exit(void) { unsigned long flags; static int spin_counter; if (!pause_on_oops) return; spin_lock_irqsave(&pause_on_oops_lock, flags); if (pause_on_oops_flag == 0) { /* This CPU may now print the oops message */ pause_on_oops_flag = 1; } else { /* We need to stall this CPU */ if (!spin_counter) { /* This CPU gets to do the counting */ spin_counter = pause_on_oops; do { spin_unlock(&pause_on_oops_lock); spin_msec(MSEC_PER_SEC); spin_lock(&pause_on_oops_lock); } while (--spin_counter); pause_on_oops_flag = 0; } else { /* This CPU waits for a different one */ while (spin_counter) { spin_unlock(&pause_on_oops_lock); spin_msec(1); spin_lock(&pause_on_oops_lock); } } } spin_unlock_irqrestore(&pause_on_oops_lock, flags); } /* * Return true if the calling CPU is allowed to print oops-related info. * This is a bit racy.. */ bool oops_may_print(void) { return pause_on_oops_flag == 0; } /* * Called when the architecture enters its oops handler, before it prints * anything. If this is the first CPU to oops, and it's oopsing the first * time then let it proceed. * * This is all enabled by the pause_on_oops kernel boot option. We do all * this to ensure that oopses don't scroll off the screen. It has the * side-effect of preventing later-oopsing CPUs from mucking up the display, * too. * * It turns out that the CPU which is allowed to print ends up pausing for * the right duration, whereas all the other CPUs pause for twice as long: * once in oops_enter(), once in oops_exit(). */ void oops_enter(void) { tracing_off(); /* can't trust the integrity of the kernel anymore: */ debug_locks_off(); do_oops_enter_exit(); if (sysctl_oops_all_cpu_backtrace) trigger_all_cpu_backtrace(); } /* * 64-bit random ID for oopses: */ static u64 oops_id; static int init_oops_id(void) { if (!oops_id) get_random_bytes(&oops_id, sizeof(oops_id)); else oops_id++; return 0; } late_initcall(init_oops_id); static void print_oops_end_marker(void) { init_oops_id(); pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id); } /* * Called when the architecture exits its oops handler, after printing * everything. */ void oops_exit(void) { do_oops_enter_exit(); print_oops_end_marker(); kmsg_dump(KMSG_DUMP_OOPS); } struct warn_args { const char *fmt; va_list args; }; void __warn(const char *file, int line, void *caller, unsigned taint, struct pt_regs *regs, struct warn_args *args) { disable_trace_on_warning(); if (file) pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", raw_smp_processor_id(), current->pid, file, line, caller); else pr_warn("WARNING: CPU: %d PID: %d at %pS\n", raw_smp_processor_id(), current->pid, caller); if (args) vprintk(args->fmt, args->args); print_modules(); if (regs) show_regs(regs); check_panic_on_warn("kernel"); if (!regs) dump_stack(); print_irqtrace_events(current); print_oops_end_marker(); /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); } #ifndef __WARN_FLAGS void warn_slowpath_fmt(const char *file, int line, unsigned taint, const char *fmt, ...) { struct warn_args args; pr_warn(CUT_HERE); if (!fmt) { __warn(file, line, __builtin_return_address(0), taint, NULL, NULL); return; } args.fmt = fmt; va_start(args.args, fmt); __warn(file, line, __builtin_return_address(0), taint, NULL, &args); va_end(args.args); } EXPORT_SYMBOL(warn_slowpath_fmt); #else void __warn_printk(const char *fmt, ...) { va_list args; pr_warn(CUT_HERE); va_start(args, fmt); vprintk(fmt, args); va_end(args); } EXPORT_SYMBOL(__warn_printk); #endif #ifdef CONFIG_BUG /* Support resetting WARN*_ONCE state */ static int clear_warn_once_set(void *data, u64 val) { generic_bug_clear_once(); memset(__start_once, 0, __end_once - __start_once); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(clear_warn_once_fops, NULL, clear_warn_once_set, "%lld\n"); static __init int register_warn_debugfs(void) { /* Don't care about failure */ debugfs_create_file_unsafe("clear_warn_once", 0200, NULL, NULL, &clear_warn_once_fops); return 0; } device_initcall(register_warn_debugfs); #endif #ifdef CONFIG_STACKPROTECTOR /* * Called when gcc's -fstack-protector feature is used, and * gcc detects corruption of the on-stack canary value */ __visible noinstr void __stack_chk_fail(void) { instrumentation_begin(); panic("stack-protector: Kernel stack is corrupted in: %pB", __builtin_return_address(0)); instrumentation_end(); } EXPORT_SYMBOL(__stack_chk_fail); #endif core_param(panic, panic_timeout, int, 0644); core_param(panic_print, panic_print, ulong, 0644); core_param(pause_on_oops, pause_on_oops, int, 0644); core_param(panic_on_warn, panic_on_warn, int, 0644); core_param(crash_kexec_post_notifiers, crash_kexec_post_notifiers, bool, 0644); static int __init oops_setup(char *s) { if (!s) return -EINVAL; if (!strcmp(s, "panic")) panic_on_oops = 1; return 0; } early_param("oops", oops_setup); static int __init panic_on_taint_setup(char *s) { char *taint_str; if (!s) return -EINVAL; taint_str = strsep(&s, ","); if (kstrtoul(taint_str, 16, &panic_on_taint)) return -EINVAL; /* make sure panic_on_taint doesn't hold out-of-range TAINT flags */ panic_on_taint &= TAINT_FLAGS_MAX; if (!panic_on_taint) return -EINVAL; if (s && !strcmp(s, "nousertaint")) panic_on_taint_nousertaint = true; pr_info("panic_on_taint: bitmask=0x%lx nousertaint_mode=%sabled\n", panic_on_taint, panic_on_taint_nousertaint ? "en" : "dis"); return 0; } early_param("panic_on_taint", panic_on_taint_setup); |
| 5 5 8 8 8 2 1 1 9 9 3 2 1 1 3 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 | /* * Copyright (c) 2006, 2019 Oracle and/or its affiliates. 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. * */ #include <linux/kernel.h> #include <linux/slab.h> #include <net/sock.h> #include <linux/in.h> #include <linux/export.h> #include <linux/time.h> #include <linux/rds.h> #include "rds.h" void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, struct in6_addr *saddr) { refcount_set(&inc->i_refcount, 1); INIT_LIST_HEAD(&inc->i_item); inc->i_conn = conn; inc->i_saddr = *saddr; inc->i_usercopy.rdma_cookie = 0; inc->i_usercopy.rx_tstamp = ktime_set(0, 0); memset(inc->i_rx_lat_trace, 0, sizeof(inc->i_rx_lat_trace)); } EXPORT_SYMBOL_GPL(rds_inc_init); void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp, struct in6_addr *saddr) { refcount_set(&inc->i_refcount, 1); INIT_LIST_HEAD(&inc->i_item); inc->i_conn = cp->cp_conn; inc->i_conn_path = cp; inc->i_saddr = *saddr; inc->i_usercopy.rdma_cookie = 0; inc->i_usercopy.rx_tstamp = ktime_set(0, 0); } EXPORT_SYMBOL_GPL(rds_inc_path_init); static void rds_inc_addref(struct rds_incoming *inc) { rdsdebug("addref inc %p ref %d\n", inc, refcount_read(&inc->i_refcount)); refcount_inc(&inc->i_refcount); } void rds_inc_put(struct rds_incoming *inc) { rdsdebug("put inc %p ref %d\n", inc, refcount_read(&inc->i_refcount)); if (refcount_dec_and_test(&inc->i_refcount)) { BUG_ON(!list_empty(&inc->i_item)); inc->i_conn->c_trans->inc_free(inc); } } EXPORT_SYMBOL_GPL(rds_inc_put); static void rds_recv_rcvbuf_delta(struct rds_sock *rs, struct sock *sk, struct rds_cong_map *map, int delta, __be16 port) { int now_congested; if (delta == 0) return; rs->rs_rcv_bytes += delta; if (delta > 0) rds_stats_add(s_recv_bytes_added_to_socket, delta); else rds_stats_add(s_recv_bytes_removed_from_socket, -delta); /* loop transport doesn't send/recv congestion updates */ if (rs->rs_transport->t_type == RDS_TRANS_LOOP) return; now_congested = rs->rs_rcv_bytes > rds_sk_rcvbuf(rs); rdsdebug("rs %p (%pI6c:%u) recv bytes %d buf %d " "now_cong %d delta %d\n", rs, &rs->rs_bound_addr, ntohs(rs->rs_bound_port), rs->rs_rcv_bytes, rds_sk_rcvbuf(rs), now_congested, delta); /* wasn't -> am congested */ if (!rs->rs_congested && now_congested) { rs->rs_congested = 1; rds_cong_set_bit(map, port); rds_cong_queue_updates(map); } /* was -> aren't congested */ /* Require more free space before reporting uncongested to prevent bouncing cong/uncong state too often */ else if (rs->rs_congested && (rs->rs_rcv_bytes < (rds_sk_rcvbuf(rs)/2))) { rs->rs_congested = 0; rds_cong_clear_bit(map, port); rds_cong_queue_updates(map); } /* do nothing if no change in cong state */ } static void rds_conn_peer_gen_update(struct rds_connection *conn, u32 peer_gen_num) { int i; struct rds_message *rm, *tmp; unsigned long flags; WARN_ON(conn->c_trans->t_type != RDS_TRANS_TCP); if (peer_gen_num != 0) { if (conn->c_peer_gen_num != 0 && peer_gen_num != conn->c_peer_gen_num) { for (i = 0; i < RDS_MPATH_WORKERS; i++) { struct rds_conn_path *cp; cp = &conn->c_path[i]; spin_lock_irqsave(&cp->cp_lock, flags); cp->cp_next_tx_seq = 1; cp->cp_next_rx_seq = 0; list_for_each_entry_safe(rm, tmp, &cp->cp_retrans, m_conn_item) { set_bit(RDS_MSG_FLUSH, &rm->m_flags); } spin_unlock_irqrestore(&cp->cp_lock, flags); } } conn->c_peer_gen_num = peer_gen_num; } } /* * Process all extension headers that come with this message. */ static void rds_recv_incoming_exthdrs(struct rds_incoming *inc, struct rds_sock *rs) { struct rds_header *hdr = &inc->i_hdr; unsigned int pos = 0, type, len; union { struct rds_ext_header_version version; struct rds_ext_header_rdma rdma; struct rds_ext_header_rdma_dest rdma_dest; } buffer; while (1) { len = sizeof(buffer); type = rds_message_next_extension(hdr, &pos, &buffer, &len); if (type == RDS_EXTHDR_NONE) break; /* Process extension header here */ switch (type) { case RDS_EXTHDR_RDMA: rds_rdma_unuse(rs, be32_to_cpu(buffer.rdma.h_rdma_rkey), 0); break; case RDS_EXTHDR_RDMA_DEST: /* We ignore the size for now. We could stash it * somewhere and use it for error checking. */ inc->i_usercopy.rdma_cookie = rds_rdma_make_cookie( be32_to_cpu(buffer.rdma_dest.h_rdma_rkey), be32_to_cpu(buffer.rdma_dest.h_rdma_offset)); break; } } } static void rds_recv_hs_exthdrs(struct rds_header *hdr, struct rds_connection *conn) { unsigned int pos = 0, type, len; union { struct rds_ext_header_version version; u16 rds_npaths; u32 rds_gen_num; } buffer; u32 new_peer_gen_num = 0; while (1) { len = sizeof(buffer); type = rds_message_next_extension(hdr, &pos, &buffer, &len); if (type == RDS_EXTHDR_NONE) break; /* Process extension header here */ switch (type) { case RDS_EXTHDR_NPATHS: conn->c_npaths = min_t(int, RDS_MPATH_WORKERS, be16_to_cpu(buffer.rds_npaths)); break; case RDS_EXTHDR_GEN_NUM: new_peer_gen_num = be32_to_cpu(buffer.rds_gen_num); break; default: pr_warn_ratelimited("ignoring unknown exthdr type " "0x%x\n", type); } } /* if RDS_EXTHDR_NPATHS was not found, default to a single-path */ conn->c_npaths = max_t(int, conn->c_npaths, 1); conn->c_ping_triggered = 0; rds_conn_peer_gen_update(conn, new_peer_gen_num); } /* rds_start_mprds() will synchronously start multiple paths when appropriate. * The scheme is based on the following rules: * * 1. rds_sendmsg on first connect attempt sends the probe ping, with the * sender's npaths (s_npaths) * 2. rcvr of probe-ping knows the mprds_paths = min(s_npaths, r_npaths). It * sends back a probe-pong with r_npaths. After that, if rcvr is the * smaller ip addr, it starts rds_conn_path_connect_if_down on all * mprds_paths. * 3. sender gets woken up, and can move to rds_conn_path_connect_if_down. * If it is the smaller ipaddr, rds_conn_path_connect_if_down can be * called after reception of the probe-pong on all mprds_paths. * Otherwise (sender of probe-ping is not the smaller ip addr): just call * rds_conn_path_connect_if_down on the hashed path. (see rule 4) * 4. rds_connect_worker must only trigger a connection if laddr < faddr. * 5. sender may end up queuing the packet on the cp. will get sent out later. * when connection is completed. */ static void rds_start_mprds(struct rds_connection *conn) { int i; struct rds_conn_path *cp; if (conn->c_npaths > 1 && rds_addr_cmp(&conn->c_laddr, &conn->c_faddr) < 0) { for (i = 0; i < conn->c_npaths; i++) { cp = &conn->c_path[i]; rds_conn_path_connect_if_down(cp); } } } /* * The transport must make sure that this is serialized against other * rx and conn reset on this specific conn. * * We currently assert that only one fragmented message will be sent * down a connection at a time. This lets us reassemble in the conn * instead of per-flow which means that we don't have to go digging through * flows to tear down partial reassembly progress on conn failure and * we save flow lookup and locking for each frag arrival. It does mean * that small messages will wait behind large ones. Fragmenting at all * is only to reduce the memory consumption of pre-posted buffers. * * The caller passes in saddr and daddr instead of us getting it from the * conn. This lets loopback, who only has one conn for both directions, * tell us which roles the addrs in the conn are playing for this message. */ void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr, struct in6_addr *daddr, struct rds_incoming *inc, gfp_t gfp) { struct rds_sock *rs = NULL; struct sock *sk; unsigned long flags; struct rds_conn_path *cp; inc->i_conn = conn; inc->i_rx_jiffies = jiffies; if (conn->c_trans->t_mp_capable) cp = inc->i_conn_path; else cp = &conn->c_path[0]; rdsdebug("conn %p next %llu inc %p seq %llu len %u sport %u dport %u " "flags 0x%x rx_jiffies %lu\n", conn, (unsigned long long)cp->cp_next_rx_seq, inc, (unsigned long long)be64_to_cpu(inc->i_hdr.h_sequence), be32_to_cpu(inc->i_hdr.h_len), be16_to_cpu(inc->i_hdr.h_sport), be16_to_cpu(inc->i_hdr.h_dport), inc->i_hdr.h_flags, inc->i_rx_jiffies); /* * Sequence numbers should only increase. Messages get their * sequence number as they're queued in a sending conn. They * can be dropped, though, if the sending socket is closed before * they hit the wire. So sequence numbers can skip forward * under normal operation. They can also drop back in the conn * failover case as previously sent messages are resent down the * new instance of a conn. We drop those, otherwise we have * to assume that the next valid seq does not come after a * hole in the fragment stream. * * The headers don't give us a way to realize if fragments of * a message have been dropped. We assume that frags that arrive * to a flow are part of the current message on the flow that is * being reassembled. This means that senders can't drop messages * from the sending conn until all their frags are sent. * * XXX we could spend more on the wire to get more robust failure * detection, arguably worth it to avoid data corruption. */ if (be64_to_cpu(inc->i_hdr.h_sequence) < cp->cp_next_rx_seq && (inc->i_hdr.h_flags & RDS_FLAG_RETRANSMITTED)) { rds_stats_inc(s_recv_drop_old_seq); goto out; } cp->cp_next_rx_seq = be64_to_cpu(inc->i_hdr.h_sequence) + 1; if (rds_sysctl_ping_enable && inc->i_hdr.h_dport == 0) { if (inc->i_hdr.h_sport == 0) { rdsdebug("ignore ping with 0 sport from %pI6c\n", saddr); goto out; } rds_stats_inc(s_recv_ping); rds_send_pong(cp, inc->i_hdr.h_sport); /* if this is a handshake ping, start multipath if necessary */ if (RDS_HS_PROBE(be16_to_cpu(inc->i_hdr.h_sport), be16_to_cpu(inc->i_hdr.h_dport))) { rds_recv_hs_exthdrs(&inc->i_hdr, cp->cp_conn); rds_start_mprds(cp->cp_conn); } goto out; } if (be16_to_cpu(inc->i_hdr.h_dport) == RDS_FLAG_PROBE_PORT && inc->i_hdr.h_sport == 0) { rds_recv_hs_exthdrs(&inc->i_hdr, cp->cp_conn); /* if this is a handshake pong, start multipath if necessary */ rds_start_mprds(cp->cp_conn); wake_up(&cp->cp_conn->c_hs_waitq); goto out; } rs = rds_find_bound(daddr, inc->i_hdr.h_dport, conn->c_bound_if); if (!rs) { rds_stats_inc(s_recv_drop_no_sock); goto out; } /* Process extension headers */ rds_recv_incoming_exthdrs(inc, rs); /* We can be racing with rds_release() which marks the socket dead. */ sk = rds_rs_to_sk(rs); /* serialize with rds_release -> sock_orphan */ write_lock_irqsave(&rs->rs_recv_lock, flags); if (!sock_flag(sk, SOCK_DEAD)) { rdsdebug("adding inc %p to rs %p's recv queue\n", inc, rs); rds_stats_inc(s_recv_queued); rds_recv_rcvbuf_delta(rs, sk, inc->i_conn->c_lcong, be32_to_cpu(inc->i_hdr.h_len), inc->i_hdr.h_dport); if (sock_flag(sk, SOCK_RCVTSTAMP)) inc->i_usercopy.rx_tstamp = ktime_get_real(); rds_inc_addref(inc); inc->i_rx_lat_trace[RDS_MSG_RX_END] = local_clock(); list_add_tail(&inc->i_item, &rs->rs_recv_queue); __rds_wake_sk_sleep(sk); } else { rds_stats_inc(s_recv_drop_dead_sock); } write_unlock_irqrestore(&rs->rs_recv_lock, flags); out: if (rs) rds_sock_put(rs); } EXPORT_SYMBOL_GPL(rds_recv_incoming); /* * be very careful here. This is being called as the condition in * wait_event_*() needs to cope with being called many times. */ static int rds_next_incoming(struct rds_sock *rs, struct rds_incoming **inc) { unsigned long flags; if (!*inc) { read_lock_irqsave(&rs->rs_recv_lock, flags); if (!list_empty(&rs->rs_recv_queue)) { *inc = list_entry(rs->rs_recv_queue.next, struct rds_incoming, i_item); rds_inc_addref(*inc); } read_unlock_irqrestore(&rs->rs_recv_lock, flags); } return *inc != NULL; } static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, int drop) { struct sock *sk = rds_rs_to_sk(rs); int ret = 0; unsigned long flags; struct rds_incoming *to_drop = NULL; write_lock_irqsave(&rs->rs_recv_lock, flags); if (!list_empty(&inc->i_item)) { ret = 1; if (drop) { /* XXX make sure this i_conn is reliable */ rds_recv_rcvbuf_delta(rs, sk, inc->i_conn->c_lcong, -be32_to_cpu(inc->i_hdr.h_len), inc->i_hdr.h_dport); list_del_init(&inc->i_item); to_drop = inc; } } write_unlock_irqrestore(&rs->rs_recv_lock, flags); if (to_drop) rds_inc_put(to_drop); rdsdebug("inc %p rs %p still %d dropped %d\n", inc, rs, ret, drop); return ret; } /* * Pull errors off the error queue. * If msghdr is NULL, we will just purge the error queue. */ int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr) { struct rds_notifier *notifier; struct rds_rdma_notify cmsg; unsigned int count = 0, max_messages = ~0U; unsigned long flags; LIST_HEAD(copy); int err = 0; memset(&cmsg, 0, sizeof(cmsg)); /* fill holes with zero */ /* put_cmsg copies to user space and thus may sleep. We can't do this * with rs_lock held, so first grab as many notifications as we can stuff * in the user provided cmsg buffer. We don't try to copy more, to avoid * losing notifications - except when the buffer is so small that it wouldn't * even hold a single notification. Then we give him as much of this single * msg as we can squeeze in, and set MSG_CTRUNC. */ if (msghdr) { max_messages = msghdr->msg_controllen / CMSG_SPACE(sizeof(cmsg)); if (!max_messages) max_messages = 1; } spin_lock_irqsave(&rs->rs_lock, flags); while (!list_empty(&rs->rs_notify_queue) && count < max_messages) { notifier = list_entry(rs->rs_notify_queue.next, struct rds_notifier, n_list); list_move(¬ifier->n_list, ©); count++; } spin_unlock_irqrestore(&rs->rs_lock, flags); if (!count) return 0; while (!list_empty(©)) { notifier = list_entry(copy.next, struct rds_notifier, n_list); if (msghdr) { cmsg.user_token = notifier->n_user_token; cmsg.status = notifier->n_status; err = put_cmsg(msghdr, SOL_RDS, RDS_CMSG_RDMA_STATUS, sizeof(cmsg), &cmsg); if (err) break; } list_del_init(¬ifier->n_list); kfree(notifier); } /* If we bailed out because of an error in put_cmsg, * we may be left with one or more notifications that we * didn't process. Return them to the head of the list. */ if (!list_empty(©)) { spin_lock_irqsave(&rs->rs_lock, flags); list_splice(©, &rs->rs_notify_queue); spin_unlock_irqrestore(&rs->rs_lock, flags); } return err; } /* * Queue a congestion notification */ static int rds_notify_cong(struct rds_sock *rs, struct msghdr *msghdr) { uint64_t notify = rs->rs_cong_notify; unsigned long flags; int err; err = put_cmsg(msghdr, SOL_RDS, RDS_CMSG_CONG_UPDATE, sizeof(notify), ¬ify); if (err) return err; spin_lock_irqsave(&rs->rs_lock, flags); rs->rs_cong_notify &= ~notify; spin_unlock_irqrestore(&rs->rs_lock, flags); return 0; } /* * Receive any control messages. */ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, struct rds_sock *rs) { int ret = 0; if (inc->i_usercopy.rdma_cookie) { ret = put_cmsg(msg, SOL_RDS, RDS_CMSG_RDMA_DEST, sizeof(inc->i_usercopy.rdma_cookie), &inc->i_usercopy.rdma_cookie); if (ret) goto out; } if ((inc->i_usercopy.rx_tstamp != 0) && sock_flag(rds_rs_to_sk(rs), SOCK_RCVTSTAMP)) { struct __kernel_old_timeval tv = ns_to_kernel_old_timeval(inc->i_usercopy.rx_tstamp); if (!sock_flag(rds_rs_to_sk(rs), SOCK_TSTAMP_NEW)) { ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } else { struct __kernel_sock_timeval sk_tv; sk_tv.tv_sec = tv.tv_sec; sk_tv.tv_usec = tv.tv_usec; ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(sk_tv), &sk_tv); } if (ret) goto out; } if (rs->rs_rx_traces) { struct rds_cmsg_rx_trace t; int i, j; memset(&t, 0, sizeof(t)); inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock(); t.rx_traces = rs->rs_rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { j = rs->rs_rx_trace[i]; t.rx_trace_pos[i] = j; t.rx_trace[i] = inc->i_rx_lat_trace[j + 1] - inc->i_rx_lat_trace[j]; } ret = put_cmsg(msg, SOL_RDS, RDS_CMSG_RXPATH_LATENCY, sizeof(t), &t); if (ret) goto out; } out: return ret; } static bool rds_recvmsg_zcookie(struct rds_sock *rs, struct msghdr *msg) { struct rds_msg_zcopy_queue *q = &rs->rs_zcookie_queue; struct rds_msg_zcopy_info *info = NULL; struct rds_zcopy_cookies *done; unsigned long flags; if (!msg->msg_control) return false; if (!sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY) || msg->msg_controllen < CMSG_SPACE(sizeof(*done))) return false; spin_lock_irqsave(&q->lock, flags); if (!list_empty(&q->zcookie_head)) { info = list_entry(q->zcookie_head.next, struct rds_msg_zcopy_info, rs_zcookie_next); list_del(&info->rs_zcookie_next); } spin_unlock_irqrestore(&q->lock, flags); if (!info) return false; done = &info->zcookies; if (put_cmsg(msg, SOL_RDS, RDS_CMSG_ZCOPY_COMPLETION, sizeof(*done), done)) { spin_lock_irqsave(&q->lock, flags); list_add(&info->rs_zcookie_next, &q->zcookie_head); spin_unlock_irqrestore(&q->lock, flags); return false; } kfree(info); return true; } int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int msg_flags) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); long timeo; int ret = 0, nonblock = msg_flags & MSG_DONTWAIT; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct rds_incoming *inc = NULL; /* udp_recvmsg()->sock_recvtimeo() gets away without locking too.. */ timeo = sock_rcvtimeo(sk, nonblock); rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo); if (msg_flags & MSG_OOB) goto out; if (msg_flags & MSG_ERRQUEUE) return sock_recv_errqueue(sk, msg, size, SOL_IP, IP_RECVERR); while (1) { /* If there are pending notifications, do those - and nothing else */ if (!list_empty(&rs->rs_notify_queue)) { ret = rds_notify_queue_get(rs, msg); break; } if (rs->rs_cong_notify) { ret = rds_notify_cong(rs, msg); break; } if (!rds_next_incoming(rs, &inc)) { if (nonblock) { bool reaped = rds_recvmsg_zcookie(rs, msg); ret = reaped ? 0 : -EAGAIN; break; } timeo = wait_event_interruptible_timeout(*sk_sleep(sk), (!list_empty(&rs->rs_notify_queue) || rs->rs_cong_notify || rds_next_incoming(rs, &inc)), timeo); rdsdebug("recvmsg woke inc %p timeo %ld\n", inc, timeo); if (timeo > 0 || timeo == MAX_SCHEDULE_TIMEOUT) continue; ret = timeo; if (ret == 0) ret = -ETIMEDOUT; break; } rdsdebug("copying inc %p from %pI6c:%u to user\n", inc, &inc->i_conn->c_faddr, ntohs(inc->i_hdr.h_sport)); ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &msg->msg_iter); if (ret < 0) break; /* * if the message we just copied isn't at the head of the * recv queue then someone else raced us to return it, try * to get the next message. */ if (!rds_still_queued(rs, inc, !(msg_flags & MSG_PEEK))) { rds_inc_put(inc); inc = NULL; rds_stats_inc(s_recv_deliver_raced); iov_iter_revert(&msg->msg_iter, ret); continue; } if (ret < be32_to_cpu(inc->i_hdr.h_len)) { if (msg_flags & MSG_TRUNC) ret = be32_to_cpu(inc->i_hdr.h_len); msg->msg_flags |= MSG_TRUNC; } if (rds_cmsg_recv(inc, msg, rs)) { ret = -EFAULT; break; } rds_recvmsg_zcookie(rs, msg); rds_stats_inc(s_recv_delivered); if (msg->msg_name) { if (ipv6_addr_v4mapped(&inc->i_saddr)) { sin->sin_family = AF_INET; sin->sin_port = inc->i_hdr.h_sport; sin->sin_addr.s_addr = inc->i_saddr.s6_addr32[3]; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); msg->msg_namelen = sizeof(*sin); } else { sin6->sin6_family = AF_INET6; sin6->sin6_port = inc->i_hdr.h_sport; sin6->sin6_addr = inc->i_saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = rs->rs_bound_scope_id; msg->msg_namelen = sizeof(*sin6); } } break; } if (inc) rds_inc_put(inc); out: return ret; } /* * The socket is being shut down and we're asked to drop messages that were * queued for recvmsg. The caller has unbound the socket so the receive path * won't queue any more incoming fragments or messages on the socket. */ void rds_clear_recv_queue(struct rds_sock *rs) { struct sock *sk = rds_rs_to_sk(rs); struct rds_incoming *inc, *tmp; unsigned long flags; LIST_HEAD(to_drop); write_lock_irqsave(&rs->rs_recv_lock, flags); list_for_each_entry_safe(inc, tmp, &rs->rs_recv_queue, i_item) { rds_recv_rcvbuf_delta(rs, sk, inc->i_conn->c_lcong, -be32_to_cpu(inc->i_hdr.h_len), inc->i_hdr.h_dport); list_move(&inc->i_item, &to_drop); } write_unlock_irqrestore(&rs->rs_recv_lock, flags); list_for_each_entry_safe(inc, tmp, &to_drop, i_item) { list_del_init(&inc->i_item); rds_inc_put(inc); } } /* * inc->i_saddr isn't used here because it is only set in the receive * path. */ void rds_inc_info_copy(struct rds_incoming *inc, struct rds_info_iterator *iter, __be32 saddr, __be32 daddr, int flip) { struct rds_info_message minfo; minfo.seq = be64_to_cpu(inc->i_hdr.h_sequence); minfo.len = be32_to_cpu(inc->i_hdr.h_len); minfo.tos = inc->i_conn->c_tos; if (flip) { minfo.laddr = daddr; minfo.faddr = saddr; minfo.lport = inc->i_hdr.h_dport; minfo.fport = inc->i_hdr.h_sport; } else { minfo.laddr = saddr; minfo.faddr = daddr; minfo.lport = inc->i_hdr.h_sport; minfo.fport = inc->i_hdr.h_dport; } minfo.flags = 0; rds_info_copy(iter, &minfo, sizeof(minfo)); } #if IS_ENABLED(CONFIG_IPV6) void rds6_inc_info_copy(struct rds_incoming *inc, struct rds_info_iterator *iter, struct in6_addr *saddr, struct in6_addr *daddr, int flip) { struct rds6_info_message minfo6; minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence); minfo6.len = be32_to_cpu(inc->i_hdr.h_len); minfo6.tos = inc->i_conn->c_tos; if (flip) { minfo6.laddr = *daddr; minfo6.faddr = *saddr; minfo6.lport = inc->i_hdr.h_dport; minfo6.fport = inc->i_hdr.h_sport; } else { minfo6.laddr = *saddr; minfo6.faddr = *daddr; minfo6.lport = inc->i_hdr.h_sport; minfo6.fport = inc->i_hdr.h_dport; } minfo6.flags = 0; rds_info_copy(iter, &minfo6, sizeof(minfo6)); } #endif |
| 43 174 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Checksumming functions for IP, TCP, UDP and so on * * Authors: Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Borrows very liberally from tcp.c and ip.c, see those * files for more names. */ #ifndef _CHECKSUM_H #define _CHECKSUM_H #include <linux/errno.h> #include <asm/types.h> #include <asm/byteorder.h> #include <linux/uaccess.h> #include <asm/checksum.h> #ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER static __always_inline __wsum csum_and_copy_from_user (const void __user *src, void *dst, int len) { if (copy_from_user(dst, src, len)) return 0; return csum_partial(dst, len, ~0U); } #endif #ifndef HAVE_CSUM_COPY_USER static __always_inline __wsum csum_and_copy_to_user (const void *src, void __user *dst, int len) { __wsum sum = csum_partial(src, len, ~0U); if (copy_to_user(dst, src, len) == 0) return sum; return 0; } #endif #ifndef _HAVE_ARCH_CSUM_AND_COPY static __always_inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len) { memcpy(dst, src, len); return csum_partial(dst, len, 0); } #endif #ifndef HAVE_ARCH_CSUM_ADD static __always_inline __wsum csum_add(__wsum csum, __wsum addend) { u32 res = (__force u32)csum; res += (__force u32)addend; return (__force __wsum)(res + (res < (__force u32)addend)); } #endif static __always_inline __wsum csum_sub(__wsum csum, __wsum addend) { return csum_add(csum, ~addend); } static __always_inline __sum16 csum16_add(__sum16 csum, __be16 addend) { u16 res = (__force u16)csum; res += (__force u16)addend; return (__force __sum16)(res + (res < (__force u16)addend)); } static __always_inline __sum16 csum16_sub(__sum16 csum, __be16 addend) { return csum16_add(csum, ~addend); } static __always_inline __wsum csum_shift(__wsum sum, int offset) { /* rotate sum to align it with a 16b boundary */ if (offset & 1) return (__force __wsum)ror32((__force u32)sum, 8); return sum; } static __always_inline __wsum csum_block_add(__wsum csum, __wsum csum2, int offset) { return csum_add(csum, csum_shift(csum2, offset)); } static __always_inline __wsum csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len) { return csum_block_add(csum, csum2, offset); } static __always_inline __wsum csum_block_sub(__wsum csum, __wsum csum2, int offset) { return csum_block_add(csum, ~csum2, offset); } static __always_inline __wsum csum_unfold(__sum16 n) { return (__force __wsum)n; } static __always_inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum) { return csum_partial(buff, len, sum); } #define CSUM_MANGLED_0 ((__force __sum16)0xffff) static __always_inline void csum_replace_by_diff(__sum16 *sum, __wsum diff) { *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); } static __always_inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) { __wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from); *sum = csum_fold(csum_add(tmp, (__force __wsum)to)); } /* Implements RFC 1624 (Incremental Internet Checksum) * 3. Discussion states : * HC' = ~(~HC + ~m + m') * m : old value of a 16bit field * m' : new value of a 16bit field */ static __always_inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new) { *sum = ~csum16_add(csum16_sub(~(*sum), old), new); } static inline void csum_replace(__wsum *csum, __wsum old, __wsum new) { *csum = csum_add(csum_sub(*csum, old), new); } struct sk_buff; void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr); void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr); void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, __wsum diff, bool pseudohdr); static __always_inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb, __be16 from, __be16 to, bool pseudohdr) { inet_proto_csum_replace4(sum, skb, (__force __be32)from, (__force __be32)to, pseudohdr); } static __always_inline __wsum remcsum_adjust(void *ptr, __wsum csum, int start, int offset) { __sum16 *psum = (__sum16 *)(ptr + offset); __wsum delta; /* Subtract out checksum up to start */ csum = csum_sub(csum, csum_partial(ptr, start, 0)); /* Set derived checksum in packet */ delta = csum_sub((__force __wsum)csum_fold(csum), (__force __wsum)*psum); *psum = csum_fold(csum); return delta; } static __always_inline void remcsum_unadjust(__sum16 *psum, __wsum delta) { *psum = csum_fold(csum_sub(delta, (__force __wsum)*psum)); } #endif |
| 8081 8203 8074 102 27 27 27 27 27 27 333 336 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 | // SPDX-License-Identifier: GPL-2.0-or-later /* Common capabilities, needed by capability.o. */ #include <linux/capability.h> #include <linux/audit.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/ptrace.h> #include <linux/xattr.h> #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/securebits.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> #include <linux/mnt_idmapping.h> /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. * However if fE is also set, then the intent is for only * the file capabilities to be applied, and the setuid-root * bit is left on either to change the uid (plausible) or * to get full privilege on a kernel without file capabilities * support. So in that case we do not raise capabilities. * * Warn if that happens, once per boot. */ static void warn_setuid_and_fcaps_mixed(const char *fname) { static int warned; if (!warned) { printk(KERN_INFO "warning: `%s' has both setuid-root and" " effective capabilities. Therefore not raising all" " capabilities.\n", fname); warned = 1; } } /** * cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @targ_ns: The user namespace in which we need the capability * @cap: The capability to check for * @opts: Bitmask of options defined in include/linux/security.h * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() * and has_capability() functions. That is, it has the reverse semantics: * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, int cap, unsigned int opts) { struct user_namespace *ns = targ_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target * user namespace's parents. */ for (;;) { /* Do we have the necessary capabilities? */ if (ns == cred->user_ns) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ if (ns->level <= cred->user_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* * If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ ns = ns->parent; } /* We never get here */ } /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set * @tz: The timezone to set * * Determine whether the current process may set the system clock and timezone * information, returning 0 if permission granted, -ve if denied. */ int cap_settime(const struct timespec64 *ts, const struct timezone *tz) { if (!capable(CAP_SYS_TIME)) return -EPERM; return 0; } /** * cap_ptrace_access_check - Determine whether the current process may access * another * @child: The process to be accessed * @mode: The mode of attachment. * * If we are in the same or an ancestor user_ns and have all the target * task's capabilities, then ptrace access is allowed. * If we have the ptrace capability to the target user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); if (mode & PTRACE_MODE_FSCREDS) caller_caps = &cred->cap_effective; else caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * * If parent is in the same or an ancestor user_ns and has all current's * capabilities, then ptrace access is allowed. * If parent has the ptrace capability to current's user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; const struct cred *cred, *child_cred; rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_capget - Retrieve a task's capability sets * @target: The task from which to retrieve the capability sets * @effective: The place to record the effective set * @inheritable: The place to record the inheritable set * @permitted: The place to record the permitted set * * This function retrieves the capabilities of the nominated task and returns * them to the caller. */ int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { const struct cred *cred; /* Derived from kernel/capability.c:sys_capget. */ rcu_read_lock(); cred = __task_cred(target); *effective = cred->cap_effective; *inheritable = cred->cap_inheritable; *permitted = cred->cap_permitted; rcu_read_unlock(); return 0; } /* * Determine whether the inheritable capabilities are limited to the old * permitted set. Returns 1 if they are limited, 0 if they are not. */ static inline int cap_inh_is_capped(void) { /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } /** * cap_capset - Validate and apply proposed changes to current's capabilities * @new: The proposed new credentials; alterations should be made here * @old: The current task's current credentials * @effective: A pointer to the proposed new effective capabilities set * @inheritable: A pointer to the proposed new inheritable capabilities set * @permitted: A pointer to the proposed new permitted capabilities set * * This function validates and applies a proposed mass change to the current * process's capability sets. The changes are made to the proposed new * credentials, and assuming no error, will be committed by the caller of LSM. */ int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { if (cap_inh_is_capped() && !cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; if (!cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; /* verify restrictions on target's new Permitted set */ if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ if (!cap_issubset(*effective, *permitted)) return -EPERM; new->cap_effective = *effective; new->cap_inheritable = *inheritable; new->cap_permitted = *permitted; /* * Mask off ambient bits that are no longer both permitted and * inheritable. */ new->cap_ambient = cap_intersect(new->cap_ambient, cap_intersect(*permitted, *inheritable)); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EINVAL; return 0; } /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should * inode_killpriv() be invoked or the change rejected. * * Return: 1 if security.capability has a value, meaning inode_killpriv() * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); int error; error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0); return error > 0; } /** * cap_inode_killpriv - Erase the security markings on an inode * * @mnt_userns: user namespace of the mount the inode was found from * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. * * Return: 0 if successful, -ve on error. */ int cap_inode_killpriv(struct user_namespace *mnt_userns, struct dentry *dentry) { int error; error = __vfs_removexattr(mnt_userns, dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; } static bool rootid_owns_currentns(kuid_t kroot) { struct user_namespace *ns; if (!uid_valid(kroot)) return false; for (ns = current_user_ns(); ; ns = ns->parent) { if (from_kuid(ns, kroot) == 0) return true; if (ns == &init_user_ns) break; } return false; } static __u32 sansflags(__u32 m) { return m & ~VFS_CAP_FLAGS_EFFECTIVE; } static bool is_v2header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_2) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2; } static bool is_v3header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_3) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3; } /* * getsecurity: We are called for security.* before any attempt to read the * xattr from the inode itself. * * This gives us a chance to read the on-disk value and convert it. If we * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. * * Note we are not called by vfs_getxattr_alloc(), but that is only called * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ int cap_inode_getsecurity(struct user_namespace *mnt_userns, struct inode *inode, const char *name, void **buffer, bool alloc) { int size, ret; kuid_t kroot; u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; if (strcmp(name, "capability") != 0) return -EOPNOTSUPP; dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; size = sizeof(struct vfs_ns_cap_data); ret = (int)vfs_getxattr_alloc(mnt_userns, dentry, XATTR_NAME_CAPS, &tmpbuf, size, GFP_NOFS); dput(dentry); if (ret < 0 || !tmpbuf) { size = ret; goto out_free; } fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header((size_t) ret, cap)) { root = 0; } else if (is_v3header((size_t) ret, cap)) { nscap = (struct vfs_ns_cap_data *) tmpbuf; root = le32_to_cpu(nscap->rootid); } else { size = -EINVAL; goto out_free; } kroot = make_kuid(fs_ns, root); /* If this is an idmapped mount shift the kuid. */ kroot = mapped_kuid_fs(mnt_userns, fs_ns, kroot); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), kroot); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { size = sizeof(struct vfs_ns_cap_data); if (alloc) { if (!nscap) { /* v2 -> v3 conversion */ nscap = kzalloc(size, GFP_ATOMIC); if (!nscap) { size = -ENOMEM; goto out_free; } nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); nscap->magic_etc = cpu_to_le32(nsmagic); } else { /* use allocated v3 buffer */ tmpbuf = NULL; } nscap->rootid = cpu_to_le32(mappedroot); *buffer = nscap; } goto out_free; } if (!rootid_owns_currentns(kroot)) { size = -EOVERFLOW; goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { if (nscap) { /* v3 -> v2 conversion */ cap = kzalloc(size, GFP_ATOMIC); if (!cap) { size = -ENOMEM; goto out_free; } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { /* use unconverted v2 */ tmpbuf = NULL; } *buffer = cap; } out_free: kfree(tmpbuf); return size; } /** * rootid_from_xattr - translate root uid of vfs caps * * @value: vfs caps value which may be modified by this function * @size: size of @ivalue * @task_ns: user namespace of the caller * @mnt_userns: user namespace of the mount the inode was found from * @fs_userns: user namespace of the filesystem * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. */ static kuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns, struct user_namespace *mnt_userns, struct user_namespace *fs_userns) { const struct vfs_ns_cap_data *nscap = value; kuid_t rootkid; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); rootkid = make_kuid(task_ns, rootid); return mapped_kuid_user(mnt_userns, fs_userns, rootkid); } static bool validheader(size_t size, const struct vfs_cap_data *cap) { return is_v2header(size, cap) || is_v3header(size, cap); } /** * cap_convert_nscap - check vfs caps * * @mnt_userns: user namespace of the mount the inode was found from * @dentry: used to retrieve inode to check permissions on * @ivalue: vfs caps value which may be modified by this function * @size: size of @ivalue * * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. * * Return: On success, return the new size; on error, return < 0. */ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, const void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; const struct vfs_cap_data *cap = *ivalue; __u32 magic, nsmagic; struct inode *inode = d_backing_inode(dentry); struct user_namespace *task_ns = current_user_ns(), *fs_ns = inode->i_sb->s_user_ns; kuid_t rootid; size_t newsize; if (!*ivalue) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2 && (mnt_userns == fs_ns)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, fs_ns); if (!uid_valid(rootid)) return -EINVAL; nsrootid = from_kuid(fs_ns, rootid); if (nsrootid == -1) return -EINVAL; newsize = sizeof(struct vfs_ns_cap_data); nscap = kmalloc(newsize, GFP_ATOMIC); if (!nscap) return -ENOMEM; nscap->rootid = cpu_to_le32(nsrootid); nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); *ivalue = nscap; return newsize; } /* * Calculate the new process capability sets from the capability sets attached * to a file. */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, bool *effective, bool *has_fcap) { struct cred *new = bprm->cred; unsigned i; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; CAP_FOR_EACH_U32(i) { __u32 permitted = caps->permitted.cap[i]; __u32 inheritable = caps->inheritable.cap[i]; /* * pP' = (X & fP) | (pI & fI) * The addition of pA' is handled later. */ new->cap_permitted.cap[i] = (new->cap_bset.cap[i] & permitted) | (new->cap_inheritable.cap[i] & inheritable); if (permitted & ~new->cap_permitted.cap[i]) /* insufficient to execute correctly */ ret = -EPERM; } /* * For legacy apps, with no internal support for recognizing they * do not have enough capabilities, we return an error if they are * missing some "forced" (aka file-permitted) capabilities. */ return *effective ? ret : 0; } /** * get_vfs_caps_from_disk - retrieve vfs caps from disk * * @mnt_userns: user namespace of the mount the inode was found from * @dentry: dentry from which @inode is retrieved * @cpu_caps: vfs capabilities * * Extract the on-exec-apply capability sets for an executable file. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. */ int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; unsigned tocopy, i; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; tocopy = VFS_CAP_U32_1; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; tocopy = VFS_CAP_U32_2; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; tocopy = VFS_CAP_U32_3; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; default: return -EINVAL; } /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ rootkuid = mapped_kuid_fs(mnt_userns, fs_ns, rootkuid); if (!rootid_owns_currentns(rootkuid)) return -ENODATA; CAP_FOR_EACH_U32(i) { if (i >= tocopy) break; cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted); cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable); } cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->rootid = rootkuid; return 0; } /* * Attempt to get the on-exec apply capability sets for an executable file from * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ static int get_file_caps(struct linux_binprm *bprm, struct file *file, bool *effective, bool *has_fcap) { int rc = 0; struct cpu_vfs_cap_data vcaps; cap_clear(bprm->cred->cap_permitted); if (!file_caps_enabled) return 0; if (!mnt_may_suid(file->f_path.mnt)) return 0; /* * This check is redundant with mnt_may_suid() but is kept to make * explicit that capability bits are limited to s_user_ns and its * descendants. */ if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; rc = get_vfs_caps_from_disk(file_mnt_user_ns(file), file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; } rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap); out: if (rc) cap_clear(bprm->cred->cap_permitted); return rc; } static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); } static inline bool __is_real(kuid_t uid, struct cred *cred) { return uid_eq(cred->uid, uid); } static inline bool __is_eff(kuid_t uid, struct cred *cred) { return uid_eq(cred->euid, uid); } static inline bool __is_suid(kuid_t uid, struct cred *cred) { return !__is_real(uid, cred) && __is_eff(uid, cred); } /* * handle_privileged_root - Handle case of privileged root * @bprm: The execution parameters, including the proposed creds * @has_fcap: Are any file capabilities set? * @effective: Do we have effective root privilege? * @root_uid: This namespace' root UID WRT initial USER namespace * * Handle the case where root is privileged and hasn't been neutered by * SECURE_NOROOT. If file capabilities are set, they won't be combined with * set UID root and nothing is changed. If we are root, cap_permitted is * updated. If we have become set UID root, the effective bit is set. */ static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap, bool *effective, kuid_t root_uid) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; if (!root_privileged()) return; /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ if (has_fcap && __is_suid(root_uid, new)) { warn_setuid_and_fcaps_mixed(bprm->filename); return; } /* * To support inheritance of root-permissions and suid-root * executables under compatibility mode, we override the * capability sets for the file. */ if (__is_eff(root_uid, new) || __is_real(root_uid, new)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } /* * If only the real uid is 0, we do not set the effective bit. */ if (__is_eff(root_uid, new)) *effective = true; } #define __cap_gained(field, target, source) \ !cap_issubset(target->cap_##field, source->cap_##field) #define __cap_grew(target, source, cred) \ !cap_issubset(cred->cap_##target, cred->cap_##source) #define __cap_full(field, cred) \ cap_issubset(CAP_FULL_SET, cred->cap_##field) static inline bool __is_setuid(struct cred *new, const struct cred *old) { return !uid_eq(new->euid, old->uid); } static inline bool __is_setgid(struct cred *new, const struct cred *old) { return !gid_eq(new->egid, old->gid); } /* * 1) Audit candidate if current->cap_effective is set * * We do not bother to audit if 3 things are true: * 1) cap_effective has all caps * 2) we became root *OR* are were already root * 3) root is supposed to have all caps (SECURE_NOROOT) * Since this is just a normal root execing a process. * * Number 1 above might fail if you don't have a full bset, but I think * that is interesting information to audit. * * A number of other conditions require logging: * 2) something prevented setuid root getting all caps * 3) non-setuid root gets fcaps * 4) non-setuid root gets ambient */ static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old, kuid_t root, bool has_fcap) { bool ret = false; if ((__cap_grew(effective, ambient, new) && !(__cap_full(effective, new) && (__is_eff(root, new) || __is_real(root, new)) && root_privileged())) || (root_privileged() && __is_suid(root, new) && !__cap_full(effective, new)) || (!__is_setuid(new, old) && ((has_fcap && __cap_gained(permitted, new, old)) || __cap_gained(ambient, new, old)))) ret = true; return ret; } /** * cap_bprm_creds_from_file - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds * @file: The file to pull the credentials from * * Set up the proposed credentials for a new execution context being * constructed by execve(). The proposed creds in @bprm->cred is altered, * which won't take effect immediately. * * Return: 0 if successful, -ve on error. */ int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file) { /* Process setpcap binaries and capabilities for uid 0 */ const struct cred *old = current_cred(); struct cred *new = bprm->cred; bool effective = false, has_fcap = false, is_setid; int ret; kuid_t root_uid; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; ret = get_file_caps(bprm, file, &effective, &has_fcap); if (ret < 0) return ret; root_uid = make_kuid(new->user_ns, 0); handle_privileged_root(bprm, has_fcap, &effective, root_uid); /* if we have fs caps, clear dangerous personality flags */ if (__cap_gained(permitted, new, old)) bprm->per_clear |= PER_CLEAR_ON_SETID; /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit. * * In addition, if NO_NEW_PRIVS, then ensure we get no new privs. */ is_setid = __is_setuid(new, old) || __is_setgid(new, old); if ((is_setid || __cap_gained(permitted, new, old)) && ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) || !ptracer_capable(current, new->user_ns))) { /* downgrade; they get no more than they had, and maybe less */ if (!ns_capable(new->user_ns, CAP_SETUID) || (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) { new->euid = new->uid; new->egid = new->gid; } new->cap_permitted = cap_intersect(new->cap_permitted, old->cap_permitted); } new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; /* File caps or setid cancels ambient. */ if (has_fcap || is_setid) cap_clear(new->cap_ambient); /* * Now that we've computed pA', update pP' to give: * pP' = (X & fP) | (pI & fI) | pA' */ new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient); /* * Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set, * this is the same as pE' = (fE ? pP' : 0) | pA'. */ if (effective) new->cap_effective = new->cap_permitted; else new->cap_effective = new->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; if (nonroot_raised_pE(new, old, root_uid, has_fcap)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) return ret; } new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; /* Check for privilege-elevated exec. */ if (is_setid || (!__is_real(root_uid, new) && (effective || __cap_grew(permitted, ambient, new)))) bprm->secureexec = 1; return 0; } /** * cap_inode_setxattr - Determine whether an xattr may be altered * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * @value: The value that the xattr will be changed to * @size: The size of value * @flags: The replacement flag * * Determine whether an xattr may be altered or set on an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get updated or set by those * who aren't privileged to do so. */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; /* * For XATTR_NAME_CAPS the check will be done in * cap_convert_nscap(), called by setxattr() */ if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /** * cap_inode_removexattr - Determine whether an xattr may be removed * * @mnt_userns: User namespace of the mount the inode was found from * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ int cap_inode_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; if (strcmp(name, XATTR_NAME_CAPS) == 0) { /* security.capability gets namespaced */ struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; return 0; } if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * * 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of * {r,e,s}uid != 0, the permitted and effective capabilities are * cleared. * * 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective * capabilities of the process are cleared. * * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it * calls setuid() and switches away from uid==0. Both permitted and * effective sets will be retained. * Without this change, it was impossible for a daemon to drop only some * of its privilege. The call to setuid(!=0) would drop all privileges! * Keeping uid 0 is not an option because uid 0 owns too many vital * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { kuid_t root_uid = make_kuid(old->user_ns, 0); if ((uid_eq(old->uid, root_uid) || uid_eq(old->euid, root_uid) || uid_eq(old->suid, root_uid)) && (!uid_eq(new->uid, root_uid) && !uid_eq(new->euid, root_uid) && !uid_eq(new->suid, root_uid))) { if (!issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } /* * Pre-ambient programs expect setresuid to nonroot followed * by exec to drop capabilities. We should make sure that * this remains the case. */ cap_clear(new->cap_ambient); } if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } /** * cap_task_fix_setuid - Fix up the results of setuid() call * @new: The proposed credentials * @old: The current task's current credentials * @flags: Indications of what has changed * * Fix up the results of setuid() call before the credential changes are * actually applied. * * Return: 0 to grant the changes, -ve to deny them. */ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: /* juggle the capabilities to follow [RES]UID changes unless * otherwise suppressed */ if (!issecure(SECURE_NO_SETUID_FIXUP)) cap_emulate_setxuid(new, old); break; case LSM_SETID_FS: /* juggle the capabilties to follow FSUID changes, unless * otherwise suppressed * * FIXME - is fsuser used for all CAP_FS_MASK capabilities? * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(old->user_ns, 0); if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); } break; default: return -EINVAL; } return 0; } /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that * . if capable(cap_sys_nice), then those actions should be allowed * . if not capable(cap_sys_nice), but acting on your own processes, * then those actions should be allowed * This is insufficient now since you can call code without suid, but * yet with increased caps. * So we check for increased caps on the target process. */ static int cap_safe_nice(struct task_struct *p) { int is_subset, ret = 0; rcu_read_lock(); is_subset = cap_issubset(__task_cred(p)->cap_permitted, current_cred()->cap_permitted); if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) ret = -EPERM; rcu_read_unlock(); return ret; } /** * cap_task_setscheduler - Detemine if scheduler policy change is permitted * @p: The task to affect * * Detemine if the requested scheduler policy change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setscheduler(struct task_struct *p) { return cap_safe_nice(p); } /** * cap_task_setioprio - Detemine if I/O priority change is permitted * @p: The task to affect * @ioprio: The I/O priority to set * * Detemine if the requested I/O priority change is permitted for the specified * task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } /** * cap_task_setnice - Detemine if task priority change is permitted * @p: The task to affect * @nice: The nice value to set * * Detemine if the requested task priority change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from * the current task's bounding set. Returns 0 on success, -ve on error. */ static int cap_prctl_drop(unsigned long cap) { struct cred *new; if (!ns_capable(current_user_ns(), CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_lower(new->cap_bset, cap); return commit_creds(new); } /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested * @arg2: The argument data for this function * @arg3: The argument data for this function * @arg4: The argument data for this function * @arg5: The argument data for this function * * Allow process control functions (sys_prctl()) to alter capabilities; may * also deny access to other functions not otherwise implemented here. * * Return: 0 or +ve on success, -ENOSYS if this function is not implemented * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM * modules will consider performing the function. */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { const struct cred *old = current_cred(); struct cred *new; switch (option) { case PR_CAPBSET_READ: if (!cap_valid(arg2)) return -EINVAL; return !!cap_raised(old->cap_bset, arg2); case PR_CAPBSET_DROP: return cap_prctl_drop(arg2); /* * The next four prctl's remain to assist with transitioning a * system from legacy UID=0 based privilege (when filesystem * capabilities are not in use) to a system using filesystem * capabilities only - as the POSIX.1e draft intended. * * Note: * * PR_SET_SECUREBITS = * issecure_mask(SECURE_KEEP_CAPS_LOCKED) * | issecure_mask(SECURE_NOROOT) * | issecure_mask(SECURE_NOROOT_LOCKED) * | issecure_mask(SECURE_NO_SETUID_FIXUP) * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED) * * will ensure that the current process and all of its * children will be locked into a pure * capability-based-privilege environment. */ case PR_SET_SECUREBITS: if ((((old->securebits & SECURE_ALL_LOCKS) >> 1) & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ || (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits * [4] doing anything requires privilege (go read about * the "sendmail capabilities bug") */ ) /* cannot change a locked bit */ return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; new->securebits = arg2; return commit_creds(new); case PR_GET_SECUREBITS: return old->securebits; case PR_GET_KEEPCAPS: return !!issecure(SECURE_KEEP_CAPS); case PR_SET_KEEPCAPS: if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ return -EINVAL; if (issecure(SECURE_KEEP_CAPS_LOCKED)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2) new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); return commit_creds(new); case PR_CAP_AMBIENT: if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) { if (arg3 | arg4 | arg5) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_clear(new->cap_ambient); return commit_creds(new); } if (((!cap_valid(arg3)) | arg4 | arg5)) return -EINVAL; if (arg2 == PR_CAP_AMBIENT_IS_SET) { return !!cap_raised(current_cred()->cap_ambient, arg3); } else if (arg2 != PR_CAP_AMBIENT_RAISE && arg2 != PR_CAP_AMBIENT_LOWER) { return -EINVAL; } else { if (arg2 == PR_CAP_AMBIENT_RAISE && (!cap_raised(current_cred()->cap_permitted, arg3) || !cap_raised(current_cred()->cap_inheritable, arg3) || issecure(SECURE_NO_CAP_AMBIENT_RAISE))) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2 == PR_CAP_AMBIENT_RAISE) cap_raise(new->cap_ambient, arg3); else cap_lower(new->cap_ambient, arg3); return commit_creds(new); } default: /* No functionality available - continue with default */ return -ENOSYS; } } /** * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted * @mm: The VM space in which the new mapping is to be made * @pages: The size of the mapping * * Determine whether the allocation of a new virtual mapping by the current * task is permitted. * * Return: 1 if permission is granted, 0 if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { int cap_sys_admin = 0; if (cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) == 0) cap_sys_admin = 1; return cap_sys_admin; } /** * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. * * Return: 0 if this mapping should be allowed or -EPERM if not. */ int cap_mmap_addr(unsigned long addr) { int ret = 0; if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; } return ret; } int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { return 0; } #ifdef CONFIG_SECURITY static struct security_hook_list capability_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme), LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), LSM_HOOK_INIT(task_setioprio, cap_task_setioprio), LSM_HOOK_INIT(task_setnice, cap_task_setnice), LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), "capability"); return 0; } DEFINE_LSM(capability) = { .name = "capability", .order = LSM_ORDER_FIRST, .init = capability_init, }; #endif /* CONFIG_SECURITY */ |
| 24 21 3 20 13 13 12 2 18 18 6 2 2 8 8 132 131 8 8 4 2 6 6 8 8 2 6 7 1 1 8 7 1 21 21 1 7 13 4 5 9 3 6 6 6 4 2 67 33 1 32 32 17 17 17 17 13 17 31 31 41 41 1 4 1 2 34 32 1 34 32 32 32 29 6 86 41 5 4 47 31 32 169 169 1 1 162 149 10 1 151 1 4 156 7 100 51 4 39 119 106 31 22 2 128 41 87 110 9 119 39 34 49 78 41 1 117 3 107 5 107 103 41 3 3 66 127 126 3 5 8 1 2 12 7 1 1 2 1 28 2 1 1 24 14 11 2 1 7 10 7 3 10 72 70 2 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * RAW sockets for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Adapted from linux/net/ipv4/raw.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance) * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/slab.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #include <linux/mroute6.h> #include <net/raw.h> #include <net/rawv6.h> #include <net/xfrm.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> #define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ struct raw_hashinfo raw_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), }; EXPORT_SYMBOL_GPL(raw_v6_hashinfo); struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif, int sdif) { bool is_multicast = ipv6_addr_is_multicast(loc_addr); sk_for_each_from(sk) if (inet_sk(sk)->inet_num == num) { if (!net_eq(sock_net(sk), net)) continue; if (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; if (!raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) continue; if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) goto found; if (is_multicast && inet6_mc_check(sk, loc_addr, rmt_addr)) goto found; continue; } goto found; } sk = NULL; found: return sk; } EXPORT_SYMBOL_GPL(__raw_v6_lookup); /* * 0 - deliver * 1 - block */ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { struct icmp6hdr _hdr; const struct icmp6hdr *hdr; /* We require only the four bytes of the ICMPv6 header, not any * additional bytes of message body in "struct icmp6hdr". */ hdr = skb_header_pointer(skb, skb_transport_offset(skb), ICMPV6_HDRLEN, &_hdr); if (hdr) { const __u32 *data = &raw6_sk(sk)->filter.data[0]; unsigned int type = hdr->icmp6_type; return (data[type >> 5] & (1U << (type & 31))) != 0; } return 1; } #if IS_ENABLED(CONFIG_IPV6_MIP6) typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); static mh_filter_t __rcu *mh_filter __read_mostly; int rawv6_mh_filter_register(mh_filter_t filter) { rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); int rawv6_mh_filter_unregister(mh_filter_t filter) { RCU_INIT_POINTER(mh_filter, NULL); synchronize_rcu(); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_unregister); #endif /* * demultiplex raw sockets. * (should consider queueing the skb in the sock receive_queue * without calling rawv6.c) * * Caller owns SKB so we must make clones. */ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { const struct in6_addr *saddr; const struct in6_addr *daddr; struct sock *sk; bool delivered = false; __u8 hash; struct net *net; saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (!sk) goto out; net = dev_net(skb->dev); sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb)); while (sk) { int filtered; delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: filtered = icmpv6_filter(sk, skb); break; #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: { /* XXX: To validate MH only once for each packet, * this is placed here. It should be after checking * xfrm policy, however it doesn't. The checking xfrm * policy is placed in rawv6_rcv() because it is * required for each socket. */ mh_filter_t *filter; filter = rcu_dereference(mh_filter); filtered = filter ? (*filter)(sk, skb) : 0; break; } #endif default: filtered = 0; break; } if (filtered < 0) break; if (filtered == 0) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ if (clone) { nf_reset_ct(clone); rawv6_rcv(sk, clone); } } sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb)); } out: read_unlock(&raw_v6_hashinfo.lock); return delivered; } bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { struct sock *raw_sk; raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]); if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) raw_sk = NULL; return raw_sk != NULL; } /* This cleans up af_inet6 a bit. -DaveM */ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; __be32 v4addr = 0; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (addr->sin6_family != AF_INET6) return -EINVAL; addr_type = ipv6_addr_type(&addr->sin6_addr); /* Raw sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) return -EADDRNOTAVAIL; lock_sock(sk); err = -EINVAL; if (sk->sk_state != TCP_CLOSE) goto out; rcu_read_lock(); /* Check if the address belongs to the host. */ if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { /* Override any existing binding, if another * one is supplied by user. */ sk->sk_bound_dev_if = addr->sin6_scope_id; } /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) goto out_unlock; } if (sk->sk_bound_dev_if) { err = -ENODEV; dev = dev_get_by_index_rcu(sock_net(sk), sk->sk_bound_dev_if); if (!dev) goto out_unlock; } /* ipv4 addr of the socket is invalid. Only the * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST) && !ipv6_can_nonlocal_bind(sock_net(sk), inet)) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { goto out_unlock; } } } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; err = 0; out_unlock: rcu_read_unlock(); out: release_sock(sk); return err; } static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int err; int harderr; /* Report error on raw socket, if: 1. User requested recverr. 2. Socket is connected (otherwise the error indication is useless without recverr and error is hard. */ if (!np->recverr && sk->sk_state != TCP_ESTABLISHED) return; harderr = icmpv6_err_convert(type, code, &err); if (type == ICMPV6_PKT_TOOBIG) { ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); return; } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) payload += offset; ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload); } if (np->recverr || harderr) { sk->sk_err = err; sk_error_report(sk); } } void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct sock *sk; int hash; const struct in6_addr *saddr, *daddr; struct net *net; hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (sk) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; saddr = &ip6h->saddr; daddr = &ip6h->daddr; net = dev_net(skb->dev); while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, inet6_iif(skb), inet6_iif(skb)))) { rawv6_err(sk, skb, NULL, type, code, inner_offset, info); sk = sk_next(sk); } } read_unlock(&raw_v6_hashinfo.lock); } static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } return 0; } /* * This is next to useless... * if we demultiplex in network layer we don't need the extra call * just to queue the skb... * maybe we could have the network decide upon a hint if it * should call raw_rcv for demultiplexing */ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(sk); struct raw6_sock *rp = raw6_sk(sk); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; if (skb->ip_summed == CHECKSUM_COMPLETE) { skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (!skb_csum_unnecessary(skb)) skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, 0)); if (inet->hdrincl) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } } rawv6_rcv_skb(sk, skb); return 0; } /* * This should be easy, if there is something there * we return it, otherwise we block. */ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct sk_buff *skb; size_t copied; int err; if (flags & MSG_OOB) return -EOPNOTSUPP; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } if (skb_csum_unnecessary(skb)) { err = skb_copy_datagram_msg(skb, 0, msg, copied); } else if (msg->msg_flags&MSG_TRUNC) { if (__skb_checksum_complete(skb)) goto csum_copy_err; err = skb_copy_datagram_msg(skb, 0, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, 0, msg); if (err == -EINVAL) goto csum_copy_err; } if (err) goto out_free; /* Copy the address. */ if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); *addr_len = sizeof(*sin6); } sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) err = skb->len; out_free: skb_free_datagram(sk, skb); out: return err; csum_copy_err: skb_kill_datagram(sk, skb, flags); /* Error for blocking case is chosen to masquerade as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; goto out; } static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; int len; int total_len; __wsum tmp_csum; __sum16 csum; if (!rp->checksum) goto send; skb = skb_peek(&sk->sk_write_queue); if (!skb) goto out; offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; opt = inet6_sk(sk)->cork.opt; total_len -= opt ? opt->opt_flen : 0; if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); goto out; } /* should be check HW csum miyazawa */ if (skb_queue_len(&sk->sk_write_queue) == 1) { /* * Only one fragment on the socket. */ tmp_csum = skb->csum; } else { struct sk_buff *csum_skb = NULL; tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); if (csum_skb) continue; len = skb->len - skb_transport_offset(skb); if (offset >= len) { offset -= len; continue; } csum_skb = skb; } skb = csum_skb; } offset += skb_transport_offset(skb); err = skb_copy_bits(skb, offset, &csum, 2); if (err < 0) { ip6_flush_pending_frames(sk); goto out; } /* in case cksum was not initialized */ if (unlikely(csum)) tmp_csum = csum_sub(tmp_csum, csum_unfold(csum)); csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, total_len, fl6->flowi6_proto, tmp_csum); if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) csum = CSUM_MANGLED_0; BUG_ON(skb_store_bits(skb, offset, &csum, 2)); send: err = ip6_push_pending_frames(sk); out: return err; } static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, struct flowi6 *fl6, struct dst_entry **dstp, unsigned int flags, const struct sockcm_cookie *sockc) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *iph; struct sk_buff *skb; int err; struct rt6_info *rt = (struct rt6_info *)*dstp; int hlen = LL_RESERVED_SPACE(rt->dst.dev); int tlen = rt->dst.dev->needed_tailroom; if (length > rt->dst.dev->mtu) { ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } if (length < sizeof(struct ipv6hdr)) return -EINVAL; if (flags&MSG_PROBE) goto out; skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (!skb) goto error; skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_NONE; skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); skb->transport_header = skb->network_header; err = memcpy_from_msg(iph, msg, length); if (err) { err = -EFAULT; kfree_skb(skb); goto error; } skb_dst_set(skb, &rt->dst); *dstp = NULL; /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; /* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev * in the error path. Since skb has been freed, the dst could * have been queued for deletion. */ rcu_read_lock(); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) { IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); goto error_check; } rcu_read_unlock(); out: return 0; error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); error_check: if (err == -ENOBUFS && !np->recverr) err = 0; return err; } struct raw6_frag_vec { struct msghdr *msg; int hlen; char c[4]; }; static int rawv6_probe_proto_opt(struct raw6_frag_vec *rfv, struct flowi6 *fl6) { int err = 0; switch (fl6->flowi6_proto) { case IPPROTO_ICMPV6: rfv->hlen = 2; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) { fl6->fl6_icmp_type = rfv->c[0]; fl6->fl6_icmp_code = rfv->c[1]; } break; case IPPROTO_MH: rfv->hlen = 4; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) fl6->fl6_mh_type = rfv->c[2]; } return err; } static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct raw6_frag_vec *rfv = from; if (offset < rfv->hlen) { int copy = min(rfv->hlen - offset, len); if (skb->ip_summed == CHECKSUM_PARTIAL) memcpy(to, rfv->c + offset, copy); else skb->csum = csum_block_add( skb->csum, csum_partial_copy_nocheck(rfv->c + offset, to, copy), odd); odd = 0; offset += copy; to += copy; len -= copy; if (!len) return 0; } offset -= rfv->hlen; return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct raw6_sock *rp = raw6_sk(sk); struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; struct raw6_frag_vec rfv; struct flowi6 fl6; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int hdrincl; u16 proto; int err; /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ if (len > INT_MAX) return -EMSGSIZE; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* hdrincl should be READ_ONCE(inet->hdrincl) * but READ_ONCE() doesn't work with bit fields. * Doing this indirectly yields the same result. */ hdrincl = inet->hdrincl; hdrincl = READ_ONCE(hdrincl); /* * Get and verify the address. */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = sk->sk_mark; fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (sin6->sin6_family && sin6->sin6_family != AF_INET6) return -EAFNOSUPPORT; /* port is the proto value [0..255] carried in nexthdr */ proto = ntohs(sin6->sin6_port); if (!proto) proto = inet->inet_num; else if (proto != inet->inet_num && inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) return -EINVAL; daddr = &sin6->sin6_addr; if (np->sndflow) { fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } } /* * Otherwise it will be difficult to maintain * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; proto = inet->inet_num; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } if (fl6.flowi6_oif == 0) fl6.flowi6_oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); ipc6.opt = opt; err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } if (!opt) { opt = txopt_get(np); opt_to_free = opt; } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); fl6.flowi6_proto = proto; fl6.flowi6_mark = ipc6.sockc.mark; if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; err = rawv6_probe_proto_opt(&rfv, &fl6); if (err) goto out; } if (!ipv6_addr_any(daddr)) fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; final_p = fl6_update_dst(&fl6, opt, &final); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); if (hdrincl) fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; if (ipc6.tclass < 0) ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (ipc6.dontfrag < 0) ipc6.dontfrag = np->dontfrag; if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: if (hdrincl) err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags, &ipc6.sockc); else { ipc6.opt = opt; lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, len, 0, &ipc6, &fl6, (struct rt6_info *)dst, msg->msg_flags); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) err = rawv6_push_pending_frames(sk, &fl6, rp); release_sock(sk); } done: dst_release(dst); out: fl6_sock_release(flowlabel); txopt_put(opt_to_free); return err < 0 ? err : len; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(dst, &fl6.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto done; } static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, sockptr_t optval, int optlen) { switch (optname) { case ICMPV6_FILTER: if (optlen > sizeof(struct icmp6_filter)) optlen = sizeof(struct icmp6_filter); if (copy_from_sockptr(&raw6_sk(sk)->filter, optval, optlen)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int len; switch (optname) { case ICMPV6_FILTER: if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; if (len > sizeof(struct icmp6_filter)) len = sizeof(struct icmp6_filter); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &raw6_sk(sk)->filter, len)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { case IPV6_HDRINCL: if (sk->sk_type != SOCK_RAW) return -EINVAL; inet_sk(sk)->hdrincl = !!val; return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { /* * RFC3542 tells that IPV6_CHECKSUM socket * option in the IPPROTO_IPV6 level is not * allowed on ICMPv6 sockets. * If you want to set it, use IPPROTO_RAW * level IPV6_CHECKSUM socket option * (Linux extension). */ return -EINVAL; } /* You may get strange result with a positive odd offset; RFC2292bis agrees with me. */ if (val > 0 && (val&1)) return -EINVAL; if (val < 0) { rp->checksum = 0; } else { rp->checksum = 1; rp->offset = val; } return 0; default: return -ENOPROTOOPT; } } static int rawv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; fallthrough; default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct raw6_sock *rp = raw6_sk(sk); int val, len; if (get_user(len, optlen)) return -EFAULT; switch (optname) { case IPV6_HDRINCL: val = inet_sk(sk)->hdrincl; break; case IPV6_CHECKSUM: /* * We allow getsockopt() for IPPROTO_IPV6-level * IPV6_CHECKSUM socket option on ICMPv6 sockets * since RFC3542 is silent about it. */ if (rp->checksum == 0) val = -1; else val = rp->offset; break; default: return -ENOPROTOOPT; } len = min_t(unsigned int, sizeof(int), len); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; fallthrough; default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_ioctl(sk, cmd, (void __user *)arg); #else return -ENOIOCTLCMD; #endif } } #ifdef CONFIG_COMPAT static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: case SIOCINQ: return -ENOIOCTLCMD; default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg)); #else return -ENOIOCTLCMD; #endif } } #endif static void rawv6_close(struct sock *sk, long timeout) { if (inet_sk(sk)->inet_num == IPPROTO_RAW) ip6_ra_control(sk, -1); ip6mr_sk_done(sk); sk_common_release(sk); } static void raw6_destroy(struct sock *sk) { lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); } static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); switch (inet_sk(sk)->inet_num) { case IPPROTO_ICMPV6: rp->checksum = 1; rp->offset = 2; break; case IPPROTO_MH: rp->checksum = 1; rp->offset = 4; break; default: break; } return 0; } struct proto rawv6_prot = { .name = "RAWv6", .owner = THIS_MODULE, .close = rawv6_close, .destroy = raw6_destroy, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .ioctl = rawv6_ioctl, .init = rawv6_init_sk, .setsockopt = rawv6_setsockopt, .getsockopt = rawv6_getsockopt, .sendmsg = rawv6_sendmsg, .recvmsg = rawv6_recvmsg, .bind = rawv6_bind, .backlog_rcv = rawv6_rcv_skb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw6_sock), .useroffset = offsetof(struct raw6_sock, filter), .usersize = sizeof_field(struct raw6_sock, filter), .h.raw_hash = &raw_v6_hashinfo, #ifdef CONFIG_COMPAT .compat_ioctl = compat_rawv6_ioctl, #endif .diag_destroy = raw_abort, }; #ifdef CONFIG_PROC_FS static int raw6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { struct sock *sp = v; __u16 srcp = inet_sk(sp)->inet_num; ip6_dgram_sock_seq_show(seq, v, srcp, 0, raw_seq_private(seq)->bucket); } return 0; } static const struct seq_operations raw6_seq_ops = { .start = raw_seq_start, .next = raw_seq_next, .stop = raw_seq_stop, .show = raw6_seq_show, }; static int __net_init raw6_init_net(struct net *net) { if (!proc_create_net_data("raw6", 0444, net->proc_net, &raw6_seq_ops, sizeof(struct raw_iter_state), &raw_v6_hashinfo)) return -ENOMEM; return 0; } static void __net_exit raw6_exit_net(struct net *net) { remove_proc_entry("raw6", net->proc_net); } static struct pernet_operations raw6_net_ops = { .init = raw6_init_net, .exit = raw6_exit_net, }; int __init raw6_proc_init(void) { return register_pernet_subsys(&raw6_net_ops); } void raw6_proc_exit(void) { unregister_pernet_subsys(&raw6_net_ops); } #endif /* CONFIG_PROC_FS */ /* Same as inet6_dgram_ops, sans udp_poll. */ const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_dgram_connect, /* ok */ .socketpair = sock_no_socketpair, /* a do nothing */ .accept = sock_no_accept, /* a do nothing */ .getname = inet6_getname, .poll = datagram_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ .gettstamp = sock_gettstamp, .listen = sock_no_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet_sendmsg, /* ok */ .recvmsg = sock_common_recvmsg, /* ok */ .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif }; static struct inet_protosw rawv6_protosw = { .type = SOCK_RAW, .protocol = IPPROTO_IP, /* wild card */ .prot = &rawv6_prot, .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; int __init rawv6_init(void) { return inet6_register_protosw(&rawv6_protosw); } void rawv6_exit(void) { inet6_unregister_protosw(&rawv6_protosw); } |
| 13 9 5 4 13 13 5 5 5 9 9 9 12 1 9 2 1 6 5 5 5 5 5 4 4 4 3 1 2 6 2 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 | // SPDX-License-Identifier: GPL-2.0-or-later /* L2TPv3 IP encapsulation support * * Copyright (c) 2008,2009,2010 Katalix Systems Ltd */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/ioctls.h> #include <linux/icmp.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/random.h> #include <linux/socket.h> #include <linux/l2tp.h> #include <linux/in.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> #include "l2tp_core.h" struct l2tp_ip_sock { /* inet_sock has to be the first member of l2tp_ip_sock */ struct inet_sock inet; u32 conn_id; u32 peer_conn_id; }; static DEFINE_RWLOCK(l2tp_ip_lock); static struct hlist_head l2tp_ip_table; static struct hlist_head l2tp_ip_bind_table; static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) { return (struct l2tp_ip_sock *)sk; } static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr, __be32 raddr, int dif, u32 tunnel_id) { struct sock *sk; sk_for_each_bound(sk, &l2tp_ip_bind_table) { const struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk); const struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_bound_dev_if && dif && sk->sk_bound_dev_if != dif) continue; if (inet->inet_rcv_saddr && laddr && inet->inet_rcv_saddr != laddr) continue; if (inet->inet_daddr && raddr && inet->inet_daddr != raddr) continue; if (l2tp->conn_id != tunnel_id) continue; goto found; } sk = NULL; found: return sk; } /* When processing receive frames, there are two cases to * consider. Data frames consist of a non-zero session-id and an * optional cookie. Control frames consist of a regular L2TP header * preceded by 32-bits of zeros. * * L2TPv3 Session Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Cookie (optional, maximum 64 bits)... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 Control Message Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | (32 bits of zeros) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |T|L|x|x|S|x|x|x|x|x|x|x| Ver | Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Control Connection ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ns | Nr | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * All control frames are passed to userspace. */ static int l2tp_ip_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct sock *sk; u32 session_id; u32 tunnel_id; unsigned char *ptr, *optr; struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct iphdr *iph; if (!pskb_may_pull(skb, 4)) goto discard; /* Point to L2TP header */ optr = skb->data; ptr = skb->data; session_id = ntohl(*((__be32 *)ptr)); ptr += 4; /* RFC3931: L2TP/IP packets have the first 4 bytes containing * the session_id. If it is 0, the packet is a L2TP control * frame and the session_id value can be discarded. */ if (session_id == 0) { __skb_pull(skb, 4); goto pass_up; } /* Ok, this is a data packet. Lookup the session. */ session = l2tp_session_get(net, session_id); if (!session) goto discard; tunnel = session->tunnel; if (!tunnel) goto discard_sess; if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); return 0; pass_up: /* Get the tunnel_id from the L2TP header */ if (!pskb_may_pull(skb, 12)) goto discard; if ((skb->data[0] & 0xc0) != 0xc0) goto discard; tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = (struct iphdr *)skb_network_header(skb); read_lock_bh(&l2tp_ip_lock); sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb), tunnel_id); if (!sk) { read_unlock_bh(&l2tp_ip_lock); goto discard; } sock_hold(sk); read_unlock_bh(&l2tp_ip_lock); if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; nf_reset_ct(skb); return sk_receive_skb(sk, skb, 1); discard_sess: l2tp_session_dec_refcount(session); goto discard; discard_put: sock_put(sk); discard: kfree_skb(skb); return 0; } static int l2tp_ip_hash(struct sock *sk) { if (sk_unhashed(sk)) { write_lock_bh(&l2tp_ip_lock); sk_add_node(sk, &l2tp_ip_table); write_unlock_bh(&l2tp_ip_lock); } return 0; } static void l2tp_ip_unhash(struct sock *sk) { if (sk_unhashed(sk)) return; write_lock_bh(&l2tp_ip_lock); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); } static int l2tp_ip_open(struct sock *sk) { /* Prevent autobind. We don't have ports. */ inet_sk(sk)->inet_num = IPPROTO_L2TP; l2tp_ip_hash(sk); return 0; } static void l2tp_ip_close(struct sock *sk, long timeout) { write_lock_bh(&l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); sk_common_release(sk); } static void l2tp_ip_destroy_sock(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); if (tunnel) l2tp_tunnel_delete(tunnel); } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *)uaddr; struct net *net = sock_net(sk); int ret; int chk_addr_ret; if (addr_len < sizeof(struct sockaddr_l2tpip)) return -EINVAL; if (addr->l2tp_family != AF_INET) return -EINVAL; lock_sock(sk); ret = -EINVAL; if (!sock_flag(sk, SOCK_ZAPPED)) goto out; if (sk->sk_state != TCP_CLOSE) goto out; chk_addr_ret = inet_addr_type(net, addr->l2tp_addr.s_addr); ret = -EADDRNOTAVAIL; if (addr->l2tp_addr.s_addr && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) goto out; if (addr->l2tp_addr.s_addr) { inet->inet_rcv_saddr = addr->l2tp_addr.s_addr; inet->inet_saddr = addr->l2tp_addr.s_addr; } if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ write_lock_bh(&l2tp_ip_lock); if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, 0, sk->sk_bound_dev_if, addr->l2tp_conn_id)) { write_unlock_bh(&l2tp_ip_lock); ret = -EADDRINUSE; goto out; } sk_dst_reset(sk); l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; sk_add_bind_node(sk, &l2tp_ip_bind_table); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); ret = 0; sock_reset_flag(sk, SOCK_ZAPPED); out: release_sock(sk); return ret; } static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; int rc; if (addr_len < sizeof(*lsa)) return -EINVAL; if (ipv4_is_multicast(lsa->l2tp_addr.s_addr)) return -EINVAL; lock_sock(sk); /* Must bind first - autobinding does not work */ if (sock_flag(sk, SOCK_ZAPPED)) { rc = -EINVAL; goto out_sk; } rc = __ip4_datagram_connect(sk, uaddr, addr_len); if (rc < 0) goto out_sk; l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; write_lock_bh(&l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_add_bind_node(sk, &l2tp_ip_bind_table); write_unlock_bh(&l2tp_ip_lock); out_sk: release_sock(sk); return rc; } static int l2tp_ip_disconnect(struct sock *sk, int flags) { if (sock_flag(sk, SOCK_ZAPPED)) return 0; return __udp_disconnect(sk, flags); } static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct l2tp_ip_sock *lsk = l2tp_ip_sk(sk); struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; memset(lsa, 0, sizeof(*lsa)); lsa->l2tp_family = AF_INET; if (peer) { if (!inet->inet_dport) return -ENOTCONN; lsa->l2tp_conn_id = lsk->peer_conn_id; lsa->l2tp_addr.s_addr = inet->inet_daddr; } else { __be32 addr = inet->inet_rcv_saddr; if (!addr) addr = inet->inet_saddr; lsa->l2tp_conn_id = lsk->conn_id; lsa->l2tp_addr.s_addr = addr; } return sizeof(*lsa); } static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) { int rc; /* Charge it to the socket, dropping if the queue is full. */ rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) goto drop; return 0; drop: IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS); kfree_skb(skb); return 0; } /* Userspace will call sendmsg() on the tunnel socket to send L2TP * control frames. */ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct sk_buff *skb; int rc; struct inet_sock *inet = inet_sk(sk); struct rtable *rt = NULL; struct flowi4 *fl4; int connected = 0; __be32 daddr; lock_sock(sk); rc = -ENOTCONN; if (sock_flag(sk, SOCK_DEAD)) goto out; /* Get and verify the address. */ if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_l2tpip *, lip, msg->msg_name); rc = -EINVAL; if (msg->msg_namelen < sizeof(*lip)) goto out; if (lip->l2tp_family != AF_INET) { rc = -EAFNOSUPPORT; if (lip->l2tp_family != AF_UNSPEC) goto out; } daddr = lip->l2tp_addr.s_addr; } else { rc = -EDESTADDRREQ; if (sk->sk_state != TCP_ESTABLISHED) goto out; daddr = inet->inet_daddr; connected = 1; } /* Allocate a socket buffer */ rc = -ENOMEM; skb = sock_wmalloc(sk, 2 + NET_SKB_PAD + sizeof(struct iphdr) + 4 + len, 0, GFP_KERNEL); if (!skb) goto error; /* Reserve space for headers, putting IP header on 4-byte boundary. */ skb_reserve(skb, 2 + NET_SKB_PAD); skb_reset_network_header(skb); skb_reserve(skb, sizeof(struct iphdr)); skb_reset_transport_header(skb); /* Insert 0 session_id */ *((__be32 *)skb_put(skb, 4)) = 0; /* Copy user data into skb */ rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc < 0) { kfree_skb(skb); goto error; } fl4 = &inet->cork.fl.u.ip4; if (connected) rt = (struct rtable *)__sk_dst_check(sk, 0); rcu_read_lock(); if (!rt) { const struct ip_options_rcu *inet_opt; inet_opt = rcu_dereference(inet->inet_opt); /* Use correct destination address if we have options. */ if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; if (connected) { sk_setup_caps(sk, &rt->dst); } else { skb_dst_set(skb, &rt->dst); goto xmit; } } /* We don't need to clone dst here, it is guaranteed to not disappear. * __dev_xmit_skb() might force a refcount if needed. */ skb_dst_set_noref(skb, &rt->dst); xmit: /* Queue the packet to IP for output */ rc = ip_queue_xmit(sk, skb, &inet->cork.fl); rcu_read_unlock(); error: if (rc >= 0) rc = len; out: release_sock(sk); return rc; no_route: rcu_read_unlock(); IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); rc = -EHOSTUNREACH; goto out; } static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); size_t copied = 0; int err = -EOPNOTSUPP; DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; if (flags & MSG_OOB) goto out; skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto done; sock_recv_timestamp(msg, sk, skb); /* Copy the address. */ if (sin) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); if (flags & MSG_TRUNC) copied = skb->len; done: skb_free_datagram(sk, skb); out: return err ? err : copied; } int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct sk_buff *skb; int amount; switch (cmd) { case SIOCOUTQ: amount = sk_wmem_alloc_get(sk); break; case SIOCINQ: spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; spin_unlock_bh(&sk->sk_receive_queue.lock); break; default: return -ENOIOCTLCMD; } return put_user(amount, (int __user *)arg); } EXPORT_SYMBOL_GPL(l2tp_ioctl); static struct proto l2tp_ip_prot = { .name = "L2TP/IP", .owner = THIS_MODULE, .init = l2tp_ip_open, .close = l2tp_ip_close, .bind = l2tp_ip_bind, .connect = l2tp_ip_connect, .disconnect = l2tp_ip_disconnect, .ioctl = l2tp_ioctl, .destroy = l2tp_ip_destroy_sock, .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .sendmsg = l2tp_ip_sendmsg, .recvmsg = l2tp_ip_recvmsg, .backlog_rcv = l2tp_ip_backlog_recv, .hash = l2tp_ip_hash, .unhash = l2tp_ip_unhash, .obj_size = sizeof(struct l2tp_ip_sock), }; static const struct proto_ops l2tp_ip_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = l2tp_ip_getname, .poll = datagram_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; static struct inet_protosw l2tp_ip_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_L2TP, .prot = &l2tp_ip_prot, .ops = &l2tp_ip_ops, }; static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, }; static int __init l2tp_ip_init(void) { int err; pr_info("L2TP IP encapsulation support (L2TPv3)\n"); err = proto_register(&l2tp_ip_prot, 1); if (err != 0) goto out; err = inet_add_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); if (err) goto out1; inet_register_protosw(&l2tp_ip_protosw); return 0; out1: proto_unregister(&l2tp_ip_prot); out: return err; } static void __exit l2tp_ip_exit(void) { inet_unregister_protosw(&l2tp_ip_protosw); inet_del_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip_prot); } module_init(l2tp_ip_init); module_exit(l2tp_ip_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); /* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like * enums */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP); MODULE_ALIAS_NET_PF_PROTO(PF_INET, IPPROTO_L2TP); |
| 89 102 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mmap_lock #if !defined(_TRACE_MMAP_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MMAP_LOCK_H #include <linux/tracepoint.h> #include <linux/types.h> struct mm_struct; extern int trace_mmap_lock_reg(void); extern void trace_mmap_lock_unreg(void); TRACE_EVENT_FN(mmap_lock_start_locking, TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write), TP_ARGS(mm, memcg_path, write), TP_STRUCT__entry( __field(struct mm_struct *, mm) __string(memcg_path, memcg_path) __field(bool, write) ), TP_fast_assign( __entry->mm = mm; __assign_str(memcg_path, memcg_path); __entry->write = write; ), TP_printk( "mm=%p memcg_path=%s write=%s\n", __entry->mm, __get_str(memcg_path), __entry->write ? "true" : "false" ), trace_mmap_lock_reg, trace_mmap_lock_unreg ); TRACE_EVENT_FN(mmap_lock_acquire_returned, TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write, bool success), TP_ARGS(mm, memcg_path, write, success), TP_STRUCT__entry( __field(struct mm_struct *, mm) __string(memcg_path, memcg_path) __field(bool, write) __field(bool, success) ), TP_fast_assign( __entry->mm = mm; __assign_str(memcg_path, memcg_path); __entry->write = write; __entry->success = success; ), TP_printk( "mm=%p memcg_path=%s write=%s success=%s\n", __entry->mm, __get_str(memcg_path), __entry->write ? "true" : "false", __entry->success ? "true" : "false" ), trace_mmap_lock_reg, trace_mmap_lock_unreg ); TRACE_EVENT_FN(mmap_lock_released, TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write), TP_ARGS(mm, memcg_path, write), TP_STRUCT__entry( __field(struct mm_struct *, mm) __string(memcg_path, memcg_path) __field(bool, write) ), TP_fast_assign( __entry->mm = mm; __assign_str(memcg_path, memcg_path); __entry->write = write; ), TP_printk( "mm=%p memcg_path=%s write=%s\n", __entry->mm, __get_str(memcg_path), __entry->write ? "true" : "false" ), trace_mmap_lock_reg, trace_mmap_lock_unreg ); #endif /* _TRACE_MMAP_LOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1946 1953 540 96 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMSTAT_H #define _LINUX_VMSTAT_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> #include <linux/static_key.h> #include <linux/mmdebug.h> extern int sysctl_stat_interval; #ifdef CONFIG_NUMA #define ENABLE_NUMA_STAT 1 #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { unsigned nr_dirty; unsigned nr_unqueued_dirty; unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; unsigned nr_pageout; unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; }; enum writeback_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, NR_VM_WRITEBACK_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. * * Counters should only be incremented and no critical kernel component * should rely on the counter values. * * Counters are handled completely inline. On many platforms the code * generated will simply be the increment of a global address. */ struct vm_event_state { unsigned long event[NR_VM_EVENT_ITEMS]; }; DECLARE_PER_CPU(struct vm_event_state, vm_event_states); /* * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the * local_irq_disable overhead. */ static inline void __count_vm_event(enum vm_event_item item) { raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); extern void vm_events_fold_cpu(int cpu); #else /* Disable counters */ static inline void count_vm_event(enum vm_event_item item) { } static inline void count_vm_events(enum vm_event_item item, long delta) { } static inline void __count_vm_event(enum vm_event_item item) { } static inline void __count_vm_events(enum vm_event_item item, long delta) { } static inline void all_vm_events(unsigned long *ret) { } static inline void vm_events_fold_cpu(int cpu) { } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_NUMA_BALANCING #define count_vm_numa_event(x) count_vm_event(x) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_DEBUG_TLBFLUSH #define count_vm_tlb_event(x) count_vm_event(x) #define count_vm_tlb_events(x, y) count_vm_events(x, y) #else #define count_vm_tlb_event(x) do {} while (0) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif #ifdef CONFIG_DEBUG_VM_VMACACHE #define count_vm_vmacache_event(x) count_vm_event(x) #else #define count_vm_vmacache_event(x) do {} while (0) #endif #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; extern atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #ifdef CONFIG_NUMA static inline void zone_numa_event_add(long x, struct zone *zone, enum numa_stat_item item) { atomic_long_add(x, &zone->vm_numa_event[item]); atomic_long_add(x, &vm_numa_event[item]); } static inline unsigned long zone_numa_event_state(struct zone *zone, enum numa_stat_item item) { return atomic_long_read(&zone->vm_numa_event[item]); } static inline unsigned long global_numa_event_state(enum numa_stat_item item) { return atomic_long_read(&vm_numa_event[item]); } #endif /* CONFIG_NUMA */ static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); atomic_long_add(x, &vm_zone_stat[item]); } static inline void node_page_state_add(long x, struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_add(x, &pgdat->vm_stat[item]); atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state_pages(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); return global_node_page_state_pages(item); } static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * More accurate version that also considers the currently pending * deltas. For that we need to loop over all cpus to find the current * deltas. There is no synchronization so the result cannot be * exactly accurate either. */ static inline unsigned long zone_page_state_snapshot(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; #endif return x; } #ifdef CONFIG_NUMA /* See __count_vm_event comment on why raw_cpu_inc is used. */ static inline void __count_numa_event(struct zone *zone, enum numa_stat_item item) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_inc(pzstats->vm_numa_event[item]); } static inline void __count_numa_events(struct zone *zone, enum numa_stat_item item, long delta) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_add(pzstats->vm_numa_event[item], delta); } extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); extern void fold_vm_numa_events(void); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) static inline void fold_vm_numa_events(void) { } #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); void __inc_node_page_state(struct page *, enum node_stat_item); void __dec_node_page_state(struct page *, enum node_stat_item); void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)); #else /* CONFIG_SMP */ /* * We do not maintain differentials in a single processor configuration. * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { /* * Only cgroups use subpage accounting right now; at * the global level, these items still change in * multiples of whole pages. Store them as pages * internally to keep the per-cpu counters compact. */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } node_page_state_add(delta, pgdat, item); } static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); atomic_long_inc(&vm_zone_stat[item]); } static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_inc(&pgdat->vm_stat[item]); atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); atomic_long_dec(&vm_zone_stat[item]); } static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_dec(&pgdat->vm_stat[item]); atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } static inline void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } static inline void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. */ #define inc_zone_page_state __inc_zone_page_state #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state #define inc_node_page_state __inc_node_page_state #define dec_node_page_state __dec_node_page_state #define mod_node_page_state __mod_node_page_state #define inc_zone_state __inc_zone_state #define inc_node_state __inc_node_state #define dec_zone_state __dec_zone_state #define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, int migratetype) { __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); if (is_migrate_cma(migratetype)) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); } extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) { return vmstat_text[item]; } #ifdef CONFIG_NUMA static inline const char *numa_stat_name(enum numa_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + item]; } #endif /* CONFIG_NUMA */ static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + item]; } static inline const char *lru_list_name(enum lru_list lru) { return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_" } static inline const char *writeback_stat_name(enum writeback_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + item]; } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_WRITEBACK_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ #ifdef CONFIG_MEMCG void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val); static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_page_state(page, idx, val); local_irq_restore(flags); } #else static inline void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { mod_node_page_state(page_pgdat(page), idx, val); } #endif /* CONFIG_MEMCG */ static inline void inc_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { mod_lruvec_state(lruvec, idx, 1); } static inline void __inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { __mod_lruvec_page_state(page, idx, 1); } static inline void __dec_lruvec_page_state(struct page *page, enum node_stat_item idx) { __mod_lruvec_page_state(page, idx, -1); } static inline void inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { mod_lruvec_page_state(page, idx, 1); } static inline void dec_lruvec_page_state(struct page *page, enum node_stat_item idx) { mod_lruvec_page_state(page, idx, -1); } #endif /* _LINUX_VMSTAT_H */ |
| 13 93 259 3 3 2 4 4 4 15 15 6 5 4 14 15 15 15 4 4 17 18 12 6 6 4 80 2 9 9 9 9 20 20 1 7 8 2 4 9 2 2 1 2 2 3 4 17 17 18 13 4 11 45 1 8 23 65 16 23 23 32 7 18 18 18 206 208 208 1 58 1 122 30 8 116 6 2 61 11 116 21 1 6 107 1 1 108 8 57 44 2 90 22 86 73 4 32 25 10 1 84 84 83 74 10 21 29 33 84 18 79 62 6 47 21 33 7 7 18 15 2 25 93 96 77 30 9 8 17 47 47 26 21 25 22 133 11 123 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * UDP over IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/ipv4/udp.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data * YOSHIFUJI Hideaki @USAGI: convert /proc/net/udp6 to seq_file. */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/indirect_call_wrapper.h> #include <net/addrconf.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/raw.h> #include <net/seg6.h> #include <net/tcp_states.h> #include <net/ip6_checksum.h> #include <net/ip6_tunnel.h> #include <net/xfrm.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/busy_poll.h> #include <net/sock_reuseport.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <trace/events/skb.h> #include "udp_impl.h" static void udpv6_destruct_sock(struct sock *sk) { udp_destruct_common(sk); inet6_sock_destruct(sk); } int udpv6_init_sock(struct sock *sk) { skb_queue_head_init(&udp_sk(sk)->reader_queue); sk->sk_destruct = udpv6_destruct_sock; return 0; } INDIRECT_CALLABLE_SCOPE u32 udp6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) { static u32 udp6_ehash_secret __read_mostly; static u32 udp_ipv6_hash_secret __read_mostly; u32 lhash, fhash; net_get_random_once(&udp6_ehash_secret, sizeof(udp6_ehash_secret)); net_get_random_once(&udp_ipv6_hash_secret, sizeof(udp_ipv6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, udp6_ehash_secret + net_hash_mix(net)); } int udp_v6_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = ipv6_portaddr_hash(sock_net(sk), &in6addr_any, snum); unsigned int hash2_partial = ipv6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0); /* precompute partial secondary hash */ udp_sk(sk)->udp_portaddr_hash = hash2_partial; return udp_lib_get_port(sk, snum, hash2_nulladdr); } void udp_v6_rehash(struct sock *sk) { u16 new_hash = ipv6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, inet_sk(sk)->inet_num); udp_lib_rehash(sk, new_hash); } static int compute_score(struct sock *sk, struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, int dif, int sdif) { int score; struct inet_sock *inet; bool dev_match; if (!net_eq(sock_net(sk), net) || udp_sk(sk)->udp_port_hash != hnum || sk->sk_family != PF_INET6) return -1; if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; score = 0; inet = inet_sk(sk); if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; score++; } if (!ipv6_addr_any(&sk->sk_v6_daddr)) { if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) return -1; score++; } dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif); if (!dev_match) return -1; if (sk->sk_bound_dev_if) score++; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; } /* called with rcu_read_lock() */ static struct sock *udp6_lib_lookup2(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned int hnum, int dif, int sdif, struct udp_hslot *hslot2, struct sk_buff *skb) { struct sock *sk, *result; int score, badness; bool need_rescore; result = NULL; badness = -1; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { need_rescore = false; rescore: score = compute_score(need_rescore ? result : sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { badness = score; if (need_rescore) continue; if (sk->sk_state == TCP_ESTABLISHED) { result = sk; continue; } result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), saddr, sport, daddr, hnum, udp6_ehashfn); if (!result) { result = sk; continue; } /* Fall back to scoring if group has connections */ if (!reuseport_has_conns(sk)) return result; /* Reuseport logic returned an error, keep original score. */ if (IS_ERR(result)) continue; /* compute_score is too long of a function to be * inlined, and calling it again here yields * measureable overhead for some * workloads. Work around it by jumping * backwards to rescore 'result'. */ need_rescore = true; goto rescore; } } return result; } static inline struct sock *udp6_lookup_run_bpf(struct net *net, struct udp_table *udptable, struct sk_buff *skb, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, u16 hnum) { struct sock *sk, *reuse_sk; bool no_reuseport; if (udptable != &udp_table) return NULL; /* only UDP is supported */ no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport, daddr, hnum, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), saddr, sport, daddr, hnum, udp6_ehashfn); if (reuse_sk) sk = reuse_sk; return sk; } /* rcu_read_lock() must be held */ struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, struct sk_buff *skb) { unsigned short hnum = ntohs(dport); unsigned int hash2, slot2; struct udp_hslot *hslot2; struct sock *result, *sk; hash2 = ipv6_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; /* Lookup connected or non-wildcard sockets */ result = udp6_lib_lookup2(net, saddr, sport, daddr, hnum, dif, sdif, hslot2, skb); if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED) goto done; /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { sk = udp6_lookup_run_bpf(net, udptable, skb, saddr, sport, daddr, hnum); if (sk) { result = sk; goto done; } } /* Got non-wildcard socket or error on first lookup */ if (result) goto done; /* Lookup wildcard sockets */ hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; result = udp6_lib_lookup2(net, saddr, sport, &in6addr_any, hnum, dif, sdif, hslot2, skb); done: if (IS_ERR(result)) return NULL; return result; } EXPORT_SYMBOL_GPL(__udp6_lib_lookup); static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, struct udp_table *udptable) { const struct ipv6hdr *iph = ipv6_hdr(skb); return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), inet6_sdif(skb), udptable, skb); } struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { const struct ipv6hdr *iph = ipv6_hdr(skb); return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), inet6_sdif(skb), &udp_table, NULL); } /* Must be called under rcu_read_lock(). * Does increment socket refcount. */ #if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6) struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif) { struct sock *sk; sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, 0, &udp_table, NULL); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } EXPORT_SYMBOL_GPL(udp6_lib_lookup); #endif /* do not use the scratch area len for jumbogram: their length execeeds the * scratch area space; note that the IP6CB flags is still in the first * cacheline, so checking for jumbograms is cheap */ static int udp6_skb_len(struct sk_buff *skb) { return unlikely(inet6_is_jumbogram(skb)) ? skb->len : udp_skb_len(skb); } /* * This should be easy, if there is something there we * return it, otherwise we block. */ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; unsigned int ulen, copied; int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); struct udp_mib __percpu *mib; bool checksum_valid = false; int is_udp4; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: off = sk_peek_offset(sk, flags); skb = __skb_recv_udp(sk, flags, noblock, &off, &err); if (!skb) return err; ulen = udp6_skb_len(skb); copied = len; if (copied > ulen - off) copied = ulen - off; else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; is_udp4 = (skb->protocol == htons(ETH_P_IP)); mib = __UDPX_MIB(sk, is_udp4); /* * If checksum is needed at all, try to do it while copying the * data. If the data is truncated, or if we only want a partial * coverage checksum (UDP-Lite), do it before the copy. */ if (copied < ulen || peeking || (is_udplite && UDP_SKB_CB(skb)->partial_cov)) { checksum_valid = udp_skb_csum_unnecessary(skb) || !__udp_lib_checksum_complete(skb); if (!checksum_valid) goto csum_copy_err; } if (checksum_valid || udp_skb_csum_unnecessary(skb)) { if (udp_skb_is_linear(skb)) err = copy_linear_skb(skb, copied, off, &msg->msg_iter); else err = skb_copy_datagram_msg(skb, off, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) goto csum_copy_err; } if (unlikely(err)) { if (!peeking) { atomic_inc(&sk->sk_drops); SNMP_INC_STATS(mib, UDP_MIB_INERRORS); } kfree_skb(skb); return err; } if (!peeking) SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS); sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); sin6->sin6_family = AF_INET6; sin6->sin6_port = udp_hdr(skb)->source; sin6->sin6_flowinfo = 0; if (is_udp4) { ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin6->sin6_addr); sin6->sin6_scope_id = 0; } else { sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); } *addr_len = sizeof(*sin6); BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, (struct sockaddr *)sin6); } if (udp_sk(sk)->gro_enabled) udp_cmsg_recv(msg, sk, skb); if (np->rxopt.all) ip6_datagram_recv_common_ctl(sk, msg, skb); if (is_udp4) { if (inet->cmsg_flags) ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off); } else { if (np->rxopt.all) ip6_datagram_recv_specific_ctl(sk, msg, skb); } err = copied; if (flags & MSG_TRUNC) err = ulen; skb_consume_udp(sk, skb, peeking ? -err : err); return err; csum_copy_err: if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, udp_skb_destructor)) { SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS); SNMP_INC_STATS(mib, UDP_MIB_INERRORS); } kfree_skb(skb); /* starting over for a new packet, but check if we need to yield */ cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); } EXPORT_SYMBOL(udpv6_encap_enable); /* Handler for tunnels with arbitrary destination ports: no socket lookup, go * through error handlers in encapsulations looking for a match. */ static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { int i; for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); const struct ip6_tnl_encap_ops *encap; encap = rcu_dereference(ip6tun_encaps[i]); if (!encap) continue; handler = encap->err_handler; if (handler && !handler(skb, opt, type, code, offset, info)) return 0; } return -ENOENT; } /* Try to match ICMP errors to UDP tunnels by looking up a socket without * reversing source and destination port: this will match tunnels that force the * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that * lwtunnels might actually break this assumption by being configured with * different destination ports on endpoints, in this case we won't be able to * trace ICMP messages back to them. * * If this doesn't match any socket, probe tunnels with arbitrary destination * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port * we've sent packets to won't necessarily match the local destination port. * * Then ask the tunnel implementation to match the error against a valid * association. * * Return an error if we can't find a match, the socket if we need further * processing, zero otherwise. */ static struct sock *__udp6_lib_err_encap(struct net *net, const struct ipv6hdr *hdr, int offset, struct udphdr *uh, struct udp_table *udptable, struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, __be32 info) { int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); /* Network header needs to point to the outer IPv6 header inside ICMP */ skb_reset_network_header(skb); /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, offset); if (sk) { up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (lookup && lookup(sk, skb)) sk = NULL; goto out; } sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source, &hdr->saddr, uh->dest, inet6_iif(skb), 0, udptable, skb); if (sk) { up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; } out: if (!sk) { sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code, offset, info)); } skb_set_transport_header(skb, transport_offset); skb_set_network_header(skb, network_offset); return sk; } int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info, struct udp_table *udptable) { struct ipv6_pinfo *np; const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct in6_addr *saddr = &hdr->saddr; const struct in6_addr *daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr; struct udphdr *uh = (struct udphdr *)(skb->data+offset); bool tunnel = false; struct sock *sk; int harderr; int err; struct net *net = dev_net(skb->dev); sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), inet6_sdif(skb), udptable, NULL); if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ if (static_branch_unlikely(&udpv6_encap_needed_key)) { sk = __udp6_lib_err_encap(net, hdr, offset, uh, udptable, sk, skb, opt, type, code, info); if (!sk) return 0; } else sk = ERR_PTR(-ENOENT); if (IS_ERR(sk)) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return PTR_ERR(sk); } tunnel = true; } harderr = icmpv6_err_convert(type, code, &err); np = inet6_sk(sk); if (type == ICMPV6_PKT_TOOBIG) { if (!ip6_sk_accept_pmtu(sk)) goto out; ip6_sk_update_pmtu(skb, sk, info); if (np->pmtudisc != IPV6_PMTUDISC_DONT) harderr = 1; } if (type == NDISC_REDIRECT) { if (tunnel) { ip6_redirect(skb, sock_net(sk), inet6_iif(skb), sk->sk_mark, sk->sk_uid); } else { ip6_sk_redirect(skb, sk); } goto out; } /* Tunnels don't have an application socket: don't pass errors back */ if (tunnel) { if (udp_sk(sk)->encap_err_rcv) udp_sk(sk)->encap_err_rcv(sk, skb, offset); goto out; } if (!np->recverr) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else { ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1)); } sk->sk_err = err; sk_error_report(sk); out: return 0; } static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; if (!ipv6_addr_any(&sk->sk_v6_daddr)) { sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); sk_incoming_cpu_update(sk); } else { sk_mark_napi_id_once(sk, skb); } rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) UDP6_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); else UDP6_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS, is_udplite); UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return -1; } return 0; } static __inline__ int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { return __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); } static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* * This is an encapsulation socket so pass the skb to * the socket's udp_encap_rcv() hook. Otherwise, just * fall through and pass this up the UDP socket. * up->encap_rcv() returns the following value: * =0 if skb was successfully passed to the encap * handler or was discarded by it. * >0 if skb should be passed on to UDP. * <0 if skb should be resubmitted as proto -N */ /* if we're overly short, let UDP handle it */ encap_rcv = READ_ONCE(up->encap_rcv); if (encap_rcv) { int ret; /* Verify checksum before giving to encap */ if (udp_lib_checksum_complete(skb)) goto csum_error; ret = encap_rcv(sk, skb); if (ret <= 0) { __UDP_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS, is_udplite); return -ret; } } /* FALLTHROUGH -- it's a UDP Packet */ } /* * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). */ if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { if (up->pcrlen == 0) { /* full coverage was set */ net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n", UDP_SKB_CB(skb)->cscov, skb->len); goto drop; } if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n", UDP_SKB_CB(skb)->cscov, up->pcrlen); goto drop; } } prefetch(&sk->sk_rmem_alloc); if (rcu_access_pointer(sk->sk_filter) && udp_lib_checksum_complete(skb)) goto csum_error; if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) goto drop; udp_csum_pull_header(skb); skb_dst_drop(skb); return __udpv6_queue_rcv_skb(sk, skb); csum_error: __UDP6_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: __UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); kfree_skb(skb); return -1; } static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff *next, *segs; int ret; if (likely(!udp_unexpected_gso(sk, skb))) return udpv6_queue_rcv_one_skb(sk, skb); __skb_push(skb, -skb_mac_offset(skb)); segs = udp_rcv_segment(sk, skb, false); skb_list_walk_safe(segs, skb, next) { __skb_pull(skb, skb_transport_offset(skb)); udp_post_segment_fix_csum(skb); ret = udpv6_queue_rcv_one_skb(sk, skb); if (ret > 0) ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret, true); } return 0; } static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, __be16 loc_port, const struct in6_addr *loc_addr, __be16 rmt_port, const struct in6_addr *rmt_addr, int dif, int sdif, unsigned short hnum) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) return false; if (udp_sk(sk)->udp_port_hash != hnum || sk->sk_family != PF_INET6 || (inet->inet_dport && inet->inet_dport != rmt_port) || (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif) || (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))) return false; if (!inet6_mc_check(sk, loc_addr, rmt_addr)) return false; return true; } static void udp6_csum_zero_error(struct sk_buff *skb) { /* RFC 2460 section 8.1 says that we SHOULD log * this error. Well, it is reasonable. */ net_dbg_ratelimited("IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n", &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source), &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest)); } /* * Note: called only from the BH handler context, * so we don't need to lock the hashes. */ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, struct udp_table *udptable, int proto) { struct sock *sk, *first = NULL; const struct udphdr *uh = udp_hdr(skb); unsigned short hnum = ntohs(uh->dest); struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); unsigned int offset = offsetof(typeof(*sk), sk_node); unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); int dif = inet6_iif(skb); int sdif = inet6_sdif(skb); struct hlist_node *node; struct sk_buff *nskb; if (use_hash2) { hash2_any = ipv6_portaddr_hash(net, &in6addr_any, hnum) & udptable->mask; hash2 = ipv6_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) { if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr, uh->source, saddr, dif, sdif, hnum)) continue; /* If zero checksum and no_check is not on for * the socket then skip it. */ if (!uh->check && !udp_sk(sk)->no_check6_rx) continue; if (!first) { first = sk; continue; } nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) { atomic_inc(&sk->sk_drops); __UDP6_INC_STATS(net, UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk)); __UDP6_INC_STATS(net, UDP_MIB_INERRORS, IS_UDPLITE(sk)); continue; } if (udpv6_queue_rcv_skb(sk, nskb) > 0) consume_skb(nskb); } /* Also lookup *:port if we are using hash2 and haven't done so yet. */ if (use_hash2 && hash2 != hash2_any) { hash2 = hash2_any; goto start_lookup; } if (first) { if (udpv6_queue_rcv_skb(first, skb) > 0) consume_skb(skb); } else { kfree_skb(skb); __UDP6_INC_STATS(net, UDP_MIB_IGNOREDMULTI, proto == IPPROTO_UDPLITE); } return 0; } static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { if (udp_sk_rx_dst_set(sk, dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; sk->sk_rx_dst_cookie = rt6_get_cookie(rt); } } /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and * return code conversion for ip layer consumption */ static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, struct udphdr *uh) { int ret; if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) skb_checksum_try_convert(skb, IPPROTO_UDP, ip6_compute_pseudo); ret = udpv6_queue_rcv_skb(sk, skb); /* a return value > 0 means to resubmit the input */ if (ret > 0) return ret; return 0; } int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; const struct in6_addr *saddr, *daddr; struct net *net = dev_net(skb->dev); struct udphdr *uh; struct sock *sk; bool refcounted; u32 ulen = 0; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto discard; saddr = &ipv6_hdr(skb)->saddr; daddr = &ipv6_hdr(skb)->daddr; uh = udp_hdr(skb); ulen = ntohs(uh->len); if (ulen > skb->len) goto short_packet; if (proto == IPPROTO_UDP) { /* UDP validates ulen. */ /* Check for jumbo payload */ if (ulen == 0) ulen = skb->len; if (ulen < sizeof(*uh)) goto short_packet; if (ulen < skb->len) { if (pskb_trim_rcsum(skb, ulen)) goto short_packet; saddr = &ipv6_hdr(skb)->saddr; daddr = &ipv6_hdr(skb)->daddr; uh = udp_hdr(skb); } } if (udp6_csum_init(skb, uh, proto)) goto csum_error; /* Check if the socket is already available, e.g. due to early demux */ sk = skb_steal_sock(skb, &refcounted); if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp6_sk_rx_dst_set(sk, dst); if (!uh->check && !udp_sk(sk)->no_check6_rx) { if (refcounted) sock_put(sk); goto report_csum_error; } ret = udp6_unicast_rcv_skb(sk, skb, uh); if (refcounted) sock_put(sk); return ret; } /* * Multicast receive code */ if (ipv6_addr_is_multicast(daddr)) return __udp6_lib_mcast_deliver(net, skb, saddr, daddr, udptable, proto); /* Unicast */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { if (!uh->check && !udp_sk(sk)->no_check6_rx) goto report_csum_error; return udp6_unicast_rcv_skb(sk, skb, uh); } reason = SKB_DROP_REASON_NO_SOCKET; if (!uh->check) goto report_csum_error; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; if (udp_lib_checksum_complete(skb)) goto csum_error; __UDP6_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb_reason(skb, reason); return 0; short_packet: if (reason == SKB_DROP_REASON_NOT_SPECIFIED) reason = SKB_DROP_REASON_PKT_TOO_SMALL; net_dbg_ratelimited("UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n", proto == IPPROTO_UDPLITE ? "-Lite" : "", saddr, ntohs(uh->source), ulen, skb->len, daddr, ntohs(uh->dest)); goto discard; report_csum_error: udp6_csum_zero_error(skb); csum_error: if (reason == SKB_DROP_REASON_NOT_SPECIFIED) reason = SKB_DROP_REASON_UDP_CSUM; __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: __UDP6_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); kfree_skb_reason(skb, reason); return 0; } static struct sock *__udp6_lib_demux_lookup(struct net *net, __be16 loc_port, const struct in6_addr *loc_addr, __be16 rmt_port, const struct in6_addr *rmt_addr, int dif, int sdif) { unsigned short hnum = ntohs(loc_port); unsigned int hash2 = ipv6_portaddr_hash(net, loc_addr, hnum); unsigned int slot2 = hash2 & udp_table.mask; struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum); struct sock *sk; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { if (sk->sk_state == TCP_ESTABLISHED && inet6_match(net, sk, rmt_addr, loc_addr, ports, dif, sdif)) return sk; /* Only check first socket in chain */ break; } return NULL; } void udp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct udphdr *uh; struct sock *sk; struct dst_entry *dst; int dif = skb->dev->ifindex; int sdif = inet6_sdif(skb); if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) return; uh = udp_hdr(skb); if (skb->pkt_type == PACKET_HOST) sk = __udp6_lib_demux_lookup(net, uh->dest, &ipv6_hdr(skb)->daddr, uh->source, &ipv6_hdr(skb)->saddr, dif, sdif); else return; if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return; skb->sk = sk; skb->destructor = sock_efree; dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, sk->sk_rx_dst_cookie); if (dst) { /* set noref for now. * any place which wants to hold dst has to call * dst_hold_safe() */ skb_dst_set_noref(skb, dst); } } INDIRECT_CALLABLE_SCOPE int udpv6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP); } /* * Throw away all pending data and cancel the corking. Socket is locked. */ static void udp_v6_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); if (up->pending == AF_INET) udp_flush_pending_frames(sk); else if (up->pending) { up->len = 0; up->pending = 0; ip6_flush_pending_frames(sk); } } static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { if (addr_len < offsetofend(struct sockaddr, sa_family)) return -EINVAL; /* The following checks are replicated from __ip6_datagram_connect() * and intended to prevent BPF program called below from accessing * bytes that are out of the bound specified by user in addr_len. */ if (uaddr->sa_family == AF_INET) { if (__ipv6_only_sock(sk)) return -EAFNOSUPPORT; return udp_pre_connect(sk, uaddr, addr_len); } if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr); } /** * udp6_hwcsum_outgoing - handle outgoing HW checksumming * @sk: socket we are sending on * @skb: sk_buff containing the filled-in UDP header * (checksum field must be zeroed out) * @saddr: source address * @daddr: destination address * @len: length of packet */ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, int len) { unsigned int offset; struct udphdr *uh = udp_hdr(skb); struct sk_buff *frags = skb_shinfo(skb)->frag_list; __wsum csum = 0; if (!frags) { /* Only one fragment on the socket. */ skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); uh->check = ~csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, 0); } else { /* * HW-checksum won't work as there are two or more * fragments on the socket so that all csums of sk_buffs * should be together */ offset = skb_transport_offset(skb); skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); csum = skb->csum; skb->ip_summed = CHECKSUM_NONE; do { csum = csum_add(csum, frags->csum); } while ((frags = frags->next)); uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } } /* * Sending */ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, struct inet_cork *cork) { struct sock *sk = skb->sk; struct udphdr *uh; int err = 0; int is_udplite = IS_UDPLITE(sk); __wsum csum = 0; int offset = skb_transport_offset(skb); int len = skb->len - offset; int datalen = len - sizeof(*uh); /* * Create a UDP header */ uh = udp_hdr(skb); uh->source = fl6->fl6_sport; uh->dest = fl6->fl6_dport; uh->len = htons(len); uh->check = 0; if (cork->gso_size) { const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); if (hlen + cork->gso_size > cork->fragsize) { kfree_skb(skb); return -EINVAL; } if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); return -EINVAL; } if (udp_sk(sk)->no_check6_tx) { kfree_skb(skb); return -EINVAL; } if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || dst_xfrm(skb_dst(skb))) { kfree_skb(skb); return -EIO; } if (datalen > cork->gso_size) { skb_shinfo(skb)->gso_size = cork->gso_size; skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, cork->gso_size); } goto csum_partial; } if (is_udplite) csum = udplite_csum(skb); else if (udp_sk(sk)->no_check6_tx) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ csum_partial: udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len); goto send; } else csum = udp_csum(skb); /* add protocol-dependent pseudo-header */ uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, len, fl6->flowi6_proto, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; send: err = ip6_send_skb(skb); if (err) { if (err == -ENOBUFS && !inet6_sk(sk)->recverr) { UDP6_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); err = 0; } } else { UDP6_INC_STATS(sock_net(sk), UDP_MIB_OUTDATAGRAMS, is_udplite); } return err; } static int udp_v6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; struct udp_sock *up = udp_sk(sk); struct flowi6 fl6; int err = 0; if (up->pending == AF_INET) return udp_push_pending_frames(sk); /* ip6_finish_skb will release the cork, so make a copy of * fl6 here. */ fl6 = inet_sk(sk)->cork.fl.u.ip6; skb = ip6_finish_skb(sk); if (!skb) goto out; err = udp_v6_send_skb(skb, &fl6, &inet_sk(sk)->cork.base); out: up->len = 0; up->pending = 0; return err; } int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct ipv6_txoptions *opt = NULL; struct ipv6_txoptions *opt_to_free = NULL; struct ip6_flowlabel *flowlabel = NULL; struct flowi6 fl6; struct dst_entry *dst; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; bool connected = false; int ulen = len; int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int err; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); ipcm6_init(&ipc6); ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; /* destination address check */ if (sin6) { if (addr_len < offsetof(struct sockaddr, sa_data)) return -EINVAL; switch (sin6->sin6_family) { case AF_INET6: if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; daddr = &sin6->sin6_addr; if (ipv6_addr_any(daddr) && ipv6_addr_v4mapped(&np->saddr)) ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), daddr); break; case AF_INET: goto do_udp_sendmsg; case AF_UNSPEC: msg->msg_name = sin6 = NULL; msg->msg_namelen = addr_len = 0; daddr = NULL; break; default: return -EINVAL; } } else if (!up->pending) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; } else daddr = NULL; if (daddr) { if (ipv6_addr_v4mapped(daddr)) { struct sockaddr_in sin; sin.sin_family = AF_INET; sin.sin_port = sin6 ? sin6->sin6_port : inet->inet_dport; sin.sin_addr.s_addr = daddr->s6_addr32[3]; msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: err = __ipv6_only_sock(sk) ? -ENETUNREACH : udp_sendmsg(sk, msg, len); msg->msg_name = sin6; msg->msg_namelen = addr_len; return err; } } if (up->pending == AF_INET) return udp_sendmsg(sk, msg, len); /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ if (len > INT_MAX - sizeof(struct udphdr)) return -EMSGSIZE; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; if (up->pending) { /* * There are pending frames. * The socket lock must be held while it's corked. */ lock_sock(sk); if (likely(up->pending)) { if (unlikely(up->pending != AF_INET6)) { release_sock(sk); return -EAFNOSUPPORT; } dst = NULL; goto do_append_data; } release_sock(sk); } ulen += sizeof(struct udphdr); memset(&fl6, 0, sizeof(fl6)); if (sin6) { if (sin6->sin6_port == 0) return -EINVAL; fl6.fl6_dport = sin6->sin6_port; daddr = &sin6->sin6_addr; if (np->sndflow) { fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } } /* * Otherwise it will be difficult to maintain * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; fl6.fl6_dport = inet->inet_dport; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; connected = true; } if (!fl6.flowi6_oif) fl6.flowi6_oif = sk->sk_bound_dev_if; if (!fl6.flowi6_oif) fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; fl6.flowi6_uid = sk->sk_uid; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); ipc6.opt = opt; err = udp_cmsg_send(sk, msg, &ipc6.gso_size); if (err > 0) { err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); connected = false; } if (err < 0) { fl6_sock_release(flowlabel); return err; } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } if (!opt) { opt = txopt_get(np); opt_to_free = opt; } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); ipc6.opt = opt; fl6.flowi6_proto = sk->sk_protocol; fl6.flowi6_mark = ipc6.sockc.mark; fl6.daddr = *daddr; if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, (struct sockaddr *)sin6, &fl6.saddr); if (err) goto out_no_dst; if (sin6) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { /* BPF program rewrote IPv6-only by IPv4-mapped * IPv6. It's currently unsupported. */ err = -ENOTSUPP; goto out_no_dst; } if (sin6->sin6_port == 0) { /* BPF program set invalid port. Reject it. */ err = -EINVAL; goto out_no_dst; } fl6.fl6_dport = sin6->sin6_port; fl6.daddr = sin6->sin6_addr; } } if (ipv6_addr_any(&fl6.daddr)) fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ final_p = fl6_update_dst(&fl6, opt, &final); if (final_p) connected = false; if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) { fl6.flowi6_oif = np->mcast_oif; connected = false; } else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); if (ipc6.tclass < 0) ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, connected); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto out; } if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: /* Lockless fast path for the non-corking case */ if (!corkreq) { struct inet_cork_full cork; struct sk_buff *skb; skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, &fl6, (struct rt6_info *)dst, msg->msg_flags, &cork); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) err = udp_v6_send_skb(skb, &fl6, &cork.base); goto out; } lock_sock(sk); if (unlikely(up->pending)) { /* The socket is already corked while preparing it. */ /* ... which is an evident application bug. --ANK */ release_sock(sk); net_dbg_ratelimited("udp cork app bug 2\n"); err = -EINVAL; goto out; } up->pending = AF_INET6; do_append_data: if (ipc6.dontfrag < 0) ipc6.dontfrag = np->dontfrag; up->len += ulen; err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, &fl6, (struct rt6_info *)dst, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_v6_flush_pending_frames(sk); else if (!corkreq) err = udp_v6_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) up->pending = 0; if (err > 0) err = np->recverr ? net_xmit_errno(err) : 0; release_sock(sk); out: dst_release(dst); out_no_dst: fl6_sock_release(flowlabel); txopt_put(opt_to_free); if (!err) return len; /* * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting * ENOBUFS might not be good (it's not tunable per se), but otherwise * we don't have a good statistic (IpOutDiscards but it can be too many * things). We could add another new stat but at least for now that * seems like overkill. */ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { UDP6_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); } return err; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(dst, &fl6.daddr); if (!(msg->msg_flags&MSG_PROBE) || len) goto back_from_confirm; err = 0; goto out; } void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); lock_sock(sk); /* protects from races with udp_abort() */ sock_set_flag(sk, SOCK_DEAD); udp_v6_flush_pending_frames(sk); release_sock(sk); if (static_branch_unlikely(&udpv6_encap_needed_key)) { if (up->encap_type) { void (*encap_destroy)(struct sock *sk); encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) encap_destroy(sk); } if (up->encap_enabled) { static_branch_dec(&udpv6_encap_needed_key); udp_encap_disable(); } } } /* * Socket option code for UDP */ int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_v6_push_pending_frames); return ipv6_setsockopt(sk, level, optname, optval, optlen); } int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_getsockopt(sk, level, optname, optval, optlen); return ipv6_getsockopt(sk, level, optname, optval, optlen); } static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS int udp6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { int bucket = ((struct udp_iter_state *)seq->private)->bucket; struct inet_sock *inet = inet_sk(v); __u16 srcp = ntohs(inet->inet_sport); __u16 destp = ntohs(inet->inet_dport); __ip6_dgram_sock_seq_show(seq, v, srcp, destp, udp_rqueue_get(v), bucket); } return 0; } const struct seq_operations udp6_seq_ops = { .start = udp_seq_start, .next = udp_seq_next, .stop = udp_seq_stop, .show = udp6_seq_show, }; EXPORT_SYMBOL(udp6_seq_ops); static struct udp_seq_afinfo udp6_seq_afinfo = { .family = AF_INET6, .udp_table = &udp_table, }; int __net_init udp6_proc_init(struct net *net) { if (!proc_create_net_data("udp6", 0444, net->proc_net, &udp6_seq_ops, sizeof(struct udp_iter_state), &udp6_seq_afinfo)) return -ENOMEM; return 0; } void udp6_proc_exit(struct net *net) { remove_proc_entry("udp6", net->proc_net); } #endif /* CONFIG_PROC_FS */ /* ------------------------------------------------------------------------ */ struct proto udpv6_prot = { .name = "UDPv6", .owner = THIS_MODULE, .close = udp_lib_close, .pre_connect = udpv6_pre_connect, .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, .init = udpv6_init_sock, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt, .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, .release_cb = ip6_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), .h.udp_table = &udp_table, .diag_destroy = udp_abort, }; static struct inet_protosw udpv6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_UDP, .prot = &udpv6_prot, .ops = &inet6_dgram_ops, .flags = INET_PROTOSW_PERMANENT, }; int __init udpv6_init(void) { int ret; ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP); if (ret) goto out; ret = inet6_register_protosw(&udpv6_protosw); if (ret) goto out_udpv6_protocol; out: return ret; out_udpv6_protocol: inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); goto out; } void udpv6_exit(void) { inet6_unregister_protosw(&udpv6_protosw); inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); } |
| 253 153 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _DELAYED_CALL_H #define _DELAYED_CALL_H /* * Poor man's closures; I wish we could've done them sanely polymorphic, * but... */ struct delayed_call { void (*fn)(void *); void *arg; }; #define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL} /* I really wish we had closures with sane typechecking... */ static inline void set_delayed_call(struct delayed_call *call, void (*fn)(void *), void *arg) { call->fn = fn; call->arg = arg; } static inline void do_delayed_call(struct delayed_call *call) { if (call->fn) call->fn(call->arg); } static inline void clear_delayed_call(struct delayed_call *call) { call->fn = NULL; } #endif |
| 119 26 1 92 10 1 92 30 3 150 151 150 990 990 130 129 922 72 154 987 990 990 130 130 131 131 91 91 10 91 10 91 3 3 2 3 3 107 107 108 9 107 89 107 33 26 108 7 100 8 100 99 8 17 90 3 93 99 3 91 6 7 100 92 92 90 92 71 17 17 8 16 13 5 5 6 7 9 16 1 1 1 8 12 24 23 15 1 2 16 4 3 2 1 1 11 3 11 11 11 11 11 11 11 11 11 11 11 11 10 11 11 11 9 1 9 1 10 8 2 3 4 9 9 26 2 24 10 10 1 3 5 8 7 13 15 2 13 13 10 7 1 1 86 87 102 73 60 1 1 1 1 1 1 1 1 2 1 51 2 1 1 1 2 21 15 16 16 1 5 1 6 21 21 5 21 15 4 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Bridge netlink control interface * * Authors: * Stephen Hemminger <shemminger@osdl.org> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/etherdevice.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/if_bridge.h> #include "br_private.h" #include "br_private_stp.h" #include "br_private_cfm.h" #include "br_private_tunnel.h" #include "br_private_mcast_eht.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int num_vlans = 0; if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; pvid = br_get_pvid(vg); /* Count number of vlan infos */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; /* only a context, bridge vlan not activated */ if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } return num_vlans; } static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { int num_vlans; if (!vg) return 0; if (filter_mask & RTEXT_FILTER_BRVLAN) return vg->num_vlans; rcu_read_lock(); num_vlans = __get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); return num_vlans; } static size_t br_get_link_af_size_filtered(const struct net_device *dev, u32 filter_mask) { struct net_bridge_vlan_group *vg = NULL; struct net_bridge_port *p = NULL; struct net_bridge *br = NULL; u32 num_cfm_peer_mep_infos; u32 num_cfm_mep_infos; size_t vinfo_sz = 0; int num_vlan_infos; rcu_read_lock(); if (netif_is_bridge_port(dev)) { p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); } else if (dev->priv_flags & IFF_EBRIDGE) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); } num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); if (p && (p->flags & BR_VLAN_TUNNEL)) vinfo_sz += br_get_vlan_tunnel_info_size(vg); /* Each VLAN is returned in bridge_vlan_info along with flags */ vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); if (!(filter_mask & RTEXT_FILTER_CFM_STATUS)) return vinfo_sz; if (!br) return vinfo_sz; /* CFM status info must be added */ br_cfm_mep_count(br, &num_cfm_mep_infos); br_cfm_peer_mep_count(br, &num_cfm_peer_mep_infos); vinfo_sz += nla_total_size(0); /* IFLA_BRIDGE_CFM */ /* For each status struct the MEP instance (u32) is added */ /* MEP instance (u32) + br_cfm_mep_status */ vinfo_sz += num_cfm_mep_infos * /*IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE */ (nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN */ + nla_total_size(sizeof(u32))); /* MEP instance (u32) + br_cfm_cc_peer_status */ vinfo_sz += num_cfm_peer_mep_infos * /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE */ (nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE */ + nla_total_size(sizeof(u8)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE */ + nla_total_size(sizeof(u8)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN */ + nla_total_size(sizeof(u32))); return vinfo_sz; } static inline size_t br_port_info_size(void) { return nla_total_size(1) /* IFLA_BRPORT_STATE */ + nla_total_size(2) /* IFLA_BRPORT_PRIORITY */ + nla_total_size(4) /* IFLA_BRPORT_COST */ + nla_total_size(1) /* IFLA_BRPORT_MODE */ + nla_total_size(1) /* IFLA_BRPORT_GUARD */ + nla_total_size(1) /* IFLA_BRPORT_PROTECT */ + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_BCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_IN_OPEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_CNT */ + 0; } static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */ + nla_total_size(br_get_link_af_size_filtered(dev, filter_mask)) /* IFLA_AF_SPEC */ + nla_total_size(4); /* IFLA_BRPORT_BACKUP_PORT */ } static int br_port_fill_attrs(struct sk_buff *skb, const struct net_bridge_port *p) { u8 mode = !!(p->flags & BR_HAIRPIN_MODE); struct net_bridge_port *backup_p; u64 timerval; if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) || nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) || nla_put_u8(skb, IFLA_BRPORT_MODE, mode) || nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) || nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) || nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_TO_UCAST, !!(p->flags & BR_MULTICAST_TO_UNICAST)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) || nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD, !!(p->flags & BR_MCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_BCAST_FLOOD, !!(p->flags & BR_BCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, !!(p->flags & BR_PROXYARP_WIFI)) || nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), &p->designated_root) || nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), &p->designated_bridge) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost) || nla_put_u16(skb, IFLA_BRPORT_ID, p->port_id) || nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) || nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, p->topology_change_ack) || nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & BR_VLAN_TUNNEL)) || nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, !!(p->flags & BR_NEIGH_SUPPRESS)) || nla_put_u8(skb, IFLA_BRPORT_MRP_RING_OPEN, !!(p->flags & BR_MRP_LOST_CONT)) || nla_put_u8(skb, IFLA_BRPORT_MRP_IN_OPEN, !!(p->flags & BR_MRP_LOST_IN_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_MESSAGE_AGE_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->forward_delay_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_FORWARD_DELAY_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->hold_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_HOLD_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, p->multicast_ctx.multicast_router) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, p->multicast_eht_hosts_cnt)) return -EMSGSIZE; #endif /* we might be called only with br->lock */ rcu_read_lock(); backup_p = rcu_dereference(p->backup_port); if (backup_p) nla_put_u32(skb, IFLA_BRPORT_BACKUP_PORT, backup_p->dev->ifindex); rcu_read_unlock(); return 0; } static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start, u16 vid_end, u16 flags) { struct bridge_vlan_info vinfo; if ((vid_end - vid_start) > 0) { /* add range to skb */ vinfo.vid = vid_start; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_BEGIN; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; vinfo.vid = vid_end; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } else { vinfo.vid = vid_start; vinfo.flags = flags; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int err = 0; /* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan * and mark vlan info with begin and end flags * if vlaninfo represents a range */ pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { /* Call it once more to send any left over vlans */ err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } return 0; } static int br_fill_ifvlaninfo(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct bridge_vlan_info vinfo; struct net_bridge_vlan *v; u16 pvid; pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; vinfo.vid = v->vid; vinfo.flags = 0; if (v->vid == pvid) vinfo.flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } /* * Create one netlink message for one interface * Contains port and master info as well as carrier and bridge state. */ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, u32 filter_mask, const struct net_device *dev, bool getlink) { u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; struct nlattr *af = NULL; struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; if (port) br = port->br; else br = netdev_priv(dev); br_debug(br, "br_fill_info event %d port %s master %s\n", event, dev->name, br->dev->name); nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); if (nlh == NULL) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ifi_family = AF_BRIDGE; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; hdr->ifi_index = dev->ifindex; hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_MASTER, br->dev->ifindex) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u8(skb, IFLA_OPERSTATE, operstate) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || (dev->ifindex != dev_get_iflink(dev) && nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; if (event == RTM_NEWLINK && port) { struct nlattr *nest; nest = nla_nest_start(skb, IFLA_PROTINFO); if (nest == NULL || br_port_fill_attrs(skb, port) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } if (filter_mask & (RTEXT_FILTER_BRVLAN | RTEXT_FILTER_BRVLAN_COMPRESSED | RTEXT_FILTER_MRP | RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) { af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) goto nla_put_failure; } /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { struct net_bridge_vlan_group *vg; int err; /* RCU needed because of the VLAN locking rules (rcu || rtnl) */ rcu_read_lock(); if (port) vg = nbp_vlan_group_rcu(port); else vg = br_vlan_group_rcu(br); if (!vg || !vg->num_vlans) { rcu_read_unlock(); goto done; } if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) err = br_fill_ifvlaninfo_compressed(skb, vg); else err = br_fill_ifvlaninfo(skb, vg); if (port && (port->flags & BR_VLAN_TUNNEL)) err = br_fill_vlan_tunnel_info(skb, vg); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_MRP) { int err; if (!br_mrp_enabled(br) || port) goto done; rcu_read_lock(); err = br_mrp_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & (RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) { struct nlattr *cfm_nest = NULL; int err; if (!br_cfm_created(br) || port) goto done; cfm_nest = nla_nest_start(skb, IFLA_BRIDGE_CFM); if (!cfm_nest) goto nla_put_failure; if (filter_mask & RTEXT_FILTER_CFM_CONFIG) { rcu_read_lock(); err = br_cfm_config_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_CFM_STATUS) { rcu_read_lock(); err = br_cfm_status_fill_info(skb, br, getlink); rcu_read_unlock(); if (err) goto nla_put_failure; } nla_nest_end(skb, cfm_nest); } done: if (af) nla_nest_end(skb, af); nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void br_info_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port, u32 filter) { struct net_device *dev; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 port_no = 0; if (WARN_ON(!port && !br)) return; if (port) { dev = port->dev; br = port->br; port_no = port->port_no; } else { dev = br->dev; } net = dev_net(dev); br_debug(br, "port %u(%s) event %d\n", port_no, dev->name, event); skb = nlmsg_new(br_nlmsg_size(dev, filter), GFP_ATOMIC); if (skb == NULL) goto errout; err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev, false); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } /* Notify listeners of a change in bridge or port information */ void br_ifinfo_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port) { u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; br_info_notify(event, br, port, filter); } /* * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { struct net_bridge_port *port = br_port_get_rtnl(dev); if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) && !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) && !(filter_mask & RTEXT_FILTER_MRP) && !(filter_mask & RTEXT_FILTER_CFM_CONFIG) && !(filter_mask & RTEXT_FILTER_CFM_STATUS)) return 0; return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, filter_mask, dev, true); } static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo, bool *changed, struct netlink_ext_ack *extack) { bool curr_change; int err = 0; switch (cmd) { case RTM_SETLINK: if (p) { /* if the MASTER flag is set this will act on the global * per-VLAN entry as well */ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags, &curr_change, extack); } else { vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY; err = br_vlan_add(br, vinfo->vid, vinfo->flags, &curr_change, extack); } if (curr_change) *changed = true; break; case RTM_DELLINK: if (p) { if (!nbp_vlan_delete(p, vinfo->vid)) *changed = true; if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) && !br_vlan_delete(p->br, vinfo->vid)) *changed = true; } else if (!br_vlan_delete(br, vinfo->vid)) { *changed = true; } break; } return err; } int br_process_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo_curr, struct bridge_vlan_info **vinfo_last, bool *changed, struct netlink_ext_ack *extack) { int err, rtm_cmd; if (!br_vlan_valid_id(vinfo_curr->vid, extack)) return -EINVAL; /* needed for vlan-only NEWVLAN/DELVLAN notifications */ rtm_cmd = br_afspec_cmd_to_rtm(cmd); if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; *vinfo_last = vinfo_curr; return 0; } if (*vinfo_last) { struct bridge_vlan_info tmp_vinfo; int v, v_change_start = 0; if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; memcpy(&tmp_vinfo, *vinfo_last, sizeof(struct bridge_vlan_info)); for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) { bool curr_change = false; tmp_vinfo.vid = v; err = br_vlan_info(br, p, cmd, &tmp_vinfo, &curr_change, extack); if (err) break; if (curr_change) { *changed = curr_change; if (!v_change_start) v_change_start = v; } else { /* nothing to notify yet */ if (!v_change_start) continue; br_vlan_notify(br, p, v_change_start, v - 1, rtm_cmd); v_change_start = 0; } cond_resched(); } /* v_change_start is set only if the last/whole range changed */ if (v_change_start) br_vlan_notify(br, p, v_change_start, v - 1, rtm_cmd); *vinfo_last = NULL; return err; } err = br_vlan_info(br, p, cmd, vinfo_curr, changed, extack); if (*changed) br_vlan_notify(br, p, vinfo_curr->vid, 0, rtm_cmd); return err; } static int br_afspec(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *af_spec, int cmd, bool *changed, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo_curr = NULL; struct bridge_vlan_info *vinfo_last = NULL; struct nlattr *attr; struct vtunnel_info tinfo_last = {}; struct vtunnel_info tinfo_curr = {}; int err = 0, rem; nla_for_each_nested(attr, af_spec, rem) { err = 0; switch (nla_type(attr)) { case IFLA_BRIDGE_VLAN_TUNNEL_INFO: if (!p || !(p->flags & BR_VLAN_TUNNEL)) return -EINVAL; err = br_parse_vlan_tunnel_info(attr, &tinfo_curr); if (err) return err; err = br_process_vlan_tunnel_info(br, p, cmd, &tinfo_curr, &tinfo_last, changed); if (err) return err; break; case IFLA_BRIDGE_VLAN_INFO: if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo_curr = nla_data(attr); err = br_process_vlan_info(br, p, cmd, vinfo_curr, &vinfo_last, changed, extack); if (err) return err; break; case IFLA_BRIDGE_MRP: err = br_mrp_parse(br, p, attr, cmd, extack); if (err) return err; break; case IFLA_BRIDGE_CFM: err = br_cfm_parse(br, p, attr, cmd, extack); if (err) return err; break; } } return err; } static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, [IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 }, [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_VLAN_TUNNEL] = { .type = NLA_U8 }, [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ static int br_set_port_state(struct net_bridge_port *p, u8 state) { if (state > BR_STATE_BLOCKING) return -EINVAL; /* if kernel STP is running, don't allow changes */ if (p->br->stp_enabled == BR_KERNEL_STP) return -EBUSY; /* if device is not up, change is not allowed * if link is not present, only allowable state is disabled */ if (!netif_running(p->dev) || (!netif_oper_up(p->dev) && state != BR_STATE_DISABLED)) return -ENETDOWN; br_set_state(p, state); br_port_state_selection(p->br); return 0; } /* Set/clear or port flags based on attribute */ static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], int attrtype, unsigned long mask) { if (!tb[attrtype]) return; if (nla_get_u8(tb[attrtype])) p->flags |= mask; else p->flags &= ~mask; } /* Process bridge protocol info on port */ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], struct netlink_ext_ack *extack) { unsigned long old_flags, changed_mask; bool br_vlan_tunnel_old; int err; old_flags = p->flags; br_vlan_tunnel_old = (old_flags & BR_VLAN_TUNNEL) ? true : false; br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); changed_mask = old_flags ^ p->flags; err = br_switchdev_set_port_flag(p, p->flags, changed_mask, extack); if (err) { p->flags = old_flags; return err; } if (br_vlan_tunnel_old && !(p->flags & BR_VLAN_TUNNEL)) nbp_vlan_tunnel_info_flush(p); br_port_flags_change(p, changed_mask); if (tb[IFLA_BRPORT_COST]) { err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); if (err) return err; } if (tb[IFLA_BRPORT_PRIORITY]) { err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY])); if (err) return err; } if (tb[IFLA_BRPORT_STATE]) { err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE])); if (err) return err; } if (tb[IFLA_BRPORT_FLUSH]) br_fdb_delete_by_port(p->br, p, 0, 0); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) { u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]); err = br_multicast_set_port_router(&p->multicast_ctx, mcast_router); if (err) return err; } if (tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]) { u32 hlimit; hlimit = nla_get_u32(tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]); err = br_multicast_eht_set_hosts_limit(p, hlimit); if (err) return err; } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_MACPAUSE) return -EINVAL; p->group_fwd_mask = fwd_mask; } if (tb[IFLA_BRPORT_BACKUP_PORT]) { struct net_device *backup_dev = NULL; u32 backup_ifindex; backup_ifindex = nla_get_u32(tb[IFLA_BRPORT_BACKUP_PORT]); if (backup_ifindex) { backup_dev = __dev_get_by_index(dev_net(p->dev), backup_ifindex); if (!backup_dev) return -ENOENT; } err = nbp_backup_change(p, backup_dev); if (err) return err; } return 0; } /* Change state and parameters on port. */ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct nlattr *tb[IFLA_BRPORT_MAX + 1]; struct net_bridge_port *p; struct nlattr *protinfo; struct nlattr *afspec; bool changed = false; int err = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!protinfo && !afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself if the AF_SPEC * is set to see if someone is setting vlan info on the bridge */ if (!p && !afspec) return -EINVAL; if (p && protinfo) { if (protinfo->nla_type & NLA_F_NESTED) { err = nla_parse_nested_deprecated(tb, IFLA_BRPORT_MAX, protinfo, br_port_policy, NULL); if (err) return err; spin_lock_bh(&p->br->lock); err = br_setport(p, tb, extack); spin_unlock_bh(&p->br->lock); } else { /* Binary compatibility with old RSTP */ if (nla_len(protinfo) < sizeof(u8)) return -EINVAL; spin_lock_bh(&p->br->lock); err = br_set_port_state(p, nla_get_u8(protinfo)); spin_unlock_bh(&p->br->lock); } if (err) goto out; changed = true; } if (afspec) err = br_afspec(br, p, afspec, RTM_SETLINK, &changed, extack); if (changed) br_ifinfo_notify(RTM_NEWLINK, br, p); out: return err; } /* Delete port information */ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct net_bridge_port *p; struct nlattr *afspec; bool changed = false; int err = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself as well */ if (!p && !(dev->priv_flags & IFF_EBRIDGE)) return -EINVAL; err = br_afspec(br, p, afspec, RTM_DELLINK, &changed, NULL); if (changed) /* Send RTM_NEWLINK because userspace * expects RTM_NEWLINK for vlan dels */ br_ifinfo_notify(RTM_NEWLINK, br, p); return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) return 0; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL] && !eth_type_vlan(nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]))) return -EPROTONOSUPPORT; if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); if (defpvid >= VLAN_VID_MASK) return -EINVAL; } #endif return 0; } static int br_port_slave_changelink(struct net_device *brdev, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int ret; if (!data) return 0; spin_lock_bh(&br->lock); ret = br_setport(br_port_get_rtnl(dev), data, extack); spin_unlock_bh(&br->lock); return ret; } static int br_port_fill_slave_info(struct sk_buff *skb, const struct net_device *brdev, const struct net_device *dev) { return br_port_fill_attrs(skb, br_port_get_rtnl(dev)); } static size_t br_port_get_slave_size(const struct net_device *brdev, const struct net_device *dev) { return br_port_info_size(); } static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 }, [IFLA_BR_HELLO_TIME] = { .type = NLA_U32 }, [IFLA_BR_MAX_AGE] = { .type = NLA_U32 }, [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERIER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 }, [IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 }, [IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, [IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 }, [IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 }, [IFLA_BR_MULTI_BOOLOPT] = NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)), }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int err; if (!data) return 0; if (data[IFLA_BR_FORWARD_DELAY]) { err = br_set_forward_delay(br, nla_get_u32(data[IFLA_BR_FORWARD_DELAY])); if (err) return err; } if (data[IFLA_BR_HELLO_TIME]) { err = br_set_hello_time(br, nla_get_u32(data[IFLA_BR_HELLO_TIME])); if (err) return err; } if (data[IFLA_BR_MAX_AGE]) { err = br_set_max_age(br, nla_get_u32(data[IFLA_BR_MAX_AGE])); if (err) return err; } if (data[IFLA_BR_AGEING_TIME]) { err = br_set_ageing_time(br, nla_get_u32(data[IFLA_BR_AGEING_TIME])); if (err) return err; } if (data[IFLA_BR_STP_STATE]) { u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]); err = br_stp_set_enabled(br, stp_enabled, extack); if (err) return err; } if (data[IFLA_BR_PRIORITY]) { u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]); br_stp_set_bridge_priority(br, priority); } if (data[IFLA_BR_VLAN_FILTERING]) { u8 vlan_filter = nla_get_u8(data[IFLA_BR_VLAN_FILTERING]); err = br_vlan_filter_toggle(br, vlan_filter, extack); if (err) return err; } #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL]) { __be16 vlan_proto = nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]); err = __br_vlan_set_proto(br, vlan_proto, extack); if (err) return err; } if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); err = __br_vlan_set_default_pvid(br, defpvid, extack); if (err) return err; } if (data[IFLA_BR_VLAN_STATS_ENABLED]) { __u8 vlan_stats = nla_get_u8(data[IFLA_BR_VLAN_STATS_ENABLED]); err = br_vlan_set_stats(br, vlan_stats); if (err) return err; } if (data[IFLA_BR_VLAN_STATS_PER_PORT]) { __u8 per_port = nla_get_u8(data[IFLA_BR_VLAN_STATS_PER_PORT]); err = br_vlan_set_stats_per_port(br, per_port); if (err) return err; } #endif if (data[IFLA_BR_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(data[IFLA_BR_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_RESTRICTED) return -EINVAL; br->group_fwd_mask = fwd_mask; } if (data[IFLA_BR_GROUP_ADDR]) { u8 new_addr[ETH_ALEN]; if (nla_len(data[IFLA_BR_GROUP_ADDR]) != ETH_ALEN) return -EINVAL; memcpy(new_addr, nla_data(data[IFLA_BR_GROUP_ADDR]), ETH_ALEN); if (!is_link_local_ether_addr(new_addr)) return -EINVAL; if (new_addr[5] == 1 || /* 802.3x Pause address */ new_addr[5] == 2 || /* 802.3ad Slow protocols */ new_addr[5] == 3) /* 802.1X PAE address */ return -EINVAL; spin_lock_bh(&br->lock); memcpy(br->group_addr, new_addr, sizeof(br->group_addr)); spin_unlock_bh(&br->lock); br_opt_toggle(br, BROPT_GROUP_ADDR_SET, true); br_recalculate_fwd_mask(br); } if (data[IFLA_BR_FDB_FLUSH]) br_fdb_flush(br); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (data[IFLA_BR_MCAST_ROUTER]) { u8 multicast_router = nla_get_u8(data[IFLA_BR_MCAST_ROUTER]); err = br_multicast_set_router(&br->multicast_ctx, multicast_router); if (err) return err; } if (data[IFLA_BR_MCAST_SNOOPING]) { u8 mcast_snooping = nla_get_u8(data[IFLA_BR_MCAST_SNOOPING]); err = br_multicast_toggle(br, mcast_snooping, extack); if (err) return err; } if (data[IFLA_BR_MCAST_QUERY_USE_IFADDR]) { u8 val; val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]); br_opt_toggle(br, BROPT_MULTICAST_QUERY_USE_IFADDR, !!val); } if (data[IFLA_BR_MCAST_QUERIER]) { u8 mcast_querier = nla_get_u8(data[IFLA_BR_MCAST_QUERIER]); err = br_multicast_set_querier(&br->multicast_ctx, mcast_querier); if (err) return err; } if (data[IFLA_BR_MCAST_HASH_ELASTICITY]) br_warn(br, "the hash_elasticity option has been deprecated and is always %u\n", RHT_ELASTICITY); if (data[IFLA_BR_MCAST_HASH_MAX]) br->hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]); if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]); br->multicast_ctx.multicast_last_member_count = val; } if (data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]); br->multicast_ctx.multicast_startup_query_count = val; } if (data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]); br->multicast_ctx.multicast_last_member_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]); br->multicast_ctx.multicast_membership_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERIER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERIER_INTVL]); br->multicast_ctx.multicast_querier_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]); br_multicast_set_query_intvl(&br->multicast_ctx, val); } if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]); br->multicast_ctx.multicast_query_response_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]); br_multicast_set_startup_query_intvl(&br->multicast_ctx, val); } if (data[IFLA_BR_MCAST_STATS_ENABLED]) { __u8 mcast_stats; mcast_stats = nla_get_u8(data[IFLA_BR_MCAST_STATS_ENABLED]); br_opt_toggle(br, BROPT_MULTICAST_STATS_ENABLED, !!mcast_stats); } if (data[IFLA_BR_MCAST_IGMP_VERSION]) { __u8 igmp_version; igmp_version = nla_get_u8(data[IFLA_BR_MCAST_IGMP_VERSION]); err = br_multicast_set_igmp_version(&br->multicast_ctx, igmp_version); if (err) return err; } #if IS_ENABLED(CONFIG_IPV6) if (data[IFLA_BR_MCAST_MLD_VERSION]) { __u8 mld_version; mld_version = nla_get_u8(data[IFLA_BR_MCAST_MLD_VERSION]); err = br_multicast_set_mld_version(&br->multicast_ctx, mld_version); if (err) return err; } #endif #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (data[IFLA_BR_NF_CALL_IPTABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IPTABLES]); br_opt_toggle(br, BROPT_NF_CALL_IPTABLES, !!val); } if (data[IFLA_BR_NF_CALL_IP6TABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IP6TABLES]); br_opt_toggle(br, BROPT_NF_CALL_IP6TABLES, !!val); } if (data[IFLA_BR_NF_CALL_ARPTABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_ARPTABLES]); br_opt_toggle(br, BROPT_NF_CALL_ARPTABLES, !!val); } #endif if (data[IFLA_BR_MULTI_BOOLOPT]) { struct br_boolopt_multi *bm; bm = nla_data(data[IFLA_BR_MULTI_BOOLOPT]); err = br_boolopt_multi_toggle(br, bm, extack); if (err) return err; } return 0; } static int br_dev_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); int err; err = register_netdevice(dev); if (err) return err; if (tb[IFLA_ADDRESS]) { spin_lock_bh(&br->lock); br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); spin_unlock_bh(&br->lock); } err = br_changelink(dev, tb, data, extack); if (err) br_dev_delete(dev, NULL); return err; } static size_t br_get_size(const struct net_device *brdev) { return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_HELLO_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MAX_AGE */ nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ nla_total_size(sizeof(u16)) + /* IFLA_BR_VLAN_DEFAULT_PVID */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_ENABLED */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_PER_PORT */ #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_STATS_ENABLED */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_LAST_MEMBER_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_MEMBERSHIP_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERIER_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_IGMP_VERSION */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_MLD_VERSION */ br_multicast_querier_state_size() + /* IFLA_BR_MCAST_QUERIER_STATE */ #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IP6TABLES */ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_ARPTABLES */ #endif nla_total_size(sizeof(struct br_boolopt_multi)) + /* IFLA_BR_MULTI_BOOLOPT */ 0; } static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) { struct net_bridge *br = netdev_priv(brdev); u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); u32 ageing_time = jiffies_to_clock_t(br->ageing_time); u32 stp_enabled = br->stp_enabled; u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; u8 vlan_enabled = br_vlan_enabled(br->dev); struct br_boolopt_multi bm; u64 clockval; clockval = br_timer_value(&br->hello_timer); if (nla_put_u64_64bit(skb, IFLA_BR_HELLO_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->tcn_timer); if (nla_put_u64_64bit(skb, IFLA_BR_TCN_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->topology_change_timer); if (nla_put_u64_64bit(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->gc_work.timer); if (nla_put_u64_64bit(skb, IFLA_BR_GC_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; br_boolopt_multi_get(br, &bm); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) || nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, br->group_fwd_mask) || nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(struct ifla_bridge_id), &br->bridge_id) || nla_put(skb, IFLA_BR_ROOT_ID, sizeof(struct ifla_bridge_id), &br->designated_root) || nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) || nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, br->topology_change_detected) || nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr) || nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto) || nla_put_u16(skb, IFLA_BR_VLAN_DEFAULT_PVID, br->default_pvid) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED, br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT, br_opt_get(br, BROPT_VLAN_STATS_PER_PORT))) return -EMSGSIZE; #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_ctx.multicast_router) || nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, br_opt_get(br, BROPT_MULTICAST_ENABLED)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_ctx.multicast_querier) || nla_put_u8(skb, IFLA_BR_MCAST_STATS_ENABLED, br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, RHT_ELASTICITY) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) || nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, br->multicast_ctx.multicast_last_member_count) || nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, br->multicast_ctx.multicast_startup_query_count) || nla_put_u8(skb, IFLA_BR_MCAST_IGMP_VERSION, br->multicast_ctx.multicast_igmp_version) || br_multicast_dump_querier_state(skb, &br->multicast_ctx, IFLA_BR_MCAST_QUERIER_STATE)) return -EMSGSIZE; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_BR_MCAST_MLD_VERSION, br->multicast_ctx.multicast_mld_version)) return -EMSGSIZE; #endif clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_last_member_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_membership_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_MEMBERSHIP_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_querier_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERIER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_response_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_startup_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_u8(skb, IFLA_BR_NF_CALL_IPTABLES, br_opt_get(br, BROPT_NF_CALL_IPTABLES) ? 1 : 0) || nla_put_u8(skb, IFLA_BR_NF_CALL_IP6TABLES, br_opt_get(br, BROPT_NF_CALL_IP6TABLES) ? 1 : 0) || nla_put_u8(skb, IFLA_BR_NF_CALL_ARPTABLES, br_opt_get(br, BROPT_NF_CALL_ARPTABLES) ? 1 : 0)) return -EMSGSIZE; #endif return 0; } static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) { struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge *br; int numvls = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: br = netdev_priv(dev); vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: p = br_port_get_rtnl(dev); if (!p) return 0; vg = nbp_vlan_group(p); break; default: return 0; } if (vg) { /* we need to count all, even placeholder entries */ list_for_each_entry(v, &vg->vlan_list, vlist) numvls++; } return numvls * nla_total_size(sizeof(struct bridge_vlan_xstats)) + nla_total_size_64bit(sizeof(struct br_mcast_stats)) + (p ? nla_total_size_64bit(sizeof(p->stp_xstats)) : 0) + nla_total_size(0); } static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr) { struct nlattr *nla __maybe_unused; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge *br; struct nlattr *nest; int vl_idx = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: br = netdev_priv(dev); vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: p = br_port_get_rtnl(dev); if (!p) return 0; br = p->br; vg = nbp_vlan_group(p); break; default: return -EINVAL; } nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BRIDGE); if (!nest) return -EMSGSIZE; if (vg) { u16 pvid; pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { struct bridge_vlan_xstats vxi; struct pcpu_sw_netstats stats; if (++vl_idx < *prividx) continue; memset(&vxi, 0, sizeof(vxi)); vxi.vid = v->vid; vxi.flags = v->flags; if (v->vid == pvid) vxi.flags |= BRIDGE_VLAN_INFO_PVID; br_vlan_get_stats(v, &stats); vxi.rx_bytes = stats.rx_bytes; vxi.rx_packets = stats.rx_packets; vxi.tx_bytes = stats.tx_bytes; vxi.tx_packets = stats.tx_packets; if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi)) goto nla_put_failure; } } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (++vl_idx >= *prividx) { nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST, sizeof(struct br_mcast_stats), BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; br_multicast_get_stats(br, p, nla_data(nla)); } #endif if (p) { nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_STP, sizeof(p->stp_xstats), BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; spin_lock_bh(&br->lock); memcpy(nla_data(nla), &p->stp_xstats, sizeof(p->stp_xstats)); spin_unlock_bh(&br->lock); } nla_nest_end(skb, nest); *prividx = 0; return 0; nla_put_failure: nla_nest_end(skb, nest); *prividx = vl_idx; return -EMSGSIZE; } static struct rtnl_af_ops br_af_ops __read_mostly = { .family = AF_BRIDGE, .get_link_af_size = br_get_link_af_size_filtered, }; struct rtnl_link_ops br_link_ops __read_mostly = { .kind = "bridge", .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .maxtype = IFLA_BR_MAX, .policy = br_policy, .validate = br_validate, .newlink = br_dev_newlink, .changelink = br_changelink, .dellink = br_dev_delete, .get_size = br_get_size, .fill_info = br_fill_info, .fill_linkxstats = br_fill_linkxstats, .get_linkxstats_size = br_get_linkxstats_size, .slave_maxtype = IFLA_BRPORT_MAX, .slave_policy = br_port_policy, .slave_changelink = br_port_slave_changelink, .get_slave_size = br_port_get_slave_size, .fill_slave_info = br_port_fill_slave_info, }; int __init br_netlink_init(void) { int err; br_mdb_init(); br_vlan_rtnl_init(); rtnl_af_register(&br_af_ops); err = rtnl_link_register(&br_link_ops); if (err) goto out_af; return 0; out_af: rtnl_af_unregister(&br_af_ops); br_mdb_uninit(); return err; } void br_netlink_fini(void) { br_mdb_uninit(); br_vlan_rtnl_uninit(); rtnl_af_unregister(&br_af_ops); rtnl_link_unregister(&br_link_ops); } |
| 6 4 72 72 10 10 10 9 1 10 6 2 2 3 1 4 4 4 2 16 3 4 2 1 9 2 7 1 34 8 2 2 9 10 1 2 97 50 44 14 14 1 13 13 13 3 3 3 3 8 8 8 8 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/dccp/proto.c * * An implementation of the DCCP protocol * Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #include <linux/dccp.h> #include <linux/module.h> #include <linux/types.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/random.h> #include <linux/slab.h> #include <net/checksum.h> #include <net/inet_sock.h> #include <net/inet_common.h> #include <net/sock.h> #include <net/xfrm.h> #include <asm/ioctls.h> #include <linux/spinlock.h> #include <linux/timer.h> #include <linux/delay.h> #include <linux/poll.h> #include "ccid.h" #include "dccp.h" #include "feat.h" #define CREATE_TRACE_POINTS #include "trace.h" DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; EXPORT_SYMBOL_GPL(dccp_statistics); DEFINE_PER_CPU(unsigned int, dccp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(dccp_orphan_count); struct inet_hashinfo dccp_hashinfo; EXPORT_SYMBOL_GPL(dccp_hashinfo); /* the maximum queue length for tx in packets. 0 is no limit */ int sysctl_dccp_tx_qlen __read_mostly = 5; #ifdef CONFIG_IP_DCCP_DEBUG static const char *dccp_state_name(const int state) { static const char *const dccp_state_names[] = { [DCCP_OPEN] = "OPEN", [DCCP_REQUESTING] = "REQUESTING", [DCCP_PARTOPEN] = "PARTOPEN", [DCCP_LISTEN] = "LISTEN", [DCCP_RESPOND] = "RESPOND", [DCCP_CLOSING] = "CLOSING", [DCCP_ACTIVE_CLOSEREQ] = "CLOSEREQ", [DCCP_PASSIVE_CLOSE] = "PASSIVE_CLOSE", [DCCP_PASSIVE_CLOSEREQ] = "PASSIVE_CLOSEREQ", [DCCP_TIME_WAIT] = "TIME_WAIT", [DCCP_CLOSED] = "CLOSED", }; if (state >= DCCP_MAX_STATES) return "INVALID STATE!"; else return dccp_state_names[state]; } #endif void dccp_set_state(struct sock *sk, const int state) { const int oldstate = sk->sk_state; dccp_pr_debug("%s(%p) %s --> %s\n", dccp_role(sk), sk, dccp_state_name(oldstate), dccp_state_name(state)); WARN_ON(state == oldstate); switch (state) { case DCCP_OPEN: if (oldstate != DCCP_OPEN) DCCP_INC_STATS(DCCP_MIB_CURRESTAB); /* Client retransmits all Confirm options until entering OPEN */ if (oldstate == DCCP_PARTOPEN) dccp_feat_list_purge(&dccp_sk(sk)->dccps_featneg); break; case DCCP_CLOSED: if (oldstate == DCCP_OPEN || oldstate == DCCP_ACTIVE_CLOSEREQ || oldstate == DCCP_CLOSING) DCCP_INC_STATS(DCCP_MIB_ESTABRESETS); sk->sk_prot->unhash(sk); if (inet_csk(sk)->icsk_bind_hash != NULL && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); fallthrough; default: if (oldstate == DCCP_OPEN) DCCP_DEC_STATS(DCCP_MIB_CURRESTAB); } /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ inet_sk_set_state(sk, state); } EXPORT_SYMBOL_GPL(dccp_set_state); static void dccp_finish_passive_close(struct sock *sk) { switch (sk->sk_state) { case DCCP_PASSIVE_CLOSE: /* Node (client or server) has received Close packet. */ dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED); dccp_set_state(sk, DCCP_CLOSED); break; case DCCP_PASSIVE_CLOSEREQ: /* * Client received CloseReq. We set the `active' flag so that * dccp_send_close() retransmits the Close as per RFC 4340, 8.3. */ dccp_send_close(sk, 1); dccp_set_state(sk, DCCP_CLOSING); } } void dccp_done(struct sock *sk) { dccp_set_state(sk, DCCP_CLOSED); dccp_clear_xmit_timers(sk); sk->sk_shutdown = SHUTDOWN_MASK; if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); else inet_csk_destroy_sock(sk); } EXPORT_SYMBOL_GPL(dccp_done); const char *dccp_packet_name(const int type) { static const char *const dccp_packet_names[] = { [DCCP_PKT_REQUEST] = "REQUEST", [DCCP_PKT_RESPONSE] = "RESPONSE", [DCCP_PKT_DATA] = "DATA", [DCCP_PKT_ACK] = "ACK", [DCCP_PKT_DATAACK] = "DATAACK", [DCCP_PKT_CLOSEREQ] = "CLOSEREQ", [DCCP_PKT_CLOSE] = "CLOSE", [DCCP_PKT_RESET] = "RESET", [DCCP_PKT_SYNC] = "SYNC", [DCCP_PKT_SYNCACK] = "SYNCACK", }; if (type >= DCCP_NR_PKT_TYPES) return "INVALID"; else return dccp_packet_names[type]; } EXPORT_SYMBOL_GPL(dccp_packet_name); void dccp_destruct_common(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); dp->dccps_hc_tx_ccid = NULL; } EXPORT_SYMBOL_GPL(dccp_destruct_common); static void dccp_sk_destruct(struct sock *sk) { dccp_destruct_common(sk); inet_sock_destruct(sk); } int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) { struct dccp_sock *dp = dccp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_rto = DCCP_TIMEOUT_INIT; icsk->icsk_syn_retries = sysctl_dccp_request_retries; sk->sk_state = DCCP_CLOSED; sk->sk_write_space = dccp_write_space; sk->sk_destruct = dccp_sk_destruct; icsk->icsk_sync_mss = dccp_sync_mss; dp->dccps_mss_cache = 536; dp->dccps_rate_last = jiffies; dp->dccps_role = DCCP_ROLE_UNDEFINED; dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT; dp->dccps_tx_qlen = sysctl_dccp_tx_qlen; dccp_init_xmit_timers(sk); INIT_LIST_HEAD(&dp->dccps_featneg); /* control socket doesn't need feat nego */ if (likely(ctl_sock_initialized)) return dccp_feat_init(sk); return 0; } EXPORT_SYMBOL_GPL(dccp_init_sock); void dccp_destroy_sock(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); __skb_queue_purge(&sk->sk_write_queue); if (sk->sk_send_head != NULL) { kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; } /* Clean up a referenced DCCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash != NULL) inet_put_port(sk); kfree(dp->dccps_service_list); dp->dccps_service_list = NULL; if (dp->dccps_hc_rx_ackvec != NULL) { dccp_ackvec_free(dp->dccps_hc_rx_ackvec); dp->dccps_hc_rx_ackvec = NULL; } ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); dp->dccps_hc_rx_ccid = NULL; /* clean up feature negotiation state */ dccp_feat_list_purge(&dp->dccps_featneg); } EXPORT_SYMBOL_GPL(dccp_destroy_sock); static inline int dccp_listen_start(struct sock *sk, int backlog) { struct dccp_sock *dp = dccp_sk(sk); dp->dccps_role = DCCP_ROLE_LISTEN; /* do not start to listen if feature negotiation setup fails */ if (dccp_feat_finalise_settings(dp)) return -EPROTO; return inet_csk_listen_start(sk, backlog); } static inline int dccp_need_reset(int state) { return state != DCCP_CLOSED && state != DCCP_LISTEN && state != DCCP_REQUESTING; } int dccp_disconnect(struct sock *sk, int flags) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); const int old_state = sk->sk_state; if (old_state != DCCP_CLOSED) dccp_set_state(sk, DCCP_CLOSED); /* * This corresponds to the ABORT function of RFC793, sec. 3.8 * TCP uses a RST segment, DCCP a Reset packet with Code 2, "Aborted". */ if (old_state == DCCP_LISTEN) { inet_csk_listen_stop(sk); } else if (dccp_need_reset(old_state)) { dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); sk->sk_err = ECONNRESET; } else if (old_state == DCCP_REQUESTING) sk->sk_err = ECONNRESET; dccp_clear_xmit_timers(sk); ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); dp->dccps_hc_rx_ccid = NULL; __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_write_queue); if (sk->sk_send_head != NULL) { __kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; } inet->inet_dport = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); icsk->icsk_backoff = 0; inet_csk_delack_init(sk); __sk_dst_reset(sk); WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); sk_error_report(sk); return 0; } EXPORT_SYMBOL_GPL(dccp_disconnect); /* * Wait for a DCCP event. * * Note that we don't need to lock the socket, as the upper poll layers * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ __poll_t dccp_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; __poll_t mask; u8 shutdown; int state; sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); if (state == DCCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events by poll logic and correct handling of state changes made by another threads is impossible in any case. */ mask = 0; if (READ_ONCE(sk->sk_err)) mask = EPOLLERR; shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected? */ if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { if (atomic_read(&sk->sk_rmem_alloc) > 0) mask |= EPOLLIN | EPOLLRDNORM; if (!(shutdown & SEND_SHUTDOWN)) { if (sk_stream_is_writeable(sk)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after * wspace test but before the flags are set, * IO signal will be lost. */ if (sk_stream_is_writeable(sk)) mask |= EPOLLOUT | EPOLLWRNORM; } } } return mask; } EXPORT_SYMBOL_GPL(dccp_poll); int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) { int rc = -ENOTCONN; lock_sock(sk); if (sk->sk_state == DCCP_LISTEN) goto out; switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); /* Using sk_wmem_alloc here because sk_wmem_queued is not used by DCCP and * always 0, comparably to UDP. */ rc = put_user(amount, (int __user *)arg); } break; case SIOCINQ: { struct sk_buff *skb; unsigned long amount = 0; skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) { /* * We will only return the amount of this packet since * that is all that will be read. */ amount = skb->len; } rc = put_user(amount, (int __user *)arg); } break; default: rc = -ENOIOCTLCMD; break; } out: release_sock(sk); return rc; } EXPORT_SYMBOL_GPL(dccp_ioctl); static int dccp_setsockopt_service(struct sock *sk, const __be32 service, sockptr_t optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_service_list *sl = NULL; if (service == DCCP_SERVICE_INVALID_VALUE || optlen > DCCP_SERVICE_LIST_MAX_LEN * sizeof(u32)) return -EINVAL; if (optlen > sizeof(service)) { sl = kmalloc(optlen, GFP_KERNEL); if (sl == NULL) return -ENOMEM; sl->dccpsl_nr = optlen / sizeof(u32) - 1; if (copy_from_sockptr_offset(sl->dccpsl_list, optval, sizeof(service), optlen - sizeof(service)) || dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) { kfree(sl); return -EFAULT; } } lock_sock(sk); dp->dccps_service = service; kfree(dp->dccps_service_list); dp->dccps_service_list = sl; release_sock(sk); return 0; } static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx) { u8 *list, len; int i, rc; if (cscov < 0 || cscov > 15) return -EINVAL; /* * Populate a list of permissible values, in the range cscov...15. This * is necessary since feature negotiation of single values only works if * both sides incidentally choose the same value. Since the list starts * lowest-value first, negotiation will pick the smallest shared value. */ if (cscov == 0) return 0; len = 16 - cscov; list = kmalloc(len, GFP_KERNEL); if (list == NULL) return -ENOBUFS; for (i = 0; i < len; i++) list[i] = cscov++; rc = dccp_feat_register_sp(sk, DCCPF_MIN_CSUM_COVER, rx, list, len); if (rc == 0) { if (rx) dccp_sk(sk)->dccps_pcrlen = cscov; else dccp_sk(sk)->dccps_pcslen = cscov; } kfree(list); return rc; } static int dccp_setsockopt_ccid(struct sock *sk, int type, sockptr_t optval, unsigned int optlen) { u8 *val; int rc = 0; if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS) return -EINVAL; val = memdup_sockptr(optval, optlen); if (IS_ERR(val)) return PTR_ERR(val); lock_sock(sk); if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID) rc = dccp_feat_register_sp(sk, DCCPF_CCID, 1, val, optlen); if (!rc && (type == DCCP_SOCKOPT_RX_CCID || type == DCCP_SOCKOPT_CCID)) rc = dccp_feat_register_sp(sk, DCCPF_CCID, 0, val, optlen); release_sock(sk); kfree(val); return rc; } static int do_dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); int val, err = 0; switch (optname) { case DCCP_SOCKOPT_PACKET_SIZE: DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n"); return 0; case DCCP_SOCKOPT_CHANGE_L: case DCCP_SOCKOPT_CHANGE_R: DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n"); return 0; case DCCP_SOCKOPT_CCID: case DCCP_SOCKOPT_RX_CCID: case DCCP_SOCKOPT_TX_CCID: return dccp_setsockopt_ccid(sk, optname, optval, optlen); } if (optlen < (int)sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; if (optname == DCCP_SOCKOPT_SERVICE) return dccp_setsockopt_service(sk, val, optval, optlen); lock_sock(sk); switch (optname) { case DCCP_SOCKOPT_SERVER_TIMEWAIT: if (dp->dccps_role != DCCP_ROLE_SERVER) err = -EOPNOTSUPP; else dp->dccps_server_timewait = (val != 0); break; case DCCP_SOCKOPT_SEND_CSCOV: err = dccp_setsockopt_cscov(sk, val, false); break; case DCCP_SOCKOPT_RECV_CSCOV: err = dccp_setsockopt_cscov(sk, val, true); break; case DCCP_SOCKOPT_QPOLICY_ID: if (sk->sk_state != DCCP_CLOSED) err = -EISCONN; else if (val < 0 || val >= DCCPQ_POLICY_MAX) err = -EINVAL; else dp->dccps_qpolicy = val; break; case DCCP_SOCKOPT_QPOLICY_TXQLEN: if (val < 0) err = -EINVAL; else dp->dccps_tx_qlen = val; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } int dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, optname, optval, optlen); return do_dccp_setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL_GPL(dccp_setsockopt); static int dccp_getsockopt_service(struct sock *sk, int len, __be32 __user *optval, int __user *optlen) { const struct dccp_sock *dp = dccp_sk(sk); const struct dccp_service_list *sl; int err = -ENOENT, slen = 0, total_len = sizeof(u32); lock_sock(sk); if ((sl = dp->dccps_service_list) != NULL) { slen = sl->dccpsl_nr * sizeof(u32); total_len += slen; } err = -EINVAL; if (total_len > len) goto out; err = 0; if (put_user(total_len, optlen) || put_user(dp->dccps_service, optval) || (sl != NULL && copy_to_user(optval + 1, sl->dccpsl_list, slen))) err = -EFAULT; out: release_sock(sk); return err; } static int do_dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct dccp_sock *dp; int val, len; if (get_user(len, optlen)) return -EFAULT; if (len < (int)sizeof(int)) return -EINVAL; dp = dccp_sk(sk); switch (optname) { case DCCP_SOCKOPT_PACKET_SIZE: DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n"); return 0; case DCCP_SOCKOPT_SERVICE: return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); case DCCP_SOCKOPT_TX_CCID: val = ccid_get_current_tx_ccid(dp); if (val < 0) return -ENOPROTOOPT; break; case DCCP_SOCKOPT_RX_CCID: val = ccid_get_current_rx_ccid(dp); if (val < 0) return -ENOPROTOOPT; break; case DCCP_SOCKOPT_SERVER_TIMEWAIT: val = dp->dccps_server_timewait; break; case DCCP_SOCKOPT_SEND_CSCOV: val = dp->dccps_pcslen; break; case DCCP_SOCKOPT_RECV_CSCOV: val = dp->dccps_pcrlen; break; case DCCP_SOCKOPT_QPOLICY_ID: val = dp->dccps_qpolicy; break; case DCCP_SOCKOPT_QPOLICY_TXQLEN: val = dp->dccps_tx_qlen; break; case 128 ... 191: return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname, len, (u32 __user *)optval, optlen); case 192 ... 255: return ccid_hc_tx_getsockopt(dp->dccps_hc_tx_ccid, sk, optname, len, (u32 __user *)optval, optlen); default: return -ENOPROTOOPT; } len = sizeof(val); if (put_user(len, optlen) || copy_to_user(optval, &val, len)) return -EFAULT; return 0; } int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level, optname, optval, optlen); return do_dccp_getsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL_GPL(dccp_getsockopt); static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb) { struct cmsghdr *cmsg; /* * Assign an (opaque) qpolicy priority value to skb->priority. * * We are overloading this skb field for use with the qpolicy subystem. * The skb->priority is normally used for the SO_PRIORITY option, which * is initialised from sk_priority. Since the assignment of sk_priority * to skb->priority happens later (on layer 3), we overload this field * for use with queueing priorities as long as the skb is on layer 4. * The default priority value (if nothing is set) is 0. */ skb->priority = 0; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_DCCP) continue; if (cmsg->cmsg_type <= DCCP_SCM_QPOLICY_MAX && !dccp_qpolicy_param_ok(skb->sk, cmsg->cmsg_type)) return -EINVAL; switch (cmsg->cmsg_type) { case DCCP_SCM_PRIORITY: if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u32))) return -EINVAL; skb->priority = *(__u32 *)CMSG_DATA(cmsg); break; default: return -EINVAL; } } return 0; } int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { const struct dccp_sock *dp = dccp_sk(sk); const int flags = msg->msg_flags; const int noblock = flags & MSG_DONTWAIT; struct sk_buff *skb; int rc, size; long timeo; trace_dccp_probe(sk, len); if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); timeo = sock_sndtimeo(sk, noblock); /* * We have to use sk_stream_wait_connect here to set sk_write_pending, * so that the trick in dccp_rcv_request_sent_state_process. */ /* Wait for a connection to finish. */ if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN)) if ((rc = sk_stream_wait_connect(sk, &timeo)) != 0) goto out_release; size = sk->sk_prot->max_header + len; release_sock(sk); skb = sock_alloc_send_skb(sk, size, noblock, &rc); lock_sock(sk); if (skb == NULL) goto out_release; if (dccp_qpolicy_full(sk)) { rc = -EAGAIN; goto out_discard; } if (sk->sk_state == DCCP_CLOSED) { rc = -ENOTCONN; goto out_discard; } /* We need to check dccps_mss_cache after socket is locked. */ if (len > dp->dccps_mss_cache) { rc = -EMSGSIZE; goto out_discard; } skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) goto out_discard; rc = dccp_msghdr_parse(msg, skb); if (rc != 0) goto out_discard; dccp_qpolicy_push(sk, skb); /* * The xmit_timer is set if the TX CCID is rate-based and will expire * when congestion control permits to release further packets into the * network. Window-based CCIDs do not use this timer. */ if (!timer_pending(&dp->dccps_xmit_timer)) dccp_write_xmit(sk); out_release: release_sock(sk); return rc ? : len; out_discard: kfree_skb(skb); goto out_release; } EXPORT_SYMBOL_GPL(dccp_sendmsg); int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { const struct dccp_hdr *dh; long timeo; lock_sock(sk); if (sk->sk_state == DCCP_LISTEN) { len = -ENOTCONN; goto out; } timeo = sock_rcvtimeo(sk, nonblock); do { struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); if (skb == NULL) goto verify_sock_status; dh = dccp_hdr(skb); switch (dh->dccph_type) { case DCCP_PKT_DATA: case DCCP_PKT_DATAACK: goto found_ok_skb; case DCCP_PKT_CLOSE: case DCCP_PKT_CLOSEREQ: if (!(flags & MSG_PEEK)) dccp_finish_passive_close(sk); fallthrough; case DCCP_PKT_RESET: dccp_pr_debug("found fin (%s) ok!\n", dccp_packet_name(dh->dccph_type)); len = 0; goto found_fin_ok; default: dccp_pr_debug("packet_type=%s\n", dccp_packet_name(dh->dccph_type)); sk_eat_skb(sk, skb); } verify_sock_status: if (sock_flag(sk, SOCK_DONE)) { len = 0; break; } if (sk->sk_err) { len = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) { len = 0; break; } if (sk->sk_state == DCCP_CLOSED) { if (!sock_flag(sk, SOCK_DONE)) { /* This occurs when user tries to read * from never connected socket. */ len = -ENOTCONN; break; } len = 0; break; } if (!timeo) { len = -EAGAIN; break; } if (signal_pending(current)) { len = sock_intr_errno(timeo); break; } sk_wait_data(sk, &timeo, NULL); continue; found_ok_skb: if (len > skb->len) len = skb->len; else if (len < skb->len) msg->msg_flags |= MSG_TRUNC; if (skb_copy_datagram_msg(skb, 0, msg, len)) { /* Exception. Bailout! */ len = -EFAULT; break; } if (flags & MSG_TRUNC) len = skb->len; found_fin_ok: if (!(flags & MSG_PEEK)) sk_eat_skb(sk, skb); break; } while (1); out: release_sock(sk); return len; } EXPORT_SYMBOL_GPL(dccp_recvmsg); int inet_dccp_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; int err; lock_sock(sk); err = -EINVAL; if (sock->state != SS_UNCONNECTED || sock->type != SOCK_DCCP) goto out; old_state = sk->sk_state; if (!((1 << old_state) & (DCCPF_CLOSED | DCCPF_LISTEN))) goto out; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ if (old_state != DCCP_LISTEN) { /* * FIXME: here it probably should be sk->sk_prot->listen_start * see tcp_listen_start */ err = dccp_listen_start(sk, backlog); if (err) goto out; } err = 0; out: release_sock(sk); return err; } EXPORT_SYMBOL_GPL(inet_dccp_listen); static void dccp_terminate_connection(struct sock *sk) { u8 next_state = DCCP_CLOSED; switch (sk->sk_state) { case DCCP_PASSIVE_CLOSE: case DCCP_PASSIVE_CLOSEREQ: dccp_finish_passive_close(sk); break; case DCCP_PARTOPEN: dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); fallthrough; case DCCP_OPEN: dccp_send_close(sk, 1); if (dccp_sk(sk)->dccps_role == DCCP_ROLE_SERVER && !dccp_sk(sk)->dccps_server_timewait) next_state = DCCP_ACTIVE_CLOSEREQ; else next_state = DCCP_CLOSING; fallthrough; default: dccp_set_state(sk, next_state); } } void dccp_close(struct sock *sk, long timeout) { struct dccp_sock *dp = dccp_sk(sk); struct sk_buff *skb; u32 data_was_unread = 0; int state; lock_sock(sk); sk->sk_shutdown = SHUTDOWN_MASK; if (sk->sk_state == DCCP_LISTEN) { dccp_set_state(sk, DCCP_CLOSED); /* Special case. */ inet_csk_listen_stop(sk); goto adjudge_to_death; } sk_stop_timer(sk, &dp->dccps_xmit_timer); /* * We need to flush the recv. buffs. We do this only on the * descriptor close, not protocol-sourced closes, because the *reader process may not have drained the data yet! */ while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { data_was_unread += skb->len; __kfree_skb(skb); } /* If socket has been already reset kill it. */ if (sk->sk_state == DCCP_CLOSED) goto adjudge_to_death; if (data_was_unread) { /* Unread data was tossed, send an appropriate Reset Code */ DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_set_state(sk, DCCP_CLOSED); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); } else if (sk->sk_state != DCCP_CLOSED) { /* * Normal connection termination. May need to wait if there are * still packets in the TX queue that are delayed by the CCID. */ dccp_flush_write_queue(sk, &timeout); dccp_terminate_connection(sk); } /* * Flush write queue. This may be necessary in several cases: * - we have been closed by the peer but still have application data; * - abortive termination (unread data or zero linger time), * - normal termination but queue could not be flushed within time limit */ __skb_queue_purge(&sk->sk_write_queue); sk_stream_wait_close(sk, timeout); adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); /* * It is the last release_sock in its life. It will remove backlog. */ release_sock(sk); /* * Now socket is owned by kernel and we acquire BH lock * to finish close. No need to check for user refs. */ local_bh_disable(); bh_lock_sock(sk); WARN_ON(sock_owned_by_user(sk)); this_cpu_inc(dccp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED) goto out; if (sk->sk_state == DCCP_CLOSED) inet_csk_destroy_sock(sk); /* Otherwise, socket is reprieved until protocol close. */ out: bh_unlock_sock(sk); local_bh_enable(); sock_put(sk); } EXPORT_SYMBOL_GPL(dccp_close); void dccp_shutdown(struct sock *sk, int how) { dccp_pr_debug("called shutdown(%x)\n", how); } EXPORT_SYMBOL_GPL(dccp_shutdown); static inline int __init dccp_mib_init(void) { dccp_statistics = alloc_percpu(struct dccp_mib); if (!dccp_statistics) return -ENOMEM; return 0; } static inline void dccp_mib_exit(void) { free_percpu(dccp_statistics); } static int thash_entries; module_param(thash_entries, int, 0444); MODULE_PARM_DESC(thash_entries, "Number of ehash buckets"); #ifdef CONFIG_IP_DCCP_DEBUG bool dccp_debug; module_param(dccp_debug, bool, 0644); MODULE_PARM_DESC(dccp_debug, "Enable debug messages"); EXPORT_SYMBOL_GPL(dccp_debug); #endif static int __init dccp_init(void) { unsigned long goal; unsigned long nr_pages = totalram_pages(); int ehash_order, bhash_order, i; int rc; BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > sizeof_field(struct sk_buff, cb)); rc = inet_hashinfo2_init_mod(&dccp_hashinfo); if (rc) goto out_fail; rc = -ENOBUFS; dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!dccp_hashinfo.bind_bucket_cachep) goto out_free_hashinfo2; /* * Size and allocate the main established and bind bucket * hash tables. * * The methodology is similar to that of the buffer cache. */ if (nr_pages >= (128 * 1024)) goal = nr_pages >> (21 - PAGE_SHIFT); else goal = nr_pages >> (23 - PAGE_SHIFT); if (thash_entries) goal = (thash_entries * sizeof(struct inet_ehash_bucket)) >> PAGE_SHIFT; for (ehash_order = 0; (1UL << ehash_order) < goal; ehash_order++) ; do { unsigned long hash_size = (1UL << ehash_order) * PAGE_SIZE / sizeof(struct inet_ehash_bucket); while (hash_size & (hash_size - 1)) hash_size--; dccp_hashinfo.ehash_mask = hash_size - 1; dccp_hashinfo.ehash = (struct inet_ehash_bucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, ehash_order); } while (!dccp_hashinfo.ehash && --ehash_order > 0); if (!dccp_hashinfo.ehash) { DCCP_CRIT("Failed to allocate DCCP established hash table"); goto out_free_bind_bucket_cachep; } for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i); if (inet_ehash_locks_alloc(&dccp_hashinfo)) goto out_free_dccp_ehash; bhash_order = ehash_order; do { dccp_hashinfo.bhash_size = (1UL << bhash_order) * PAGE_SIZE / sizeof(struct inet_bind_hashbucket); if ((dccp_hashinfo.bhash_size > (64 * 1024)) && bhash_order > 0) continue; dccp_hashinfo.bhash = (struct inet_bind_hashbucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, bhash_order); } while (!dccp_hashinfo.bhash && --bhash_order >= 0); if (!dccp_hashinfo.bhash) { DCCP_CRIT("Failed to allocate DCCP bind hash table"); goto out_free_dccp_locks; } for (i = 0; i < dccp_hashinfo.bhash_size; i++) { spin_lock_init(&dccp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain); } rc = dccp_mib_init(); if (rc) goto out_free_dccp_bhash; rc = dccp_ackvec_init(); if (rc) goto out_free_dccp_mib; rc = dccp_sysctl_init(); if (rc) goto out_ackvec_exit; rc = ccid_initialize_builtins(); if (rc) goto out_sysctl_exit; dccp_timestamping_init(); return 0; out_sysctl_exit: dccp_sysctl_exit(); out_ackvec_exit: dccp_ackvec_exit(); out_free_dccp_mib: dccp_mib_exit(); out_free_dccp_bhash: free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); out_free_dccp_locks: inet_ehash_locks_free(&dccp_hashinfo); out_free_dccp_ehash: free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order); out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); out_free_hashinfo2: inet_hashinfo2_free_mod(&dccp_hashinfo); out_fail: dccp_hashinfo.bhash = NULL; dccp_hashinfo.ehash = NULL; dccp_hashinfo.bind_bucket_cachep = NULL; return rc; } static void __exit dccp_fini(void) { ccid_cleanup_builtins(); dccp_mib_exit(); free_pages((unsigned long)dccp_hashinfo.bhash, get_order(dccp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket))); free_pages((unsigned long)dccp_hashinfo.ehash, get_order((dccp_hashinfo.ehash_mask + 1) * sizeof(struct inet_ehash_bucket))); inet_ehash_locks_free(&dccp_hashinfo); kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_ackvec_exit(); dccp_sysctl_exit(); inet_hashinfo2_free_mod(&dccp_hashinfo); } module_init(dccp_init); module_exit(dccp_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@conectiva.com.br>"); MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol"); |
| 5 5 131 1 1 4 4 22 22 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 */ #ifndef __BEN_VLAN_802_1Q_INC__ #define __BEN_VLAN_802_1Q_INC__ #include <linux/if_vlan.h> #include <linux/u64_stats_sync.h> #include <linux/list.h> /* if this changes, algorithm will have to be reworked because this * depends on completely exhausting the VLAN identifier space. Thus * it gives constant time look-up, but in many cases it wastes memory. */ #define VLAN_GROUP_ARRAY_SPLIT_PARTS 8 #define VLAN_GROUP_ARRAY_PART_LEN (VLAN_N_VID/VLAN_GROUP_ARRAY_SPLIT_PARTS) enum vlan_protos { VLAN_PROTO_8021Q = 0, VLAN_PROTO_8021AD, VLAN_PROTO_NUM, }; struct vlan_group { unsigned int nr_vlan_devs; struct hlist_node hlist; /* linked list */ struct net_device **vlan_devices_arrays[VLAN_PROTO_NUM] [VLAN_GROUP_ARRAY_SPLIT_PARTS]; }; struct vlan_info { struct net_device *real_dev; /* The ethernet(like) device * the vlan is attached to. */ struct vlan_group grp; struct list_head vid_list; unsigned int nr_vids; struct rcu_head rcu; }; static inline int vlan_proto_idx(__be16 proto) { switch (proto) { case htons(ETH_P_8021Q): return VLAN_PROTO_8021Q; case htons(ETH_P_8021AD): return VLAN_PROTO_8021AD; default: WARN(1, "invalid VLAN protocol: 0x%04x\n", ntohs(proto)); return -EINVAL; } } static inline struct net_device *__vlan_group_get_device(struct vlan_group *vg, unsigned int pidx, u16 vlan_id) { struct net_device **array; array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; /* paired with smp_wmb() in vlan_group_prealloc_vid() */ smp_rmb(); return array ? array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] : NULL; } static inline struct net_device *vlan_group_get_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { int pidx = vlan_proto_idx(vlan_proto); if (pidx < 0) return NULL; return __vlan_group_get_device(vg, pidx, vlan_id); } static inline void vlan_group_set_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id, struct net_device *dev) { int pidx = vlan_proto_idx(vlan_proto); struct net_device **array; if (!vg || pidx < 0) return; array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev; } /* Must be invoked with rcu_read_lock or with RTNL. */ static inline struct net_device *vlan_find_dev(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info); if (vlan_info) return vlan_group_get_device(&vlan_info->grp, vlan_proto, vlan_id); return NULL; } static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev) { netdev_features_t ret; ret = real_dev->hw_enc_features & (NETIF_F_CSUM_MASK | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL); if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK)) return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM; return 0; } #define vlan_group_for_each_dev(grp, i, dev) \ for ((i) = 0; i < VLAN_PROTO_NUM * VLAN_N_VID; i++) \ if (((dev) = __vlan_group_get_device((grp), (i) / VLAN_N_VID, \ (i) % VLAN_N_VID))) int vlan_filter_push_vids(struct vlan_info *vlan_info, __be16 proto); void vlan_filter_drop_vids(struct vlan_info *vlan_info, __be16 proto); /* found in vlan_dev.c */ void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); void vlan_dev_free_egress_priority(const struct net_device *dev); int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask); void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size); int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, struct netlink_ext_ack *extack); void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); static inline u32 vlan_get_ingress_priority(struct net_device *dev, u16 vlan_tci) { struct vlan_dev_priv *vip = vlan_dev_priv(dev); return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7]; } #ifdef CONFIG_VLAN_8021Q_GVRP int vlan_gvrp_request_join(const struct net_device *dev); void vlan_gvrp_request_leave(const struct net_device *dev); int vlan_gvrp_init_applicant(struct net_device *dev); void vlan_gvrp_uninit_applicant(struct net_device *dev); int vlan_gvrp_init(void); void vlan_gvrp_uninit(void); #else static inline int vlan_gvrp_request_join(const struct net_device *dev) { return 0; } static inline void vlan_gvrp_request_leave(const struct net_device *dev) {} static inline int vlan_gvrp_init_applicant(struct net_device *dev) { return 0; } static inline void vlan_gvrp_uninit_applicant(struct net_device *dev) {} static inline int vlan_gvrp_init(void) { return 0; } static inline void vlan_gvrp_uninit(void) {} #endif #ifdef CONFIG_VLAN_8021Q_MVRP int vlan_mvrp_request_join(const struct net_device *dev); void vlan_mvrp_request_leave(const struct net_device *dev); int vlan_mvrp_init_applicant(struct net_device *dev); void vlan_mvrp_uninit_applicant(struct net_device *dev); int vlan_mvrp_init(void); void vlan_mvrp_uninit(void); #else static inline int vlan_mvrp_request_join(const struct net_device *dev) { return 0; } static inline void vlan_mvrp_request_leave(const struct net_device *dev) {} static inline int vlan_mvrp_init_applicant(struct net_device *dev) { return 0; } static inline void vlan_mvrp_uninit_applicant(struct net_device *dev) {} static inline int vlan_mvrp_init(void) { return 0; } static inline void vlan_mvrp_uninit(void) {} #endif extern const char vlan_fullname[]; extern const char vlan_version[]; int vlan_netlink_init(void); void vlan_netlink_fini(void); extern struct rtnl_link_ops vlan_link_ops; extern unsigned int vlan_net_id; struct proc_dir_entry; struct vlan_net { /* /proc/net/vlan */ struct proc_dir_entry *proc_vlan_dir; /* /proc/net/vlan/config */ struct proc_dir_entry *proc_vlan_conf; /* Determines interface naming scheme. */ unsigned short name_type; }; #endif /* !(__BEN_VLAN_802_1Q_INC__) */ |
| 10 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Cryptographic API. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_H #define _CRYPTO_INTERNAL_H #include <crypto/algapi.h> #include <linux/completion.h> #include <linux/list.h> #include <linux/module.h> #include <linux/notifier.h> #include <linux/numa.h> #include <linux/refcount.h> #include <linux/rwsem.h> #include <linux/sched.h> #include <linux/types.h> struct crypto_instance; struct crypto_template; struct crypto_larval { struct crypto_alg alg; struct crypto_alg *adult; struct completion completion; u32 mask; }; enum { CRYPTOA_UNSPEC, CRYPTOA_ALG, CRYPTOA_TYPE, __CRYPTOA_MAX, }; #define CRYPTOA_MAX (__CRYPTOA_MAX - 1) /* Maximum number of (rtattr) parameters for each template. */ #define CRYPTO_MAX_ATTRS 32 extern struct list_head crypto_alg_list; extern struct rw_semaphore crypto_alg_sem; extern struct blocking_notifier_head crypto_chain; #ifdef CONFIG_PROC_FS void __init crypto_init_proc(void); void __exit crypto_exit_proc(void); #else static inline void crypto_init_proc(void) { } static inline void crypto_exit_proc(void) { } #endif static inline unsigned int crypto_cipher_ctxsize(struct crypto_alg *alg) { return alg->cra_ctxsize; } static inline unsigned int crypto_compress_ctxsize(struct crypto_alg *alg) { return alg->cra_ctxsize; } struct crypto_alg *crypto_mod_get(struct crypto_alg *alg); struct crypto_alg *crypto_alg_mod_lookup(const char *name, u32 type, u32 mask); struct crypto_larval *crypto_larval_alloc(const char *name, u32 type, u32 mask); void crypto_larval_kill(struct crypto_alg *alg); void crypto_alg_tested(const char *name, int err); void crypto_remove_spawns(struct crypto_alg *alg, struct list_head *list, struct crypto_alg *nalg); void crypto_remove_final(struct list_head *list); void crypto_shoot_alg(struct crypto_alg *alg); struct crypto_tfm *__crypto_alloc_tfm(struct crypto_alg *alg, u32 type, u32 mask); void *crypto_create_tfm_node(struct crypto_alg *alg, const struct crypto_type *frontend, int node); static inline void *crypto_create_tfm(struct crypto_alg *alg, const struct crypto_type *frontend) { return crypto_create_tfm_node(alg, frontend, NUMA_NO_NODE); } struct crypto_alg *crypto_find_alg(const char *alg_name, const struct crypto_type *frontend, u32 type, u32 mask); void *crypto_alloc_tfm_node(const char *alg_name, const struct crypto_type *frontend, u32 type, u32 mask, int node); static inline void *crypto_alloc_tfm(const char *alg_name, const struct crypto_type *frontend, u32 type, u32 mask) { return crypto_alloc_tfm_node(alg_name, frontend, type, mask, NUMA_NO_NODE); } int crypto_probing_notify(unsigned long val, void *v); unsigned int crypto_alg_extsize(struct crypto_alg *alg); int crypto_type_has_alg(const char *name, const struct crypto_type *frontend, u32 type, u32 mask); static inline struct crypto_alg *crypto_alg_get(struct crypto_alg *alg) { refcount_inc(&alg->cra_refcnt); return alg; } static inline void crypto_alg_put(struct crypto_alg *alg) { if (refcount_dec_and_test(&alg->cra_refcnt) && alg->cra_destroy) alg->cra_destroy(alg); } static inline int crypto_tmpl_get(struct crypto_template *tmpl) { return try_module_get(tmpl->module); } static inline void crypto_tmpl_put(struct crypto_template *tmpl) { module_put(tmpl->module); } static inline int crypto_is_larval(struct crypto_alg *alg) { return alg->cra_flags & CRYPTO_ALG_LARVAL; } static inline int crypto_is_dead(struct crypto_alg *alg) { return alg->cra_flags & CRYPTO_ALG_DEAD; } static inline int crypto_is_moribund(struct crypto_alg *alg) { return alg->cra_flags & (CRYPTO_ALG_DEAD | CRYPTO_ALG_DYING); } static inline void crypto_notify(unsigned long val, void *v) { blocking_notifier_call_chain(&crypto_chain, val, v); } static inline void crypto_yield(u32 flags) { if (flags & CRYPTO_TFM_REQ_MAY_SLEEP) cond_resched(); } #endif /* _CRYPTO_INTERNAL_H */ |
| 38 2 1 1 1 9 7 4 1 1 1 1 1 14 7 55 55 55 55 1 53 52 7 48 9 55 215 215 215 214 215 13 203 215 159 20 20 8 8 18 18 18 7 18 18 18 18 7 7 7 7 7 2 2 2 1 1 3 3 2 3 2 2 2 2 2 17 17 17 1 1 17 48 48 13 35 47 1 10 232 230 234 232 234 52 52 25 24 1 19 19 19 2 18 19 18 1 5 18 18 1 7 7 18 18 18 13 13 13 188 189 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * drivers/net/veth.c * * Copyright (C) 2007 OpenVZ http://openvz.org, SWsoft Inc * * Author: Pavel Emelianov <xemul@openvz.org> * Ethtool interface from: Eric W. Biederman <ebiederm@xmission.com> * */ #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/u64_stats_sync.h> #include <net/rtnetlink.h> #include <net/dst.h> #include <net/xfrm.h> #include <net/xdp.h> #include <linux/veth.h> #include <linux/module.h> #include <linux/bpf.h> #include <linux/filter.h> #include <linux/ptr_ring.h> #include <linux/bpf_trace.h> #include <linux/net_tstamp.h> #define DRV_NAME "veth" #define DRV_VERSION "1.0" #define VETH_XDP_FLAG BIT(0) #define VETH_RING_SIZE 256 #define VETH_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN) #define VETH_XDP_TX_BULK_SIZE 16 #define VETH_XDP_BATCH 16 struct veth_stats { u64 rx_drops; /* xdp */ u64 xdp_packets; u64 xdp_bytes; u64 xdp_redirect; u64 xdp_drops; u64 xdp_tx; u64 xdp_tx_err; u64 peer_tq_xdp_xmit; u64 peer_tq_xdp_xmit_err; }; struct veth_rq_stats { struct veth_stats vs; struct u64_stats_sync syncp; }; struct veth_rq { struct napi_struct xdp_napi; struct napi_struct __rcu *napi; /* points to xdp_napi when the latter is initialized */ struct net_device *dev; struct bpf_prog __rcu *xdp_prog; struct xdp_mem_info xdp_mem; struct veth_rq_stats stats; bool rx_notify_masked; struct ptr_ring xdp_ring; struct xdp_rxq_info xdp_rxq; }; struct veth_priv { struct net_device __rcu *peer; atomic64_t dropped; struct bpf_prog *_xdp_prog; struct veth_rq *rq; unsigned int requested_headroom; }; struct veth_xdp_tx_bq { struct xdp_frame *q[VETH_XDP_TX_BULK_SIZE]; unsigned int count; }; /* * ethtool interface */ struct veth_q_stat_desc { char desc[ETH_GSTRING_LEN]; size_t offset; }; #define VETH_RQ_STAT(m) offsetof(struct veth_stats, m) static const struct veth_q_stat_desc veth_rq_stats_desc[] = { { "xdp_packets", VETH_RQ_STAT(xdp_packets) }, { "xdp_bytes", VETH_RQ_STAT(xdp_bytes) }, { "drops", VETH_RQ_STAT(rx_drops) }, { "xdp_redirect", VETH_RQ_STAT(xdp_redirect) }, { "xdp_drops", VETH_RQ_STAT(xdp_drops) }, { "xdp_tx", VETH_RQ_STAT(xdp_tx) }, { "xdp_tx_errors", VETH_RQ_STAT(xdp_tx_err) }, }; #define VETH_RQ_STATS_LEN ARRAY_SIZE(veth_rq_stats_desc) static const struct veth_q_stat_desc veth_tq_stats_desc[] = { { "xdp_xmit", VETH_RQ_STAT(peer_tq_xdp_xmit) }, { "xdp_xmit_errors", VETH_RQ_STAT(peer_tq_xdp_xmit_err) }, }; #define VETH_TQ_STATS_LEN ARRAY_SIZE(veth_tq_stats_desc) static struct { const char string[ETH_GSTRING_LEN]; } ethtool_stats_keys[] = { { "peer_ifindex" }, }; static int veth_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { cmd->base.speed = SPEED_10000; cmd->base.duplex = DUPLEX_FULL; cmd->base.port = PORT_TP; cmd->base.autoneg = AUTONEG_DISABLE; return 0; } static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); strlcpy(info->version, DRV_VERSION, sizeof(info->version)); } static void veth_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { char *p = (char *)buf; int i, j; switch(stringset) { case ETH_SS_STATS: memcpy(p, ðtool_stats_keys, sizeof(ethtool_stats_keys)); p += sizeof(ethtool_stats_keys); for (i = 0; i < dev->real_num_rx_queues; i++) { for (j = 0; j < VETH_RQ_STATS_LEN; j++) { snprintf(p, ETH_GSTRING_LEN, "rx_queue_%u_%.18s", i, veth_rq_stats_desc[j].desc); p += ETH_GSTRING_LEN; } } for (i = 0; i < dev->real_num_tx_queues; i++) { for (j = 0; j < VETH_TQ_STATS_LEN; j++) { snprintf(p, ETH_GSTRING_LEN, "tx_queue_%u_%.18s", i, veth_tq_stats_desc[j].desc); p += ETH_GSTRING_LEN; } } break; } } static int veth_get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: return ARRAY_SIZE(ethtool_stats_keys) + VETH_RQ_STATS_LEN * dev->real_num_rx_queues + VETH_TQ_STATS_LEN * dev->real_num_tx_queues; default: return -EOPNOTSUPP; } } static void veth_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); int i, j, idx; data[0] = peer ? peer->ifindex : 0; idx = 1; for (i = 0; i < dev->real_num_rx_queues; i++) { const struct veth_rq_stats *rq_stats = &priv->rq[i].stats; const void *stats_base = (void *)&rq_stats->vs; unsigned int start; size_t offset; do { start = u64_stats_fetch_begin_irq(&rq_stats->syncp); for (j = 0; j < VETH_RQ_STATS_LEN; j++) { offset = veth_rq_stats_desc[j].offset; data[idx + j] = *(u64 *)(stats_base + offset); } } while (u64_stats_fetch_retry_irq(&rq_stats->syncp, start)); idx += VETH_RQ_STATS_LEN; } if (!peer) return; rcv_priv = netdev_priv(peer); for (i = 0; i < peer->real_num_rx_queues; i++) { const struct veth_rq_stats *rq_stats = &rcv_priv->rq[i].stats; const void *base = (void *)&rq_stats->vs; unsigned int start, tx_idx = idx; size_t offset; tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN; do { start = u64_stats_fetch_begin_irq(&rq_stats->syncp); for (j = 0; j < VETH_TQ_STATS_LEN; j++) { offset = veth_tq_stats_desc[j].offset; data[tx_idx + j] += *(u64 *)(base + offset); } } while (u64_stats_fetch_retry_irq(&rq_stats->syncp, start)); } } static void veth_get_channels(struct net_device *dev, struct ethtool_channels *channels) { channels->tx_count = dev->real_num_tx_queues; channels->rx_count = dev->real_num_rx_queues; channels->max_tx = dev->num_tx_queues; channels->max_rx = dev->num_rx_queues; } static int veth_set_channels(struct net_device *dev, struct ethtool_channels *ch); static const struct ethtool_ops veth_ethtool_ops = { .get_drvinfo = veth_get_drvinfo, .get_link = ethtool_op_get_link, .get_strings = veth_get_strings, .get_sset_count = veth_get_sset_count, .get_ethtool_stats = veth_get_ethtool_stats, .get_link_ksettings = veth_get_link_ksettings, .get_ts_info = ethtool_op_get_ts_info, .get_channels = veth_get_channels, .set_channels = veth_set_channels, }; /* general routines */ static bool veth_is_xdp_frame(void *ptr) { return (unsigned long)ptr & VETH_XDP_FLAG; } static struct xdp_frame *veth_ptr_to_xdp(void *ptr) { return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG); } static void *veth_xdp_to_ptr(struct xdp_frame *xdp) { return (void *)((unsigned long)xdp | VETH_XDP_FLAG); } static void veth_ptr_free(void *ptr) { if (veth_is_xdp_frame(ptr)) xdp_return_frame(veth_ptr_to_xdp(ptr)); else kfree_skb(ptr); } static void __veth_xdp_flush(struct veth_rq *rq) { /* Write ptr_ring before reading rx_notify_masked */ smp_mb(); if (!READ_ONCE(rq->rx_notify_masked) && napi_schedule_prep(&rq->xdp_napi)) { WRITE_ONCE(rq->rx_notify_masked, true); __napi_schedule(&rq->xdp_napi); } } static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb) { if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb))) { dev_kfree_skb_any(skb); return NET_RX_DROP; } return NET_RX_SUCCESS; } static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb, struct veth_rq *rq, bool xdp) { return __dev_forward_skb(dev, skb) ?: xdp ? veth_xdp_rx(rq, skb) : netif_rx(skb); } /* return true if the specified skb has chances of GRO aggregation * Don't strive for accuracy, but try to avoid GRO overhead in the most * common scenarios. * When XDP is enabled, all traffic is considered eligible, as the xmit * device has TSO off. * When TSO is enabled on the xmit device, we are likely interested only * in UDP aggregation, explicitly check for that if the skb is suspected * - the sock_wfree destructor is used by UDP, ICMP and XDP sockets - * to belong to locally generated UDP traffic. */ static bool veth_skb_is_eligible_for_gro(const struct net_device *dev, const struct net_device *rcv, const struct sk_buff *skb) { return !(dev->features & NETIF_F_ALL_TSO) || (skb->destructor == sock_wfree && rcv->features & (NETIF_F_GRO_FRAGLIST | NETIF_F_GRO_UDP_FWD)); } static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); struct veth_rq *rq = NULL; int ret = NETDEV_TX_OK; struct net_device *rcv; int length = skb->len; bool use_napi = false; int rxq; rcu_read_lock(); rcv = rcu_dereference(priv->peer); if (unlikely(!rcv) || !pskb_may_pull(skb, ETH_HLEN)) { kfree_skb(skb); goto drop; } rcv_priv = netdev_priv(rcv); rxq = skb_get_queue_mapping(skb); if (rxq < rcv->real_num_rx_queues) { rq = &rcv_priv->rq[rxq]; /* The napi pointer is available when an XDP program is * attached or when GRO is enabled * Don't bother with napi/GRO if the skb can't be aggregated */ use_napi = rcu_access_pointer(rq->napi) && veth_skb_is_eligible_for_gro(dev, rcv, skb); } skb_tx_timestamp(skb); if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) { if (!use_napi) dev_lstats_add(dev, length); } else { drop: atomic64_inc(&priv->dropped); ret = NET_XMIT_DROP; } if (use_napi) __veth_xdp_flush(rq); rcu_read_unlock(); return ret; } static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes) { struct veth_priv *priv = netdev_priv(dev); dev_lstats_read(dev, packets, bytes); return atomic64_read(&priv->dropped); } static void veth_stats_rx(struct veth_stats *result, struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int i; result->peer_tq_xdp_xmit_err = 0; result->xdp_packets = 0; result->xdp_tx_err = 0; result->xdp_bytes = 0; result->rx_drops = 0; for (i = 0; i < dev->num_rx_queues; i++) { u64 packets, bytes, drops, xdp_tx_err, peer_tq_xdp_xmit_err; struct veth_rq_stats *stats = &priv->rq[i].stats; unsigned int start; do { start = u64_stats_fetch_begin_irq(&stats->syncp); peer_tq_xdp_xmit_err = stats->vs.peer_tq_xdp_xmit_err; xdp_tx_err = stats->vs.xdp_tx_err; packets = stats->vs.xdp_packets; bytes = stats->vs.xdp_bytes; drops = stats->vs.rx_drops; } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); result->peer_tq_xdp_xmit_err += peer_tq_xdp_xmit_err; result->xdp_tx_err += xdp_tx_err; result->xdp_packets += packets; result->xdp_bytes += bytes; result->rx_drops += drops; } } static void veth_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; struct veth_stats rx; u64 packets, bytes; tot->tx_dropped = veth_stats_tx(dev, &packets, &bytes); tot->tx_bytes = bytes; tot->tx_packets = packets; veth_stats_rx(&rx, dev); tot->tx_dropped += rx.xdp_tx_err; tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err; tot->rx_bytes = rx.xdp_bytes; tot->rx_packets = rx.xdp_packets; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (peer) { veth_stats_tx(peer, &packets, &bytes); tot->rx_bytes += bytes; tot->rx_packets += packets; veth_stats_rx(&rx, peer); tot->tx_dropped += rx.peer_tq_xdp_xmit_err; tot->rx_dropped += rx.xdp_tx_err; tot->tx_bytes += rx.xdp_bytes; tot->tx_packets += rx.xdp_packets; } rcu_read_unlock(); } /* fake multicast ability */ static void veth_set_multicast_list(struct net_device *dev) { } static struct sk_buff *veth_build_skb(void *head, int headroom, int len, int buflen) { struct sk_buff *skb; skb = build_skb(head, buflen); if (!skb) return NULL; skb_reserve(skb, headroom); skb_put(skb, len); return skb; } static int veth_select_rxq(struct net_device *dev) { return smp_processor_id() % dev->real_num_rx_queues; } static struct net_device *veth_peer_dev(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); /* Callers must be under RCU read side. */ return rcu_dereference(priv->peer); } static int veth_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags, bool ndo_xmit) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); int i, ret = -ENXIO, nxmit = 0; struct net_device *rcv; unsigned int max_len; struct veth_rq *rq; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; rcu_read_lock(); rcv = rcu_dereference(priv->peer); if (unlikely(!rcv)) goto out; rcv_priv = netdev_priv(rcv); rq = &rcv_priv->rq[veth_select_rxq(rcv)]; /* The napi pointer is set if NAPI is enabled, which ensures that * xdp_ring is initialized on receive side and the peer device is up. */ if (!rcu_access_pointer(rq->napi)) goto out; max_len = rcv->mtu + rcv->hard_header_len + VLAN_HLEN; spin_lock(&rq->xdp_ring.producer_lock); for (i = 0; i < n; i++) { struct xdp_frame *frame = frames[i]; void *ptr = veth_xdp_to_ptr(frame); if (unlikely(frame->len > max_len || __ptr_ring_produce(&rq->xdp_ring, ptr))) break; nxmit++; } spin_unlock(&rq->xdp_ring.producer_lock); if (flags & XDP_XMIT_FLUSH) __veth_xdp_flush(rq); ret = nxmit; if (ndo_xmit) { u64_stats_update_begin(&rq->stats.syncp); rq->stats.vs.peer_tq_xdp_xmit += nxmit; rq->stats.vs.peer_tq_xdp_xmit_err += n - nxmit; u64_stats_update_end(&rq->stats.syncp); } out: rcu_read_unlock(); return ret; } static int veth_ndo_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { int err; err = veth_xdp_xmit(dev, n, frames, flags, true); if (err < 0) { struct veth_priv *priv = netdev_priv(dev); atomic64_add(n, &priv->dropped); } return err; } static void veth_xdp_flush_bq(struct veth_rq *rq, struct veth_xdp_tx_bq *bq) { int sent, i, err = 0, drops; sent = veth_xdp_xmit(rq->dev, bq->count, bq->q, 0, false); if (sent < 0) { err = sent; sent = 0; } for (i = sent; unlikely(i < bq->count); i++) xdp_return_frame(bq->q[i]); drops = bq->count - sent; trace_xdp_bulk_tx(rq->dev, sent, drops, err); u64_stats_update_begin(&rq->stats.syncp); rq->stats.vs.xdp_tx += sent; rq->stats.vs.xdp_tx_err += drops; u64_stats_update_end(&rq->stats.syncp); bq->count = 0; } static void veth_xdp_flush(struct veth_rq *rq, struct veth_xdp_tx_bq *bq) { struct veth_priv *rcv_priv, *priv = netdev_priv(rq->dev); struct net_device *rcv; struct veth_rq *rcv_rq; rcu_read_lock(); veth_xdp_flush_bq(rq, bq); rcv = rcu_dereference(priv->peer); if (unlikely(!rcv)) goto out; rcv_priv = netdev_priv(rcv); rcv_rq = &rcv_priv->rq[veth_select_rxq(rcv)]; /* xdp_ring is initialized on receive side? */ if (unlikely(!rcu_access_pointer(rcv_rq->xdp_prog))) goto out; __veth_xdp_flush(rcv_rq); out: rcu_read_unlock(); } static int veth_xdp_tx(struct veth_rq *rq, struct xdp_buff *xdp, struct veth_xdp_tx_bq *bq) { struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp); if (unlikely(!frame)) return -EOVERFLOW; if (unlikely(bq->count == VETH_XDP_TX_BULK_SIZE)) veth_xdp_flush_bq(rq, bq); bq->q[bq->count++] = frame; return 0; } static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq, struct xdp_frame *frame, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { struct xdp_frame orig_frame; struct bpf_prog *xdp_prog; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (likely(xdp_prog)) { struct xdp_buff xdp; u32 act; xdp_convert_frame_to_buff(frame, &xdp); xdp.rxq = &rq->xdp_rxq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { case XDP_PASS: if (xdp_update_frame_from_buff(&xdp, frame)) goto err_xdp; break; case XDP_TX: orig_frame = *frame; xdp.rxq->mem = frame->mem; if (unlikely(veth_xdp_tx(rq, &xdp, bq) < 0)) { trace_xdp_exception(rq->dev, xdp_prog, act); frame = &orig_frame; stats->rx_drops++; goto err_xdp; } stats->xdp_tx++; rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: orig_frame = *frame; xdp.rxq->mem = frame->mem; if (xdp_do_redirect(rq->dev, &xdp, xdp_prog)) { frame = &orig_frame; stats->rx_drops++; goto err_xdp; } stats->xdp_redirect++; rcu_read_unlock(); goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); fallthrough; case XDP_DROP: stats->xdp_drops++; goto err_xdp; } } rcu_read_unlock(); return frame; err_xdp: rcu_read_unlock(); xdp_return_frame(frame); xdp_xmit: return NULL; } /* frames array contains VETH_XDP_BATCH at most */ static void veth_xdp_rcv_bulk_skb(struct veth_rq *rq, void **frames, int n_xdpf, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { void *skbs[VETH_XDP_BATCH]; int i; if (xdp_alloc_skb_bulk(skbs, n_xdpf, GFP_ATOMIC | __GFP_ZERO) < 0) { for (i = 0; i < n_xdpf; i++) xdp_return_frame(frames[i]); stats->rx_drops += n_xdpf; return; } for (i = 0; i < n_xdpf; i++) { struct sk_buff *skb = skbs[i]; skb = __xdp_build_skb_from_frame(frames[i], skb, rq->dev); if (!skb) { xdp_return_frame(frames[i]); stats->rx_drops++; continue; } napi_gro_receive(&rq->xdp_napi, skb); } } static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { u32 pktlen, headroom, act, metalen, frame_sz; void *orig_data, *orig_data_end; struct bpf_prog *xdp_prog; int mac_len, delta, off; struct xdp_buff xdp; skb_prepare_for_gro(skb); rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (unlikely(!xdp_prog)) { rcu_read_unlock(); goto out; } mac_len = skb->data - skb_mac_header(skb); pktlen = skb->len + mac_len; headroom = skb_headroom(skb) - mac_len; if (skb_shared(skb) || skb_head_is_locked(skb) || skb_is_nonlinear(skb) || headroom < XDP_PACKET_HEADROOM) { struct sk_buff *nskb; int size, head_off; void *head, *start; struct page *page; size = SKB_DATA_ALIGN(VETH_XDP_HEADROOM + pktlen) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (size > PAGE_SIZE) goto drop; page = alloc_page(GFP_ATOMIC | __GFP_NOWARN); if (!page) goto drop; head = page_address(page); start = head + VETH_XDP_HEADROOM; if (skb_copy_bits(skb, -mac_len, start, pktlen)) { page_frag_free(head); goto drop; } nskb = veth_build_skb(head, VETH_XDP_HEADROOM + mac_len, skb->len, PAGE_SIZE); if (!nskb) { page_frag_free(head); goto drop; } skb_copy_header(nskb, skb); head_off = skb_headroom(nskb) - skb_headroom(skb); skb_headers_offset_update(nskb, head_off); consume_skb(skb); skb = nskb; } /* SKB "head" area always have tailroom for skb_shared_info */ frame_sz = skb_end_pointer(skb) - skb->head; frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); xdp_init_buff(&xdp, frame_sz, &rq->xdp_rxq); xdp_prepare_buff(&xdp, skb->head, skb->mac_header, pktlen, true); orig_data = xdp.data; orig_data_end = xdp.data_end; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { case XDP_PASS: break; case XDP_TX: get_page(virt_to_page(xdp.data)); consume_skb(skb); xdp.rxq->mem = rq->xdp_mem; if (unlikely(veth_xdp_tx(rq, &xdp, bq) < 0)) { trace_xdp_exception(rq->dev, xdp_prog, act); stats->rx_drops++; goto err_xdp; } stats->xdp_tx++; rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: get_page(virt_to_page(xdp.data)); consume_skb(skb); xdp.rxq->mem = rq->xdp_mem; if (xdp_do_redirect(rq->dev, &xdp, xdp_prog)) { stats->rx_drops++; goto err_xdp; } stats->xdp_redirect++; rcu_read_unlock(); goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); fallthrough; case XDP_DROP: stats->xdp_drops++; goto xdp_drop; } rcu_read_unlock(); /* check if bpf_xdp_adjust_head was used */ delta = orig_data - xdp.data; off = mac_len + delta; if (off > 0) __skb_push(skb, off); else if (off < 0) __skb_pull(skb, -off); skb->mac_header -= delta; /* check if bpf_xdp_adjust_tail was used */ off = xdp.data_end - orig_data_end; if (off != 0) __skb_put(skb, off); /* positive on grow, negative on shrink */ skb->protocol = eth_type_trans(skb, rq->dev); metalen = xdp.data - xdp.data_meta; if (metalen) skb_metadata_set(skb, metalen); out: return skb; drop: stats->rx_drops++; xdp_drop: rcu_read_unlock(); kfree_skb(skb); return NULL; err_xdp: rcu_read_unlock(); page_frag_free(xdp.data); xdp_xmit: return NULL; } static int veth_xdp_rcv(struct veth_rq *rq, int budget, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { int i, done = 0, n_xdpf = 0; void *xdpf[VETH_XDP_BATCH]; for (i = 0; i < budget; i++) { void *ptr = __ptr_ring_consume(&rq->xdp_ring); if (!ptr) break; if (veth_is_xdp_frame(ptr)) { /* ndo_xdp_xmit */ struct xdp_frame *frame = veth_ptr_to_xdp(ptr); stats->xdp_bytes += frame->len; frame = veth_xdp_rcv_one(rq, frame, bq, stats); if (frame) { /* XDP_PASS */ xdpf[n_xdpf++] = frame; if (n_xdpf == VETH_XDP_BATCH) { veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, bq, stats); n_xdpf = 0; } } } else { /* ndo_start_xmit */ struct sk_buff *skb = ptr; stats->xdp_bytes += skb->len; skb = veth_xdp_rcv_skb(rq, skb, bq, stats); if (skb) { if (skb_shared(skb) || skb_unclone(skb, GFP_ATOMIC)) netif_receive_skb(skb); else napi_gro_receive(&rq->xdp_napi, skb); } } done++; } if (n_xdpf) veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, bq, stats); u64_stats_update_begin(&rq->stats.syncp); rq->stats.vs.xdp_redirect += stats->xdp_redirect; rq->stats.vs.xdp_bytes += stats->xdp_bytes; rq->stats.vs.xdp_drops += stats->xdp_drops; rq->stats.vs.rx_drops += stats->rx_drops; rq->stats.vs.xdp_packets += done; u64_stats_update_end(&rq->stats.syncp); return done; } static int veth_poll(struct napi_struct *napi, int budget) { struct veth_rq *rq = container_of(napi, struct veth_rq, xdp_napi); struct veth_stats stats = {}; struct veth_xdp_tx_bq bq; int done; bq.count = 0; xdp_set_return_frame_no_direct(); done = veth_xdp_rcv(rq, budget, &bq, &stats); if (stats.xdp_redirect > 0) xdp_do_flush(); if (done < budget && napi_complete_done(napi, done)) { /* Write rx_notify_masked before reading ptr_ring */ smp_store_mb(rq->rx_notify_masked, false); if (unlikely(!__ptr_ring_empty(&rq->xdp_ring))) { if (napi_schedule_prep(&rq->xdp_napi)) { WRITE_ONCE(rq->rx_notify_masked, true); __napi_schedule(&rq->xdp_napi); } } } if (stats.xdp_tx > 0) veth_xdp_flush(rq, &bq); xdp_clear_return_frame_no_direct(); return done; } static int __veth_napi_enable_range(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int err, i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; err = ptr_ring_init(&rq->xdp_ring, VETH_RING_SIZE, GFP_KERNEL); if (err) goto err_xdp_ring; } for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; napi_enable(&rq->xdp_napi); rcu_assign_pointer(priv->rq[i].napi, &priv->rq[i].xdp_napi); } return 0; err_xdp_ring: for (i--; i >= start; i--) ptr_ring_cleanup(&priv->rq[i].xdp_ring, veth_ptr_free); return err; } static int __veth_napi_enable(struct net_device *dev) { return __veth_napi_enable_range(dev, 0, dev->real_num_rx_queues); } static void veth_napi_del_range(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; rcu_assign_pointer(priv->rq[i].napi, NULL); napi_disable(&rq->xdp_napi); __netif_napi_del(&rq->xdp_napi); } synchronize_net(); for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; rq->rx_notify_masked = false; ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free); } } static void veth_napi_del(struct net_device *dev) { veth_napi_del_range(dev, 0, dev->real_num_rx_queues); } static bool veth_gro_requested(const struct net_device *dev) { return !!(dev->wanted_features & NETIF_F_GRO); } static int veth_enable_xdp_range(struct net_device *dev, int start, int end, bool napi_already_on) { struct veth_priv *priv = netdev_priv(dev); int err, i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; if (!napi_already_on) netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT); err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i, rq->xdp_napi.napi_id); if (err < 0) goto err_rxq_reg; err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err < 0) goto err_reg_mem; /* Save original mem info as it can be overwritten */ rq->xdp_mem = rq->xdp_rxq.mem; } return 0; err_reg_mem: xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq); err_rxq_reg: for (i--; i >= start; i--) { struct veth_rq *rq = &priv->rq[i]; xdp_rxq_info_unreg(&rq->xdp_rxq); if (!napi_already_on) netif_napi_del(&rq->xdp_napi); } return err; } static void veth_disable_xdp_range(struct net_device *dev, int start, int end, bool delete_napi) { struct veth_priv *priv = netdev_priv(dev); int i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; rq->xdp_rxq.mem = rq->xdp_mem; xdp_rxq_info_unreg(&rq->xdp_rxq); if (delete_napi) netif_napi_del(&rq->xdp_napi); } } static int veth_enable_xdp(struct net_device *dev) { bool napi_already_on = veth_gro_requested(dev) && (dev->flags & IFF_UP); struct veth_priv *priv = netdev_priv(dev); int err, i; if (!xdp_rxq_info_is_reg(&priv->rq[0].xdp_rxq)) { err = veth_enable_xdp_range(dev, 0, dev->real_num_rx_queues, napi_already_on); if (err) return err; if (!napi_already_on) { err = __veth_napi_enable(dev); if (err) { veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true); return err; } } } for (i = 0; i < dev->real_num_rx_queues; i++) { rcu_assign_pointer(priv->rq[i].xdp_prog, priv->_xdp_prog); rcu_assign_pointer(priv->rq[i].napi, &priv->rq[i].xdp_napi); } return 0; } static void veth_disable_xdp(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int i; for (i = 0; i < dev->real_num_rx_queues; i++) rcu_assign_pointer(priv->rq[i].xdp_prog, NULL); if (!netif_running(dev) || !veth_gro_requested(dev)) veth_napi_del(dev); veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false); } static int veth_napi_enable_range(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int err, i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT); } err = __veth_napi_enable_range(dev, start, end); if (err) { for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; netif_napi_del(&rq->xdp_napi); } return err; } return err; } static int veth_napi_enable(struct net_device *dev) { return veth_napi_enable_range(dev, 0, dev->real_num_rx_queues); } static void veth_disable_range_safe(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); if (start >= end) return; if (priv->_xdp_prog) { veth_napi_del_range(dev, start, end); veth_disable_xdp_range(dev, start, end, false); } else if (veth_gro_requested(dev)) { veth_napi_del_range(dev, start, end); } } static int veth_enable_range_safe(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int err; if (start >= end) return 0; if (priv->_xdp_prog) { /* these channels are freshly initialized, napi is not on there even * when GRO is requeste */ err = veth_enable_xdp_range(dev, start, end, false); if (err) return err; err = __veth_napi_enable_range(dev, start, end); if (err) { /* on error always delete the newly added napis */ veth_disable_xdp_range(dev, start, end, true); return err; } } else if (veth_gro_requested(dev)) { return veth_napi_enable_range(dev, start, end); } return 0; } static int veth_set_channels(struct net_device *dev, struct ethtool_channels *ch) { struct veth_priv *priv = netdev_priv(dev); unsigned int old_rx_count, new_rx_count; struct veth_priv *peer_priv; struct net_device *peer; int err; /* sanity check. Upper bounds are already enforced by the caller */ if (!ch->rx_count || !ch->tx_count) return -EINVAL; /* avoid braking XDP, if that is enabled */ peer = rtnl_dereference(priv->peer); peer_priv = peer ? netdev_priv(peer) : NULL; if (priv->_xdp_prog && peer && ch->rx_count < peer->real_num_tx_queues) return -EINVAL; if (peer && peer_priv && peer_priv->_xdp_prog && ch->tx_count > peer->real_num_rx_queues) return -EINVAL; old_rx_count = dev->real_num_rx_queues; new_rx_count = ch->rx_count; if (netif_running(dev)) { /* turn device off */ netif_carrier_off(dev); if (peer) netif_carrier_off(peer); /* try to allocate new resurces, as needed*/ err = veth_enable_range_safe(dev, old_rx_count, new_rx_count); if (err) goto out; } err = netif_set_real_num_rx_queues(dev, ch->rx_count); if (err) goto revert; err = netif_set_real_num_tx_queues(dev, ch->tx_count); if (err) { int err2 = netif_set_real_num_rx_queues(dev, old_rx_count); /* this error condition could happen only if rx and tx change * in opposite directions (e.g. tx nr raises, rx nr decreases) * and we can't do anything to fully restore the original * status */ if (err2) pr_warn("Can't restore rx queues config %d -> %d %d", new_rx_count, old_rx_count, err2); else goto revert; } out: if (netif_running(dev)) { /* note that we need to swap the arguments WRT the enable part * to identify the range we have to disable */ veth_disable_range_safe(dev, new_rx_count, old_rx_count); netif_carrier_on(dev); if (peer) netif_carrier_on(peer); } return err; revert: new_rx_count = old_rx_count; old_rx_count = ch->rx_count; goto out; } static int veth_open(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); int err; if (!peer) return -ENOTCONN; if (priv->_xdp_prog) { err = veth_enable_xdp(dev); if (err) return err; } else if (veth_gro_requested(dev)) { err = veth_napi_enable(dev); if (err) return err; } if (peer->flags & IFF_UP) { netif_carrier_on(dev); netif_carrier_on(peer); } return 0; } static int veth_close(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); netif_carrier_off(dev); if (peer) netif_carrier_off(peer); if (priv->_xdp_prog) veth_disable_xdp(dev); else if (veth_gro_requested(dev)) veth_napi_del(dev); return 0; } static int is_valid_veth_mtu(int mtu) { return mtu >= ETH_MIN_MTU && mtu <= ETH_MAX_MTU; } static int veth_alloc_queues(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int i; priv->rq = kvcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!priv->rq) return -ENOMEM; for (i = 0; i < dev->num_rx_queues; i++) { priv->rq[i].dev = dev; u64_stats_init(&priv->rq[i].stats.syncp); } return 0; } static void veth_free_queues(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); kvfree(priv->rq); } static int veth_dev_init(struct net_device *dev) { int err; dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); if (!dev->lstats) return -ENOMEM; err = veth_alloc_queues(dev); if (err) { free_percpu(dev->lstats); return err; } return 0; } static void veth_dev_free(struct net_device *dev) { veth_free_queues(dev); free_percpu(dev->lstats); } #ifdef CONFIG_NET_POLL_CONTROLLER static void veth_poll_controller(struct net_device *dev) { /* veth only receives frames when its peer sends one * Since it has nothing to do with disabling irqs, we are guaranteed * never to have pending data when we poll for it so * there is nothing to do here. * * We need this though so netpoll recognizes us as an interface that * supports polling, which enables bridge devices in virt setups to * still use netconsole */ } #endif /* CONFIG_NET_POLL_CONTROLLER */ static int veth_get_iflink(const struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; int iflink; rcu_read_lock(); peer = rcu_dereference(priv->peer); iflink = peer ? peer->ifindex : 0; rcu_read_unlock(); return iflink; } static netdev_features_t veth_fix_features(struct net_device *dev, netdev_features_t features) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; peer = rtnl_dereference(priv->peer); if (peer) { struct veth_priv *peer_priv = netdev_priv(peer); if (peer_priv->_xdp_prog) features &= ~NETIF_F_GSO_SOFTWARE; } return features; } static int veth_set_features(struct net_device *dev, netdev_features_t features) { netdev_features_t changed = features ^ dev->features; struct veth_priv *priv = netdev_priv(dev); int err; if (!(changed & NETIF_F_GRO) || !(dev->flags & IFF_UP) || priv->_xdp_prog) return 0; if (features & NETIF_F_GRO) { err = veth_napi_enable(dev); if (err) return err; } else { veth_napi_del(dev); } return 0; } static void veth_set_rx_headroom(struct net_device *dev, int new_hr) { struct veth_priv *peer_priv, *priv = netdev_priv(dev); struct net_device *peer; if (new_hr < 0) new_hr = 0; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (unlikely(!peer)) goto out; peer_priv = netdev_priv(peer); priv->requested_headroom = new_hr; new_hr = max(priv->requested_headroom, peer_priv->requested_headroom); dev->needed_headroom = new_hr; peer->needed_headroom = new_hr; out: rcu_read_unlock(); } static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct veth_priv *priv = netdev_priv(dev); struct bpf_prog *old_prog; struct net_device *peer; unsigned int max_mtu; int err; old_prog = priv->_xdp_prog; priv->_xdp_prog = prog; peer = rtnl_dereference(priv->peer); if (prog) { if (!peer) { NL_SET_ERR_MSG_MOD(extack, "Cannot set XDP when peer is detached"); err = -ENOTCONN; goto err; } max_mtu = PAGE_SIZE - VETH_XDP_HEADROOM - peer->hard_header_len - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (peer->mtu > max_mtu) { NL_SET_ERR_MSG_MOD(extack, "Peer MTU is too large to set XDP"); err = -ERANGE; goto err; } if (dev->real_num_rx_queues < peer->real_num_tx_queues) { NL_SET_ERR_MSG_MOD(extack, "XDP expects number of rx queues not less than peer tx queues"); err = -ENOSPC; goto err; } if (dev->flags & IFF_UP) { err = veth_enable_xdp(dev); if (err) { NL_SET_ERR_MSG_MOD(extack, "Setup for XDP failed"); goto err; } } if (!old_prog) { peer->hw_features &= ~NETIF_F_GSO_SOFTWARE; peer->max_mtu = max_mtu; } } if (old_prog) { if (!prog) { if (dev->flags & IFF_UP) veth_disable_xdp(dev); if (peer) { peer->hw_features |= NETIF_F_GSO_SOFTWARE; peer->max_mtu = ETH_MAX_MTU; } } bpf_prog_put(old_prog); } if ((!!old_prog ^ !!prog) && peer) netdev_update_features(peer); return 0; err: priv->_xdp_prog = old_prog; return err; } static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return veth_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static const struct net_device_ops veth_netdev_ops = { .ndo_init = veth_dev_init, .ndo_open = veth_open, .ndo_stop = veth_close, .ndo_start_xmit = veth_xmit, .ndo_get_stats64 = veth_get_stats64, .ndo_set_rx_mode = veth_set_multicast_list, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = veth_poll_controller, #endif .ndo_get_iflink = veth_get_iflink, .ndo_fix_features = veth_fix_features, .ndo_set_features = veth_set_features, .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = veth_set_rx_headroom, .ndo_bpf = veth_xdp, .ndo_xdp_xmit = veth_ndo_xdp_xmit, .ndo_get_peer_dev = veth_peer_dev, }; #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \ NETIF_F_RXCSUM | NETIF_F_SCTP_CRC | NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_STAG_RX ) static void veth_setup(struct net_device *dev) { ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_PHONY_HEADROOM; dev->netdev_ops = &veth_netdev_ops; dev->ethtool_ops = &veth_ethtool_ops; dev->features |= NETIF_F_LLTX; dev->features |= VETH_FEATURES; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX); dev->needs_free_netdev = true; dev->priv_destructor = veth_dev_free; dev->max_mtu = ETH_MAX_MTU; dev->hw_features = VETH_FEATURES; dev->hw_enc_features = VETH_FEATURES; dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE; } /* * netlink interface */ static int veth_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (tb[IFLA_MTU]) { if (!is_valid_veth_mtu(nla_get_u32(tb[IFLA_MTU]))) return -EINVAL; } return 0; } static struct rtnl_link_ops veth_link_ops; static void veth_disable_gro(struct net_device *dev) { dev->features &= ~NETIF_F_GRO; dev->wanted_features &= ~NETIF_F_GRO; netdev_update_features(dev); } static int veth_init_queues(struct net_device *dev, struct nlattr *tb[]) { int err; if (!tb[IFLA_NUM_TX_QUEUES] && dev->num_tx_queues > 1) { err = netif_set_real_num_tx_queues(dev, 1); if (err) return err; } if (!tb[IFLA_NUM_RX_QUEUES] && dev->num_rx_queues > 1) { err = netif_set_real_num_rx_queues(dev, 1); if (err) return err; } return 0; } static int veth_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { int err; struct net_device *peer; struct veth_priv *priv; char ifname[IFNAMSIZ]; struct nlattr *peer_tb[IFLA_MAX + 1], **tbp; unsigned char name_assign_type; struct ifinfomsg *ifmp; struct net *net; /* * create and register peer first */ if (data != NULL && data[VETH_INFO_PEER] != NULL) { struct nlattr *nla_peer; nla_peer = data[VETH_INFO_PEER]; ifmp = nla_data(nla_peer); err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); if (err < 0) return err; err = veth_validate(peer_tb, NULL, extack); if (err < 0) return err; tbp = peer_tb; } else { ifmp = NULL; tbp = tb; } if (ifmp && tbp[IFLA_IFNAME]) { nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ); name_assign_type = NET_NAME_USER; } else { snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d"); name_assign_type = NET_NAME_ENUM; } net = rtnl_link_get_net(src_net, tbp); if (IS_ERR(net)) return PTR_ERR(net); peer = rtnl_create_link(net, ifname, name_assign_type, &veth_link_ops, tbp, extack); if (IS_ERR(peer)) { put_net(net); return PTR_ERR(peer); } if (!ifmp || !tbp[IFLA_ADDRESS]) eth_hw_addr_random(peer); if (ifmp && (dev->ifindex != 0)) peer->ifindex = ifmp->ifi_index; peer->gso_max_size = dev->gso_max_size; peer->gso_max_segs = dev->gso_max_segs; err = register_netdevice(peer); put_net(net); net = NULL; if (err < 0) goto err_register_peer; /* keep GRO disabled by default to be consistent with the established * veth behavior */ veth_disable_gro(peer); netif_carrier_off(peer); err = rtnl_configure_link(peer, ifmp); if (err < 0) goto err_configure_peer; /* * register dev last * * note, that since we've registered new device the dev's name * should be re-allocated */ if (tb[IFLA_ADDRESS] == NULL) eth_hw_addr_random(dev); if (tb[IFLA_IFNAME]) nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); else snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d"); err = register_netdevice(dev); if (err < 0) goto err_register_dev; netif_carrier_off(dev); /* * tie the deviced together */ priv = netdev_priv(dev); rcu_assign_pointer(priv->peer, peer); err = veth_init_queues(dev, tb); if (err) goto err_queues; priv = netdev_priv(peer); rcu_assign_pointer(priv->peer, dev); err = veth_init_queues(peer, tb); if (err) goto err_queues; veth_disable_gro(dev); return 0; err_queues: unregister_netdevice(dev); err_register_dev: /* nothing to do */ err_configure_peer: unregister_netdevice(peer); return err; err_register_peer: free_netdev(peer); return err; } static void veth_dellink(struct net_device *dev, struct list_head *head) { struct veth_priv *priv; struct net_device *peer; priv = netdev_priv(dev); peer = rtnl_dereference(priv->peer); /* Note : dellink() is called from default_device_exit_batch(), * before a rcu_synchronize() point. The devices are guaranteed * not being freed before one RCU grace period. */ RCU_INIT_POINTER(priv->peer, NULL); unregister_netdevice_queue(dev, head); if (peer) { priv = netdev_priv(peer); RCU_INIT_POINTER(priv->peer, NULL); unregister_netdevice_queue(peer, head); } } static const struct nla_policy veth_policy[VETH_INFO_MAX + 1] = { [VETH_INFO_PEER] = { .len = sizeof(struct ifinfomsg) }, }; static struct net *veth_get_link_net(const struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); return peer ? dev_net(peer) : dev_net(dev); } static unsigned int veth_get_num_queues(void) { /* enforce the same queue limit as rtnl_create_link */ int queues = num_possible_cpus(); if (queues > 4096) queues = 4096; return queues; } static struct rtnl_link_ops veth_link_ops = { .kind = DRV_NAME, .priv_size = sizeof(struct veth_priv), .setup = veth_setup, .validate = veth_validate, .newlink = veth_newlink, .dellink = veth_dellink, .policy = veth_policy, .maxtype = VETH_INFO_MAX, .get_link_net = veth_get_link_net, .get_num_tx_queues = veth_get_num_queues, .get_num_rx_queues = veth_get_num_queues, }; /* * init/fini */ static __init int veth_init(void) { return rtnl_link_register(&veth_link_ops); } static __exit void veth_exit(void) { rtnl_link_unregister(&veth_link_ops); } module_init(veth_init); module_exit(veth_exit); MODULE_DESCRIPTION("Virtual Ethernet Tunnel"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); |
| 1 13 18 17 13 17 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 | /* * llc_core.c - Minimum needed routines for sap handling and module init/exit * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/module.h> #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/init.h> #include <net/net_namespace.h> #include <net/llc.h> LIST_HEAD(llc_sap_list); static DEFINE_SPINLOCK(llc_sap_list_lock); /** * llc_sap_alloc - allocates and initializes sap. * * Allocates and initializes sap. */ static struct llc_sap *llc_sap_alloc(void) { struct llc_sap *sap = kzalloc(sizeof(*sap), GFP_ATOMIC); int i; if (sap) { /* sap->laddr.mac - leave as a null, it's filled by bind */ sap->state = LLC_SAP_STATE_ACTIVE; spin_lock_init(&sap->sk_lock); for (i = 0; i < LLC_SK_LADDR_HASH_ENTRIES; i++) INIT_HLIST_NULLS_HEAD(&sap->sk_laddr_hash[i], i); refcount_set(&sap->refcnt, 1); } return sap; } static struct llc_sap *__llc_sap_find(unsigned char sap_value) { struct llc_sap *sap; list_for_each_entry(sap, &llc_sap_list, node) if (sap->laddr.lsap == sap_value) goto out; sap = NULL; out: return sap; } /** * llc_sap_find - searches a SAP in station * @sap_value: sap to be found * * Searches for a sap in the sap list of the LLC's station upon the sap ID. * If the sap is found it will be refcounted and the user will have to do * a llc_sap_put after use. * Returns the sap or %NULL if not found. */ struct llc_sap *llc_sap_find(unsigned char sap_value) { struct llc_sap *sap; rcu_read_lock_bh(); sap = __llc_sap_find(sap_value); if (!sap || !llc_sap_hold_safe(sap)) sap = NULL; rcu_read_unlock_bh(); return sap; } /** * llc_sap_open - open interface to the upper layers. * @lsap: SAP number. * @func: rcv func for datalink protos * * Interface function to upper layer. Each one who wants to get a SAP * (for example NetBEUI) should call this function. Returns the opened * SAP for success, NULL for failure. */ struct llc_sap *llc_sap_open(unsigned char lsap, int (*func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)) { struct llc_sap *sap = NULL; spin_lock_bh(&llc_sap_list_lock); if (__llc_sap_find(lsap)) /* SAP already exists */ goto out; sap = llc_sap_alloc(); if (!sap) goto out; sap->laddr.lsap = lsap; sap->rcv_func = func; list_add_tail_rcu(&sap->node, &llc_sap_list); out: spin_unlock_bh(&llc_sap_list_lock); return sap; } /** * llc_sap_close - close interface for upper layers. * @sap: SAP to be closed. * * Close interface function to upper layer. Each one who wants to * close an open SAP (for example NetBEUI) should call this function. * Removes this sap from the list of saps in the station and then * frees the memory for this sap. */ void llc_sap_close(struct llc_sap *sap) { WARN_ON(sap->sk_count); spin_lock_bh(&llc_sap_list_lock); list_del_rcu(&sap->node); spin_unlock_bh(&llc_sap_list_lock); kfree_rcu(sap, rcu); } static struct packet_type llc_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_802_2), .func = llc_rcv, }; static int __init llc_init(void) { dev_add_pack(&llc_packet_type); return 0; } static void __exit llc_exit(void) { dev_remove_pack(&llc_packet_type); } module_init(llc_init); module_exit(llc_exit); EXPORT_SYMBOL(llc_sap_list); EXPORT_SYMBOL(llc_sap_find); EXPORT_SYMBOL(llc_sap_open); EXPORT_SYMBOL(llc_sap_close); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Procom 1997, Jay Schullist 2001, Arnaldo C. Melo 2001-2003"); MODULE_DESCRIPTION("LLC IEEE 802.2 core support"); |
| 14 15 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2002-2004, Instant802 Networks, Inc. * Copyright 2008, Jouni Malinen <j@w1.fi> * Copyright (C) 2016-2017 Intel Deutschland GmbH * Copyright (C) 2020-2021 Intel Corporation */ #include <linux/netdevice.h> #include <linux/types.h> #include <linux/skbuff.h> #include <linux/compiler.h> #include <linux/ieee80211.h> #include <linux/gfp.h> #include <asm/unaligned.h> #include <net/mac80211.h> #include <crypto/aes.h> #include <crypto/algapi.h> #include "ieee80211_i.h" #include "michael.h" #include "tkip.h" #include "aes_ccm.h" #include "aes_cmac.h" #include "aes_gmac.h" #include "aes_gcm.h" #include "wpa.h" ieee80211_tx_result ieee80211_tx_h_michael_mic_add(struct ieee80211_tx_data *tx) { u8 *data, *key, *mic; size_t data_len; unsigned int hdrlen; struct ieee80211_hdr *hdr; struct sk_buff *skb = tx->skb; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int tail; hdr = (struct ieee80211_hdr *)skb->data; if (!tx->key || tx->key->conf.cipher != WLAN_CIPHER_SUITE_TKIP || skb->len < 24 || !ieee80211_is_data_present(hdr->frame_control)) return TX_CONTINUE; hdrlen = ieee80211_hdrlen(hdr->frame_control); if (skb->len < hdrlen) return TX_DROP; data = skb->data + hdrlen; data_len = skb->len - hdrlen; if (unlikely(info->flags & IEEE80211_TX_INTFL_TKIP_MIC_FAILURE)) { /* Need to use software crypto for the test */ info->control.hw_key = NULL; } if (info->control.hw_key && (info->flags & IEEE80211_TX_CTL_DONTFRAG || ieee80211_hw_check(&tx->local->hw, SUPPORTS_TX_FRAG)) && !(tx->key->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | IEEE80211_KEY_FLAG_PUT_MIC_SPACE))) { /* hwaccel - with no need for SW-generated MMIC or MIC space */ return TX_CONTINUE; } tail = MICHAEL_MIC_LEN; if (!info->control.hw_key) tail += IEEE80211_TKIP_ICV_LEN; if (WARN(skb_tailroom(skb) < tail || skb_headroom(skb) < IEEE80211_TKIP_IV_LEN, "mmic: not enough head/tail (%d/%d,%d/%d)\n", skb_headroom(skb), IEEE80211_TKIP_IV_LEN, skb_tailroom(skb), tail)) return TX_DROP; mic = skb_put(skb, MICHAEL_MIC_LEN); if (tx->key->conf.flags & IEEE80211_KEY_FLAG_PUT_MIC_SPACE) { /* Zeroed MIC can help with debug */ memset(mic, 0, MICHAEL_MIC_LEN); return TX_CONTINUE; } key = &tx->key->conf.key[NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY]; michael_mic(key, hdr, data, data_len, mic); if (unlikely(info->flags & IEEE80211_TX_INTFL_TKIP_MIC_FAILURE)) mic[0]++; return TX_CONTINUE; } ieee80211_rx_result ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) { u8 *data, *key = NULL; size_t data_len; unsigned int hdrlen; u8 mic[MICHAEL_MIC_LEN]; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; /* * it makes no sense to check for MIC errors on anything other * than data frames. */ if (!ieee80211_is_data_present(hdr->frame_control)) return RX_CONTINUE; /* * No way to verify the MIC if the hardware stripped it or * the IV with the key index. In this case we have solely rely * on the driver to set RX_FLAG_MMIC_ERROR in the event of a * MIC failure report. */ if (status->flag & (RX_FLAG_MMIC_STRIPPED | RX_FLAG_IV_STRIPPED)) { if (status->flag & RX_FLAG_MMIC_ERROR) goto mic_fail_no_key; if (!(status->flag & RX_FLAG_IV_STRIPPED) && rx->key && rx->key->conf.cipher == WLAN_CIPHER_SUITE_TKIP) goto update_iv; return RX_CONTINUE; } /* * Some hardware seems to generate Michael MIC failure reports; even * though, the frame was not encrypted with TKIP and therefore has no * MIC. Ignore the flag them to avoid triggering countermeasures. */ if (!rx->key || rx->key->conf.cipher != WLAN_CIPHER_SUITE_TKIP || !(status->flag & RX_FLAG_DECRYPTED)) return RX_CONTINUE; if (rx->sdata->vif.type == NL80211_IFTYPE_AP && rx->key->conf.keyidx) { /* * APs with pairwise keys should never receive Michael MIC * errors for non-zero keyidx because these are reserved for * group keys and only the AP is sending real multicast * frames in the BSS. */ return RX_DROP_UNUSABLE; } if (status->flag & RX_FLAG_MMIC_ERROR) goto mic_fail; hdrlen = ieee80211_hdrlen(hdr->frame_control); if (skb->len < hdrlen + MICHAEL_MIC_LEN) return RX_DROP_UNUSABLE; if (skb_linearize(rx->skb)) return RX_DROP_UNUSABLE; hdr = (void *)skb->data; data = skb->data + hdrlen; data_len = skb->len - hdrlen - MICHAEL_MIC_LEN; key = &rx->key->conf.key[NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY]; michael_mic(key, hdr, data, data_len, mic); if (crypto_memneq(mic, data + data_len, MICHAEL_MIC_LEN)) goto mic_fail; /* remove Michael MIC from payload */ skb_trim(skb, skb->len - MICHAEL_MIC_LEN); update_iv: /* update IV in key information to be able to detect replays */ rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip.iv32; rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip.iv16; return RX_CONTINUE; mic_fail: rx->key->u.tkip.mic_failures++; mic_fail_no_key: /* * In some cases the key can be unset - e.g. a multicast packet, in * a driver that supports HW encryption. Send up the key idx only if * t |