| 9 9 9 9 9 9 9 9 9 9 9 9 400 43 460 402 401 400 399 402 613 611 609 612 255 254 47 47 47 47 46 47 47 47 48 47 46 47 47 45 46 47 46 48 48 47 47 47 47 48 48 17 14 46 47 47 44 44 44 44 44 41 44 44 44 43 44 43 44 16 17 44 43 33 44 44 44 44 48 44 47 46 47 47 45 47 44 46 46 44 45 610 611 613 6 6 6 610 610 608 610 607 255 253 253 253 251 253 254 255 253 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 | // SPDX-License-Identifier: GPL-2.0 #include <linux/memcontrol.h> #include <linux/rwsem.h> #include <linux/shrinker.h> #include <linux/rculist.h> #include <trace/events/vmscan.h> #include "internal.h" LIST_HEAD(shrinker_list); DEFINE_MUTEX(shrinker_mutex); #ifdef CONFIG_MEMCG static int shrinker_nr_max; static inline int shrinker_unit_size(int nr_items) { return (DIV_ROUND_UP(nr_items, SHRINKER_UNIT_BITS) * sizeof(struct shrinker_info_unit *)); } static inline void shrinker_unit_free(struct shrinker_info *info, int start) { struct shrinker_info_unit **unit; int nr, i; if (!info) return; unit = info->unit; nr = DIV_ROUND_UP(info->map_nr_max, SHRINKER_UNIT_BITS); for (i = start; i < nr; i++) { if (!unit[i]) break; kfree(unit[i]); unit[i] = NULL; } } static inline int shrinker_unit_alloc(struct shrinker_info *new, struct shrinker_info *old, int nid) { struct shrinker_info_unit *unit; int nr = DIV_ROUND_UP(new->map_nr_max, SHRINKER_UNIT_BITS); int start = old ? DIV_ROUND_UP(old->map_nr_max, SHRINKER_UNIT_BITS) : 0; int i; for (i = start; i < nr; i++) { unit = kzalloc_node(sizeof(*unit), GFP_KERNEL, nid); if (!unit) { shrinker_unit_free(new, start); return -ENOMEM; } new->unit[i] = unit; } return 0; } void free_shrinker_info(struct mem_cgroup *memcg) { struct mem_cgroup_per_node *pn; struct shrinker_info *info; int nid; for_each_node(nid) { pn = memcg->nodeinfo[nid]; info = rcu_dereference_protected(pn->shrinker_info, true); shrinker_unit_free(info, 0); kvfree(info); rcu_assign_pointer(pn->shrinker_info, NULL); } } int alloc_shrinker_info(struct mem_cgroup *memcg) { struct shrinker_info *info; int nid, ret = 0; int array_size = 0; mutex_lock(&shrinker_mutex); array_size = shrinker_unit_size(shrinker_nr_max); for_each_node(nid) { info = kvzalloc_node(sizeof(*info) + array_size, GFP_KERNEL, nid); if (!info) goto err; info->map_nr_max = shrinker_nr_max; if (shrinker_unit_alloc(info, NULL, nid)) goto err; rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } mutex_unlock(&shrinker_mutex); return ret; err: mutex_unlock(&shrinker_mutex); free_shrinker_info(memcg); return -ENOMEM; } static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, int nid) { return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, lockdep_is_held(&shrinker_mutex)); } static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size, int old_size, int new_nr_max) { struct shrinker_info *new, *old; struct mem_cgroup_per_node *pn; int nid; for_each_node(nid) { pn = memcg->nodeinfo[nid]; old = shrinker_info_protected(memcg, nid); /* Not yet online memcg */ if (!old) return 0; /* Already expanded this shrinker_info */ if (new_nr_max <= old->map_nr_max) continue; new = kvzalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid); if (!new) return -ENOMEM; new->map_nr_max = new_nr_max; memcpy(new->unit, old->unit, old_size); if (shrinker_unit_alloc(new, old, nid)) { kvfree(new); return -ENOMEM; } rcu_assign_pointer(pn->shrinker_info, new); kvfree_rcu(old, rcu); } return 0; } static int expand_shrinker_info(int new_id) { int ret = 0; int new_nr_max = round_up(new_id + 1, SHRINKER_UNIT_BITS); int new_size, old_size = 0; struct mem_cgroup *memcg; if (!root_mem_cgroup) goto out; lockdep_assert_held(&shrinker_mutex); new_size = shrinker_unit_size(new_nr_max); old_size = shrinker_unit_size(shrinker_nr_max); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { ret = expand_one_shrinker_info(memcg, new_size, old_size, new_nr_max); if (ret) { mem_cgroup_iter_break(NULL, memcg); goto out; } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); out: if (!ret) shrinker_nr_max = new_nr_max; return ret; } static inline int shrinker_id_to_index(int shrinker_id) { return shrinker_id / SHRINKER_UNIT_BITS; } static inline int shrinker_id_to_offset(int shrinker_id) { return shrinker_id % SHRINKER_UNIT_BITS; } static inline int calc_shrinker_id(int index, int offset) { return index * SHRINKER_UNIT_BITS + offset; } void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { struct shrinker_info *info; struct shrinker_info_unit *unit; rcu_read_lock(); info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); unit = info->unit[shrinker_id_to_index(shrinker_id)]; if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { /* Pairs with smp mb in shrink_slab() */ smp_mb__before_atomic(); set_bit(shrinker_id_to_offset(shrinker_id), unit->map); } rcu_read_unlock(); } } static DEFINE_IDR(shrinker_idr); static int shrinker_memcg_alloc(struct shrinker *shrinker) { int id, ret = -ENOMEM; if (mem_cgroup_disabled()) return -ENOSYS; mutex_lock(&shrinker_mutex); id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; if (id >= shrinker_nr_max) { if (expand_shrinker_info(id)) { idr_remove(&shrinker_idr, id); goto unlock; } } shrinker->id = id; ret = 0; unlock: mutex_unlock(&shrinker_mutex); return ret; } static void shrinker_memcg_remove(struct shrinker *shrinker) { int id = shrinker->id; BUG_ON(id < 0); lockdep_assert_held(&shrinker_mutex); idr_remove(&shrinker_idr, id); } static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { struct shrinker_info *info; struct shrinker_info_unit *unit; long nr_deferred; rcu_read_lock(); info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); unit = info->unit[shrinker_id_to_index(shrinker->id)]; nr_deferred = atomic_long_xchg(&unit->nr_deferred[shrinker_id_to_offset(shrinker->id)], 0); rcu_read_unlock(); return nr_deferred; } static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { struct shrinker_info *info; struct shrinker_info_unit *unit; long nr_deferred; rcu_read_lock(); info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); unit = info->unit[shrinker_id_to_index(shrinker->id)]; nr_deferred = atomic_long_add_return(nr, &unit->nr_deferred[shrinker_id_to_offset(shrinker->id)]); rcu_read_unlock(); return nr_deferred; } void reparent_shrinker_deferred(struct mem_cgroup *memcg) { int nid, index, offset; long nr; struct mem_cgroup *parent; struct shrinker_info *child_info, *parent_info; struct shrinker_info_unit *child_unit, *parent_unit; parent = parent_mem_cgroup(memcg); if (!parent) parent = root_mem_cgroup; /* Prevent from concurrent shrinker_info expand */ mutex_lock(&shrinker_mutex); for_each_node(nid) { child_info = shrinker_info_protected(memcg, nid); parent_info = shrinker_info_protected(parent, nid); for (index = 0; index < shrinker_id_to_index(child_info->map_nr_max); index++) { child_unit = child_info->unit[index]; parent_unit = parent_info->unit[index]; for (offset = 0; offset < SHRINKER_UNIT_BITS; offset++) { nr = atomic_long_read(&child_unit->nr_deferred[offset]); atomic_long_add(nr, &parent_unit->nr_deferred[offset]); } } } mutex_unlock(&shrinker_mutex); } #else static int shrinker_memcg_alloc(struct shrinker *shrinker) { return -ENOSYS; } static void shrinker_memcg_remove(struct shrinker *shrinker) { } static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { return 0; } static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { return 0; } #endif /* CONFIG_MEMCG */ static long xchg_nr_deferred(struct shrinker *shrinker, struct shrink_control *sc) { int nid = sc->nid; if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) nid = 0; if (sc->memcg && (shrinker->flags & SHRINKER_MEMCG_AWARE)) return xchg_nr_deferred_memcg(nid, shrinker, sc->memcg); return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); } static long add_nr_deferred(long nr, struct shrinker *shrinker, struct shrink_control *sc) { int nid = sc->nid; if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) nid = 0; if (sc->memcg && (shrinker->flags & SHRINKER_MEMCG_AWARE)) return add_nr_deferred_memcg(nr, nid, shrinker, sc->memcg); return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); } #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, struct shrinker *shrinker, int priority) { unsigned long freed = 0; unsigned long long delta; long total_scan; long freeable; long nr; long new_nr; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; long scanned = 0, next_deferred; freeable = shrinker->count_objects(shrinker, shrinkctl); if (freeable == 0 || freeable == SHRINK_EMPTY) return freeable; /* * copy the current shrinker scan count into a local variable * and zero it so that other concurrent shrinker invocations * don't also do this scanning work. */ nr = xchg_nr_deferred(shrinker, shrinkctl); if (shrinker->seeks) { delta = freeable >> priority; delta *= 4; do_div(delta, shrinker->seeks); } else { /* * These objects don't require any IO to create. Trim * them aggressively under memory pressure to keep * them from causing refetches in the IO caches. */ delta = freeable / 2; } total_scan = nr >> priority; total_scan += delta; total_scan = min(total_scan, (2 * freeable)); trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, freeable, delta, total_scan, priority); /* * Normally, we should not scan less than batch_size objects in one * pass to avoid too frequent shrinker calls, but if the slab has less * than batch_size objects in total and we are really tight on memory, * we will try to reclaim all available objects, otherwise we can end * up failing allocations although there are plenty of reclaimable * objects spread over several slabs with usage less than the * batch_size. * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || total_scan >= freeable) { unsigned long ret; unsigned long nr_to_scan = min(batch_size, total_scan); shrinkctl->nr_to_scan = nr_to_scan; shrinkctl->nr_scanned = nr_to_scan; ret = shrinker->scan_objects(shrinker, shrinkctl); if (ret == SHRINK_STOP) break; freed += ret; count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); total_scan -= shrinkctl->nr_scanned; scanned += shrinkctl->nr_scanned; cond_resched(); } /* * The deferred work is increased by any new work (delta) that wasn't * done, decreased by old deferred work that was done now. * * And it is capped to two times of the freeable items. */ next_deferred = max_t(long, (nr + delta - scanned), 0); next_deferred = min(next_deferred, (2 * freeable)); /* * move the unused scan count back into the shrinker in a * manner that handles concurrent updates. */ new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); return freed; } #ifdef CONFIG_MEMCG static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { struct shrinker_info *info; unsigned long ret, freed = 0; int offset, index = 0; if (!mem_cgroup_online(memcg)) return 0; /* * lockless algorithm of memcg shrink. * * The shrinker_info may be freed asynchronously via RCU in the * expand_one_shrinker_info(), so the rcu_read_lock() needs to be used * to ensure the existence of the shrinker_info. * * The shrinker_info_unit is never freed unless its corresponding memcg * is destroyed. Here we already hold the refcount of memcg, so the * memcg will not be destroyed, and of course shrinker_info_unit will * not be freed. * * So in the memcg shrink: * step 1: use rcu_read_lock() to guarantee existence of the * shrinker_info. * step 2: after getting shrinker_info_unit we can safely release the * RCU lock. * step 3: traverse the bitmap and calculate shrinker_id * step 4: use rcu_read_lock() to guarantee existence of the shrinker. * step 5: use shrinker_id to find the shrinker, then use * shrinker_try_get() to guarantee existence of the shrinker, * then we can release the RCU lock to do do_shrink_slab() that * may sleep. * step 6: do shrinker_put() paired with step 5 to put the refcount, * if the refcount reaches 0, then wake up the waiter in * shrinker_free() by calling complete(). * Note: here is different from the global shrink, we don't * need to acquire the RCU lock to guarantee existence of * the shrinker, because we don't need to use this * shrinker to traverse the next shrinker in the bitmap. * step 7: we have already exited the read-side of rcu critical section * before calling do_shrink_slab(), the shrinker_info may be * released in expand_one_shrinker_info(), so go back to step 1 * to reacquire the shrinker_info. */ again: rcu_read_lock(); info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); if (unlikely(!info)) goto unlock; if (index < shrinker_id_to_index(info->map_nr_max)) { struct shrinker_info_unit *unit; unit = info->unit[index]; rcu_read_unlock(); for_each_set_bit(offset, unit->map, SHRINKER_UNIT_BITS) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; struct shrinker *shrinker; int shrinker_id = calc_shrinker_id(index, offset); rcu_read_lock(); shrinker = idr_find(&shrinker_idr, shrinker_id); if (unlikely(!shrinker || !shrinker_try_get(shrinker))) { clear_bit(offset, unit->map); rcu_read_unlock(); continue; } rcu_read_unlock(); /* Call non-slab shrinkers even though kmem is disabled */ if (!memcg_kmem_online() && !(shrinker->flags & SHRINKER_NONSLAB)) continue; ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) { clear_bit(offset, unit->map); /* * After the shrinker reported that it had no objects to * free, but before we cleared the corresponding bit in * the memcg shrinker map, a new object might have been * added. To make sure, we have the bit set in this * case, we invoke the shrinker one more time and reset * the bit if it reports that it is not empty anymore. * The memory barrier here pairs with the barrier in * set_shrinker_bit(): * * list_lru_add() shrink_slab_memcg() * list_add_tail() clear_bit() * <MB> <MB> * set_bit() do_shrink_slab() */ smp_mb__after_atomic(); ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; else set_shrinker_bit(memcg, nid, shrinker_id); } freed += ret; shrinker_put(shrinker); } index++; goto again; } unlock: rcu_read_unlock(); return freed; } #else /* !CONFIG_MEMCG */ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { return 0; } #endif /* CONFIG_MEMCG */ /** * shrink_slab - shrink slab caches * @gfp_mask: allocation context * @nid: node whose slab caches to target * @memcg: memory cgroup whose slab caches to target * @priority: the reclaim priority * * Call the shrink functions to age shrinkable caches. * * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, * unaware shrinkers will receive a node id of 0 instead. * * @memcg specifies the memory cgroup to target. Unaware shrinkers * are called only if it is the root cgroup. * * @priority is sc->priority, we take the number of objects and >> by priority * in order to get the scan target. * * Returns the number of reclaimed slab objects. */ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { unsigned long ret, freed = 0; struct shrinker *shrinker; /* * The root memcg might be allocated even though memcg is disabled * via "cgroup_disable=memory" boot parameter. This could make * mem_cgroup_is_root() return false, then just run memcg slab * shrink, but skip global shrink. This may result in premature * oom. */ if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); /* * lockless algorithm of global shrink. * * In the unregistration setp, the shrinker will be freed asynchronously * via RCU after its refcount reaches 0. So both rcu_read_lock() and * shrinker_try_get() can be used to ensure the existence of the shrinker. * * So in the global shrink: * step 1: use rcu_read_lock() to guarantee existence of the shrinker * and the validity of the shrinker_list walk. * step 2: use shrinker_try_get() to try get the refcount, if successful, * then the existence of the shrinker can also be guaranteed, * so we can release the RCU lock to do do_shrink_slab() that * may sleep. * step 3: *MUST* to reacquire the RCU lock before calling shrinker_put(), * which ensures that neither this shrinker nor the next shrinker * will be freed in the next traversal operation. * step 4: do shrinker_put() paired with step 2 to put the refcount, * if the refcount reaches 0, then wake up the waiter in * shrinker_free() by calling complete(). */ rcu_read_lock(); list_for_each_entry_rcu(shrinker, &shrinker_list, list) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; if (!shrinker_try_get(shrinker)) continue; rcu_read_unlock(); ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; freed += ret; rcu_read_lock(); shrinker_put(shrinker); } rcu_read_unlock(); cond_resched(); return freed; } struct shrinker *shrinker_alloc(unsigned int flags, const char *fmt, ...) { struct shrinker *shrinker; unsigned int size; va_list ap; int err; shrinker = kzalloc(sizeof(struct shrinker), GFP_KERNEL); if (!shrinker) return NULL; va_start(ap, fmt); err = shrinker_debugfs_name_alloc(shrinker, fmt, ap); va_end(ap); if (err) goto err_name; shrinker->flags = flags | SHRINKER_ALLOCATED; shrinker->seeks = DEFAULT_SEEKS; if (flags & SHRINKER_MEMCG_AWARE) { err = shrinker_memcg_alloc(shrinker); if (err == -ENOSYS) { /* Memcg is not supported, fallback to non-memcg-aware shrinker. */ shrinker->flags &= ~SHRINKER_MEMCG_AWARE; goto non_memcg; } if (err) goto err_flags; return shrinker; } non_memcg: /* * The nr_deferred is available on per memcg level for memcg aware * shrinkers, so only allocate nr_deferred in the following cases: * - non-memcg-aware shrinkers * - !CONFIG_MEMCG * - memcg is disabled by kernel command line */ size = sizeof(*shrinker->nr_deferred); if (flags & SHRINKER_NUMA_AWARE) size *= nr_node_ids; shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); if (!shrinker->nr_deferred) goto err_flags; return shrinker; err_flags: shrinker_debugfs_name_free(shrinker); err_name: kfree(shrinker); return NULL; } EXPORT_SYMBOL_GPL(shrinker_alloc); void shrinker_register(struct shrinker *shrinker) { if (unlikely(!(shrinker->flags & SHRINKER_ALLOCATED))) { pr_warn("Must use shrinker_alloc() to dynamically allocate the shrinker"); return; } mutex_lock(&shrinker_mutex); list_add_tail_rcu(&shrinker->list, &shrinker_list); shrinker->flags |= SHRINKER_REGISTERED; shrinker_debugfs_add(shrinker); mutex_unlock(&shrinker_mutex); init_completion(&shrinker->done); /* * Now the shrinker is fully set up, take the first reference to it to * indicate that lookup operations are now allowed to use it via * shrinker_try_get(). */ refcount_set(&shrinker->refcount, 1); } EXPORT_SYMBOL_GPL(shrinker_register); static void shrinker_free_rcu_cb(struct rcu_head *head) { struct shrinker *shrinker = container_of(head, struct shrinker, rcu); kfree(shrinker->nr_deferred); kfree(shrinker); } void shrinker_free(struct shrinker *shrinker) { struct dentry *debugfs_entry = NULL; int debugfs_id; if (!shrinker) return; if (shrinker->flags & SHRINKER_REGISTERED) { /* drop the initial refcount */ shrinker_put(shrinker); /* * Wait for all lookups of the shrinker to complete, after that, * no shrinker is running or will run again, then we can safely * free it asynchronously via RCU and safely free the structure * where the shrinker is located, such as super_block etc. */ wait_for_completion(&shrinker->done); } mutex_lock(&shrinker_mutex); if (shrinker->flags & SHRINKER_REGISTERED) { /* * Now we can safely remove it from the shrinker_list and then * free it. */ list_del_rcu(&shrinker->list); debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); shrinker->flags &= ~SHRINKER_REGISTERED; } shrinker_debugfs_name_free(shrinker); if (shrinker->flags & SHRINKER_MEMCG_AWARE) shrinker_memcg_remove(shrinker); mutex_unlock(&shrinker_mutex); if (debugfs_entry) shrinker_debugfs_remove(debugfs_entry, debugfs_id); call_rcu(&shrinker->rcu, shrinker_free_rcu_cb); } EXPORT_SYMBOL_GPL(shrinker_free); |
| 2 2 5 2 1 1 1 1 8 6 5 5 3 2 1 3 8 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved. */ #include <linux/fs.h> #include <linux/filelock.h> #include <linux/miscdevice.h> #include <linux/poll.h> #include <linux/dlm.h> #include <linux/dlm_plock.h> #include <linux/slab.h> #include <trace/events/dlm.h> #include "dlm_internal.h" #include "lockspace.h" static DEFINE_SPINLOCK(ops_lock); static LIST_HEAD(send_list); static LIST_HEAD(recv_list); static DECLARE_WAIT_QUEUE_HEAD(send_wq); static DECLARE_WAIT_QUEUE_HEAD(recv_wq); struct plock_async_data { void *fl; void *file; struct file_lock flc; int (*callback)(struct file_lock *fl, int result); }; struct plock_op { struct list_head list; int done; struct dlm_plock_info info; /* if set indicates async handling */ struct plock_async_data *data; }; static inline void set_version(struct dlm_plock_info *info) { info->version[0] = DLM_PLOCK_VERSION_MAJOR; info->version[1] = DLM_PLOCK_VERSION_MINOR; info->version[2] = DLM_PLOCK_VERSION_PATCH; } static struct plock_op *plock_lookup_waiter(const struct dlm_plock_info *info) { struct plock_op *op = NULL, *iter; list_for_each_entry(iter, &recv_list, list) { if (iter->info.fsid == info->fsid && iter->info.number == info->number && iter->info.owner == info->owner && iter->info.pid == info->pid && iter->info.start == info->start && iter->info.end == info->end && iter->info.ex == info->ex && iter->info.wait) { op = iter; break; } } return op; } static int check_version(struct dlm_plock_info *info) { if ((DLM_PLOCK_VERSION_MAJOR != info->version[0]) || (DLM_PLOCK_VERSION_MINOR < info->version[1])) { log_print("plock device version mismatch: " "kernel (%u.%u.%u), user (%u.%u.%u)", DLM_PLOCK_VERSION_MAJOR, DLM_PLOCK_VERSION_MINOR, DLM_PLOCK_VERSION_PATCH, info->version[0], info->version[1], info->version[2]); return -EINVAL; } return 0; } static void dlm_release_plock_op(struct plock_op *op) { kfree(op->data); kfree(op); } static void send_op(struct plock_op *op) { set_version(&op->info); spin_lock(&ops_lock); list_add_tail(&op->list, &send_list); spin_unlock(&ops_lock); wake_up(&send_wq); } static int do_lock_cancel(const struct dlm_plock_info *orig_info) { struct plock_op *op; int rv; op = kzalloc(sizeof(*op), GFP_NOFS); if (!op) return -ENOMEM; op->info = *orig_info; op->info.optype = DLM_PLOCK_OP_CANCEL; op->info.wait = 0; send_op(op); wait_event(recv_wq, (op->done != 0)); rv = op->info.rv; dlm_release_plock_op(op); return rv; } int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, int cmd, struct file_lock *fl) { struct plock_async_data *op_data; struct dlm_ls *ls; struct plock_op *op; int rv; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; op = kzalloc(sizeof(*op), GFP_NOFS); if (!op) { rv = -ENOMEM; goto out; } op->info.optype = DLM_PLOCK_OP_LOCK; op->info.pid = fl->c.flc_pid; op->info.ex = lock_is_write(fl); op->info.wait = !!(fl->c.flc_flags & FL_SLEEP); op->info.fsid = ls->ls_global_id; op->info.number = number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; op->info.owner = (__u64)(long) fl->c.flc_owner; /* async handling */ if (fl->fl_lmops && fl->fl_lmops->lm_grant) { op_data = kzalloc(sizeof(*op_data), GFP_NOFS); if (!op_data) { dlm_release_plock_op(op); rv = -ENOMEM; goto out; } op_data->callback = fl->fl_lmops->lm_grant; locks_init_lock(&op_data->flc); locks_copy_lock(&op_data->flc, fl); op_data->fl = fl; op_data->file = file; op->data = op_data; send_op(op); rv = FILE_LOCK_DEFERRED; goto out; } send_op(op); if (op->info.wait) { rv = wait_event_interruptible(recv_wq, (op->done != 0)); if (rv == -ERESTARTSYS) { spin_lock(&ops_lock); /* recheck under ops_lock if we got a done != 0, * if so this interrupt case should be ignored */ if (op->done != 0) { spin_unlock(&ops_lock); goto do_lock_wait; } spin_unlock(&ops_lock); rv = do_lock_cancel(&op->info); switch (rv) { case 0: /* waiter was deleted in user space, answer will never come * remove original request. The original request must be * on recv_list because the answer of do_lock_cancel() * synchronized it. */ spin_lock(&ops_lock); list_del(&op->list); spin_unlock(&ops_lock); rv = -EINTR; break; case -ENOENT: /* cancellation wasn't successful but op should be done */ fallthrough; default: /* internal error doing cancel we need to wait */ goto wait; } log_debug(ls, "%s: wait interrupted %x %llx pid %d", __func__, ls->ls_global_id, (unsigned long long)number, op->info.pid); dlm_release_plock_op(op); goto out; } } else { wait: wait_event(recv_wq, (op->done != 0)); } do_lock_wait: WARN_ON(!list_empty(&op->list)); rv = op->info.rv; if (!rv) { if (locks_lock_file_wait(file, fl) < 0) log_error(ls, "dlm_posix_lock: vfs lock error %llx", (unsigned long long)number); } dlm_release_plock_op(op); out: dlm_put_lockspace(ls); return rv; } EXPORT_SYMBOL_GPL(dlm_posix_lock); /* Returns failure iff a successful lock operation should be canceled */ static int dlm_plock_callback(struct plock_op *op) { struct plock_async_data *op_data = op->data; struct file *file; struct file_lock *fl; struct file_lock *flc; int (*notify)(struct file_lock *fl, int result) = NULL; int rv = 0; WARN_ON(!list_empty(&op->list)); /* check if the following 2 are still valid or make a copy */ file = op_data->file; flc = &op_data->flc; fl = op_data->fl; notify = op_data->callback; if (op->info.rv) { notify(fl, op->info.rv); goto out; } /* got fs lock; bookkeep locally as well: */ flc->c.flc_flags &= ~FL_SLEEP; if (posix_lock_file(file, flc, NULL)) { /* * This can only happen in the case of kmalloc() failure. * The filesystem's own lock is the authoritative lock, * so a failure to get the lock locally is not a disaster. * As long as the fs cannot reliably cancel locks (especially * in a low-memory situation), we're better off ignoring * this failure than trying to recover. */ log_print("dlm_plock_callback: vfs lock error %llx file %p fl %p", (unsigned long long)op->info.number, file, fl); } rv = notify(fl, 0); if (rv) { /* XXX: We need to cancel the fs lock here: */ log_print("%s: lock granted after lock request failed; dangling lock!", __func__); goto out; } out: dlm_release_plock_op(op); return rv; } int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, struct file_lock *fl) { struct dlm_ls *ls; struct plock_op *op; int rv; unsigned char saved_flags = fl->c.flc_flags; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; op = kzalloc(sizeof(*op), GFP_NOFS); if (!op) { rv = -ENOMEM; goto out; } /* cause the vfs unlock to return ENOENT if lock is not found */ fl->c.flc_flags |= FL_EXISTS; rv = locks_lock_file_wait(file, fl); if (rv == -ENOENT) { rv = 0; goto out_free; } if (rv < 0) { log_error(ls, "dlm_posix_unlock: vfs unlock error %d %llx", rv, (unsigned long long)number); } op->info.optype = DLM_PLOCK_OP_UNLOCK; op->info.pid = fl->c.flc_pid; op->info.fsid = ls->ls_global_id; op->info.number = number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; op->info.owner = (__u64)(long) fl->c.flc_owner; if (fl->c.flc_flags & FL_CLOSE) { op->info.flags |= DLM_PLOCK_FL_CLOSE; send_op(op); rv = 0; goto out; } send_op(op); wait_event(recv_wq, (op->done != 0)); WARN_ON(!list_empty(&op->list)); rv = op->info.rv; if (rv == -ENOENT) rv = 0; out_free: dlm_release_plock_op(op); out: dlm_put_lockspace(ls); fl->c.flc_flags = saved_flags; return rv; } EXPORT_SYMBOL_GPL(dlm_posix_unlock); /* * NOTE: This implementation can only handle async lock requests as nfs * do it. It cannot handle cancellation of a pending lock request sitting * in wait_event(), but for now only nfs is the only user local kernel * user. */ int dlm_posix_cancel(dlm_lockspace_t *lockspace, u64 number, struct file *file, struct file_lock *fl) { struct dlm_plock_info info; struct plock_op *op; struct dlm_ls *ls; int rv; /* this only works for async request for now and nfs is the only * kernel user right now. */ if (WARN_ON_ONCE(!fl->fl_lmops || !fl->fl_lmops->lm_grant)) return -EOPNOTSUPP; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; memset(&info, 0, sizeof(info)); info.pid = fl->c.flc_pid; info.ex = lock_is_write(fl); info.fsid = ls->ls_global_id; dlm_put_lockspace(ls); info.number = number; info.start = fl->fl_start; info.end = fl->fl_end; info.owner = (__u64)(long) fl->c.flc_owner; rv = do_lock_cancel(&info); switch (rv) { case 0: spin_lock(&ops_lock); /* lock request to cancel must be on recv_list because * do_lock_cancel() synchronizes it. */ op = plock_lookup_waiter(&info); if (WARN_ON_ONCE(!op)) { spin_unlock(&ops_lock); rv = -ENOLCK; break; } list_del(&op->list); spin_unlock(&ops_lock); WARN_ON(op->info.optype != DLM_PLOCK_OP_LOCK); op->data->callback(op->data->fl, -EINTR); dlm_release_plock_op(op); rv = -EINTR; break; case -ENOENT: /* if cancel wasn't successful we probably were to late * or it was a non-blocking lock request, so just unlock it. */ rv = dlm_posix_unlock(lockspace, number, file, fl); break; default: break; } return rv; } EXPORT_SYMBOL_GPL(dlm_posix_cancel); int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file, struct file_lock *fl) { struct dlm_ls *ls; struct plock_op *op; int rv; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; op = kzalloc(sizeof(*op), GFP_NOFS); if (!op) { rv = -ENOMEM; goto out; } op->info.optype = DLM_PLOCK_OP_GET; op->info.pid = fl->c.flc_pid; op->info.ex = lock_is_write(fl); op->info.fsid = ls->ls_global_id; op->info.number = number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; op->info.owner = (__u64)(long) fl->c.flc_owner; send_op(op); wait_event(recv_wq, (op->done != 0)); WARN_ON(!list_empty(&op->list)); /* info.rv from userspace is 1 for conflict, 0 for no-conflict, -ENOENT if there are no locks on the file */ rv = op->info.rv; fl->c.flc_type = F_UNLCK; if (rv == -ENOENT) rv = 0; else if (rv > 0) { locks_init_lock(fl); fl->c.flc_type = (op->info.ex) ? F_WRLCK : F_RDLCK; fl->c.flc_flags = FL_POSIX; fl->c.flc_pid = op->info.pid; if (op->info.nodeid != dlm_our_nodeid()) fl->c.flc_pid = -fl->c.flc_pid; fl->fl_start = op->info.start; fl->fl_end = op->info.end; rv = 0; } dlm_release_plock_op(op); out: dlm_put_lockspace(ls); return rv; } EXPORT_SYMBOL_GPL(dlm_posix_get); /* a read copies out one plock request from the send list */ static ssize_t dev_read(struct file *file, char __user *u, size_t count, loff_t *ppos) { struct dlm_plock_info info; struct plock_op *op = NULL; if (count < sizeof(info)) return -EINVAL; spin_lock(&ops_lock); if (!list_empty(&send_list)) { op = list_first_entry(&send_list, struct plock_op, list); if (op->info.flags & DLM_PLOCK_FL_CLOSE) list_del(&op->list); else list_move_tail(&op->list, &recv_list); memcpy(&info, &op->info, sizeof(info)); } spin_unlock(&ops_lock); if (!op) return -EAGAIN; trace_dlm_plock_read(&info); /* there is no need to get a reply from userspace for unlocks that were generated by the vfs cleaning up for a close (the process did not make an unlock call). */ if (op->info.flags & DLM_PLOCK_FL_CLOSE) dlm_release_plock_op(op); if (copy_to_user(u, &info, sizeof(info))) return -EFAULT; return sizeof(info); } /* a write copies in one plock result that should match a plock_op on the recv list */ static ssize_t dev_write(struct file *file, const char __user *u, size_t count, loff_t *ppos) { struct plock_op *op = NULL, *iter; struct dlm_plock_info info; int do_callback = 0; if (count != sizeof(info)) return -EINVAL; if (copy_from_user(&info, u, sizeof(info))) return -EFAULT; trace_dlm_plock_write(&info); if (check_version(&info)) return -EINVAL; /* * The results for waiting ops (SETLKW) can be returned in any * order, so match all fields to find the op. The results for * non-waiting ops are returned in the order that they were sent * to userspace, so match the result with the first non-waiting op. */ spin_lock(&ops_lock); if (info.wait) { op = plock_lookup_waiter(&info); } else { list_for_each_entry(iter, &recv_list, list) { if (!iter->info.wait && iter->info.fsid == info.fsid) { op = iter; break; } } } if (op) { /* Sanity check that op and info match. */ if (info.wait) WARN_ON(op->info.optype != DLM_PLOCK_OP_LOCK); else WARN_ON(op->info.number != info.number || op->info.owner != info.owner || op->info.optype != info.optype); list_del_init(&op->list); memcpy(&op->info, &info, sizeof(info)); if (op->data) do_callback = 1; else op->done = 1; } spin_unlock(&ops_lock); if (op) { if (do_callback) dlm_plock_callback(op); else wake_up(&recv_wq); } else pr_debug("%s: no op %x %llx", __func__, info.fsid, (unsigned long long)info.number); return count; } static __poll_t dev_poll(struct file *file, poll_table *wait) { __poll_t mask = 0; poll_wait(file, &send_wq, wait); spin_lock(&ops_lock); if (!list_empty(&send_list)) mask = EPOLLIN | EPOLLRDNORM; spin_unlock(&ops_lock); return mask; } static const struct file_operations dev_fops = { .read = dev_read, .write = dev_write, .poll = dev_poll, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice plock_dev_misc = { .minor = MISC_DYNAMIC_MINOR, .name = DLM_PLOCK_MISC_NAME, .fops = &dev_fops }; int dlm_plock_init(void) { int rv; rv = misc_register(&plock_dev_misc); if (rv) log_print("dlm_plock_init: misc_register failed %d", rv); return rv; } void dlm_plock_exit(void) { misc_deregister(&plock_dev_misc); WARN_ON(!list_empty(&send_list)); WARN_ON(!list_empty(&recv_list)); } |
| 48 50 46 46 3 3 3 46 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 | // SPDX-License-Identifier: GPL-2.0 /* * of.c The helpers for hcd device tree support * * Copyright (C) 2016 Freescale Semiconductor, Inc. * Author: Peter Chen <peter.chen@freescale.com> * Copyright (C) 2017 Johan Hovold <johan@kernel.org> */ #include <linux/of.h> #include <linux/of_graph.h> #include <linux/usb/of.h> /** * usb_of_get_device_node() - get a USB device node * @hub: hub to which device is connected * @port1: one-based index of port * * Look up the node of a USB device given its parent hub device and one-based * port number. * * Return: A pointer to the node with incremented refcount if found, or * %NULL otherwise. */ struct device_node *usb_of_get_device_node(struct usb_device *hub, int port1) { struct device_node *node; u32 reg; for_each_child_of_node(hub->dev.of_node, node) { if (of_property_read_u32(node, "reg", ®)) continue; if (reg == port1) return node; } return NULL; } EXPORT_SYMBOL_GPL(usb_of_get_device_node); /** * usb_of_has_combined_node() - determine whether a device has a combined node * @udev: USB device * * Determine whether a USB device has a so called combined node which is * shared with its sole interface. This is the case if and only if the device * has a node and its descriptors report the following: * * 1) bDeviceClass is 0 or 9, and * 2) bNumConfigurations is 1, and * 3) bNumInterfaces is 1. * * Return: True iff the device has a device node and its descriptors match the * criteria for a combined node. */ bool usb_of_has_combined_node(struct usb_device *udev) { struct usb_device_descriptor *ddesc = &udev->descriptor; struct usb_config_descriptor *cdesc; if (!udev->dev.of_node) return false; switch (ddesc->bDeviceClass) { case USB_CLASS_PER_INTERFACE: case USB_CLASS_HUB: if (ddesc->bNumConfigurations == 1) { cdesc = &udev->config->desc; if (cdesc->bNumInterfaces == 1) return true; } } return false; } EXPORT_SYMBOL_GPL(usb_of_has_combined_node); static bool usb_of_has_devices_or_graph(const struct usb_device *hub) { const struct device_node *np = hub->dev.of_node; struct device_node *child; if (of_graph_is_present(np)) return true; for_each_child_of_node(np, child) { if (of_property_present(child, "reg")) { of_node_put(child); return true; } } return false; } /** * usb_of_get_connect_type() - get a USB hub's port connect_type * @hub: hub to which port is for @port1 * @port1: one-based index of port * * Get the connect_type of @port1 based on the device node for @hub. If the * port is described in the OF graph, the connect_type is "hotplug". If the * @hub has a child device has with a 'reg' property equal to @port1 the * connect_type is "hard-wired". If there isn't an OF graph or child node at * all then the connect_type is "unknown". Otherwise, the port is considered * "unused" because it isn't described at all. * * Return: A connect_type for @port1 based on the device node for @hub. */ enum usb_port_connect_type usb_of_get_connect_type(struct usb_device *hub, int port1) { struct device_node *np, *child, *ep, *remote_np; enum usb_port_connect_type connect_type; /* Only set connect_type if binding has ports/hardwired devices. */ if (!usb_of_has_devices_or_graph(hub)) return USB_PORT_CONNECT_TYPE_UNKNOWN; /* Assume port is unused if there's a graph or a child node. */ connect_type = USB_PORT_NOT_USED; np = hub->dev.of_node; /* * Hotplug ports are connected to an available remote node, e.g. * usb-a-connector compatible node, in the OF graph. */ if (of_graph_is_present(np)) { ep = of_graph_get_endpoint_by_regs(np, port1, -1); if (ep) { remote_np = of_graph_get_remote_port_parent(ep); of_node_put(ep); if (of_device_is_available(remote_np)) connect_type = USB_PORT_CONNECT_TYPE_HOT_PLUG; of_node_put(remote_np); } } /* * Hard-wired ports are child nodes with a reg property corresponding * to the port number, i.e. a usb device. */ child = usb_of_get_device_node(hub, port1); if (of_device_is_available(child)) connect_type = USB_PORT_CONNECT_TYPE_HARD_WIRED; of_node_put(child); return connect_type; } EXPORT_SYMBOL_GPL(usb_of_get_connect_type); /** * usb_of_get_interface_node() - get a USB interface node * @udev: USB device of interface * @config: configuration value * @ifnum: interface number * * Look up the node of a USB interface given its USB device, configuration * value and interface number. * * Return: A pointer to the node with incremented refcount if found, or * %NULL otherwise. */ struct device_node * usb_of_get_interface_node(struct usb_device *udev, u8 config, u8 ifnum) { struct device_node *node; u32 reg[2]; for_each_child_of_node(udev->dev.of_node, node) { if (of_property_read_u32_array(node, "reg", reg, 2)) continue; if (reg[0] == ifnum && reg[1] == config) return node; } return NULL; } EXPORT_SYMBOL_GPL(usb_of_get_interface_node); |
| 36 41 36 74 611 98 45 53 30 4 46 8 30 91 68 63 5 7 121 192 102 46 124 46 105 54 75 54 30 30 106 76 76 74 74 2 100 100 8 106 106 105 3 3 3 106 106 9 122 56 41 41 80 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGETLB_H #define _LINUX_HUGETLB_H #include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/fs.h> #include <linux/hugetlb_inline.h> #include <linux/cgroup.h> #include <linux/page_ref.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> #include <linux/gfp.h> #include <linux/userfaultfd_k.h> struct ctl_table; struct user_struct; struct mmu_gather; struct node; void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE #include <linux/pagemap.h> #include <linux/shm.h> #include <asm/tlbflush.h> /* * For HugeTLB page, there are more metadata to save in the struct page. But * the head struct page cannot meet our needs, so we have to abuse other tail * struct page to store the metadata. */ #define __NR_USED_SUBPAGE 3 struct hugepage_subpool { spinlock_t lock; long count; long max_hpages; /* Maximum huge pages or -1 if no maximum. */ long used_hpages; /* Used count against maximum, includes */ /* both allocated and reserved pages. */ struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ /* satisfy minimum size. */ }; struct resv_map { struct kref refs; spinlock_t lock; struct list_head regions; long adds_in_progress; struct list_head region_cache; long region_cache_count; struct rw_semaphore rw_sema; #ifdef CONFIG_CGROUP_HUGETLB /* * On private mappings, the counter to uncharge reservations is stored * here. If these fields are 0, then either the mapping is shared, or * cgroup accounting is disabled for this resv_map. */ struct page_counter *reservation_counter; unsigned long pages_per_hpage; struct cgroup_subsys_state *css; #endif }; /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * * The region data structures are embedded into a resv_map and protected * by a resv_map's lock. The set of regions within the resv_map represent * reservations for huge pages, or huge pages that have already been * instantiated within the map. The from and to elements are huge page * indices into the associated mapping. from indicates the starting index * of the region. to represents the first index past the end of the region. * * For example, a file region structure with from == 0 and to == 4 represents * four huge pages in a mapping. It is important to note that the to element * represents the first element past the end of the region. This is used in * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. * * Interval notation of the form [from, to) will be used to indicate that * the endpoint from is inclusive and to is exclusive. */ struct file_region { struct list_head link; long from; long to; #ifdef CONFIG_CGROUP_HUGETLB /* * On shared mappings, each reserved region appears as a struct * file_region in resv_map. These fields hold the info needed to * uncharge each reservation. */ struct page_counter *reservation_counter; struct cgroup_subsys_state *css; #endif }; struct hugetlb_vma_lock { struct kref refs; struct rw_semaphore rw_sema; struct vm_area_struct *vma; }; extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); extern spinlock_t hugetlb_lock; extern int hugetlb_max_hstate __read_mostly; #define for_each_hstate(h) \ for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++) struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo_node(int nid); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void folio_putback_active_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address); struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages[MAX_NUMNODES]; /* arch callbacks */ #ifndef CONFIG_HIGHPTE /* * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures * which may go down to the lowest PTE level in their huge_pte_offset() and * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). */ static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) { return pte_offset_kernel(pmd, address); } static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); } #endif pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. * Returns the pte_t* if found, or NULL if the address is not mapped. * * IMPORTANT: we should normally not directly call this function, instead * this is only a common interface to implement arch-specific * walker. Please use hugetlb_walk() instead, because that will attempt to * verify the locking for you. * * Since this function will walk all the pgtable pages (including not only * high-level pgtable page, but also PUD entry that can be unshared * concurrently for VM_SHARED), the caller of this function should be * responsible of its thread safety. One can follow this rule: * * (1) For private mappings: pmd unsharing is not possible, so holding the * mmap_lock for either read or write is sufficient. Most callers * already hold the mmap_lock, so normally, no special action is * required. * * (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged * pgtable page can go away from under us! It can be done by a pmd * unshare with a follow up munmap() on the other process), then we * need either: * * (2.1) hugetlb vma lock read or write held, to make sure pmd unshare * won't happen upon the range (it also makes sure the pte_t we * read is the right and stable one), or, * * (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make * sure even if unshare happened the racy unmap() will wait until * i_mmap_rwsem is released. * * Option (2.1) is the safest, which guarantees pte stability from pmd * sharing pov, until the vma lock released. Option (2.2) doesn't protect * a concurrent pmd unshare, but it makes sure the pgtable page is safe to * access. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); extern void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *begin, unsigned long *end); extern void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details); static inline void hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_begin(vma, start, end); } static inline void hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_end(vma, details); } void hugetlb_vma_lock_read(struct vm_area_struct *vma); void hugetlb_vma_unlock_read(struct vm_area_struct *vma); void hugetlb_vma_lock_write(struct vm_area_struct *vma); void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) { } static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { } static inline unsigned long hugetlb_total_pages(void) { return 0; } static inline struct address_space *hugetlb_folio_mapping_lock_write( struct folio *folio) { return NULL; } static inline int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_begin( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_end( struct vm_area_struct *vma, struct zap_details *details) { } static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { BUG(); return 0; } static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { BUG(); return 0; } static inline void hugetlb_report_meminfo(struct seq_file *m) { } static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) { return 0; } static inline void hugetlb_show_meminfo_node(int nid) { } static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { return -EINVAL; } static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { } static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { return 1; } static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { } static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { BUG(); } #ifdef CONFIG_USERFAULTFD static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { BUG(); return 0; } #endif /* CONFIG_USERFAULTFD */ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { return NULL; } static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list) { return false; } static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { return 0; } static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { return 0; } static inline void folio_putback_active_hugetlb(struct folio *folio) { } static inline void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { } static inline long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { return 0; } static inline void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { BUG(); } static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { BUG(); return 0; } static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write static inline int pgd_write(pgd_t pgd) { BUG(); return 0; } #endif #define HUGETLB_ANON_FILE "anon_hugepage" enum { /* * The file will be used as an shm file so shmfs accounting rules * apply */ HUGETLB_SHMFS_INODE = 1, /* * The file is being created on the internal vfs mount and shmfs * accounting rules do not apply */ HUGETLB_ANONHUGE_INODE = 2, }; #ifdef CONFIG_HUGETLBFS struct hugetlbfs_sb_info { long max_inodes; /* inodes allowed */ long free_inodes; /* inodes free */ spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; kuid_t uid; kgid_t gid; umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) { return sb->s_fs_info; } struct hugetlbfs_inode_info { struct inode vfs_inode; unsigned int seals; }; static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) { return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); static inline bool is_file_hugepages(const struct file *file) { return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) { return HUGETLBFS_SB(i->i_sb)->hstate; } #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); } static inline struct hstate *hstate_inode(struct inode *i) { return NULL; } #endif /* !CONFIG_HUGETLBFS */ #ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ unsigned long generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be * used to manipulate these flags. * * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. * Synchronization: Examined or modified by code that knows it has * the only reference to page. i.e. After allocation but before use * or when the page is being freed. * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. * Synchronization: Initially set after new page allocation with no * locking. When examined and modified during migration processing * (isolate, migrate, putback) the hugetlb_lock is held. * HPG_temporary - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. * Synchronization: Can be set after huge page allocation from buddy when * code knows it has only reference. All other examinations and * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page * that is not tracked by raw_hwp_page list. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, HPG_vmemmap_optimized, HPG_raw_hwp_unreliable, __NR_HPAGEFLAGS, }; /* * Macros to create test, set and clear function definitions for * hugetlb specific page flags. */ #ifdef CONFIG_HUGETLB_PAGE #define TESTHPAGEFLAG(uname, flname) \ static __always_inline \ bool folio_test_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ return test_bit(HPG_##flname, private); \ } #define SETHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_set_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ set_bit(HPG_##flname, private); \ } #define CLEARHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_clear_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ clear_bit(HPG_##flname, private); \ } #else #define TESTHPAGEFLAG(uname, flname) \ static inline bool \ folio_test_hugetlb_##flname(struct folio *folio) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ static inline void \ folio_set_hugetlb_##flname(struct folio *folio) \ { } #define CLEARHPAGEFLAG(uname, flname) \ static inline void \ folio_clear_hugetlb_##flname(struct folio *folio) \ { } #endif #define HPAGEFLAG(uname, flname) \ TESTHPAGEFLAG(uname, flname) \ SETHPAGEFLAG(uname, flname) \ CLEARHPAGEFLAG(uname, flname) \ /* * Create functions associated with hugetlb page flags */ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) #ifdef CONFIG_HUGETLB_PAGE #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { struct mutex resize_lock; struct lock_class_key resize_key; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; unsigned long free_huge_pages; unsigned long resv_huge_pages; unsigned long surplus_huge_pages; unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; char name[HSTATE_NAME_LEN]; }; struct huge_bootmem_page { struct list_head list; struct hstate *hstate; }; int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback); struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); int __init alloc_bootmem_huge_page(struct hstate *h, int nid); bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE #define HUGE_MAX_HSTATE 1 #endif extern struct hstate hstates[HUGE_MAX_HSTATE]; extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return folio->_hugetlb_subpool; } static inline void hugetlb_set_folio_subpool(struct folio *folio, struct hugepage_subpool *subpool) { folio->_hugetlb_subpool = subpool; } static inline struct hstate *hstate_file(struct file *f) { return hstate_inode(file_inode(f)); } static inline struct hstate *hstate_sizelog(int page_size_log) { if (!page_size_log) return &default_hstate; if (page_size_log < BITS_PER_LONG) return size_to_hstate(1UL << page_size_log); return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return hstate_file(vma->vm_file); } static inline unsigned long huge_page_size(const struct hstate *h) { return (unsigned long)PAGE_SIZE << h->order; } extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma); extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma); static inline unsigned long huge_page_mask(struct hstate *h) { return h->mask; } static inline unsigned int huge_page_order(struct hstate *h) { return h->order; } static inline unsigned huge_page_shift(struct hstate *h) { return h->order + PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return huge_page_order(h) > MAX_PAGE_ORDER; } static inline unsigned int pages_per_huge_page(const struct hstate *h) { return 1 << h->order; } static inline unsigned int blocks_per_huge_page(struct hstate *h) { return huge_page_size(h) / 512; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return filemap_lock_folio(mapping, idx << huge_page_order(h)); } #include <asm/hugetlb.h> #ifndef is_hugepage_only_range static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } #define is_hugepage_only_range is_hugepage_only_range #endif #ifndef arch_clear_hugetlb_flags static inline void arch_clear_hugetlb_flags(struct folio *folio) { } #define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { return pte_mkhuge(entry); } #endif static inline struct hstate *folio_hstate(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); return size_to_hstate(folio_size(folio)); } static inline unsigned hstate_index_to_shift(unsigned index) { return hstates[index].order + PAGE_SHIFT; } static inline int hstate_index(struct hstate *h) { return h - hstates; } int dissolve_free_hugetlb_folio(struct folio *folio); int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE extern void folio_clear_hugetlb_hwpoison(struct folio *folio); #else static inline void folio_clear_hugetlb_hwpoison(struct folio *folio) { } #endif #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION #ifndef arch_hugetlb_migration_supported static inline bool arch_hugetlb_migration_supported(struct hstate *h) { if ((huge_page_shift(h) == PMD_SHIFT) || (huge_page_shift(h) == PUD_SHIFT) || (huge_page_shift(h) == PGDIR_SHIFT)) return true; else return false; } #endif #else static inline bool arch_hugetlb_migration_supported(struct hstate *h) { return false; } #endif static inline bool hugepage_migration_supported(struct hstate *h) { return arch_hugetlb_migration_supported(h); } /* * Movability check is different as compared to migration check. * It determines whether or not a huge page should be placed on * movable zone or not. Movability of any huge page should be * required only if huge page size is supported for migration. * There won't be any reason for the huge page to be movable if * it is not migratable to start with. Also the size of the huge * page should be large enough to be placed under a movable zone * and still feasible enough to be migratable. Just the presence * in movable zone does not make the migration feasible. * * So even though large huge page sizes like the gigantic ones * are migratable they should not be movable because its not * feasible to migrate them from movable zone. */ static inline bool hugepage_movable_supported(struct hstate *h) { if (!hugepage_migration_supported(h)) return false; if (hstate_is_gigantic(h)) return false; return true; } /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { gfp_t gfp = __GFP_COMP | __GFP_NOWARN; gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER; return gfp; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { gfp_t modified_mask = htlb_alloc_mask(h); /* Some callers might want to enforce node */ modified_mask |= (gfp_mask & __GFP_THISNODE); modified_mask |= (gfp_mask & __GFP_NOWARN); return modified_mask; } static inline bool htlb_allow_alloc_fallback(int reason) { bool allowed_fallback = false; /* * Note: the memory offline, memory failure and migration syscalls will * be allowed to fallback to other nodes due to lack of a better chioce, * that might break the per-node hugetlb pool. While other cases will * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool. */ switch (reason) { case MR_MEMORY_HOTPLUG: case MR_MEMORY_FAILURE: case MR_SYSCALL: case MR_MEMPOLICY_MBIND: allowed_fallback = true; break; default: break; } return allowed_fallback; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { const unsigned long size = huge_page_size(h); VM_WARN_ON(size == PAGE_SIZE); /* * hugetlb must use the exact same PT locks as core-mm page table * walkers would. When modifying a PTE table, hugetlb must take the * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD * PT lock etc. * * The expectation is that any hugetlb folio smaller than a PMD is * always mapped into a single PTE table and that any hugetlb folio * smaller than a PUD (but at least as big as a PMD) is always mapped * into a single PMD table. * * If that does not hold for an architecture, then that architecture * must disable split PT locks such that all *_lockptr() functions * will give us the same result: the per-MM PT lock. * * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() * and core-mm would use pmd_lockptr(). However, in such configurations * split PMD locks are disabled -- they don't make sense on a single * PGDIR page table -- and the end result is the same. */ if (size >= PUD_SIZE) return pud_lockptr(mm, (pud_t *) pte); else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ return ptep_lockptr(mm, pte); } #ifndef hugepages_supported /* * Some platform decide whether they support huge pages at boot * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0 * when there is no such support */ #define hugepages_supported() (HPAGE_SHIFT != 0) #endif void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); static inline void hugetlb_count_init(struct mm_struct *mm) { atomic_long_set(&mm->hugetlb_usage, 0); } static inline void hugetlb_count_add(long l, struct mm_struct *mm) { atomic_long_add(l, &mm->hugetlb_usage); } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { atomic_long_sub(l, &mm->hugetlb_usage); } #ifndef huge_ptep_modify_prot_start #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); } #endif #ifndef huge_ptep_modify_prot_commit #define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { unsigned long psize = huge_page_size(hstate_vma(vma)); set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } #endif #ifdef CONFIG_NUMA void hugetlb_register_node(struct node *node); void hugetlb_unregister_node(struct node *node); #endif /* * Check if a given raw @page in a hugepage is HWPOISON. */ bool is_raw_hwpoison_page_in_hugepage(struct page *page); #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return NULL; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return NULL; } static inline int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { return -ENOMEM; } static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { return NULL; } static inline struct folio * alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { return NULL; } static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { return NULL; } static inline int __alloc_bootmem_huge_page(struct hstate *h) { return 0; } static inline struct hstate *hstate_file(struct file *f) { return NULL; } static inline struct hstate *hstate_sizelog(int page_size_log) { return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return NULL; } static inline struct hstate *folio_hstate(struct folio *folio) { return NULL; } static inline struct hstate *size_to_hstate(unsigned long size) { return NULL; } static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; } static inline unsigned long huge_page_mask(struct hstate *h) { return PAGE_MASK; } static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned int huge_page_order(struct hstate *h) { return 0; } static inline unsigned int huge_page_shift(struct hstate *h) { return PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return false; } static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } static inline unsigned hstate_index_to_shift(unsigned index) { return 0; } static inline int hstate_index(struct hstate *h) { return 0; } static inline int dissolve_free_hugetlb_folio(struct folio *folio) { return 0; } static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; } static inline bool hugepage_migration_supported(struct hstate *h) { return false; } static inline bool hugepage_movable_supported(struct hstate *h) { return false; } static inline gfp_t htlb_alloc_mask(struct hstate *h) { return 0; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { return 0; } static inline bool htlb_allow_alloc_fallback(int reason) { return false; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } static inline void hugetlb_count_init(struct mm_struct *mm) { } static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) { } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { #ifdef CONFIG_MMU return ptep_get(ptep); #else return *ptep; #endif } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { } static inline void hugetlb_register_node(struct node *node) { } static inline void hugetlb_unregister_node(struct node *node) { } static inline bool hugetlbfs_pagecache_present( struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return false; } #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { spinlock_t *ptl; ptl = huge_pte_lockptr(h, mm, pte); spin_lock(ptl); return ptl; } #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) extern void __init hugetlb_cma_reserve(int order); #else static inline __init void hugetlb_cma_reserve(int order) { } #endif #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { return page_count(virt_to_page(pte)) > 1; } #else static inline bool hugetlb_pmd_shared(pte_t *pte) { return false; } #endif bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE /* * ARCHes with special requirements for evicting HUGETLB backing TLB entries can * implement this. */ #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif static inline bool __vma_shareable_lock(struct vm_area_struct *vma) { return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } bool __vma_private_lock(struct vm_area_struct *vma); /* * Safe version of huge_pte_offset() to check the locks. See comments * above huge_pte_offset(). */ static inline pte_t * hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { #if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING) && defined(CONFIG_LOCKDEP) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; /* * If pmd sharing possible, locking needed to safely walk the * hugetlb pgtables. More information can be found at the comment * above huge_pte_offset() in the same file. * * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP. */ if (__vma_shareable_lock(vma)) WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) && !lockdep_is_held( &vma->vm_file->f_mapping->i_mmap_rwsem)); #endif return huge_pte_offset(vma->vm_mm, addr, sz); } #endif /* _LINUX_HUGETLB_H */ |
| 16 52 65 65 19 24 4 4 3 21 1 1 9 9 9 93 59 24 9 52 52 52 51 4 3 4 16 19 19 54 48 52 56 25 12 10 10 25 56 2 2 2 56 93 65 93 3 3 1 93 55 92 62 93 15 2 15 12 15 10 15 93 31 31 3 62 60 60 62 24 21 56 52 16 3 16 16 16 3 16 16 16 55 56 9 9 62 2 2 2 2 93 62 1 1 1 93 89 25 25 44 40 33 20 93 93 53 93 93 56 1 1 56 44 44 1 1 1 44 38 1 38 92 1 19 19 17 4 4 4 4 4 4 3 2 3 2 3 2 1 1 3 2 1 9 7 5 1 4 4 1 3 1 1 24 19 5 1 25 25 24 4 24 3 23 23 9 3 14 20 2 20 1 20 7 20 1 20 3 20 2 20 1 20 1 20 2 20 2 20 1 20 3 20 20 18 20 23 24 25 26 25 21 5 18 17 13 13 13 12 1 1 1 13 13 13 13 13 13 13 13 13 13 13 13 2 1 2 1 2 13 12 1 1 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_netem.c Network emulator * * Many of the algorithms and ideas for this came from * NIST Net which is not copyrighted. * * Authors: Stephen Hemminger <shemminger@osdl.org> * Catalin(ux aka Dino) BOIE <catab at umbrella dot ro> */ #include <linux/mm.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/rtnetlink.h> #include <linux/reciprocal_div.h> #include <linux/rbtree.h> #include <net/gso.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> #define VERSION "1.3" /* Network Emulation Queuing algorithm. ==================================== Sources: [1] Mark Carson, Darrin Santay, "NIST Net - A Linux-based Network Emulation Tool [2] Luigi Rizzo, DummyNet for FreeBSD ---------------------------------------------------------------- This started out as a simple way to delay outgoing packets to test TCP but has grown to include most of the functionality of a full blown network emulator like NISTnet. It can delay packets and add random jitter (and correlation). The random distribution can be loaded from a table as well to provide normal, Pareto, or experimental curves. Packet loss, duplication, and reordering can also be emulated. This qdisc does not do classification that can be handled in layering other disciplines. It does not need to do bandwidth control either since that can be handled by using token bucket or other rate control. Correlated Loss Generator models Added generation of correlated loss according to the "Gilbert-Elliot" model, a 4-state markov model. References: [1] NetemCLG Home http://netgroup.uniroma2.it/NetemCLG [2] S. Salsano, F. Ludovici, A. Ordine, "Definition of a general and intuitive loss model for packet networks and its implementation in the Netem module in the Linux kernel", available in [1] Authors: Stefano Salsano <stefano.salsano at uniroma2.it Fabio Ludovici <fabio.ludovici at yahoo.it> */ struct disttable { u32 size; s16 table[] __counted_by(size); }; struct netem_sched_data { /* internal t(ime)fifo qdisc uses t_root and sch->limit */ struct rb_root t_root; /* a linear queue; reduces rbtree rebalancing when jitter is low */ struct sk_buff *t_head; struct sk_buff *t_tail; /* optional qdisc for classful handling (NULL at netem init) */ struct Qdisc *qdisc; struct qdisc_watchdog watchdog; s64 latency; s64 jitter; u32 loss; u32 ecn; u32 limit; u32 counter; u32 gap; u32 duplicate; u32 reorder; u32 corrupt; u64 rate; s32 packet_overhead; u32 cell_size; struct reciprocal_value cell_size_reciprocal; s32 cell_overhead; struct crndstate { u32 last; u32 rho; } delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor; struct prng { u64 seed; struct rnd_state prng_state; } prng; struct disttable *delay_dist; enum { CLG_RANDOM, CLG_4_STATES, CLG_GILB_ELL, } loss_model; enum { TX_IN_GAP_PERIOD = 1, TX_IN_BURST_PERIOD, LOST_IN_GAP_PERIOD, LOST_IN_BURST_PERIOD, } _4_state_model; enum { GOOD_STATE = 1, BAD_STATE, } GE_state_model; /* Correlated Loss Generation models */ struct clgstate { /* state of the Markov chain */ u8 state; /* 4-states and Gilbert-Elliot models */ u32 a1; /* p13 for 4-states or p for GE */ u32 a2; /* p31 for 4-states or r for GE */ u32 a3; /* p32 for 4-states or h for GE */ u32 a4; /* p14 for 4-states or 1-k for GE */ u32 a5; /* p23 used only in 4-states */ } clg; struct tc_netem_slot slot_config; struct slotstate { u64 slot_next; s32 packets_left; s32 bytes_left; } slot; struct disttable *slot_dist; }; /* Time stamp put into socket buffer control block * Only valid when skbs are in our internal t(ime)fifo queue. * * As skb->rbnode uses same storage than skb->next, skb->prev and skb->tstamp, * and skb->next & skb->prev are scratch space for a qdisc, * we save skb->tstamp value in skb->cb[] before destroying it. */ struct netem_skb_cb { u64 time_to_send; }; static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { /* we assume we can use skb next/prev/tstamp as storage for rb_node */ qdisc_cb_private_validate(skb, sizeof(struct netem_skb_cb)); return (struct netem_skb_cb *)qdisc_skb_cb(skb)->data; } /* init_crandom - initialize correlated random number generator * Use entropy source for initial seed. */ static void init_crandom(struct crndstate *state, unsigned long rho) { state->rho = rho; state->last = get_random_u32(); } /* get_crandom - correlated random number generator * Next number depends on last value. * rho is scaled to avoid floating point. */ static u32 get_crandom(struct crndstate *state, struct prng *p) { u64 value, rho; unsigned long answer; struct rnd_state *s = &p->prng_state; if (!state || state->rho == 0) /* no correlation */ return prandom_u32_state(s); value = prandom_u32_state(s); rho = (u64)state->rho + 1; answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32; state->last = answer; return answer; } /* loss_4state - 4-state model loss generator * Generates losses according to the 4-state Markov chain adopted in * the GI (General and Intuitive) loss model. */ static bool loss_4state(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; u32 rnd = prandom_u32_state(&q->prng.prng_state); /* * Makes a comparison between rnd and the transition * probabilities outgoing from the current state, then decides the * next state and if the next packet has to be transmitted or lost. * The four states correspond to: * TX_IN_GAP_PERIOD => successfully transmitted packets within a gap period * LOST_IN_GAP_PERIOD => isolated losses within a gap period * LOST_IN_BURST_PERIOD => lost packets within a burst period * TX_IN_BURST_PERIOD => successfully transmitted packets within a burst period */ switch (clg->state) { case TX_IN_GAP_PERIOD: if (rnd < clg->a4) { clg->state = LOST_IN_GAP_PERIOD; return true; } else if (clg->a4 < rnd && rnd < clg->a1 + clg->a4) { clg->state = LOST_IN_BURST_PERIOD; return true; } else if (clg->a1 + clg->a4 < rnd) { clg->state = TX_IN_GAP_PERIOD; } break; case TX_IN_BURST_PERIOD: if (rnd < clg->a5) { clg->state = LOST_IN_BURST_PERIOD; return true; } else { clg->state = TX_IN_BURST_PERIOD; } break; case LOST_IN_BURST_PERIOD: if (rnd < clg->a3) clg->state = TX_IN_BURST_PERIOD; else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) { clg->state = TX_IN_GAP_PERIOD; } else if (clg->a2 + clg->a3 < rnd) { clg->state = LOST_IN_BURST_PERIOD; return true; } break; case LOST_IN_GAP_PERIOD: clg->state = TX_IN_GAP_PERIOD; break; } return false; } /* loss_gilb_ell - Gilbert-Elliot model loss generator * Generates losses according to the Gilbert-Elliot loss model or * its special cases (Gilbert or Simple Gilbert) * * Makes a comparison between random number and the transition * probabilities outgoing from the current state, then decides the * next state. A second random number is extracted and the comparison * with the loss probability of the current state decides if the next * packet will be transmitted or lost. */ static bool loss_gilb_ell(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; struct rnd_state *s = &q->prng.prng_state; switch (clg->state) { case GOOD_STATE: if (prandom_u32_state(s) < clg->a1) clg->state = BAD_STATE; if (prandom_u32_state(s) < clg->a4) return true; break; case BAD_STATE: if (prandom_u32_state(s) < clg->a2) clg->state = GOOD_STATE; if (prandom_u32_state(s) > clg->a3) return true; } return false; } static bool loss_event(struct netem_sched_data *q) { switch (q->loss_model) { case CLG_RANDOM: /* Random packet drop 0 => none, ~0 => all */ return q->loss && q->loss >= get_crandom(&q->loss_cor, &q->prng); case CLG_4_STATES: /* 4state loss model algorithm (used also for GI model) * Extracts a value from the markov 4 state loss generator, * if it is 1 drops a packet and if needed writes the event in * the kernel logs */ return loss_4state(q); case CLG_GILB_ELL: /* Gilbert-Elliot loss model algorithm * Extracts a value from the Gilbert-Elliot loss generator, * if it is 1 drops a packet and if needed writes the event in * the kernel logs */ return loss_gilb_ell(q); } return false; /* not reached */ } /* tabledist - return a pseudo-randomly distributed value with mean mu and * std deviation sigma. Uses table lookup to approximate the desired * distribution, and a uniformly-distributed pseudo-random source. */ static s64 tabledist(s64 mu, s32 sigma, struct crndstate *state, struct prng *prng, const struct disttable *dist) { s64 x; long t; u32 rnd; if (sigma == 0) return mu; rnd = get_crandom(state, prng); /* default uniform distribution */ if (dist == NULL) return ((rnd % (2 * (u32)sigma)) + mu) - sigma; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; if (x >= 0) x += NETEM_DIST_SCALE/2; else x -= NETEM_DIST_SCALE/2; return x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu; } static u64 packet_time_ns(u64 len, const struct netem_sched_data *q) { len += q->packet_overhead; if (q->cell_size) { u32 cells = reciprocal_divide(len, q->cell_size_reciprocal); if (len > cells * q->cell_size) /* extra cell needed for remainder */ cells++; len = cells * (q->cell_size + q->cell_overhead); } return div64_u64(len * NSEC_PER_SEC, q->rate); } static void tfifo_reset(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); struct rb_node *p = rb_first(&q->t_root); while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); rb_erase(&skb->rbnode, &q->t_root); rtnl_kfree_skbs(skb, skb); } rtnl_kfree_skbs(q->t_head, q->t_tail); q->t_head = NULL; q->t_tail = NULL; } static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); u64 tnext = netem_skb_cb(nskb)->time_to_send; if (!q->t_tail || tnext >= netem_skb_cb(q->t_tail)->time_to_send) { if (q->t_tail) q->t_tail->next = nskb; else q->t_head = nskb; q->t_tail = nskb; } else { struct rb_node **p = &q->t_root.rb_node, *parent = NULL; while (*p) { struct sk_buff *skb; parent = *p; skb = rb_to_skb(parent); if (tnext >= netem_skb_cb(skb)->time_to_send) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&nskb->rbnode, parent, p); rb_insert_color(&nskb->rbnode, &q->t_root); } sch->q.qlen++; } /* netem can't properly corrupt a megapacket (like we get from GSO), so instead * when we statistically choose to corrupt one, we instead segment it, returning * the first packet to be corrupted, and re-enqueue the remaining frames */ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct sk_buff *segs; netdev_features_t features = netif_skb_features(skb); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { qdisc_drop(skb, sch, to_free); return NULL; } consume_skb(skb); return segs; } /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. * NET_XMIT_DROP: queue length didn't change. * NET_XMIT_SUCCESS: one skb was queued. */ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; /* Random duplication */ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor, &q->prng)) ++count; /* Drop packet? */ if (loss_event(q)) { if (q->ecn && INET_ECN_set_ce(skb)) qdisc_qstats_drop(sch); /* mark packet */ else --count; } if (count == 0) { qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } /* If a delay is expected, orphan the skb. (orphaning usually takes * place at TX completion time, so _before_ the link transit delay) */ if (q->latency || q->jitter || q->rate) skb_orphan_partial(skb); /* * If we need to duplicate packet, then clone it before * original is modified. */ if (count > 1) skb2 = skb_clone(skb, GFP_ATOMIC); /* * Randomized packet corruption. * Make copy if needed since we are modifying * If packet is going to be hardware checksummed, then * do it now in software before we mangle it. */ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor, &q->prng)) { if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); if (!skb) goto finish_segs; segs = skb->next; skb_mark_not_on_list(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; } skb = skb_unshare(skb, GFP_ATOMIC); if (unlikely(!skb)) { qdisc_qstats_drop(sch); goto finish_segs; } if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) { qdisc_drop(skb, sch, to_free); skb = NULL; goto finish_segs; } skb->data[get_random_u32_below(skb_headlen(skb))] ^= 1<<get_random_u32_below(8); } if (unlikely(sch->q.qlen >= sch->limit)) { /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); if (skb2) __qdisc_drop(skb2, to_free); return NET_XMIT_DROP; } /* * If doing duplication then re-insert at top of the * qdisc tree, since parent queuer expects that only one * skb will be queued. */ if (skb2) { struct Qdisc *rootq = qdisc_root_bh(sch); u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ q->duplicate = 0; rootq->enqueue(skb2, rootq, to_free); q->duplicate = dupsave; skb2 = NULL; } qdisc_qstats_backlog_inc(sch, skb); cb = netem_skb_cb(skb); if (q->gap == 0 || /* not doing reordering */ q->counter < q->gap - 1 || /* inside last reordering gap */ q->reorder < get_crandom(&q->reorder_cor, &q->prng)) { u64 now; s64 delay; delay = tabledist(q->latency, q->jitter, &q->delay_cor, &q->prng, q->delay_dist); now = ktime_get_ns(); if (q->rate) { struct netem_skb_cb *last = NULL; if (sch->q.tail) last = netem_skb_cb(sch->q.tail); if (q->t_root.rb_node) { struct sk_buff *t_skb; struct netem_skb_cb *t_last; t_skb = skb_rb_last(&q->t_root); t_last = netem_skb_cb(t_skb); if (!last || t_last->time_to_send > last->time_to_send) last = t_last; } if (q->t_tail) { struct netem_skb_cb *t_last = netem_skb_cb(q->t_tail); if (!last || t_last->time_to_send > last->time_to_send) last = t_last; } if (last) { /* * Last packet in queue is reference point (now), * calculate this time bonus and subtract * from delay. */ delay -= last->time_to_send - now; delay = max_t(s64, 0, delay); now = last->time_to_send; } delay += packet_time_ns(qdisc_pkt_len(skb), q); } cb->time_to_send = now + delay; ++q->counter; tfifo_enqueue(skb, sch); } else { /* * Do re-ordering by putting one out of N packets at the front * of the queue. */ cb->time_to_send = ktime_get_ns(); q->counter = 0; __qdisc_enqueue_head(skb, &sch->q); sch->qstats.requeues++; } finish_segs: if (skb2) __qdisc_drop(skb2, to_free); if (segs) { unsigned int len, last_len; int rc, nb; len = skb ? skb->len : 0; nb = skb ? 1 : 0; while (segs) { skb2 = segs->next; skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; last_len = segs->len; rc = qdisc_enqueue(segs, sch, to_free); if (rc != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(rc)) qdisc_qstats_drop(sch); } else { nb++; len += last_len; } segs = skb2; } /* Parent qdiscs accounted for 1 skb of size @prev_len */ qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len)); } else if (!skb) { return NET_XMIT_DROP; } return NET_XMIT_SUCCESS; } /* Delay the next round with a new future slot with a * correct number of bytes and packets. */ static void get_slot_next(struct netem_sched_data *q, u64 now) { s64 next_delay; if (!q->slot_dist) next_delay = q->slot_config.min_delay + (get_random_u32() * (q->slot_config.max_delay - q->slot_config.min_delay) >> 32); else next_delay = tabledist(q->slot_config.dist_delay, (s32)(q->slot_config.dist_jitter), NULL, &q->prng, q->slot_dist); q->slot.slot_next = now + next_delay; q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; } static struct sk_buff *netem_peek(struct netem_sched_data *q) { struct sk_buff *skb = skb_rb_first(&q->t_root); u64 t1, t2; if (!skb) return q->t_head; if (!q->t_head) return skb; t1 = netem_skb_cb(skb)->time_to_send; t2 = netem_skb_cb(q->t_head)->time_to_send; if (t1 < t2) return skb; return q->t_head; } static void netem_erase_head(struct netem_sched_data *q, struct sk_buff *skb) { if (skb == q->t_head) { q->t_head = skb->next; if (!q->t_head) q->t_tail = NULL; } else { rb_erase(&skb->rbnode, &q->t_root); } } static struct sk_buff *netem_dequeue(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; tfifo_dequeue: skb = __qdisc_dequeue_head(&sch->q); if (skb) { qdisc_qstats_backlog_dec(sch, skb); deliver: qdisc_bstats_update(sch, skb); return skb; } skb = netem_peek(q); if (skb) { u64 time_to_send; u64 now = ktime_get_ns(); /* if more time remaining? */ time_to_send = netem_skb_cb(skb)->time_to_send; if (q->slot.slot_next && q->slot.slot_next < time_to_send) get_slot_next(q, now); if (time_to_send <= now && q->slot.slot_next <= now) { netem_erase_head(q, skb); sch->q.qlen--; qdisc_qstats_backlog_dec(sch, skb); skb->next = NULL; skb->prev = NULL; /* skb->dev shares skb->rbnode area, * we need to restore its value. */ skb->dev = qdisc_dev(sch); if (q->slot.slot_next) { q->slot.packets_left--; q->slot.bytes_left -= qdisc_pkt_len(skb); if (q->slot.packets_left <= 0 || q->slot.bytes_left <= 0) get_slot_next(q, now); } if (q->qdisc) { unsigned int pkt_len = qdisc_pkt_len(skb); struct sk_buff *to_free = NULL; int err; err = qdisc_enqueue(skb, q->qdisc, &to_free); kfree_skb_list(to_free); if (err != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(err)) qdisc_qstats_drop(sch); qdisc_tree_reduce_backlog(sch, 1, pkt_len); } goto tfifo_dequeue; } goto deliver; } if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); if (skb) goto deliver; } qdisc_watchdog_schedule_ns(&q->watchdog, max(time_to_send, q->slot.slot_next)); } if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); if (skb) goto deliver; } return NULL; } static void netem_reset(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); tfifo_reset(sch); if (q->qdisc) qdisc_reset(q->qdisc); qdisc_watchdog_cancel(&q->watchdog); } static void dist_free(struct disttable *d) { kvfree(d); } /* * Distribution data is a variable size payload containing * signed 16 bit values. */ static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); struct disttable *d; int i; if (!n || n > NETEM_DIST_MAX) return -EINVAL; d = kvmalloc(struct_size(d, table, n), GFP_KERNEL); if (!d) return -ENOMEM; d->size = n; for (i = 0; i < n; i++) d->table[i] = data[i]; *tbl = d; return 0; } static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_slot *c = nla_data(attr); q->slot_config = *c; if (q->slot_config.max_packets == 0) q->slot_config.max_packets = INT_MAX; if (q->slot_config.max_bytes == 0) q->slot_config.max_bytes = INT_MAX; /* capping dist_jitter to the range acceptable by tabledist() */ q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter)); q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; if (q->slot_config.min_delay | q->slot_config.max_delay | q->slot_config.dist_jitter) q->slot.slot_next = ktime_get_ns(); else q->slot.slot_next = 0; } static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_corr *c = nla_data(attr); init_crandom(&q->delay_cor, c->delay_corr); init_crandom(&q->loss_cor, c->loss_corr); init_crandom(&q->dup_cor, c->dup_corr); } static void get_reorder(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_reorder *r = nla_data(attr); q->reorder = r->probability; init_crandom(&q->reorder_cor, r->correlation); } static void get_corrupt(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_corrupt *r = nla_data(attr); q->corrupt = r->probability; init_crandom(&q->corrupt_cor, r->correlation); } static void get_rate(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_rate *r = nla_data(attr); q->rate = r->rate; q->packet_overhead = r->packet_overhead; q->cell_size = r->cell_size; q->cell_overhead = r->cell_overhead; if (q->cell_size) q->cell_size_reciprocal = reciprocal_value(q->cell_size); else q->cell_size_reciprocal = (struct reciprocal_value) { 0 }; } static int get_loss_clg(struct netem_sched_data *q, const struct nlattr *attr) { const struct nlattr *la; int rem; nla_for_each_nested(la, attr, rem) { u16 type = nla_type(la); switch (type) { case NETEM_LOSS_GI: { const struct tc_netem_gimodel *gi = nla_data(la); if (nla_len(la) < sizeof(struct tc_netem_gimodel)) { pr_info("netem: incorrect gi model size\n"); return -EINVAL; } q->loss_model = CLG_4_STATES; q->clg.state = TX_IN_GAP_PERIOD; q->clg.a1 = gi->p13; q->clg.a2 = gi->p31; q->clg.a3 = gi->p32; q->clg.a4 = gi->p14; q->clg.a5 = gi->p23; break; } case NETEM_LOSS_GE: { const struct tc_netem_gemodel *ge = nla_data(la); if (nla_len(la) < sizeof(struct tc_netem_gemodel)) { pr_info("netem: incorrect ge model size\n"); return -EINVAL; } q->loss_model = CLG_GILB_ELL; q->clg.state = GOOD_STATE; q->clg.a1 = ge->p; q->clg.a2 = ge->r; q->clg.a3 = ge->h; q->clg.a4 = ge->k1; break; } default: pr_info("netem: unknown loss type %u\n", type); return -EINVAL; } } return 0; } static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_CORR] = { .len = sizeof(struct tc_netem_corr) }, [TCA_NETEM_REORDER] = { .len = sizeof(struct tc_netem_reorder) }, [TCA_NETEM_CORRUPT] = { .len = sizeof(struct tc_netem_corrupt) }, [TCA_NETEM_RATE] = { .len = sizeof(struct tc_netem_rate) }, [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, [TCA_NETEM_ECN] = { .type = NLA_U32 }, [TCA_NETEM_RATE64] = { .type = NLA_U64 }, [TCA_NETEM_LATENCY64] = { .type = NLA_S64 }, [TCA_NETEM_JITTER64] = { .type = NLA_S64 }, [TCA_NETEM_SLOT] = { .len = sizeof(struct tc_netem_slot) }, [TCA_NETEM_PRNG_SEED] = { .type = NLA_U64 }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, const struct nla_policy *policy, int len) { int nested_len = nla_len(nla) - NLA_ALIGN(len); if (nested_len < 0) { pr_info("netem: invalid attributes len %d\n", nested_len); return -EINVAL; } if (nested_len >= nla_attr_size(0)) return nla_parse_deprecated(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), nested_len, policy, NULL); memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); return 0; } /* Parse netlink message to set options */ static int netem_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; struct disttable *delay_dist = NULL; struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; int ret; qopt = nla_data(opt); ret = parse_attr(tb, TCA_NETEM_MAX, opt, netem_policy, sizeof(*qopt)); if (ret < 0) return ret; if (tb[TCA_NETEM_DELAY_DIST]) { ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); if (ret) goto table_free; } if (tb[TCA_NETEM_SLOT_DIST]) { ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); if (ret) goto table_free; } sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; old_loss_model = q->loss_model; if (tb[TCA_NETEM_LOSS]) { ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; q->clg = old_clg; goto unlock; } } else { q->loss_model = CLG_RANDOM; } if (delay_dist) swap(q->delay_dist, delay_dist); if (slot_dist) swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; q->latency = PSCHED_TICKS2NS(qopt->latency); q->jitter = PSCHED_TICKS2NS(qopt->jitter); q->limit = qopt->limit; q->gap = qopt->gap; q->counter = 0; q->loss = qopt->loss; q->duplicate = qopt->duplicate; /* for compatibility with earlier versions. * if gap is set, need to assume 100% probability */ if (q->gap) q->reorder = ~0; if (tb[TCA_NETEM_CORR]) get_correlation(q, tb[TCA_NETEM_CORR]); if (tb[TCA_NETEM_REORDER]) get_reorder(q, tb[TCA_NETEM_REORDER]); if (tb[TCA_NETEM_CORRUPT]) get_corrupt(q, tb[TCA_NETEM_CORRUPT]); if (tb[TCA_NETEM_RATE]) get_rate(q, tb[TCA_NETEM_RATE]); if (tb[TCA_NETEM_RATE64]) q->rate = max_t(u64, q->rate, nla_get_u64(tb[TCA_NETEM_RATE64])); if (tb[TCA_NETEM_LATENCY64]) q->latency = nla_get_s64(tb[TCA_NETEM_LATENCY64]); if (tb[TCA_NETEM_JITTER64]) q->jitter = nla_get_s64(tb[TCA_NETEM_JITTER64]); if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); if (tb[TCA_NETEM_SLOT]) get_slot(q, tb[TCA_NETEM_SLOT]); /* capping jitter to the range acceptable by tabledist() */ q->jitter = min_t(s64, abs(q->jitter), INT_MAX); if (tb[TCA_NETEM_PRNG_SEED]) q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]); else q->prng.seed = get_random_u64(); prandom_seed_state(&q->prng.prng_state, q->prng.seed); unlock: sch_tree_unlock(sch); table_free: dist_free(delay_dist); dist_free(slot_dist); return ret; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); int ret; qdisc_watchdog_init(&q->watchdog, sch); if (!opt) return -EINVAL; q->loss_model = CLG_RANDOM; ret = netem_change(sch, opt, extack); if (ret) pr_info("netem: change failed\n"); return ret; } static void netem_destroy(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); if (q->qdisc) qdisc_put(q->qdisc); dist_free(q->delay_dist); dist_free(q->slot_dist); } static int dump_loss_model(const struct netem_sched_data *q, struct sk_buff *skb) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, TCA_NETEM_LOSS); if (nest == NULL) goto nla_put_failure; switch (q->loss_model) { case CLG_RANDOM: /* legacy loss model */ nla_nest_cancel(skb, nest); return 0; /* no data */ case CLG_4_STATES: { struct tc_netem_gimodel gi = { .p13 = q->clg.a1, .p31 = q->clg.a2, .p32 = q->clg.a3, .p14 = q->clg.a4, .p23 = q->clg.a5, }; if (nla_put(skb, NETEM_LOSS_GI, sizeof(gi), &gi)) goto nla_put_failure; break; } case CLG_GILB_ELL: { struct tc_netem_gemodel ge = { .p = q->clg.a1, .r = q->clg.a2, .h = q->clg.a3, .k1 = q->clg.a4, }; if (nla_put(skb, NETEM_LOSS_GE, sizeof(ge), &ge)) goto nla_put_failure; break; } } nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -1; } static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) { const struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *nla = (struct nlattr *) skb_tail_pointer(skb); struct tc_netem_qopt qopt; struct tc_netem_corr cor; struct tc_netem_reorder reorder; struct tc_netem_corrupt corrupt; struct tc_netem_rate rate; struct tc_netem_slot slot; qopt.latency = min_t(psched_time_t, PSCHED_NS2TICKS(q->latency), UINT_MAX); qopt.jitter = min_t(psched_time_t, PSCHED_NS2TICKS(q->jitter), UINT_MAX); qopt.limit = q->limit; qopt.loss = q->loss; qopt.gap = q->gap; qopt.duplicate = q->duplicate; if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; if (nla_put(skb, TCA_NETEM_LATENCY64, sizeof(q->latency), &q->latency)) goto nla_put_failure; if (nla_put(skb, TCA_NETEM_JITTER64, sizeof(q->jitter), &q->jitter)) goto nla_put_failure; cor.delay_corr = q->delay_cor.rho; cor.loss_corr = q->loss_cor.rho; cor.dup_corr = q->dup_cor.rho; if (nla_put(skb, TCA_NETEM_CORR, sizeof(cor), &cor)) goto nla_put_failure; reorder.probability = q->reorder; reorder.correlation = q->reorder_cor.rho; if (nla_put(skb, TCA_NETEM_REORDER, sizeof(reorder), &reorder)) goto nla_put_failure; corrupt.probability = q->corrupt; corrupt.correlation = q->corrupt_cor.rho; if (nla_put(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt)) goto nla_put_failure; if (q->rate >= (1ULL << 32)) { if (nla_put_u64_64bit(skb, TCA_NETEM_RATE64, q->rate, TCA_NETEM_PAD)) goto nla_put_failure; rate.rate = ~0U; } else { rate.rate = q->rate; } rate.packet_overhead = q->packet_overhead; rate.cell_size = q->cell_size; rate.cell_overhead = q->cell_overhead; if (nla_put(skb, TCA_NETEM_RATE, sizeof(rate), &rate)) goto nla_put_failure; if (q->ecn && nla_put_u32(skb, TCA_NETEM_ECN, q->ecn)) goto nla_put_failure; if (dump_loss_model(q, skb) != 0) goto nla_put_failure; if (q->slot_config.min_delay | q->slot_config.max_delay | q->slot_config.dist_jitter) { slot = q->slot_config; if (slot.max_packets == INT_MAX) slot.max_packets = 0; if (slot.max_bytes == INT_MAX) slot.max_bytes = 0; if (nla_put(skb, TCA_NETEM_SLOT, sizeof(slot), &slot)) goto nla_put_failure; } if (nla_put_u64_64bit(skb, TCA_NETEM_PRNG_SEED, q->prng.seed, TCA_NETEM_PAD)) goto nla_put_failure; return nla_nest_end(skb, nla); nla_put_failure: nlmsg_trim(skb, nla); return -1; } static int netem_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct netem_sched_data *q = qdisc_priv(sch); if (cl != 1 || !q->qdisc) /* only one class */ return -ENOENT; tcm->tcm_handle |= TC_H_MIN(1); tcm->tcm_info = q->qdisc->handle; return 0; } static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); *old = qdisc_replace(sch, new, &q->qdisc); return 0; } static struct Qdisc *netem_leaf(struct Qdisc *sch, unsigned long arg) { struct netem_sched_data *q = qdisc_priv(sch); return q->qdisc; } static unsigned long netem_find(struct Qdisc *sch, u32 classid) { return 1; } static void netem_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { if (!tc_qdisc_stats_dump(sch, 1, walker)) return; } } static const struct Qdisc_class_ops netem_class_ops = { .graft = netem_graft, .leaf = netem_leaf, .find = netem_find, .walk = netem_walk, .dump = netem_dump_class, }; static struct Qdisc_ops netem_qdisc_ops __read_mostly = { .id = "netem", .cl_ops = &netem_class_ops, .priv_size = sizeof(struct netem_sched_data), .enqueue = netem_enqueue, .dequeue = netem_dequeue, .peek = qdisc_peek_dequeued, .init = netem_init, .reset = netem_reset, .destroy = netem_destroy, .change = netem_change, .dump = netem_dump, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("netem"); static int __init netem_module_init(void) { pr_info("netem: version " VERSION "\n"); return register_qdisc(&netem_qdisc_ops); } static void __exit netem_module_exit(void) { unregister_qdisc(&netem_qdisc_ops); } module_init(netem_module_init) module_exit(netem_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Network characteristics emulator qdisc"); |
| 94 93 84 42 15 42 4 4 93 95 96 94 93 23 73 74 8 6 70 68 66 1 1 1 1 1 67 64 63 4 4 4 4 4 4 68 5 5 5 5 19 20 15 15 15 58 58 37 37 36 36 45 11 38 20 16 16 15 20 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Fast Userspace Mutexes (which I call "Futexes!"). * (C) Rusty Russell, IBM 2002 * * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar * (C) Copyright 2003 Red Hat Inc, All Rights Reserved * * Removed page pinning, fix privately mapped COW pages and other cleanups * (C) Copyright 2003, 2004 Jamie Lokier * * Robust futex support started by Ingo Molnar * (C) Copyright 2006 Red Hat Inc, All Rights Reserved * Thanks to Thomas Gleixner for suggestions, analysis and fixes. * * PI-futex support started by Ingo Molnar and Thomas Gleixner * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * PRIVATE futexes by Eric Dumazet * Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com> * * Requeue-PI support by Darren Hart <dvhltc@us.ibm.com> * Copyright (C) IBM Corporation, 2009 * Thanks to Thomas Gleixner for conceptual design and careful reviews. * * Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly * enough at me, Linus for the original (flawed) idea, Matthew * Kirkwood for proof-of-concept implementation. * * "The futexes are also cursed." * "But they come in a choice of three flavours!" */ #include <linux/compat.h> #include <linux/jhash.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/plist.h> #include <linux/memblock.h> #include <linux/fault-inject.h> #include <linux/slab.h> #include "futex.h" #include "../locking/rtmutex_common.h" /* * The base of the bucket array and its size are always used together * (after initialization only in futex_hash()), so ensure that they * reside in the same cacheline. */ static struct { struct futex_hash_bucket *queues; unsigned long hashsize; } __futex_data __read_mostly __aligned(2*sizeof(long)); #define futex_queues (__futex_data.queues) #define futex_hashsize (__futex_data.hashsize) /* * Fault injections for futexes. */ #ifdef CONFIG_FAIL_FUTEX static struct { struct fault_attr attr; bool ignore_private; } fail_futex = { .attr = FAULT_ATTR_INITIALIZER, .ignore_private = false, }; static int __init setup_fail_futex(char *str) { return setup_fault_attr(&fail_futex.attr, str); } __setup("fail_futex=", setup_fail_futex); bool should_fail_futex(bool fshared) { if (fail_futex.ignore_private && !fshared) return false; return should_fail(&fail_futex.attr, 1); } #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_futex_debugfs(void) { umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; dir = fault_create_debugfs_attr("fail_futex", NULL, &fail_futex.attr); if (IS_ERR(dir)) return PTR_ERR(dir); debugfs_create_bool("ignore-private", mode, dir, &fail_futex.ignore_private); return 0; } late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ #endif /* CONFIG_FAIL_FUTEX */ /** * futex_hash - Return the hash bucket in the global hash * @key: Pointer to the futex key for which the hash is calculated * * We hash on the keys returned from get_futex_key (see below) and return the * corresponding hash bucket in the global hash. */ struct futex_hash_bucket *futex_hash(union futex_key *key) { u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, key->both.offset); return &futex_queues[hash & (futex_hashsize - 1)]; } /** * futex_setup_timer - set up the sleeping hrtimer. * @time: ptr to the given timeout value * @timeout: the hrtimer_sleeper structure to be set up * @flags: futex flags * @range_ns: optional range in ns * * Return: Initialized hrtimer_sleeper structure or NULL if no timeout * value given */ struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns) { if (!time) return NULL; hrtimer_init_sleeper_on_stack(timeout, (flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC, HRTIMER_MODE_ABS); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is * effectively the same as calling hrtimer_set_expires(). */ hrtimer_set_expires_range_ns(&timeout->timer, *time, range_ns); return timeout; } /* * Generate a machine wide unique identifier for this inode. * * This relies on u64 not wrapping in the life-time of the machine; which with * 1ns resolution means almost 585 years. * * This further relies on the fact that a well formed program will not unmap * the file while it has a (shared) futex waiting on it. This mapping will have * a file reference which pins the mount and inode. * * If for some reason an inode gets evicted and read back in again, it will get * a new sequence number and will _NOT_ match, even though it is the exact same * file. * * It is important that futex_match() will never have a false-positive, esp. * for PI futexes that can mess up the state. The above argues that false-negatives * are only possible for malformed programs. */ static u64 get_inode_sequence_number(struct inode *inode) { static atomic64_t i_seq; u64 old; /* Does the inode already have a sequence number? */ old = atomic64_read(&inode->i_sequence); if (likely(old)) return old; for (;;) { u64 new = atomic64_add_return(1, &i_seq); if (WARN_ON_ONCE(!new)) continue; old = atomic64_cmpxchg_relaxed(&inode->i_sequence, 0, new); if (old) return old; return new; } } /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex * @flags: FLAGS_* * @key: address where result is stored. * @rw: mapping needs to be read/write (values: FUTEX_READ, * FUTEX_WRITE) * * Return: a negative error code or 0 * * The key words are stored in @key on success. * * For shared mappings (when @fshared), the key is: * * ( inode->i_sequence, page->index, offset_within_page ) * * [ also see get_inode_sequence_number() ] * * For private mappings (or when !@fshared), the key is: * * ( current->mm, address, 0 ) * * This allows (cross process, where applicable) identification of the futex * without keeping the page pinned for the duration of the FUTEX_WAIT. * * lock_page() might sleep, the caller should not hold a spinlock. */ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; struct page *page; struct folio *folio; struct address_space *mapping; int err, ro = 0; bool fshared; fshared = flags & FLAGS_SHARED; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; if (unlikely((address % sizeof(u32)) != 0)) return -EINVAL; address -= key->both.offset; if (unlikely(!access_ok(uaddr, sizeof(u32)))) return -EFAULT; if (unlikely(should_fail_futex(fshared))) return -EFAULT; /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs * virtual address, we dont even have to find the underlying vma. * Note : We do have to check 'uaddr' is a valid user address, * but access_ok() should be faster than find_vma() */ if (!fshared) { /* * On no-MMU, shared futexes are treated as private, therefore * we must not include the current process in the key. Since * there is only one address space, the address is a unique key * on its own. */ if (IS_ENABLED(CONFIG_MMU)) key->private.mm = mm; else key->private.mm = NULL; key->private.address = address; return 0; } again: /* Ignore any VERIFY_READ mapping (futex common case) */ if (unlikely(should_fail_futex(true))) return -EFAULT; err = get_user_pages_fast(address, 1, FOLL_WRITE, &page); /* * If write access is not required (eg. FUTEX_WAIT), try * and get read-only access. */ if (err == -EFAULT && rw == FUTEX_READ) { err = get_user_pages_fast(address, 1, 0, &page); ro = 1; } if (err < 0) return err; else err = 0; /* * The treatment of mapping from this point on is critical. The folio * lock protects many things but in this context the folio lock * stabilizes mapping, prevents inode freeing in the shared * file-backed region case and guards against movement to swap cache. * * Strictly speaking the folio lock is not needed in all cases being * considered here and folio lock forces unnecessarily serialization. * From this point on, mapping will be re-verified if necessary and * folio lock will be acquired only if it is unavoidable * * Mapping checks require the folio so it is looked up now. For * anonymous pages, it does not matter if the folio is split * in the future as the key is based on the address. For * filesystem-backed pages, the precise page is required as the * index of the page determines the key. */ folio = page_folio(page); mapping = READ_ONCE(folio->mapping); /* * If folio->mapping is NULL, then it cannot be an anonymous * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast * found it, but truncated or holepunched or subjected to * invalidate_complete_page2 before we got the folio lock (also * cases which we are happy to fail). And we hold a reference, * so refcount care in invalidate_inode_page's remove_mapping * prevents drop_caches from setting mapping to NULL beneath us. * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: * an unlikely race, but we do need to retry for folio->mapping. */ if (unlikely(!mapping)) { int shmem_swizzled; /* * Folio lock is required to identify which special case above * applies. If this is really a shmem page then the folio lock * will prevent unexpected transitions. */ folio_lock(folio); shmem_swizzled = folio_test_swapcache(folio) || folio->mapping; folio_unlock(folio); folio_put(folio); if (shmem_swizzled) goto again; return -EFAULT; } /* * Private mappings are handled in a simple way. * * If the futex key is stored in anonymous memory, then the associated * object is the mm which is implicitly pinned by the calling process. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ if (folio_test_anon(folio)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. */ if (unlikely(should_fail_futex(true)) || ro) { err = -EFAULT; goto out; } key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; } else { struct inode *inode; /* * The associated futex object in this case is the inode and * the folio->mapping must be traversed. Ordinarily this should * be stabilised under folio lock but it's not strictly * necessary in this case as we just want to pin the inode, not * update i_pages or anything like that. * * The RCU read lock is taken as the inode is finally freed * under RCU. If the mapping still matches expectations then the * mapping->host can be safely accessed as being a valid inode. */ rcu_read_lock(); if (READ_ONCE(folio->mapping) != mapping) { rcu_read_unlock(); folio_put(folio); goto again; } inode = READ_ONCE(mapping->host); if (!inode) { rcu_read_unlock(); folio_put(folio); goto again; } key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); key->shared.pgoff = folio->index + folio_page_idx(folio, page); rcu_read_unlock(); } out: folio_put(folio); return err; } /** * fault_in_user_writeable() - Fault in user address and verify RW access * @uaddr: pointer to faulting user space address * * Slow path to fixup the fault we just took in the atomic write * access to @uaddr. * * We have no generic implementation of a non-destructive write to the * user address. We know that we faulted in the atomic pagefault * disabled section so we can as well avoid the #PF overhead by * calling get_user_pages() right away. */ int fault_in_user_writeable(u32 __user *uaddr) { struct mm_struct *mm = current->mm; int ret; mmap_read_lock(mm); ret = fixup_user_fault(mm, (unsigned long)uaddr, FAULT_FLAG_WRITE, NULL); mmap_read_unlock(mm); return ret < 0 ? ret : 0; } /** * futex_top_waiter() - Return the highest priority waiter on a futex * @hb: the hash bucket the futex_q's reside in * @key: the futex key (to distinguish it from other futex futex_q's) * * Must be called with the hb lock held. */ struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key) { struct futex_q *this; plist_for_each_entry(this, &hb->chain, list) { if (futex_match(&this->key, key)) return this; } return NULL; } int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval) { int ret; pagefault_disable(); ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); pagefault_enable(); return ret; } int futex_get_value_locked(u32 *dest, u32 __user *from) { int ret; pagefault_disable(); ret = __get_user(*dest, from); pagefault_enable(); return ret ? -EFAULT : 0; } /** * wait_for_owner_exiting - Block until the owner has exited * @ret: owner's current futex lock status * @exiting: Pointer to the exiting task * * Caller must hold a refcount on @exiting. */ void wait_for_owner_exiting(int ret, struct task_struct *exiting) { if (ret != -EBUSY) { WARN_ON_ONCE(exiting); return; } if (WARN_ON_ONCE(ret == -EBUSY && !exiting)) return; mutex_lock(&exiting->futex_exit_mutex); /* * No point in doing state checking here. If the waiter got here * while the task was in exec()->exec_futex_release() then it can * have any FUTEX_STATE_* value when the waiter has acquired the * mutex. OK, if running, EXITING or DEAD if it reached exit() * already. Highly unlikely and not a problem. Just one more round * through the futex maze. */ mutex_unlock(&exiting->futex_exit_mutex); put_task_struct(exiting); } /** * __futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be NULL and must be held by the caller. */ void __futex_unqueue(struct futex_q *q) { struct futex_hash_bucket *hb; if (WARN_ON_SMP(!q->lock_ptr) || WARN_ON(plist_node_empty(&q->list))) return; lockdep_assert_held(q->lock_ptr); hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); plist_del(&q->list, &hb->chain); futex_hb_waiters_dec(hb); } /* The key must be already stored in q->key. */ struct futex_hash_bucket *futex_q_lock(struct futex_q *q) __acquires(&hb->lock) { struct futex_hash_bucket *hb; hb = futex_hash(&q->key); /* * Increment the counter before taking the lock so that * a potential waker won't miss a to-be-slept task that is * waiting for the spinlock. This is safe as all futex_q_lock() * users end up calling futex_queue(). Similarly, for housekeeping, * decrement the counter at futex_q_unlock() when some error has * occurred and we don't end up adding the task to the list. */ futex_hb_waiters_inc(hb); /* implies smp_mb(); (A) */ q->lock_ptr = &hb->lock; spin_lock(&hb->lock); return hb; } void futex_q_unlock(struct futex_hash_bucket *hb) __releases(&hb->lock) { spin_unlock(&hb->lock); futex_hb_waiters_dec(hb); } void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) { int prio; /* * The priority used to register this element is * - either the real thread-priority for the real-time threads * (i.e. threads with a priority lower than MAX_RT_PRIO) * - or MAX_RT_PRIO for non-RT threads. * Thus, all RT-threads are woken first in priority order, and * the others are woken last, in FIFO order. */ prio = min(current->normal_prio, MAX_RT_PRIO); plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); q->task = current; } /** * futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be held by the caller. A call to futex_unqueue() must * be paired with exactly one earlier call to futex_queue(). * * Return: * - 1 - if the futex_q was still queued (and we removed unqueued it); * - 0 - if the futex_q was already removed by the waking thread */ int futex_unqueue(struct futex_q *q) { spinlock_t *lock_ptr; int ret = 0; /* In the common case we don't take the spinlock, which is nice. */ retry: /* * q->lock_ptr can change between this read and the following spin_lock. * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and * optimizing lock_ptr out of the logic below. */ lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* * q->lock_ptr can change between reading it and * spin_lock(), causing us to take the wrong lock. This * corrects the race condition. * * Reasoning goes like this: if we have the wrong lock, * q->lock_ptr must have changed (maybe several times) * between reading it and the spin_lock(). It can * change again after the spin_lock() but only if it was * already changed before the spin_lock(). It cannot, * however, change back to the original value. Therefore * we can detect whether we acquired the correct lock. */ if (unlikely(lock_ptr != q->lock_ptr)) { spin_unlock(lock_ptr); goto retry; } __futex_unqueue(q); BUG_ON(q->pi_state); spin_unlock(lock_ptr); ret = 1; } return ret; } /* * PI futexes can not be requeued and must remove themselves from the hash * bucket. The hash bucket lock (i.e. lock_ptr) is held. */ void futex_unqueue_pi(struct futex_q *q) { /* * If the lock was not acquired (due to timeout or signal) then the * rt_waiter is removed before futex_q is. If this is observed by * an unlocker after dropping the rtmutex wait lock and before * acquiring the hash bucket lock, then the unlocker dequeues the * futex_q from the hash bucket list to guarantee consistent state * vs. userspace. Therefore the dequeue here must be conditional. */ if (!plist_node_empty(&q->list)) __futex_unqueue(q); BUG_ON(!q->pi_state); put_pi_state(q->pi_state); q->pi_state = NULL; } /* Constants for the pending_op argument of handle_futex_death */ #define HANDLE_DEATH_PENDING true #define HANDLE_DEATH_LIST false /* * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, bool pi, bool pending_op) { u32 uval, nval, mval; pid_t owner; int err; /* Futex address must be 32bit aligned */ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0) return -1; retry: if (get_user(uval, uaddr)) return -1; /* * Special case for regular (non PI) futexes. The unlock path in * user space has two race scenarios: * * 1. The unlock path releases the user space futex value and * before it can execute the futex() syscall to wake up * waiters it is killed. * * 2. A woken up waiter is killed before it can acquire the * futex in user space. * * In the second case, the wake up notification could be generated * by the unlock path in user space after setting the futex value * to zero or by the kernel after setting the OWNER_DIED bit below. * * In both cases the TID validation below prevents a wakeup of * potential waiters which can cause these waiters to block * forever. * * In both cases the following conditions are met: * * 1) task->robust_list->list_op_pending != NULL * @pending_op == true * 2) The owner part of user space futex value == 0 * 3) Regular futex: @pi == false * * If these conditions are met, it is safe to attempt waking up a * potential waiter without touching the user space futex value and * trying to set the OWNER_DIED bit. If the futex value is zero, * the rest of the user space mutex state is consistent, so a woken * waiter will just take over the uncontended futex. Setting the * OWNER_DIED bit would create inconsistent state and malfunction * of the user space owner died handling. Otherwise, the OWNER_DIED * bit is already set, and the woken waiter is expected to deal with * this. */ owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); return 0; } if (owner != task_pid_vnr(curr)) return 0; /* * Ok, this dying thread is truly holding a futex * of interest. Set the OWNER_DIED bit atomically * via cmpxchg, and if the value had FUTEX_WAITERS * set, wake up a waiter (if any). (We have to do a * futex_wake() even if OWNER_DIED is already set - * to handle the rare but possible case of recursive * thread-death.) The rest of the cleanup is done in * userspace. */ mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; /* * We are not holding a lock here, but we want to have * the pagefault_disable/enable() protection because * we want to handle the fault gracefully. If the * access fails we try to fault in the futex with R/W * verification via get_user_pages. get_user() above * does not guarantee R/W access. If that fails we * give up and leave the futex locked. */ if ((err = futex_cmpxchg_value_locked(&nval, uaddr, uval, mval))) { switch (err) { case -EFAULT: if (fault_in_user_writeable(uaddr)) return -1; goto retry; case -EAGAIN: cond_resched(); goto retry; default: WARN_ON_ONCE(1); return err; } } if (nval != uval) goto retry; /* * Wake robust non-PI futexes here. The wakeup of * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int fetch_robust_entry(struct robust_list __user **entry, struct robust_list __user * __user *head, unsigned int *pi) { unsigned long uentry; if (get_user(uentry, (unsigned long __user *)head)) return -EFAULT; *entry = (void __user *)(uentry & ~1UL); *pi = uentry & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; unsigned long futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (fetch_robust_entry(&entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi); /* * A pending lock might already be on the list, so * don't process it twice: */ if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { handle_futex_death((void __user *)pending + futex_offset, curr, pip, HANDLE_DEATH_PENDING); } } #ifdef CONFIG_COMPAT static void __user *futex_uaddr(struct robust_list __user *entry, compat_long_t futex_offset) { compat_uptr_t base = ptr_to_compat(entry); void __user *uaddr = compat_ptr(base + futex_offset); return uaddr; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, compat_uptr_t __user *head, unsigned int *pi) { if (get_user(*uentry, head)) return -EFAULT; *entry = compat_ptr((*uentry) & ~1); *pi = (unsigned int)(*uentry) & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void compat_exit_robust_list(struct task_struct *curr) { struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; compat_uptr_t uentry, next_uentry, upending; compat_long_t futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (compat_fetch_robust_entry(&upending, &pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != (struct robust_list __user *) &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = compat_fetch_robust_entry(&next_uentry, &next_entry, (compat_uptr_t __user *)&entry->next, &next_pi); /* * A pending lock might already be on the list, so * dont process it twice: */ if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); if (handle_futex_death(uaddr, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; uentry = next_uentry; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } } #endif #ifdef CONFIG_FUTEX_PI /* * This task is holding PI mutexes at exit time => bad. * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */ static void exit_pi_state_list(struct task_struct *curr) { struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; struct futex_hash_bucket *hb; union futex_key key = FUTEX_KEY_INIT; /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: */ raw_spin_lock_irq(&curr->pi_lock); while (!list_empty(head)) { next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; hb = futex_hash(&key); /* * We can race against put_pi_state() removing itself from the * list (a waiter going away). put_pi_state() will first * decrement the reference count and then modify the list, so * its possible to see the list entry but fail this reference * acquire. * * In that case; drop the locks to let put_pi_state() make * progress and retry the loop. */ if (!refcount_inc_not_zero(&pi_state->refcount)) { raw_spin_unlock_irq(&curr->pi_lock); cpu_relax(); raw_spin_lock_irq(&curr->pi_lock); continue; } raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { /* retain curr->pi_lock for the loop invariant */ raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); put_pi_state(pi_state); continue; } WARN_ON(pi_state->owner != curr); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; raw_spin_unlock(&curr->pi_lock); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); put_pi_state(pi_state); raw_spin_lock_irq(&curr->pi_lock); } raw_spin_unlock_irq(&curr->pi_lock); } #else static inline void exit_pi_state_list(struct task_struct *curr) { } #endif static void futex_cleanup(struct task_struct *tsk) { if (unlikely(tsk->robust_list)) { exit_robust_list(tsk); tsk->robust_list = NULL; } #ifdef CONFIG_COMPAT if (unlikely(tsk->compat_robust_list)) { compat_exit_robust_list(tsk); tsk->compat_robust_list = NULL; } #endif if (unlikely(!list_empty(&tsk->pi_state_list))) exit_pi_state_list(tsk); } /** * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD * @tsk: task to set the state on * * Set the futex exit state of the task lockless. The futex waiter code * observes that state when a task is exiting and loops until the task has * actually finished the futex cleanup. The worst case for this is that the * waiter runs through the wait loop until the state becomes visible. * * This is called from the recursive fault handling path in make_task_dead(). * * This is best effort. Either the futex exit code has run already or * not. If the OWNER_DIED bit has been set on the futex then the waiter can * take it over. If not, the problem is pushed back to user space. If the * futex exit code did not run yet, then an already queued waiter might * block forever, but there is nothing which can be done about that. */ void futex_exit_recursive(struct task_struct *tsk) { /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ if (tsk->futex_state == FUTEX_STATE_EXITING) mutex_unlock(&tsk->futex_exit_mutex); tsk->futex_state = FUTEX_STATE_DEAD; } static void futex_cleanup_begin(struct task_struct *tsk) { /* * Prevent various race issues against a concurrent incoming waiter * including live locks by forcing the waiter to block on * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in * attach_to_pi_owner(). */ mutex_lock(&tsk->futex_exit_mutex); /* * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. * * This ensures that all subsequent checks of tsk->futex_state in * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with * tsk->pi_lock held. * * It guarantees also that a pi_state which was queued right before * the state change under tsk->pi_lock by a concurrent waiter must * be observed in exit_pi_state_list(). */ raw_spin_lock_irq(&tsk->pi_lock); tsk->futex_state = FUTEX_STATE_EXITING; raw_spin_unlock_irq(&tsk->pi_lock); } static void futex_cleanup_end(struct task_struct *tsk, int state) { /* * Lockless store. The only side effect is that an observer might * take another loop until it becomes visible. */ tsk->futex_state = state; /* * Drop the exit protection. This unblocks waiters which observed * FUTEX_STATE_EXITING to reevaluate the state. */ mutex_unlock(&tsk->futex_exit_mutex); } void futex_exec_release(struct task_struct *tsk) { /* * The state handling is done for consistency, but in the case of * exec() there is no way to prevent further damage as the PID stays * the same. But for the unlikely and arguably buggy case that a * futex is held on exec(), this provides at least as much state * consistency protection which is possible. */ futex_cleanup_begin(tsk); futex_cleanup(tsk); /* * Reset the state to FUTEX_STATE_OK. The task is alive and about * exec a new binary. */ futex_cleanup_end(tsk, FUTEX_STATE_OK); } void futex_exit_release(struct task_struct *tsk) { futex_cleanup_begin(tsk); futex_cleanup(tsk); futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } static int __init futex_init(void) { unsigned int futex_shift; unsigned long i; #ifdef CONFIG_BASE_SMALL futex_hashsize = 16; #else futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus()); #endif futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues), futex_hashsize, 0, 0, &futex_shift, NULL, futex_hashsize, futex_hashsize); futex_hashsize = 1UL << futex_shift; for (i = 0; i < futex_hashsize; i++) { atomic_set(&futex_queues[i].waiters, 0); plist_head_init(&futex_queues[i].chain); spin_lock_init(&futex_queues[i].lock); } return 0; } core_initcall(futex_init); |
| 49 49 56 56 18 18 56 56 56 55 54 20 8 7 7 7 20 14 14 14 14 14 14 14 10 15 7 2 2 2 2 2 2 2 2 6 6 6 6 6 1 6 6 6 6 6 6 6 6 6 6 6 6 3 3 3 5 5 5 41 40 38 52 10 5 23 5 3 5 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 | // SPDX-License-Identifier: GPL-2.0 /* * file.c - part of debugfs, a tiny little debug file system * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Inc. * * debugfs is for people to use instead of /proc or /sys. * See Documentation/filesystems/ for more details. */ #include <linux/module.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/io.h> #include <linux/slab.h> #include <linux/atomic.h> #include <linux/device.h> #include <linux/pm_runtime.h> #include <linux/poll.h> #include <linux/security.h> #include "internal.h" struct poll_table_struct; static ssize_t default_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) { return 0; } static ssize_t default_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { return count; } const struct file_operations debugfs_noop_file_operations = { .read = default_read_file, .write = default_write_file, .open = simple_open, .llseek = noop_llseek, }; #define F_DENTRY(filp) ((filp)->f_path.dentry) const struct file_operations *debugfs_real_fops(const struct file *filp) { struct debugfs_fsdata *fsd = F_DENTRY(filp)->d_fsdata; if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) { /* * Urgh, we've been called w/o a protecting * debugfs_file_get(). */ WARN_ON(1); return NULL; } return fsd->real_fops; } EXPORT_SYMBOL_GPL(debugfs_real_fops); /** * debugfs_file_get - mark the beginning of file data access * @dentry: the dentry object whose data is being accessed. * * Up to a matching call to debugfs_file_put(), any successive call * into the file removing functions debugfs_remove() and * debugfs_remove_recursive() will block. Since associated private * file data may only get freed after a successful return of any of * the removal functions, you may safely access it after a successful * call to debugfs_file_get() without worrying about lifetime issues. * * If -%EIO is returned, the file has already been removed and thus, * it is not safe to access any of its data. If, on the other hand, * it is allowed to access the file data, zero is returned. */ int debugfs_file_get(struct dentry *dentry) { struct debugfs_fsdata *fsd; void *d_fsd; /* * This could only happen if some debugfs user erroneously calls * debugfs_file_get() on a dentry that isn't even a file, let * them know about it. */ if (WARN_ON(!d_is_reg(dentry))) return -EINVAL; d_fsd = READ_ONCE(dentry->d_fsdata); if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) { fsd = d_fsd; } else { fsd = kmalloc(sizeof(*fsd), GFP_KERNEL); if (!fsd) return -ENOMEM; fsd->real_fops = (void *)((unsigned long)d_fsd & ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); refcount_set(&fsd->active_users, 1); init_completion(&fsd->active_users_drained); INIT_LIST_HEAD(&fsd->cancellations); mutex_init(&fsd->cancellations_mtx); if (cmpxchg(&dentry->d_fsdata, d_fsd, fsd) != d_fsd) { mutex_destroy(&fsd->cancellations_mtx); kfree(fsd); fsd = READ_ONCE(dentry->d_fsdata); } } /* * In case of a successful cmpxchg() above, this check is * strictly necessary and must follow it, see the comment in * __debugfs_remove_file(). * OTOH, if the cmpxchg() hasn't been executed or wasn't * successful, this serves the purpose of not starving * removers. */ if (d_unlinked(dentry)) return -EIO; if (!refcount_inc_not_zero(&fsd->active_users)) return -EIO; return 0; } EXPORT_SYMBOL_GPL(debugfs_file_get); /** * debugfs_file_put - mark the end of file data access * @dentry: the dentry object formerly passed to * debugfs_file_get(). * * Allow any ongoing concurrent call into debugfs_remove() or * debugfs_remove_recursive() blocked by a former call to * debugfs_file_get() to proceed and return to its caller. */ void debugfs_file_put(struct dentry *dentry) { struct debugfs_fsdata *fsd = READ_ONCE(dentry->d_fsdata); if (refcount_dec_and_test(&fsd->active_users)) complete(&fsd->active_users_drained); } EXPORT_SYMBOL_GPL(debugfs_file_put); /** * debugfs_enter_cancellation - enter a debugfs cancellation * @file: the file being accessed * @cancellation: the cancellation object, the cancel callback * inside of it must be initialized * * When a debugfs file is removed it needs to wait for all active * operations to complete. However, the operation itself may need * to wait for hardware or completion of some asynchronous process * or similar. As such, it may need to be cancelled to avoid long * waits or even deadlocks. * * This function can be used inside a debugfs handler that may * need to be cancelled. As soon as this function is called, the * cancellation's 'cancel' callback may be called, at which point * the caller should proceed to call debugfs_leave_cancellation() * and leave the debugfs handler function as soon as possible. * Note that the 'cancel' callback is only ever called in the * context of some kind of debugfs_remove(). * * This function must be paired with debugfs_leave_cancellation(). */ void debugfs_enter_cancellation(struct file *file, struct debugfs_cancellation *cancellation) { struct debugfs_fsdata *fsd; struct dentry *dentry = F_DENTRY(file); INIT_LIST_HEAD(&cancellation->list); if (WARN_ON(!d_is_reg(dentry))) return; if (WARN_ON(!cancellation->cancel)) return; fsd = READ_ONCE(dentry->d_fsdata); if (WARN_ON(!fsd || ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) return; mutex_lock(&fsd->cancellations_mtx); list_add(&cancellation->list, &fsd->cancellations); mutex_unlock(&fsd->cancellations_mtx); /* if we're already removing wake it up to cancel */ if (d_unlinked(dentry)) complete(&fsd->active_users_drained); } EXPORT_SYMBOL_GPL(debugfs_enter_cancellation); /** * debugfs_leave_cancellation - leave cancellation section * @file: the file being accessed * @cancellation: the cancellation previously registered with * debugfs_enter_cancellation() * * See the documentation of debugfs_enter_cancellation(). */ void debugfs_leave_cancellation(struct file *file, struct debugfs_cancellation *cancellation) { struct debugfs_fsdata *fsd; struct dentry *dentry = F_DENTRY(file); if (WARN_ON(!d_is_reg(dentry))) return; fsd = READ_ONCE(dentry->d_fsdata); if (WARN_ON(!fsd || ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) return; mutex_lock(&fsd->cancellations_mtx); if (!list_empty(&cancellation->list)) list_del(&cancellation->list); mutex_unlock(&fsd->cancellations_mtx); } EXPORT_SYMBOL_GPL(debugfs_leave_cancellation); /* * Only permit access to world-readable files when the kernel is locked down. * We also need to exclude any file that has ways to write or alter it as root * can bypass the permissions check. */ static int debugfs_locked_down(struct inode *inode, struct file *filp, const struct file_operations *real_fops) { if ((inode->i_mode & 07777 & ~0444) == 0 && !(filp->f_mode & FMODE_WRITE) && !real_fops->unlocked_ioctl && !real_fops->compat_ioctl && !real_fops->mmap) return 0; if (security_locked_down(LOCKDOWN_DEBUGFS)) return -EPERM; return 0; } static int open_proxy_open(struct inode *inode, struct file *filp) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = NULL; int r; r = debugfs_file_get(dentry); if (r) return r == -EIO ? -ENOENT : r; real_fops = debugfs_real_fops(filp); r = debugfs_locked_down(inode, filp, real_fops); if (r) goto out; if (!fops_get(real_fops)) { #ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) { r = -ENXIO; goto out; } #endif /* Huh? Module did not clean up after itself at exit? */ WARN(1, "debugfs file owner did not clean up at exit: %pd", dentry); r = -ENXIO; goto out; } replace_fops(filp, real_fops); if (real_fops->open) r = real_fops->open(inode, filp); out: debugfs_file_put(dentry); return r; } const struct file_operations debugfs_open_proxy_file_operations = { .open = open_proxy_open, }; #define PROTO(args...) args #define ARGS(args...) args #define FULL_PROXY_FUNC(name, ret_type, filp, proto, args) \ static ret_type full_proxy_ ## name(proto) \ { \ struct dentry *dentry = F_DENTRY(filp); \ const struct file_operations *real_fops; \ ret_type r; \ \ r = debugfs_file_get(dentry); \ if (unlikely(r)) \ return r; \ real_fops = debugfs_real_fops(filp); \ r = real_fops->name(args); \ debugfs_file_put(dentry); \ return r; \ } FULL_PROXY_FUNC(llseek, loff_t, filp, PROTO(struct file *filp, loff_t offset, int whence), ARGS(filp, offset, whence)); FULL_PROXY_FUNC(read, ssize_t, filp, PROTO(struct file *filp, char __user *buf, size_t size, loff_t *ppos), ARGS(filp, buf, size, ppos)); FULL_PROXY_FUNC(write, ssize_t, filp, PROTO(struct file *filp, const char __user *buf, size_t size, loff_t *ppos), ARGS(filp, buf, size, ppos)); FULL_PROXY_FUNC(unlocked_ioctl, long, filp, PROTO(struct file *filp, unsigned int cmd, unsigned long arg), ARGS(filp, cmd, arg)); static __poll_t full_proxy_poll(struct file *filp, struct poll_table_struct *wait) { struct dentry *dentry = F_DENTRY(filp); __poll_t r = 0; const struct file_operations *real_fops; if (debugfs_file_get(dentry)) return EPOLLHUP; real_fops = debugfs_real_fops(filp); r = real_fops->poll(filp, wait); debugfs_file_put(dentry); return r; } static int full_proxy_release(struct inode *inode, struct file *filp) { const struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = debugfs_real_fops(filp); const struct file_operations *proxy_fops = filp->f_op; int r = 0; /* * We must not protect this against removal races here: the * original releaser should be called unconditionally in order * not to leak any resources. Releasers must not assume that * ->i_private is still being meaningful here. */ if (real_fops->release) r = real_fops->release(inode, filp); replace_fops(filp, d_inode(dentry)->i_fop); kfree(proxy_fops); fops_put(real_fops); return r; } static void __full_proxy_fops_init(struct file_operations *proxy_fops, const struct file_operations *real_fops) { proxy_fops->release = full_proxy_release; if (real_fops->llseek) proxy_fops->llseek = full_proxy_llseek; if (real_fops->read) proxy_fops->read = full_proxy_read; if (real_fops->write) proxy_fops->write = full_proxy_write; if (real_fops->poll) proxy_fops->poll = full_proxy_poll; if (real_fops->unlocked_ioctl) proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl; } static int full_proxy_open(struct inode *inode, struct file *filp) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = NULL; struct file_operations *proxy_fops = NULL; int r; r = debugfs_file_get(dentry); if (r) return r == -EIO ? -ENOENT : r; real_fops = debugfs_real_fops(filp); r = debugfs_locked_down(inode, filp, real_fops); if (r) goto out; if (!fops_get(real_fops)) { #ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) { r = -ENXIO; goto out; } #endif /* Huh? Module did not cleanup after itself at exit? */ WARN(1, "debugfs file owner did not clean up at exit: %pd", dentry); r = -ENXIO; goto out; } proxy_fops = kzalloc(sizeof(*proxy_fops), GFP_KERNEL); if (!proxy_fops) { r = -ENOMEM; goto free_proxy; } __full_proxy_fops_init(proxy_fops, real_fops); replace_fops(filp, proxy_fops); if (real_fops->open) { r = real_fops->open(inode, filp); if (r) { replace_fops(filp, d_inode(dentry)->i_fop); goto free_proxy; } else if (filp->f_op != proxy_fops) { /* No protection against file removal anymore. */ WARN(1, "debugfs file owner replaced proxy fops: %pd", dentry); goto free_proxy; } } goto out; free_proxy: kfree(proxy_fops); fops_put(real_fops); out: debugfs_file_put(dentry); return r; } const struct file_operations debugfs_full_proxy_file_operations = { .open = full_proxy_open, }; ssize_t debugfs_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { struct dentry *dentry = F_DENTRY(file); ssize_t ret; ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; ret = simple_attr_read(file, buf, len, ppos); debugfs_file_put(dentry); return ret; } EXPORT_SYMBOL_GPL(debugfs_attr_read); static ssize_t debugfs_attr_write_xsigned(struct file *file, const char __user *buf, size_t len, loff_t *ppos, bool is_signed) { struct dentry *dentry = F_DENTRY(file); ssize_t ret; ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; if (is_signed) ret = simple_attr_write_signed(file, buf, len, ppos); else ret = simple_attr_write(file, buf, len, ppos); debugfs_file_put(dentry); return ret; } ssize_t debugfs_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return debugfs_attr_write_xsigned(file, buf, len, ppos, false); } EXPORT_SYMBOL_GPL(debugfs_attr_write); ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return debugfs_attr_write_xsigned(file, buf, len, ppos, true); } EXPORT_SYMBOL_GPL(debugfs_attr_write_signed); static struct dentry *debugfs_create_mode_unsafe(const char *name, umode_t mode, struct dentry *parent, void *value, const struct file_operations *fops, const struct file_operations *fops_ro, const struct file_operations *fops_wo) { /* if there are no write bits set, make read only */ if (!(mode & S_IWUGO)) return debugfs_create_file_unsafe(name, mode, parent, value, fops_ro); /* if there are no read bits set, make write only */ if (!(mode & S_IRUGO)) return debugfs_create_file_unsafe(name, mode, parent, value, fops_wo); return debugfs_create_file_unsafe(name, mode, parent, value, fops); } static int debugfs_u8_set(void *data, u64 val) { *(u8 *)data = val; return 0; } static int debugfs_u8_get(void *data, u64 *val) { *val = *(u8 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u8, debugfs_u8_get, debugfs_u8_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_ro, debugfs_u8_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n"); /** * debugfs_create_u8 - create a debugfs file that is used to read and write an unsigned 8-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u8, &fops_u8_ro, &fops_u8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u8); static int debugfs_u16_set(void *data, u64 val) { *(u16 *)data = val; return 0; } static int debugfs_u16_get(void *data, u64 *val) { *val = *(u16 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u16, debugfs_u16_get, debugfs_u16_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_ro, debugfs_u16_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n"); /** * debugfs_create_u16 - create a debugfs file that is used to read and write an unsigned 16-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u16, &fops_u16_ro, &fops_u16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u16); static int debugfs_u32_set(void *data, u64 val) { *(u32 *)data = val; return 0; } static int debugfs_u32_get(void *data, u64 *val) { *val = *(u32 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u32, debugfs_u32_get, debugfs_u32_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_ro, debugfs_u32_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n"); /** * debugfs_create_u32 - create a debugfs file that is used to read and write an unsigned 32-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u32, &fops_u32_ro, &fops_u32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u32); static int debugfs_u64_set(void *data, u64 val) { *(u64 *)data = val; return 0; } static int debugfs_u64_get(void *data, u64 *val) { *val = *(u64 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u64, debugfs_u64_get, debugfs_u64_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_ro, debugfs_u64_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n"); /** * debugfs_create_u64 - create a debugfs file that is used to read and write an unsigned 64-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u64, &fops_u64_ro, &fops_u64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u64); static int debugfs_ulong_set(void *data, u64 val) { *(unsigned long *)data = val; return 0; } static int debugfs_ulong_get(void *data, u64 *val) { *val = *(unsigned long *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong, debugfs_ulong_get, debugfs_ulong_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong_ro, debugfs_ulong_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong_wo, NULL, debugfs_ulong_set, "%llu\n"); /** * debugfs_create_ulong - create a debugfs file that is used to read and write * an unsigned long value. * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_ulong(const char *name, umode_t mode, struct dentry *parent, unsigned long *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_ulong, &fops_ulong_ro, &fops_ulong_wo); } EXPORT_SYMBOL_GPL(debugfs_create_ulong); DEFINE_DEBUGFS_ATTRIBUTE(fops_x8, debugfs_u8_get, debugfs_u8_set, "0x%02llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x8_ro, debugfs_u8_get, NULL, "0x%02llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x8_wo, NULL, debugfs_u8_set, "0x%02llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x16, debugfs_u16_get, debugfs_u16_set, "0x%04llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x16_ro, debugfs_u16_get, NULL, "0x%04llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x16_wo, NULL, debugfs_u16_set, "0x%04llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x32, debugfs_u32_get, debugfs_u32_set, "0x%08llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x32_ro, debugfs_u32_get, NULL, "0x%08llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x32_wo, NULL, debugfs_u32_set, "0x%08llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x64, debugfs_u64_get, debugfs_u64_set, "0x%016llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x64_ro, debugfs_u64_get, NULL, "0x%016llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x64_wo, NULL, debugfs_u64_set, "0x%016llx\n"); /* * debugfs_create_x{8,16,32,64} - create a debugfs file that is used to read and write an unsigned {8,16,32,64}-bit value * * These functions are exactly the same as the above functions (but use a hex * output for the decimal challenged). For details look at the above unsigned * decimal functions. */ /** * debugfs_create_x8 - create a debugfs file that is used to read and write an unsigned 8-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x8, &fops_x8_ro, &fops_x8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x8); /** * debugfs_create_x16 - create a debugfs file that is used to read and write an unsigned 16-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x16, &fops_x16_ro, &fops_x16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x16); /** * debugfs_create_x32 - create a debugfs file that is used to read and write an unsigned 32-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x32, &fops_x32_ro, &fops_x32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x32); /** * debugfs_create_x64 - create a debugfs file that is used to read and write an unsigned 64-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x64, &fops_x64_ro, &fops_x64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x64); static int debugfs_size_t_set(void *data, u64 val) { *(size_t *)data = val; return 0; } static int debugfs_size_t_get(void *data, u64 *val) { *val = *(size_t *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t, debugfs_size_t_get, debugfs_size_t_set, "%llu\n"); /* %llu and %zu are more or less the same */ DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t_ro, debugfs_size_t_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t_wo, NULL, debugfs_size_t_set, "%llu\n"); /** * debugfs_create_size_t - create a debugfs file that is used to read and write an size_t value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_size_t, &fops_size_t_ro, &fops_size_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_size_t); static int debugfs_atomic_t_set(void *data, u64 val) { atomic_set((atomic_t *)data, val); return 0; } static int debugfs_atomic_t_get(void *data, u64 *val) { *val = atomic_read((atomic_t *)data); return 0; } DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t, debugfs_atomic_t_get, debugfs_atomic_t_set, "%lld\n"); DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_ro, debugfs_atomic_t_get, NULL, "%lld\n"); DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, "%lld\n"); /** * debugfs_create_atomic_t - create a debugfs file that is used to read and * write an atomic_t value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_atomic_t, &fops_atomic_t_ro, &fops_atomic_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_atomic_t); ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { char buf[2]; bool val; int r; struct dentry *dentry = F_DENTRY(file); r = debugfs_file_get(dentry); if (unlikely(r)) return r; val = *(bool *)file->private_data; debugfs_file_put(dentry); if (val) buf[0] = 'Y'; else buf[0] = 'N'; buf[1] = '\n'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } EXPORT_SYMBOL_GPL(debugfs_read_file_bool); ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { bool bv; int r; bool *val = file->private_data; struct dentry *dentry = F_DENTRY(file); r = kstrtobool_from_user(user_buf, count, &bv); if (!r) { r = debugfs_file_get(dentry); if (unlikely(r)) return r; *val = bv; debugfs_file_put(dentry); } return count; } EXPORT_SYMBOL_GPL(debugfs_write_file_bool); static const struct file_operations fops_bool = { .read = debugfs_read_file_bool, .write = debugfs_write_file_bool, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_bool_ro = { .read = debugfs_read_file_bool, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_bool_wo = { .write = debugfs_write_file_bool, .open = simple_open, .llseek = default_llseek, }; /** * debugfs_create_bool - create a debugfs file that is used to read and write a boolean value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, bool *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_bool, &fops_bool_ro, &fops_bool_wo); } EXPORT_SYMBOL_GPL(debugfs_create_bool); ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct dentry *dentry = F_DENTRY(file); char *str, *copy = NULL; int copy_len, len; ssize_t ret; ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; str = *(char **)file->private_data; len = strlen(str) + 1; copy = kmalloc(len, GFP_KERNEL); if (!copy) { debugfs_file_put(dentry); return -ENOMEM; } copy_len = strscpy(copy, str, len); debugfs_file_put(dentry); if (copy_len < 0) { kfree(copy); return copy_len; } copy[copy_len] = '\n'; ret = simple_read_from_buffer(user_buf, count, ppos, copy, len); kfree(copy); return ret; } EXPORT_SYMBOL_GPL(debugfs_create_str); static ssize_t debugfs_write_file_str(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct dentry *dentry = F_DENTRY(file); char *old, *new = NULL; int pos = *ppos; int r; r = debugfs_file_get(dentry); if (unlikely(r)) return r; old = *(char **)file->private_data; /* only allow strict concatenation */ r = -EINVAL; if (pos && pos != strlen(old)) goto error; r = -E2BIG; if (pos + count + 1 > PAGE_SIZE) goto error; r = -ENOMEM; new = kmalloc(pos + count + 1, GFP_KERNEL); if (!new) goto error; if (pos) memcpy(new, old, pos); r = -EFAULT; if (copy_from_user(new + pos, user_buf, count)) goto error; new[pos + count] = '\0'; strim(new); rcu_assign_pointer(*(char __rcu **)file->private_data, new); synchronize_rcu(); kfree(old); debugfs_file_put(dentry); return count; error: kfree(new); debugfs_file_put(dentry); return r; } static const struct file_operations fops_str = { .read = debugfs_read_file_str, .write = debugfs_write_file_str, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_str_ro = { .read = debugfs_read_file_str, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_str_wo = { .write = debugfs_write_file_str, .open = simple_open, .llseek = default_llseek, }; /** * debugfs_create_str - create a debugfs file that is used to read and write a string value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_str(const char *name, umode_t mode, struct dentry *parent, char **value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_str, &fops_str_ro, &fops_str_wo); } static ssize_t read_file_blob(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct debugfs_blob_wrapper *blob = file->private_data; struct dentry *dentry = F_DENTRY(file); ssize_t r; r = debugfs_file_get(dentry); if (unlikely(r)) return r; r = simple_read_from_buffer(user_buf, count, ppos, blob->data, blob->size); debugfs_file_put(dentry); return r; } static ssize_t write_file_blob(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct debugfs_blob_wrapper *blob = file->private_data; struct dentry *dentry = F_DENTRY(file); ssize_t r; r = debugfs_file_get(dentry); if (unlikely(r)) return r; r = simple_write_to_buffer(blob->data, blob->size, ppos, user_buf, count); debugfs_file_put(dentry); return r; } static const struct file_operations fops_blob = { .read = read_file_blob, .write = write_file_blob, .open = simple_open, .llseek = default_llseek, }; /** * debugfs_create_blob - create a debugfs file that is used to read and write * a binary blob * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @blob: a pointer to a struct debugfs_blob_wrapper which contains a pointer * to the blob data and the size of the data. * * This function creates a file in debugfs with the given name that exports * @blob->data as a binary blob. If the @mode variable is so set it can be * read from and written to. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be * returned. * * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will * be returned. */ struct dentry *debugfs_create_blob(const char *name, umode_t mode, struct dentry *parent, struct debugfs_blob_wrapper *blob) { return debugfs_create_file_unsafe(name, mode & 0644, parent, blob, &fops_blob); } EXPORT_SYMBOL_GPL(debugfs_create_blob); static size_t u32_format_array(char *buf, size_t bufsize, u32 *array, int array_size) { size_t ret = 0; while (--array_size >= 0) { size_t len; char term = array_size ? ' ' : '\n'; len = snprintf(buf, bufsize, "%u%c", *array++, term); ret += len; buf += len; bufsize -= len; } return ret; } static int u32_array_open(struct inode *inode, struct file *file) { struct debugfs_u32_array *data = inode->i_private; int size, elements = data->n_elements; char *buf; /* * Max size: * - 10 digits + ' '/'\n' = 11 bytes per number * - terminating NUL character */ size = elements*11; buf = kmalloc(size+1, GFP_KERNEL); if (!buf) return -ENOMEM; buf[size] = 0; file->private_data = buf; u32_format_array(buf, size, data->array, data->n_elements); return nonseekable_open(inode, file); } static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { size_t size = strlen(file->private_data); return simple_read_from_buffer(buf, len, ppos, file->private_data, size); } static int u32_array_release(struct inode *inode, struct file *file) { kfree(file->private_data); return 0; } static const struct file_operations u32_array_fops = { .owner = THIS_MODULE, .open = u32_array_open, .release = u32_array_release, .read = u32_array_read, }; /** * debugfs_create_u32_array - create a debugfs file that is used to read u32 * array. * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @array: wrapper struct containing data pointer and size of the array. * * This function creates a file in debugfs with the given name that exports * @array as data. If the @mode variable is so set it can be read from. * Writing is not supported. Seek within the file is also not supported. * Once array is created its size can not be changed. */ void debugfs_create_u32_array(const char *name, umode_t mode, struct dentry *parent, struct debugfs_u32_array *array) { debugfs_create_file_unsafe(name, mode, parent, array, &u32_array_fops); } EXPORT_SYMBOL_GPL(debugfs_create_u32_array); #ifdef CONFIG_HAS_IOMEM /* * The regset32 stuff is used to print 32-bit registers using the * seq_file utilities. We offer printing a register set in an already-opened * sequential file or create a debugfs file that only prints a regset32. */ /** * debugfs_print_regs32 - use seq_print to describe a set of registers * @s: the seq_file structure being used to generate output * @regs: an array if struct debugfs_reg32 structures * @nregs: the length of the above array * @base: the base address to be used in reading the registers * @prefix: a string to be prefixed to every output line * * This function outputs a text block describing the current values of * some 32-bit hardware registers. It is meant to be used within debugfs * files based on seq_file that need to show registers, intermixed with other * information. The prefix argument may be used to specify a leading string, * because some peripherals have several blocks of identical registers, * for example configuration of dma channels */ void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix) { int i; for (i = 0; i < nregs; i++, regs++) { if (prefix) seq_printf(s, "%s", prefix); seq_printf(s, "%s = 0x%08x\n", regs->name, readl(base + regs->offset)); if (seq_has_overflowed(s)) break; } } EXPORT_SYMBOL_GPL(debugfs_print_regs32); static int debugfs_regset32_show(struct seq_file *s, void *data) { struct debugfs_regset32 *regset = s->private; if (regset->dev) pm_runtime_get_sync(regset->dev); debugfs_print_regs32(s, regset->regs, regset->nregs, regset->base, ""); if (regset->dev) pm_runtime_put(regset->dev); return 0; } DEFINE_SHOW_ATTRIBUTE(debugfs_regset32); /** * debugfs_create_regset32 - create a debugfs file that returns register values * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @regset: a pointer to a struct debugfs_regset32, which contains a pointer * to an array of register definitions, the array size and the base * address where the register bank is to be found. * * This function creates a file in debugfs with the given name that reports * the names and values of a set of 32-bit registers. If the @mode variable * is so set it can be read from. Writing is not supported. */ void debugfs_create_regset32(const char *name, umode_t mode, struct dentry *parent, struct debugfs_regset32 *regset) { debugfs_create_file(name, mode, parent, regset, &debugfs_regset32_fops); } EXPORT_SYMBOL_GPL(debugfs_create_regset32); #endif /* CONFIG_HAS_IOMEM */ struct debugfs_devm_entry { int (*read)(struct seq_file *seq, void *data); struct device *dev; }; static int debugfs_devm_entry_open(struct inode *inode, struct file *f) { struct debugfs_devm_entry *entry = inode->i_private; return single_open(f, entry->read, entry->dev); } static const struct file_operations debugfs_devm_entry_ops = { .owner = THIS_MODULE, .open = debugfs_devm_entry_open, .release = single_release, .read = seq_read, .llseek = seq_lseek }; /** * debugfs_create_devm_seqfile - create a debugfs file that is bound to device. * * @dev: device related to this debugfs file. * @name: name of the debugfs file. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @read_fn: function pointer called to print the seq_file content. */ void debugfs_create_devm_seqfile(struct device *dev, const char *name, struct dentry *parent, int (*read_fn)(struct seq_file *s, void *data)) { struct debugfs_devm_entry *entry; if (IS_ERR(parent)) return; entry = devm_kzalloc(dev, sizeof(*entry), GFP_KERNEL); if (!entry) return; entry->read = read_fn; entry->dev = dev; debugfs_create_file(name, S_IRUGO, parent, entry, &debugfs_devm_entry_ops); } EXPORT_SYMBOL_GPL(debugfs_create_devm_seqfile); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2008 by Karsten Keil <kkeil@novell.com> */ #include <linux/slab.h> #include <linux/types.h> #include <linux/stddef.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/mISDNif.h> #include "core.h" static u_int debug; MODULE_AUTHOR("Karsten Keil"); MODULE_DESCRIPTION("Modular ISDN core driver"); MODULE_LICENSE("GPL"); module_param(debug, uint, S_IRUGO | S_IWUSR); static u64 device_ids; #define MAX_DEVICE_ID 63 static LIST_HEAD(Bprotocols); static DEFINE_RWLOCK(bp_lock); static void mISDN_dev_release(struct device *dev) { /* nothing to do: the device is part of its parent's data structure */ } static ssize_t id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mISDNdevice *mdev = dev_to_mISDN(dev); if (!mdev) return -ENODEV; return sprintf(buf, "%d\n", mdev->id); } static DEVICE_ATTR_RO(id); static ssize_t nrbchan_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mISDNdevice *mdev = dev_to_mISDN(dev); if (!mdev) return -ENODEV; return sprintf(buf, "%d\n", mdev->nrbchan); } static DEVICE_ATTR_RO(nrbchan); static ssize_t d_protocols_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mISDNdevice *mdev = dev_to_mISDN(dev); if (!mdev) return -ENODEV; return sprintf(buf, "%d\n", mdev->Dprotocols); } static DEVICE_ATTR_RO(d_protocols); static ssize_t b_protocols_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mISDNdevice *mdev = dev_to_mISDN(dev); if (!mdev) return -ENODEV; return sprintf(buf, "%d\n", mdev->Bprotocols | get_all_Bprotocols()); } static DEVICE_ATTR_RO(b_protocols); static ssize_t protocol_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mISDNdevice *mdev = dev_to_mISDN(dev); if (!mdev) return -ENODEV; return sprintf(buf, "%d\n", mdev->D.protocol); } static DEVICE_ATTR_RO(protocol); static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { strcpy(buf, dev_name(dev)); return strlen(buf); } static DEVICE_ATTR_RO(name); #if 0 /* hangs */ static ssize_t name_set(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int err = 0; char *out = kmalloc(count + 1, GFP_KERNEL); if (!out) return -ENOMEM; memcpy(out, buf, count); if (count && out[count - 1] == '\n') out[--count] = 0; if (count) err = device_rename(dev, out); kfree(out); return (err < 0) ? err : count; } static DEVICE_ATTR_RW(name); #endif static ssize_t channelmap_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mISDNdevice *mdev = dev_to_mISDN(dev); char *bp = buf; int i; for (i = 0; i <= mdev->nrbchan; i++) *bp++ = test_channelmap(i, mdev->channelmap) ? '1' : '0'; return bp - buf; } static DEVICE_ATTR_RO(channelmap); static struct attribute *mISDN_attrs[] = { &dev_attr_id.attr, &dev_attr_d_protocols.attr, &dev_attr_b_protocols.attr, &dev_attr_protocol.attr, &dev_attr_channelmap.attr, &dev_attr_nrbchan.attr, &dev_attr_name.attr, NULL, }; ATTRIBUTE_GROUPS(mISDN); static int mISDN_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct mISDNdevice *mdev = dev_to_mISDN(dev); if (!mdev) return 0; if (add_uevent_var(env, "nchans=%d", mdev->nrbchan)) return -ENOMEM; return 0; } static struct class mISDN_class = { .name = "mISDN", .dev_uevent = mISDN_uevent, .dev_groups = mISDN_groups, .dev_release = mISDN_dev_release, }; static int _get_mdevice(struct device *dev, const void *id) { struct mISDNdevice *mdev = dev_to_mISDN(dev); if (!mdev) return 0; if (mdev->id != *(const u_int *)id) return 0; return 1; } struct mISDNdevice *get_mdevice(u_int id) { return dev_to_mISDN(class_find_device(&mISDN_class, NULL, &id, _get_mdevice)); } static int _get_mdevice_count(struct device *dev, void *cnt) { *(int *)cnt += 1; return 0; } int get_mdevice_count(void) { int cnt = 0; class_for_each_device(&mISDN_class, NULL, &cnt, _get_mdevice_count); return cnt; } static int get_free_devid(void) { u_int i; for (i = 0; i <= MAX_DEVICE_ID; i++) if (!test_and_set_bit(i, (u_long *)&device_ids)) break; if (i > MAX_DEVICE_ID) return -EBUSY; return i; } int mISDN_register_device(struct mISDNdevice *dev, struct device *parent, char *name) { int err; err = get_free_devid(); if (err < 0) return err; dev->id = err; device_initialize(&dev->dev); if (name && name[0]) dev_set_name(&dev->dev, "%s", name); else dev_set_name(&dev->dev, "mISDN%d", dev->id); if (debug & DEBUG_CORE) printk(KERN_DEBUG "mISDN_register %s %d\n", dev_name(&dev->dev), dev->id); dev->dev.class = &mISDN_class; err = create_stack(dev); if (err) goto error1; dev->dev.platform_data = dev; dev->dev.parent = parent; dev_set_drvdata(&dev->dev, dev); err = device_add(&dev->dev); if (err) goto error3; return 0; error3: delete_stack(dev); error1: put_device(&dev->dev); return err; } EXPORT_SYMBOL(mISDN_register_device); void mISDN_unregister_device(struct mISDNdevice *dev) { if (debug & DEBUG_CORE) printk(KERN_DEBUG "mISDN_unregister %s %d\n", dev_name(&dev->dev), dev->id); /* sysfs_remove_link(&dev->dev.kobj, "device"); */ device_del(&dev->dev); dev_set_drvdata(&dev->dev, NULL); test_and_clear_bit(dev->id, (u_long *)&device_ids); delete_stack(dev); put_device(&dev->dev); } EXPORT_SYMBOL(mISDN_unregister_device); u_int get_all_Bprotocols(void) { struct Bprotocol *bp; u_int m = 0; read_lock(&bp_lock); list_for_each_entry(bp, &Bprotocols, list) m |= bp->Bprotocols; read_unlock(&bp_lock); return m; } struct Bprotocol * get_Bprotocol4mask(u_int m) { struct Bprotocol *bp; read_lock(&bp_lock); list_for_each_entry(bp, &Bprotocols, list) if (bp->Bprotocols & m) { read_unlock(&bp_lock); return bp; } read_unlock(&bp_lock); return NULL; } struct Bprotocol * get_Bprotocol4id(u_int id) { u_int m; if (id < ISDN_P_B_START || id > 63) { printk(KERN_WARNING "%s id not in range %d\n", __func__, id); return NULL; } m = 1 << (id & ISDN_P_B_MASK); return get_Bprotocol4mask(m); } int mISDN_register_Bprotocol(struct Bprotocol *bp) { u_long flags; struct Bprotocol *old; if (debug & DEBUG_CORE) printk(KERN_DEBUG "%s: %s/%x\n", __func__, bp->name, bp->Bprotocols); old = get_Bprotocol4mask(bp->Bprotocols); if (old) { printk(KERN_WARNING "register duplicate protocol old %s/%x new %s/%x\n", old->name, old->Bprotocols, bp->name, bp->Bprotocols); return -EBUSY; } write_lock_irqsave(&bp_lock, flags); list_add_tail(&bp->list, &Bprotocols); write_unlock_irqrestore(&bp_lock, flags); return 0; } EXPORT_SYMBOL(mISDN_register_Bprotocol); void mISDN_unregister_Bprotocol(struct Bprotocol *bp) { u_long flags; if (debug & DEBUG_CORE) printk(KERN_DEBUG "%s: %s/%x\n", __func__, bp->name, bp->Bprotocols); write_lock_irqsave(&bp_lock, flags); list_del(&bp->list); write_unlock_irqrestore(&bp_lock, flags); } EXPORT_SYMBOL(mISDN_unregister_Bprotocol); static const char *msg_no_channel = "<no channel>"; static const char *msg_no_stack = "<no stack>"; static const char *msg_no_stackdev = "<no stack device>"; const char *mISDNDevName4ch(struct mISDNchannel *ch) { if (!ch) return msg_no_channel; if (!ch->st) return msg_no_stack; if (!ch->st->dev) return msg_no_stackdev; return dev_name(&ch->st->dev->dev); }; EXPORT_SYMBOL(mISDNDevName4ch); static int mISDNInit(void) { int err; printk(KERN_INFO "Modular ISDN core version %d.%d.%d\n", MISDN_MAJOR_VERSION, MISDN_MINOR_VERSION, MISDN_RELEASE); mISDN_init_clock(&debug); mISDN_initstack(&debug); err = class_register(&mISDN_class); if (err) goto error1; err = mISDN_inittimer(&debug); if (err) goto error2; err = Isdnl1_Init(&debug); if (err) goto error3; err = Isdnl2_Init(&debug); if (err) goto error4; err = misdn_sock_init(&debug); if (err) goto error5; return 0; error5: Isdnl2_cleanup(); error4: Isdnl1_cleanup(); error3: mISDN_timer_cleanup(); error2: class_unregister(&mISDN_class); error1: return err; } static void mISDN_cleanup(void) { misdn_sock_cleanup(); Isdnl2_cleanup(); Isdnl1_cleanup(); mISDN_timer_cleanup(); class_unregister(&mISDN_class); printk(KERN_DEBUG "mISDNcore unloaded\n"); } module_init(mISDNInit); module_exit(mISDN_cleanup); |
| 7 7 4 3 19 17 7 4 9 2 19 2 1 1 1 1 1 4 4 3 2 2 3 2 2 5 2 2 14 14 14 12 11 11 11 10 9 7 7 3 121 121 121 121 12660 12919 12516 12585 457 74 2870 5836 5872 591 589 614 617 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/capability.c * * Copyright (C) 1997 Andrew Main <zefram@fysh.org> * * Integrated into 2.1.97+, Andrew G. Morgan <morgan@kernel.org> * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/audit.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/uaccess.h> int file_caps_enabled = 1; static int __init file_caps_disable(char *str) { file_caps_enabled = 0; return 1; } __setup("no_file_caps", file_caps_disable); #ifdef CONFIG_MULTIUSER /* * More recent versions of libcap are available from: * * http://www.kernel.org/pub/linux/libs/security/linux-privs/ */ static void warn_legacy_capability_use(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n", get_task_comm(name, current)); } /* * Version 2 capabilities worked fine, but the linux/capability.h file * that accompanied their introduction encouraged their use without * the necessary user-space source code changes. As such, we have * created a version 3 with equivalent functionality to version 2, but * with a header change to protect legacy source code from using * version 2 when it wanted to use version 1. If your system has code * that trips the following warning, it is using version 2 specific * capabilities and may be doing so insecurely. * * The remedy is to either upgrade your version of libcap (to 2.10+, * if the application is linked against it), or recompile your * application with modern kernel headers and this warning will go * away. */ static void warn_deprecated_v2(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n", get_task_comm(name, current)); } /* * Version check. Return the number of u32s in each capability flag * array, or a negative value on error. */ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) { __u32 version; if (get_user(version, &header->version)) return -EFAULT; switch (version) { case _LINUX_CAPABILITY_VERSION_1: warn_legacy_capability_use(); *tocopy = _LINUX_CAPABILITY_U32S_1; break; case _LINUX_CAPABILITY_VERSION_2: warn_deprecated_v2(); fallthrough; /* v3 is otherwise equivalent to v2 */ case _LINUX_CAPABILITY_VERSION_3: *tocopy = _LINUX_CAPABILITY_U32S_3; break; default: if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version)) return -EFAULT; return -EINVAL; } return 0; } /* * The only thing that can change the capabilities of the current * process is the current process. As such, we can't be in this code * at the same time as we are in the process of setting capabilities * in this process. The net result is that we can limit our use of * locks to when we are reading the caps of another process. */ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, kernel_cap_t *pIp, kernel_cap_t *pPp) { int ret; if (pid && (pid != task_pid_vnr(current))) { const struct task_struct *target; rcu_read_lock(); target = find_task_by_vpid(pid); if (!target) ret = -ESRCH; else ret = security_capget(target, pEp, pIp, pPp); rcu_read_unlock(); } else ret = security_capget(current, pEp, pIp, pPp); return ret; } /** * sys_capget - get the capabilities of a given process. * @header: pointer to struct that contains capability version and * target pid data * @dataptr: pointer to struct that contains the effective, permitted, * and inheritable capabilities that are returned * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) { int ret = 0; pid_t pid; unsigned tocopy; kernel_cap_t pE, pI, pP; struct __user_cap_data_struct kdata[2]; ret = cap_validate_magic(header, &tocopy); if ((dataptr == NULL) || (ret != 0)) return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret; if (get_user(pid, &header->pid)) return -EFAULT; if (pid < 0) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); if (ret) return ret; /* * Annoying legacy format with 64-bit capabilities exposed * as two sets of 32-bit fields, so we need to split the * capability values up. */ kdata[0].effective = pE.val; kdata[1].effective = pE.val >> 32; kdata[0].permitted = pP.val; kdata[1].permitted = pP.val >> 32; kdata[0].inheritable = pI.val; kdata[1].inheritable = pI.val >> 32; /* * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, * we silently drop the upper capabilities here. This * has the effect of making older libcap * implementations implicitly drop upper capability * bits when they perform a: capget/modify/capset * sequence. * * This behavior is considered fail-safe * behavior. Upgrading the application to a newer * version of libcap will enable access to the newer * capabilities. * * An alternative would be to return an error here * (-ERANGE), but that causes legacy applications to * unexpectedly fail; the capget/modify/capset aborts * before modification is attempted and the application * fails. */ if (copy_to_user(dataptr, kdata, tocopy * sizeof(kdata[0]))) return -EFAULT; return 0; } static kernel_cap_t mk_kernel_cap(u32 low, u32 high) { return (kernel_cap_t) { (low | ((u64)high << 32)) & CAP_VALID_MASK }; } /** * sys_capset - set capabilities for a process or (*) a group of processes * @header: pointer to struct that contains capability version and * target pid data * @data: pointer to struct that contains the effective, permitted, * and inheritable capabilities * * Set capabilities for the current process only. The ability to any other * process(es) has been deprecated and removed. * * The restrictions on setting capabilities are specified as: * * I: any raised capabilities must be a subset of the old permitted * P: any raised capabilities must be a subset of the old permitted * E: must be set to a subset of new permitted * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { struct __user_cap_data_struct kdata[2] = { { 0, }, }; unsigned tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; pid_t pid; ret = cap_validate_magic(header, &tocopy); if (ret != 0) return ret; if (get_user(pid, &header->pid)) return -EFAULT; /* may only affect current now */ if (pid != 0 && pid != task_pid_vnr(current)) return -EPERM; copybytes = tocopy * sizeof(struct __user_cap_data_struct); if (copybytes > sizeof(kdata)) return -EFAULT; if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; effective = mk_kernel_cap(kdata[0].effective, kdata[1].effective); permitted = mk_kernel_cap(kdata[0].permitted, kdata[1].permitted); inheritable = mk_kernel_cap(kdata[0].inheritable, kdata[1].inheritable); new = prepare_creds(); if (!new) return -ENOMEM; ret = security_capset(new, current_cred(), &effective, &inheritable, &permitted); if (ret < 0) goto error; audit_log_capset(new, current_cred()); return commit_creds(new); error: abort_creds(new); return ret; } /** * has_ns_capability - Does a task have a capability in a specific user ns * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NONE); rcu_read_unlock(); return (ret == 0); } /** * has_capability - Does a task have a capability in init_user_ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the initial user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability(struct task_struct *t, int cap) { return has_ns_capability(t, &init_user_ns, cap); } EXPORT_SYMBOL(has_capability); /** * has_ns_capability_noaudit - Does a task have a capability (unaudited) * in a specific user ns. * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * Do not write an audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } /** * has_capability_noaudit - Does a task have a capability (unaudited) in the * initial user ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to init_user_ns, false if not. Don't write an * audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability_noaudit(struct task_struct *t, int cap) { return has_ns_capability_noaudit(t, &init_user_ns, cap); } EXPORT_SYMBOL(has_capability_noaudit); static bool ns_capable_common(struct user_namespace *ns, int cap, unsigned int opts) { int capable; if (unlikely(!cap_valid(cap))) { pr_crit("capable() called with invalid cap=%u\n", cap); BUG(); } capable = security_capable(current_cred(), ns, cap, opts); if (capable == 0) { current->flags |= PF_SUPERPRIV; return true; } return false; } /** * ns_capable - Determine if the current task has a superior capability in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NONE); } EXPORT_SYMBOL(ns_capable); /** * ns_capable_noaudit - Determine if the current task has a superior capability * (unaudited) in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_noaudit(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NOAUDIT); } EXPORT_SYMBOL(ns_capable_noaudit); /** * ns_capable_setid - Determine if the current task has a superior capability * in effect, while signalling that this check is being done from within a * setid or setgroups syscall. * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_setid(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_INSETID); } EXPORT_SYMBOL(ns_capable_setid); /** * capable - Determine if the current task has a superior capability in effect * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool capable(int cap) { return ns_capable(&init_user_ns, cap); } EXPORT_SYMBOL(capable); #endif /* CONFIG_MULTIUSER */ /** * file_ns_capable - Determine if the file's opener had a capability in effect * @file: The file we want to check * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if task that opened the file had a capability in effect * when the file was opened. * * This does not set PF_SUPERPRIV because the caller may not * actually be privileged. */ bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap) { if (WARN_ON_ONCE(!cap_valid(cap))) return false; if (security_capable(file->f_cred, ns, cap, CAP_OPT_NONE) == 0) return true; return false; } EXPORT_SYMBOL(file_ns_capable); /** * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode? * @ns: The user namespace in question * @idmap: idmap of the mount @inode was found from * @inode: The inode in question * * Return true if the inode uid and gid are within the namespace. */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, struct mnt_idmap *idmap, const struct inode *inode) { return vfsuid_has_mapping(ns, i_uid_into_vfsuid(idmap, inode)) && vfsgid_has_mapping(ns, i_gid_into_vfsgid(idmap, inode)); } /** * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped * @idmap: idmap of the mount @inode was found from * @inode: The inode in question * @cap: The capability in question * * Return true if the current task has the given capability targeted at * its own user namespace and that the given inode's uid and gid are * mapped into the current user namespace. */ bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap, const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, idmap, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); /** * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace * @tsk: The task that may be ptraced * @ns: The user namespace to search for CAP_SYS_PTRACE in * * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE * in the specified user namespace. */ bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns) { int ret = 0; /* An absent tracer adds no restrictions */ const struct cred *cred; rcu_read_lock(); cred = rcu_dereference(tsk->ptracer_cred); if (cred) ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } |
| 16 28 19 28 7 640 642 639 21 21 16 16 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 | // SPDX-License-Identifier: GPL-2.0-only /* * The "user cache". * * (C) Copyright 1991-2000 Linus Torvalds * * We have a per-user structure to keep track of how many * processes, files etc the user has claimed, in order to be * able to have per-user limits for system resources. */ #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/bitops.h> #include <linux/key.h> #include <linux/sched/user.h> #include <linux/interrupt.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/proc_ns.h> #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc init_binfmt_misc = { .entries = LIST_HEAD_INIT(init_binfmt_misc.entries), .enabled = true, .entries_lock = __RW_LOCK_UNLOCKED(init_binfmt_misc.entries_lock), }; EXPORT_SYMBOL_GPL(init_binfmt_misc); #endif /* * userns count is 1 for root user, 1 for init_uts_ns, * and 1 for... ? */ struct user_namespace init_user_ns = { .uid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .gid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .projid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .ns.count = REFCOUNT_INIT(3), .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .ns.inum = PROC_USER_INIT_INO, #ifdef CONFIG_USER_NS .ns.ops = &userns_operations, #endif .flags = USERNS_INIT_FLAGS, #ifdef CONFIG_KEYS .keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list), .keyring_sem = __RWSEM_INITIALIZER(init_user_ns.keyring_sem), #endif #if IS_ENABLED(CONFIG_BINFMT_MISC) .binfmt_misc = &init_binfmt_misc, #endif }; EXPORT_SYMBOL_GPL(init_user_ns); /* * UID task count cache, to get fast user lookup in "alloc_uid" * when changing user ID's (ie setuid() and friends). */ #define UIDHASH_BITS (IS_ENABLED(CONFIG_BASE_SMALL) ? 3 : 7) #define UIDHASH_SZ (1 << UIDHASH_BITS) #define UIDHASH_MASK (UIDHASH_SZ - 1) #define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK) #define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid)))) static struct kmem_cache *uid_cachep; static struct hlist_head uidhash_table[UIDHASH_SZ]; /* * The uidhash_lock is mostly taken from process context, but it is * occasionally also taken from softirq/tasklet context, when * task-structs get RCU-freed. Hence all locking must be softirq-safe. * But free_uid() is also called with local interrupts disabled, and running * local_bh_enable() with local interrupts disabled is an error - we'll run * softirq callbacks, and they can unconditionally enable interrupts, and * the caller of free_uid() didn't expect that.. */ static DEFINE_SPINLOCK(uidhash_lock); /* root_user.__count is 1, for init task cred */ struct user_struct root_user = { .__count = REFCOUNT_INIT(1), .uid = GLOBAL_ROOT_UID, .ratelimit = RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0), }; /* * These routines must be called with the uidhash spinlock held! */ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent) { hlist_add_head(&up->uidhash_node, hashent); } static void uid_hash_remove(struct user_struct *up) { hlist_del_init(&up->uidhash_node); } static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent) { struct user_struct *user; hlist_for_each_entry(user, hashent, uidhash_node) { if (uid_eq(user->uid, uid)) { refcount_inc(&user->__count); return user; } } return NULL; } static int user_epoll_alloc(struct user_struct *up) { #ifdef CONFIG_EPOLL return percpu_counter_init(&up->epoll_watches, 0, GFP_KERNEL); #else return 0; #endif } static void user_epoll_free(struct user_struct *up) { #ifdef CONFIG_EPOLL percpu_counter_destroy(&up->epoll_watches); #endif } /* IRQs are disabled and uidhash_lock is held upon function entry. * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. */ static void free_user(struct user_struct *up, unsigned long flags) __releases(&uidhash_lock) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); user_epoll_free(up); kmem_cache_free(uid_cachep, up); } /* * Locate the user_struct for the passed UID. If found, take a ref on it. The * caller must undo that ref with free_uid(). * * If the user_struct could not be found, return NULL. */ struct user_struct *find_user(kuid_t uid) { struct user_struct *ret; unsigned long flags; spin_lock_irqsave(&uidhash_lock, flags); ret = uid_hash_find(uid, uidhashentry(uid)); spin_unlock_irqrestore(&uidhash_lock, flags); return ret; } void free_uid(struct user_struct *up) { unsigned long flags; if (!up) return; if (refcount_dec_and_lock_irqsave(&up->__count, &uidhash_lock, &flags)) free_user(up, flags); } EXPORT_SYMBOL_GPL(free_uid); struct user_struct *alloc_uid(kuid_t uid) { struct hlist_head *hashent = uidhashentry(uid); struct user_struct *up, *new; spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); spin_unlock_irq(&uidhash_lock); if (!up) { new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL); if (!new) return NULL; new->uid = uid; refcount_set(&new->__count, 1); if (user_epoll_alloc(new)) { kmem_cache_free(uid_cachep, new); return NULL; } ratelimit_state_init(&new->ratelimit, HZ, 100); ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE); /* * Before adding this, check whether we raced * on adding the same user already.. */ spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { user_epoll_free(new); kmem_cache_free(uid_cachep, new); } else { uid_hash_insert(new, hashent); up = new; } spin_unlock_irq(&uidhash_lock); } return up; } static int __init uid_cache_init(void) { int n; uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); for(n = 0; n < UIDHASH_SZ; ++n) INIT_HLIST_HEAD(uidhash_table + n); if (user_epoll_alloc(&root_user)) panic("root_user epoll percpu counter alloc failed"); /* Insert the root user immediately (init already runs as root) */ spin_lock_irq(&uidhash_lock); uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID)); spin_unlock_irq(&uidhash_lock); return 0; } subsys_initcall(uid_cache_init); |
| 1 4 3 4 14 12 2 14 66 36 36 809 808 30 30 30 29 30 30 30 20 809 827 808 809 20 2 2 2 2 2 16 16 16 47 47 31 47 47 16 16 16 16 11 11 15 15 16 16 16 15 1 16 1 1 14 16 16 16 16 16 16 1 16 16 16 16 16 16 16 16 11 11 1 1 1 16 16 15 16 16 16 11 1 1 16 16 16 11 16 16 16 47 47 47 46 47 47 47 46 36 36 35 35 36 36 36 37 37 33 34 33 34 37 1 16 16 3 3 3 3 3 3 3 3 1 1 1 1 1 47 47 47 3 47 45 47 47 47 18 18 18 18 18 18 3 16 16 15 16 16 16 16 16 16 16 16 11 11 11 11 11 11 11 11 11 11 18 17 18 18 18 17 18 3 18 13 13 17 18 18 18 18 17 18 1 18 18 18 18 18 18 18 18 18 12 18 18 18 18 18 18 19 19 19 19 19 19 19 19 19 19 19 3 2 3 3 3 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 18 18 1 1 1 19 19 17 17 17 16 16 16 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 17 29 29 29 29 29 29 29 29 29 29 29 29 19 16 19 29 29 29 29 29 29 29 29 29 29 29 25 29 29 29 29 1 1 18 18 1 18 18 17 17 17 17 6 6 17 17 17 16 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 15 2 2 15 15 15 18 18 18 29 29 29 29 29 29 2 29 29 29 29 2 2 29 29 29 20 20 22 26 51 51 51 35 49 48 30 47 29 29 29 29 47 47 29 29 29 18 32 31 32 29 19 19 19 19 19 49 22 33 33 33 30 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 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 | // 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/page_table_check.h> #include <linux/rcupdate_wait.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/ksm.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" #include "mm_slot.h" enum scan_result { SCAN_FAIL, SCAN_SUCCEED, SCAN_PMD_NULL, SCAN_PMD_NONE, SCAN_PMD_MAPPED, SCAN_EXCEED_NONE_PTE, SCAN_EXCEED_SWAP_PTE, SCAN_EXCEED_SHARED_PTE, SCAN_PTE_NON_PRESENT, SCAN_PTE_UFFD_WP, SCAN_PTE_MAPPED_HUGEPAGE, 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_DEL_PAGE_LRU, SCAN_ALLOC_HUGE_PAGE_FAIL, SCAN_CGROUP_CHARGE_FAIL, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, SCAN_STORE_FAILED, SCAN_COPY_MC, SCAN_PAGE_FILLED, }; #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. * * Note that these are only respected if collapse was initiated by khugepaged. */ 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 DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct kmem_cache *mm_slot_cache __ro_after_init; struct collapse_control { bool is_khugepaged; /* Num pages scanned per node */ u32 node_load[MAX_NUMNODES]; /* nodemask for allocation fallback */ nodemask_t alloc_nmask; }; /** * struct khugepaged_mm_slot - khugepaged information per mm that is being scanned * @slot: hash lookup from mm to mm_slot */ struct khugepaged_mm_slot { struct mm_slot slot; }; /** * 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 khugepaged_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_RW(scan_sleep_millisecs); 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_RW(alloc_sleep_millisecs); 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_RW(pages_to_scan); 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 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 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_RW(defrag); /* * 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 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 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_RW(max_ptes_none); static ssize_t 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 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_RW(max_ptes_swap); static ssize_t 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 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_RW(max_ptes_shared); 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. */ khugepaged_enter_vma(vma, *vm_flags); 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(khugepaged_mm_slot, 0); 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 int hpage_collapse_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm) { return hpage_collapse_test_exit(mm) || test_bit(MMF_DISABLE_THP, &mm->flags); } static bool hugepage_pmd_enabled(void) { /* * We cover both the anon and the file-backed case here; file-backed * hugepages, when configured in, are determined by the global control. * Anon pmd-sized hugepages are determined by the pmd-size control. */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && hugepage_global_enabled()) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_always)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_madvise)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) && hugepage_global_enabled()) return true; return false; } void __khugepaged_enter(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int wakeup; /* __khugepaged_exit() must not run from under us */ VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) return; mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return; slot = &mm_slot->slot; spin_lock(&khugepaged_mm_lock); mm_slot_insert(mm_slots_hash, 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(&slot->mm_node, &khugepaged_scan.mm_head); spin_unlock(&khugepaged_mm_lock); mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); } void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_pmd_enabled()) { if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) __khugepaged_enter(vma->vm_mm); } } void __khugepaged_exit(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int free = 0; spin_lock(&khugepaged_mm_lock); slot = mm_slot_lookup(mm_slots_hash, mm); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { hash_del(&slot->hash); list_del(&slot->mm_node); free = 1; } spin_unlock(&khugepaged_mm_lock); if (free) { clear_bit(MMF_VM_HUGEPAGE, &mm->flags); mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } else if (mm_slot) { /* * This is required to serialize against * hpage_collapse_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_folio(struct folio *folio) { node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), -folio_nr_pages(folio)); folio_unlock(folio); folio_putback_lru(folio); } static void release_pte_pages(pte_t *pte, pte_t *_pte, struct list_head *compound_pagelist) { struct folio *folio, *tmp; while (--_pte >= pte) { pte_t pteval = ptep_get(_pte); unsigned long pfn; if (pte_none(pteval)) continue; pfn = pte_pfn(pteval); if (is_zero_pfn(pfn)) continue; folio = pfn_folio(pfn); if (folio_test_large(folio)) continue; release_pte_folio(folio); } list_for_each_entry_safe(folio, tmp, compound_pagelist, lru) { list_del(&folio->lru); release_pte_folio(folio); } } static bool is_refcount_suitable(struct folio *folio) { int expected_refcount = folio_mapcount(folio); if (!folio_test_anon(folio) || folio_test_swapcache(folio)) expected_refcount += folio_nr_pages(folio); if (folio_test_private(folio)) expected_refcount++; return folio_ref_count(folio) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte, struct collapse_control *cc, struct list_head *compound_pagelist) { struct page *page = NULL; struct folio *folio = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0; bool writable = false; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_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) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out; } folio = page_folio(page); VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio); /* See hpage_collapse_scan_pmd(). */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out; } } if (folio_test_large(folio)) { struct folio *f; /* * Check if we have dealt with the compound page * already */ list_for_each_entry(f, compound_pagelist, lru) { if (folio == f) goto next; } } /* * We can do it before folio_isolate_lru because the * folio can't be freed from under us. NOTE: PG_lock * is needed to serialize against split_huge_page * when invoked from the VM. */ if (!folio_trylock(folio)) { 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(folio)) { folio_unlock(folio); result = SCAN_PAGE_COUNT; goto out; } /* * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ if (!folio_isolate_lru(folio)) { folio_unlock(folio); result = SCAN_DEL_PAGE_LRU; goto out; } node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (folio_test_large(folio)) list_add_tail(&folio->lru, compound_pagelist); next: /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || 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(cc->is_khugepaged && !referenced)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } static void __collapse_huge_page_copy_succeeded(pte_t *pte, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { struct folio *src, *tmp; pte_t *_pte; pte_t pteval; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pteval = ptep_get(_pte); if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { /* * ptl mostly unnecessary. */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); ksm_might_unmap_zero_page(vma->vm_mm, pteval); } } else { struct page *src_page = pte_page(pteval); src = page_folio(src_page); if (!folio_test_large(src)) release_pte_folio(src); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats * inside folio_remove_rmap_pte(). */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); folio_remove_rmap_pte(src, src_page, vma); spin_unlock(ptl); free_page_and_swap_cache(src_page); } } list_for_each_entry_safe(src, tmp, compound_pagelist, lru) { list_del(&src->lru); node_stat_sub_folio(src, NR_ISOLATED_ANON + folio_is_file_lru(src)); folio_unlock(src); free_swap_cache(src); folio_putback_lru(src); } } static void __collapse_huge_page_copy_failed(pte_t *pte, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, struct list_head *compound_pagelist) { spinlock_t *pmd_ptl; /* * Re-establish the PMD to point to the original page table * entry. Restoring PMD needs to be done prior to releasing * pages. Since pages are still isolated and locked here, * acquiring anon_vma_lock_write is unnecessary. */ pmd_ptl = pmd_lock(vma->vm_mm, pmd); pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd)); spin_unlock(pmd_ptl); /* * Release both raw and compound pages isolated * in __collapse_huge_page_isolate. */ release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist); } /* * __collapse_huge_page_copy - attempts to copy memory contents from raw * pages to a hugepage. Cleans up the raw pages if copying succeeds; * otherwise restores the original page table and releases isolated raw pages. * Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC. * * @pte: starting of the PTEs to copy from * @folio: the new hugepage to copy contents to * @pmd: pointer to the new hugepage's PMD * @orig_pmd: the original raw pages' PMD * @vma: the original raw pages' virtual memory area * @address: starting address to copy * @ptl: lock on raw pages' PTEs * @compound_pagelist: list that stores compound pages */ static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { unsigned int i; int result = SCAN_SUCCEED; /* * Copying pages' contents is subject to memory poison at any iteration. */ for (i = 0; i < HPAGE_PMD_NR; i++) { pte_t pteval = ptep_get(pte + i); struct page *page = folio_page(folio, i); unsigned long src_addr = address + i * PAGE_SIZE; struct page *src_page; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, src_addr); continue; } src_page = pte_page(pteval); if (copy_mc_user_highpage(page, src_page, src_addr, vma) > 0) { result = SCAN_COPY_MC; break; } } if (likely(result == SCAN_SUCCEED)) __collapse_huge_page_copy_succeeded(pte, vma, address, ptl, compound_pagelist); else __collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma, compound_pagelist); return result; } static void khugepaged_alloc_sleep(void) { DEFINE_WAIT(wait); add_wait_queue(&khugepaged_wait, &wait); __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); schedule_timeout(msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); remove_wait_queue(&khugepaged_wait, &wait); } struct collapse_control khugepaged_collapse_control = { .is_khugepaged = true, }; static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc) { 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 (cc->node_load[nid]) return false; for (i = 0; i < MAX_NUMNODES; i++) { if (!cc->node_load[i]) continue; if (node_distance(nid, i) > node_reclaim_distance) return true; } return false; } #define khugepaged_defrag() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) /* 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 hpage_collapse_find_target_node(struct collapse_control *cc) { int nid, target_node = 0, max_value = 0; /* find first node with max normal pages hit */ for (nid = 0; nid < MAX_NUMNODES; nid++) if (cc->node_load[nid] > max_value) { max_value = cc->node_load[nid]; target_node = nid; } for_each_online_node(nid) { if (max_value == cc->node_load[nid]) node_set(nid, cc->alloc_nmask); } return target_node; } #else static int hpage_collapse_find_target_node(struct collapse_control *cc) { return 0; } #endif /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. * Returns enum scan_result value. */ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, bool expect_anon, struct vm_area_struct **vmap, struct collapse_control *cc) { struct vm_area_struct *vma; unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) return SCAN_ANY_PROCESS; *vmap = vma = find_vma(mm, address); if (!vma) return SCAN_VMA_NULL; if (!thp_vma_suitable_order(vma, address, PMD_ORDER)) return SCAN_ADDRESS_RANGE; if (!thp_vma_allowable_order(vma, vma->vm_flags, tva_flags, PMD_ORDER)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then * remapped to file after khugepaged reaquired the mmap_lock. * * thp_vma_allowable_order may return true for qualified file * vmas. */ if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap))) return SCAN_PAGE_ANON; return SCAN_SUCCEED; } static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) { pmd_t pmde; *pmd = mm_find_pmd(mm, address); if (!*pmd) return SCAN_PMD_NULL; pmde = pmdp_get_lockless(*pmd); if (pmd_none(pmde)) return SCAN_PMD_NONE; if (!pmd_present(pmde)) return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; if (pmd_devmap(pmde)) return SCAN_PMD_NULL; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; } static int check_pmd_still_valid(struct mm_struct *mm, unsigned long address, pmd_t *pmd) { pmd_t *new_pmd; int result = find_pmd_or_thp_or_none(mm, address, &new_pmd); if (result != SCAN_SUCCEED) return result; if (new_pmd != pmd) return SCAN_FAIL; return SCAN_SUCCEED; } /* * Bring missing pages in from swap, to complete THP collapse. * Only done if hpage_collapse_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held. * Returns result: if not SCAN_SUCCEED, mmap_lock has been released. */ static int __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); int result; pte_t *pte = NULL; spinlock_t *ptl; for (address = haddr; address < end; address += PAGE_SIZE) { struct vm_fault vmf = { .vma = vma, .address = address, .pgoff = linear_page_index(vma, address), .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, }; if (!pte++) { pte = pte_offset_map_nolock(mm, pmd, address, &ptl); if (!pte) { mmap_read_unlock(mm); result = SCAN_PMD_NULL; goto out; } } vmf.orig_pte = ptep_get_lockless(pte); if (!is_swap_pte(vmf.orig_pte)) continue; vmf.pte = pte; vmf.ptl = ptl; ret = do_swap_page(&vmf); /* Which unmaps pte (after perhaps re-checking the entry) */ pte = NULL; /* * do_swap_page returns VM_FAULT_RETRY with released mmap_lock. * Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because * we do not retry here and swap entry will remain in pagetable * resulting in later failure. */ if (ret & VM_FAULT_RETRY) { /* Likely, but not guaranteed, that page lock failed */ result = SCAN_PAGE_LOCK; goto out; } if (ret & VM_FAULT_ERROR) { mmap_read_unlock(mm); result = SCAN_FAIL; goto out; } swapped_in++; } if (pte) pte_unmap(pte); /* Drain LRU cache to remove extra pin on the swapped in pages */ if (swapped_in) lru_add_drain(); result = SCAN_SUCCEED; out: trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result); return result; } static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm, struct collapse_control *cc) { gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : GFP_TRANSHUGE); int node = hpage_collapse_find_target_node(cc); struct folio *folio; folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask); if (!folio) { *foliop = NULL; count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return SCAN_ALLOC_HUGE_PAGE_FAIL; } count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); *foliop = NULL; return SCAN_CGROUP_CHARGE_FAIL; } count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); *foliop = folio; return SCAN_SUCCEED; } static int collapse_huge_page(struct mm_struct *mm, unsigned long address, int referenced, int unmapped, struct collapse_control *cc) { LIST_HEAD(compound_pagelist); pmd_t *pmd, _pmd; pte_t *pte; pgtable_t pgtable; struct folio *folio; spinlock_t *pmd_ptl, *pte_ptl; int result = SCAN_FAIL; struct vm_area_struct *vma; struct mmu_notifier_range range; VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* * 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); result = alloc_charge_folio(&folio, mm, cc); if (result != SCAN_SUCCEED) goto out_nolock; mmap_read_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } if (unmapped) { /* * __collapse_huge_page_swapin will return with mmap_lock * released when it fails. So we jump out_nolock directly in * that case. Continuing to collapse causes inconsistency. */ result = __collapse_huge_page_swapin(mm, vma, address, pmd, referenced); if (result != SCAN_SUCCEED) 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. * * UFFDIO_MOVE is prevented to race as well thanks to the * mmap_lock. */ mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); 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 GUP-fast is fine since GUP-fast 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(); pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl); if (pte) { result = __collapse_huge_page_isolate(vma, address, pte, cc, &compound_pagelist); spin_unlock(pte_ptl); } else { result = SCAN_PMD_NULL; } if (unlikely(result != SCAN_SUCCEED)) { if (pte) 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); 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); result = __collapse_huge_page_copy(pte, folio, pmd, _pmd, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); if (unlikely(result != SCAN_SUCCEED)) goto out_up_write; /* * The smp_wmb() inside __folio_mark_uptodate() ensures the * copy_huge_page writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); deferred_split_folio(folio, false); spin_unlock(pmd_ptl); folio = NULL; result = SCAN_SUCCEED; out_up_write: mmap_write_unlock(mm); out_nolock: if (folio) folio_put(folio); trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result); return result; } static int hpage_collapse_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, bool *mmap_locked, struct collapse_control *cc) { pmd_t *pmd; pte_t *pte, *_pte; int result = SCAN_FAIL, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; struct folio *folio = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; bool writable = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) goto out; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); pte = pte_offset_map_lock(mm, pmd, address, &ptl); if (!pte) { result = SCAN_PMD_NULL; goto out; } for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (is_swap_pte(pteval)) { ++unmapped; if (!cc->is_khugepaged || 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_any(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } continue; } else { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); goto out_unmap; } } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_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) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out_unmap; } folio = page_folio(page); if (!folio_test_anon(folio)) { result = SCAN_PAGE_ANON; goto out_unmap; } /* * We treat a single page as shared if any part of the THP * is shared. "False negatives" from * folio_likely_mapped_shared() are not expected to matter * much in practice. */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out_unmap; } } /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; goto out_unmap; } if (folio_test_locked(folio)) { result = SCAN_PAGE_LOCK; goto out_unmap; } /* * Check if the page has any GUP (or other external) pins. * * Here the check may be racy: * it may see folio_mapcount() > folio_ref_count(). * 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(folio)) { result = SCAN_PAGE_COUNT; goto out_unmap; } /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; } if (!writable) { result = SCAN_PAGE_RO; } else if (cc->is_khugepaged && (!referenced || (unmapped && referenced < HPAGE_PMD_NR / 2))) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; } out_unmap: pte_unmap_unlock(pte, ptl); if (result == SCAN_SUCCEED) { result = collapse_huge_page(mm, address, referenced, unmapped, cc); /* collapse_huge_page will return with the mmap_lock released */ *mmap_locked = false; } out: trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced, none_or_zero, result, unmapped); return result; } static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot) { struct mm_slot *slot = &mm_slot->slot; struct mm_struct *mm = slot->mm; lockdep_assert_held(&khugepaged_mm_lock); if (hpage_collapse_test_exit(mm)) { /* free mm_slot */ hash_del(&slot->hash); list_del(&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 */ mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } } #ifdef CONFIG_SHMEM /* hpage must be locked, and mmap_lock must be held */ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct page *hpage) { struct vm_fault vmf = { .vma = vma, .address = addr, .flags = 0, .pmd = pmdp, }; VM_BUG_ON(!PageTransHuge(hpage)); mmap_assert_locked(vma->vm_mm); if (do_set_pmd(&vmf, hpage)) return SCAN_FAIL; get_page(hpage); return SCAN_SUCCEED; } /** * 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 * @install_pmd: If a huge PMD should be installed * * 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. Possibly install a huge PMD mapping the THP. */ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd) { struct mmu_notifier_range range; bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = vma_lookup(mm, haddr); struct folio *folio; pte_t *start_pte, *pte; pmd_t *pmd, pgt_pmd; spinlock_t *pml = NULL, *ptl; int nr_ptes = 0, result = SCAN_FAIL; int i; mmap_assert_locked(mm); /* First check VMA found, in case page tables are being torn down */ if (!vma || !vma->vm_file || !range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE)) return SCAN_VMA_CHECK; /* Fast check before locking page if already PMD-mapped */ result = find_pmd_or_thp_or_none(mm, haddr, &pmd); if (result == SCAN_PMD_MAPPED) return result; /* * If we are here, we've succeeded in replacing all the native pages * in the page cache with a single hugepage. If a mm were to fault-in * this memory (mapped by a suitably aligned VMA), we'd get the hugepage * and map it by a PMD, regardless of sysfs THP settings. As such, let's * analogously elide sysfs THP settings here. */ if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return SCAN_VMA_CHECK; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; folio = filemap_lock_folio(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (IS_ERR(folio)) return SCAN_PAGE_NULL; if (folio_order(folio) != HPAGE_PMD_ORDER) { result = SCAN_PAGE_COMPOUND; goto drop_folio; } result = find_pmd_or_thp_or_none(mm, haddr, &pmd); switch (result) { case SCAN_SUCCEED: break; case SCAN_PMD_NONE: /* * All pte entries have been removed and pmd cleared. * Skip all the pte checks and just update the pmd mapping. */ goto maybe_install_pmd; default: goto drop_folio; } result = SCAN_FAIL; start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto drop_folio; /* 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; pte_t ptent = ptep_get(pte); /* empty pte, skip */ if (pte_none(ptent)) continue; /* page swapped out, abort */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (WARN_ON_ONCE(page && is_zone_device_page(page))) page = NULL; /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ if (folio_page(folio, i) != page) goto abort; } pte_unmap_unlock(start_pte, ptl); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); notified = true; /* * pmd_lock covers a wider range than ptl, and (if split from mm's * page_table_lock) ptl nests inside pml. The less time we hold pml, * the better; but userfaultfd's mfill_atomic_pte() on a private VMA * inserts a valid as-if-COWed PTE without even looking up page cache. * So page lock of folio does not protect from it, so we must not drop * ptl before pgt_pmd is removed, so uffd private needs pml taken now. */ if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) pml = pmd_lock(mm, pmd); start_pte = pte_offset_map_nolock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto abort; if (!pml) spin_lock(ptl); else if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); /* step 2: clear page table and adjust rmap */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * We dropped ptl after the first scan, to do the mmu_notifier: * page lock stops more PTEs of the folio being faulted in, but * does not stop write faults COWing anon copies from existing * PTEs; and does not stop those being swapped out or migrated. */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (folio_page(folio, i) != page) goto abort; /* * Must clear entry, or a racing truncate may re-remove it. * TLB flush can be left until pmdp_collapse_flush() does it. * PTE dirty? Shmem page is already dirty; file is read-only. */ ptep_clear(mm, addr, pte); folio_remove_rmap_pte(folio, page, vma); nr_ptes++; } pte_unmap(start_pte); if (!pml) spin_unlock(ptl); /* step 3: set proper refcount and mm_counters. */ if (nr_ptes) { folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } /* step 4: remove empty page table */ if (!pml) { pml = pmd_lock(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); } pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd); pmdp_get_lockless_sync(); if (ptl != pml) spin_unlock(ptl); spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, haddr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd ? set_huge_pmd(vma, haddr, pmd, &folio->page) : SCAN_SUCCEED; goto drop_folio; abort: if (nr_ptes) { flush_tlb_mm(mm); folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } if (start_pte) pte_unmap_unlock(start_pte, ptl); if (pml && pml != ptl) spin_unlock(pml); if (notified) mmu_notifier_invalidate_range_end(&range); drop_folio: folio_unlock(folio); folio_put(folio); return result; } static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) { struct vm_area_struct *vma; i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { struct mmu_notifier_range range; struct mm_struct *mm; unsigned long addr; pmd_t *pmd, pgt_pmd; spinlock_t *pml; spinlock_t *ptl; bool skipped_uffd = false; /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that * got written to. These VMAs are likely not worth removing * page tables from, as PMD-mapping is likely to be split later. */ if (READ_ONCE(vma->anon_vma)) continue; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (addr & ~HPAGE_PMD_MASK || vma->vm_end < addr + HPAGE_PMD_SIZE) continue; mm = vma->vm_mm; if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED) continue; if (hpage_collapse_test_exit(mm)) continue; /* * When a vma is registered with uffd-wp, we cannot recycle * the page table because there may be pte markers installed. * Other vmas can still have the same file mapped hugely, but * skip this one: it will always be mapped in small page size * for uffd-wp registered ranges. */ if (userfaultfd_wp(vma)) continue; /* PTEs were notified when unmapped; but now for the PMD? */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pml = pmd_lock(mm, pmd); ptl = pte_lockptr(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); /* * Huge page lock is still held, so normally the page table * must remain empty; and we have already skipped anon_vma * and userfaultfd_wp() vmas. But since the mmap_lock is not * held, it is still possible for a racing userfaultfd_ioctl() * to have inserted ptes or markers. Now that we hold ptlock, * repeating the anon_vma check protects from one category, * and repeating the userfaultfd_wp() check from another. */ if (unlikely(vma->anon_vma || userfaultfd_wp(vma))) { skipped_uffd = true; } else { pgt_pmd = pmdp_collapse_flush(vma, addr, pmd); pmdp_get_lockless_sync(); } if (ptl != pml) spin_unlock(ptl); spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); if (!skipped_uffd) { mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, addr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); } } i_mmap_unlock_read(mapping); } /** * collapse_file - collapse filemap/tmpfs/shmem pages into huge one. * * @mm: process address space where collapse happens * @addr: virtual collapse start address * @file: file that collapse on * @start: collapse start address * @cc: collapse context and scratchpad * * Basic scheme is simple, details are more complex: * - allocate and lock a new huge page; * - scan page cache, locking old pages * + swap/gup in pages if necessary; * - copy data to new page * - handle shmem holes * + re-validate that holes weren't filled by someone else * + check for userfaultfd * - finalize updates to the page cache; * - if replacing succeeds: * + unlock huge page; * + free old pages; * - if replacing failed; * + unlock old pages * + unlock and free huge page; */ static int collapse_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct address_space *mapping = file->f_mapping; struct page *dst; struct folio *folio, *tmp, *new_folio; pgoff_t index = 0, 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); VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); result = alloc_charge_folio(&new_folio, mm, cc); if (result != SCAN_SUCCEED) goto out; __folio_set_locked(new_folio); if (is_shmem) __folio_set_swapbacked(new_folio); new_folio->index = start; new_folio->mapping = mapping; /* * Ensure we have slots for all the pages in the range. This is * almost certainly a no-op because most of the pages must be present */ 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 rollback; } } while (1); for (index = start; index < end;) { xas_set(&xas, index); folio = xas_load(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { if (!folio) { /* * 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; } } nr_none++; index++; continue; } if (xa_is_value(folio) || !folio_test_uptodate(folio)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_get_folio(mapping->host, index, 0, &folio, SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; } /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } else { /* !is_shmem */ if (!folio || xa_is_value(folio)) { xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (folio_test_dirty(folio)) { /* * 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 (folio_test_writeback(folio)) { xas_unlock_irq(&xas); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } /* * The folio must be locked, so we can drop the i_pages lock * without racing with truncate. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); /* make sure the folio is up to date */ if (unlikely(!folio_test_uptodate(folio))) { result = SCAN_FAIL; goto out_unlock; } /* * If file was truncated then extended, or hole-punched, before * we locked the first folio, then a THP might be there already. * This will be discovered on the first iteration. */ if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; goto out_unlock; } if (folio_mapping(folio) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } if (!is_shmem && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* * khugepaged only works on read-only fd, so this * folio is dirty because it hasn't been flushed * since first write. */ result = SCAN_FAIL; goto out_unlock; } if (!folio_isolate_lru(folio)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } if (!filemap_release_folio(folio, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; folio_putback_lru(folio); goto out_unlock; } if (folio_mapped(folio)) try_to_unmap(folio, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); VM_BUG_ON_FOLIO(folio != xa_load(xas.xa, index), folio); /* * We control 2 + nr_pages references to the folio: * - we hold a pin on it; * - nr_pages reference from page cache; * - one from lru_isolate_folio; * If those are the only references, then any new usage * of the folio will have to fetch it from the page * cache. That requires locking the folio to handle * truncate, so any new usage will be blocked until we * unlock folio after collapse/during rollback. */ if (folio_ref_count(folio) != 2 + folio_nr_pages(folio)) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); folio_putback_lru(folio); goto out_unlock; } /* * Accumulate the folios that are being collapsed. */ list_add_tail(&folio->lru, &pagelist); index += folio_nr_pages(folio); continue; out_unlock: folio_unlock(folio); folio_put(folio); goto xa_unlocked; } if (!is_shmem) { filemap_nr_thps_inc(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * 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; filemap_nr_thps_dec(mapping); } } xa_locked: xas_unlock_irq(&xas); xa_unlocked: /* * If collapse is successful, flush must be done now before copying. * If collapse is unsuccessful, does flush actually need to be done? * Do it anyway, to clear the state. */ try_to_unmap_flush(); if (result == SCAN_SUCCEED && nr_none && !shmem_charge(mapping->host, nr_none)) result = SCAN_FAIL; if (result != SCAN_SUCCEED) { nr_none = 0; goto rollback; } /* * The old folios are locked, so they won't change anymore. */ index = start; dst = folio_page(new_folio, 0); list_for_each_entry(folio, &pagelist, lru) { int i, nr_pages = folio_nr_pages(folio); while (index < folio->index) { clear_highpage(dst); index++; dst++; } for (i = 0; i < nr_pages; i++) { if (copy_mc_highpage(dst, folio_page(folio, i)) > 0) { result = SCAN_COPY_MC; goto rollback; } index++; dst++; } } while (index < end) { clear_highpage(dst); index++; dst++; } if (nr_none) { struct vm_area_struct *vma; int nr_none_check = 0; i_mmap_lock_read(mapping); xas_lock_irq(&xas); xas_set(&xas, start); for (index = start; index < end; index++) { if (!xas_next(&xas)) { xas_store(&xas, XA_RETRY_ENTRY); if (xas_error(&xas)) { result = SCAN_STORE_FAILED; goto immap_locked; } nr_none_check++; } } if (nr_none != nr_none_check) { result = SCAN_PAGE_FILLED; goto immap_locked; } /* * If userspace observed a missing page in a VMA with * a MODE_MISSING userfaultfd, then it might expect a * UFFD_EVENT_PAGEFAULT for that page. If so, we need to * roll back to avoid suppressing such an event. Since * wp/minor userfaultfds don't give userspace any * guarantees that the kernel doesn't fill a missing * page with a zero page, so they don't matter here. * * Any userfaultfds registered after this point will * not be able to observe any missing pages due to the * previously inserted retry entries. */ vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) { if (userfaultfd_missing(vma)) { result = SCAN_EXCEED_NONE_PTE; goto immap_locked; } } immap_locked: i_mmap_unlock_read(mapping); if (result != SCAN_SUCCEED) { xas_set(&xas, start); for (index = start; index < end; index++) { if (xas_next(&xas) == XA_RETRY_ENTRY) xas_store(&xas, NULL); } xas_unlock_irq(&xas); goto rollback; } } else { xas_lock_irq(&xas); } if (is_shmem) __lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR); else __lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR); if (nr_none) { __lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none); /* nr_none is always 0 for non-shmem. */ __lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none); } /* * Mark new_folio as uptodate before inserting it into the * page cache so that it isn't mistaken for an fallocated but * unwritten page. */ folio_mark_uptodate(new_folio); folio_ref_add(new_folio, HPAGE_PMD_NR - 1); if (is_shmem) folio_mark_dirty(new_folio); folio_add_lru(new_folio); /* Join all the small entries into a single multi-index entry. */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); xas_store(&xas, new_folio); WARN_ON_ONCE(xas_error(&xas)); xas_unlock_irq(&xas); /* * Remove pte page tables, so we can re-fault the page as huge. * If MADV_COLLAPSE, adjust result to call collapse_pte_mapped_thp(). */ retract_page_tables(mapping, start); if (cc && !cc->is_khugepaged) result = SCAN_PTE_MAPPED_HUGEPAGE; folio_unlock(new_folio); /* * The collapse has succeeded, so free the old folios. */ list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio->mapping = NULL; folio_clear_active(folio); folio_clear_unevictable(folio); folio_unlock(folio); folio_put_refs(folio, 2 + folio_nr_pages(folio)); } goto out; rollback: /* Something went wrong: roll back page cache changes */ if (nr_none) { xas_lock_irq(&xas); mapping->nrpages -= nr_none; xas_unlock_irq(&xas); shmem_uncharge(mapping->host, nr_none); } list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio_unlock(folio); folio_putback_lru(folio); folio_put(folio); } /* * Undo the updates of filemap_nr_thps_inc for non-SHMEM * file only. This undo is not needed unless failure is * due to SCAN_COPY_MC. */ if (!is_shmem && result == SCAN_COPY_MC) { filemap_nr_thps_dec(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure the update to nr_thps is visible. */ smp_mb(); } new_folio->mapping = NULL; folio_unlock(new_folio); folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result); return result; } static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct folio *folio = 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(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); rcu_read_lock(); xas_for_each(&xas, folio, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) { swap += 1 << xas_get_order(&xas); if (cc->is_khugepaged && swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); break; } continue; } if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; /* * For SCAN_PTE_MAPPED_HUGEPAGE, further processing * by the caller won't touch the page cache, and so * it's safe to skip LRU and refcount checks before * returning. */ break; } node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; break; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; break; } if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; break; } /* * We probably should check if the folio is referenced * here, but nobody would transfer pte_young() to * folio_test_referenced() for us. And rmap walk here * is just too costly... */ present += folio_nr_pages(folio); if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); if (result == SCAN_SUCCEED) { if (cc->is_khugepaged && present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); } else { result = collapse_file(mm, addr, file, start, cc); } } trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result); return result; } #else static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { BUILD_BUG(); } #endif static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, struct collapse_control *cc) __releases(&khugepaged_mm_lock) __acquires(&khugepaged_mm_lock) { struct vma_iterator vmi; struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int progress = 0; VM_BUG_ON(!pages); lockdep_assert_held(&khugepaged_mm_lock); *result = SCAN_FAIL; if (khugepaged_scan.mm_slot) { mm_slot = khugepaged_scan.mm_slot; slot = &mm_slot->slot; } else { slot = list_entry(khugepaged_scan.mm_head.next, struct mm_slot, mm_node); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; khugepaged_scan.mm_slot = mm_slot; } spin_unlock(&khugepaged_mm_lock); 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; progress++; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; vma_iter_init(&vmi, mm, khugepaged_scan.address); for_each_vma(vmi, vma) { unsigned long hstart, hend; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) { progress++; break; } if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) { skip: progress++; continue; } hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE); hend = round_down(vma->vm_end, HPAGE_PMD_SIZE); 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); while (khugepaged_scan.address < hend) { bool mmap_locked = true; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(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); mmap_locked = false; *result = hpage_collapse_scan_file(mm, khugepaged_scan.address, file, pgoff, cc); fput(file); if (*result == SCAN_PTE_MAPPED_HUGEPAGE) { mmap_read_lock(mm); if (hpage_collapse_test_exit_or_disable(mm)) goto breakouterloop; *result = collapse_pte_mapped_thp(mm, khugepaged_scan.address, false); if (*result == SCAN_PMD_MAPPED) *result = SCAN_SUCCEED; mmap_read_unlock(mm); } } else { *result = hpage_collapse_scan_pmd(mm, vma, khugepaged_scan.address, &mmap_locked, cc); } if (*result == SCAN_SUCCEED) ++khugepaged_pages_collapsed; /* move to next address */ khugepaged_scan.address += HPAGE_PMD_SIZE; progress += HPAGE_PMD_NR; if (!mmap_locked) /* * We released mmap_lock so break loop. Note * that we drop mmap_lock before all hugepage * allocations, so if allocation fails, we are * guaranteed to break here and report the * correct result back to caller. */ 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 (hpage_collapse_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 (slot->mm_node.next != &khugepaged_scan.mm_head) { slot = list_entry(slot->mm_node.next, struct mm_slot, mm_node); khugepaged_scan.mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); 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) && hugepage_pmd_enabled(); } static int khugepaged_wait_event(void) { return !list_empty(&khugepaged_scan.mm_head) || kthread_should_stop(); } static void khugepaged_do_scan(struct collapse_control *cc) { unsigned int progress = 0, pass_through_head = 0; unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); bool wait = true; int result = SCAN_SUCCEED; lru_add_drain_all(); while (true) { cond_resched(); if (unlikely(kthread_should_stop())) 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, &result, cc); else progress = pages; spin_unlock(&khugepaged_mm_lock); if (progress >= pages) break; if (result == SCAN_ALLOC_HUGE_PAGE_FAIL) { /* * If fail to allocate the first time, try to sleep for * a while. When hit again, cancel the scan. */ if (!wait) break; wait = false; khugepaged_alloc_sleep(); } } } 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 (hugepage_pmd_enabled()) wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); } static int khugepaged(void *none) { struct khugepaged_mm_slot *mm_slot; set_freezable(); set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(&khugepaged_collapse_control); 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; if (!hugepage_pmd_enabled()) { calculate_min_free_kbytes(); goto update_wmarks; } 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; } update_wmarks: setup_per_zone_wmarks(); } int start_stop_khugepaged(void) { int err = 0; mutex_lock(&khugepaged_mutex); if (hugepage_pmd_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); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } set_recommended_min_free_kbytes(); fail: mutex_unlock(&khugepaged_mutex); return err; } void khugepaged_min_free_kbytes_update(void) { mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled() && khugepaged_thread) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } bool current_is_khugepaged(void) { return kthread_func(current) == khugepaged; } static int madvise_collapse_errno(enum scan_result r) { /* * MADV_COLLAPSE breaks from existing madvise(2) conventions to provide * actionable feedback to caller, so they may take an appropriate * fallback measure depending on the nature of the failure. */ switch (r) { case SCAN_ALLOC_HUGE_PAGE_FAIL: return -ENOMEM; case SCAN_CGROUP_CHARGE_FAIL: case SCAN_EXCEED_NONE_PTE: return -EBUSY; /* Resource temporary unavailable - trying again might succeed */ case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: case SCAN_PAGE_FILLED: return -EAGAIN; /* * Other: Trying again likely not to succeed / error intrinsic to * specified memory range. khugepaged likely won't be able to collapse * either. */ default: return -EINVAL; } } int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct collapse_control *cc; struct mm_struct *mm = vma->vm_mm; unsigned long hstart, hend, addr; int thps = 0, last_fail = SCAN_FAIL; bool mmap_locked = true; BUG_ON(vma->vm_start > start); BUG_ON(vma->vm_end < end); *prev = vma; if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return -EINVAL; cc = kmalloc(sizeof(*cc), GFP_KERNEL); if (!cc) return -ENOMEM; cc->is_khugepaged = false; mmgrab(mm); lru_add_drain_all(); hstart = (start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = end & HPAGE_PMD_MASK; for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) { int result = SCAN_FAIL; if (!mmap_locked) { cond_resched(); mmap_read_lock(mm); mmap_locked = true; result = hugepage_vma_revalidate(mm, addr, false, &vma, cc); if (result != SCAN_SUCCEED) { last_fail = result; goto out_nolock; } hend = min(hend, vma->vm_end & HPAGE_PMD_MASK); } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); mmap_read_unlock(mm); mmap_locked = false; result = hpage_collapse_scan_file(mm, addr, file, pgoff, cc); fput(file); } else { result = hpage_collapse_scan_pmd(mm, vma, addr, &mmap_locked, cc); } if (!mmap_locked) *prev = NULL; /* Tell caller we dropped mmap_lock */ handle_result: switch (result) { case SCAN_SUCCEED: case SCAN_PMD_MAPPED: ++thps; break; case SCAN_PTE_MAPPED_HUGEPAGE: BUG_ON(mmap_locked); BUG_ON(*prev); mmap_read_lock(mm); result = collapse_pte_mapped_thp(mm, addr, true); mmap_read_unlock(mm); goto handle_result; /* Whitelisted set of results where continuing OK */ case SCAN_PMD_NULL: case SCAN_PTE_NON_PRESENT: case SCAN_PTE_UFFD_WP: case SCAN_PAGE_RO: case SCAN_LACK_REFERENCED_PAGE: case SCAN_PAGE_NULL: case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_COMPOUND: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: last_fail = result; break; default: last_fail = result; /* Other error, exit */ goto out_maybelock; } } out_maybelock: /* Caller expects us to hold mmap_lock on return */ if (!mmap_locked) mmap_read_lock(mm); out_nolock: mmap_assert_locked(mm); mmdrop(mm); kfree(cc); return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0 : madvise_collapse_errno(last_fail); } |
| 253 253 253 38 2 37 38 2 6 38 537 640 655 663 643 10 10 18 17 18 18 18 10 10 10 10 158 157 157 158 157 596 410 331 331 326 285 280 284 331 274 38 6 6 308 303 13 13 5 7 7 4 4 2 3 13 2 2 2 2 2 2 23 23 23 2 23 9 9 23 14 14 273 269 268 272 272 270 262 263 270 11 11 6 3 5 3 8 7 8 3 8 1 7 2 1 2 2 1 1 1 3 6 2 6 6 6 5 4 4 4 2 2 1 2 1 2 2 2 12 12 11 11 3 1 1 5 5 6 11 12 12 11 4 1 3 7 1 6 1 12 110 110 109 1 107 1 107 101 15 5 10 9 7 4 1 11 26 24 5 8 40 39 5 97 5 4 2 95 1 101 110 20 17 1 16 2 14 20 90 85 85 20 1 91 21 13 21 1 20 19 2 18 1 17 4 13 17 17 16 16 10 3 5 5 3 20 2 13 4 12 18 18 18 13 5 3 15 13 5 5 2 1 3 8 8 7 8 8 6 8 7 8 18 162 162 160 161 161 162 72 106 72 1 72 70 8 69 64 60 59 61 59 3 3 3 3 3 3 104 2 1 1 102 103 102 101 100 104 16 16 6 6 6 1 1 6 3 3 2 3 2 3 1 3 1 3 3 3 3 2 3 2 16 103 104 103 101 103 103 104 103 103 102 42 2 2 2 2 1 1 2 2 2 2 2 2 39 39 380 158 295 381 118 27 103 99 25 117 1063 230 1067 1037 218 47 218 230 258 253 10 259 70 1066 173 229 39 38 39 39 39 39 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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. * * IPv4 Forwarding Information Base: FIB frontend. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <trace/events/fib.h> #ifndef CONFIG_IP_MULTIPLE_TABLES static int __net_init fib4_rules_init(struct net *net) { struct fib_table *local_table, *main_table; main_table = fib_trie_table(RT_TABLE_MAIN, NULL); if (!main_table) return -ENOMEM; local_table = fib_trie_table(RT_TABLE_LOCAL, main_table); if (!local_table) goto fail; hlist_add_head_rcu(&local_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]); hlist_add_head_rcu(&main_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]); return 0; fail: fib_free_table(main_table); return -ENOMEM; } #else struct fib_table *fib_new_table(struct net *net, u32 id) { struct fib_table *tb, *alias = NULL; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; tb = fib_get_table(net, id); if (tb) return tb; if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules) alias = fib_new_table(net, RT_TABLE_MAIN); tb = fib_trie_table(id, alias); if (!tb) return NULL; switch (id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, tb); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, tb); break; default: break; } h = id & (FIB_TABLE_HASHSZ - 1); hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]); return tb; } EXPORT_SYMBOL_GPL(fib_new_table); /* caller must hold either rtnl or rcu read lock */ struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; h = id & (FIB_TABLE_HASHSZ - 1); head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) { if (tb->tb_id == id) return tb; } return NULL; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ static void fib_replace_table(struct net *net, struct fib_table *old, struct fib_table *new) { #ifdef CONFIG_IP_MULTIPLE_TABLES switch (new->tb_id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, new); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, new); break; default: break; } #endif /* replace the old table in the hlist */ hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist); } int fib_unmerge(struct net *net) { struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); if (!old) return 0; new = fib_trie_unmerge(old); if (!new) return -ENOMEM; /* table is already unmerged */ if (new == old) return 0; /* replace merged table with clean table */ fib_replace_table(net, old, new); fib_free_table(old); /* attempt to fetch main table if it has been allocated */ main_table = fib_get_table(net, RT_TABLE_MAIN); if (!main_table) return 0; /* flush local entries from main table */ fib_table_flush_external(main_table); return 0; } void fib_flush(struct net *net) { int flushed = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) flushed += fib_table_flush(net, tb, false); } if (flushed) rt_cache_flush(net); } /* * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. */ static inline unsigned int __inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr, u32 tb_id) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; unsigned int ret = RTN_BROADCAST; struct fib_table *table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; if (ipv4_is_multicast(addr)) return RTN_MULTICAST; rcu_read_lock(); table = fib_get_table(net, tb_id); if (table) { ret = RTN_UNICAST; if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { struct fib_nh_common *nhc = fib_info_nhc(res.fi, 0); if (!dev || dev == nhc->nhc_dev) ret = res.type; } } rcu_read_unlock(); return ret; } unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id) { return __inet_dev_addr_type(net, NULL, addr, tb_id); } EXPORT_SYMBOL(inet_addr_type_table); unsigned int inet_addr_type(struct net *net, __be32 addr) { return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL); } EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, dev, addr, rt_table); } EXPORT_SYMBOL(inet_dev_addr_type); /* inet_addr_type with dev == NULL but using the table from a dev * if one is associated */ unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, NULL, addr, rt_table); } EXPORT_SYMBOL(inet_addr_type_dev_table); __be32 fib_compute_spec_dst(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct rtable *rt; struct net *net; int scope; rt = skb_rtable(skb); if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) == RTCF_LOCAL) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK, .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return fib_result_prefsrc(net, &res); } else { scope = RT_SCOPE_LINK; } return inet_select_addr(dev, ip_hdr(skb)->saddr, scope); } bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) { bool dev_match = false; #ifdef CONFIG_IP_ROUTE_MULTIPATH if (unlikely(fi->nh)) { dev_match = nexthop_uses_dev(fi->nh, dev); } else { int ret; for (ret = 0; ret < fib_info_num_path(fi); ret++) { const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); if (nhc_l3mdev_matches_dev(nhc, dev)) { dev_match = true; break; } } } #else if (fib_info_nhc(fi, 0)->nhc_dev == dev) dev_match = true; #endif return dev_match; } EXPORT_SYMBOL_GPL(fib_info_nh_uses_dev); /* Given (packet source, input interface) and optional (dst, oif, tos): * - (main) check, that source is valid i.e. not broadcast or our local * address. * - figure out what "logical" interface this packet arrived * and calculate "specific destination" address. * - check, that packet arrived from expected physical interface. * called with rcu_read_lock() */ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, int rpf, struct in_device *idev, u32 *itag) { struct net *net = dev_net(dev); struct flow_keys flkeys; int ret, no_addr; struct fib_result res; struct flowi4 fl4; bool dev_match; fl4.flowi4_oif = 0; fl4.flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev); fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } else { swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; if (res.type != RTN_UNICAST && (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev))) goto e_inval; fib_combine_itag(itag, &res); dev_match = fib_info_nh_uses_dev(res.fi, dev); /* This is not common, loopback packets retain skb_dst so normally they * would not even hit this slow path. */ dev_match = dev_match || (res.type == RTN_LOCAL && dev == net->loopback_dev); if (dev_match) { ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) goto last_resort; if (rpf == 1) goto e_rpf; fl4.flowi4_oif = dev->ifindex; ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; last_resort: if (rpf) goto e_rpf; *itag = 0; return 0; e_inval: return -EINVAL; e_rpf: return -EXDEV; } /* Ignore rp_filter for packets protected by IPsec. */ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, struct in_device *idev, u32 *itag) { int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); struct net *net = dev_net(dev); if (!r && !fib_num_tclassid_users(net) && (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) { if (IN_DEV_ACCEPT_LOCAL(idev)) goto ok; /* with custom local routes in place, checking local addresses * only will be too optimistic, with custom rules, checking * local addresses only can be too strict, e.g. due to vrf */ if (net->ipv4.fib_has_custom_local_routes || fib4_has_custom_rules(net)) goto full_check; /* Within the same container, it is regarded as a martian source, * and the same host but different containers are not. */ if (inet_lookup_ifaddr_rcu(net, src)) return -EINVAL; ok: *itag = 0; return 0; } full_check: return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag); } static inline __be32 sk_extract_addr(struct sockaddr *addr) { return ((struct sockaddr_in *) addr)->sin_addr.s_addr; } static int put_rtax(struct nlattr *mx, int len, int type, u32 value) { struct nlattr *nla; nla = (struct nlattr *) ((char *) mx + len); nla->nla_type = type; nla->nla_len = nla_attr_size(4); *(u32 *) nla_data(nla) = value; return len + nla_total_size(4); } static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, struct fib_config *cfg) { __be32 addr; int plen; memset(cfg, 0, sizeof(*cfg)); cfg->fc_nlinfo.nl_net = net; if (rt->rt_dst.sa_family != AF_INET) return -EAFNOSUPPORT; /* * Check mask for validity: * a) it must be contiguous. * b) destination must have all host bits clear. * c) if application forgot to set correct family (AF_INET), * reject request unless it is absolutely clear i.e. * both family and mask are zero. */ plen = 32; addr = sk_extract_addr(&rt->rt_dst); if (!(rt->rt_flags & RTF_HOST)) { __be32 mask = sk_extract_addr(&rt->rt_genmask); if (rt->rt_genmask.sa_family != AF_INET) { if (mask || rt->rt_genmask.sa_family) return -EAFNOSUPPORT; } if (bad_mask(mask, addr)) return -EINVAL; plen = inet_mask_len(mask); } cfg->fc_dst_len = plen; cfg->fc_dst = addr; if (cmd != SIOCDELRT) { cfg->fc_nlflags = NLM_F_CREATE; cfg->fc_protocol = RTPROT_BOOT; } if (rt->rt_metric) cfg->fc_priority = rt->rt_metric - 1; if (rt->rt_flags & RTF_REJECT) { cfg->fc_scope = RT_SCOPE_HOST; cfg->fc_type = RTN_UNREACHABLE; return 0; } cfg->fc_scope = RT_SCOPE_NOWHERE; cfg->fc_type = RTN_UNICAST; if (rt->rt_dev) { char *colon; struct net_device *dev; char devname[IFNAMSIZ]; if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1)) return -EFAULT; devname[IFNAMSIZ-1] = 0; colon = strchr(devname, ':'); if (colon) *colon = 0; dev = __dev_get_by_name(net, devname); if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; cfg->fc_table = l3mdev_fib_table(dev); if (colon) { const struct in_ifaddr *ifa; struct in_device *in_dev; in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return -ENODEV; *colon = ':'; rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (strcmp(ifa->ifa_label, devname) == 0) break; } rcu_read_unlock(); if (!ifa) return -ENODEV; cfg->fc_prefsrc = ifa->ifa_local; } } addr = sk_extract_addr(&rt->rt_gateway); if (rt->rt_gateway.sa_family == AF_INET && addr) { unsigned int addr_type; cfg->fc_gw4 = addr; cfg->fc_gw_family = AF_INET; addr_type = inet_addr_type_table(net, addr, cfg->fc_table); if (rt->rt_flags & RTF_GATEWAY && addr_type == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } if (!cfg->fc_table) cfg->fc_table = RT_TABLE_MAIN; if (cmd == SIOCDELRT) return 0; if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family) return -EINVAL; if (cfg->fc_scope == RT_SCOPE_NOWHERE) cfg->fc_scope = RT_SCOPE_LINK; if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) { struct nlattr *mx; int len = 0; mx = kcalloc(3, nla_total_size(4), GFP_KERNEL); if (!mx) return -ENOMEM; if (rt->rt_flags & RTF_MTU) len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40); if (rt->rt_flags & RTF_WINDOW) len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window); if (rt->rt_flags & RTF_IRTT) len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3); cfg->fc_mx = mx; cfg->fc_mx_len = len; } return 0; } /* * Handle IP routing ioctl calls. * These are used to manipulate the routing tables */ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt) { struct fib_config cfg; int err; switch (cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_lock(); err = rtentry_to_fib_config(net, cmd, rt, &cfg); if (err == 0) { struct fib_table *tb; if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) err = fib_table_delete(net, tb, &cfg, NULL); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) err = fib_table_insert(net, tb, &cfg, NULL); else err = -ENOBUFS; } /* allocated by rtentry_to_fib_config() */ kfree(cfg.fc_mx); } rtnl_unlock(); return err; } return -EINVAL; } const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_DST] = { .type = NLA_U32 }, [RTA_SRC] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_GATEWAY] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_FLOW] = { .type = NLA_U32 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, }; int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack) { struct rtvia *via; int alen; if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) { NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA"); return -EINVAL; } via = nla_data(nla); alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); switch (via->rtvia_family) { case AF_INET: if (alen != sizeof(__be32)) { NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET; cfg->fc_gw4 = *((__be32 *)via->rtvia_addr); break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) if (alen != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET6; cfg->fc_gw6 = *((struct in6_addr *)via->rtvia_addr); #else NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel"); return -EINVAL; #endif break; default: NL_SET_ERR_MSG(extack, "Unsupported address family in RTA_VIA"); return -EINVAL; } return 0; } static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_config *cfg, struct netlink_ext_ack *extack) { bool has_gw = false, has_via = false; struct nlattr *attr; int err, remaining; struct rtmsg *rtm; err = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) goto errout; memset(cfg, 0, sizeof(*cfg)); rtm = nlmsg_data(nlh); if (!inet_validate_dscp(rtm->rtm_tos)) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): ECN bits must be 0"); err = -EINVAL; goto errout; } cfg->fc_dscp = inet_dsfield_to_dscp(rtm->rtm_tos); cfg->fc_dst_len = rtm->rtm_dst_len; cfg->fc_table = rtm->rtm_table; cfg->fc_protocol = rtm->rtm_protocol; cfg->fc_scope = rtm->rtm_scope; cfg->fc_type = rtm->rtm_type; cfg->fc_flags = rtm->rtm_flags; cfg->fc_nlflags = nlh->nlmsg_flags; cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = net; if (cfg->fc_type > RTN_MAX) { NL_SET_ERR_MSG(extack, "Invalid route type"); err = -EINVAL; goto errout; } nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) { switch (nla_type(attr)) { case RTA_DST: cfg->fc_dst = nla_get_be32(attr); break; case RTA_OIF: cfg->fc_oif = nla_get_u32(attr); break; case RTA_GATEWAY: has_gw = true; cfg->fc_gw4 = nla_get_be32(attr); if (cfg->fc_gw4) cfg->fc_gw_family = AF_INET; break; case RTA_VIA: has_via = true; err = fib_gw_from_via(cfg, attr, extack); if (err) goto errout; break; case RTA_PRIORITY: cfg->fc_priority = nla_get_u32(attr); break; case RTA_PREFSRC: cfg->fc_prefsrc = nla_get_be32(attr); break; case RTA_METRICS: cfg->fc_mx = nla_data(attr); cfg->fc_mx_len = nla_len(attr); break; case RTA_MULTIPATH: err = lwtunnel_valid_encap_type_attr(nla_data(attr), nla_len(attr), extack); if (err < 0) goto errout; cfg->fc_mp = nla_data(attr); cfg->fc_mp_len = nla_len(attr); break; case RTA_FLOW: cfg->fc_flow = nla_get_u32(attr); break; case RTA_TABLE: cfg->fc_table = nla_get_u32(attr); break; case RTA_ENCAP: cfg->fc_encap = attr; break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; break; case RTA_NH_ID: cfg->fc_nh_id = nla_get_u32(attr); break; } } if (cfg->fc_nh_id) { if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_encap || cfg->fc_mp) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); return -EINVAL; } } if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); return -EINVAL; } if (!cfg->fc_table) cfg->fc_table = RT_TABLE_MAIN; return 0; errout: return err; } static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; if (cfg.fc_nh_id && !nexthop_find_by_id(net, cfg.fc_nh_id)) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); err = -EINVAL; goto errout; } tb = fib_get_table(net, cfg.fc_table); if (!tb) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); err = -ESRCH; goto errout; } err = fib_table_delete(net, tb, &cfg, extack); errout: return err; } static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; tb = fib_new_table(net, cfg.fc_table); if (!tb) { err = -ENOBUFS; goto errout; } err = fib_table_insert(net, tb, &cfg, extack); if (!err && cfg.fc_type == RTN_LOCAL) net->ipv4.fib_has_custom_local_routes = true; errout: return err; } int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[RTA_MAX + 1]; struct rtmsg *rtm; int err, i; if (filter->rtnl_held) ASSERT_RTNL(); if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request"); return -EINVAL; } rtm = nlmsg_data(nlh); if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_scope) { NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request"); return -EINVAL; } if (rtm->rtm_flags & ~(RTM_F_CLONED | RTM_F_PREFIX)) { NL_SET_ERR_MSG(extack, "Invalid flags for FIB dump request"); return -EINVAL; } if (rtm->rtm_flags & RTM_F_CLONED) filter->dump_routes = false; else filter->dump_exceptions = false; filter->flags = rtm->rtm_flags; filter->protocol = rtm->rtm_protocol; filter->rt_type = rtm->rtm_type; filter->table_id = rtm->rtm_table; err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) return err; for (i = 0; i <= RTA_MAX; ++i) { int ifindex; if (!tb[i]) continue; switch (i) { case RTA_TABLE: filter->table_id = nla_get_u32(tb[i]); break; case RTA_OIF: ifindex = nla_get_u32(tb[i]); if (filter->rtnl_held) filter->dev = __dev_get_by_index(net, ifindex); else filter->dev = dev_get_by_index_rcu(net, ifindex); if (!filter->dev) return -ENODEV; break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; } } if (filter->flags || filter->protocol || filter->rt_type || filter->table_id || filter->dev) { filter->filter_set = 1; cb->answer_flags = NLM_F_DUMP_FILTERED; } return 0; } EXPORT_SYMBOL_GPL(ip_valid_fib_dump_req); static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { struct fib_dump_filter filter = { .dump_routes = true, .dump_exceptions = true, .rtnl_held = false, }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_head *head; int dumped = 0, err = 0; rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); filter.flags = rtm->rtm_flags & (RTM_F_PREFIX | RTM_F_CLONED); } /* ipv4 does not use prefix flag */ if (filter.flags & RTM_F_PREFIX) goto unlock; if (filter.table_id) { tb = fib_get_table(net, filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET) goto unlock; NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist"); err = -ENOENT; goto unlock; } err = fib_table_dump(tb, skb, cb, &filter); goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; err = 0; for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { if (e < s_e) goto next; if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); err = fib_table_dump(tb, skb, cb, &filter); if (err < 0) goto out; dumped = 1; next: e++; } } out: cb->args[1] = e; cb->args[0] = h; unlock: rcu_read_unlock(); return err; } /* Prepare and feed intra-kernel routing request. * Really, it should be netlink message, but :-( netlink * can be not configured, so that we feed it directly * to fib engine. It is legal, because all events occur * only when netlink is already locked. */ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa, u32 rt_priority) { struct net *net = dev_net(ifa->ifa_dev->dev); u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, .fc_type = type, .fc_dst = dst, .fc_dst_len = dst_len, .fc_priority = rt_priority, .fc_prefsrc = ifa->ifa_local, .fc_oif = ifa->ifa_dev->dev->ifindex, .fc_nlflags = NLM_F_CREATE | NLM_F_APPEND, .fc_nlinfo = { .nl_net = net, }, }; if (!tb_id) tb_id = (type == RTN_UNICAST) ? RT_TABLE_MAIN : RT_TABLE_LOCAL; tb = fib_new_table(net, tb_id); if (!tb) return; cfg.fc_table = tb->tb_id; if (type != RTN_LOCAL) cfg.fc_scope = RT_SCOPE_LINK; else cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) fib_table_insert(net, tb, &cfg, NULL); else fib_table_delete(net, tb, &cfg, NULL); } void fib_add_ifaddr(struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *prim = ifa; __be32 mask = ifa->ifa_mask; __be32 addr = ifa->ifa_local; __be32 prefix = ifa->ifa_address & mask; if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); if (!prim) { pr_warn("%s: bug: prim == NULL\n", __func__); return; } } fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim, 0); if (!(dev->flags & IFF_UP)) return; /* Add broadcast address, if it is explicitly assigned. */ if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); arp_invalidate(dev, ifa->ifa_broadcast, false); } if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) && (prefix != addr || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, prim, ifa->ifa_rt_priority); /* Add the network broadcast address, when it makes sense */ if (ifa->ifa_prefixlen < 31) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, 32, prim, 0); arp_invalidate(dev, prefix | ~mask, false); } } } void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric) { __be32 prefix = ifa->ifa_address & ifa->ifa_mask; struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; if (!(dev->flags & IFF_UP) || ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) || ipv4_is_zeronet(prefix) || (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32)) return; /* add the new */ fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, ifa, new_metric); /* delete the old */ fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, ifa, ifa->ifa_rt_priority); } /* Delete primary or secondary address. * Optionally, on secondary address promotion consider the addresses * from subnet iprim as deleted, even if they are in device list. * In this case the secondary ifa can be in device list. */ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *ifa1; struct in_ifaddr *prim = ifa, *prim1 = NULL; __be32 brd = ifa->ifa_address | ~ifa->ifa_mask; __be32 any = ifa->ifa_address & ifa->ifa_mask; #define LOCAL_OK 1 #define BRD_OK 2 #define BRD0_OK 4 #define BRD1_OK 8 unsigned int ok = 0; int subnet = 0; /* Primary network */ int gone = 1; /* Address is missing */ int same_prefsrc = 0; /* Another primary with same IP */ if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (!prim) { /* if the device has been deleted, we don't perform * address promotion */ if (!in_dev->dead) pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { pr_warn("%s: bug: iprim != prim\n", __func__); return; } } else if (!ipv4_is_zeronet(any) && (any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, any, ifa->ifa_prefixlen, prim, 0); subnet = 1; } if (in_dev->dead) goto no_promotions; /* Deletion is more complicated than add. * We should take care of not to delete too much :-) * * Scan address list to be sure that addresses are really gone. */ rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa1, in_dev) { if (ifa1 == ifa) { /* promotion, keep the IP */ gone = 0; continue; } /* Ignore IFAs from our subnet */ if (iprim && ifa1->ifa_mask == iprim->ifa_mask && inet_ifa_match(ifa1->ifa_address, iprim)) continue; /* Ignore ifa1 if it uses different primary IP (prefsrc) */ if (ifa1->ifa_flags & IFA_F_SECONDARY) { /* Another address from our subnet? */ if (ifa1->ifa_mask == prim->ifa_mask && inet_ifa_match(ifa1->ifa_address, prim)) prim1 = prim; else { /* We reached the secondaries, so * same_prefsrc should be determined. */ if (!same_prefsrc) continue; /* Search new prim1 if ifa1 is not * using the current prim1 */ if (!prim1 || ifa1->ifa_mask != prim1->ifa_mask || !inet_ifa_match(ifa1->ifa_address, prim1)) prim1 = inet_ifa_byprefix(in_dev, ifa1->ifa_address, ifa1->ifa_mask); if (!prim1) continue; if (prim1->ifa_local != prim->ifa_local) continue; } } else { if (prim->ifa_local != ifa1->ifa_local) continue; prim1 = ifa1; if (prim != prim1) same_prefsrc = 1; } if (ifa->ifa_local == ifa1->ifa_local) ok |= LOCAL_OK; if (ifa->ifa_broadcast == ifa1->ifa_broadcast) ok |= BRD_OK; if (brd == ifa1->ifa_broadcast) ok |= BRD1_OK; if (any == ifa1->ifa_broadcast) ok |= BRD0_OK; /* primary has network specific broadcasts */ if (prim1 == ifa1 && ifa1->ifa_prefixlen < 31) { __be32 brd1 = ifa1->ifa_address | ~ifa1->ifa_mask; __be32 any1 = ifa1->ifa_address & ifa1->ifa_mask; if (!ipv4_is_zeronet(any1)) { if (ifa->ifa_broadcast == brd1 || ifa->ifa_broadcast == any1) ok |= BRD_OK; if (brd == brd1 || brd == any1) ok |= BRD1_OK; if (any == brd1 || any == any1) ok |= BRD0_OK; } } } rcu_read_unlock(); no_promotions: if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); if (subnet && ifa->ifa_prefixlen < 31) { if (!(ok & BRD1_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim, 0); if (!(ok & BRD0_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim, 0); } if (!(ok & LOCAL_OK)) { unsigned int addr_type; fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim, 0); /* Check, that this local address finally disappeared. */ addr_type = inet_addr_type_dev_table(dev_net(dev), dev, ifa->ifa_local); if (gone && addr_type != RTN_LOCAL) { /* And the last, but not the least thing. * We must flush stray FIB entries. * * First of all, we scan fib_info list searching * for stray nexthop entries, then ignite fib_flush. */ if (fib_sync_down_addr(dev, ifa->ifa_local)) fib_flush(dev_net(dev)); } } #undef LOCAL_OK #undef BRD_OK #undef BRD0_OK #undef BRD1_OK } static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn) { struct fib_result res; struct flowi4 fl4 = { .flowi4_mark = frn->fl_mark, .daddr = frn->fl_addr, .flowi4_tos = frn->fl_tos & INET_DSCP_MASK, .flowi4_scope = frn->fl_scope, }; struct fib_table *tb; rcu_read_lock(); tb = fib_get_table(net, frn->tb_id_in); frn->err = -ENOENT; if (tb) { local_bh_disable(); frn->tb_id = tb->tb_id; frn->err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); if (!frn->err) { frn->prefixlen = res.prefixlen; frn->nh_sel = res.nh_sel; frn->type = res.type; frn->scope = res.scope; } local_bh_enable(); } rcu_read_unlock(); } static void nl_fib_input(struct sk_buff *skb) { struct net *net; struct fib_result_nl *frn; struct nlmsghdr *nlh; u32 portid; net = sock_net(skb->sk); nlh = nlmsg_hdr(skb); if (skb->len < nlmsg_total_size(sizeof(*frn)) || skb->len < nlh->nlmsg_len || nlmsg_len(nlh) < sizeof(*frn)) return; skb = netlink_skb_clone(skb, GFP_KERNEL); if (!skb) return; nlh = nlmsg_hdr(skb); frn = nlmsg_data(nlh); nl_fib_lookup(net, frn); portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ nlmsg_unicast(net->ipv4.fibnl, skb, portid); } static int __net_init nl_fib_lookup_init(struct net *net) { struct sock *sk; struct netlink_kernel_cfg cfg = { .input = nl_fib_input, }; sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg); if (!sk) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; return 0; } static void nl_fib_lookup_exit(struct net *net) { netlink_kernel_release(net->ipv4.fibnl); net->ipv4.fibnl = NULL; } static void fib_disable_ip(struct net_device *dev, unsigned long event, bool force) { if (fib_sync_down_dev(dev, event, force)) fib_flush(dev_net(dev)); else rt_cache_flush(dev_net(dev)); arp_ifdown(dev); } static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct in_ifaddr *ifa = ptr; struct net_device *dev = ifa->ifa_dev->dev; struct net *net = dev_net(dev); switch (event) { case NETDEV_UP: fib_add_ifaddr(ifa); #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(dev_net(dev)); break; case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); atomic_inc(&net->ipv4.dev_addr_genid); if (!ifa->ifa_dev->ifa_list) { /* Last address was deleted from this interface. * Disable IP. */ fib_disable_ip(dev, event, true); } else { rt_cache_flush(dev_net(dev)); } break; } return NOTIFY_DONE; } static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *upper_info = ptr; struct netdev_notifier_info_ext *info_ext = ptr; struct in_device *in_dev; struct net *net = dev_net(dev); struct in_ifaddr *ifa; unsigned int flags; if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, event, true); rt_flush_dev(dev); return NOTIFY_DONE; } in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return NOTIFY_DONE; switch (event) { case NETDEV_UP: in_dev_for_each_ifa_rtnl(ifa, in_dev) { fib_add_ifaddr(ifa); } #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(net); break; case NETDEV_DOWN: fib_disable_ip(dev, event, false); break; case NETDEV_CHANGE: flags = dev_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) fib_sync_up(dev, RTNH_F_LINKDOWN); else fib_sync_down_dev(dev, event, false); rt_cache_flush(net); break; case NETDEV_CHANGEMTU: fib_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(net); break; case NETDEV_CHANGEUPPER: upper_info = ptr; /* flush all routes if dev is linked to or unlinked from * an L3 master device (e.g., VRF) */ if (upper_info->upper_dev && netif_is_l3_master(upper_info->upper_dev)) fib_disable_ip(dev, NETDEV_DOWN, true); break; } return NOTIFY_DONE; } static struct notifier_block fib_inetaddr_notifier = { .notifier_call = fib_inetaddr_event, }; static struct notifier_block fib_netdev_notifier = { .notifier_call = fib_netdev_event, }; static int __net_init ip_fib_net_init(struct net *net) { int err; size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ; err = fib4_notifier_init(net); if (err) return err; #ifdef CONFIG_IP_ROUTE_MULTIPATH /* Default to 3-tuple */ net->ipv4.sysctl_fib_multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; #endif /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv4.fib_table_hash) { err = -ENOMEM; goto err_table_hash_alloc; } err = fib4_rules_init(net); if (err < 0) goto err_rules_init; return 0; err_rules_init: kfree(net->ipv4.fib_table_hash); err_table_hash_alloc: fib4_notifier_exit(net); return err; } static void ip_fib_net_exit(struct net *net) { int i; ASSERT_RTNL(); #ifdef CONFIG_IP_MULTIPLE_TABLES RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); #endif /* Destroy the tables in reverse order to guarantee that the * local table, ID 255, is destroyed before the main table, ID * 254. This is necessary as the local table may contain * references to data contained in the main table. */ for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) { struct hlist_head *head = &net->ipv4.fib_table_hash[i]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { hlist_del(&tb->tb_hlist); fib_table_flush(net, tb, true); fib_free_table(tb); } } #ifdef CONFIG_IP_MULTIPLE_TABLES fib4_rules_exit(net); #endif kfree(net->ipv4.fib_table_hash); fib4_notifier_exit(net); } static int __net_init fib_net_init(struct net *net) { int error; #ifdef CONFIG_IP_ROUTE_CLASSID atomic_set(&net->ipv4.fib_num_tclassid_users, 0); #endif error = ip_fib_net_init(net); if (error < 0) goto out; error = nl_fib_lookup_init(net); if (error < 0) goto out_nlfl; error = fib_proc_init(net); if (error < 0) goto out_proc; out: return error; out_proc: nl_fib_lookup_exit(net); out_nlfl: rtnl_lock(); ip_fib_net_exit(net); rtnl_unlock(); goto out; } static void __net_exit fib_net_exit(struct net *net) { fib_proc_exit(net); nl_fib_lookup_exit(net); } static void __net_exit fib_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) ip_fib_net_exit(net); rtnl_unlock(); } static struct pernet_operations fib_net_ops = { .init = fib_net_init, .exit = fib_net_exit, .exit_batch = fib_net_exit_batch, }; void __init ip_fib_init(void) { fib_trie_init(); register_pernet_subsys(&fib_net_ops); register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0); rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0); rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE); } |
| 7 4 5 4 5 4 5 4 5 5 2 7 7 39 39 31 31 31 31 31 31 31 23 23 2 2 28 28 28 19 19 19 19 19 19 19 19 19 9 12 3 12 31 39 5 2 5 2 5 2 5 2 5 4 2 5 2 35 3 3 1 2 2 2 20 35 35 20 20 20 20 20 20 20 6 6 6 6 6 6 35 35 35 46 46 46 46 46 36 29 45 46 46 50 50 3 48 47 47 35 35 6 50 50 20 50 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dccp/options.c * * An implementation of the DCCP protocol * Copyright (c) 2005 Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org> * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net> * Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz> */ #include <linux/dccp.h> #include <linux/module.h> #include <linux/types.h> #include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include "ackvec.h" #include "ccid.h" #include "dccp.h" #include "feat.h" u64 dccp_decode_value_var(const u8 *bf, const u8 len) { u64 value = 0; if (len >= DCCP_OPTVAL_MAXLEN) value += ((u64)*bf++) << 40; if (len > 4) value += ((u64)*bf++) << 32; if (len > 3) value += ((u64)*bf++) << 24; if (len > 2) value += ((u64)*bf++) << 16; if (len > 1) value += ((u64)*bf++) << 8; if (len > 0) value += *bf; return value; } /** * dccp_parse_options - Parse DCCP options present in @skb * @sk: client|server|listening dccp socket (when @dreq != NULL) * @dreq: request socket to use during connection setup, or NULL * @skb: frame to parse */ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); const struct dccp_hdr *dh = dccp_hdr(skb); const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type; unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb); unsigned char *opt_ptr = options; const unsigned char *opt_end = (unsigned char *)dh + (dh->dccph_doff * 4); struct dccp_options_received *opt_recv = &dp->dccps_options_received; unsigned char opt, len; unsigned char *value; u32 elapsed_time; __be32 opt_val; int rc; int mandatory = 0; memset(opt_recv, 0, sizeof(*opt_recv)); opt = len = 0; while (opt_ptr != opt_end) { opt = *opt_ptr++; len = 0; value = NULL; /* Check if this isn't a single byte option */ if (opt > DCCPO_MAX_RESERVED) { if (opt_ptr == opt_end) goto out_nonsensical_length; len = *opt_ptr++; if (len < 2) goto out_nonsensical_length; /* * Remove the type and len fields, leaving * just the value size */ len -= 2; value = opt_ptr; opt_ptr += len; if (opt_ptr > opt_end) goto out_nonsensical_length; } /* * CCID-specific options are ignored during connection setup, as * negotiation may still be in progress (see RFC 4340, 10.3). * The same applies to Ack Vectors, as these depend on the CCID. */ if (dreq != NULL && (opt >= DCCPO_MIN_RX_CCID_SPECIFIC || opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1)) goto ignore_option; switch (opt) { case DCCPO_PADDING: break; case DCCPO_MANDATORY: if (mandatory) goto out_invalid_option; if (pkt_type != DCCP_PKT_DATA) mandatory = 1; break; case DCCPO_NDP_COUNT: if (len > 6) goto out_invalid_option; opt_recv->dccpor_ndp = dccp_decode_value_var(value, len); dccp_pr_debug("%s opt: NDP count=%llu\n", dccp_role(sk), (unsigned long long)opt_recv->dccpor_ndp); break; case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R: if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */ break; if (len == 0) goto out_invalid_option; rc = dccp_feat_parse_options(sk, dreq, mandatory, opt, *value, value + 1, len - 1); if (rc) goto out_featneg_failed; break; case DCCPO_TIMESTAMP: if (len != 4) goto out_invalid_option; /* * RFC 4340 13.1: "The precise time corresponding to * Timestamp Value zero is not specified". We use * zero to indicate absence of a meaningful timestamp. */ opt_val = get_unaligned((__be32 *)value); if (unlikely(opt_val == 0)) { DCCP_WARN("Timestamp with zero value\n"); break; } if (dreq != NULL) { dreq->dreq_timestamp_echo = ntohl(opt_val); dreq->dreq_timestamp_time = dccp_timestamp(); } else { opt_recv->dccpor_timestamp = dp->dccps_timestamp_echo = ntohl(opt_val); dp->dccps_timestamp_time = dccp_timestamp(); } dccp_pr_debug("%s rx opt: TIMESTAMP=%u, ackno=%llu\n", dccp_role(sk), ntohl(opt_val), (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq); /* schedule an Ack in case this sender is quiescent */ inet_csk_schedule_ack(sk); break; case DCCPO_TIMESTAMP_ECHO: if (len != 4 && len != 6 && len != 8) goto out_invalid_option; opt_val = get_unaligned((__be32 *)value); opt_recv->dccpor_timestamp_echo = ntohl(opt_val); dccp_pr_debug("%s rx opt: TIMESTAMP_ECHO=%u, len=%d, " "ackno=%llu", dccp_role(sk), opt_recv->dccpor_timestamp_echo, len + 2, (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq); value += 4; if (len == 4) { /* no elapsed time included */ dccp_pr_debug_cat("\n"); break; } if (len == 6) { /* 2-byte elapsed time */ __be16 opt_val2 = get_unaligned((__be16 *)value); elapsed_time = ntohs(opt_val2); } else { /* 4-byte elapsed time */ opt_val = get_unaligned((__be32 *)value); elapsed_time = ntohl(opt_val); } dccp_pr_debug_cat(", ELAPSED_TIME=%u\n", elapsed_time); /* Give precedence to the biggest ELAPSED_TIME */ if (elapsed_time > opt_recv->dccpor_elapsed_time) opt_recv->dccpor_elapsed_time = elapsed_time; break; case DCCPO_ELAPSED_TIME: if (dccp_packet_without_ack(skb)) /* RFC 4340, 13.2 */ break; if (len == 2) { __be16 opt_val2 = get_unaligned((__be16 *)value); elapsed_time = ntohs(opt_val2); } else if (len == 4) { opt_val = get_unaligned((__be32 *)value); elapsed_time = ntohl(opt_val); } else { goto out_invalid_option; } if (elapsed_time > opt_recv->dccpor_elapsed_time) opt_recv->dccpor_elapsed_time = elapsed_time; dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n", dccp_role(sk), elapsed_time); break; case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC: if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk, pkt_type, opt, value, len)) goto out_invalid_option; break; case DCCPO_ACK_VECTOR_0: case DCCPO_ACK_VECTOR_1: if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */ break; /* * Ack vectors are processed by the TX CCID if it is * interested. The RX CCID need not parse Ack Vectors, * since it is only interested in clearing old state. */ fallthrough; case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, pkt_type, opt, value, len)) goto out_invalid_option; break; default: DCCP_CRIT("DCCP(%p): option %d(len=%d) not " "implemented, ignoring", sk, opt, len); break; } ignore_option: if (opt != DCCPO_MANDATORY) mandatory = 0; } /* mandatory was the last byte in option list -> reset connection */ if (mandatory) goto out_invalid_option; out_nonsensical_length: /* RFC 4340, 5.8: ignore option and all remaining option space */ return 0; out_invalid_option: DCCP_INC_STATS(DCCP_MIB_INVALIDOPT); rc = DCCP_RESET_CODE_OPTION_ERROR; out_featneg_failed: DCCP_WARN("DCCP(%p): Option %d (len=%d) error=%u\n", sk, opt, len, rc); DCCP_SKB_CB(skb)->dccpd_reset_code = rc; DCCP_SKB_CB(skb)->dccpd_reset_data[0] = opt; DCCP_SKB_CB(skb)->dccpd_reset_data[1] = len > 0 ? value[0] : 0; DCCP_SKB_CB(skb)->dccpd_reset_data[2] = len > 1 ? value[1] : 0; return -1; } EXPORT_SYMBOL_GPL(dccp_parse_options); void dccp_encode_value_var(const u64 value, u8 *to, const u8 len) { if (len >= DCCP_OPTVAL_MAXLEN) *to++ = (value & 0xFF0000000000ull) >> 40; if (len > 4) *to++ = (value & 0xFF00000000ull) >> 32; if (len > 3) *to++ = (value & 0xFF000000) >> 24; if (len > 2) *to++ = (value & 0xFF0000) >> 16; if (len > 1) *to++ = (value & 0xFF00) >> 8; if (len > 0) *to++ = (value & 0xFF); } static inline u8 dccp_ndp_len(const u64 ndp) { if (likely(ndp <= 0xFF)) return 1; return likely(ndp <= USHRT_MAX) ? 2 : (ndp <= UINT_MAX ? 4 : 6); } int dccp_insert_option(struct sk_buff *skb, const unsigned char option, const void *value, const unsigned char len) { unsigned char *to; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 2 > DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len + 2; to = skb_push(skb, len + 2); *to++ = option; *to++ = len + 2; memcpy(to, value, len); return 0; } EXPORT_SYMBOL_GPL(dccp_insert_option); static int dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); u64 ndp = dp->dccps_ndp_count; if (dccp_non_data_packet(skb)) ++dp->dccps_ndp_count; else dp->dccps_ndp_count = 0; if (ndp > 0) { unsigned char *ptr; const int ndp_len = dccp_ndp_len(ndp); const int len = ndp_len + 2; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; ptr = skb_push(skb, len); *ptr++ = DCCPO_NDP_COUNT; *ptr++ = len; dccp_encode_value_var(ndp, ptr, ndp_len); } return 0; } static inline int dccp_elapsed_time_len(const u32 elapsed_time) { return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4; } static int dccp_insert_option_timestamp(struct sk_buff *skb) { __be32 now = htonl(dccp_timestamp()); /* yes this will overflow but that is the point as we want a * 10 usec 32 bit timer which mean it wraps every 11.9 hours */ return dccp_insert_option(skb, DCCPO_TIMESTAMP, &now, sizeof(now)); } static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp, struct dccp_request_sock *dreq, struct sk_buff *skb) { __be32 tstamp_echo; unsigned char *to; u32 elapsed_time, elapsed_time_len, len; if (dreq != NULL) { elapsed_time = dccp_timestamp() - dreq->dreq_timestamp_time; tstamp_echo = htonl(dreq->dreq_timestamp_echo); dreq->dreq_timestamp_echo = 0; } else { elapsed_time = dccp_timestamp() - dp->dccps_timestamp_time; tstamp_echo = htonl(dp->dccps_timestamp_echo); dp->dccps_timestamp_echo = 0; } elapsed_time_len = dccp_elapsed_time_len(elapsed_time); len = 6 + elapsed_time_len; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; to = skb_push(skb, len); *to++ = DCCPO_TIMESTAMP_ECHO; *to++ = len; memcpy(to, &tstamp_echo, 4); to += 4; if (elapsed_time_len == 2) { const __be16 var16 = htons((u16)elapsed_time); memcpy(to, &var16, 2); } else if (elapsed_time_len == 4) { const __be32 var32 = htonl(elapsed_time); memcpy(to, &var32, 4); } return 0; } static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); const u16 buflen = dccp_ackvec_buflen(av); /* Figure out how many options do we need to represent the ackvec */ const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN); u16 len = buflen + 2 * nr_opts; u8 i, nonce = 0; const unsigned char *tail, *from; unsigned char *to; if (dcb->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) { DCCP_WARN("Lacking space for %u bytes on %s packet\n", len, dccp_packet_name(dcb->dccpd_type)); return -1; } /* * Since Ack Vectors are variable-length, we can not always predict * their size. To catch exception cases where the space is running out * on the skb, a separate Sync is scheduled to carry the Ack Vector. */ if (len > DCCPAV_MIN_OPTLEN && len + dcb->dccpd_opt_len + skb->len > dp->dccps_mss_cache) { DCCP_WARN("No space left for Ack Vector (%u) on skb (%u+%u), " "MPS=%u ==> reduce payload size?\n", len, skb->len, dcb->dccpd_opt_len, dp->dccps_mss_cache); dp->dccps_sync_scheduled = 1; return 0; } dcb->dccpd_opt_len += len; to = skb_push(skb, len); len = buflen; from = av->av_buf + av->av_buf_head; tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; for (i = 0; i < nr_opts; ++i) { int copylen = len; if (len > DCCP_SINGLE_OPT_MAXLEN) copylen = DCCP_SINGLE_OPT_MAXLEN; /* * RFC 4340, 12.2: Encode the Nonce Echo for this Ack Vector via * its type; ack_nonce is the sum of all individual buf_nonce's. */ nonce ^= av->av_buf_nonce[i]; *to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i]; *to++ = copylen + 2; /* Check if buf_head wraps */ if (from + copylen > tail) { const u16 tailsize = tail - from; memcpy(to, from, tailsize); to += tailsize; len -= tailsize; copylen -= tailsize; from = av->av_buf; } memcpy(to, from, copylen); from += copylen; to += copylen; len -= copylen; } /* * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340. */ if (dccp_ackvec_update_records(av, dcb->dccpd_seq, nonce)) return -ENOBUFS; return 0; } /** * dccp_insert_option_mandatory - Mandatory option (5.8.2) * @skb: frame into which to insert option * * Note that since we are using skb_push, this function needs to be called * _after_ inserting the option it is supposed to influence (stack order). */ int dccp_insert_option_mandatory(struct sk_buff *skb) { if (DCCP_SKB_CB(skb)->dccpd_opt_len >= DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len++; *(u8 *)skb_push(skb, 1) = DCCPO_MANDATORY; return 0; } /** * dccp_insert_fn_opt - Insert single Feature-Negotiation option into @skb * @skb: frame to insert feature negotiation option into * @type: %DCCPO_CHANGE_L, %DCCPO_CHANGE_R, %DCCPO_CONFIRM_L, %DCCPO_CONFIRM_R * @feat: one out of %dccp_feature_numbers * @val: NN value or SP array (preferred element first) to copy * @len: true length of @val in bytes (excluding first element repetition) * @repeat_first: whether to copy the first element of @val twice * * The last argument is used to construct Confirm options, where the preferred * value and the preference list appear separately (RFC 4340, 6.3.1). Preference * lists are kept such that the preferred entry is always first, so we only need * to copy twice, and avoid the overhead of cloning into a bigger array. */ int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat, u8 *val, u8 len, bool repeat_first) { u8 tot_len, *to; /* take the `Feature' field and possible repetition into account */ if (len > (DCCP_SINGLE_OPT_MAXLEN - 2)) { DCCP_WARN("length %u for feature %u too large\n", len, feat); return -1; } if (unlikely(val == NULL || len == 0)) len = repeat_first = false; tot_len = 3 + repeat_first + len; if (DCCP_SKB_CB(skb)->dccpd_opt_len + tot_len > DCCP_MAX_OPT_LEN) { DCCP_WARN("packet too small for feature %d option!\n", feat); return -1; } DCCP_SKB_CB(skb)->dccpd_opt_len += tot_len; to = skb_push(skb, tot_len); *to++ = type; *to++ = tot_len; *to++ = feat; if (repeat_first) *to++ = *val; if (len) memcpy(to, val, len); return 0; } /* The length of all options needs to be a multiple of 4 (5.8) */ static void dccp_insert_option_padding(struct sk_buff *skb) { int padding = DCCP_SKB_CB(skb)->dccpd_opt_len % 4; if (padding != 0) { padding = 4 - padding; memset(skb_push(skb, padding), 0, padding); DCCP_SKB_CB(skb)->dccpd_opt_len += padding; } } int dccp_insert_options(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); DCCP_SKB_CB(skb)->dccpd_opt_len = 0; if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb)) return -1; if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) { /* Feature Negotiation */ if (dccp_feat_insert_opts(dp, NULL, skb)) return -1; if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST) { /* * Obtain RTT sample from Request/Response exchange. * This is currently used for TFRC initialisation. */ if (dccp_insert_option_timestamp(skb)) return -1; } else if (dccp_ackvec_pending(sk) && dccp_insert_option_ackvec(sk, skb)) { return -1; } } if (dp->dccps_hc_rx_insert_options) { if (ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb)) return -1; dp->dccps_hc_rx_insert_options = 0; } if (dp->dccps_timestamp_echo != 0 && dccp_insert_option_timestamp_echo(dp, NULL, skb)) return -1; dccp_insert_option_padding(skb); return 0; } int dccp_insert_options_rsk(struct dccp_request_sock *dreq, struct sk_buff *skb) { DCCP_SKB_CB(skb)->dccpd_opt_len = 0; if (dccp_feat_insert_opts(NULL, dreq, skb)) return -1; /* Obtain RTT sample from Response/Ack exchange (used by TFRC). */ if (dccp_insert_option_timestamp(skb)) return -1; if (dreq->dreq_timestamp_echo != 0 && dccp_insert_option_timestamp_echo(NULL, dreq, skb)) return -1; dccp_insert_option_padding(skb); return 0; } |
| 58 8 58 10 163 10 8 10 10 9 10 10 10 10 10 162 58 132 58 58 163 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | // SPDX-License-Identifier: GPL-2.0 /* * lib/minmax.c: windowed min/max tracker * * Kathleen Nichols' algorithm for tracking the minimum (or maximum) * value of a data stream over some fixed time interval. (E.g., * the minimum RTT over the past five minutes.) It uses constant * space and constant time per update yet almost always delivers * the same minimum as an implementation that has to keep all the * data in the window. * * The algorithm keeps track of the best, 2nd best & 3rd best min * values, maintaining an invariant that the measurement time of * the n'th best >= n-1'th best. It also makes sure that the three * values are widely separated in the time window since that bounds * the worse case error when that data is monotonically increasing * over the window. * * Upon getting a new min, we can forget everything earlier because * it has no value - the new min is <= everything else in the window * by definition and it's the most recent. So we restart fresh on * every new min and overwrites 2nd & 3rd choices. The same property * holds for 2nd & 3rd best. */ #include <linux/module.h> #include <linux/win_minmax.h> /* As time advances, update the 1st, 2nd, and 3rd choices. */ static u32 minmax_subwin_update(struct minmax *m, u32 win, const struct minmax_sample *val) { u32 dt = val->t - m->s[0].t; if (unlikely(dt > win)) { /* * Passed entire window without a new val so make 2nd * choice the new val & 3rd choice the new 2nd choice. * we may have to iterate this since our 2nd choice * may also be outside the window (we checked on entry * that the third choice was in the window). */ m->s[0] = m->s[1]; m->s[1] = m->s[2]; m->s[2] = *val; if (unlikely(val->t - m->s[0].t > win)) { m->s[0] = m->s[1]; m->s[1] = m->s[2]; m->s[2] = *val; } } else if (unlikely(m->s[1].t == m->s[0].t) && dt > win/4) { /* * We've passed a quarter of the window without a new val * so take a 2nd choice from the 2nd quarter of the window. */ m->s[2] = m->s[1] = *val; } else if (unlikely(m->s[2].t == m->s[1].t) && dt > win/2) { /* * We've passed half the window without finding a new val * so take a 3rd choice from the last half of the window */ m->s[2] = *val; } return m->s[0].v; } /* Check if new measurement updates the 1st, 2nd or 3rd choice max. */ u32 minmax_running_max(struct minmax *m, u32 win, u32 t, u32 meas) { struct minmax_sample val = { .t = t, .v = meas }; if (unlikely(val.v >= m->s[0].v) || /* found new max? */ unlikely(val.t - m->s[2].t > win)) /* nothing left in window? */ return minmax_reset(m, t, meas); /* forget earlier samples */ if (unlikely(val.v >= m->s[1].v)) m->s[2] = m->s[1] = val; else if (unlikely(val.v >= m->s[2].v)) m->s[2] = val; return minmax_subwin_update(m, win, &val); } EXPORT_SYMBOL(minmax_running_max); /* Check if new measurement updates the 1st, 2nd or 3rd choice min. */ u32 minmax_running_min(struct minmax *m, u32 win, u32 t, u32 meas) { struct minmax_sample val = { .t = t, .v = meas }; if (unlikely(val.v <= m->s[0].v) || /* found new min? */ unlikely(val.t - m->s[2].t > win)) /* nothing left in window? */ return minmax_reset(m, t, meas); /* forget earlier samples */ if (unlikely(val.v <= m->s[1].v)) m->s[2] = m->s[1] = val; else if (unlikely(val.v <= m->s[2].v)) m->s[2] = val; return minmax_subwin_update(m, win, &val); } |
| 27 27 27 10 10 10 5 4 4 2 4 2 4 1 4 1 4 1 4 3 4 4 6 5 4 4 1 6 3 3 3 3 3 3 3 1 3 3 3 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 | // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Codel - The Controlled-Delay Active Queue Management algorithm * * Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com> * Copyright (C) 2011-2012 Van Jacobson <van@pollere.net> * * Implemented on linux by : * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/prefetch.h> #include <net/pkt_sched.h> #include <net/codel.h> #include <net/codel_impl.h> #include <net/codel_qdisc.h> #define DEFAULT_CODEL_LIMIT 1000 struct codel_sched_data { struct codel_params params; struct codel_vars vars; struct codel_stats stats; u32 drop_overlimit; }; /* This is the specific function called from codel_dequeue() * to dequeue a packet from queue. Note: backlog is handled in * codel, we dont need to reduce it here. */ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx) { struct Qdisc *sch = ctx; struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); if (skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); prefetch(&skb->end); /* we'll need skb_shinfo() */ } return skb; } static void drop_func(struct sk_buff *skb, void *ctx) { struct Qdisc *sch = ctx; kfree_skb(skb); qdisc_qstats_drop(sch); } static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch) { struct codel_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; skb = codel_dequeue(sch, &sch->qstats.backlog, &q->params, &q->vars, &q->stats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, * or HTB crashes. Defer it for next round. */ if (q->stats.drop_count && sch->q.qlen) { qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len); q->stats.drop_count = 0; q->stats.drop_len = 0; } if (skb) qdisc_bstats_update(sch, skb); return skb; } static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct codel_sched_data *q; if (likely(qdisc_qlen(sch) < sch->limit)) { codel_set_enqueue_time(skb); return qdisc_enqueue_tail(skb, sch); } q = qdisc_priv(sch); q->drop_overlimit++; return qdisc_drop(skb, sch, to_free); } static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { [TCA_CODEL_TARGET] = { .type = NLA_U32 }, [TCA_CODEL_LIMIT] = { .type = NLA_U32 }, [TCA_CODEL_INTERVAL] = { .type = NLA_U32 }, [TCA_CODEL_ECN] = { .type = NLA_U32 }, [TCA_CODEL_CE_THRESHOLD]= { .type = NLA_U32 }, }; static int codel_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_CODEL_MAX, opt, codel_policy, NULL); if (err < 0) return err; sch_tree_lock(sch); if (tb[TCA_CODEL_TARGET]) { u32 target = nla_get_u32(tb[TCA_CODEL_TARGET]); WRITE_ONCE(q->params.target, ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_CE_THRESHOLD]) { u64 val = nla_get_u32(tb[TCA_CODEL_CE_THRESHOLD]); WRITE_ONCE(q->params.ce_threshold, (val * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_INTERVAL]) { u32 interval = nla_get_u32(tb[TCA_CODEL_INTERVAL]); WRITE_ONCE(q->params.interval, ((u64)interval * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_LIMIT]) WRITE_ONCE(sch->limit, nla_get_u32(tb[TCA_CODEL_LIMIT])); if (tb[TCA_CODEL_ECN]) WRITE_ONCE(q->params.ecn, !!nla_get_u32(tb[TCA_CODEL_ECN])); qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); rtnl_qdisc_drop(skb, sch); } qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); sch_tree_unlock(sch); return 0; } static int codel_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct codel_sched_data *q = qdisc_priv(sch); sch->limit = DEFAULT_CODEL_LIMIT; codel_params_init(&q->params); codel_vars_init(&q->vars); codel_stats_init(&q->stats); q->params.mtu = psched_mtu(qdisc_dev(sch)); if (opt) { int err = codel_change(sch, opt, extack); if (err) return err; } if (sch->limit >= 1) sch->flags |= TCQ_F_CAN_BYPASS; else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } static int codel_dump(struct Qdisc *sch, struct sk_buff *skb) { struct codel_sched_data *q = qdisc_priv(sch); codel_time_t ce_threshold; struct nlattr *opts; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put_u32(skb, TCA_CODEL_TARGET, codel_time_to_us(READ_ONCE(q->params.target))) || nla_put_u32(skb, TCA_CODEL_LIMIT, READ_ONCE(sch->limit)) || nla_put_u32(skb, TCA_CODEL_INTERVAL, codel_time_to_us(READ_ONCE(q->params.interval))) || nla_put_u32(skb, TCA_CODEL_ECN, READ_ONCE(q->params.ecn))) goto nla_put_failure; ce_threshold = READ_ONCE(q->params.ce_threshold); if (ce_threshold != CODEL_DISABLED_THRESHOLD && nla_put_u32(skb, TCA_CODEL_CE_THRESHOLD, codel_time_to_us(ce_threshold))) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: nla_nest_cancel(skb, opts); return -1; } static int codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { const struct codel_sched_data *q = qdisc_priv(sch); struct tc_codel_xstats st = { .maxpacket = q->stats.maxpacket, .count = q->vars.count, .lastcount = q->vars.lastcount, .drop_overlimit = q->drop_overlimit, .ldelay = codel_time_to_us(q->vars.ldelay), .dropping = q->vars.dropping, .ecn_mark = q->stats.ecn_mark, .ce_mark = q->stats.ce_mark, }; if (q->vars.dropping) { codel_tdiff_t delta = q->vars.drop_next - codel_get_time(); if (delta >= 0) st.drop_next = codel_time_to_us(delta); else st.drop_next = -codel_time_to_us(-delta); } return gnet_stats_copy_app(d, &st, sizeof(st)); } static void codel_reset(struct Qdisc *sch) { struct codel_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); codel_vars_init(&q->vars); } static struct Qdisc_ops codel_qdisc_ops __read_mostly = { .id = "codel", .priv_size = sizeof(struct codel_sched_data), .enqueue = codel_qdisc_enqueue, .dequeue = codel_qdisc_dequeue, .peek = qdisc_peek_dequeued, .init = codel_init, .reset = codel_reset, .change = codel_change, .dump = codel_dump, .dump_stats = codel_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("codel"); static int __init codel_module_init(void) { return register_qdisc(&codel_qdisc_ops); } static void __exit codel_module_exit(void) { unregister_qdisc(&codel_qdisc_ops); } module_init(codel_module_init) module_exit(codel_module_exit) MODULE_DESCRIPTION("Controlled Delay queue discipline"); MODULE_AUTHOR("Dave Taht"); MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("Dual BSD/GPL"); |
| 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 | /* * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. 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/list.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <net/inet_connection_sock.h> #include <net/tls.h> #include <net/tls_toe.h> #include "tls.h" static LIST_HEAD(device_list); static DEFINE_SPINLOCK(device_spinlock); static void tls_toe_sk_destruct(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx = tls_get_ctx(sk); ctx->sk_destruct(sk); /* Free ctx */ rcu_assign_pointer(icsk->icsk_ulp_data, NULL); tls_ctx_free(sk, ctx); } int tls_toe_bypass(struct sock *sk) { struct tls_toe_device *dev; struct tls_context *ctx; int rc = 0; spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { if (dev->feature && dev->feature(dev)) { ctx = tls_ctx_create(sk); if (!ctx) goto out; ctx->sk_destruct = sk->sk_destruct; sk->sk_destruct = tls_toe_sk_destruct; ctx->rx_conf = TLS_HW_RECORD; ctx->tx_conf = TLS_HW_RECORD; update_sk_prot(sk, ctx); rc = 1; break; } } out: spin_unlock_bh(&device_spinlock); return rc; } void tls_toe_unhash(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); struct tls_toe_device *dev; spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { if (dev->unhash) { kref_get(&dev->kref); spin_unlock_bh(&device_spinlock); dev->unhash(dev, sk); kref_put(&dev->kref, dev->release); spin_lock_bh(&device_spinlock); } } spin_unlock_bh(&device_spinlock); ctx->sk_proto->unhash(sk); } int tls_toe_hash(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); struct tls_toe_device *dev; int err; err = ctx->sk_proto->hash(sk); spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { if (dev->hash) { kref_get(&dev->kref); spin_unlock_bh(&device_spinlock); err |= dev->hash(dev, sk); kref_put(&dev->kref, dev->release); spin_lock_bh(&device_spinlock); } } spin_unlock_bh(&device_spinlock); if (err) tls_toe_unhash(sk); return err; } void tls_toe_register_device(struct tls_toe_device *device) { spin_lock_bh(&device_spinlock); list_add_tail(&device->dev_list, &device_list); spin_unlock_bh(&device_spinlock); } EXPORT_SYMBOL(tls_toe_register_device); void tls_toe_unregister_device(struct tls_toe_device *device) { spin_lock_bh(&device_spinlock); list_del(&device->dev_list); spin_unlock_bh(&device_spinlock); } EXPORT_SYMBOL(tls_toe_unregister_device); |
| 8 8 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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _ACKVEC_H #define _ACKVEC_H /* * net/dccp/ackvec.h * * An implementation of Ack Vectors for the DCCP protocol * Copyright (c) 2007 University of Aberdeen, Scotland, UK * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@mandriva.com> */ #include <linux/dccp.h> #include <linux/compiler.h> #include <linux/list.h> #include <linux/types.h> /* * Ack Vector buffer space is static, in multiples of %DCCP_SINGLE_OPT_MAXLEN, * the maximum size of a single Ack Vector. Setting %DCCPAV_NUM_ACKVECS to 1 * will be sufficient for most cases of low Ack Ratios, using a value of 2 gives * more headroom if Ack Ratio is higher or when the sender acknowledges slowly. * The maximum value is bounded by the u16 types for indices and functions. */ #define DCCPAV_NUM_ACKVECS 2 #define DCCPAV_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * DCCPAV_NUM_ACKVECS) /* Estimated minimum average Ack Vector length - used for updating MPS */ #define DCCPAV_MIN_OPTLEN 16 /* Threshold for coping with large bursts of losses */ #define DCCPAV_BURST_THRESH (DCCPAV_MAX_ACKVEC_LEN / 8) enum dccp_ackvec_states { DCCPAV_RECEIVED = 0x00, DCCPAV_ECN_MARKED = 0x40, DCCPAV_RESERVED = 0x80, DCCPAV_NOT_RECEIVED = 0xC0 }; #define DCCPAV_MAX_RUNLEN 0x3F static inline u8 dccp_ackvec_runlen(const u8 *cell) { return *cell & DCCPAV_MAX_RUNLEN; } static inline u8 dccp_ackvec_state(const u8 *cell) { return *cell & ~DCCPAV_MAX_RUNLEN; } /** * struct dccp_ackvec - Ack Vector main data structure * * This implements a fixed-size circular buffer within an array and is largely * based on Appendix A of RFC 4340. * * @av_buf: circular buffer storage area * @av_buf_head: head index; begin of live portion in @av_buf * @av_buf_tail: tail index; first index _after_ the live portion in @av_buf * @av_buf_ackno: highest seqno of acknowledgeable packet recorded in @av_buf * @av_tail_ackno: lowest seqno of acknowledgeable packet recorded in @av_buf * @av_buf_nonce: ECN nonce sums, each covering subsequent segments of up to * %DCCP_SINGLE_OPT_MAXLEN cells in the live portion of @av_buf * @av_overflow: if 1 then buf_head == buf_tail indicates buffer wraparound * @av_records: list of %dccp_ackvec_record (Ack Vectors sent previously) */ struct dccp_ackvec { u8 av_buf[DCCPAV_MAX_ACKVEC_LEN]; u16 av_buf_head; u16 av_buf_tail; u64 av_buf_ackno:48; u64 av_tail_ackno:48; bool av_buf_nonce[DCCPAV_NUM_ACKVECS]; u8 av_overflow:1; struct list_head av_records; }; /** * struct dccp_ackvec_record - Records information about sent Ack Vectors * * These list entries define the additional information which the HC-Receiver * keeps about recently-sent Ack Vectors; again refer to RFC 4340, Appendix A. * * @avr_node: the list node in @av_records * @avr_ack_seqno: sequence number of the packet the Ack Vector was sent on * @avr_ack_ackno: the Ack number that this record/Ack Vector refers to * @avr_ack_ptr: pointer into @av_buf where this record starts * @avr_ack_runlen: run length of @avr_ack_ptr at the time of sending * @avr_ack_nonce: the sum of @av_buf_nonce's at the time this record was sent * * The list as a whole is sorted in descending order by @avr_ack_seqno. */ struct dccp_ackvec_record { struct list_head avr_node; u64 avr_ack_seqno:48; u64 avr_ack_ackno:48; u16 avr_ack_ptr; u8 avr_ack_runlen; u8 avr_ack_nonce:1; }; int dccp_ackvec_init(void); void dccp_ackvec_exit(void); struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority); void dccp_ackvec_free(struct dccp_ackvec *av); void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb); int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seq, u8 sum); void dccp_ackvec_clear_state(struct dccp_ackvec *av, const u64 ackno); u16 dccp_ackvec_buflen(const struct dccp_ackvec *av); static inline bool dccp_ackvec_is_empty(const struct dccp_ackvec *av) { return av->av_overflow == 0 && av->av_buf_head == av->av_buf_tail; } /** * struct dccp_ackvec_parsed - Record offsets of Ack Vectors in skb * @vec: start of vector (offset into skb) * @len: length of @vec * @nonce: whether @vec had an ECN nonce of 0 or 1 * @node: FIFO - arranged in descending order of ack_ackno * * This structure is used by CCIDs to access Ack Vectors in a received skb. */ struct dccp_ackvec_parsed { u8 *vec, len, nonce:1; struct list_head node; }; int dccp_ackvec_parsed_add(struct list_head *head, u8 *vec, u8 len, u8 nonce); void dccp_ackvec_parsed_cleanup(struct list_head *parsed_chunks); #endif /* _ACKVEC_H */ |
| 3 6 6 6 6 6 4 4 4 4 4 4 4 4 4 2 2 1 3 3 3 3 3 3 3 3 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_fib.h> #include <net/inet_dscp.h> #include <net/ip_fib.h> #include <net/route.h> /* don't try to find route from mcast/bcast/zeronet */ static __be32 get_saddr(__be32 addr) { if (ipv4_is_multicast(addr) || ipv4_is_lbcast(addr) || ipv4_is_zeronet(addr)) return 0; return addr; } void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_fib *priv = nft_expr_priv(expr); int noff = skb_network_offset(pkt->skb); u32 *dst = ®s->data[priv->dreg]; const struct net_device *dev = NULL; struct iphdr *iph, _iph; __be32 addr; if (priv->flags & NFTA_FIB_F_IIF) dev = nft_in(pkt); else if (priv->flags & NFTA_FIB_F_OIF) dev = nft_out(pkt); iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph); if (!iph) { regs->verdict.code = NFT_BREAK; return; } if (priv->flags & NFTA_FIB_F_DADDR) addr = iph->daddr; else addr = iph->saddr; *dst = inet_dev_addr_type(nft_net(pkt), dev, addr); } EXPORT_SYMBOL_GPL(nft_fib4_eval_type); void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_fib *priv = nft_expr_priv(expr); int noff = skb_network_offset(pkt->skb); u32 *dest = ®s->data[priv->dreg]; struct iphdr *iph, _iph; struct fib_result res; struct flowi4 fl4 = { .flowi4_scope = RT_SCOPE_UNIVERSE, .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_uid = sock_net_uid(nft_net(pkt), NULL), .flowi4_l3mdev = l3mdev_master_ifindex_rcu(nft_in(pkt)), }; const struct net_device *oif; const struct net_device *found; /* * Do not set flowi4_oif, it restricts results (for example, asking * for oif 3 will get RTN_UNICAST result even if the daddr exits * on another interface. * * Search results for the desired outinterface instead. */ if (priv->flags & NFTA_FIB_F_OIF) oif = nft_out(pkt); else if (priv->flags & NFTA_FIB_F_IIF) oif = nft_in(pkt); else oif = NULL; if (nft_hook(pkt) == NF_INET_PRE_ROUTING && nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { nft_fib_store_result(dest, priv, nft_in(pkt)); return; } iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph); if (!iph) { regs->verdict.code = NFT_BREAK; return; } if (ipv4_is_zeronet(iph->saddr)) { if (ipv4_is_lbcast(iph->daddr) || ipv4_is_local_multicast(iph->daddr)) { nft_fib_store_result(dest, priv, pkt->skb->dev); return; } } if (priv->flags & NFTA_FIB_F_MARK) fl4.flowi4_mark = pkt->skb->mark; fl4.flowi4_tos = iph->tos & INET_DSCP_MASK; if (priv->flags & NFTA_FIB_F_DADDR) { fl4.daddr = iph->daddr; fl4.saddr = get_saddr(iph->saddr); } else { if (nft_hook(pkt) == NF_INET_FORWARD && priv->flags & NFTA_FIB_F_IIF) fl4.flowi4_iif = nft_out(pkt)->ifindex; fl4.daddr = iph->saddr; fl4.saddr = get_saddr(iph->daddr); } *dest = 0; if (fib_lookup(nft_net(pkt), &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE)) return; switch (res.type) { case RTN_UNICAST: break; case RTN_LOCAL: /* Should not see RTN_LOCAL here */ return; default: break; } if (!oif) { found = FIB_RES_DEV(res); } else { if (!fib_info_nh_uses_dev(res.fi, oif)) return; found = oif; } nft_fib_store_result(dest, priv, found); } EXPORT_SYMBOL_GPL(nft_fib4_eval); static struct nft_expr_type nft_fib4_type; static const struct nft_expr_ops nft_fib4_type_ops = { .type = &nft_fib4_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), .eval = nft_fib4_eval_type, .init = nft_fib_init, .dump = nft_fib_dump, .validate = nft_fib_validate, .reduce = nft_fib_reduce, }; static const struct nft_expr_ops nft_fib4_ops = { .type = &nft_fib4_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), .eval = nft_fib4_eval, .init = nft_fib_init, .dump = nft_fib_dump, .validate = nft_fib_validate, .reduce = nft_fib_reduce, }; static const struct nft_expr_ops * nft_fib4_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { enum nft_fib_result result; if (!tb[NFTA_FIB_RESULT]) return ERR_PTR(-EINVAL); result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT])); switch (result) { case NFT_FIB_RESULT_OIF: return &nft_fib4_ops; case NFT_FIB_RESULT_OIFNAME: return &nft_fib4_ops; case NFT_FIB_RESULT_ADDRTYPE: return &nft_fib4_type_ops; default: return ERR_PTR(-EOPNOTSUPP); } } static struct nft_expr_type nft_fib4_type __read_mostly = { .name = "fib", .select_ops = nft_fib4_select_ops, .policy = nft_fib_policy, .maxattr = NFTA_FIB_MAX, .family = NFPROTO_IPV4, .owner = THIS_MODULE, }; static int __init nft_fib4_module_init(void) { return nft_register_expr(&nft_fib4_type); } static void __exit nft_fib4_module_exit(void) { nft_unregister_expr(&nft_fib4_type); } module_init(nft_fib4_module_init); module_exit(nft_fib4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_ALIAS_NFT_AF_EXPR(2, "fib"); MODULE_DESCRIPTION("nftables fib / ip route lookup support"); |
| 3 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * fs/f2fs/f2fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ */ #ifndef _LINUX_F2FS_H #define _LINUX_F2FS_H #include <linux/uio.h> #include <linux/types.h> #include <linux/page-flags.h> #include <linux/slab.h> #include <linux/crc32.h> #include <linux/magic.h> #include <linux/kobject.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/sched/mm.h> #include <linux/vmalloc.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/quotaops.h> #include <linux/part_stat.h> #include <linux/rw_hint.h> #include <crypto/hash.h> #include <linux/fscrypt.h> #include <linux/fsverity.h> struct pagevec; #ifdef CONFIG_F2FS_CHECK_FS #define f2fs_bug_on(sbi, condition) BUG_ON(condition) #else #define f2fs_bug_on(sbi, condition) \ do { \ if (WARN_ON(condition)) \ set_sbi_flag(sbi, SBI_NEED_FSCK); \ } while (0) #endif enum { FAULT_KMALLOC, FAULT_KVMALLOC, FAULT_PAGE_ALLOC, FAULT_PAGE_GET, FAULT_ALLOC_BIO, /* it's obsolete due to bio_alloc() will never fail */ FAULT_ALLOC_NID, FAULT_ORPHAN, FAULT_BLOCK, FAULT_DIR_DEPTH, FAULT_EVICT_INODE, FAULT_TRUNCATE, FAULT_READ_IO, FAULT_CHECKPOINT, FAULT_DISCARD, FAULT_WRITE_IO, FAULT_SLAB_ALLOC, FAULT_DQUOT_INIT, FAULT_LOCK_OP, FAULT_BLKADDR_VALIDITY, FAULT_BLKADDR_CONSISTENCE, FAULT_NO_SEGMENT, FAULT_MAX, }; #ifdef CONFIG_F2FS_FAULT_INJECTION #define F2FS_ALL_FAULT_TYPE (GENMASK(FAULT_MAX - 1, 0)) struct f2fs_fault_info { atomic_t inject_ops; int inject_rate; unsigned int inject_type; }; extern const char *f2fs_fault_name[FAULT_MAX]; #define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type)) /* maximum retry count for injected failure */ #define DEFAULT_FAILURE_RETRY_COUNT 8 #else #define DEFAULT_FAILURE_RETRY_COUNT 1 #endif /* * For mount options */ #define F2FS_MOUNT_DISABLE_ROLL_FORWARD 0x00000001 #define F2FS_MOUNT_DISCARD 0x00000002 #define F2FS_MOUNT_NOHEAP 0x00000004 #define F2FS_MOUNT_XATTR_USER 0x00000008 #define F2FS_MOUNT_POSIX_ACL 0x00000010 #define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000020 #define F2FS_MOUNT_INLINE_XATTR 0x00000040 #define F2FS_MOUNT_INLINE_DATA 0x00000080 #define F2FS_MOUNT_INLINE_DENTRY 0x00000100 #define F2FS_MOUNT_FLUSH_MERGE 0x00000200 #define F2FS_MOUNT_NOBARRIER 0x00000400 #define F2FS_MOUNT_FASTBOOT 0x00000800 #define F2FS_MOUNT_READ_EXTENT_CACHE 0x00001000 #define F2FS_MOUNT_DATA_FLUSH 0x00002000 #define F2FS_MOUNT_FAULT_INJECTION 0x00004000 #define F2FS_MOUNT_USRQUOTA 0x00008000 #define F2FS_MOUNT_GRPQUOTA 0x00010000 #define F2FS_MOUNT_PRJQUOTA 0x00020000 #define F2FS_MOUNT_QUOTA 0x00040000 #define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00080000 #define F2FS_MOUNT_RESERVE_ROOT 0x00100000 #define F2FS_MOUNT_DISABLE_CHECKPOINT 0x00200000 #define F2FS_MOUNT_NORECOVERY 0x00400000 #define F2FS_MOUNT_ATGC 0x00800000 #define F2FS_MOUNT_MERGE_CHECKPOINT 0x01000000 #define F2FS_MOUNT_GC_MERGE 0x02000000 #define F2FS_MOUNT_COMPRESS_CACHE 0x04000000 #define F2FS_MOUNT_AGE_EXTENT_CACHE 0x08000000 #define F2FS_OPTION(sbi) ((sbi)->mount_opt) #define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) #define set_opt(sbi, option) (F2FS_OPTION(sbi).opt |= F2FS_MOUNT_##option) #define test_opt(sbi, option) (F2FS_OPTION(sbi).opt & F2FS_MOUNT_##option) #define ver_after(a, b) (typecheck(unsigned long long, a) && \ typecheck(unsigned long long, b) && \ ((long long)((a) - (b)) > 0)) typedef u32 block_t; /* * should not change u32, since it is the on-disk block * address format, __le32. */ typedef u32 nid_t; #define COMPRESS_EXT_NUM 16 enum blkzone_allocation_policy { BLKZONE_ALLOC_PRIOR_SEQ, /* Prioritize writing to sequential zones */ BLKZONE_ALLOC_ONLY_SEQ, /* Only allow writing to sequential zones */ BLKZONE_ALLOC_PRIOR_CONV, /* Prioritize writing to conventional zones */ }; /* * An implementation of an rwsem that is explicitly unfair to readers. This * prevents priority inversion when a low-priority reader acquires the read lock * while sleeping on the write lock but the write lock is needed by * higher-priority clients. */ struct f2fs_rwsem { struct rw_semaphore internal_rwsem; #ifdef CONFIG_F2FS_UNFAIR_RWSEM wait_queue_head_t read_waiters; #endif }; struct f2fs_mount_info { unsigned int opt; block_t root_reserved_blocks; /* root reserved blocks */ kuid_t s_resuid; /* reserved blocks for uid */ kgid_t s_resgid; /* reserved blocks for gid */ int active_logs; /* # of active logs */ int inline_xattr_size; /* inline xattr size */ #ifdef CONFIG_F2FS_FAULT_INJECTION struct f2fs_fault_info fault_info; /* For fault injection */ #endif #ifdef CONFIG_QUOTA /* Names of quota files with journalled quota */ char *s_qf_names[MAXQUOTAS]; int s_jquota_fmt; /* Format of quota to use */ #endif /* For which write hints are passed down to block layer */ int alloc_mode; /* segment allocation policy */ int fsync_mode; /* fsync policy */ int fs_mode; /* fs mode: LFS or ADAPTIVE */ int bggc_mode; /* bggc mode: off, on or sync */ int memory_mode; /* memory mode */ int errors; /* errors parameter */ int discard_unit; /* * discard command's offset/size should * be aligned to this unit: block, * segment or section */ struct fscrypt_dummy_policy dummy_enc_policy; /* test dummy encryption */ block_t unusable_cap_perc; /* percentage for cap */ block_t unusable_cap; /* Amount of space allowed to be * unusable when disabling checkpoint */ /* For compression */ unsigned char compress_algorithm; /* algorithm type */ unsigned char compress_log_size; /* cluster log size */ unsigned char compress_level; /* compress level */ bool compress_chksum; /* compressed data chksum */ unsigned char compress_ext_cnt; /* extension count */ unsigned char nocompress_ext_cnt; /* nocompress extension count */ int compress_mode; /* compression mode */ unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */ unsigned char noextensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */ }; #define F2FS_FEATURE_ENCRYPT 0x00000001 #define F2FS_FEATURE_BLKZONED 0x00000002 #define F2FS_FEATURE_ATOMIC_WRITE 0x00000004 #define F2FS_FEATURE_EXTRA_ATTR 0x00000008 #define F2FS_FEATURE_PRJQUOTA 0x00000010 #define F2FS_FEATURE_INODE_CHKSUM 0x00000020 #define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR 0x00000040 #define F2FS_FEATURE_QUOTA_INO 0x00000080 #define F2FS_FEATURE_INODE_CRTIME 0x00000100 #define F2FS_FEATURE_LOST_FOUND 0x00000200 #define F2FS_FEATURE_VERITY 0x00000400 #define F2FS_FEATURE_SB_CHKSUM 0x00000800 #define F2FS_FEATURE_CASEFOLD 0x00001000 #define F2FS_FEATURE_COMPRESSION 0x00002000 #define F2FS_FEATURE_RO 0x00004000 #define __F2FS_HAS_FEATURE(raw_super, mask) \ ((raw_super->feature & cpu_to_le32(mask)) != 0) #define F2FS_HAS_FEATURE(sbi, mask) __F2FS_HAS_FEATURE(sbi->raw_super, mask) /* * Default values for user and/or group using reserved blocks */ #define F2FS_DEF_RESUID 0 #define F2FS_DEF_RESGID 0 /* * For checkpoint manager */ enum { NAT_BITMAP, SIT_BITMAP }; #define CP_UMOUNT 0x00000001 #define CP_FASTBOOT 0x00000002 #define CP_SYNC 0x00000004 #define CP_RECOVERY 0x00000008 #define CP_DISCARD 0x00000010 #define CP_TRIMMED 0x00000020 #define CP_PAUSE 0x00000040 #define CP_RESIZE 0x00000080 #define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */ #define DEF_MIN_DISCARD_ISSUE_TIME 50 /* 50 ms, if exists */ #define DEF_MID_DISCARD_ISSUE_TIME 500 /* 500 ms, if device busy */ #define DEF_MAX_DISCARD_ISSUE_TIME 60000 /* 60 s, if no candidates */ #define DEF_DISCARD_URGENT_UTIL 80 /* do more discard over 80% */ #define DEF_CP_INTERVAL 60 /* 60 secs */ #define DEF_IDLE_INTERVAL 5 /* 5 secs */ #define DEF_DISABLE_INTERVAL 5 /* 5 secs */ #define DEF_DISABLE_QUICK_INTERVAL 1 /* 1 secs */ #define DEF_UMOUNT_DISCARD_TIMEOUT 5 /* 5 secs */ struct cp_control { int reason; __u64 trim_start; __u64 trim_end; __u64 trim_minlen; }; /* * indicate meta/data type */ enum { META_CP, META_NAT, META_SIT, META_SSA, META_MAX, META_POR, DATA_GENERIC, /* check range only */ DATA_GENERIC_ENHANCE, /* strong check on range and segment bitmap */ DATA_GENERIC_ENHANCE_READ, /* * strong check on range and segment * bitmap but no warning due to race * condition of read on truncated area * by extent_cache */ DATA_GENERIC_ENHANCE_UPDATE, /* * strong check on range and segment * bitmap for update case */ META_GENERIC, }; /* for the list of ino */ enum { ORPHAN_INO, /* for orphan ino list */ APPEND_INO, /* for append ino list */ UPDATE_INO, /* for update ino list */ TRANS_DIR_INO, /* for transactions dir ino list */ XATTR_DIR_INO, /* for xattr updated dir ino list */ FLUSH_INO, /* for multiple device flushing */ MAX_INO_ENTRY, /* max. list */ }; struct ino_entry { struct list_head list; /* list head */ nid_t ino; /* inode number */ unsigned int dirty_device; /* dirty device bitmap */ }; /* for the list of inodes to be GCed */ struct inode_entry { struct list_head list; /* list head */ struct inode *inode; /* vfs inode pointer */ }; struct fsync_node_entry { struct list_head list; /* list head */ struct page *page; /* warm node page pointer */ unsigned int seq_id; /* sequence id */ }; struct ckpt_req { struct completion wait; /* completion for checkpoint done */ struct llist_node llnode; /* llist_node to be linked in wait queue */ int ret; /* return code of checkpoint */ ktime_t queue_time; /* request queued time */ }; struct ckpt_req_control { struct task_struct *f2fs_issue_ckpt; /* checkpoint task */ int ckpt_thread_ioprio; /* checkpoint merge thread ioprio */ wait_queue_head_t ckpt_wait_queue; /* waiting queue for wake-up */ atomic_t issued_ckpt; /* # of actually issued ckpts */ atomic_t total_ckpt; /* # of total ckpts */ atomic_t queued_ckpt; /* # of queued ckpts */ struct llist_head issue_list; /* list for command issue */ spinlock_t stat_lock; /* lock for below checkpoint time stats */ unsigned int cur_time; /* cur wait time in msec for currently issued checkpoint */ unsigned int peak_time; /* peak wait time in msec until now */ }; /* for the bitmap indicate blocks to be discarded */ struct discard_entry { struct list_head list; /* list head */ block_t start_blkaddr; /* start blockaddr of current segment */ unsigned char discard_map[SIT_VBLOCK_MAP_SIZE]; /* segment discard bitmap */ }; /* minimum discard granularity, unit: block count */ #define MIN_DISCARD_GRANULARITY 1 /* default discard granularity of inner discard thread, unit: block count */ #define DEFAULT_DISCARD_GRANULARITY 16 /* default maximum discard granularity of ordered discard, unit: block count */ #define DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY 16 /* max discard pend list number */ #define MAX_PLIST_NUM 512 #define plist_idx(blk_num) ((blk_num) >= MAX_PLIST_NUM ? \ (MAX_PLIST_NUM - 1) : ((blk_num) - 1)) enum { D_PREP, /* initial */ D_PARTIAL, /* partially submitted */ D_SUBMIT, /* all submitted */ D_DONE, /* finished */ }; struct discard_info { block_t lstart; /* logical start address */ block_t len; /* length */ block_t start; /* actual start address in dev */ }; struct discard_cmd { struct rb_node rb_node; /* rb node located in rb-tree */ struct discard_info di; /* discard info */ struct list_head list; /* command list */ struct completion wait; /* compleation */ struct block_device *bdev; /* bdev */ unsigned short ref; /* reference count */ unsigned char state; /* state */ unsigned char queued; /* queued discard */ int error; /* bio error */ spinlock_t lock; /* for state/bio_ref updating */ unsigned short bio_ref; /* bio reference count */ }; enum { DPOLICY_BG, DPOLICY_FORCE, DPOLICY_FSTRIM, DPOLICY_UMOUNT, MAX_DPOLICY, }; enum { DPOLICY_IO_AWARE_DISABLE, /* force to not be aware of IO */ DPOLICY_IO_AWARE_ENABLE, /* force to be aware of IO */ DPOLICY_IO_AWARE_MAX, }; struct discard_policy { int type; /* type of discard */ unsigned int min_interval; /* used for candidates exist */ unsigned int mid_interval; /* used for device busy */ unsigned int max_interval; /* used for candidates not exist */ unsigned int max_requests; /* # of discards issued per round */ unsigned int io_aware_gran; /* minimum granularity discard not be aware of I/O */ bool io_aware; /* issue discard in idle time */ bool sync; /* submit discard with REQ_SYNC flag */ bool ordered; /* issue discard by lba order */ bool timeout; /* discard timeout for put_super */ unsigned int granularity; /* discard granularity */ }; struct discard_cmd_control { struct task_struct *f2fs_issue_discard; /* discard thread */ struct list_head entry_list; /* 4KB discard entry list */ struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */ struct list_head wait_list; /* store on-flushing entries */ struct list_head fstrim_list; /* in-flight discard from fstrim */ wait_queue_head_t discard_wait_queue; /* waiting queue for wake-up */ struct mutex cmd_lock; unsigned int nr_discards; /* # of discards in the list */ unsigned int max_discards; /* max. discards to be issued */ unsigned int max_discard_request; /* max. discard request per round */ unsigned int min_discard_issue_time; /* min. interval between discard issue */ unsigned int mid_discard_issue_time; /* mid. interval between discard issue */ unsigned int max_discard_issue_time; /* max. interval between discard issue */ unsigned int discard_io_aware_gran; /* minimum discard granularity not be aware of I/O */ unsigned int discard_urgent_util; /* utilization which issue discard proactively */ unsigned int discard_granularity; /* discard granularity */ unsigned int max_ordered_discard; /* maximum discard granularity issued by lba order */ unsigned int discard_io_aware; /* io_aware policy */ unsigned int undiscard_blks; /* # of undiscard blocks */ unsigned int next_pos; /* next discard position */ atomic_t issued_discard; /* # of issued discard */ atomic_t queued_discard; /* # of queued discard */ atomic_t discard_cmd_cnt; /* # of cached cmd count */ struct rb_root_cached root; /* root of discard rb-tree */ bool rbtree_check; /* config for consistence check */ bool discard_wake; /* to wake up discard thread */ }; /* for the list of fsync inodes, used only during recovery */ struct fsync_inode_entry { struct list_head list; /* list head */ struct inode *inode; /* vfs inode pointer */ block_t blkaddr; /* block address locating the last fsync */ block_t last_dentry; /* block address locating the last dentry */ }; #define nats_in_cursum(jnl) (le16_to_cpu((jnl)->n_nats)) #define sits_in_cursum(jnl) (le16_to_cpu((jnl)->n_sits)) #define nat_in_journal(jnl, i) ((jnl)->nat_j.entries[i].ne) #define nid_in_journal(jnl, i) ((jnl)->nat_j.entries[i].nid) #define sit_in_journal(jnl, i) ((jnl)->sit_j.entries[i].se) #define segno_in_journal(jnl, i) ((jnl)->sit_j.entries[i].segno) #define MAX_NAT_JENTRIES(jnl) (NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl)) #define MAX_SIT_JENTRIES(jnl) (SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl)) static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i) { int before = nats_in_cursum(journal); journal->n_nats = cpu_to_le16(before + i); return before; } static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i) { int before = sits_in_cursum(journal); journal->n_sits = cpu_to_le16(before + i); return before; } static inline bool __has_cursum_space(struct f2fs_journal *journal, int size, int type) { if (type == NAT_JOURNAL) return size <= MAX_NAT_JENTRIES(journal); return size <= MAX_SIT_JENTRIES(journal); } /* for inline stuff */ #define DEF_INLINE_RESERVED_SIZE 1 static inline int get_extra_isize(struct inode *inode); static inline int get_inline_xattr_addrs(struct inode *inode); #define MAX_INLINE_DATA(inode) (sizeof(__le32) * \ (CUR_ADDRS_PER_INODE(inode) - \ get_inline_xattr_addrs(inode) - \ DEF_INLINE_RESERVED_SIZE)) /* for inline dir */ #define NR_INLINE_DENTRY(inode) (MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \ ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ BITS_PER_BYTE + 1)) #define INLINE_DENTRY_BITMAP_SIZE(inode) \ DIV_ROUND_UP(NR_INLINE_DENTRY(inode), BITS_PER_BYTE) #define INLINE_RESERVED_SIZE(inode) (MAX_INLINE_DATA(inode) - \ ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ NR_INLINE_DENTRY(inode) + \ INLINE_DENTRY_BITMAP_SIZE(inode))) /* * For INODE and NODE manager */ /* for directory operations */ struct f2fs_filename { /* * The filename the user specified. This is NULL for some * filesystem-internal operations, e.g. converting an inline directory * to a non-inline one, or roll-forward recovering an encrypted dentry. */ const struct qstr *usr_fname; /* * The on-disk filename. For encrypted directories, this is encrypted. * This may be NULL for lookups in an encrypted dir without the key. */ struct fscrypt_str disk_name; /* The dirhash of this filename */ f2fs_hash_t hash; #ifdef CONFIG_FS_ENCRYPTION /* * For lookups in encrypted directories: either the buffer backing * disk_name, or a buffer that holds the decoded no-key name. */ struct fscrypt_str crypto_buf; #endif #if IS_ENABLED(CONFIG_UNICODE) /* * For casefolded directories: the casefolded name, but it's left NULL * if the original name is not valid Unicode, if the original name is * "." or "..", if the directory is both casefolded and encrypted and * its encryption key is unavailable, or if the filesystem is doing an * internal operation where usr_fname is also NULL. In all these cases * we fall back to treating the name as an opaque byte sequence. */ struct qstr cf_name; #endif }; struct f2fs_dentry_ptr { struct inode *inode; void *bitmap; struct f2fs_dir_entry *dentry; __u8 (*filename)[F2FS_SLOT_LEN]; int max; int nr_bitmap; }; static inline void make_dentry_ptr_block(struct inode *inode, struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t) { d->inode = inode; d->max = NR_DENTRY_IN_BLOCK; d->nr_bitmap = SIZE_OF_DENTRY_BITMAP; d->bitmap = t->dentry_bitmap; d->dentry = t->dentry; d->filename = t->filename; } static inline void make_dentry_ptr_inline(struct inode *inode, struct f2fs_dentry_ptr *d, void *t) { int entry_cnt = NR_INLINE_DENTRY(inode); int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode); int reserved_size = INLINE_RESERVED_SIZE(inode); d->inode = inode; d->max = entry_cnt; d->nr_bitmap = bitmap_size; d->bitmap = t; d->dentry = t + bitmap_size + reserved_size; d->filename = t + bitmap_size + reserved_size + SIZE_OF_DIR_ENTRY * entry_cnt; } /* * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1 * as its node offset to distinguish from index node blocks. * But some bits are used to mark the node block. */ #define XATTR_NODE_OFFSET ((((unsigned int)-1) << OFFSET_BIT_SHIFT) \ >> OFFSET_BIT_SHIFT) enum { ALLOC_NODE, /* allocate a new node page if needed */ LOOKUP_NODE, /* look up a node without readahead */ LOOKUP_NODE_RA, /* * look up a node with readahead called * by get_data_block. */ }; #define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO or flush count */ /* congestion wait timeout value, default: 20ms */ #define DEFAULT_IO_TIMEOUT (msecs_to_jiffies(20)) /* maximum retry quota flush count */ #define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8 /* maximum retry of EIO'ed page */ #define MAX_RETRY_PAGE_EIO 100 #define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */ #define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ /* dirty segments threshold for triggering CP */ #define DEFAULT_DIRTY_THRESHOLD 4 #define RECOVERY_MAX_RA_BLOCKS BIO_MAX_VECS #define RECOVERY_MIN_RA_BLOCKS 1 #define F2FS_ONSTACK_PAGES 16 /* nr of onstack pages */ /* for in-memory extent cache entry */ #define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */ /* number of extent info in extent cache we try to shrink */ #define READ_EXTENT_CACHE_SHRINK_NUMBER 128 /* number of age extent info in extent cache we try to shrink */ #define AGE_EXTENT_CACHE_SHRINK_NUMBER 128 #define LAST_AGE_WEIGHT 30 #define SAME_AGE_REGION 1024 /* * Define data block with age less than 1GB as hot data * define data block with age less than 10GB but more than 1GB as warm data */ #define DEF_HOT_DATA_AGE_THRESHOLD 262144 #define DEF_WARM_DATA_AGE_THRESHOLD 2621440 /* extent cache type */ enum extent_type { EX_READ, EX_BLOCK_AGE, NR_EXTENT_CACHES, }; struct extent_info { unsigned int fofs; /* start offset in a file */ unsigned int len; /* length of the extent */ union { /* read extent_cache */ struct { /* start block address of the extent */ block_t blk; #ifdef CONFIG_F2FS_FS_COMPRESSION /* physical extent length of compressed blocks */ unsigned int c_len; #endif }; /* block age extent_cache */ struct { /* block age of the extent */ unsigned long long age; /* last total blocks allocated */ unsigned long long last_blocks; }; }; }; struct extent_node { struct rb_node rb_node; /* rb node located in rb-tree */ struct extent_info ei; /* extent info */ struct list_head list; /* node in global extent list of sbi */ struct extent_tree *et; /* extent tree pointer */ }; struct extent_tree { nid_t ino; /* inode number */ enum extent_type type; /* keep the extent tree type */ struct rb_root_cached root; /* root of extent info rb-tree */ struct extent_node *cached_en; /* recently accessed extent node */ struct list_head list; /* to be used by sbi->zombie_list */ rwlock_t lock; /* protect extent info rb-tree */ atomic_t node_cnt; /* # of extent node in rb-tree*/ bool largest_updated; /* largest extent updated */ struct extent_info largest; /* largest cached extent for EX_READ */ }; struct extent_tree_info { struct radix_tree_root extent_tree_root;/* cache extent cache entries */ struct mutex extent_tree_lock; /* locking extent radix tree */ struct list_head extent_list; /* lru list for shrinker */ spinlock_t extent_lock; /* locking extent lru list */ atomic_t total_ext_tree; /* extent tree count */ struct list_head zombie_list; /* extent zombie tree list */ atomic_t total_zombie_tree; /* extent zombie tree count */ atomic_t total_ext_node; /* extent info count */ }; /* * State of block returned by f2fs_map_blocks. */ #define F2FS_MAP_NEW (1U << 0) #define F2FS_MAP_MAPPED (1U << 1) #define F2FS_MAP_DELALLOC (1U << 2) #define F2FS_MAP_FLAGS (F2FS_MAP_NEW | F2FS_MAP_MAPPED |\ F2FS_MAP_DELALLOC) struct f2fs_map_blocks { struct block_device *m_bdev; /* for multi-device dio */ block_t m_pblk; block_t m_lblk; unsigned int m_len; unsigned int m_flags; pgoff_t *m_next_pgofs; /* point next possible non-hole pgofs */ pgoff_t *m_next_extent; /* point to next possible extent */ int m_seg_type; bool m_may_create; /* indicate it is from write path */ bool m_multidev_dio; /* indicate it allows multi-device dio */ }; /* for flag in get_data_block */ enum { F2FS_GET_BLOCK_DEFAULT, F2FS_GET_BLOCK_FIEMAP, F2FS_GET_BLOCK_BMAP, F2FS_GET_BLOCK_DIO, F2FS_GET_BLOCK_PRE_DIO, F2FS_GET_BLOCK_PRE_AIO, F2FS_GET_BLOCK_PRECACHE, }; /* * i_advise uses FADVISE_XXX_BIT. We can add additional hints later. */ #define FADVISE_COLD_BIT 0x01 #define FADVISE_LOST_PINO_BIT 0x02 #define FADVISE_ENCRYPT_BIT 0x04 #define FADVISE_ENC_NAME_BIT 0x08 #define FADVISE_KEEP_SIZE_BIT 0x10 #define FADVISE_HOT_BIT 0x20 #define FADVISE_VERITY_BIT 0x40 #define FADVISE_TRUNC_BIT 0x80 #define FADVISE_MODIFIABLE_BITS (FADVISE_COLD_BIT | FADVISE_HOT_BIT) #define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) #define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT) #define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT) #define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) #define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT) #define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT) #define file_is_encrypt(inode) is_file(inode, FADVISE_ENCRYPT_BIT) #define file_set_encrypt(inode) set_file(inode, FADVISE_ENCRYPT_BIT) #define file_enc_name(inode) is_file(inode, FADVISE_ENC_NAME_BIT) #define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT) #define file_keep_isize(inode) is_file(inode, FADVISE_KEEP_SIZE_BIT) #define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT) #define file_is_hot(inode) is_file(inode, FADVISE_HOT_BIT) #define file_set_hot(inode) set_file(inode, FADVISE_HOT_BIT) #define file_clear_hot(inode) clear_file(inode, FADVISE_HOT_BIT) #define file_is_verity(inode) is_file(inode, FADVISE_VERITY_BIT) #define file_set_verity(inode) set_file(inode, FADVISE_VERITY_BIT) #define file_should_truncate(inode) is_file(inode, FADVISE_TRUNC_BIT) #define file_need_truncate(inode) set_file(inode, FADVISE_TRUNC_BIT) #define file_dont_truncate(inode) clear_file(inode, FADVISE_TRUNC_BIT) #define DEF_DIR_LEVEL 0 /* used for f2fs_inode_info->flags */ enum { FI_NEW_INODE, /* indicate newly allocated inode */ FI_DIRTY_INODE, /* indicate inode is dirty or not */ FI_AUTO_RECOVER, /* indicate inode is recoverable */ FI_DIRTY_DIR, /* indicate directory has dirty pages */ FI_INC_LINK, /* need to increment i_nlink */ FI_ACL_MODE, /* indicate acl mode */ FI_NO_ALLOC, /* should not allocate any blocks */ FI_FREE_NID, /* free allocated nide */ FI_NO_EXTENT, /* not to use the extent cache */ FI_INLINE_XATTR, /* used for inline xattr */ FI_INLINE_DATA, /* used for inline data*/ FI_INLINE_DENTRY, /* used for inline dentry */ FI_APPEND_WRITE, /* inode has appended data */ FI_UPDATE_WRITE, /* inode has in-place-update data */ FI_NEED_IPU, /* used for ipu per file */ FI_ATOMIC_FILE, /* indicate atomic file */ FI_DATA_EXIST, /* indicate data exists */ FI_SKIP_WRITES, /* should skip data page writeback */ FI_OPU_WRITE, /* used for opu per file */ FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ FI_PREALLOCATED_ALL, /* all blocks for write were preallocated */ FI_HOT_DATA, /* indicate file is hot */ FI_EXTRA_ATTR, /* indicate file has extra attribute */ FI_PROJ_INHERIT, /* indicate file inherits projectid */ FI_PIN_FILE, /* indicate file should not be gced */ FI_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */ FI_COMPRESSED_FILE, /* indicate file's data can be compressed */ FI_COMPRESS_CORRUPT, /* indicate compressed cluster is corrupted */ FI_MMAP_FILE, /* indicate file was mmapped */ FI_ENABLE_COMPRESS, /* enable compression in "user" compression mode */ FI_COMPRESS_RELEASED, /* compressed blocks were released */ FI_ALIGNED_WRITE, /* enable aligned write */ FI_COW_FILE, /* indicate COW file */ FI_ATOMIC_COMMITTED, /* indicate atomic commit completed except disk sync */ FI_ATOMIC_DIRTIED, /* indicate atomic file is dirtied */ FI_ATOMIC_REPLACE, /* indicate atomic replace */ FI_OPENED_FILE, /* indicate file has been opened */ FI_MAX, /* max flag, never be used */ }; struct f2fs_inode_info { struct inode vfs_inode; /* serve a vfs inode */ unsigned long i_flags; /* keep an inode flags for ioctl */ unsigned char i_advise; /* use to give file attribute hints */ unsigned char i_dir_level; /* use for dentry level for large dir */ union { unsigned int i_current_depth; /* only for directory depth */ unsigned short i_gc_failures; /* for gc failure statistic */ }; unsigned int i_pino; /* parent inode number */ umode_t i_acl_mode; /* keep file acl mode temporarily */ /* Use below internally in f2fs*/ unsigned long flags[BITS_TO_LONGS(FI_MAX)]; /* use to pass per-file flags */ struct f2fs_rwsem i_sem; /* protect fi info */ atomic_t dirty_pages; /* # of dirty pages */ f2fs_hash_t chash; /* hash value of given file name */ unsigned int clevel; /* maximum level of given file name */ struct task_struct *task; /* lookup and create consistency */ struct task_struct *cp_task; /* separate cp/wb IO stats*/ struct task_struct *wb_task; /* indicate inode is in context of writeback */ nid_t i_xattr_nid; /* node id that contains xattrs */ loff_t last_disk_size; /* lastly written file size */ spinlock_t i_size_lock; /* protect last_disk_size */ #ifdef CONFIG_QUOTA struct dquot __rcu *i_dquot[MAXQUOTAS]; /* quota space reservation, managed internally by quota code */ qsize_t i_reserved_quota; #endif struct list_head dirty_list; /* dirty list for dirs and files */ struct list_head gdirty_list; /* linked in global dirty list */ struct task_struct *atomic_write_task; /* store atomic write task */ struct extent_tree *extent_tree[NR_EXTENT_CACHES]; /* cached extent_tree entry */ union { struct inode *cow_inode; /* copy-on-write inode for atomic write */ struct inode *atomic_inode; /* point to atomic_inode, available only for cow_inode */ }; /* avoid racing between foreground op and gc */ struct f2fs_rwsem i_gc_rwsem[2]; struct f2fs_rwsem i_xattr_sem; /* avoid racing between reading and changing EAs */ int i_extra_isize; /* size of extra space located in i_addr */ kprojid_t i_projid; /* id for project quota */ int i_inline_xattr_size; /* inline xattr size */ struct timespec64 i_crtime; /* inode creation time */ struct timespec64 i_disk_time[3];/* inode disk times */ /* for file compress */ atomic_t i_compr_blocks; /* # of compressed blocks */ unsigned char i_compress_algorithm; /* algorithm type */ unsigned char i_log_cluster_size; /* log of cluster size */ unsigned char i_compress_level; /* compress level (lz4hc,zstd) */ unsigned char i_compress_flag; /* compress flag */ unsigned int i_cluster_size; /* cluster size */ unsigned int atomic_write_cnt; loff_t original_i_size; /* original i_size before atomic write */ }; static inline void get_read_extent_info(struct extent_info *ext, struct f2fs_extent *i_ext) { ext->fofs = le32_to_cpu(i_ext->fofs); ext->blk = le32_to_cpu(i_ext->blk); ext->len = le32_to_cpu(i_ext->len); } static inline void set_raw_read_extent(struct extent_info *ext, struct f2fs_extent *i_ext) { i_ext->fofs = cpu_to_le32(ext->fofs); i_ext->blk = cpu_to_le32(ext->blk); i_ext->len = cpu_to_le32(ext->len); } static inline bool __is_discard_mergeable(struct discard_info *back, struct discard_info *front, unsigned int max_len) { return (back->lstart + back->len == front->lstart) && (back->len + front->len <= max_len); } static inline bool __is_discard_back_mergeable(struct discard_info *cur, struct discard_info *back, unsigned int max_len) { return __is_discard_mergeable(back, cur, max_len); } static inline bool __is_discard_front_mergeable(struct discard_info *cur, struct discard_info *front, unsigned int max_len) { return __is_discard_mergeable(cur, front, max_len); } /* * For free nid management */ enum nid_state { FREE_NID, /* newly added to free nid list */ PREALLOC_NID, /* it is preallocated */ MAX_NID_STATE, }; enum nat_state { TOTAL_NAT, DIRTY_NAT, RECLAIMABLE_NAT, MAX_NAT_STATE, }; struct f2fs_nm_info { block_t nat_blkaddr; /* base disk address of NAT */ nid_t max_nid; /* maximum possible node ids */ nid_t available_nids; /* # of available node ids */ nid_t next_scan_nid; /* the next nid to be scanned */ nid_t max_rf_node_blocks; /* max # of nodes for recovery */ unsigned int ram_thresh; /* control the memory footprint */ unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */ unsigned int dirty_nats_ratio; /* control dirty nats ratio threshold */ /* NAT cache management */ struct radix_tree_root nat_root;/* root of the nat entry cache */ struct radix_tree_root nat_set_root;/* root of the nat set cache */ struct f2fs_rwsem nat_tree_lock; /* protect nat entry tree */ struct list_head nat_entries; /* cached nat entry list (clean) */ spinlock_t nat_list_lock; /* protect clean nat entry list */ unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */ unsigned int nat_blocks; /* # of nat blocks */ /* free node ids management */ struct radix_tree_root free_nid_root;/* root of the free_nid cache */ struct list_head free_nid_list; /* list for free nids excluding preallocated nids */ unsigned int nid_cnt[MAX_NID_STATE]; /* the number of free node id */ spinlock_t nid_list_lock; /* protect nid lists ops */ struct mutex build_lock; /* lock for build free nids */ unsigned char **free_nid_bitmap; unsigned char *nat_block_bitmap; unsigned short *free_nid_count; /* free nid count of NAT block */ /* for checkpoint */ char *nat_bitmap; /* NAT bitmap pointer */ unsigned int nat_bits_blocks; /* # of nat bits blocks */ unsigned char *nat_bits; /* NAT bits blocks */ unsigned char *full_nat_bits; /* full NAT pages */ unsigned char *empty_nat_bits; /* empty NAT pages */ #ifdef CONFIG_F2FS_CHECK_FS char *nat_bitmap_mir; /* NAT bitmap mirror */ #endif int bitmap_size; /* bitmap size */ }; /* * this structure is used as one of function parameters. * all the information are dedicated to a given direct node block determined * by the data offset in a file. */ struct dnode_of_data { struct inode *inode; /* vfs inode pointer */ struct page *inode_page; /* its inode page, NULL is possible */ struct page *node_page; /* cached direct node page */ nid_t nid; /* node id of the direct node block */ unsigned int ofs_in_node; /* data offset in the node page */ bool inode_page_locked; /* inode page is locked or not */ bool node_changed; /* is node block changed */ char cur_level; /* level of hole node page */ char max_level; /* level of current page located */ block_t data_blkaddr; /* block address of the node block */ }; static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode, struct page *ipage, struct page *npage, nid_t nid) { memset(dn, 0, sizeof(*dn)); dn->inode = inode; dn->inode_page = ipage; dn->node_page = npage; dn->nid = nid; } /* * For SIT manager * * By default, there are 6 active log areas across the whole main area. * When considering hot and cold data separation to reduce cleaning overhead, * we split 3 for data logs and 3 for node logs as hot, warm, and cold types, * respectively. * In the current design, you should not change the numbers intentionally. * Instead, as a mount option such as active_logs=x, you can use 2, 4, and 6 * logs individually according to the underlying devices. (default: 6) * Just in case, on-disk layout covers maximum 16 logs that consist of 8 for * data and 8 for node logs. */ #define NR_CURSEG_DATA_TYPE (3) #define NR_CURSEG_NODE_TYPE (3) #define NR_CURSEG_INMEM_TYPE (2) #define NR_CURSEG_RO_TYPE (2) #define NR_CURSEG_PERSIST_TYPE (NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE) #define NR_CURSEG_TYPE (NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE) enum { CURSEG_HOT_DATA = 0, /* directory entry blocks */ CURSEG_WARM_DATA, /* data blocks */ CURSEG_COLD_DATA, /* multimedia or GCed data blocks */ CURSEG_HOT_NODE, /* direct node blocks of directory files */ CURSEG_WARM_NODE, /* direct node blocks of normal files */ CURSEG_COLD_NODE, /* indirect node blocks */ NR_PERSISTENT_LOG, /* number of persistent log */ CURSEG_COLD_DATA_PINNED = NR_PERSISTENT_LOG, /* pinned file that needs consecutive block address */ CURSEG_ALL_DATA_ATGC, /* SSR alloctor in hot/warm/cold data area */ NO_CHECK_TYPE, /* number of persistent & inmem log */ }; struct flush_cmd { struct completion wait; struct llist_node llnode; nid_t ino; int ret; }; struct flush_cmd_control { struct task_struct *f2fs_issue_flush; /* flush thread */ wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */ atomic_t issued_flush; /* # of issued flushes */ atomic_t queued_flush; /* # of queued flushes */ struct llist_head issue_list; /* list for command issue */ struct llist_node *dispatch_list; /* list for command dispatch */ }; struct f2fs_sm_info { struct sit_info *sit_info; /* whole segment information */ struct free_segmap_info *free_info; /* free segment information */ struct dirty_seglist_info *dirty_info; /* dirty segment information */ struct curseg_info *curseg_array; /* active segment information */ struct f2fs_rwsem curseg_lock; /* for preventing curseg change */ block_t seg0_blkaddr; /* block address of 0'th segment */ block_t main_blkaddr; /* start block address of main area */ block_t ssa_blkaddr; /* start block address of SSA area */ unsigned int segment_count; /* total # of segments */ unsigned int main_segments; /* # of segments in main area */ unsigned int reserved_segments; /* # of reserved segments */ unsigned int additional_reserved_segments;/* reserved segs for IO align feature */ unsigned int ovp_segments; /* # of overprovision segments */ /* a threshold to reclaim prefree segments */ unsigned int rec_prefree_segments; struct list_head sit_entry_set; /* sit entry set list */ unsigned int ipu_policy; /* in-place-update policy */ unsigned int min_ipu_util; /* in-place-update threshold */ unsigned int min_fsync_blocks; /* threshold for fsync */ unsigned int min_seq_blocks; /* threshold for sequential blocks */ unsigned int min_hot_blocks; /* threshold for hot block allocation */ unsigned int min_ssr_sections; /* threshold to trigger SSR allocation */ /* for flush command control */ struct flush_cmd_control *fcc_info; /* for discard command control */ struct discard_cmd_control *dcc_info; }; /* * For superblock */ /* * COUNT_TYPE for monitoring * * f2fs monitors the number of several block types such as on-writeback, * dirty dentry blocks, dirty node blocks, and dirty meta blocks. */ #define WB_DATA_TYPE(p, f) \ (f || f2fs_is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) enum count_type { F2FS_DIRTY_DENTS, F2FS_DIRTY_DATA, F2FS_DIRTY_QDATA, F2FS_DIRTY_NODES, F2FS_DIRTY_META, F2FS_DIRTY_IMETA, F2FS_WB_CP_DATA, F2FS_WB_DATA, F2FS_RD_DATA, F2FS_RD_NODE, F2FS_RD_META, F2FS_DIO_WRITE, F2FS_DIO_READ, NR_COUNT_TYPE, }; /* * The below are the page types of bios used in submit_bio(). * The available types are: * DATA User data pages. It operates as async mode. * NODE Node pages. It operates as async mode. * META FS metadata pages such as SIT, NAT, CP. * NR_PAGE_TYPE The number of page types. * META_FLUSH Make sure the previous pages are written * with waiting the bio's completion * ... Only can be used with META. */ #define PAGE_TYPE_OF_BIO(type) ((type) > META ? META : (type)) #define PAGE_TYPE_ON_MAIN(type) ((type) == DATA || (type) == NODE) enum page_type { DATA = 0, NODE = 1, /* should not change this */ META, NR_PAGE_TYPE, META_FLUSH, IPU, /* the below types are used by tracepoints only. */ OPU, }; enum temp_type { HOT = 0, /* must be zero for meta bio */ WARM, COLD, NR_TEMP_TYPE, }; enum need_lock_type { LOCK_REQ = 0, LOCK_DONE, LOCK_RETRY, }; enum cp_reason_type { CP_NO_NEEDED, CP_NON_REGULAR, CP_COMPRESSED, CP_HARDLINK, CP_SB_NEED_CP, CP_WRONG_PINO, CP_NO_SPC_ROLL, CP_NODE_NEED_CP, CP_FASTBOOT_MODE, CP_SPEC_LOG_NUM, CP_RECOVER_DIR, CP_XATTR_DIR, }; enum iostat_type { /* WRITE IO */ APP_DIRECT_IO, /* app direct write IOs */ APP_BUFFERED_IO, /* app buffered write IOs */ APP_WRITE_IO, /* app write IOs */ APP_MAPPED_IO, /* app mapped IOs */ APP_BUFFERED_CDATA_IO, /* app buffered write IOs on compressed file */ APP_MAPPED_CDATA_IO, /* app mapped write IOs on compressed file */ FS_DATA_IO, /* data IOs from kworker/fsync/reclaimer */ FS_CDATA_IO, /* data IOs from kworker/fsync/reclaimer on compressed file */ FS_NODE_IO, /* node IOs from kworker/fsync/reclaimer */ FS_META_IO, /* meta IOs from kworker/reclaimer */ FS_GC_DATA_IO, /* data IOs from forground gc */ FS_GC_NODE_IO, /* node IOs from forground gc */ FS_CP_DATA_IO, /* data IOs from checkpoint */ FS_CP_NODE_IO, /* node IOs from checkpoint */ FS_CP_META_IO, /* meta IOs from checkpoint */ /* READ IO */ APP_DIRECT_READ_IO, /* app direct read IOs */ APP_BUFFERED_READ_IO, /* app buffered read IOs */ APP_READ_IO, /* app read IOs */ APP_MAPPED_READ_IO, /* app mapped read IOs */ APP_BUFFERED_CDATA_READ_IO, /* app buffered read IOs on compressed file */ APP_MAPPED_CDATA_READ_IO, /* app mapped read IOs on compressed file */ FS_DATA_READ_IO, /* data read IOs */ FS_GDATA_READ_IO, /* data read IOs from background gc */ FS_CDATA_READ_IO, /* compressed data read IOs */ FS_NODE_READ_IO, /* node read IOs */ FS_META_READ_IO, /* meta read IOs */ /* other */ FS_DISCARD_IO, /* discard */ FS_FLUSH_IO, /* flush */ FS_ZONE_RESET_IO, /* zone reset */ NR_IO_TYPE, }; struct f2fs_io_info { struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */ nid_t ino; /* inode number */ enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ enum temp_type temp; /* contains HOT/WARM/COLD */ enum req_op op; /* contains REQ_OP_ */ blk_opf_t op_flags; /* req_flag_bits */ block_t new_blkaddr; /* new block address to be written */ block_t old_blkaddr; /* old block address before Cow */ struct page *page; /* page to be written */ struct page *encrypted_page; /* encrypted page */ struct page *compressed_page; /* compressed page */ struct list_head list; /* serialize IOs */ unsigned int compr_blocks; /* # of compressed block addresses */ unsigned int need_lock:8; /* indicate we need to lock cp_rwsem */ unsigned int version:8; /* version of the node */ unsigned int submitted:1; /* indicate IO submission */ unsigned int in_list:1; /* indicate fio is in io_list */ unsigned int is_por:1; /* indicate IO is from recovery or not */ unsigned int encrypted:1; /* indicate file is encrypted */ unsigned int meta_gc:1; /* require meta inode GC */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ struct bio **bio; /* bio for ipu */ sector_t *last_block; /* last block number in bio */ }; struct bio_entry { struct bio *bio; struct list_head list; }; #define is_read_io(rw) ((rw) == READ) struct f2fs_bio_info { struct f2fs_sb_info *sbi; /* f2fs superblock */ struct bio *bio; /* bios to merge */ sector_t last_block_in_bio; /* last block number */ struct f2fs_io_info fio; /* store buffered io info. */ #ifdef CONFIG_BLK_DEV_ZONED struct completion zone_wait; /* condition value for the previous open zone to close */ struct bio *zone_pending_bio; /* pending bio for the previous zone */ void *bi_private; /* previous bi_private for pending bio */ #endif struct f2fs_rwsem io_rwsem; /* blocking op for bio */ spinlock_t io_lock; /* serialize DATA/NODE IOs */ struct list_head io_list; /* track fios */ struct list_head bio_list; /* bio entry list head */ struct f2fs_rwsem bio_list_lock; /* lock to protect bio entry list */ }; #define FDEV(i) (sbi->devs[i]) #define RDEV(i) (raw_super->devs[i]) struct f2fs_dev_info { struct file *bdev_file; struct block_device *bdev; char path[MAX_PATH_LEN]; unsigned int total_segments; block_t start_blk; block_t end_blk; #ifdef CONFIG_BLK_DEV_ZONED unsigned int nr_blkz; /* Total number of zones */ unsigned long *blkz_seq; /* Bitmap indicating sequential zones */ #endif }; enum inode_type { DIR_INODE, /* for dirty dir inode */ FILE_INODE, /* for dirty regular/symlink inode */ DIRTY_META, /* for all dirtied inode metadata */ NR_INODE_TYPE, }; /* for inner inode cache management */ struct inode_management { struct radix_tree_root ino_root; /* ino entry array */ spinlock_t ino_lock; /* for ino entry lock */ struct list_head ino_list; /* inode list head */ unsigned long ino_num; /* number of entries */ }; /* for GC_AT */ struct atgc_management { bool atgc_enabled; /* ATGC is enabled or not */ struct rb_root_cached root; /* root of victim rb-tree */ struct list_head victim_list; /* linked with all victim entries */ unsigned int victim_count; /* victim count in rb-tree */ unsigned int candidate_ratio; /* candidate ratio */ unsigned int max_candidate_count; /* max candidate count */ unsigned int age_weight; /* age weight, vblock_weight = 100 - age_weight */ unsigned long long age_threshold; /* age threshold */ }; struct f2fs_gc_control { unsigned int victim_segno; /* target victim segment number */ int init_gc_type; /* FG_GC or BG_GC */ bool no_bg_gc; /* check the space and stop bg_gc */ bool should_migrate_blocks; /* should migrate blocks */ bool err_gc_skipped; /* return EAGAIN if GC skipped */ bool one_time; /* require one time GC in one migration unit */ unsigned int nr_free_secs; /* # of free sections to do GC */ }; /* * For s_flag in struct f2fs_sb_info * Modification on enum should be synchronized with s_flag array */ enum { SBI_IS_DIRTY, /* dirty flag for checkpoint */ SBI_IS_CLOSE, /* specify unmounting */ SBI_NEED_FSCK, /* need fsck.f2fs to fix */ SBI_POR_DOING, /* recovery is doing or not */ SBI_NEED_SB_WRITE, /* need to recover superblock */ SBI_NEED_CP, /* need to checkpoint */ SBI_IS_SHUTDOWN, /* shutdown by ioctl */ SBI_IS_RECOVERED, /* recovered orphan/data */ SBI_CP_DISABLED, /* CP was disabled last mount */ SBI_CP_DISABLED_QUICK, /* CP was disabled quickly */ SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */ SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */ SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */ SBI_IS_RESIZEFS, /* resizefs is in process */ SBI_IS_FREEZING, /* freezefs is in process */ SBI_IS_WRITABLE, /* remove ro mountoption transiently */ MAX_SBI_FLAG, }; enum { CP_TIME, REQ_TIME, DISCARD_TIME, GC_TIME, DISABLE_TIME, UMOUNT_DISCARD_TIMEOUT, MAX_TIME, }; /* Note that you need to keep synchronization with this gc_mode_names array */ enum { GC_NORMAL, GC_IDLE_CB, GC_IDLE_GREEDY, GC_IDLE_AT, GC_URGENT_HIGH, GC_URGENT_LOW, GC_URGENT_MID, MAX_GC_MODE, }; enum { BGGC_MODE_ON, /* background gc is on */ BGGC_MODE_OFF, /* background gc is off */ BGGC_MODE_SYNC, /* * background gc is on, migrating blocks * like foreground gc */ }; enum { FS_MODE_ADAPTIVE, /* use both lfs/ssr allocation */ FS_MODE_LFS, /* use lfs allocation only */ FS_MODE_FRAGMENT_SEG, /* segment fragmentation mode */ FS_MODE_FRAGMENT_BLK, /* block fragmentation mode */ }; enum { ALLOC_MODE_DEFAULT, /* stay default */ ALLOC_MODE_REUSE, /* reuse segments as much as possible */ }; enum fsync_mode { FSYNC_MODE_POSIX, /* fsync follows posix semantics */ FSYNC_MODE_STRICT, /* fsync behaves in line with ext4 */ FSYNC_MODE_NOBARRIER, /* fsync behaves nobarrier based on posix */ }; enum { COMPR_MODE_FS, /* * automatically compress compression * enabled files */ COMPR_MODE_USER, /* * automatical compression is disabled. * user can control the file compression * using ioctls */ }; enum { DISCARD_UNIT_BLOCK, /* basic discard unit is block */ DISCARD_UNIT_SEGMENT, /* basic discard unit is segment */ DISCARD_UNIT_SECTION, /* basic discard unit is section */ }; enum { MEMORY_MODE_NORMAL, /* memory mode for normal devices */ MEMORY_MODE_LOW, /* memory mode for low memry devices */ }; enum errors_option { MOUNT_ERRORS_READONLY, /* remount fs ro on errors */ MOUNT_ERRORS_CONTINUE, /* continue on errors */ MOUNT_ERRORS_PANIC, /* panic on errors */ }; enum { BACKGROUND, FOREGROUND, MAX_CALL_TYPE, TOTAL_CALL = FOREGROUND, }; static inline int f2fs_test_bit(unsigned int nr, char *addr); static inline void f2fs_set_bit(unsigned int nr, char *addr); static inline void f2fs_clear_bit(unsigned int nr, char *addr); /* * Layout of f2fs page.private: * * Layout A: lowest bit should be 1 * | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | * bit 0 PAGE_PRIVATE_NOT_POINTER * bit 1 PAGE_PRIVATE_ONGOING_MIGRATION * bit 2 PAGE_PRIVATE_INLINE_INODE * bit 3 PAGE_PRIVATE_REF_RESOURCE * bit 4 PAGE_PRIVATE_ATOMIC_WRITE * bit 5- f2fs private data * * Layout B: lowest bit should be 0 * page.private is a wrapped pointer. */ enum { PAGE_PRIVATE_NOT_POINTER, /* private contains non-pointer data */ PAGE_PRIVATE_ONGOING_MIGRATION, /* data page which is on-going migrating */ PAGE_PRIVATE_INLINE_INODE, /* inode page contains inline data */ PAGE_PRIVATE_REF_RESOURCE, /* dirty page has referenced resources */ PAGE_PRIVATE_ATOMIC_WRITE, /* data page from atomic write path */ PAGE_PRIVATE_MAX }; /* For compression */ enum compress_algorithm_type { COMPRESS_LZO, COMPRESS_LZ4, COMPRESS_ZSTD, COMPRESS_LZORLE, COMPRESS_MAX, }; enum compress_flag { COMPRESS_CHKSUM, COMPRESS_MAX_FLAG, }; #define COMPRESS_WATERMARK 20 #define COMPRESS_PERCENT 20 #define COMPRESS_DATA_RESERVED_SIZE 4 struct compress_data { __le32 clen; /* compressed data size */ __le32 chksum; /* compressed data chksum */ __le32 reserved[COMPRESS_DATA_RESERVED_SIZE]; /* reserved */ u8 cdata[]; /* compressed data */ }; #define COMPRESS_HEADER_SIZE (sizeof(struct compress_data)) #define F2FS_COMPRESSED_PAGE_MAGIC 0xF5F2C000 #define F2FS_ZSTD_DEFAULT_CLEVEL 1 #define COMPRESS_LEVEL_OFFSET 8 /* compress context */ struct compress_ctx { struct inode *inode; /* inode the context belong to */ pgoff_t cluster_idx; /* cluster index number */ unsigned int cluster_size; /* page count in cluster */ unsigned int log_cluster_size; /* log of cluster size */ struct page **rpages; /* pages store raw data in cluster */ unsigned int nr_rpages; /* total page number in rpages */ struct page **cpages; /* pages store compressed data in cluster */ unsigned int nr_cpages; /* total page number in cpages */ unsigned int valid_nr_cpages; /* valid page number in cpages */ void *rbuf; /* virtual mapped address on rpages */ struct compress_data *cbuf; /* virtual mapped address on cpages */ size_t rlen; /* valid data length in rbuf */ size_t clen; /* valid data length in cbuf */ void *private; /* payload buffer for specified compression algorithm */ void *private2; /* extra payload buffer */ }; /* compress context for write IO path */ struct compress_io_ctx { u32 magic; /* magic number to indicate page is compressed */ struct inode *inode; /* inode the context belong to */ struct page **rpages; /* pages store raw data in cluster */ unsigned int nr_rpages; /* total page number in rpages */ atomic_t pending_pages; /* in-flight compressed page count */ }; /* Context for decompressing one cluster on the read IO path */ struct decompress_io_ctx { u32 magic; /* magic number to indicate page is compressed */ struct inode *inode; /* inode the context belong to */ pgoff_t cluster_idx; /* cluster index number */ unsigned int cluster_size; /* page count in cluster */ unsigned int log_cluster_size; /* log of cluster size */ struct page **rpages; /* pages store raw data in cluster */ unsigned int nr_rpages; /* total page number in rpages */ struct page **cpages; /* pages store compressed data in cluster */ unsigned int nr_cpages; /* total page number in cpages */ struct page **tpages; /* temp pages to pad holes in cluster */ void *rbuf; /* virtual mapped address on rpages */ struct compress_data *cbuf; /* virtual mapped address on cpages */ size_t rlen; /* valid data length in rbuf */ size_t clen; /* valid data length in cbuf */ /* * The number of compressed pages remaining to be read in this cluster. * This is initially nr_cpages. It is decremented by 1 each time a page * has been read (or failed to be read). When it reaches 0, the cluster * is decompressed (or an error is reported). * * If an error occurs before all the pages have been submitted for I/O, * then this will never reach 0. In this case the I/O submitter is * responsible for calling f2fs_decompress_end_io() instead. */ atomic_t remaining_pages; /* * Number of references to this decompress_io_ctx. * * One reference is held for I/O completion. This reference is dropped * after the pagecache pages are updated and unlocked -- either after * decompression (and verity if enabled), or after an error. * * In addition, each compressed page holds a reference while it is in a * bio. These references are necessary prevent compressed pages from * being freed while they are still in a bio. */ refcount_t refcnt; bool failed; /* IO error occurred before decompression? */ bool need_verity; /* need fs-verity verification after decompression? */ void *private; /* payload buffer for specified decompression algorithm */ void *private2; /* extra payload buffer */ struct work_struct verity_work; /* work to verify the decompressed pages */ struct work_struct free_work; /* work for late free this structure itself */ }; #define NULL_CLUSTER ((unsigned int)(~0)) #define MIN_COMPRESS_LOG_SIZE 2 #define MAX_COMPRESS_LOG_SIZE 8 #define MAX_COMPRESS_WINDOW_SIZE(log_size) ((PAGE_SIZE) << (log_size)) struct f2fs_sb_info { struct super_block *sb; /* pointer to VFS super block */ struct proc_dir_entry *s_proc; /* proc entry */ struct f2fs_super_block *raw_super; /* raw super block pointer */ struct f2fs_rwsem sb_lock; /* lock for raw super block */ int valid_super_block; /* valid super block no */ unsigned long s_flag; /* flags for sbi */ struct mutex writepages; /* mutex for writepages() */ #ifdef CONFIG_BLK_DEV_ZONED unsigned int blocks_per_blkz; /* F2FS blocks per zone */ unsigned int max_open_zones; /* max open zone resources of the zoned device */ /* For adjust the priority writing position of data in zone UFS */ unsigned int blkzone_alloc_policy; #endif /* for node-related operations */ struct f2fs_nm_info *nm_info; /* node manager */ struct inode *node_inode; /* cache node blocks */ /* for segment-related operations */ struct f2fs_sm_info *sm_info; /* segment manager */ /* for bio operations */ struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */ /* keep migration IO order for LFS mode */ struct f2fs_rwsem io_order_lock; pgoff_t page_eio_ofs[NR_PAGE_TYPE]; /* EIO page offset */ int page_eio_cnt[NR_PAGE_TYPE]; /* EIO count */ /* for checkpoint */ struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ int cur_cp_pack; /* remain current cp pack */ spinlock_t cp_lock; /* for flag in ckpt */ struct inode *meta_inode; /* cache meta blocks */ struct f2fs_rwsem cp_global_sem; /* checkpoint procedure lock */ struct f2fs_rwsem cp_rwsem; /* blocking FS operations */ struct f2fs_rwsem node_write; /* locking node writes */ struct f2fs_rwsem node_change; /* locking node change */ wait_queue_head_t cp_wait; unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ long interval_time[MAX_TIME]; /* to store thresholds */ struct ckpt_req_control cprc_info; /* for checkpoint request control */ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ spinlock_t fsync_node_lock; /* for node entry lock */ struct list_head fsync_node_list; /* node list head */ unsigned int fsync_seg_id; /* sequence id */ unsigned int fsync_node_num; /* number of node entries */ /* for orphan inode, use 0'th array */ unsigned int max_orphans; /* max orphan inodes */ /* for inode management */ struct list_head inode_list[NR_INODE_TYPE]; /* dirty inode list */ spinlock_t inode_lock[NR_INODE_TYPE]; /* for dirty inode list lock */ struct mutex flush_lock; /* for flush exclusion */ /* for extent tree cache */ struct extent_tree_info extent_tree[NR_EXTENT_CACHES]; atomic64_t allocated_data_blocks; /* for block age extent_cache */ /* The threshold used for hot and warm data seperation*/ unsigned int hot_data_age_threshold; unsigned int warm_data_age_threshold; unsigned int last_age_weight; /* basic filesystem units */ unsigned int log_sectors_per_block; /* log2 sectors per block */ unsigned int log_blocksize; /* log2 block size */ unsigned int blocksize; /* block size */ unsigned int root_ino_num; /* root inode number*/ unsigned int node_ino_num; /* node inode number*/ unsigned int meta_ino_num; /* meta inode number*/ unsigned int log_blocks_per_seg; /* log2 blocks per segment */ unsigned int blocks_per_seg; /* blocks per segment */ unsigned int unusable_blocks_per_sec; /* unusable blocks per section */ unsigned int segs_per_sec; /* segments per section */ unsigned int secs_per_zone; /* sections per zone */ unsigned int total_sections; /* total section count */ unsigned int total_node_count; /* total node block count */ unsigned int total_valid_node_count; /* valid node block count */ int dir_level; /* directory level */ bool readdir_ra; /* readahead inode in readdir */ u64 max_io_bytes; /* max io bytes to merge IOs */ block_t user_block_count; /* # of user blocks */ block_t total_valid_block_count; /* # of valid blocks */ block_t discard_blks; /* discard command candidats */ block_t last_valid_block_count; /* for recovery */ block_t reserved_blocks; /* configurable reserved blocks */ block_t current_reserved_blocks; /* current reserved blocks */ /* Additional tracking for no checkpoint mode */ block_t unusable_block_count; /* # of blocks saved by last cp */ unsigned int nquota_files; /* # of quota sysfile */ struct f2fs_rwsem quota_sem; /* blocking cp for flags */ /* # of pages, see count_type */ atomic_t nr_pages[NR_COUNT_TYPE]; /* # of allocated blocks */ struct percpu_counter alloc_valid_block_count; /* # of node block writes as roll forward recovery */ struct percpu_counter rf_node_block_count; /* writeback control */ atomic_t wb_sync_req[META]; /* count # of WB_SYNC threads */ /* valid inode count */ struct percpu_counter total_valid_inode_count; struct f2fs_mount_info mount_opt; /* mount options */ /* for cleaning operations */ struct f2fs_rwsem gc_lock; /* * semaphore for GC, avoid * race between GC and GC or CP */ struct f2fs_gc_kthread *gc_thread; /* GC thread */ struct atgc_management am; /* atgc management */ unsigned int cur_victim_sec; /* current victim section num */ unsigned int gc_mode; /* current GC state */ unsigned int next_victim_seg[2]; /* next segment in victim section */ spinlock_t gc_remaining_trials_lock; /* remaining trial count for GC_URGENT_* and GC_IDLE_* */ unsigned int gc_remaining_trials; /* for skip statistic */ unsigned long long skipped_gc_rwsem; /* FG_GC only */ /* threshold for gc trials on pinned files */ unsigned short gc_pin_file_threshold; struct f2fs_rwsem pin_sem; /* maximum # of trials to find a victim segment for SSR and GC */ unsigned int max_victim_search; /* migration granularity of garbage collection, unit: segment */ unsigned int migration_granularity; /* migration window granularity of garbage collection, unit: segment */ unsigned int migration_window_granularity; /* * for stat information. * one is for the LFS mode, and the other is for the SSR mode. */ #ifdef CONFIG_F2FS_STAT_FS struct f2fs_stat_info *stat_info; /* FS status information */ atomic_t meta_count[META_MAX]; /* # of meta blocks */ unsigned int segment_count[2]; /* # of allocated segments */ unsigned int block_count[2]; /* # of allocated blocks */ atomic_t inplace_count; /* # of inplace update */ /* # of lookup extent cache */ atomic64_t total_hit_ext[NR_EXTENT_CACHES]; /* # of hit rbtree extent node */ atomic64_t read_hit_rbtree[NR_EXTENT_CACHES]; /* # of hit cached extent node */ atomic64_t read_hit_cached[NR_EXTENT_CACHES]; /* # of hit largest extent node in read extent cache */ atomic64_t read_hit_largest; atomic_t inline_xattr; /* # of inline_xattr inodes */ atomic_t inline_inode; /* # of inline_data inodes */ atomic_t inline_dir; /* # of inline_dentry inodes */ atomic_t compr_inode; /* # of compressed inodes */ atomic64_t compr_blocks; /* # of compressed blocks */ atomic_t swapfile_inode; /* # of swapfile inodes */ atomic_t atomic_files; /* # of opened atomic file */ atomic_t max_aw_cnt; /* max # of atomic writes */ unsigned int io_skip_bggc; /* skip background gc for in-flight IO */ unsigned int other_skip_bggc; /* skip background gc for other reasons */ unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */ atomic_t cp_call_count[MAX_CALL_TYPE]; /* # of cp call */ #endif spinlock_t stat_lock; /* lock for stat operations */ /* to attach REQ_META|REQ_FUA flags */ unsigned int data_io_flag; unsigned int node_io_flag; /* For sysfs support */ struct kobject s_kobj; /* /sys/fs/f2fs/<devname> */ struct completion s_kobj_unregister; struct kobject s_stat_kobj; /* /sys/fs/f2fs/<devname>/stat */ struct completion s_stat_kobj_unregister; struct kobject s_feature_list_kobj; /* /sys/fs/f2fs/<devname>/feature_list */ struct completion s_feature_list_kobj_unregister; /* For shrinker support */ struct list_head s_list; struct mutex umount_mutex; unsigned int shrinker_run_no; /* For multi devices */ int s_ndevs; /* number of devices */ struct f2fs_dev_info *devs; /* for device list */ unsigned int dirty_device; /* for checkpoint data flush */ spinlock_t dev_lock; /* protect dirty_device */ bool aligned_blksize; /* all devices has the same logical blksize */ /* For write statistics */ u64 sectors_written_start; u64 kbytes_written; /* Reference to checksum algorithm driver via cryptoapi */ struct crypto_shash *s_chksum_driver; /* Precomputed FS UUID checksum for seeding other checksums */ __u32 s_chksum_seed; struct workqueue_struct *post_read_wq; /* post read workqueue */ /* * If we are in irq context, let's update error information into * on-disk superblock in the work. */ struct work_struct s_error_work; unsigned char errors[MAX_F2FS_ERRORS]; /* error flags */ unsigned char stop_reason[MAX_STOP_REASON]; /* stop reason */ spinlock_t error_lock; /* protect errors/stop_reason array */ bool error_dirty; /* errors of sb is dirty */ struct kmem_cache *inline_xattr_slab; /* inline xattr entry */ unsigned int inline_xattr_slab_size; /* default inline xattr slab size */ /* For reclaimed segs statistics per each GC mode */ unsigned int gc_segment_mode; /* GC state for reclaimed segments */ unsigned int gc_reclaimed_segs[MAX_GC_MODE]; /* Reclaimed segs for each mode */ unsigned long seq_file_ra_mul; /* multiplier for ra_pages of seq. files in fadvise */ int max_fragment_chunk; /* max chunk size for block fragmentation mode */ int max_fragment_hole; /* max hole size for block fragmentation mode */ /* For atomic write statistics */ atomic64_t current_atomic_write; s64 peak_atomic_write; u64 committed_atomic_block; u64 revoked_atomic_block; #ifdef CONFIG_F2FS_FS_COMPRESSION struct kmem_cache *page_array_slab; /* page array entry */ unsigned int page_array_slab_size; /* default page array slab size */ /* For runtime compression statistics */ u64 compr_written_block; u64 compr_saved_block; u32 compr_new_inode; /* For compressed block cache */ struct inode *compress_inode; /* cache compressed blocks */ unsigned int compress_percent; /* cache page percentage */ unsigned int compress_watermark; /* cache page watermark */ atomic_t compress_page_hit; /* cache hit count */ #endif #ifdef CONFIG_F2FS_IOSTAT /* For app/fs IO statistics */ spinlock_t iostat_lock; unsigned long long iostat_count[NR_IO_TYPE]; unsigned long long iostat_bytes[NR_IO_TYPE]; unsigned long long prev_iostat_bytes[NR_IO_TYPE]; bool iostat_enable; unsigned long iostat_next_period; unsigned int iostat_period_ms; /* For io latency related statistics info in one iostat period */ spinlock_t iostat_lat_lock; struct iostat_lat_info *iostat_io_lat; #endif }; /* Definitions to access f2fs_sb_info */ #define SEGS_TO_BLKS(sbi, segs) \ ((segs) << (sbi)->log_blocks_per_seg) #define BLKS_TO_SEGS(sbi, blks) \ ((blks) >> (sbi)->log_blocks_per_seg) #define BLKS_PER_SEG(sbi) ((sbi)->blocks_per_seg) #define BLKS_PER_SEC(sbi) (SEGS_TO_BLKS(sbi, (sbi)->segs_per_sec)) #define SEGS_PER_SEC(sbi) ((sbi)->segs_per_sec) __printf(3, 4) void f2fs_printk(struct f2fs_sb_info *sbi, bool limit_rate, const char *fmt, ...); #define f2fs_err(sbi, fmt, ...) \ f2fs_printk(sbi, false, KERN_ERR fmt, ##__VA_ARGS__) #define f2fs_warn(sbi, fmt, ...) \ f2fs_printk(sbi, false, KERN_WARNING fmt, ##__VA_ARGS__) #define f2fs_notice(sbi, fmt, ...) \ f2fs_printk(sbi, false, KERN_NOTICE fmt, ##__VA_ARGS__) #define f2fs_info(sbi, fmt, ...) \ f2fs_printk(sbi, false, KERN_INFO fmt, ##__VA_ARGS__) #define f2fs_debug(sbi, fmt, ...) \ f2fs_printk(sbi, false, KERN_DEBUG fmt, ##__VA_ARGS__) #define f2fs_err_ratelimited(sbi, fmt, ...) \ f2fs_printk(sbi, true, KERN_ERR fmt, ##__VA_ARGS__) #define f2fs_warn_ratelimited(sbi, fmt, ...) \ f2fs_printk(sbi, true, KERN_WARNING fmt, ##__VA_ARGS__) #define f2fs_info_ratelimited(sbi, fmt, ...) \ f2fs_printk(sbi, true, KERN_INFO fmt, ##__VA_ARGS__) #ifdef CONFIG_F2FS_FAULT_INJECTION #define time_to_inject(sbi, type) __time_to_inject(sbi, type, __func__, \ __builtin_return_address(0)) static inline bool __time_to_inject(struct f2fs_sb_info *sbi, int type, const char *func, const char *parent_func) { struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info; if (!ffi->inject_rate) return false; if (!IS_FAULT_SET(ffi, type)) return false; atomic_inc(&ffi->inject_ops); if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) { atomic_set(&ffi->inject_ops, 0); f2fs_info_ratelimited(sbi, "inject %s in %s of %pS", f2fs_fault_name[type], func, parent_func); return true; } return false; } #else static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) { return false; } #endif /* * Test if the mounted volume is a multi-device volume. * - For a single regular disk volume, sbi->s_ndevs is 0. * - For a single zoned disk volume, sbi->s_ndevs is 1. * - For a multi-device volume, sbi->s_ndevs is always 2 or more. */ static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) { return sbi->s_ndevs > 1; } static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) { unsigned long now = jiffies; sbi->last_time[type] = now; /* DISCARD_TIME and GC_TIME are based on REQ_TIME */ if (type == REQ_TIME) { sbi->last_time[DISCARD_TIME] = now; sbi->last_time[GC_TIME] = now; } } static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type) { unsigned long interval = sbi->interval_time[type] * HZ; return time_after(jiffies, sbi->last_time[type] + interval); } static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi, int type) { unsigned long interval = sbi->interval_time[type] * HZ; unsigned int wait_ms = 0; long delta; delta = (sbi->last_time[type] + interval) - jiffies; if (delta > 0) wait_ms = jiffies_to_msecs(delta); return wait_ms; } /* * Inline functions */ static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc, const void *address, unsigned int length) { struct { struct shash_desc shash; char ctx[4]; } desc; int err; BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx)); desc.shash.tfm = sbi->s_chksum_driver; *(u32 *)desc.ctx = crc; err = crypto_shash_update(&desc.shash, address, length); BUG_ON(err); return *(u32 *)desc.ctx; } static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address, unsigned int length) { return __f2fs_crc32(sbi, F2FS_SUPER_MAGIC, address, length); } static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc, void *buf, size_t buf_size) { return f2fs_crc32(sbi, buf, buf_size) == blk_crc; } static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc, const void *address, unsigned int length) { return __f2fs_crc32(sbi, crc, address, length); } static inline struct f2fs_inode_info *F2FS_I(struct inode *inode) { return container_of(inode, struct f2fs_inode_info, vfs_inode); } static inline struct f2fs_sb_info *F2FS_SB(struct super_block *sb) { return sb->s_fs_info; } static inline struct f2fs_sb_info *F2FS_I_SB(struct inode *inode) { return F2FS_SB(inode->i_sb); } static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping) { return F2FS_I_SB(mapping->host); } static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page) { return F2FS_M_SB(page_file_mapping(page)); } static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi) { return (struct f2fs_super_block *)(sbi->raw_super); } static inline struct f2fs_super_block *F2FS_SUPER_BLOCK(struct folio *folio, pgoff_t index) { pgoff_t idx_in_folio = index % (1 << folio_order(folio)); return (struct f2fs_super_block *) (page_address(folio_page(folio, idx_in_folio)) + F2FS_SUPER_OFFSET); } static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi) { return (struct f2fs_checkpoint *)(sbi->ckpt); } static inline struct f2fs_node *F2FS_NODE(struct page *page) { return (struct f2fs_node *)page_address(page); } static inline struct f2fs_inode *F2FS_INODE(struct page *page) { return &((struct f2fs_node *)page_address(page))->i; } static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi) { return (struct f2fs_nm_info *)(sbi->nm_info); } static inline struct f2fs_sm_info *SM_I(struct f2fs_sb_info *sbi) { return (struct f2fs_sm_info *)(sbi->sm_info); } static inline struct sit_info *SIT_I(struct f2fs_sb_info *sbi) { return (struct sit_info *)(SM_I(sbi)->sit_info); } static inline struct free_segmap_info *FREE_I(struct f2fs_sb_info *sbi) { return (struct free_segmap_info *)(SM_I(sbi)->free_info); } static inline struct dirty_seglist_info *DIRTY_I(struct f2fs_sb_info *sbi) { return (struct dirty_seglist_info *)(SM_I(sbi)->dirty_info); } static inline struct address_space *META_MAPPING(struct f2fs_sb_info *sbi) { return sbi->meta_inode->i_mapping; } static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi) { return sbi->node_inode->i_mapping; } static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type) { return test_bit(type, &sbi->s_flag); } static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type) { set_bit(type, &sbi->s_flag); } static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type) { clear_bit(type, &sbi->s_flag); } static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp) { return le64_to_cpu(cp->checkpoint_ver); } static inline unsigned long f2fs_qf_ino(struct super_block *sb, int type) { if (type < F2FS_MAX_QUOTAS) return le32_to_cpu(F2FS_SB(sb)->raw_super->qf_ino[type]); return 0; } static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp) { size_t crc_offset = le32_to_cpu(cp->checksum_offset); return le32_to_cpu(*((__le32 *)((unsigned char *)cp + crc_offset))); } static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) { unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags); return ckpt_flags & f; } static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) { return __is_set_ckpt_flags(F2FS_CKPT(sbi), f); } static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) { unsigned int ckpt_flags; ckpt_flags = le32_to_cpu(cp->ckpt_flags); ckpt_flags |= f; cp->ckpt_flags = cpu_to_le32(ckpt_flags); } static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) { unsigned long flags; spin_lock_irqsave(&sbi->cp_lock, flags); __set_ckpt_flags(F2FS_CKPT(sbi), f); spin_unlock_irqrestore(&sbi->cp_lock, flags); } static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) { unsigned int ckpt_flags; ckpt_flags = le32_to_cpu(cp->ckpt_flags); ckpt_flags &= (~f); cp->ckpt_flags = cpu_to_le32(ckpt_flags); } static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) { unsigned long flags; spin_lock_irqsave(&sbi->cp_lock, flags); __clear_ckpt_flags(F2FS_CKPT(sbi), f); spin_unlock_irqrestore(&sbi->cp_lock, flags); } #define init_f2fs_rwsem(sem) \ do { \ static struct lock_class_key __key; \ \ __init_f2fs_rwsem((sem), #sem, &__key); \ } while (0) static inline void __init_f2fs_rwsem(struct f2fs_rwsem *sem, const char *sem_name, struct lock_class_key *key) { __init_rwsem(&sem->internal_rwsem, sem_name, key); #ifdef CONFIG_F2FS_UNFAIR_RWSEM init_waitqueue_head(&sem->read_waiters); #endif } static inline int f2fs_rwsem_is_locked(struct f2fs_rwsem *sem) { return rwsem_is_locked(&sem->internal_rwsem); } static inline int f2fs_rwsem_is_contended(struct f2fs_rwsem *sem) { return rwsem_is_contended(&sem->internal_rwsem); } static inline void f2fs_down_read(struct f2fs_rwsem *sem) { #ifdef CONFIG_F2FS_UNFAIR_RWSEM wait_event(sem->read_waiters, down_read_trylock(&sem->internal_rwsem)); #else down_read(&sem->internal_rwsem); #endif } static inline int f2fs_down_read_trylock(struct f2fs_rwsem *sem) { return down_read_trylock(&sem->internal_rwsem); } static inline void f2fs_up_read(struct f2fs_rwsem *sem) { up_read(&sem->internal_rwsem); } static inline void f2fs_down_write(struct f2fs_rwsem *sem) { down_write(&sem->internal_rwsem); } #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass) { down_read_nested(&sem->internal_rwsem, subclass); } static inline void f2fs_down_write_nested(struct f2fs_rwsem *sem, int subclass) { down_write_nested(&sem->internal_rwsem, subclass); } #else #define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem) #define f2fs_down_write_nested(sem, subclass) f2fs_down_write(sem) #endif static inline int f2fs_down_write_trylock(struct f2fs_rwsem *sem) { return down_write_trylock(&sem->internal_rwsem); } static inline void f2fs_up_write(struct f2fs_rwsem *sem) { up_write(&sem->internal_rwsem); #ifdef CONFIG_F2FS_UNFAIR_RWSEM wake_up_all(&sem->read_waiters); #endif } static inline void f2fs_lock_op(struct f2fs_sb_info *sbi) { f2fs_down_read(&sbi->cp_rwsem); } static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi) { if (time_to_inject(sbi, FAULT_LOCK_OP)) return 0; return f2fs_down_read_trylock(&sbi->cp_rwsem); } static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) { f2fs_up_read(&sbi->cp_rwsem); } static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) { f2fs_down_write(&sbi->cp_rwsem); } static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) { f2fs_up_write(&sbi->cp_rwsem); } static inline int __get_cp_reason(struct f2fs_sb_info *sbi) { int reason = CP_SYNC; if (test_opt(sbi, FASTBOOT)) reason = CP_FASTBOOT; if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) reason = CP_UMOUNT; return reason; } static inline bool __remain_node_summaries(int reason) { return (reason & (CP_UMOUNT | CP_FASTBOOT)); } static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi) { return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) || is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG)); } /* * Check whether the inode has blocks or not */ static inline int F2FS_HAS_BLOCKS(struct inode *inode) { block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0; return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block; } static inline bool f2fs_has_xattr_block(unsigned int ofs) { return ofs == XATTR_NODE_OFFSET; } static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, struct inode *inode, bool cap) { if (!inode) return true; if (!test_opt(sbi, RESERVE_ROOT)) return false; if (IS_NOQUOTA(inode)) return true; if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid())) return true; if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) && in_group_p(F2FS_OPTION(sbi).s_resgid)) return true; if (cap && capable(CAP_SYS_RESOURCE)) return true; return false; } static inline unsigned int get_available_block_count(struct f2fs_sb_info *sbi, struct inode *inode, bool cap) { block_t avail_user_block_count; avail_user_block_count = sbi->user_block_count - sbi->current_reserved_blocks; if (!__allow_reserved_blocks(sbi, inode, cap)) avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { if (avail_user_block_count > sbi->unusable_block_count) avail_user_block_count -= sbi->unusable_block_count; else avail_user_block_count = 0; } return avail_user_block_count; } static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool); static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, struct inode *inode, blkcnt_t *count, bool partial) { long long diff = 0, release = 0; block_t avail_user_block_count; int ret; ret = dquot_reserve_block(inode, *count); if (ret) return ret; if (time_to_inject(sbi, FAULT_BLOCK)) { release = *count; goto release_quota; } /* * let's increase this in prior to actual block count change in order * for f2fs_sync_file to avoid data races when deciding checkpoint. */ percpu_counter_add(&sbi->alloc_valid_block_count, (*count)); spin_lock(&sbi->stat_lock); avail_user_block_count = get_available_block_count(sbi, inode, true); diff = (long long)sbi->total_valid_block_count + *count - avail_user_block_count; if (unlikely(diff > 0)) { if (!partial) { spin_unlock(&sbi->stat_lock); release = *count; goto enospc; } if (diff > *count) diff = *count; *count -= diff; release = diff; if (!*count) { spin_unlock(&sbi->stat_lock); goto enospc; } } sbi->total_valid_block_count += (block_t)(*count); spin_unlock(&sbi->stat_lock); if (unlikely(release)) { percpu_counter_sub(&sbi->alloc_valid_block_count, release); dquot_release_reservation_block(inode, release); } f2fs_i_blocks_write(inode, *count, true, true); return 0; enospc: percpu_counter_sub(&sbi->alloc_valid_block_count, release); release_quota: dquot_release_reservation_block(inode, release); return -ENOSPC; } #define PAGE_PRIVATE_GET_FUNC(name, flagname) \ static inline bool page_private_##name(struct page *page) \ { \ return PagePrivate(page) && \ test_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)) && \ test_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ } #define PAGE_PRIVATE_SET_FUNC(name, flagname) \ static inline void set_page_private_##name(struct page *page) \ { \ if (!PagePrivate(page)) \ attach_page_private(page, (void *)0); \ set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)); \ set_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ } #define PAGE_PRIVATE_CLEAR_FUNC(name, flagname) \ static inline void clear_page_private_##name(struct page *page) \ { \ clear_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) \ detach_page_private(page); \ } PAGE_PRIVATE_GET_FUNC(nonpointer, NOT_POINTER); PAGE_PRIVATE_GET_FUNC(inline, INLINE_INODE); PAGE_PRIVATE_GET_FUNC(gcing, ONGOING_MIGRATION); PAGE_PRIVATE_GET_FUNC(atomic, ATOMIC_WRITE); PAGE_PRIVATE_SET_FUNC(reference, REF_RESOURCE); PAGE_PRIVATE_SET_FUNC(inline, INLINE_INODE); PAGE_PRIVATE_SET_FUNC(gcing, ONGOING_MIGRATION); PAGE_PRIVATE_SET_FUNC(atomic, ATOMIC_WRITE); PAGE_PRIVATE_CLEAR_FUNC(reference, REF_RESOURCE); PAGE_PRIVATE_CLEAR_FUNC(inline, INLINE_INODE); PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION); PAGE_PRIVATE_CLEAR_FUNC(atomic, ATOMIC_WRITE); static inline unsigned long get_page_private_data(struct page *page) { unsigned long data = page_private(page); if (!test_bit(PAGE_PRIVATE_NOT_POINTER, &data)) return 0; return data >> PAGE_PRIVATE_MAX; } static inline void set_page_private_data(struct page *page, unsigned long data) { if (!PagePrivate(page)) attach_page_private(page, (void *)0); set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)); page_private(page) |= data << PAGE_PRIVATE_MAX; } static inline void clear_page_private_data(struct page *page) { page_private(page) &= GENMASK(PAGE_PRIVATE_MAX - 1, 0); if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) detach_page_private(page); } static inline void clear_page_private_all(struct page *page) { clear_page_private_data(page); clear_page_private_reference(page); clear_page_private_gcing(page); clear_page_private_inline(page); clear_page_private_atomic(page); f2fs_bug_on(F2FS_P_SB(page), page_private(page)); } static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, struct inode *inode, block_t count) { blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK; spin_lock(&sbi->stat_lock); f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); sbi->total_valid_block_count -= (block_t)count; if (sbi->reserved_blocks && sbi->current_reserved_blocks < sbi->reserved_blocks) sbi->current_reserved_blocks = min(sbi->reserved_blocks, sbi->current_reserved_blocks + count); spin_unlock(&sbi->stat_lock); if (unlikely(inode->i_blocks < sectors)) { f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu", inode->i_ino, (unsigned long long)inode->i_blocks, (unsigned long long)sectors); set_sbi_flag(sbi, SBI_NEED_FSCK); return; } f2fs_i_blocks_write(inode, count, false, true); } static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) { atomic_inc(&sbi->nr_pages[count_type]); if (count_type == F2FS_DIRTY_DENTS || count_type == F2FS_DIRTY_NODES || count_type == F2FS_DIRTY_META || count_type == F2FS_DIRTY_QDATA || count_type == F2FS_DIRTY_IMETA) set_sbi_flag(sbi, SBI_IS_DIRTY); } static inline void inode_inc_dirty_pages(struct inode *inode) { atomic_inc(&F2FS_I(inode)->dirty_pages); inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); if (IS_NOQUOTA(inode)) inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA); } static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type) { atomic_dec(&sbi->nr_pages[count_type]); } static inline void inode_dec_dirty_pages(struct inode *inode) { if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode)) return; atomic_dec(&F2FS_I(inode)->dirty_pages); dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); if (IS_NOQUOTA(inode)) dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA); } static inline void inc_atomic_write_cnt(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); u64 current_write; fi->atomic_write_cnt++; atomic64_inc(&sbi->current_atomic_write); current_write = atomic64_read(&sbi->current_atomic_write); if (current_write > sbi->peak_atomic_write) sbi->peak_atomic_write = current_write; } static inline void release_atomic_write_cnt(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); atomic64_sub(fi->atomic_write_cnt, &sbi->current_atomic_write); fi->atomic_write_cnt = 0; } static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type) { return atomic_read(&sbi->nr_pages[count_type]); } static inline int get_dirty_pages(struct inode *inode) { return atomic_read(&F2FS_I(inode)->dirty_pages); } static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type) { return div_u64(get_pages(sbi, block_type) + BLKS_PER_SEC(sbi) - 1, BLKS_PER_SEC(sbi)); } static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi) { return sbi->total_valid_block_count; } static inline block_t discard_blocks(struct f2fs_sb_info *sbi) { return sbi->discard_blks; } static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); /* return NAT or SIT bitmap */ if (flag == NAT_BITMAP) return le32_to_cpu(ckpt->nat_ver_bitmap_bytesize); else if (flag == SIT_BITMAP) return le32_to_cpu(ckpt->sit_ver_bitmap_bytesize); return 0; } static inline block_t __cp_payload(struct f2fs_sb_info *sbi) { return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload); } static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); void *tmp_ptr = &ckpt->sit_nat_version_bitmap; int offset; if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) { offset = (flag == SIT_BITMAP) ? le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0; /* * if large_nat_bitmap feature is enabled, leave checksum * protection for all nat/sit bitmaps. */ return tmp_ptr + offset + sizeof(__le32); } if (__cp_payload(sbi) > 0) { if (flag == NAT_BITMAP) return tmp_ptr; else return (unsigned char *)ckpt + F2FS_BLKSIZE; } else { offset = (flag == NAT_BITMAP) ? le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0; return tmp_ptr + offset; } } static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi) { block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr); if (sbi->cur_cp_pack == 2) start_addr += BLKS_PER_SEG(sbi); return start_addr; } static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi) { block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr); if (sbi->cur_cp_pack == 1) start_addr += BLKS_PER_SEG(sbi); return start_addr; } static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi) { sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1; } static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi) { return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum); } extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync); static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, struct inode *inode, bool is_inode) { block_t valid_block_count; unsigned int valid_node_count; unsigned int avail_user_block_count; int err; if (is_inode) { if (inode) { err = dquot_alloc_inode(inode); if (err) return err; } } else { err = dquot_reserve_block(inode, 1); if (err) return err; } if (time_to_inject(sbi, FAULT_BLOCK)) goto enospc; spin_lock(&sbi->stat_lock); valid_block_count = sbi->total_valid_block_count + 1; avail_user_block_count = get_available_block_count(sbi, inode, false); if (unlikely(valid_block_count > avail_user_block_count)) { spin_unlock(&sbi->stat_lock); goto enospc; } valid_node_count = sbi->total_valid_node_count + 1; if (unlikely(valid_node_count > sbi->total_node_count)) { spin_unlock(&sbi->stat_lock); goto enospc; } sbi->total_valid_node_count++; sbi->total_valid_block_count++; spin_unlock(&sbi->stat_lock); if (inode) { if (is_inode) f2fs_mark_inode_dirty_sync(inode, true); else f2fs_i_blocks_write(inode, 1, true, true); } percpu_counter_inc(&sbi->alloc_valid_block_count); return 0; enospc: if (is_inode) { if (inode) dquot_free_inode(inode); } else { dquot_release_reservation_block(inode, 1); } return -ENOSPC; } static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, struct inode *inode, bool is_inode) { spin_lock(&sbi->stat_lock); if (unlikely(!sbi->total_valid_block_count || !sbi->total_valid_node_count)) { f2fs_warn(sbi, "dec_valid_node_count: inconsistent block counts, total_valid_block:%u, total_valid_node:%u", sbi->total_valid_block_count, sbi->total_valid_node_count); set_sbi_flag(sbi, SBI_NEED_FSCK); } else { sbi->total_valid_block_count--; sbi->total_valid_node_count--; } if (sbi->reserved_blocks && sbi->current_reserved_blocks < sbi->reserved_blocks) sbi->current_reserved_blocks++; spin_unlock(&sbi->stat_lock); if (is_inode) { dquot_free_inode(inode); } else { if (unlikely(inode->i_blocks == 0)) { f2fs_warn(sbi, "dec_valid_node_count: inconsistent i_blocks, ino:%lu, iblocks:%llu", inode->i_ino, (unsigned long long)inode->i_blocks); set_sbi_flag(sbi, SBI_NEED_FSCK); return; } f2fs_i_blocks_write(inode, 1, false, true); } } static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi) { return sbi->total_valid_node_count; } static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi) { percpu_counter_inc(&sbi->total_valid_inode_count); } static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi) { percpu_counter_dec(&sbi->total_valid_inode_count); } static inline s64 valid_inode_count(struct f2fs_sb_info *sbi) { return percpu_counter_sum_positive(&sbi->total_valid_inode_count); } static inline struct page *f2fs_grab_cache_page(struct address_space *mapping, pgoff_t index, bool for_write) { struct page *page; unsigned int flags; if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) { if (!for_write) page = find_get_page_flags(mapping, index, FGP_LOCK | FGP_ACCESSED); else page = find_lock_page(mapping, index); if (page) return page; if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) return NULL; } if (!for_write) return grab_cache_page(mapping, index); flags = memalloc_nofs_save(); page = grab_cache_page_write_begin(mapping, index); memalloc_nofs_restore(flags); return page; } static inline struct page *f2fs_pagecache_get_page( struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp_mask) { if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) return NULL; return pagecache_get_page(mapping, index, fgp_flags, gfp_mask); } static inline void f2fs_put_page(struct page *page, int unlock) { if (!page) return; if (unlock) { f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page)); unlock_page(page); } put_page(page); } static inline void f2fs_put_dnode(struct dnode_of_data *dn) { if (dn->node_page) f2fs_put_page(dn->node_page, 1); if (dn->inode_page && dn->node_page != dn->inode_page) f2fs_put_page(dn->inode_page, 0); dn->node_page = NULL; dn->inode_page = NULL; } static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name, size_t size) { return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL); } static inline void *f2fs_kmem_cache_alloc_nofail(struct kmem_cache *cachep, gfp_t flags) { void *entry; entry = kmem_cache_alloc(cachep, flags); if (!entry) entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL); return entry; } static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags, bool nofail, struct f2fs_sb_info *sbi) { if (nofail) return f2fs_kmem_cache_alloc_nofail(cachep, flags); if (time_to_inject(sbi, FAULT_SLAB_ALLOC)) return NULL; return kmem_cache_alloc(cachep, flags); } static inline bool is_inflight_io(struct f2fs_sb_info *sbi, int type) { if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) || get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) || get_pages(sbi, F2FS_WB_CP_DATA) || get_pages(sbi, F2FS_DIO_READ) || get_pages(sbi, F2FS_DIO_WRITE)) return true; if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info && atomic_read(&SM_I(sbi)->dcc_info->queued_discard)) return true; if (SM_I(sbi) && SM_I(sbi)->fcc_info && atomic_read(&SM_I(sbi)->fcc_info->queued_flush)) return true; return false; } static inline bool is_inflight_read_io(struct f2fs_sb_info *sbi) { return get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_DIO_READ); } static inline bool is_idle(struct f2fs_sb_info *sbi, int type) { bool zoned_gc = (type == GC_TIME && F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_BLKZONED)); if (sbi->gc_mode == GC_URGENT_HIGH) return true; if (zoned_gc) { if (is_inflight_read_io(sbi)) return false; } else { if (is_inflight_io(sbi, type)) return false; } if (sbi->gc_mode == GC_URGENT_MID) return true; if (sbi->gc_mode == GC_URGENT_LOW && (type == DISCARD_TIME || type == GC_TIME)) return true; if (zoned_gc) return true; return f2fs_time_over(sbi, type); } static inline void f2fs_radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { while (radix_tree_insert(root, index, item)) cond_resched(); } #define RAW_IS_INODE(p) ((p)->footer.nid == (p)->footer.ino) static inline bool IS_INODE(struct page *page) { struct f2fs_node *p = F2FS_NODE(page); return RAW_IS_INODE(p); } static inline int offset_in_addr(struct f2fs_inode *i) { return (i->i_inline & F2FS_EXTRA_ATTR) ? (le16_to_cpu(i->i_extra_isize) / sizeof(__le32)) : 0; } static inline __le32 *blkaddr_in_node(struct f2fs_node *node) { return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr; } static inline int f2fs_has_extra_attr(struct inode *inode); static inline unsigned int get_dnode_base(struct inode *inode, struct page *node_page) { if (!IS_INODE(node_page)) return 0; return inode ? get_extra_isize(inode) : offset_in_addr(&F2FS_NODE(node_page)->i); } static inline __le32 *get_dnode_addr(struct inode *inode, struct page *node_page) { return blkaddr_in_node(F2FS_NODE(node_page)) + get_dnode_base(inode, node_page); } static inline block_t data_blkaddr(struct inode *inode, struct page *node_page, unsigned int offset) { return le32_to_cpu(*(get_dnode_addr(inode, node_page) + offset)); } static inline block_t f2fs_data_blkaddr(struct dnode_of_data *dn) { return data_blkaddr(dn->inode, dn->node_page, dn->ofs_in_node); } static inline int f2fs_test_bit(unsigned int nr, char *addr) { int mask; addr += (nr >> 3); mask = BIT(7 - (nr & 0x07)); return mask & *addr; } static inline void f2fs_set_bit(unsigned int nr, char *addr) { int mask; addr += (nr >> 3); mask = BIT(7 - (nr & 0x07)); *addr |= mask; } static inline void f2fs_clear_bit(unsigned int nr, char *addr) { int mask; addr += (nr >> 3); mask = BIT(7 - (nr & 0x07)); *addr &= ~mask; } static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr) { int mask; int ret; addr += (nr >> 3); mask = BIT(7 - (nr & 0x07)); ret = mask & *addr; *addr |= mask; return ret; } static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr) { int mask; int ret; addr += (nr >> 3); mask = BIT(7 - (nr & 0x07)); ret = mask & *addr; *addr &= ~mask; return ret; } static inline void f2fs_change_bit(unsigned int nr, char *addr) { int mask; addr += (nr >> 3); mask = BIT(7 - (nr & 0x07)); *addr ^= mask; } /* * On-disk inode flags (f2fs_inode::i_flags) */ #define F2FS_COMPR_FL 0x00000004 /* Compress file */ #define F2FS_SYNC_FL 0x00000008 /* Synchronous updates */ #define F2FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ #define F2FS_APPEND_FL 0x00000020 /* writes to file may only append */ #define F2FS_NODUMP_FL 0x00000040 /* do not dump file */ #define F2FS_NOATIME_FL 0x00000080 /* do not update atime */ #define F2FS_NOCOMP_FL 0x00000400 /* Don't compress */ #define F2FS_INDEX_FL 0x00001000 /* hash-indexed directory */ #define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ #define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define F2FS_CASEFOLD_FL 0x40000000 /* Casefolded file */ #define F2FS_QUOTA_DEFAULT_FL (F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL) /* Flags that should be inherited by new inodes from their parent. */ #define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \ F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \ F2FS_CASEFOLD_FL) /* Flags that are appropriate for regular files (all but dir-specific ones). */ #define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \ F2FS_CASEFOLD_FL)) /* Flags that are appropriate for non-directories/regular files. */ #define F2FS_OTHER_FLMASK (F2FS_NODUMP_FL | F2FS_NOATIME_FL) static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags) { if (S_ISDIR(mode)) return flags; else if (S_ISREG(mode)) return flags & F2FS_REG_FLMASK; else return flags & F2FS_OTHER_FLMASK; } static inline void __mark_inode_dirty_flag(struct inode *inode, int flag, bool set) { switch (flag) { case FI_INLINE_XATTR: case FI_INLINE_DATA: case FI_INLINE_DENTRY: case FI_NEW_INODE: if (set) return; fallthrough; case FI_DATA_EXIST: case FI_PIN_FILE: case FI_COMPRESS_RELEASED: f2fs_mark_inode_dirty_sync(inode, true); } } static inline void set_inode_flag(struct inode *inode, int flag) { set_bit(flag, F2FS_I(inode)->flags); __mark_inode_dirty_flag(inode, flag, true); } static inline int is_inode_flag_set(struct inode *inode, int flag) { return test_bit(flag, F2FS_I(inode)->flags); } static inline void clear_inode_flag(struct inode *inode, int flag) { clear_bit(flag, F2FS_I(inode)->flags); __mark_inode_dirty_flag(inode, flag, false); } static inline bool f2fs_verity_in_progress(struct inode *inode) { return IS_ENABLED(CONFIG_FS_VERITY) && is_inode_flag_set(inode, FI_VERITY_IN_PROGRESS); } static inline void set_acl_inode(struct inode *inode, umode_t mode) { F2FS_I(inode)->i_acl_mode = mode; set_inode_flag(inode, FI_ACL_MODE); f2fs_mark_inode_dirty_sync(inode, false); } static inline void f2fs_i_links_write(struct inode *inode, bool inc) { if (inc) inc_nlink(inode); else drop_nlink(inode); f2fs_mark_inode_dirty_sync(inode, true); } static inline void f2fs_i_blocks_write(struct inode *inode, block_t diff, bool add, bool claim) { bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE); bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER); /* add = 1, claim = 1 should be dquot_reserve_block in pair */ if (add) { if (claim) dquot_claim_block(inode, diff); else dquot_alloc_block_nofail(inode, diff); } else { dquot_free_block(inode, diff); } f2fs_mark_inode_dirty_sync(inode, true); if (clean || recover) set_inode_flag(inode, FI_AUTO_RECOVER); } static inline bool f2fs_is_atomic_file(struct inode *inode); static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size) { bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE); bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER); if (i_size_read(inode) == i_size) return; i_size_write(inode, i_size); if (f2fs_is_atomic_file(inode)) return; f2fs_mark_inode_dirty_sync(inode, true); if (clean || recover) set_inode_flag(inode, FI_AUTO_RECOVER); } static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth) { F2FS_I(inode)->i_current_depth = depth; f2fs_mark_inode_dirty_sync(inode, true); } static inline void f2fs_i_gc_failures_write(struct inode *inode, unsigned int count) { F2FS_I(inode)->i_gc_failures = count; f2fs_mark_inode_dirty_sync(inode, true); } static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid) { F2FS_I(inode)->i_xattr_nid = xnid; f2fs_mark_inode_dirty_sync(inode, true); } static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino) { F2FS_I(inode)->i_pino = pino; f2fs_mark_inode_dirty_sync(inode, true); } static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri) { struct f2fs_inode_info *fi = F2FS_I(inode); if (ri->i_inline & F2FS_INLINE_XATTR) set_bit(FI_INLINE_XATTR, fi->flags); if (ri->i_inline & F2FS_INLINE_DATA) set_bit(FI_INLINE_DATA, fi->flags); if (ri->i_inline & F2FS_INLINE_DENTRY) set_bit(FI_INLINE_DENTRY, fi->flags); if (ri->i_inline & F2FS_DATA_EXIST) set_bit(FI_DATA_EXIST, fi->flags); if (ri->i_inline & F2FS_EXTRA_ATTR) set_bit(FI_EXTRA_ATTR, fi->flags); if (ri->i_inline & F2FS_PIN_FILE) set_bit(FI_PIN_FILE, fi->flags); if (ri->i_inline & F2FS_COMPRESS_RELEASED) set_bit(FI_COMPRESS_RELEASED, fi->flags); } static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri) { ri->i_inline = 0; if (is_inode_flag_set(inode, FI_INLINE_XATTR)) ri->i_inline |= F2FS_INLINE_XATTR; if (is_inode_flag_set(inode, FI_INLINE_DATA)) ri->i_inline |= F2FS_INLINE_DATA; if (is_inode_flag_set(inode, FI_INLINE_DENTRY)) ri->i_inline |= F2FS_INLINE_DENTRY; if (is_inode_flag_set(inode, FI_DATA_EXIST)) ri->i_inline |= F2FS_DATA_EXIST; if (is_inode_flag_set(inode, FI_EXTRA_ATTR)) ri->i_inline |= F2FS_EXTRA_ATTR; if (is_inode_flag_set(inode, FI_PIN_FILE)) ri->i_inline |= F2FS_PIN_FILE; if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) ri->i_inline |= F2FS_COMPRESS_RELEASED; } static inline int f2fs_has_extra_attr(struct inode *inode) { return is_inode_flag_set(inode, FI_EXTRA_ATTR); } static inline int f2fs_has_inline_xattr(struct inode *inode) { return is_inode_flag_set(inode, FI_INLINE_XATTR); } static inline int f2fs_compressed_file(struct inode *inode) { return S_ISREG(inode->i_mode) && is_inode_flag_set(inode, FI_COMPRESSED_FILE); } static inline bool f2fs_need_compress_data(struct inode *inode) { int compress_mode = F2FS_OPTION(F2FS_I_SB(inode)).compress_mode; if (!f2fs_compressed_file(inode)) return false; if (compress_mode == COMPR_MODE_FS) return true; else if (compress_mode == COMPR_MODE_USER && is_inode_flag_set(inode, FI_ENABLE_COMPRESS)) return true; return false; } static inline unsigned int addrs_per_page(struct inode *inode, bool is_inode) { unsigned int addrs = is_inode ? (CUR_ADDRS_PER_INODE(inode) - get_inline_xattr_addrs(inode)) : DEF_ADDRS_PER_BLOCK; if (f2fs_compressed_file(inode)) return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size); return addrs; } static inline void *inline_xattr_addr(struct inode *inode, struct page *page) { struct f2fs_inode *ri = F2FS_INODE(page); return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE - get_inline_xattr_addrs(inode)]); } static inline int inline_xattr_size(struct inode *inode) { if (f2fs_has_inline_xattr(inode)) return get_inline_xattr_addrs(inode) * sizeof(__le32); return 0; } /* * Notice: check inline_data flag without inode page lock is unsafe. * It could change at any time by f2fs_convert_inline_page(). */ static inline int f2fs_has_inline_data(struct inode *inode) { return is_inode_flag_set(inode, FI_INLINE_DATA); } static inline int f2fs_exist_data(struct inode *inode) { return is_inode_flag_set(inode, FI_DATA_EXIST); } static inline int f2fs_is_mmap_file(struct inode *inode) { return is_inode_flag_set(inode, FI_MMAP_FILE); } static inline bool f2fs_is_pinned_file(struct inode *inode) { return is_inode_flag_set(inode, FI_PIN_FILE); } static inline bool f2fs_is_atomic_file(struct inode *inode) { return is_inode_flag_set(inode, FI_ATOMIC_FILE); } static inline bool f2fs_is_cow_file(struct inode *inode) { return is_inode_flag_set(inode, FI_COW_FILE); } static inline void *inline_data_addr(struct inode *inode, struct page *page) { __le32 *addr = get_dnode_addr(inode, page); return (void *)(addr + DEF_INLINE_RESERVED_SIZE); } static inline int f2fs_has_inline_dentry(struct inode *inode) { return is_inode_flag_set(inode, FI_INLINE_DENTRY); } static inline int is_file(struct inode *inode, int type) { return F2FS_I(inode)->i_advise & type; } static inline void set_file(struct inode *inode, int type) { if (is_file(inode, type)) return; F2FS_I(inode)->i_advise |= type; f2fs_mark_inode_dirty_sync(inode, true); } static inline void clear_file(struct inode *inode, int type) { if (!is_file(inode, type)) return; F2FS_I(inode)->i_advise &= ~type; f2fs_mark_inode_dirty_sync(inode, true); } static inline bool f2fs_is_time_consistent(struct inode *inode) { struct timespec64 ts = inode_get_atime(inode); if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &ts)) return false; ts = inode_get_ctime(inode); if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &ts)) return false; ts = inode_get_mtime(inode); if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &ts)) return false; return true; } static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) { bool ret; if (dsync) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); spin_lock(&sbi->inode_lock[DIRTY_META]); ret = list_empty(&F2FS_I(inode)->gdirty_list); spin_unlock(&sbi->inode_lock[DIRTY_META]); return ret; } if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) || file_keep_isize(inode) || i_size_read(inode) & ~PAGE_MASK) return false; if (!f2fs_is_time_consistent(inode)) return false; spin_lock(&F2FS_I(inode)->i_size_lock); ret = F2FS_I(inode)->last_disk_size == i_size_read(inode); spin_unlock(&F2FS_I(inode)->i_size_lock); return ret; } static inline bool f2fs_readonly(struct super_block *sb) { return sb_rdonly(sb); } static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi) { return is_set_ckpt_flags(sbi, CP_ERROR_FLAG); } static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi, size_t size, gfp_t flags) { if (time_to_inject(sbi, FAULT_KMALLOC)) return NULL; return kmalloc(size, flags); } static inline void *f2fs_getname(struct f2fs_sb_info *sbi) { if (time_to_inject(sbi, FAULT_KMALLOC)) return NULL; return __getname(); } static inline void f2fs_putname(char *buf) { __putname(buf); } static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi, size_t size, gfp_t flags) { return f2fs_kmalloc(sbi, size, flags | __GFP_ZERO); } static inline void *f2fs_kvmalloc(struct f2fs_sb_info *sbi, size_t size, gfp_t flags) { if (time_to_inject(sbi, FAULT_KVMALLOC)) return NULL; return kvmalloc(size, flags); } static inline void *f2fs_kvzalloc(struct f2fs_sb_info *sbi, size_t size, gfp_t flags) { return f2fs_kvmalloc(sbi, size, flags | __GFP_ZERO); } static inline int get_extra_isize(struct inode *inode) { return F2FS_I(inode)->i_extra_isize / sizeof(__le32); } static inline int get_inline_xattr_addrs(struct inode *inode) { return F2FS_I(inode)->i_inline_xattr_size; } #define f2fs_get_inode_mode(i) \ ((is_inode_flag_set(i, FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) #define F2FS_MIN_EXTRA_ATTR_SIZE (sizeof(__le32)) #define F2FS_TOTAL_EXTRA_ATTR_SIZE \ (offsetof(struct f2fs_inode, i_extra_end) - \ offsetof(struct f2fs_inode, i_extra_isize)) \ #define F2FS_OLD_ATTRIBUTE_SIZE (offsetof(struct f2fs_inode, i_addr)) #define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field) \ ((offsetof(typeof(*(f2fs_inode)), field) + \ sizeof((f2fs_inode)->field)) \ <= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize))) \ #define __is_large_section(sbi) (SEGS_PER_SEC(sbi) > 1) #define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META) bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); static inline void verify_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.", blkaddr, type); } static inline bool __is_valid_data_blkaddr(block_t blkaddr) { if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR || blkaddr == COMPRESS_ADDR) return false; return true; } /* * file.c */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate(struct inode *inode); int f2fs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end); void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count); int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag, bool readonly, bool need_lock); int f2fs_precache_extents(struct inode *inode); int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa); int f2fs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid); int f2fs_pin_file_control(struct inode *inode, bool inc); /* * inode.c */ void f2fs_set_inode_flags(struct inode *inode); bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page); void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page); struct inode *f2fs_iget(struct super_block *sb, unsigned long ino); struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino); int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink); void f2fs_update_inode(struct inode *inode, struct page *node_page); void f2fs_update_inode_page(struct inode *inode); int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc); void f2fs_evict_inode(struct inode *inode); void f2fs_handle_failed_inode(struct inode *inode); /* * namei.c */ int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, bool hot, bool set); struct dentry *f2fs_get_parent(struct dentry *child); int f2fs_get_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct inode **new_inode); /* * dir.c */ #if IS_ENABLED(CONFIG_UNICODE) int f2fs_init_casefolded_name(const struct inode *dir, struct f2fs_filename *fname); void f2fs_free_casefolded_name(struct f2fs_filename *fname); #else static inline int f2fs_init_casefolded_name(const struct inode *dir, struct f2fs_filename *fname) { return 0; } static inline void f2fs_free_casefolded_name(struct f2fs_filename *fname) { } #endif /* CONFIG_UNICODE */ int f2fs_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct f2fs_filename *fname); int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry, struct f2fs_filename *fname); void f2fs_free_filename(struct f2fs_filename *fname); struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d, const struct f2fs_filename *fname, int *max_slots); int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, unsigned int start_pos, struct fscrypt_str *fstr); void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent, struct f2fs_dentry_ptr *d); struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir, const struct f2fs_filename *fname, struct page *dpage); void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode, unsigned int current_depth); int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots); void f2fs_drop_nlink(struct inode *dir, struct inode *inode); struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, const struct f2fs_filename *fname, struct page **res_page); struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, const struct qstr *child, struct page **res_page); struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p); ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr, struct page **page); void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, struct page *page, struct inode *inode); bool f2fs_has_enough_room(struct inode *dir, struct page *ipage, const struct f2fs_filename *fname); void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d, const struct fscrypt_str *name, f2fs_hash_t name_hash, unsigned int bit_pos); int f2fs_add_regular_entry(struct inode *dir, const struct f2fs_filename *fname, struct inode *inode, nid_t ino, umode_t mode); int f2fs_add_dentry(struct inode *dir, const struct f2fs_filename *fname, struct inode *inode, nid_t ino, umode_t mode); int f2fs_do_add_link(struct inode *dir, const struct qstr *name, struct inode *inode, nid_t ino, umode_t mode); void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, struct inode *dir, struct inode *inode); int f2fs_do_tmpfile(struct inode *inode, struct inode *dir, struct f2fs_filename *fname); bool f2fs_empty_dir(struct inode *dir); static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) { if (fscrypt_is_nokey_name(dentry)) return -ENOKEY; return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name, inode, inode->i_ino, inode->i_mode); } /* * super.c */ int f2fs_inode_dirtied(struct inode *inode, bool sync); void f2fs_inode_synced(struct inode *inode); int f2fs_dquot_initialize(struct inode *inode); int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly); int f2fs_quota_sync(struct super_block *sb, int type); loff_t max_file_blocks(struct inode *inode); void f2fs_quota_off_umount(struct super_block *sb); void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag); void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason, bool irq_context); void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error); void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error); int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi); /* * hash.c */ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname); /* * node.c */ struct node_info; int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid); bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type); bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page); void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi); void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page); void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi); int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid); bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid); bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino); int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni, bool checkpoint_context); pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs); int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode); int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from); int f2fs_truncate_xattr_node(struct inode *inode); int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, unsigned int seq_id); bool f2fs_nat_bitmap_enabled(struct f2fs_sb_info *sbi); int f2fs_remove_inode_page(struct inode *inode); struct page *f2fs_new_inode_page(struct inode *inode); struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs); void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid); struct page *f2fs_get_node_page_ra(struct page *parent, int start); int f2fs_move_node_page(struct page *node_page, int gc_type); void f2fs_flush_inline_data(struct f2fs_sb_info *sbi); int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, struct writeback_control *wbc, bool atomic, unsigned int *seq_id); int f2fs_sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, bool do_balance, enum iostat_type io_type); int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount); bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid); void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid); void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid); int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink); int f2fs_recover_inline_xattr(struct inode *inode, struct page *page); int f2fs_recover_xattr_data(struct inode *inode, struct page *page); int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page); int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, unsigned int segno, struct f2fs_summary_block *sum); void f2fs_enable_nat_bits(struct f2fs_sb_info *sbi); int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); int f2fs_build_node_manager(struct f2fs_sb_info *sbi); void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi); int __init f2fs_create_node_manager_caches(void); void f2fs_destroy_node_manager_caches(void); /* * segment.c */ bool f2fs_need_SSR(struct f2fs_sb_info *sbi); int f2fs_commit_atomic_write(struct inode *inode); void f2fs_abort_atomic_write(struct inode *inode, bool clean); void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need); void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg); int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino); int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi); int f2fs_flush_device_cache(struct f2fs_sb_info *sbi); void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free); void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); int f2fs_start_discard_thread(struct f2fs_sb_info *sbi); void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi); void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi); bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi); void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi); block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi); int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable); void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi); int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno); int f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi); int f2fs_reinit_atgc_curseg(struct f2fs_sb_info *sbi); void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi); void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi); int f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, unsigned int start, unsigned int end); int f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force); int f2fs_allocate_pinning_section(struct f2fs_sb_info *sbi); int f2fs_allocate_new_segments(struct f2fs_sb_info *sbi); int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range); bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc); struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno); void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr); void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct folio *folio, enum iostat_type io_type); void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio); void f2fs_outplace_write_data(struct dnode_of_data *dn, struct f2fs_io_info *fio); int f2fs_inplace_write_data(struct f2fs_io_info *fio); void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t old_blkaddr, block_t new_blkaddr, bool recover_curseg, bool recover_newaddr, bool from_gc); void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, block_t old_addr, block_t new_addr, unsigned char version, bool recover_curseg, bool recover_newaddr); int f2fs_get_segment_temp(int seg_type); int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, struct f2fs_io_info *fio); void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino, block_t blkaddr, unsigned int blkcnt); void f2fs_wait_on_page_writeback(struct page *page, enum page_type type, bool ordered, bool locked); void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr); void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, block_t len); void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk); void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk); int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, unsigned int val, int alloc); void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi); int f2fs_check_write_pointer(struct f2fs_sb_info *sbi); int f2fs_build_segment_manager(struct f2fs_sb_info *sbi); void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi); int __init f2fs_create_segment_manager_caches(void); void f2fs_destroy_segment_manager_caches(void); int f2fs_rw_hint_to_seg_type(struct f2fs_sb_info *sbi, enum rw_hint hint); enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, enum page_type type, enum temp_type temp); unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi); unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi, unsigned int segno); #define DEF_FRAGMENT_SIZE 4 #define MIN_FRAGMENT_SIZE 1 #define MAX_FRAGMENT_SIZE 512 static inline bool f2fs_need_rand_seg(struct f2fs_sb_info *sbi) { return F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG || F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK; } /* * checkpoint.c */ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io, unsigned char reason); void f2fs_flush_ckpt_thread(struct f2fs_sb_info *sbi); struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index); struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index); bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); bool f2fs_is_valid_blkaddr_raw(struct f2fs_sb_info *sbi, block_t blkaddr, int type); int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type, bool sync); void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index, unsigned int ra_blocks); long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, long nr_to_write, enum iostat_type io_type); void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all); bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode); void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, unsigned int devidx, int type); bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, unsigned int devidx, int type); int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi); void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi); void f2fs_add_orphan_inode(struct inode *inode); void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino); int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi); int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi); void f2fs_update_dirty_folio(struct inode *inode, struct folio *folio); void f2fs_remove_dirty_inode(struct inode *inode); int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type, bool from_cp); void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type); u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi); int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc); void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi); int __init f2fs_create_checkpoint_caches(void); void f2fs_destroy_checkpoint_caches(void); int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi); int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi); void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi); void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi); /* * data.c */ int __init f2fs_init_bioset(void); void f2fs_destroy_bioset(void); bool f2fs_is_cp_guaranteed(struct page *page); int f2fs_init_bio_entry_cache(void); void f2fs_destroy_bio_entry_cache(void); void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio, enum page_type type); int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi); void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type); void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, struct inode *inode, struct page *page, nid_t ino, enum page_type type); void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, struct bio **bio, struct page *page); void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi); int f2fs_submit_page_bio(struct f2fs_io_info *fio); int f2fs_merge_page_bio(struct f2fs_io_info *fio); void f2fs_submit_page_write(struct f2fs_io_info *fio); struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, block_t blk_addr, sector_t *sector); int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr); void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count); int f2fs_reserve_new_block(struct dnode_of_data *dn); int f2fs_get_block_locked(struct dnode_of_data *dn, pgoff_t index); int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index); struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs); struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index, pgoff_t *next_pgofs); struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, bool for_write); struct page *f2fs_get_new_data_page(struct inode *inode, struct page *ipage, pgoff_t index, bool new_i_size); int f2fs_do_write_data_page(struct f2fs_io_info *fio); int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); int f2fs_encrypt_one_page(struct f2fs_io_info *fio); bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio); bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio); int f2fs_write_single_data_page(struct folio *folio, int *submitted, struct bio **bio, sector_t *last_block, struct writeback_control *wbc, enum iostat_type io_type, int compr_blocks, bool allow_balance); void f2fs_write_failed(struct inode *inode, loff_t to); void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length); bool f2fs_release_folio(struct folio *folio, gfp_t wait); bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len); void f2fs_clear_page_cache_dirty_tag(struct folio *folio); int f2fs_init_post_read_processing(void); void f2fs_destroy_post_read_processing(void); int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi); void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi); extern const struct iomap_ops f2fs_iomap_ops; /* * gc.c */ int f2fs_start_gc_thread(struct f2fs_sb_info *sbi); void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi); block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode); int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control); void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); int f2fs_gc_range(struct f2fs_sb_info *sbi, unsigned int start_seg, unsigned int end_seg, bool dry_run, unsigned int dry_run_sections); int f2fs_resize_fs(struct file *filp, __u64 block_count); int __init f2fs_create_garbage_collection_cache(void); void f2fs_destroy_garbage_collection_cache(void); /* victim selection function for cleaning and SSR */ int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result, int gc_type, int type, char alloc_mode, unsigned long long age, bool one_time); /* * recovery.c */ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only); bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi); int __init f2fs_create_recovery_cache(void); void f2fs_destroy_recovery_cache(void); /* * debug.c */ #ifdef CONFIG_F2FS_STAT_FS struct f2fs_stat_info { struct list_head stat_list; struct f2fs_sb_info *sbi; int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs; int main_area_segs, main_area_sections, main_area_zones; unsigned long long hit_cached[NR_EXTENT_CACHES]; unsigned long long hit_rbtree[NR_EXTENT_CACHES]; unsigned long long total_ext[NR_EXTENT_CACHES]; unsigned long long hit_total[NR_EXTENT_CACHES]; int ext_tree[NR_EXTENT_CACHES]; int zombie_tree[NR_EXTENT_CACHES]; int ext_node[NR_EXTENT_CACHES]; /* to count memory footprint */ unsigned long long ext_mem[NR_EXTENT_CACHES]; /* for read extent cache */ unsigned long long hit_largest; /* for block age extent cache */ unsigned long long allocated_data_blocks; int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta; int ndirty_data, ndirty_qdata; unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all; int nats, dirty_nats, sits, dirty_sits; int free_nids, avail_nids, alloc_nids; int total_count, utilization; int nr_wb_cp_data, nr_wb_data; int nr_rd_data, nr_rd_node, nr_rd_meta; int nr_dio_read, nr_dio_write; unsigned int io_skip_bggc, other_skip_bggc; int nr_flushing, nr_flushed, flush_list_empty; int nr_discarding, nr_discarded; int nr_discard_cmd; unsigned int undiscard_blks; int nr_issued_ckpt, nr_total_ckpt, nr_queued_ckpt; unsigned int cur_ckpt_time, peak_ckpt_time; int inline_xattr, inline_inode, inline_dir, append, update, orphans; int compr_inode, swapfile_inode; unsigned long long compr_blocks; int aw_cnt, max_aw_cnt; unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks; unsigned int bimodal, avg_vblocks; int util_free, util_valid, util_invalid; int rsvd_segs, overp_segs; int dirty_count, node_pages, meta_pages, compress_pages; int compress_page_hit; int prefree_count, free_segs, free_secs; int cp_call_count[MAX_CALL_TYPE], cp_count; int gc_call_count[MAX_CALL_TYPE]; int gc_segs[2][2]; int gc_secs[2][2]; int tot_blks, data_blks, node_blks; int bg_data_blks, bg_node_blks; int curseg[NR_CURSEG_TYPE]; int cursec[NR_CURSEG_TYPE]; int curzone[NR_CURSEG_TYPE]; unsigned int dirty_seg[NR_CURSEG_TYPE]; unsigned int full_seg[NR_CURSEG_TYPE]; unsigned int valid_blks[NR_CURSEG_TYPE]; unsigned int meta_count[META_MAX]; unsigned int segment_count[2]; unsigned int block_count[2]; unsigned int inplace_count; unsigned long long base_mem, cache_mem, page_mem; }; static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) { return (struct f2fs_stat_info *)sbi->stat_info; } #define stat_inc_cp_call_count(sbi, foreground) \ atomic_inc(&sbi->cp_call_count[(foreground)]) #define stat_inc_cp_count(sbi) (F2FS_STAT(sbi)->cp_count++) #define stat_io_skip_bggc_count(sbi) ((sbi)->io_skip_bggc++) #define stat_other_skip_bggc_count(sbi) ((sbi)->other_skip_bggc++) #define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++) #define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--) #define stat_inc_total_hit(sbi, type) (atomic64_inc(&(sbi)->total_hit_ext[type])) #define stat_inc_rbtree_node_hit(sbi, type) (atomic64_inc(&(sbi)->read_hit_rbtree[type])) #define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest)) #define stat_inc_cached_node_hit(sbi, type) (atomic64_inc(&(sbi)->read_hit_cached[type])) #define stat_inc_inline_xattr(inode) \ do { \ if (f2fs_has_inline_xattr(inode)) \ (atomic_inc(&F2FS_I_SB(inode)->inline_xattr)); \ } while (0) #define stat_dec_inline_xattr(inode) \ do { \ if (f2fs_has_inline_xattr(inode)) \ (atomic_dec(&F2FS_I_SB(inode)->inline_xattr)); \ } while (0) #define stat_inc_inline_inode(inode) \ do { \ if (f2fs_has_inline_data(inode)) \ (atomic_inc(&F2FS_I_SB(inode)->inline_inode)); \ } while (0) #define stat_dec_inline_inode(inode) \ do { \ if (f2fs_has_inline_data(inode)) \ (atomic_dec(&F2FS_I_SB(inode)->inline_inode)); \ } while (0) #define stat_inc_inline_dir(inode) \ do { \ if (f2fs_has_inline_dentry(inode)) \ (atomic_inc(&F2FS_I_SB(inode)->inline_dir)); \ } while (0) #define stat_dec_inline_dir(inode) \ do { \ if (f2fs_has_inline_dentry(inode)) \ (atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \ } while (0) #define stat_inc_compr_inode(inode) \ do { \ if (f2fs_compressed_file(inode)) \ (atomic_inc(&F2FS_I_SB(inode)->compr_inode)); \ } while (0) #define stat_dec_compr_inode(inode) \ do { \ if (f2fs_compressed_file(inode)) \ (atomic_dec(&F2FS_I_SB(inode)->compr_inode)); \ } while (0) #define stat_add_compr_blocks(inode, blocks) \ (atomic64_add(blocks, &F2FS_I_SB(inode)->compr_blocks)) #define stat_sub_compr_blocks(inode, blocks) \ (atomic64_sub(blocks, &F2FS_I_SB(inode)->compr_blocks)) #define stat_inc_swapfile_inode(inode) \ (atomic_inc(&F2FS_I_SB(inode)->swapfile_inode)) #define stat_dec_swapfile_inode(inode) \ (atomic_dec(&F2FS_I_SB(inode)->swapfile_inode)) #define stat_inc_atomic_inode(inode) \ (atomic_inc(&F2FS_I_SB(inode)->atomic_files)) #define stat_dec_atomic_inode(inode) \ (atomic_dec(&F2FS_I_SB(inode)->atomic_files)) #define stat_inc_meta_count(sbi, blkaddr) \ do { \ if (blkaddr < SIT_I(sbi)->sit_base_addr) \ atomic_inc(&(sbi)->meta_count[META_CP]); \ else if (blkaddr < NM_I(sbi)->nat_blkaddr) \ atomic_inc(&(sbi)->meta_count[META_SIT]); \ else if (blkaddr < SM_I(sbi)->ssa_blkaddr) \ atomic_inc(&(sbi)->meta_count[META_NAT]); \ else if (blkaddr < SM_I(sbi)->main_blkaddr) \ atomic_inc(&(sbi)->meta_count[META_SSA]); \ } while (0) #define stat_inc_seg_type(sbi, curseg) \ ((sbi)->segment_count[(curseg)->alloc_type]++) #define stat_inc_block_count(sbi, curseg) \ ((sbi)->block_count[(curseg)->alloc_type]++) #define stat_inc_inplace_blocks(sbi) \ (atomic_inc(&(sbi)->inplace_count)) #define stat_update_max_atomic_write(inode) \ do { \ int cur = atomic_read(&F2FS_I_SB(inode)->atomic_files); \ int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt); \ if (cur > max) \ atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur); \ } while (0) #define stat_inc_gc_call_count(sbi, foreground) \ (F2FS_STAT(sbi)->gc_call_count[(foreground)]++) #define stat_inc_gc_sec_count(sbi, type, gc_type) \ (F2FS_STAT(sbi)->gc_secs[(type)][(gc_type)]++) #define stat_inc_gc_seg_count(sbi, type, gc_type) \ (F2FS_STAT(sbi)->gc_segs[(type)][(gc_type)]++) #define stat_inc_tot_blk_count(si, blks) \ ((si)->tot_blks += (blks)) #define stat_inc_data_blk_count(sbi, blks, gc_type) \ do { \ struct f2fs_stat_info *si = F2FS_STAT(sbi); \ stat_inc_tot_blk_count(si, blks); \ si->data_blks += (blks); \ si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0; \ } while (0) #define stat_inc_node_blk_count(sbi, blks, gc_type) \ do { \ struct f2fs_stat_info *si = F2FS_STAT(sbi); \ stat_inc_tot_blk_count(si, blks); \ si->node_blks += (blks); \ si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0; \ } while (0) int f2fs_build_stats(struct f2fs_sb_info *sbi); void f2fs_destroy_stats(struct f2fs_sb_info *sbi); void __init f2fs_create_root_stats(void); void f2fs_destroy_root_stats(void); void f2fs_update_sit_info(struct f2fs_sb_info *sbi); #else #define stat_inc_cp_call_count(sbi, foreground) do { } while (0) #define stat_inc_cp_count(sbi) do { } while (0) #define stat_io_skip_bggc_count(sbi) do { } while (0) #define stat_other_skip_bggc_count(sbi) do { } while (0) #define stat_inc_dirty_inode(sbi, type) do { } while (0) #define stat_dec_dirty_inode(sbi, type) do { } while (0) #define stat_inc_total_hit(sbi, type) do { } while (0) #define stat_inc_rbtree_node_hit(sbi, type) do { } while (0) #define stat_inc_largest_node_hit(sbi) do { } while (0) #define stat_inc_cached_node_hit(sbi, type) do { } while (0) #define stat_inc_inline_xattr(inode) do { } while (0) #define stat_dec_inline_xattr(inode) do { } while (0) #define stat_inc_inline_inode(inode) do { } while (0) #define stat_dec_inline_inode(inode) do { } while (0) #define stat_inc_inline_dir(inode) do { } while (0) #define stat_dec_inline_dir(inode) do { } while (0) #define stat_inc_compr_inode(inode) do { } while (0) #define stat_dec_compr_inode(inode) do { } while (0) #define stat_add_compr_blocks(inode, blocks) do { } while (0) #define stat_sub_compr_blocks(inode, blocks) do { } while (0) #define stat_inc_swapfile_inode(inode) do { } while (0) #define stat_dec_swapfile_inode(inode) do { } while (0) #define stat_inc_atomic_inode(inode) do { } while (0) #define stat_dec_atomic_inode(inode) do { } while (0) #define stat_update_max_atomic_write(inode) do { } while (0) #define stat_inc_meta_count(sbi, blkaddr) do { } while (0) #define stat_inc_seg_type(sbi, curseg) do { } while (0) #define stat_inc_block_count(sbi, curseg) do { } while (0) #define stat_inc_inplace_blocks(sbi) do { } while (0) #define stat_inc_gc_call_count(sbi, foreground) do { } while (0) #define stat_inc_gc_sec_count(sbi, type, gc_type) do { } while (0) #define stat_inc_gc_seg_count(sbi, type, gc_type) do { } while (0) #define stat_inc_tot_blk_count(si, blks) do { } while (0) #define stat_inc_data_blk_count(sbi, blks, gc_type) do { } while (0) #define stat_inc_node_blk_count(sbi, blks, gc_type) do { } while (0) static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } static inline void __init f2fs_create_root_stats(void) { } static inline void f2fs_destroy_root_stats(void) { } static inline void f2fs_update_sit_info(struct f2fs_sb_info *sbi) {} #endif extern const struct file_operations f2fs_dir_operations; extern const struct file_operations f2fs_file_operations; extern const struct inode_operations f2fs_file_inode_operations; extern const struct address_space_operations f2fs_dblock_aops; extern const struct address_space_operations f2fs_node_aops; extern const struct address_space_operations f2fs_meta_aops; extern const struct inode_operations f2fs_dir_inode_operations; extern const struct inode_operations f2fs_symlink_inode_operations; extern const struct inode_operations f2fs_encrypted_symlink_inode_operations; extern const struct inode_operations f2fs_special_inode_operations; extern struct kmem_cache *f2fs_inode_entry_slab; /* * inline.c */ bool f2fs_may_inline_data(struct inode *inode); bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage); bool f2fs_may_inline_dentry(struct inode *inode); void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage); void f2fs_truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from); int f2fs_read_inline_data(struct inode *inode, struct folio *folio); int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page); int f2fs_convert_inline_inode(struct inode *inode); int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry); int f2fs_write_inline_data(struct inode *inode, struct folio *folio); int f2fs_recover_inline_data(struct inode *inode, struct page *npage); struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, const struct f2fs_filename *fname, struct page **res_page); int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent, struct page *ipage); int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname, struct inode *inode, nid_t ino, umode_t mode); void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, struct inode *dir, struct inode *inode); bool f2fs_empty_inline_dir(struct inode *dir); int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, struct fscrypt_str *fstr); int f2fs_inline_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); /* * shrinker.c */ unsigned long f2fs_shrink_count(struct shrinker *shrink, struct shrink_control *sc); unsigned long f2fs_shrink_scan(struct shrinker *shrink, struct shrink_control *sc); void f2fs_join_shrinker(struct f2fs_sb_info *sbi); void f2fs_leave_shrinker(struct f2fs_sb_info *sbi); /* * extent_cache.c */ bool sanity_check_extent_cache(struct inode *inode, struct page *ipage); void f2fs_init_extent_tree(struct inode *inode); void f2fs_drop_extent_tree(struct inode *inode); void f2fs_destroy_extent_node(struct inode *inode); void f2fs_destroy_extent_tree(struct inode *inode); void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi); int __init f2fs_create_extent_cache(void); void f2fs_destroy_extent_cache(void); /* read extent cache ops */ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage); bool f2fs_lookup_read_extent_cache(struct inode *inode, pgoff_t pgofs, struct extent_info *ei); bool f2fs_lookup_read_extent_cache_block(struct inode *inode, pgoff_t index, block_t *blkaddr); void f2fs_update_read_extent_cache(struct dnode_of_data *dn); void f2fs_update_read_extent_cache_range(struct dnode_of_data *dn, pgoff_t fofs, block_t blkaddr, unsigned int len); unsigned int f2fs_shrink_read_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink); /* block age extent cache ops */ void f2fs_init_age_extent_tree(struct inode *inode); bool f2fs_lookup_age_extent_cache(struct inode *inode, pgoff_t pgofs, struct extent_info *ei); void f2fs_update_age_extent_cache(struct dnode_of_data *dn); void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn, pgoff_t fofs, unsigned int len); unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink); /* * sysfs.c */ #define MIN_RA_MUL 2 #define MAX_RA_MUL 256 int __init f2fs_init_sysfs(void); void f2fs_exit_sysfs(void); int f2fs_register_sysfs(struct f2fs_sb_info *sbi); void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi); /* verity.c */ extern const struct fsverity_operations f2fs_verityops; /* * crypto support */ static inline bool f2fs_encrypted_file(struct inode *inode) { return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode); } static inline void f2fs_set_encrypted_inode(struct inode *inode) { #ifdef CONFIG_FS_ENCRYPTION file_set_encrypt(inode); f2fs_set_inode_flags(inode); #endif } /* * Returns true if the reads of the inode's data need to undergo some * postprocessing step, like decryption or authenticity verification. */ static inline bool f2fs_post_read_required(struct inode *inode) { return f2fs_encrypted_file(inode) || fsverity_active(inode) || f2fs_compressed_file(inode); } static inline bool f2fs_used_in_atomic_write(struct inode *inode) { return f2fs_is_atomic_file(inode) || f2fs_is_cow_file(inode); } static inline bool f2fs_meta_inode_gc_required(struct inode *inode) { return f2fs_post_read_required(inode) || f2fs_used_in_atomic_write(inode); } /* * compress.c */ #ifdef CONFIG_F2FS_FS_COMPRESSION enum cluster_check_type { CLUSTER_IS_COMPR, /* check only if compressed cluster */ CLUSTER_COMPR_BLKS, /* return # of compressed blocks in a cluster */ CLUSTER_RAW_BLKS /* return # of raw blocks in a cluster */ }; bool f2fs_is_compressed_page(struct page *page); struct page *f2fs_compress_control_page(struct page *page); int f2fs_prepare_compress_overwrite(struct inode *inode, struct page **pagep, pgoff_t index, void **fsdata); bool f2fs_compress_write_end(struct inode *inode, void *fsdata, pgoff_t index, unsigned copied); int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock); void f2fs_compress_write_end_io(struct bio *bio, struct page *page); bool f2fs_is_compress_backend_ready(struct inode *inode); bool f2fs_is_compress_level_valid(int alg, int lvl); int __init f2fs_init_compress_mempool(void); void f2fs_destroy_compress_mempool(void); void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task); void f2fs_end_read_compressed_page(struct page *page, bool failed, block_t blkaddr, bool in_task); bool f2fs_cluster_is_empty(struct compress_ctx *cc); bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index); bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages, int index, int nr_pages, bool uptodate); bool f2fs_sanity_check_cluster(struct dnode_of_data *dn); void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct folio *folio); int f2fs_write_multi_pages(struct compress_ctx *cc, int *submitted, struct writeback_control *wbc, enum iostat_type io_type); int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index); bool f2fs_is_sparse_cluster(struct inode *inode, pgoff_t index); void f2fs_update_read_extent_tree_range_compressed(struct inode *inode, pgoff_t fofs, block_t blkaddr, unsigned int llen, unsigned int c_len); int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, unsigned nr_pages, sector_t *last_block_in_bio, struct readahead_control *rac, bool for_write); struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, bool in_task); void f2fs_put_page_dic(struct page *page, bool in_task); unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, unsigned int ofs_in_node); int f2fs_init_compress_ctx(struct compress_ctx *cc); void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse); void f2fs_init_compress_info(struct f2fs_sb_info *sbi); int f2fs_init_compress_inode(struct f2fs_sb_info *sbi); void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi); int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi); void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi); int __init f2fs_init_compress_cache(void); void f2fs_destroy_compress_cache(void); struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi); void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr); void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page, nid_t ino, block_t blkaddr); bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page, block_t blkaddr); void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino); #define inc_compr_inode_stat(inode) \ do { \ struct f2fs_sb_info *sbi = F2FS_I_SB(inode); \ sbi->compr_new_inode++; \ } while (0) #define add_compr_block_stat(inode, blocks) \ do { \ struct f2fs_sb_info *sbi = F2FS_I_SB(inode); \ int diff = F2FS_I(inode)->i_cluster_size - blocks; \ sbi->compr_written_block += blocks; \ sbi->compr_saved_block += diff; \ } while (0) #else static inline bool f2fs_is_compressed_page(struct page *page) { return false; } static inline bool f2fs_is_compress_backend_ready(struct inode *inode) { if (!f2fs_compressed_file(inode)) return true; /* not support compression */ return false; } static inline bool f2fs_is_compress_level_valid(int alg, int lvl) { return false; } static inline struct page *f2fs_compress_control_page(struct page *page) { WARN_ON_ONCE(1); return ERR_PTR(-EINVAL); } static inline int __init f2fs_init_compress_mempool(void) { return 0; } static inline void f2fs_destroy_compress_mempool(void) { } static inline void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task) { } static inline void f2fs_end_read_compressed_page(struct page *page, bool failed, block_t blkaddr, bool in_task) { WARN_ON_ONCE(1); } static inline void f2fs_put_page_dic(struct page *page, bool in_task) { WARN_ON_ONCE(1); } static inline unsigned int f2fs_cluster_blocks_are_contiguous( struct dnode_of_data *dn, unsigned int ofs_in_node) { return 0; } static inline bool f2fs_sanity_check_cluster(struct dnode_of_data *dn) { return false; } static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { } static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { } static inline int __init f2fs_init_compress_cache(void) { return 0; } static inline void f2fs_destroy_compress_cache(void) { } static inline void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr) { } static inline void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page, nid_t ino, block_t blkaddr) { } static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page, block_t blkaddr) { return false; } static inline void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino) { } #define inc_compr_inode_stat(inode) do { } while (0) static inline int f2fs_is_compressed_cluster( struct inode *inode, pgoff_t index) { return 0; } static inline bool f2fs_is_sparse_cluster( struct inode *inode, pgoff_t index) { return true; } static inline void f2fs_update_read_extent_tree_range_compressed( struct inode *inode, pgoff_t fofs, block_t blkaddr, unsigned int llen, unsigned int c_len) { } #endif static inline int set_compress_context(struct inode *inode) { #ifdef CONFIG_F2FS_FS_COMPRESSION struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); fi->i_compress_algorithm = F2FS_OPTION(sbi).compress_algorithm; fi->i_log_cluster_size = F2FS_OPTION(sbi).compress_log_size; fi->i_compress_flag = F2FS_OPTION(sbi).compress_chksum ? BIT(COMPRESS_CHKSUM) : 0; fi->i_cluster_size = BIT(fi->i_log_cluster_size); if ((fi->i_compress_algorithm == COMPRESS_LZ4 || fi->i_compress_algorithm == COMPRESS_ZSTD) && F2FS_OPTION(sbi).compress_level) fi->i_compress_level = F2FS_OPTION(sbi).compress_level; fi->i_flags |= F2FS_COMPR_FL; set_inode_flag(inode, FI_COMPRESSED_FILE); stat_inc_compr_inode(inode); inc_compr_inode_stat(inode); f2fs_mark_inode_dirty_sync(inode, true); return 0; #else return -EOPNOTSUPP; #endif } static inline bool f2fs_disable_compressed_file(struct inode *inode) { struct f2fs_inode_info *fi = F2FS_I(inode); f2fs_down_write(&fi->i_sem); if (!f2fs_compressed_file(inode)) { f2fs_up_write(&fi->i_sem); return true; } if (f2fs_is_mmap_file(inode) || (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) { f2fs_up_write(&fi->i_sem); return false; } fi->i_flags &= ~F2FS_COMPR_FL; stat_dec_compr_inode(inode); clear_inode_flag(inode, FI_COMPRESSED_FILE); f2fs_mark_inode_dirty_sync(inode, true); f2fs_up_write(&fi->i_sem); return true; } #define F2FS_FEATURE_FUNCS(name, flagname) \ static inline bool f2fs_sb_has_##name(struct f2fs_sb_info *sbi) \ { \ return F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_##flagname); \ } F2FS_FEATURE_FUNCS(encrypt, ENCRYPT); F2FS_FEATURE_FUNCS(blkzoned, BLKZONED); F2FS_FEATURE_FUNCS(extra_attr, EXTRA_ATTR); F2FS_FEATURE_FUNCS(project_quota, PRJQUOTA); F2FS_FEATURE_FUNCS(inode_chksum, INODE_CHKSUM); F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR); F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO); F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME); F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); F2FS_FEATURE_FUNCS(verity, VERITY); F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM); F2FS_FEATURE_FUNCS(casefold, CASEFOLD); F2FS_FEATURE_FUNCS(compression, COMPRESSION); F2FS_FEATURE_FUNCS(readonly, RO); #ifdef CONFIG_BLK_DEV_ZONED static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi, block_t blkaddr) { unsigned int zno = blkaddr / sbi->blocks_per_blkz; return test_bit(zno, FDEV(devi).blkz_seq); } #endif static inline int f2fs_bdev_index(struct f2fs_sb_info *sbi, struct block_device *bdev) { int i; if (!f2fs_is_multi_device(sbi)) return 0; for (i = 0; i < sbi->s_ndevs; i++) if (FDEV(i).bdev == bdev) return i; WARN_ON(1); return -1; } static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi) { return f2fs_sb_has_blkzoned(sbi); } static inline bool f2fs_bdev_support_discard(struct block_device *bdev) { return bdev_max_discard_sectors(bdev) || bdev_is_zoned(bdev); } static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi) { int i; if (!f2fs_is_multi_device(sbi)) return f2fs_bdev_support_discard(sbi->sb->s_bdev); for (i = 0; i < sbi->s_ndevs; i++) if (f2fs_bdev_support_discard(FDEV(i).bdev)) return true; return false; } static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi) { return (test_opt(sbi, DISCARD) && f2fs_hw_support_discard(sbi)) || f2fs_hw_should_discard(sbi); } static inline bool f2fs_hw_is_readonly(struct f2fs_sb_info *sbi) { int i; if (!f2fs_is_multi_device(sbi)) return bdev_read_only(sbi->sb->s_bdev); for (i = 0; i < sbi->s_ndevs; i++) if (bdev_read_only(FDEV(i).bdev)) return true; return false; } static inline bool f2fs_dev_is_readonly(struct f2fs_sb_info *sbi) { return f2fs_sb_has_readonly(sbi) || f2fs_hw_is_readonly(sbi); } static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi) { return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS; } static inline bool f2fs_valid_pinned_area(struct f2fs_sb_info *sbi, block_t blkaddr) { if (f2fs_sb_has_blkzoned(sbi)) { int devi = f2fs_target_device_index(sbi, blkaddr); return !bdev_is_zoned(FDEV(devi).bdev); } return true; } static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi) { return F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW; } static inline bool f2fs_may_compress(struct inode *inode) { if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) || f2fs_is_atomic_file(inode) || f2fs_has_inline_data(inode) || f2fs_is_mmap_file(inode)) return false; return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode); } static inline void f2fs_i_compr_blocks_update(struct inode *inode, u64 blocks, bool add) { struct f2fs_inode_info *fi = F2FS_I(inode); int diff = fi->i_cluster_size - blocks; /* don't update i_compr_blocks if saved blocks were released */ if (!add && !atomic_read(&fi->i_compr_blocks)) return; if (add) { atomic_add(diff, &fi->i_compr_blocks); stat_add_compr_blocks(inode, diff); } else { atomic_sub(diff, &fi->i_compr_blocks); stat_sub_compr_blocks(inode, diff); } f2fs_mark_inode_dirty_sync(inode, true); } static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi, int flag) { if (!f2fs_is_multi_device(sbi)) return false; if (flag != F2FS_GET_BLOCK_DIO) return false; return sbi->aligned_blksize; } static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx) { return fsverity_active(inode) && idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); } #ifdef CONFIG_F2FS_FAULT_INJECTION extern int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate, unsigned long type); #else static inline int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate, unsigned long type) { return 0; } #endif static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) { #ifdef CONFIG_QUOTA if (f2fs_sb_has_quota_ino(sbi)) return true; if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] || F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] || F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) return true; #endif return false; } static inline bool f2fs_block_unit_discard(struct f2fs_sb_info *sbi) { return F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_BLOCK; } static inline void f2fs_io_schedule_timeout(long timeout) { set_current_state(TASK_UNINTERRUPTIBLE); io_schedule_timeout(timeout); } static inline void f2fs_handle_page_eio(struct f2fs_sb_info *sbi, struct folio *folio, enum page_type type) { pgoff_t ofs = folio->index; if (unlikely(f2fs_cp_error(sbi))) return; if (ofs == sbi->page_eio_ofs[type]) { if (sbi->page_eio_cnt[type]++ == MAX_RETRY_PAGE_EIO) set_ckpt_flags(sbi, CP_ERROR_FLAG); } else { sbi->page_eio_ofs[type] = ofs; sbi->page_eio_cnt[type] = 0; } } static inline bool f2fs_is_readonly(struct f2fs_sb_info *sbi) { return f2fs_sb_has_readonly(sbi) || f2fs_readonly(sbi->sb); } static inline void f2fs_truncate_meta_inode_pages(struct f2fs_sb_info *sbi, block_t blkaddr, unsigned int cnt) { bool need_submit = false; int i = 0; do { struct page *page; page = find_get_page(META_MAPPING(sbi), blkaddr + i); if (page) { if (folio_test_writeback(page_folio(page))) need_submit = true; f2fs_put_page(page, 0); } } while (++i < cnt && !need_submit); if (need_submit) f2fs_submit_merged_write_cond(sbi, sbi->meta_inode, NULL, 0, DATA); truncate_inode_pages_range(META_MAPPING(sbi), F2FS_BLK_TO_BYTES((loff_t)blkaddr), F2FS_BLK_END_BYTES((loff_t)(blkaddr + cnt - 1))); } static inline void f2fs_invalidate_internal_cache(struct f2fs_sb_info *sbi, block_t blkaddr) { f2fs_truncate_meta_inode_pages(sbi, blkaddr, 1); f2fs_invalidate_compress_page(sbi, blkaddr); } #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _LINUX_F2FS_H */ |
| 17 17 75 37 59 21 91 49 41 21 18 87 48 40 18 10 39 19 19 10 7 28 16 12 7 12 10 2 1 1 50 28 23 11 11 15 16 29 15 14 6 3 32 3 3 53 96 53 53 53 50 50 50 1 50 14 14 14 13 14 36 1 25 23 50 26 25 24 24 1 23 50 6 3 2 2 2 52 50 49 50 51 52 55 55 56 40 32 22 8 19 1 19 40 54 56 52 56 56 56 38 38 38 38 38 38 38 38 54 53 53 51 52 54 22 56 56 56 25 29 34 34 16 16 16 16 2 2 1 1 1 2 1 2 2 14 12 12 4 6 33 34 3 4 2 1 6 70 80 61 36 29 20 110 16 16 15 16 16 77 78 78 78 78 78 14 13 13 14 52 96 97 46 46 52 16 16 16 17 17 16 68 87 18 60 28 22 22 6 6 21 5 3 2 2 5 60 60 23 14 36 36 36 36 36 57 57 57 57 57 57 56 57 57 57 57 57 57 57 3 56 44 44 16 55 55 55 55 55 16 55 4 4 4 4 4 4 17 17 17 17 17 4 17 13 17 17 17 17 16 17 17 17 17 9 9 9 9 9 4 37 36 30 30 30 30 8 30 25 30 30 30 30 30 6 30 6 8 25 43 43 43 43 43 42 4 4 45 45 45 45 43 43 43 5 42 43 44 45 43 43 4 4 4 4 4 4 42 41 40 40 41 40 41 41 10 9 6 28 1 27 28 27 28 18 11 12 16 10 6 10 32 31 1 1 32 32 32 32 21 14 14 14 14 13 13 14 12 12 12 14 3 14 9 8 9 4 4 4 9 62 61 46 46 44 17 5 5 4 4 46 14 12 62 17 5 4 10 3 3 2 4 7 4 3 59 59 60 60 59 60 15 44 44 60 59 60 28 28 28 22 28 28 60 44 60 60 60 13 13 13 13 13 13 13 30 30 30 30 30 30 3 3 3 3 3 9 3 3 3 36 35 32 30 1 8 8 36 39 39 4 4 39 19 14 14 5 29 21 6 6 6 6 6 6 26 21 22 26 36 55 33 24 54 14 23 3 23 4 4 4 12 12 11 12 11 12 12 12 12 12 12 12 12 12 12 12 12 1 1 1 11 11 11 11 4 2 2 4 4 4 4 4 4 4 8 8 8 8 8 11 12 12 12 12 2 2 2 2 2 2 5 5 5 5 5 5 5 5 2 2 2 5 5 5 5 41 40 40 41 41 41 41 41 2 40 40 14 1 13 1 34 1 13 13 13 11 13 13 13 7 3 3 10 3 3 3 13 12 41 41 36 33 32 33 32 35 29 29 4 25 33 9 9 9 9 1 1 1 1 1 1 17 17 18 18 18 18 18 18 16 2 2 16 15 16 5 5 5 1 1 1 1 1 1 2 4 4 4 4 4 4 4 4 4 4 4 4 4 4 5 5 6 6 32 32 32 32 32 5 13 55 55 55 55 52 5 5 48 19 48 8 8 48 29 19 2 48 13 13 48 19 48 48 48 48 19 13 48 48 48 51 51 53 80 62 62 62 61 12 3 3 3 3 55 1 1 8 8 6 6 6 8 8 8 8 8 8 1 8 6 2 2 2 8 8 8 8 8 8 61 10 10 8 8 21 6 21 21 15 1 8 19 13 2 11 11 6 10 10 10 10 10 8 7 5 1 1 6 6 6 6 6 1 4 4 7 2 6 2 6 6 6 6 6 6 6 4 1 1 1 1 8 8 8 8 8 8 8 8 8 3 3 3 3 3 5 8 8 8 8 8 8 85 86 86 32 16 16 16 32 32 32 16 32 32 29 14 14 14 14 4 5 5 5 4 4 4 1 1 26 25 25 26 26 26 2 25 81 57 25 24 80 55 49 50 50 50 50 50 81 81 80 81 80 81 81 81 81 80 78 79 78 76 4 50 56 56 8 8 7 8 8 8 8 8 8 8 6 6 5 6 3 3 3 3 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic hugetlb support. * (C) Nadia Yvette Chambers, April 2004 */ #include <linux/list.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/seq_file.h> #include <linux/sysctl.h> #include <linux/highmem.h> #include <linux/mmu_notifier.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> #include <linux/compiler.h> #include <linux/cpuset.h> #include <linux/mutex.h> #include <linux/memblock.h> #include <linux/sysfs.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/string_helpers.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/jhash.h> #include <linux/numa.h> #include <linux/llist.h> #include <linux/cma.h> #include <linux/migrate.h> #include <linux/nospec.h> #include <linux/delayacct.h> #include <linux/memory.h> #include <linux/mm_inline.h> #include <linux/padata.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/node.h> #include <linux/page_owner.h> #include "internal.h" #include "hugetlb_vmemmap.h" int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata; #endif static unsigned long hugetlb_cma_size __initdata; __initdata struct list_head huge_boot_pages[MAX_NUMNODES]; /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, * free_huge_pages, and surplus_huge_pages. */ __cacheline_aligned_in_smp DEFINE_SPINLOCK(hugetlb_lock); /* * Serializes faults on the same logical page. This is used to * prevent spurious OOMs when the hugepage pool is fully utilized. */ static int num_fault_mutexes __ro_after_init; struct mutex *hugetlb_fault_mutex_table __ro_after_init; /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static void hugetlb_free_folio(struct folio *folio) { #ifdef CONFIG_CMA int nid = folio_nid(folio); if (cma_free_folio(hugetlb_cma[nid], folio)) return; #endif folio_put(folio); } static inline bool subpool_is_free(struct hugepage_subpool *spool) { if (spool->count) return false; if (spool->max_hpages != -1) return spool->used_hpages == 0; if (spool->min_hpages != -1) return spool->rsv_hpages == spool->min_hpages; return true; } static inline void unlock_or_release_subpool(struct hugepage_subpool *spool, unsigned long irq_flags) { spin_unlock_irqrestore(&spool->lock, irq_flags); /* If no pages are used, and no other handles to the subpool * remain, give up any reservations based on minimum size and * free the subpool */ if (subpool_is_free(spool)) { if (spool->min_hpages != -1) hugetlb_acct_memory(spool->hstate, -spool->min_hpages); kfree(spool); } } struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages) { struct hugepage_subpool *spool; spool = kzalloc(sizeof(*spool), GFP_KERNEL); if (!spool) return NULL; spin_lock_init(&spool->lock); spool->count = 1; spool->max_hpages = max_hpages; spool->hstate = h; spool->min_hpages = min_hpages; if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { kfree(spool); return NULL; } spool->rsv_hpages = min_hpages; return spool; } void hugepage_put_subpool(struct hugepage_subpool *spool) { unsigned long flags; spin_lock_irqsave(&spool->lock, flags); BUG_ON(!spool->count); spool->count--; unlock_or_release_subpool(spool, flags); } /* * Subpool accounting for allocating and reserving pages. * Return -ENOMEM if there are not enough resources to satisfy the * request. Otherwise, return the number of pages by which the * global pools must be adjusted (upward). The returned value may * only be different than the passed value (delta) in the case where * a subpool minimum size must be maintained. */ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; if (!spool) return ret; spin_lock_irq(&spool->lock); if (spool->max_hpages != -1) { /* maximum size accounting */ if ((spool->used_hpages + delta) <= spool->max_hpages) spool->used_hpages += delta; else { ret = -ENOMEM; goto unlock_ret; } } /* minimum size accounting */ if (spool->min_hpages != -1 && spool->rsv_hpages) { if (delta > spool->rsv_hpages) { /* * Asking for more reserves than those already taken on * behalf of subpool. Return difference. */ ret = delta - spool->rsv_hpages; spool->rsv_hpages = 0; } else { ret = 0; /* reserves already accounted for */ spool->rsv_hpages -= delta; } } unlock_ret: spin_unlock_irq(&spool->lock); return ret; } /* * Subpool accounting for freeing and unreserving pages. * Return the number of global page reservations that must be dropped. * The return value may only be different than the passed value (delta) * in the case where a subpool minimum size must be maintained. */ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; unsigned long flags; if (!spool) return delta; spin_lock_irqsave(&spool->lock, flags); if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; /* minimum size accounting */ if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { if (spool->rsv_hpages + delta <= spool->min_hpages) ret = 0; else ret = spool->rsv_hpages + delta - spool->min_hpages; spool->rsv_hpages += delta; if (spool->rsv_hpages > spool->min_hpages) spool->rsv_hpages = spool->min_hpages; } /* * If hugetlbfs_put_super couldn't free spool due to an outstanding * quota reference, free it now. */ unlock_or_release_subpool(spool, flags); return ret; } static inline struct hugepage_subpool *subpool_inode(struct inode *inode) { return HUGETLBFS_SB(inode->i_sb)->spool; } static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) { return subpool_inode(file_inode(vma->vm_file)); } /* * hugetlb vma_lock helper routines */ void hugetlb_vma_lock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_read(&resv_map->rw_sema); } } void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_read(&resv_map->rw_sema); } } void hugetlb_vma_lock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_write(&resv_map->rw_sema); } } void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_write(&resv_map->rw_sema); } } int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; return down_write_trylock(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); return down_write_trylock(&resv_map->rw_sema); } return 1; } void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; lockdep_assert_held(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); lockdep_assert_held(&resv_map->rw_sema); } } void hugetlb_vma_lock_release(struct kref *kref) { struct hugetlb_vma_lock *vma_lock = container_of(kref, struct hugetlb_vma_lock, refs); kfree(vma_lock); } static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) { struct vm_area_struct *vma = vma_lock->vma; /* * vma_lock structure may or not be released as a result of put, * it certainly will no longer be attached to vma so clear pointer. * Semaphore synchronizes access to vma_lock->vma field. */ vma_lock->vma = NULL; vma->vm_private_data = NULL; up_write(&vma_lock->rw_sema); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); } static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; __hugetlb_vma_unlock_write_put(vma_lock); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); /* no free for anon vmas, but still need to unlock */ up_write(&resv_map->rw_sema); } } static void hugetlb_vma_lock_free(struct vm_area_struct *vma) { /* * Only present in sharable vmas. */ if (!vma || !__vma_shareable_lock(vma)) return; if (vma->vm_private_data) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); __hugetlb_vma_unlock_write_put(vma_lock); } } static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma) { struct hugetlb_vma_lock *vma_lock; /* Only establish in (flags) sharable vmas */ if (!vma || !(vma->vm_flags & VM_MAYSHARE)) return; /* Should never get here with non-NULL vm_private_data */ if (vma->vm_private_data) return; vma_lock = kmalloc(sizeof(*vma_lock), GFP_KERNEL); if (!vma_lock) { /* * If we can not allocate structure, then vma can not * participate in pmd sharing. This is only a possible * performance enhancement and memory saving issue. * However, the lock is also used to synchronize page * faults with truncation. If the lock is not present, * unlikely races could leave pages in a file past i_size * until the file is removed. Warn in the unlikely case of * allocation failure. */ pr_warn_once("HugeTLB: unable to allocate vma specific lock\n"); return; } kref_init(&vma_lock->refs); init_rwsem(&vma_lock->rw_sema); vma_lock->vma = vma; vma->vm_private_data = vma_lock; } /* Helper that removes a struct file_region from the resv_map cache and returns * it for use. */ static struct file_region * get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) { struct file_region *nrg; VM_BUG_ON(resv->region_cache_count <= 0); resv->region_cache_count--; nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); nrg->from = from; nrg->to = to; return nrg; } static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg, struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB nrg->reservation_counter = rg->reservation_counter; nrg->css = rg->css; if (rg->css) css_get(rg->css); #endif } /* Helper that records hugetlb_cgroup uncharge info. */ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, struct hstate *h, struct resv_map *resv, struct file_region *nrg) { #ifdef CONFIG_CGROUP_HUGETLB if (h_cg) { nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; /* * The caller will hold exactly one h_cg->css reference for the * whole contiguous reservation region. But this area might be * scattered when there are already some file_regions reside in * it. As a result, many file_regions may share only one css * reference. In order to ensure that one file_region must hold * exactly one h_cg->css reference, we should do css_get for * each file_region and leave the reference held by caller * untouched. */ css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in * a resv_map. */ VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h)); } else { nrg->reservation_counter = NULL; nrg->css = NULL; } #endif } static void put_uncharge_info(struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB if (rg->css) css_put(rg->css); #endif } static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { #ifdef CONFIG_CGROUP_HUGETLB return rg->reservation_counter == org->reservation_counter && rg->css == org->css; #else return true; #endif } static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) { struct file_region *nrg, *prg; prg = list_prev_entry(rg, link); if (&prg->link != &resv->regions && prg->to == rg->from && has_same_uncharge_info(prg, rg)) { prg->to = rg->to; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); rg = prg; } nrg = list_next_entry(rg, link); if (&nrg->link != &resv->regions && nrg->from == rg->to && has_same_uncharge_info(nrg, rg)) { nrg->from = rg->from; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); } } static inline long hugetlb_resv_map_add(struct resv_map *map, struct list_head *rg, long from, long to, struct hstate *h, struct hugetlb_cgroup *cg, long *regions_needed) { struct file_region *nrg; if (!regions_needed) { nrg = get_file_region_entry_from_cache(map, from, to); record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg); list_add(&nrg->link, rg); coalesce_file_region(map, nrg); } else *regions_needed += 1; return to - from; } /* * Must be called with resv->lock held. * * Calling this with regions_needed != NULL will count the number of pages * to be added but will not modify the linked list. And regions_needed will * indicate the number of file_regions needed in the cache to carry out to add * the regions for this range. */ static long add_reservation_in_range(struct resv_map *resv, long f, long t, struct hugetlb_cgroup *h_cg, struct hstate *h, long *regions_needed) { long add = 0; struct list_head *head = &resv->regions; long last_accounted_offset = f; struct file_region *iter, *trg = NULL; struct list_head *rg = NULL; if (regions_needed) *regions_needed = 0; /* In this loop, we essentially handle an entry for the range * [last_accounted_offset, iter->from), at every iteration, with some * bounds checking. */ list_for_each_entry_safe(iter, trg, head, link) { /* Skip irrelevant regions that start before our range. */ if (iter->from < f) { /* If this region ends after the last accounted offset, * then we need to update last_accounted_offset. */ if (iter->to > last_accounted_offset) last_accounted_offset = iter->to; continue; } /* When we find a region that starts beyond our range, we've * finished. */ if (iter->from >= t) { rg = iter->link.prev; break; } /* Add an entry for last_accounted_offset -> iter->from, and * update last_accounted_offset. */ if (iter->from > last_accounted_offset) add += hugetlb_resv_map_add(resv, iter->link.prev, last_accounted_offset, iter->from, h, h_cg, regions_needed); last_accounted_offset = iter->to; } /* Handle the case where our range extends beyond * last_accounted_offset. */ if (!rg) rg = head->prev; if (last_accounted_offset < t) add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, t, h, h_cg, regions_needed); return add; } /* Must be called with resv->lock acquired. Will drop lock to allocate entries. */ static int allocate_file_region_entries(struct resv_map *resv, int regions_needed) __must_hold(&resv->lock) { LIST_HEAD(allocated_regions); int to_allocate = 0, i = 0; struct file_region *trg = NULL, *rg = NULL; VM_BUG_ON(regions_needed < 0); /* * Check for sufficient descriptors in the cache to accommodate * the number of in progress add operations plus regions_needed. * * This is a while loop because when we drop the lock, some other call * to region_add or region_del may have consumed some region_entries, * so we keep looping here until we finally have enough entries for * (adds_in_progress + regions_needed). */ while (resv->region_cache_count < (resv->adds_in_progress + regions_needed)) { to_allocate = resv->adds_in_progress + regions_needed - resv->region_cache_count; /* At this point, we should have enough entries in the cache * for all the existing adds_in_progress. We should only be * needing to allocate for regions_needed. */ VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); spin_unlock(&resv->lock); for (i = 0; i < to_allocate; i++) { trg = kmalloc(sizeof(*trg), GFP_KERNEL); if (!trg) goto out_of_memory; list_add(&trg->link, &allocated_regions); } spin_lock(&resv->lock); list_splice(&allocated_regions, &resv->region_cache); resv->region_cache_count += to_allocate; } return 0; out_of_memory: list_for_each_entry_safe(rg, trg, &allocated_regions, link) { list_del(&rg->link); kfree(rg); } return -ENOMEM; } /* * Add the huge page range represented by [f, t) to the reserve * map. Regions will be taken from the cache to fill in this range. * Sufficient regions should exist in the cache due to the previous * call to region_chg with the same range, but in some cases the cache will not * have sufficient entries due to races with other code doing region_add or * region_del. The extra needed entries will be allocated. * * regions_needed is the out value provided by a previous call to region_chg. * * Return the number of new huge pages added to the map. This number is greater * than or equal to zero. If file_region entries needed to be allocated for * this operation and we were not able to allocate, it returns -ENOMEM. * region_add of regions of length 1 never allocate file_regions and cannot * fail; region_chg will always allocate at least 1 entry and a region_add for * 1 page will only require at most 1 entry. */ static long region_add(struct resv_map *resv, long f, long t, long in_regions_needed, struct hstate *h, struct hugetlb_cgroup *h_cg) { long add = 0, actual_regions_needed = 0; spin_lock(&resv->lock); retry: /* Count how many regions are actually needed to execute this add. */ add_reservation_in_range(resv, f, t, NULL, NULL, &actual_regions_needed); /* * Check for sufficient descriptors in the cache to accommodate * this add operation. Note that actual_regions_needed may be greater * than in_regions_needed, as the resv_map may have been modified since * the region_chg call. In this case, we need to make sure that we * allocate extra entries, such that we have enough for all the * existing adds_in_progress, plus the excess needed for this * operation. */ if (actual_regions_needed > in_regions_needed && resv->region_cache_count < resv->adds_in_progress + (actual_regions_needed - in_regions_needed)) { /* region_add operation of range 1 should never need to * allocate file_region entries. */ VM_BUG_ON(t - f <= 1); if (allocate_file_region_entries( resv, actual_regions_needed - in_regions_needed)) { return -ENOMEM; } goto retry; } add = add_reservation_in_range(resv, f, t, h_cg, h, NULL); resv->adds_in_progress -= in_regions_needed; spin_unlock(&resv->lock); return add; } /* * Examine the existing reserve map and determine how many * huge pages in the specified range [f, t) are NOT currently * represented. This routine is called before a subsequent * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the * map. A number of new file_region structures is added to the cache as a * placeholder, for the subsequent region_add call to use. At least 1 * file_region structure is added. * * out_regions_needed is the number of regions added to the * resv->adds_in_progress. This value needs to be provided to a follow up call * to region_add or region_abort for proper accounting. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to * zero. -ENOMEM is returned if a new file_region structure or cache entry * is needed and can not be allocated. */ static long region_chg(struct resv_map *resv, long f, long t, long *out_regions_needed) { long chg = 0; spin_lock(&resv->lock); /* Count how many hugepages in this range are NOT represented. */ chg = add_reservation_in_range(resv, f, t, NULL, NULL, out_regions_needed); if (*out_regions_needed == 0) *out_regions_needed = 1; if (allocate_file_region_entries(resv, *out_regions_needed)) return -ENOMEM; resv->adds_in_progress += *out_regions_needed; spin_unlock(&resv->lock); return chg; } /* * Abort the in progress add operation. The adds_in_progress field * of the resv_map keeps track of the operations in progress between * calls to region_chg and region_add. Operations are sometimes * aborted after the call to region_chg. In such cases, region_abort * is called to decrement the adds_in_progress counter. regions_needed * is the value returned by the region_chg call, it is used to decrement * the adds_in_progress counter. * * NOTE: The range arguments [f, t) are not needed or used in this * routine. They are kept to make reading the calling code easier as * arguments will match the associated region_chg call. */ static void region_abort(struct resv_map *resv, long f, long t, long regions_needed) { spin_lock(&resv->lock); VM_BUG_ON(!resv->region_cache_count); resv->adds_in_progress -= regions_needed; spin_unlock(&resv->lock); } /* * Delete the specified range [f, t) from the reserve map. If the * t parameter is LONG_MAX, this indicates that ALL regions after f * should be deleted. Locate the regions which intersect [f, t) * and either trim, delete or split the existing regions. * * Returns the number of huge pages deleted from the reserve map. * In the normal case, the return value is zero or more. In the * case where a region must be split, a new region descriptor must * be allocated. If the allocation fails, -ENOMEM will be returned. * NOTE: If the parameter t == LONG_MAX, then we will never split * a region and possibly return -ENOMEM. Callers specifying * t == LONG_MAX do not need to check for -ENOMEM error. */ static long region_del(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *trg; struct file_region *nrg = NULL; long del = 0; retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { /* * Skip regions before the range to be deleted. file_region * ranges are normally of the form [from, to). However, there * may be a "placeholder" entry in the map which is of the form * (from, to) with from == to. Check for placeholder entries * at the beginning of the range to be deleted. */ if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; if (rg->from >= t) break; if (f > rg->from && t < rg->to) { /* Must split region */ /* * Check for an entry in the cache before dropping * lock and attempting allocation. */ if (!nrg && resv->region_cache_count > resv->adds_in_progress) { nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); resv->region_cache_count--; } if (!nrg) { spin_unlock(&resv->lock); nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); if (!nrg) return -ENOMEM; goto retry; } del += t - f; hugetlb_cgroup_uncharge_file_region( resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; nrg->to = rg->to; copy_hugetlb_cgroup_uncharge_info(nrg, rg); INIT_LIST_HEAD(&nrg->link); /* Original entry is trimmed */ rg->to = f; list_add(&nrg->link, &rg->link); nrg = NULL; break; } if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; } if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - f, false); del += rg->to - f; rg->to = f; } } spin_unlock(&resv->lock); kfree(nrg); return del; } /* * A rare out of memory error was encountered which prevented removal of * the reserve map region for a page. The huge page itself was free'ed * and removed from the page cache. This routine will adjust the subpool * usage count, and the global reserve count if needed. By incrementing * these counts, the reserve map entry which could not be deleted will * appear as a "reserved" entry instead of simply dangling with incorrect * counts. */ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); if (!hugetlb_acct_memory(h, 1)) reserved = true; } else if (!rsv_adjust) { reserved = true; } if (!reserved) pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* * Count and return the number of huge pages in the reserve map * that intersect with the range [f, t). */ static long region_count(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg; long chg = 0; spin_lock(&resv->lock); /* Locate each segment we overlap with, and count that overlap. */ list_for_each_entry(rg, head, link) { long seg_from; long seg_to; if (rg->to <= f) continue; if (rg->from >= t) break; seg_from = max(rg->from, f); seg_to = min(rg->to, t); chg += seg_to - seg_from; } spin_unlock(&resv->lock); return chg; } /* * Convert the address within this vma to the page offset within * the mapping, huge page units here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return ((address - vma->vm_start) >> huge_page_shift(h)) + (vma->vm_pgoff >> huge_page_order(h)); } /** * vma_kernel_pagesize - Page size granularity for this VMA. * @vma: The user mapping. * * Folios in this VMA will be aligned to, and at least the size of the * number of bytes returned by this function. * * Return: The default size of the folios allocated when backing a VMA. */ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->pagesize) return vma->vm_ops->pagesize(vma); return PAGE_SIZE; } EXPORT_SYMBOL_GPL(vma_kernel_pagesize); /* * Return the page size being used by the MMU to back a VMA. In the majority * of cases, the page size used by the kernel matches the MMU size. On * architectures where it differs, an architecture-specific 'strong' * version of this symbol is required. */ __weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return vma_kernel_pagesize(vma); } /* * Flags for MAP_PRIVATE reservations. These are stored in the bottom * bits of the reservation map pointer, which are always clear due to * alignment. */ #define HPAGE_RESV_OWNER (1UL << 0) #define HPAGE_RESV_UNMAPPED (1UL << 1) #define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) /* * These helpers are used to track how many pages are reserved for * faults in a MAP_PRIVATE mapping. Only the process that called mmap() * is guaranteed to have their future faults succeed. * * With the exception of hugetlb_dup_vma_private() which is called at fork(), * the reserve counters are updated with the hugetlb_lock held. It is safe * to reset the VMA at fork() time as it is not in use yet and there is no * chance of the global counters getting corrupted as a result of the values. * * The private mapping reservation is represented in a subtly different * manner to a shared mapping. A shared mapping has a region map associated * with the underlying file, this region map represents the backing file * pages which have ever had a reservation assigned which this persists even * after the page is instantiated. A private mapping has a region map * associated with the original mmap which is attached to all VMAs which * reference it, this region map represents those offsets which have consumed * reservation ie. where pages have been instantiated. */ static unsigned long get_vma_private_data(struct vm_area_struct *vma) { return (unsigned long)vma->vm_private_data; } static void set_vma_private_data(struct vm_area_struct *vma, unsigned long value) { vma->vm_private_data = (void *)value; } static void resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map, struct hugetlb_cgroup *h_cg, struct hstate *h) { #ifdef CONFIG_CGROUP_HUGETLB if (!h_cg || !h) { resv_map->reservation_counter = NULL; resv_map->pages_per_hpage = 0; resv_map->css = NULL; } else { resv_map->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; resv_map->pages_per_hpage = pages_per_huge_page(h); resv_map->css = &h_cg->css; } #endif } struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL); if (!resv_map || !rg) { kfree(resv_map); kfree(rg); return NULL; } kref_init(&resv_map->refs); spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); init_rwsem(&resv_map->rw_sema); resv_map->adds_in_progress = 0; /* * Initialize these to 0. On shared mappings, 0's here indicate these * fields don't do cgroup accounting. On private mappings, these will be * re-initialized to the proper values, to indicate that hugetlb cgroup * reservations are to be un-charged from here. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL); INIT_LIST_HEAD(&resv_map->region_cache); list_add(&rg->link, &resv_map->region_cache); resv_map->region_cache_count = 1; return resv_map; } void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); struct list_head *head = &resv_map->region_cache; struct file_region *rg, *trg; /* Clear out any active regions before we release the map. */ region_del(resv_map, 0, LONG_MAX); /* ... and any entries left in the cache */ list_for_each_entry_safe(rg, trg, head, link) { list_del(&rg->link); kfree(rg); } VM_BUG_ON(resv_map->adds_in_progress); kfree(resv_map); } static inline struct resv_map *inode_resv_map(struct inode *inode) { /* * At inode evict time, i_mapping may not point to the original * address space within the inode. This original address space * contains the pointer to the resv_map. So, always use the * address space embedded within the inode. * The VERY common case is inode->mapping == &inode->i_data but, * this may not be true for device special inodes. */ return (struct resv_map *)(&inode->i_data)->i_private_data; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); if (vma->vm_flags & VM_MAYSHARE) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; return inode_resv_map(inode); } else { return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); } } static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, (unsigned long)map); } static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); return (get_vma_private_data(vma) & flag) != 0; } bool __vma_private_lock(struct vm_area_struct *vma) { return !(vma->vm_flags & VM_MAYSHARE) && get_vma_private_data(vma) & ~HPAGE_RESV_MASK && is_vma_resv_set(vma, HPAGE_RESV_OWNER); } void hugetlb_dup_vma_private(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); /* * Clear vm_private_data * - For shared mappings this is a per-vma semaphore that may be * allocated in a subsequent call to hugetlb_vm_op_open. * Before clearing, make sure pointer is not associated with vma * as this will leak the structure. This is the case when called * via clear_vma_resv_huge_pages() and hugetlb_vm_op_open has already * been called to allocate a new structure. * - For MAP_PRIVATE mappings, this is the reserve map which does * not apply to children. Faults generated by the children are * not guaranteed to succeed, even if read-only. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock && vma_lock->vma != vma) vma->vm_private_data = NULL; } else vma->vm_private_data = NULL; } /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. * This function should be only used by move_vma() and operate on * same sized vma. It should never come here with last ref on the * reservation. */ void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { /* * Clear the old hugetlb private page reservation. * It has already been transferred to new_vma. * * During a mremap() operation of a hugetlb vma we call move_vma() * which copies vma into new_vma and unmaps vma. After the copy * operation both new_vma and vma share a reference to the resv_map * struct, and at that point vma is about to be unmapped. We don't * want to return the reservation to the pool at unmap of vma because * the reservation still lives on in new_vma, so simply decrement the * ref here and remove the resv_map reference from this vma. */ struct resv_map *reservations = vma_resv_map(vma); if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_put_hugetlb_cgroup_uncharge_info(reservations); kref_put(&reservations->refs, resv_map_release); } hugetlb_dup_vma_private(vma); } /* Returns true if the VMA has associated reserve pages */ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) { if (vma->vm_flags & VM_NORESERVE) { /* * This address is already reserved by other process(chg == 0), * so, we should decrement reserved count. Without decrementing, * reserve count remains after releasing inode, because this * allocated page will go into page cache and is regarded as * coming from reserved pool in releasing step. Currently, we * don't have any other solution to deal with this situation * properly, so add work-around here. */ if (vma->vm_flags & VM_MAYSHARE && chg == 0) return true; else return false; } /* Shared mappings always use reserves */ if (vma->vm_flags & VM_MAYSHARE) { /* * We know VM_NORESERVE is not set. Therefore, there SHOULD * be a region map for all pages. The only situation where * there is no region map is if a hole was punched via * fallocate. In this case, there really are no reserves to * use. This situation is indicated if chg != 0. */ if (chg) return false; else return true; } /* * Only the process that called mmap() has reserves for * private mappings. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { /* * Like the shared case above, a hole punch or truncate * could have been performed on the private mapping. * Examine the value of chg to determine if reserves * actually exist or were previously consumed. * Very Subtle - The value of chg comes from a previous * call to vma_needs_reserves(). The reserve map for * private mappings has different (opposite) semantics * than that of shared mappings. vma_needs_reserves() * has already taken this difference in semantics into * account. Therefore, the meaning of chg is the same * as in the shared case above. Code could easily be * combined, but keeping it separate draws attention to * subtle differences. */ if (chg) return false; else return true; } return false; } static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio) { int nid = folio_nid(folio); lockdep_assert_held(&hugetlb_lock); VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); list_move(&folio->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; folio_set_hugetlb_freed(folio); } static struct folio *dequeue_hugetlb_folio_node_exact(struct hstate *h, int nid) { struct folio *folio; bool pin = !!(current->flags & PF_MEMALLOC_PIN); lockdep_assert_held(&hugetlb_lock); list_for_each_entry(folio, &h->hugepage_freelists[nid], lru) { if (pin && !folio_is_longterm_pinnable(folio)) continue; if (folio_test_hwpoison(folio)) continue; list_move(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return folio; } return NULL; } static struct folio *dequeue_hugetlb_folio_nodemask(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { unsigned int cpuset_mems_cookie; struct zonelist *zonelist; struct zone *zone; struct zoneref *z; int node = NUMA_NO_NODE; /* 'nid' should not be NUMA_NO_NODE. Try to catch any misuse of it and rectifiy. */ if (nid == NUMA_NO_NODE) nid = numa_node_id(); zonelist = node_zonelist(nid, gfp_mask); retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) { struct folio *folio; if (!cpuset_zone_allowed(zone, gfp_mask)) continue; /* * no need to ask again on the same node. Pool is node rather than * zone aware */ if (zone_to_nid(zone) == node) continue; node = zone_to_nid(zone); folio = dequeue_hugetlb_folio_node_exact(h, node); if (folio) return folio; } if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return NULL; } static unsigned long available_huge_pages(struct hstate *h) { return h->free_huge_pages - h->resv_huge_pages; } static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve, long chg) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask; nodemask_t *nodemask; int nid; /* * A child process with MAP_PRIVATE mappings created by their parent * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ if (!vma_has_reserves(vma, chg) && !available_huge_pages(h)) goto err; /* If reserves cannot be used, ensure enough pages are in the pool */ if (avoid_reserve && !available_huge_pages(h)) goto err; gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); if (folio && !avoid_reserve && vma_has_reserves(vma, chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } mpol_cond_put(mpol); return folio; err: return NULL; } /* * common helper functions for hstate_next_node_to_{alloc|free}. * We may have allocated or freed a huge page based on a different * nodes_allowed previously, so h->next_node_to_{alloc|free} might * be outside of *nodes_allowed. Ensure that we use an allowed * node for alloc or free. */ static int next_node_allowed(int nid, nodemask_t *nodes_allowed) { nid = next_node_in(nid, *nodes_allowed); VM_BUG_ON(nid >= MAX_NUMNODES); return nid; } static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) { if (!node_isset(nid, *nodes_allowed)) nid = next_node_allowed(nid, nodes_allowed); return nid; } /* * returns the previously saved node ["this node"] from which to * allocate a persistent huge page for the pool and advance the * next node from which to allocate, handling wrap at end of node * mask. */ static int hstate_next_node_to_alloc(int *next_node, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(*next_node, nodes_allowed); *next_node = next_node_allowed(nid, nodes_allowed); return nid; } /* * helper for remove_pool_hugetlb_folio() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. */ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); return nid; } #define for_each_node_mask_to_alloc(next_node, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_alloc(next_node, mask)) || 1); \ nr_nodes--) #define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE #ifdef CONFIG_CONTIG_ALLOC static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { struct folio *folio; int order = huge_page_order(h); bool retried = false; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); retry: folio = NULL; #ifdef CONFIG_CMA { int node; if (hugetlb_cma[nid]) folio = cma_alloc_folio(hugetlb_cma[nid], order, gfp_mask); if (!folio && !(gfp_mask & __GFP_THISNODE)) { for_each_node_mask(node, *nodemask) { if (node == nid || !hugetlb_cma[node]) continue; folio = cma_alloc_folio(hugetlb_cma[node], order, gfp_mask); if (folio) break; } } } #endif if (!folio) { folio = folio_alloc_gigantic(order, gfp_mask, nid, nodemask); if (!folio) return NULL; } if (folio_ref_freeze(folio, 1)) return folio; pr_warn("HugeTLB: unexpected refcount on PFN %lu\n", folio_pfn(folio)); hugetlb_free_folio(folio); if (!retried) { retried = true; goto retry; } return NULL; } #else /* !CONFIG_CONTIG_ALLOC */ static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* CONFIG_CONTIG_ALLOC */ #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* * Remove hugetlb folio from lists. * If vmemmap exists for the folio, clear the hugetlb flag so that the * folio appears as just a compound page. Otherwise, wait until after * allocating vmemmap to clear the flag. * * Must be called with hugetlb lock held. */ static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int nid = folio_nid(folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; list_del(&folio->lru); if (folio_test_hugetlb_freed(folio)) { folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; } if (adjust_surplus) { h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; } /* * We can only clear the hugetlb flag after allocating vmemmap * pages. Otherwise, someone (memory error handling) may try to write * to tail struct pages. */ if (!folio_test_hugetlb_vmemmap_optimized(folio)) __folio_clear_hugetlb(folio); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; } static void add_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int nid = folio_nid(folio); VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio); lockdep_assert_held(&hugetlb_lock); INIT_LIST_HEAD(&folio->lru); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; if (adjust_surplus) { h->surplus_huge_pages++; h->surplus_huge_pages_node[nid]++; } __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above * folio_change_private(folio, NULL) cleared it. */ folio_set_hugetlb_vmemmap_optimized(folio); arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); } static void __update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio) { bool clear_flag = folio_test_hugetlb_vmemmap_optimized(folio); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; /* * If we don't know which subpages are hwpoisoned, we can't free * the hugepage, so it's leaked intentionally. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; /* * If folio is not vmemmap optimized (!clear_flag), then the folio * is no longer identified as a hugetlb page. hugetlb_vmemmap_restore_folio * can only be passed hugetlb pages and will BUG otherwise. */ if (clear_flag && hugetlb_vmemmap_restore_folio(h, folio)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the * page and put the page back on the hugetlb free list and treat * as a surplus page. */ add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); return; } /* * If vmemmap pages were allocated above, then we need to clear the * hugetlb flag under the hugetlb lock. */ if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } /* * Move PageHWPoison flag from head page to the raw error pages, * which makes any healthy subpages reusable. */ if (unlikely(folio_test_hwpoison(folio))) folio_clear_hugetlb_hwpoison(folio); folio_ref_unfreeze(folio, 1); INIT_LIST_HEAD(&folio->_deferred_list); hugetlb_free_folio(folio); } /* * As update_and_free_hugetlb_folio() can be called under any context, so we cannot * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate * the vmemmap pages. * * free_hpage_workfn() locklessly retrieves the linked list of pages to be * freed and frees them one-by-one. As the page->mapping pointer is going * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node * structure of a lockless linked list of huge pages to be freed. */ static LLIST_HEAD(hpage_freelist); static void free_hpage_workfn(struct work_struct *work) { struct llist_node *node; node = llist_del_all(&hpage_freelist); while (node) { struct folio *folio; struct hstate *h; folio = container_of((struct address_space **)node, struct folio, mapping); node = node->next; folio->mapping = NULL; /* * The VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio) in * folio_hstate() is going to trigger because a previous call to * remove_hugetlb_folio() will clear the hugetlb bit, so do * not use folio_hstate() directly. */ h = size_to_hstate(folio_size(folio)); __update_and_free_hugetlb_folio(h, folio); cond_resched(); } } static DECLARE_WORK(free_hpage_work, free_hpage_workfn); static inline void flush_free_hpage_work(struct hstate *h) { if (hugetlb_vmemmap_optimizable(h)) flush_work(&free_hpage_work); } static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio, bool atomic) { if (!folio_test_hugetlb_vmemmap_optimized(folio) || !atomic) { __update_and_free_hugetlb_folio(h, folio); return; } /* * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages. * * Only call schedule_work() if hpage_freelist is previously * empty. Otherwise, schedule_work() had been called but the workfn * hasn't retrieved the list yet. */ if (llist_add((struct llist_node *)&folio->mapping, &hpage_freelist)) schedule_work(&free_hpage_work); } static void bulk_vmemmap_restore_error(struct hstate *h, struct list_head *folio_list, struct list_head *non_hvo_folios) { struct folio *folio, *t_folio; if (!list_empty(non_hvo_folios)) { /* * Free any restored hugetlb pages so that restore of the * entire list can be retried. * The idea is that in the common case of ENOMEM errors freeing * hugetlb pages with vmemmap we will free up memory so that we * can allocate vmemmap for more hugetlb pages. */ list_for_each_entry_safe(folio, t_folio, non_hvo_folios, lru) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } else { /* * In the case where there are no folios which can be * immediately freed, we loop through the list trying to restore * vmemmap individually in the hope that someone elsewhere may * have done something to cause success (such as freeing some * memory). If unable to restore a hugetlb page, the hugetlb * page is made a surplus page and removed from the list. * If are able to restore vmemmap and free one hugetlb page, we * quit processing the list to retry the bulk operation. */ list_for_each_entry_safe(folio, t_folio, folio_list, lru) if (hugetlb_vmemmap_restore_folio(h, folio)) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); } else { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); break; } } } static void update_and_free_pages_bulk(struct hstate *h, struct list_head *folio_list) { long ret; struct folio *folio, *t_folio; LIST_HEAD(non_hvo_folios); /* * First allocate required vmemmmap (if necessary) for all folios. * Carefully handle errors and free up any available hugetlb pages * in an effort to make forward progress. */ retry: ret = hugetlb_vmemmap_restore_folios(h, folio_list, &non_hvo_folios); if (ret < 0) { bulk_vmemmap_restore_error(h, folio_list, &non_hvo_folios); goto retry; } /* * At this point, list should be empty, ret should be >= 0 and there * should only be pages on the non_hvo_folios list. * Do note that the non_hvo_folios list could be empty. * Without HVO enabled, ret will be 0 and there is no need to call * __folio_clear_hugetlb as this was done previously. */ VM_WARN_ON(!list_empty(folio_list)); VM_WARN_ON(ret < 0); if (!list_empty(&non_hvo_folios) && ret) { spin_lock_irq(&hugetlb_lock); list_for_each_entry(folio, &non_hvo_folios, lru) __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } list_for_each_entry_safe(folio, t_folio, &non_hvo_folios, lru) { update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } struct hstate *size_to_hstate(unsigned long size) { struct hstate *h; for_each_hstate(h) { if (huge_page_size(h) == size) return h; } return NULL; } void free_huge_folio(struct folio *folio) { /* * Can't pass hstate in here because it is called from the * generic mm code. */ struct hstate *h = folio_hstate(folio); int nid = folio_nid(folio); struct hugepage_subpool *spool = hugetlb_folio_subpool(folio); bool restore_reserve; unsigned long flags; VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); VM_BUG_ON_FOLIO(folio_mapcount(folio), folio); hugetlb_set_folio_subpool(folio, NULL); if (folio_test_anon(folio)) __ClearPageAnonExclusive(&folio->page); folio->mapping = NULL; restore_reserve = folio_test_hugetlb_restore_reserve(folio); folio_clear_hugetlb_restore_reserve(folio); /* * If HPageRestoreReserve was set on page, page allocation consumed a * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the * reservation, do not call hugepage_subpool_put_pages() as this will * remove the reserved page from the subpool. */ if (!restore_reserve) { /* * A return code of zero implies that the subpool will be * under its minimum size if the reservation is not restored * after page is free. Therefore, force restore_reserve * operation. */ if (hugepage_subpool_put_pages(spool, 1) == 0) restore_reserve = true; } spin_lock_irqsave(&hugetlb_lock, flags); folio_clear_hugetlb_migratable(folio); hugetlb_cgroup_uncharge_folio(hstate_index(h), pages_per_huge_page(h), folio); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); mem_cgroup_uncharge(folio); if (restore_reserve) h->resv_huge_pages++; if (folio_test_hugetlb_temporary(folio)) { remove_hugetlb_folio(h, folio, false); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ remove_hugetlb_folio(h, folio, true); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else { arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } /* * Must be called with the hugetlb lock held */ static void __prep_account_new_huge_page(struct hstate *h, int nid) { lockdep_assert_held(&hugetlb_lock); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; } static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio) { __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); set_hugetlb_cgroup_rsvd(folio, NULL); } static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) { init_new_hugetlb_folio(h, folio); hugetlb_vmemmap_optimize_folio(h, folio); } static void prep_new_hugetlb_folio(struct hstate *h, struct folio *folio, int nid) { __prep_new_hugetlb_folio(h, folio); spin_lock_irq(&hugetlb_lock); __prep_account_new_huge_page(h, nid); spin_unlock_irq(&hugetlb_lock); } /* * Find and lock address space (mapping) in write mode. * * Upon entry, the folio is locked which means that folio_mapping() is * stable. Due to locking order, we can only trylock_write. If we can * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (!mapping) return mapping; if (i_mmap_trylock_write(mapping)) return mapping; return NULL; } static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { int order = huge_page_order(h); struct folio *folio; bool alloc_try_hard = true; bool retry = true; /* * By default we always try hard to allocate the folio with * __GFP_RETRY_MAYFAIL flag. However, if we are allocating folios in * a loop (to adjust global huge page counts) and previous allocation * failed, do not continue to try hard on the same node. Use the * node_alloc_noretry bitmap to manage this state information. */ if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry)) alloc_try_hard = false; if (alloc_try_hard) gfp_mask |= __GFP_RETRY_MAYFAIL; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); retry: folio = __folio_alloc(gfp_mask, order, nid, nmask); /* Ensure hugetlb folio won't have large_rmappable flag set. */ if (folio) folio_clear_large_rmappable(folio); if (folio && !folio_ref_freeze(folio, 1)) { folio_put(folio); if (retry) { /* retry once */ retry = false; goto retry; } /* WOW! twice in a row. */ pr_warn("HugeTLB unexpected inflated folio ref count\n"); folio = NULL; } /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a * folio this indicates an overall state change. Clear bit so * that we resume normal 'try hard' allocations. */ if (node_alloc_noretry && folio && !alloc_try_hard) node_clear(nid, *node_alloc_noretry); /* * If we tried hard to get a folio but failed, set bit so that * subsequent attempts will not try as hard until there is an * overall state change. */ if (node_alloc_noretry && !folio && alloc_try_hard) node_set(nid, *node_alloc_noretry); if (!folio) { __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); return NULL; } __count_vm_event(HTLB_BUDDY_PGALLOC); return folio; } static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; if (hstate_is_gigantic(h)) folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); else folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); if (folio) init_new_hugetlb_folio(h, folio); return folio; } /* * Common helper to allocate a fresh hugetlb page. All specific allocators * should use this function to get new hugetlb pages * * Note that returned page is 'frozen': ref count of head page and all tail * pages is zero. */ static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; if (hstate_is_gigantic(h)) folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); else folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); if (!folio) return NULL; prep_new_hugetlb_folio(h, folio, folio_nid(folio)); return folio; } static void prep_and_add_allocated_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_folios(h, folio_list); /* Add all new pool pages to free lists in one lock cycle */ spin_lock_irqsave(&hugetlb_lock, flags); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { __prep_account_new_huge_page(h, folio_nid(folio)); enqueue_hugetlb_folio(h, folio); } spin_unlock_irqrestore(&hugetlb_lock, flags); } /* * Allocates a fresh hugetlb page in a node interleaved manner. The page * will later be added to the appropriate hugetlb pool. */ static struct folio *alloc_pool_huge_folio(struct hstate *h, nodemask_t *nodes_allowed, nodemask_t *node_alloc_noretry, int *next_node) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; int nr_nodes, node; for_each_node_mask_to_alloc(next_node, nr_nodes, node, nodes_allowed) { struct folio *folio; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node, nodes_allowed, node_alloc_noretry); if (folio) return folio; } return NULL; } /* * Remove huge page from pool from next node to free. Attempt to keep * persistent huge pages more or less balanced over allowed nodes. * This routine only 'removes' the hugetlb page. The caller must make * an additional call to free the page to low level allocators. * Called with hugetlb_lock locked. */ static struct folio *remove_pool_hugetlb_folio(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { int nr_nodes, node; struct folio *folio = NULL; lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine * nodes with surplus pages. */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { folio = list_entry(h->hugepage_freelists[node].next, struct folio, lru); remove_hugetlb_folio(h, folio, acct_surplus); break; } } return folio; } /* * Dissolve a given free hugetlb folio into free buddy pages. This function * does nothing for in-use hugetlb folios and non-hugetlb folios. * This function returns values like below: * * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages * when the system is under memory pressure and the feature of * freeing unused vmemmap pages associated with each hugetlb page * is enabled. * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use * (allocated or reserved.) * 0: successfully dissolved free hugepages or the page is not a * hugepage (considered as already dissolved) */ int dissolve_free_hugetlb_folio(struct folio *folio) { int rc = -EBUSY; retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!folio_test_hugetlb(folio)) return 0; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio)) { rc = 0; goto out; } if (!folio_ref_count(folio)) { struct hstate *h = folio_hstate(folio); if (!available_huge_pages(h)) goto out; /* * We should make sure that the page is already on the free list * when it is dissolved. */ if (unlikely(!folio_test_hugetlb_freed(folio))) { spin_unlock_irq(&hugetlb_lock); cond_resched(); /* * Theoretically, we should return -EBUSY when we * encounter this race. In fact, we have a chance * to successfully dissolve the page if we do a * retry. Because the race window is quite small. * If we seize this opportunity, it is an optimization * for increasing the success rate of dissolving page. */ goto retry; } remove_hugetlb_folio(h, folio, false); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); /* * Normally update_and_free_hugtlb_folio will allocate required vmemmmap * before freeing the page. update_and_free_hugtlb_folio will fail to * free the page if it can not allocate required vmemmap. We * need to adjust max_huge_pages if the page is not freed. * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. * * The folio_test_hugetlb check here is because * remove_hugetlb_folio will clear hugetlb folio flag for * non-vmemmap optimized hugetlb folios. */ if (folio_test_hugetlb(folio)) { rc = hugetlb_vmemmap_restore_folio(h, folio); if (rc) { spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, false); h->max_huge_pages++; goto out; } } else rc = 0; update_and_free_hugetlb_folio(h, folio, false); return rc; } out: spin_unlock_irq(&hugetlb_lock); return rc; } /* * Dissolve free hugepages in a given pfn range. Used by memory hotplug to * make specified memory blocks removable from the system. * Note that this will dissolve a free gigantic hugepage completely, if any * part of it lies within the given range. * Also note that if dissolve_free_hugetlb_folio() returns with an error, all * free hugetlb folios that were dissolved before that error are lost. */ int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct folio *folio; int rc = 0; unsigned int order; struct hstate *h; if (!hugepages_supported()) return rc; order = huge_page_order(&default_hstate); for_each_hstate(h) order = min(order, huge_page_order(h)); for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) { folio = pfn_folio(pfn); rc = dissolve_free_hugetlb_folio(folio); if (rc) break; } return rc; } /* * Allocates a fresh surplus page from the page allocator. */ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio = NULL; if (hstate_is_gigantic(h)) return NULL; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) goto out_unlock; spin_unlock_irq(&hugetlb_lock); folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask); if (!folio) return NULL; spin_lock_irq(&hugetlb_lock); /* * We could have raced with the pool size change. * Double check that and simply deallocate the new page * if we would end up overcommiting the surpluses. Abuse * temporary page to workaround the nasty free_huge_folio * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { folio_set_hugetlb_temporary(folio); spin_unlock_irq(&hugetlb_lock); free_huge_folio(folio); return NULL; } h->surplus_huge_pages++; h->surplus_huge_pages_node[folio_nid(folio)]++; out_unlock: spin_unlock_irq(&hugetlb_lock); return folio; } static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; if (hstate_is_gigantic(h)) return NULL; folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask); if (!folio) return NULL; /* fresh huge pages are frozen */ folio_ref_unfreeze(folio, 1); /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ folio_set_hugetlb_temporary(folio); return folio; } /* * Use the VMA's mpolicy to allocate a huge page from the buddy. */ static struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask = htlb_alloc_mask(h); int nid; nodemask_t *nodemask; nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { gfp_t gfp = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); return folio; } struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { struct folio *folio; spin_lock_irq(&hugetlb_lock); folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); if (folio) { VM_BUG_ON(!h->resv_huge_pages); h->resv_huge_pages--; } spin_unlock_irq(&hugetlb_lock); return folio; } /* folio migration callback function */ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { spin_lock_irq(&hugetlb_lock); if (available_huge_pages(h)) { struct folio *folio; folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); if (folio) { spin_unlock_irq(&hugetlb_lock); return folio; } } spin_unlock_irq(&hugetlb_lock); /* We cannot fallback to other nodes, as we could break the per-node pool. */ if (!allow_alloc_fallback) gfp_mask |= __GFP_THISNODE; return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask); } static nodemask_t *policy_mbind_nodemask(gfp_t gfp) { #ifdef CONFIG_NUMA struct mempolicy *mpol = get_task_policy(current); /* * Only enforce MPOL_BIND policy which overlaps with cpuset policy * (from policy_nodemask) specifically for hugetlb case */ if (mpol->mode == MPOL_BIND && (apply_policy_zone(mpol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&mpol->nodes))) return &mpol->nodes; #endif return NULL; } /* * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. */ static int gather_surplus_pages(struct hstate *h, long delta) __must_hold(&hugetlb_lock) { LIST_HEAD(surplus_list); struct folio *folio, *tmp; int ret; long i; long needed, allocated; bool alloc_ok = true; int node; nodemask_t *mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h)); lockdep_assert_held(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; return 0; } allocated = 0; ret = -ENOMEM; retry: spin_unlock_irq(&hugetlb_lock); for (i = 0; i < needed; i++) { folio = NULL; for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) { folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), node, NULL); if (folio) break; } } if (!folio) { alloc_ok = false; break; } list_add(&folio->lru, &surplus_list); cond_resched(); } allocated += i; /* * After retaking hugetlb_lock, we need to recalculate 'needed' * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock_irq(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); if (needed > 0) { if (alloc_ok) goto retry; /* * We were not able to allocate enough pages to * satisfy the entire reservation so we free what * we've allocated so far. */ goto free; } /* * The surplus_list now contains _at_least_ the number of extra pages * needed to accommodate the reservation. Add the appropriate number * of pages to the hugetlb pool and free the extras back to the buddy * allocator. Commit the entire reservation here to prevent another * process from stealing the pages as they are added to the pool but * before they are reserved. */ needed += allocated; h->resv_huge_pages += delta; ret = 0; /* Free the needed pages to the hugetlb pool */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) { if ((--needed) < 0) break; /* Add the page to the hugetlb allocator */ enqueue_hugetlb_folio(h, folio); } free: spin_unlock_irq(&hugetlb_lock); /* * Free unnecessary surplus pages to the buddy allocator. * Pages have no ref count, call free_huge_folio directly. */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) free_huge_folio(folio); spin_lock_irq(&hugetlb_lock); return ret; } /* * This routine has two main purposes: * 1) Decrement the reservation count (resv_huge_pages) by the value passed * in unused_resv_pages. This corresponds to the prior adjustments made * to the associated reservation map. * 2) Free any unused surplus pages that may have been allocated to satisfy * the reservation. As many as unused_resv_pages may be freed. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); /* Uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) goto out; /* * Part (or even all) of the reservation could have been backed * by pre-allocated pages. Only free surplus pages. */ nr_pages = min(unused_resv_pages, h->surplus_huge_pages); /* * We want to release as many surplus pages as possible, spread * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. * remove_pool_hugetlb_folio() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. */ while (nr_pages--) { struct folio *folio; folio = remove_pool_hugetlb_folio(h, &node_states[N_MEMORY], 1); if (!folio) goto out; list_add(&folio->lru, &page_list); } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * vma_needs_reservation, vma_commit_reservation and vma_end_reservation * are used by the huge page allocation routines to manage reservations. * * vma_needs_reservation is called to determine if the huge page at addr * within the vma has an associated reservation. If a reservation is * needed, the value 1 is returned. The caller is then responsible for * managing the global reservation and subpool usage counts. After * the huge page has been allocated, vma_commit_reservation is called * to add the page to the reservation map. If the page allocation fails, * the reservation must be ended instead of committed. vma_end_reservation * is called in such cases. * * In the normal case, vma_commit_reservation returns the same value * as the preceding vma_needs_reservation call. The only time this * is not the case is if a reserve map was changed between calls. It * is the responsibility of the caller to notice the difference and * take appropriate action. * * vma_add_reservation is used in error paths where a reservation must * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. * * vma_del_reservation is used in error paths where an entry in the reserve * map was created during huge page allocation and must be removed. It is to * be called after calling vma_needs_reservation to determine if a reservation * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, enum vma_resv_mode mode) { struct resv_map *resv; pgoff_t idx; long ret; long dummy_out_regions_needed; resv = vma_resv_map(vma); if (!resv) return 1; idx = vma_hugecache_offset(h, vma, addr); switch (mode) { case VMA_NEEDS_RESV: ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed); /* We assume that vma_reservation_* routines always operate on * 1 page, and that adding to resv map a 1 page entry can only * ever require 1 region. */ VM_BUG_ON(dummy_out_regions_needed != 1); break; case VMA_COMMIT_RESV: ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); break; case VMA_END_RESV: region_abort(resv, idx, idx + 1, 1); ret = 0; break; case VMA_ADD_RESV: if (vma->vm_flags & VM_MAYSHARE) { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } else { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } break; case VMA_DEL_RESV: if (vma->vm_flags & VM_MAYSHARE) { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } else { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } break; default: BUG(); } if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; /* * We know private mapping must have HPAGE_RESV_OWNER set. * * In most cases, reserves always exist for private mappings. * However, a file associated with mapping could have been * hole punched or truncated after reserves were consumed. * As subsequent fault on such a range will not use reserves. * Subtle - The reserve map for private mappings has the * opposite meaning than that of shared mappings. If NO * entry is in the reserve map, it means a reservation exists. * If an entry exists in the reserve map, it means the * reservation has already been consumed. As a result, the * return value of this routine is the opposite of the * value returned from reserve map manipulation routines above. */ if (ret > 0) return 0; if (ret == 0) return 1; return ret; } static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV); } static long vma_commit_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV); } static void vma_end_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); } static long vma_add_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } static long vma_del_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); } /* * This routine is called to restore reservation information on error paths. * It should ONLY be called for folios allocated via alloc_hugetlb_folio(), * and the hugetlb mutex should remain held when calling this routine. * * It handles two specific cases: * 1) A reservation was in place and the folio consumed the reservation. * hugetlb_restore_reserve is set in the folio. * 2) No reservation was in place for the page, so hugetlb_restore_reserve is * not set. However, alloc_hugetlb_folio always updates the reserve map. * * In case 1, free_huge_folio later in the error path will increment the * global reserve count. But, free_huge_folio does not have enough context * to adjust the reservation map. This case deals primarily with private * mappings. Adjust the reserve map here to be consistent with global * reserve count adjustments to be made by free_huge_folio. Make sure the * reserve map indicates there is a reservation present. * * In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio. */ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio) { long rc = vma_needs_reservation(h, vma, address); if (folio_test_hugetlb_restore_reserve(folio)) { if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map * manipulation. Clear hugetlb_restore_reserve so * that global reserve count will not be incremented * by free_huge_folio. This will make it appear * as though the reservation for this folio was * consumed. This may prevent the task from * faulting in the folio at a later time. This * is better than inconsistent global huge page * accounting of reserve counts. */ folio_clear_hugetlb_restore_reserve(folio); else if (rc) (void)vma_add_reservation(h, vma, address); else vma_end_reservation(h, vma, address); } else { if (!rc) { /* * This indicates there is an entry in the reserve map * not added by alloc_hugetlb_folio. We know it was added * before the alloc_hugetlb_folio call, otherwise * hugetlb_restore_reserve would be set on the folio. * Remove the entry so that a subsequent allocation * does not consume a reservation. */ rc = vma_del_reservation(h, vma, address); if (rc < 0) /* * VERY rare out of memory condition. Since * we can not delete the entry, set * hugetlb_restore_reserve so that the reserve * count will be incremented when the folio * is freed. This reserve will be consumed * on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else if (rc < 0) { /* * Rare out of memory condition from * vma_needs_reservation call. Memory allocation is * only attempted if a new entry is needed. Therefore, * this implies there is not an entry in the * reserve map. * * For shared mappings, no entry in the map indicates * no reservation. We are done. */ if (!(vma->vm_flags & VM_MAYSHARE)) /* * For private mappings, no entry indicates * a reservation is present. Since we can * not add an entry, set hugetlb_restore_reserve * on the folio so reserve count will be * incremented when freed. This reserve will * be consumed on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else /* * No reservation present, do nothing */ vma_end_reservation(h, vma, address); } } /* * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve * the old one * @h: struct hstate old page belongs to * @old_folio: Old folio to dissolve * @list: List to isolate the page in case we need to * Returns 0 on success, otherwise negated error. */ static int alloc_and_dissolve_hugetlb_folio(struct hstate *h, struct folio *old_folio, struct list_head *list) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; int nid = folio_nid(old_folio); struct folio *new_folio = NULL; int ret = 0; retry: spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(old_folio)) { /* * Freed from under us. Drop new_folio too. */ goto free_new; } else if (folio_ref_count(old_folio)) { bool isolated; /* * Someone has grabbed the folio, try to isolate it here. * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); isolated = isolate_hugetlb(old_folio, list); ret = isolated ? 0 : -EBUSY; spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!folio_test_hugetlb_freed(old_folio)) { /* * Folio's refcount is 0 but it has not been enqueued in the * freelist yet. Race window is small, so we can succeed here if * we retry. */ spin_unlock_irq(&hugetlb_lock); cond_resched(); goto retry; } else { if (!new_folio) { spin_unlock_irq(&hugetlb_lock); new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL); if (!new_folio) return -ENOMEM; __prep_new_hugetlb_folio(h, new_folio); goto retry; } /* * Ok, old_folio is still a genuine free hugepage. Remove it from * the freelist and decrease the counters. These will be * incremented again when calling __prep_account_new_huge_page() * and enqueue_hugetlb_folio() for new_folio. The counters will * remain stable since this happens under the lock. */ remove_hugetlb_folio(h, old_folio, false); /* * Ref count on new_folio is already zero as it was dropped * earlier. It can be directly added to the pool free list. */ __prep_account_new_huge_page(h, nid); enqueue_hugetlb_folio(h, new_folio); /* * Folio has been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, old_folio, false); } return ret; free_new: spin_unlock_irq(&hugetlb_lock); if (new_folio) update_and_free_hugetlb_folio(h, new_folio, false); return ret; } int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { struct hstate *h; struct folio *folio = page_folio(page); int ret = -EBUSY; /* * The page might have been dissolved from under our feet, so make sure * to carefully check the state under the lock. * Return success when racing as if we dissolved the page ourselves. */ spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { h = folio_hstate(folio); } else { spin_unlock_irq(&hugetlb_lock); return 0; } spin_unlock_irq(&hugetlb_lock); /* * Fence off gigantic pages as there is a cyclic dependency between * alloc_contig_range and them. Return -ENOMEM as this has the effect * of bailing out right away without further retrying. */ if (hstate_is_gigantic(h)) return -ENOMEM; if (folio_ref_count(folio) && isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); return ret; } struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; long map_chg, map_commit, nr_pages = pages_per_huge_page(h); long gbl_chg; int memcg_charge_ret, ret, idx; struct hugetlb_cgroup *h_cg = NULL; struct mem_cgroup *memcg; bool deferred_reserve; gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL; memcg = get_mem_cgroup_from_current(); memcg_charge_ret = mem_cgroup_hugetlb_try_charge(memcg, gfp, nr_pages); if (memcg_charge_ret == -ENOMEM) { mem_cgroup_put(memcg); return ERR_PTR(-ENOMEM); } idx = hstate_index(h); /* * Examine the region/reserve map to determine if the process * has a reservation for the page to be allocated. A return * code of zero indicates a reservation exists (no change). */ map_chg = gbl_chg = vma_needs_reservation(h, vma, addr); if (map_chg < 0) { if (!memcg_charge_ret) mem_cgroup_cancel_charge(memcg, nr_pages); mem_cgroup_put(memcg); return ERR_PTR(-ENOMEM); } /* * Processes that did not create the mapping will have no * reserves as indicated by the region/reserve map. Check * that the allocation will not exceed the subpool limit. * Allocations for MAP_NORESERVE mappings also need to be * checked against any subpool limit. */ if (map_chg || avoid_reserve) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) goto out_end_reservation; /* * Even though there was no reservation in the region/reserve * map, there could be reservations associated with the * subpool that can be used. This would be indicated if the * return value of hugepage_subpool_get_pages() is zero. * However, if avoid_reserve is specified we still avoid even * the subpool reservations. */ if (avoid_reserve) gbl_chg = 1; } /* If this allocation is not consuming a reservation, charge it now. */ deferred_reserve = map_chg || avoid_reserve; if (deferred_reserve) { ret = hugetlb_cgroup_charge_cgroup_rsvd( idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_subpool_put; } ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_uncharge_cgroup_reservation; spin_lock_irq(&hugetlb_lock); /* * glb_chg is passed to indicate whether or not a page must be taken * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ folio = dequeue_hugetlb_folio_vma(h, vma, addr, avoid_reserve, gbl_chg); if (!folio) { spin_unlock_irq(&hugetlb_lock); folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); if (!folio) goto out_uncharge_cgroup; spin_lock_irq(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } list_add(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); /* Fall through */ } hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. */ if (deferred_reserve) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), h_cg, folio); } spin_unlock_irq(&hugetlb_lock); hugetlb_set_folio_subpool(folio, spool); map_commit = vma_commit_reservation(h, vma, addr); if (unlikely(map_chg > map_commit)) { /* * The page was added to the reservation map between * vma_needs_reservation and vma_commit_reservation. * This indicates a race with hugetlb_reserve_pages. * Adjust for the subpool count incremented above AND * in hugetlb_reserve_pages for the same page. Also, * the reservation count added in hugetlb_reserve_pages * no longer applies. */ long rsv_adjust; rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); if (deferred_reserve) { spin_lock_irq(&hugetlb_lock); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); spin_unlock_irq(&hugetlb_lock); } } if (!memcg_charge_ret) mem_cgroup_commit_charge(folio, memcg); mem_cgroup_put(memcg); return folio; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); out_uncharge_cgroup_reservation: if (deferred_reserve) hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: if (map_chg || avoid_reserve) hugepage_subpool_put_pages(spool, 1); out_end_reservation: vma_end_reservation(h, vma, addr); if (!memcg_charge_ret) mem_cgroup_cancel_charge(memcg, nr_pages); mem_cgroup_put(memcg); return ERR_PTR(-ENOSPC); } int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); int __alloc_bootmem_huge_page(struct hstate *h, int nid) { struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node = nid; /* do node specific alloc */ if (nid != NUMA_NO_NODE) { m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!m) return 0; goto found; } /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, &node_states[N_MEMORY]) { m = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); /* * Use the beginning of the huge page to store the * huge_bootmem_page struct (until gather_bootmem * puts them into the mem_map). */ if (!m) return 0; goto found; } found: /* * Only initialize the head struct page in memmap_init_reserved_pages, * rest of the struct pages will be initialized by the HugeTLB * subsystem itself. * The head struct page is used to get folio information by the HugeTLB * subsystem like zone id and node id. */ memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE), huge_page_size(h) - PAGE_SIZE); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages[node]); m->hstate = h; return 1; } /* Initialize [start_page:end_page_number] tail struct pages of a hugepage */ static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio, unsigned long start_page_number, unsigned long end_page_number) { enum zone_type zone = zone_idx(folio_zone(folio)); int nid = folio_nid(folio); unsigned long head_pfn = folio_pfn(folio); unsigned long pfn, end_pfn = head_pfn + end_page_number; int ret; for (pfn = head_pfn + start_page_number; pfn < end_pfn; pfn++) { struct page *page = pfn_to_page(pfn); __ClearPageReserved(folio_page(folio, pfn - head_pfn)); __init_single_page(page, pfn, zone, nid); prep_compound_tail((struct page *)folio, pfn - head_pfn); ret = page_ref_freeze(page, 1); VM_BUG_ON(!ret); } } static void __init hugetlb_folio_init_vmemmap(struct folio *folio, struct hstate *h, unsigned long nr_pages) { int ret; /* Prepare folio head */ __folio_clear_reserved(folio); __folio_set_head(folio); ret = folio_ref_freeze(folio, 1); VM_BUG_ON(!ret); /* Initialize the necessary tail struct pages */ hugetlb_folio_init_tail_vmemmap(folio, 1, nr_pages); prep_compound_head((struct page *)folio, huge_page_order(h)); } static void __init prep_and_add_bootmem_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_folios(h, folio_list); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { if (!folio_test_hugetlb_vmemmap_optimized(folio)) { /* * If HVO fails, initialize all tail struct pages * We do not worry about potential long lock hold * time as this is early in boot and there should * be no contention. */ hugetlb_folio_init_tail_vmemmap(folio, HUGETLB_VMEMMAP_RESERVE_PAGES, pages_per_huge_page(h)); } /* Subdivide locks to achieve better parallel performance */ spin_lock_irqsave(&hugetlb_lock, flags); __prep_account_new_huge_page(h, folio_nid(folio)); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } /* * Put bootmem huge pages into the standard lists after mem_map is up. * Note: This only applies to gigantic (order > MAX_PAGE_ORDER) pages. */ static void __init gather_bootmem_prealloc_node(unsigned long nid) { LIST_HEAD(folio_list); struct huge_bootmem_page *m; struct hstate *h = NULL, *prev_h = NULL; list_for_each_entry(m, &huge_boot_pages[nid], list) { struct page *page = virt_to_page(m); struct folio *folio = (void *)page; h = m->hstate; /* * It is possible to have multiple huge page sizes (hstates) * in this list. If so, process each size separately. */ if (h != prev_h && prev_h != NULL) prep_and_add_bootmem_folios(prev_h, &folio_list); prev_h = h; VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(folio_ref_count(folio) != 1); hugetlb_folio_init_vmemmap(folio, h, HUGETLB_VMEMMAP_RESERVE_PAGES); init_new_hugetlb_folio(h, folio); list_add(&folio->lru, &folio_list); /* * We need to restore the 'stolen' pages to totalram_pages * in order to fix confusing memory reports from free(1) and * other side-effects, like CommitLimit going negative. */ adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } prep_and_add_bootmem_folios(h, &folio_list); } static void __init gather_bootmem_prealloc_parallel(unsigned long start, unsigned long end, void *arg) { int nid; for (nid = start; nid < end; nid++) gather_bootmem_prealloc_node(nid); } static void __init gather_bootmem_prealloc(void) { struct padata_mt_job job = { .thread_fn = gather_bootmem_prealloc_parallel, .fn_arg = NULL, .start = 0, .size = num_node_state(N_MEMORY), .align = 1, .min_chunk = 1, .max_threads = num_node_state(N_MEMORY), .numa_aware = true, }; padata_do_multithreaded(&job); } static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) { unsigned long i; char buf[32]; for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { if (hstate_is_gigantic(h)) { if (!alloc_bootmem_huge_page(h, nid)) break; } else { struct folio *folio; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, &node_states[N_MEMORY]); if (!folio) break; free_huge_folio(folio); /* free it into the hugepage allocator */ } cond_resched(); } if (i == h->max_huge_pages_node[nid]) return; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", h->max_huge_pages_node[nid], buf, nid, i); h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); h->max_huge_pages_node[nid] = i; } static bool __init hugetlb_hstate_alloc_pages_specific_nodes(struct hstate *h) { int i; bool node_specific_alloc = false; for_each_online_node(i) { if (h->max_huge_pages_node[i] > 0) { hugetlb_hstate_alloc_pages_onenode(h, i); node_specific_alloc = true; } } return node_specific_alloc; } static void __init hugetlb_hstate_alloc_pages_errcheck(unsigned long allocated, struct hstate *h) { if (allocated < h->max_huge_pages) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n", h->max_huge_pages, buf, allocated); h->max_huge_pages = allocated; } } static void __init hugetlb_pages_alloc_boot_node(unsigned long start, unsigned long end, void *arg) { struct hstate *h = (struct hstate *)arg; int i, num = end - start; nodemask_t node_alloc_noretry; LIST_HEAD(folio_list); int next_node = first_online_node; /* Bit mask controlling how hard we retry per-node allocations.*/ nodes_clear(node_alloc_noretry); for (i = 0; i < num; ++i) { struct folio *folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY], &node_alloc_noretry, &next_node); if (!folio) break; list_move(&folio->lru, &folio_list); cond_resched(); } prep_and_add_allocated_folios(h, &folio_list); } static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstate *h) { unsigned long i; for (i = 0; i < h->max_huge_pages; ++i) { if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; cond_resched(); } return i; } static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h) { struct padata_mt_job job = { .fn_arg = h, .align = 1, .numa_aware = true }; job.thread_fn = hugetlb_pages_alloc_boot_node; job.start = 0; job.size = h->max_huge_pages; /* * job.max_threads is twice the num_node_state(N_MEMORY), * * Tests below indicate that a multiplier of 2 significantly improves * performance, and although larger values also provide improvements, * the gains are marginal. * * Therefore, choosing 2 as the multiplier strikes a good balance between * enhancing parallel processing capabilities and maintaining efficient * resource management. * * +------------+-------+-------+-------+-------+-------+ * | multiplier | 1 | 2 | 3 | 4 | 5 | * +------------+-------+-------+-------+-------+-------+ * | 256G 2node | 358ms | 215ms | 157ms | 134ms | 126ms | * | 2T 4node | 979ms | 679ms | 543ms | 489ms | 481ms | * | 50G 2node | 71ms | 44ms | 37ms | 30ms | 31ms | * +------------+-------+-------+-------+-------+-------+ */ job.max_threads = num_node_state(N_MEMORY) * 2; job.min_chunk = h->max_huge_pages / num_node_state(N_MEMORY) / 2; padata_do_multithreaded(&job); return h->nr_huge_pages; } /* * NOTE: this routine is called in different contexts for gigantic and * non-gigantic pages. * - For gigantic pages, this is called early in the boot process and * pages are allocated from memblock allocated or something similar. * Gigantic pages are actually added to pools later with the routine * gather_bootmem_prealloc. * - For non-gigantic pages, this is called later in the boot process after * all of mm is up and functional. Pages are allocated from buddy and * then added to hugetlb pools. */ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long allocated; static bool initialized __initdata; /* skip gigantic hugepages allocation if hugetlb_cma enabled */ if (hstate_is_gigantic(h) && hugetlb_cma_size) { pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); return; } /* hugetlb_hstate_alloc_pages will be called many times, initialize huge_boot_pages once */ if (!initialized) { int i = 0; for (i = 0; i < MAX_NUMNODES; i++) INIT_LIST_HEAD(&huge_boot_pages[i]); initialized = true; } /* do node specific alloc */ if (hugetlb_hstate_alloc_pages_specific_nodes(h)) return; /* below will do all node balanced alloc */ if (hstate_is_gigantic(h)) allocated = hugetlb_gigantic_pages_alloc_boot(h); else allocated = hugetlb_pages_alloc_boot(h); hugetlb_hstate_alloc_pages_errcheck(allocated, h); } static void __init hugetlb_init_hstates(void) { struct hstate *h, *h2; for_each_hstate(h) { /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); /* * Set demote order for each hstate. Note that * h->demote_order is initially 0. * - We can not demote gigantic pages if runtime freeing * is not supported, so skip this. * - If CMA allocation is possible, we can not demote * HUGETLB_PAGE_ORDER or smaller size pages. */ if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) continue; if (hugetlb_cma_size && h->order <= HUGETLB_PAGE_ORDER) continue; for_each_hstate(h2) { if (h2 == h) continue; if (h2->order < h->order && h2->order > h->demote_order) h->demote_order = h2->order; } } } static void __init report_hugepages(void) { struct hstate *h; for_each_hstate(h) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n", buf, h->free_huge_pages); pr_info("HugeTLB: %d KiB vmemmap can be freed for a %s page\n", hugetlb_vmemmap_optimizable_size(h) / SZ_1K, buf); } } #ifdef CONFIG_HIGHMEM static void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { int i; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h)) return; /* * Collect pages to be freed on a list, and free after dropping lock */ for_each_node_mask(i, *nodes_allowed) { struct folio *folio, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(folio, next, freel, lru) { if (count >= h->nr_huge_pages) goto out; if (folio_test_highmem(folio)) continue; remove_hugetlb_folio(h, folio, false); list_add(&folio->lru, &page_list); } } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { } #endif /* * Increment or decrement surplus_huge_pages. Keep node-specific counters * balanced by operating on them in a round-robin fashion. * Returns 1 if an adjustment was made. */ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { int nr_nodes, node; lockdep_assert_held(&hugetlb_lock); VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) { for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node]) goto found; } } else { for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node] < h->nr_huge_pages_node[node]) goto found; } } return 0; found: h->surplus_huge_pages += delta; h->surplus_huge_pages_node[node] += delta; return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long min_count; unsigned long allocated; struct folio *folio; LIST_HEAD(page_list); NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); /* * Bit mask controlling how hard we retry per-node allocations. * If we can not allocate the bit mask, do not attempt to allocate * the requested huge pages. */ if (node_alloc_noretry) nodes_clear(*node_alloc_noretry); else return -ENOMEM; /* * resize_lock mutex prevents concurrent adjustments to number of * pages in hstate via the proc/sysfs interfaces. */ mutex_lock(&h->resize_lock); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); /* * Check for a node specific request. * Changing node specific huge page count may require a corresponding * change to the global count. In any case, the passed node mask * (nodes_allowed) will restrict alloc/free to the specified node. */ if (nid != NUMA_NO_NODE) { unsigned long old_count = count; count += persistent_huge_pages(h) - (h->nr_huge_pages_node[nid] - h->surplus_huge_pages_node[nid]); /* * User may have specified a large count value which caused the * above calculation to overflow. In this case, they wanted * to allocate as many huge pages as possible. Set count to * largest possible value to align with their intention. */ if (count < old_count) count = ULONG_MAX; } /* * Gigantic pages runtime allocation depend on the capability for large * page range allocation. * If the system does not provide this feature, return an error when * the user tries to allocate gigantic pages but let the user free the * boottime allocated gigantic pages. */ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } /* Fall through to decrease pool */ } /* * Increase the pool size * First take pages out of surplus state. Then make up the * remaining difference by allocating fresh huge pages. * * We might race with alloc_surplus_hugetlb_folio() here and be unable * to convert a surplus huge page to a normal huge page. That is * not critical, though, it just means the overall size of the * pool might be one hugepage larger than it needs to be, but * within all the constraints specified by the sysctls. */ while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, -1)) break; } allocated = 0; while (count > (persistent_huge_pages(h) + allocated)) { /* * If this allocation races such that we no longer need the * page, free_huge_folio will handle it by freeing the page * and reducing the surplus. */ spin_unlock_irq(&hugetlb_lock); /* yield cpu to avoid soft lockup */ cond_resched(); folio = alloc_pool_huge_folio(h, nodes_allowed, node_alloc_noretry, &h->next_nid_to_alloc); if (!folio) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } list_add(&folio->lru, &page_list); allocated++; /* Bail for signals. Probably ctrl-c from user */ if (signal_pending(current)) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } spin_lock_irq(&hugetlb_lock); } /* Add allocated pages to the pool */ if (!list_empty(&page_list)) { spin_unlock_irq(&hugetlb_lock); prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * Decrease the pool size * First return free pages to the buddy allocator (being careful * to keep enough around to satisfy reservations). Then place * pages into surplus state as needed so the pool will shrink * to the desired size as pages become free. * * By placing pages into the surplus state independent of the * overcommit value, we are allowing the surplus pool size to * exceed overcommit. There are few sane options here. Since * alloc_surplus_hugetlb_folio() is checking the global counter, * though, we'll note that we're not allowed to exceed surplus * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. */ min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); /* * Collect pages to be removed on list without dropping lock */ while (min_count < persistent_huge_pages(h)) { folio = remove_pool_hugetlb_folio(h, nodes_allowed, 0); if (!folio) break; list_add(&folio->lru, &page_list); } /* free the pages after dropping lock */ spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: h->max_huge_pages = persistent_huge_pages(h); spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return 0; } static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, struct list_head *src_list) { long rc; struct folio *folio, *next; LIST_HEAD(dst_list); LIST_HEAD(ret_list); rc = hugetlb_vmemmap_restore_folios(src, src_list, &ret_list); list_splice_init(&ret_list, src_list); /* * Taking target hstate mutex synchronizes with set_max_huge_pages. * Without the mutex, pages added to target hstate could be marked * as surplus. * * Note that we already hold src->resize_lock. To prevent deadlock, * use the convention of always taking larger size hstate mutex first. */ mutex_lock(&dst->resize_lock); list_for_each_entry_safe(folio, next, src_list, lru) { int i; if (folio_test_hugetlb_vmemmap_optimized(folio)) continue; list_del(&folio->lru); split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst)); pgalloc_tag_split(folio, huge_page_order(src), huge_page_order(dst)); for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) { struct page *page = folio_page(folio, i); page->mapping = NULL; clear_compound_head(page); prep_compound_page(page, dst->order); init_new_hugetlb_folio(dst, page_folio(page)); list_add(&page->lru, &dst_list); } } prep_and_add_allocated_folios(dst, &dst_list); mutex_unlock(&dst->resize_lock); return rc; } static long demote_pool_huge_page(struct hstate *src, nodemask_t *nodes_allowed, unsigned long nr_to_demote) __must_hold(&hugetlb_lock) { int nr_nodes, node; struct hstate *dst; long rc = 0; long nr_demoted = 0; lockdep_assert_held(&hugetlb_lock); /* We should never get here if no demote order */ if (!src->demote_order) { pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); return -EINVAL; /* internal error */ } dst = size_to_hstate(PAGE_SIZE << src->demote_order); for_each_node_mask_to_free(src, nr_nodes, node, nodes_allowed) { LIST_HEAD(list); struct folio *folio, *next; list_for_each_entry_safe(folio, next, &src->hugepage_freelists[node], lru) { if (folio_test_hwpoison(folio)) continue; remove_hugetlb_folio(src, folio, false); list_add(&folio->lru, &list); if (++nr_demoted == nr_to_demote) break; } spin_unlock_irq(&hugetlb_lock); rc = demote_free_hugetlb_folios(src, dst, &list); spin_lock_irq(&hugetlb_lock); list_for_each_entry_safe(folio, next, &list, lru) { list_del(&folio->lru); add_hugetlb_folio(src, folio, false); nr_demoted--; } if (rc < 0 || nr_demoted == nr_to_demote) break; } /* * Not absolutely necessary, but for consistency update max_huge_pages * based on pool changes for the demoted page. */ src->max_huge_pages -= nr_demoted; dst->max_huge_pages += nr_demoted << (huge_page_order(src) - huge_page_order(dst)); if (rc < 0) return rc; if (nr_demoted) return nr_demoted; /* * Only way to get here is if all pages on free lists are poisoned. * Return -EBUSY so that caller will not retry. */ return -EBUSY; } #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define HSTATE_ATTR_WO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_WO(_name) #define HSTATE_ATTR(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static struct kobject *hugepages_kobj; static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp); static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp) { int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (hstate_kobjs[i] == kobj) { if (nidp) *nidp = NUMA_NO_NODE; return &hstates[i]; } return kobj_to_node_hstate(kobj, nidp); } static ssize_t nr_hugepages_show_common(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long nr_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) nr_huge_pages = h->nr_huge_pages; else nr_huge_pages = h->nr_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", nr_huge_pages); } static ssize_t __nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h, int nid, unsigned long count, size_t len) { int err; nodemask_t nodes_allowed, *n_mask; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return -EINVAL; if (nid == NUMA_NO_NODE) { /* * global hstate attribute */ if (!(obey_mempolicy && init_nodemask_of_mempolicy(&nodes_allowed))) n_mask = &node_states[N_MEMORY]; else n_mask = &nodes_allowed; } else { /* * Node specific request. count adjustment happens in * set_max_huge_pages() after acquiring hugetlb_lock. */ init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } err = set_max_huge_pages(h, count, nid, n_mask); return err ? err : len; } static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct kobject *kobj, const char *buf, size_t len) { struct hstate *h; unsigned long count; int nid; int err; err = kstrtoul(buf, 10, &count); if (err) return err; h = kobj_to_hstate(kobj, &nid); return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len); } static ssize_t nr_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(false, kobj, buf, len); } HSTATE_ATTR(nr_hugepages); #ifdef CONFIG_NUMA /* * hstate attribute for optionally mempolicy-based constraint on persistent * huge page alloc/free. */ static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(true, kobj, buf, len); } HSTATE_ATTR(nr_hugepages_mempolicy); #endif static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sysfs_emit(buf, "%lu\n", h->nr_overcommit_huge_pages); } static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); if (hstate_is_gigantic(h)) return -EINVAL; err = kstrtoul(buf, 10, &input); if (err) return err; spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = input; spin_unlock_irq(&hugetlb_lock); return count; } HSTATE_ATTR(nr_overcommit_hugepages); static ssize_t free_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long free_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) free_huge_pages = h->free_huge_pages; else free_huge_pages = h->free_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", free_huge_pages); } HSTATE_ATTR_RO(free_hugepages); static ssize_t resv_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sysfs_emit(buf, "%lu\n", h->resv_huge_pages); } HSTATE_ATTR_RO(resv_hugepages); static ssize_t surplus_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long surplus_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) surplus_huge_pages = h->surplus_huge_pages; else surplus_huge_pages = h->surplus_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", surplus_huge_pages); } HSTATE_ATTR_RO(surplus_hugepages); static ssize_t demote_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned long nr_demote; unsigned long nr_available; nodemask_t nodes_allowed, *n_mask; struct hstate *h; int err; int nid; err = kstrtoul(buf, 10, &nr_demote); if (err) return err; h = kobj_to_hstate(kobj, &nid); if (nid != NUMA_NO_NODE) { init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } else { n_mask = &node_states[N_MEMORY]; } /* Synchronize with other sysfs operations modifying huge pages */ mutex_lock(&h->resize_lock); spin_lock_irq(&hugetlb_lock); while (nr_demote) { long rc; /* * Check for available pages to demote each time thorough the * loop as demote_pool_huge_page will drop hugetlb_lock. */ if (nid != NUMA_NO_NODE) nr_available = h->free_huge_pages_node[nid]; else nr_available = h->free_huge_pages; nr_available -= h->resv_huge_pages; if (!nr_available) break; rc = demote_pool_huge_page(h, n_mask, nr_demote); if (rc < 0) { err = rc; break; } nr_demote -= rc; } spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); if (err) return err; return len; } HSTATE_ATTR_WO(demote); static ssize_t demote_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K; return sysfs_emit(buf, "%lukB\n", demote_size); } static ssize_t demote_size_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct hstate *h, *demote_hstate; unsigned long demote_size; unsigned int demote_order; demote_size = (unsigned long)memparse(buf, NULL); demote_hstate = size_to_hstate(demote_size); if (!demote_hstate) return -EINVAL; demote_order = demote_hstate->order; if (demote_order < HUGETLB_PAGE_ORDER) return -EINVAL; /* demote order must be smaller than hstate order */ h = kobj_to_hstate(kobj, NULL); if (demote_order >= h->order) return -EINVAL; /* resize_lock synchronizes access to demote size and writes */ mutex_lock(&h->resize_lock); h->demote_order = demote_order; mutex_unlock(&h->resize_lock); return count; } HSTATE_ATTR(demote_size); static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, &free_hugepages_attr.attr, &resv_hugepages_attr.attr, &surplus_hugepages_attr.attr, #ifdef CONFIG_NUMA &nr_hugepages_mempolicy_attr.attr, #endif NULL, }; static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; static struct attribute *hstate_demote_attrs[] = { &demote_size_attr.attr, &demote_attr.attr, NULL, }; static const struct attribute_group hstate_demote_attr_group = { .attrs = hstate_demote_attrs, }; static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) { int retval; int hi = hstate_index(h); hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); if (!hstate_kobjs[hi]) return -ENOMEM; retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); if (retval) { kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; return retval; } if (h->demote_order) { retval = sysfs_create_group(hstate_kobjs[hi], &hstate_demote_attr_group); if (retval) { pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name); sysfs_remove_group(hstate_kobjs[hi], hstate_attr_group); kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; return retval; } } return 0; } #ifdef CONFIG_NUMA static bool hugetlb_sysfs_initialized __ro_after_init; /* * node_hstate/s - associate per node hstate attributes, via their kobjects, * with node devices in node_devices[] using a parallel array. The array * index of a node device or _hstate == node id. * This is here to avoid any static dependency of the node device driver, in * the base kernel, on the hugetlb module. */ struct node_hstate { struct kobject *hugepages_kobj; struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; }; static struct node_hstate node_hstates[MAX_NUMNODES]; /* * A subset of global hstate attributes for node devices */ static struct attribute *per_node_hstate_attrs[] = { &nr_hugepages_attr.attr, &free_hugepages_attr.attr, &surplus_hugepages_attr.attr, NULL, }; static const struct attribute_group per_node_hstate_attr_group = { .attrs = per_node_hstate_attrs, }; /* * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj. * Returns node id via non-NULL nidp. */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { int nid; for (nid = 0; nid < nr_node_ids; nid++) { struct node_hstate *nhs = &node_hstates[nid]; int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (nhs->hstate_kobjs[i] == kobj) { if (nidp) *nidp = nid; return &hstates[i]; } } BUG(); return NULL; } /* * Unregister hstate attributes from a single node device. * No-op if no hstate attributes attached. */ void hugetlb_unregister_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; if (!nhs->hugepages_kobj) return; /* no hstate attributes */ for_each_hstate(h) { int idx = hstate_index(h); struct kobject *hstate_kobj = nhs->hstate_kobjs[idx]; if (!hstate_kobj) continue; if (h->demote_order) sysfs_remove_group(hstate_kobj, &hstate_demote_attr_group); sysfs_remove_group(hstate_kobj, &per_node_hstate_attr_group); kobject_put(hstate_kobj); nhs->hstate_kobjs[idx] = NULL; } kobject_put(nhs->hugepages_kobj); nhs->hugepages_kobj = NULL; } /* * Register hstate attributes for a single node device. * No-op if attributes already registered. */ void hugetlb_register_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; int err; if (!hugetlb_sysfs_initialized) return; if (nhs->hugepages_kobj) return; /* already allocated */ nhs->hugepages_kobj = kobject_create_and_add("hugepages", &node->dev.kobj); if (!nhs->hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj, nhs->hstate_kobjs, &per_node_hstate_attr_group); if (err) { pr_err("HugeTLB: Unable to add hstate %s for node %d\n", h->name, node->dev.id); hugetlb_unregister_node(node); break; } } } /* * hugetlb init time: register hstate attributes for all registered node * devices of nodes that have memory. All on-line nodes should have * registered their associated device by this time. */ static void __init hugetlb_register_all_nodes(void) { int nid; for_each_online_node(nid) hugetlb_register_node(node_devices[nid]); } #else /* !CONFIG_NUMA */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { BUG(); if (nidp) *nidp = -1; return NULL; } static void hugetlb_register_all_nodes(void) { } #endif #ifdef CONFIG_CMA static void __init hugetlb_cma_check(void); #else static inline __init void hugetlb_cma_check(void) { } #endif static void __init hugetlb_sysfs_init(void) { struct hstate *h; int err; hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); if (!hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) pr_err("HugeTLB: Unable to add hstate %s", h->name); } #ifdef CONFIG_NUMA hugetlb_sysfs_initialized = true; #endif hugetlb_register_all_nodes(); } #ifdef CONFIG_SYSCTL static void hugetlb_sysctl_init(void); #else static inline void hugetlb_sysctl_init(void) { } #endif static int __init hugetlb_init(void) { int i; BUILD_BUG_ON(sizeof_field(struct page, private) * BITS_PER_BYTE < __NR_HPAGEFLAGS); if (!hugepages_supported()) { if (hugetlb_max_hstate || default_hstate_max_huge_pages) pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); return 0; } /* * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some * architectures depend on setup being done here. */ hugetlb_add_hstate(HUGETLB_PAGE_ORDER); if (!parsed_default_hugepagesz) { /* * If we did not parse a default huge page size, set * default_hstate_idx to HPAGE_SIZE hstate. And, if the * number of huge pages for this default size was implicitly * specified, set that here as well. * Note that the implicit setting will overwrite an explicit * setting. A warning will be printed in this case. */ default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE)); if (default_hstate_max_huge_pages) { if (default_hstate.max_huge_pages) { char buf[32]; string_get_size(huge_page_size(&default_hstate), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n", default_hstate.max_huge_pages, buf); pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n", default_hstate_max_huge_pages); } default_hstate.max_huge_pages = default_hstate_max_huge_pages; for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; } } hugetlb_cma_check(); hugetlb_init_hstates(); gather_bootmem_prealloc(); report_hugepages(); hugetlb_sysfs_init(); hugetlb_cgroup_file_init(); hugetlb_sysctl_init(); #ifdef CONFIG_SMP num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); #else num_fault_mutexes = 1; #endif hugetlb_fault_mutex_table = kmalloc_array(num_fault_mutexes, sizeof(struct mutex), GFP_KERNEL); BUG_ON(!hugetlb_fault_mutex_table); for (i = 0; i < num_fault_mutexes; i++) mutex_init(&hugetlb_fault_mutex_table[i]); return 0; } subsys_initcall(hugetlb_init); /* Overwritten by architectures with more huge page sizes */ bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) { return size == HPAGE_SIZE; } void __init hugetlb_add_hstate(unsigned int order) { struct hstate *h; unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order < order_base_2(__NR_USED_SUBPAGE)); h = &hstates[hugetlb_max_hstate++]; __mutex_init(&h->resize_lock, "resize mutex", &h->resize_key); h->order = order; h->mask = ~(huge_page_size(h) - 1); for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); INIT_LIST_HEAD(&h->hugepage_activelist); h->next_nid_to_alloc = first_memory_node; h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/SZ_1K); parsed_hstate = h; } bool __init __weak hugetlb_node_alloc_supported(void) { return true; } static void __init hugepages_clear_pages_in_node(void) { if (!hugetlb_max_hstate) { default_hstate_max_huge_pages = 0; memset(default_hugepages_in_node, 0, sizeof(default_hugepages_in_node)); } else { parsed_hstate->max_huge_pages = 0; memset(parsed_hstate->max_huge_pages_node, 0, sizeof(parsed_hstate->max_huge_pages_node)); } } /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz * specification. If not, ignore the hugepages value. hugepages can also * be the first huge page command line option in which case it implicitly * specifies the number of huge pages for the default size. */ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; int node = NUMA_NO_NODE; int count; unsigned long tmp; char *p = s; if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; return 1; } /* * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter * yet, so this hugepages= parameter goes to the "default hstate". * Otherwise, it goes with the previously parsed hugepagesz or * default_hugepagesz. */ else if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); return 1; } while (*p) { count = 0; if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; /* Parameter is node format */ if (p[count] == ':') { if (!hugetlb_node_alloc_supported()) { pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); return 1; } if (tmp >= MAX_NUMNODES || !node_online(tmp)) goto invalid; node = array_index_nospec(tmp, MAX_NUMNODES); p += count + 1; /* Parse hugepages */ if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; if (!hugetlb_max_hstate) default_hugepages_in_node[node] = tmp; else parsed_hstate->max_huge_pages_node[node] = tmp; *mhp += tmp; /* Go to parse next node*/ if (p[count] == ',') p += count + 1; else break; } else { if (p != s) goto invalid; *mhp = tmp; break; } } /* * Global state is always initialized later in hugetlb_init. * But we need to allocate gigantic hstates here early to still * use the bootmem allocator. */ if (hugetlb_max_hstate && hstate_is_gigantic(parsed_hstate)) hugetlb_hstate_alloc_pages(parsed_hstate); last_mhp = mhp; return 1; invalid: pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); hugepages_clear_pages_in_node(); return 1; } __setup("hugepages=", hugepages_setup); /* * hugepagesz command line processing * A specific huge page size can only be specified once with hugepagesz. * hugepagesz is followed by hugepages on the command line. The global * variable 'parsed_valid_hugepagesz' is used to determine if prior * hugepagesz argument was valid. */ static int __init hugepagesz_setup(char *s) { unsigned long size; struct hstate *h; parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); return 1; } h = size_to_hstate(size); if (h) { /* * hstate for this size already exists. This is normally * an error, but is allowed if the existing hstate is the * default hstate. More specifically, it is only allowed if * the number of huge pages for the default hstate was not * previously specified. */ if (!parsed_default_hugepagesz || h != &default_hstate || default_hstate.max_huge_pages) { pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); return 1; } /* * No need to call hugetlb_add_hstate() as hstate already * exists. But, do set parsed_hstate so that a following * hugepages= parameter will be applied to this hstate. */ parsed_hstate = h; parsed_valid_hugepagesz = true; return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; return 1; } __setup("hugepagesz=", hugepagesz_setup); /* * default_hugepagesz command line input * Only one instance of default_hugepagesz allowed on command line. */ static int __init default_hugepagesz_setup(char *s) { unsigned long size; int i; parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); return 1; } size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; parsed_default_hugepagesz = true; default_hstate_idx = hstate_index(size_to_hstate(size)); /* * The number of default huge pages (for this size) could have been * specified as the first hugetlb parameter: hugepages=X. If so, * then default_hstate_max_huge_pages is set. If the default huge * page size is gigantic (> MAX_PAGE_ORDER), then the pages must be * allocated here from bootmem allocator. */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; if (hstate_is_gigantic(&default_hstate)) hugetlb_hstate_alloc_pages(&default_hstate); default_hstate_max_huge_pages = 0; } return 1; } __setup("default_hugepagesz=", default_hugepagesz_setup); static unsigned int allowed_mems_nr(struct hstate *h) { int node; unsigned int nr = 0; nodemask_t *mbind_nodemask; unsigned int *array = h->free_huge_pages_node; gfp_t gfp_mask = htlb_alloc_mask(h); mbind_nodemask = policy_mbind_nodemask(gfp_mask); for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) nr += array[node]; } return nr; } #ifdef CONFIG_SYSCTL static int proc_hugetlb_doulongvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos, unsigned long *out) { struct ctl_table dup_table; /* * In order to avoid races with __do_proc_doulongvec_minmax(), we * can duplicate the @table and alter the duplicate of it. */ dup_table = *table; dup_table.data = out; return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); } static int hugetlb_sysctl_handler_common(bool obey_mempolicy, const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp = h->max_huge_pages; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) ret = __nr_hugepages_store_common(obey_mempolicy, h, NUMA_NO_NODE, tmp, *length); out: return ret; } static int hugetlb_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(false, table, write, buffer, length, ppos); } #ifdef CONFIG_NUMA static int hugetlb_mempolicy_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(true, table, write, buffer, length, ppos); } #endif /* CONFIG_NUMA */ static int hugetlb_overcommit_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; tmp = h->nr_overcommit_huge_pages; if (write && hstate_is_gigantic(h)) return -EINVAL; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) { spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = tmp; spin_unlock_irq(&hugetlb_lock); } out: return ret; } static struct ctl_table hugetlb_table[] = { { .procname = "nr_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_sysctl_handler, }, #ifdef CONFIG_NUMA { .procname = "nr_hugepages_mempolicy", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &hugetlb_mempolicy_sysctl_handler, }, #endif { .procname = "hugetlb_shm_group", .data = &sysctl_hugetlb_shm_group, .maxlen = sizeof(gid_t), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "nr_overcommit_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_overcommit_handler, }, }; static void hugetlb_sysctl_init(void) { register_sysctl_init("vm", hugetlb_table); } #endif /* CONFIG_SYSCTL */ void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h; unsigned long total = 0; if (!hugepages_supported()) return; for_each_hstate(h) { unsigned long count = h->nr_huge_pages; total += huge_page_size(h) * count; if (h == &default_hstate) seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" "HugePages_Rsvd: %5lu\n" "HugePages_Surp: %5lu\n" "Hugepagesize: %8lu kB\n", count, h->free_huge_pages, h->resv_huge_pages, h->surplus_huge_pages, huge_page_size(h) / SZ_1K); } seq_printf(m, "Hugetlb: %8lu kB\n", total / SZ_1K); } int hugetlb_report_node_meminfo(char *buf, int len, int nid) { struct hstate *h = &default_hstate; if (!hugepages_supported()) return 0; return sysfs_emit_at(buf, len, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", nid, h->nr_huge_pages_node[nid], nid, h->free_huge_pages_node[nid], nid, h->surplus_huge_pages_node[nid]); } void hugetlb_show_meminfo_node(int nid) { struct hstate *h; if (!hugepages_supported()) return; for_each_hstate(h) printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", nid, h->nr_huge_pages_node[nid], h->free_huge_pages_node[nid], h->surplus_huge_pages_node[nid], huge_page_size(h) / SZ_1K); } void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) { seq_printf(m, "HugetlbPages:\t%8lu kB\n", K(atomic_long_read(&mm->hugetlb_usage))); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { struct hstate *h; unsigned long nr_total_pages = 0; for_each_hstate(h) nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h); return nr_total_pages; } static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; if (!delta) return 0; spin_lock_irq(&hugetlb_lock); /* * When cpuset is configured, it breaks the strict hugetlb page * reservation as the accounting is done on a global variable. Such * reservation is completely rubbish in the presence of cpuset because * the reservation is not checked against page availability for the * current cpuset. Application can still potentially OOM'ed by kernel * with lack of free htlb page in cpuset that the task is in. * Attempt to enforce strict accounting with cpuset is almost * impossible (or too ugly) because cpuset is too fluid that * task or memory node can be dynamically moved between cpusets. * * The change of semantics for shared hugetlb mapping with cpuset is * undesirable. However, in order to preserve some of the semantics, * we fall back to check against current free page availability as * a best attempt and hopefully to minimize the impact of changing * semantics that cpuset has. * * Apart from cpuset, we also have memory policy mechanism that * also determines from which node the kernel will allocate memory * in a NUMA system. So similar to cpuset, we also should consider * the memory policy of the current task. Similar to the description * above. */ if (delta > 0) { if (gather_surplus_pages(h, delta) < 0) goto out; if (delta > allowed_mems_nr(h)) { return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock_irq(&hugetlb_lock); return ret; } static void hugetlb_vm_op_open(struct vm_area_struct *vma) { struct resv_map *resv = vma_resv_map(vma); /* * HPAGE_RESV_OWNER indicates a private mapping. * This new VMA should share its siblings reservation map if present. * The VMA will only ever have a valid reservation map pointer where * it is being copied for another still existing VMA. As that VMA * has a reference to the reservation map it cannot disappear until * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); } /* * vma_lock structure for sharable mappings is vma specific. * Clear old pointer (if copied via vm_area_dup) and allocate * new structure. Before clearing, make sure vma_lock is not * for this vma. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock) { if (vma_lock->vma != vma) { vma->vm_private_data = NULL; hugetlb_vma_lock_alloc(vma); } else pr_warn("HugeTLB: vma_lock already exists in %s.\n", __func__); } else hugetlb_vma_lock_alloc(vma); } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *resv; struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; long gbl_reserve; hugetlb_vma_lock_free(vma); resv = vma_resv_map(vma); if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; start = vma_hugecache_offset(h, vma, vma->vm_start); end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(resv, start, end); hugetlb_cgroup_uncharge_counter(resv, start, end); if (reserve) { /* * Decrement reserve counts. The global reserve count may be * adjusted if the subpool has a minimum size. */ gbl_reserve = hugepage_subpool_put_pages(spool, reserve); hugetlb_acct_memory(h, -gbl_reserve); } kref_put(&resv->refs, resv_map_release); } static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. */ if (addr & ~PUD_MASK) { /* * hugetlb_vm_op_split is called right before we attempt to * split the VMA. We will need to unshare PMDs in the old and * new VMAs, so let's unshare before we split. */ unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; if (floor >= vma->vm_start && ceil <= vma->vm_end) hugetlb_unshare_pmds(vma, floor, ceil); } return 0; } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) { return huge_page_size(hstate_vma(vma)); } /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the * hugepage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) { BUG(); return 0; } /* * When a new function is introduced to vm_operations_struct and added * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. * This is because under System V memory model, mappings created via * shmget/shmat with "huge page" specified are backed by hugetlbfs files, * their original vm_ops are overwritten with shm_vm_ops. */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, .may_split = hugetlb_vm_op_split, .pagesize = hugetlb_vm_op_pagesize, }; static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable) { pte_t entry; unsigned int shift = huge_page_shift(hstate_vma(vma)); if (writable) { entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, vma->vm_page_prot))); } else { entry = huge_pte_wrprotect(mk_huge_pte(page, vma->vm_page_prot)); } entry = pte_mkyoung(entry); entry = arch_make_huge_pte(entry, shift, vma->vm_flags); return entry; } static void set_huge_ptep_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t entry; entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(vma->vm_mm, address, ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); } bool is_hugetlb_entry_migration(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_migration_entry(swp)) return true; else return false; } bool is_hugetlb_entry_hwpoisoned(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_hwpoison_entry(swp)) return true; else return false; } static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, struct folio *new_folio, pte_t old, unsigned long sz) { pte_t newpte = make_huge_pte(vma, &new_folio->page, 1); __folio_mark_uptodate(new_folio); hugetlb_add_new_anon_rmap(new_folio, vma, addr); if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pte_t *src_pte, *dst_pte, entry; struct folio *pte_folio; unsigned long addr; bool cow = is_cow_mapping(src_vma->vm_flags); struct hstate *h = hstate_vma(src_vma); unsigned long sz = huge_page_size(h); unsigned long npages = pages_per_huge_page(h); struct mmu_notifier_range range; unsigned long last_addr_mask; int ret = 0; if (cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src, src_vma->vm_start, src_vma->vm_end); mmu_notifier_invalidate_range_start(&range); vma_assert_write_locked(src_vma); raw_write_seqcount_begin(&src->write_protect_seq); } else { /* * For shared mappings the vma lock must be held before * calling hugetlb_walk() in the src vma. Otherwise, the * returned ptep could go away if part of a shared pmd and * another thread calls huge_pmd_unshare. */ hugetlb_vma_lock_read(src_vma); } last_addr_mask = hugetlb_mask_last_page(h); for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = hugetlb_walk(src_vma, addr, sz); if (!src_pte) { addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; } /* * If the pagetables are shared don't copy or take references. * * dst_pte == src_pte is the common case of src/dest sharing. * However, src could have 'unshared' and dst shares with * another vma. So page_count of ptep page is checked instead * to reliably determine whether pte is shared. */ if (page_count(virt_to_page(dst_pte)) > 1) { addr |= last_addr_mask; continue; } dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); again: if (huge_pte_none(entry)) { /* * Skip if src entry none. */ ; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); bool uffd_wp = pte_swp_uffd_wp(entry); if (!is_readable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ swp_entry = make_readable_migration_entry( swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); if (userfaultfd_wp(src_vma) && uffd_wp) entry = pte_swp_mkuffd_wp(entry); set_huge_pte_at(src, addr, src_pte, entry, sz); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_pte_marker(entry))) { pte_marker marker = copy_pte_marker( pte_to_swp_entry(entry), dst_vma); if (marker) set_huge_pte_at(dst, addr, dst_pte, make_pte_marker(marker), sz); } else { entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); pte_folio = page_folio(pte_page(entry)); folio_get(pte_folio); /* * Failing to duplicate the anon rmap is a rare case * where we see pinned hugetlb pages while they're * prone to COW. We need to do the COW earlier during * fork. * * When pre-allocating the page or copying data, we * need to be without the pgtable locks since we could * sleep during the process. */ if (!folio_test_anon(pte_folio)) { hugetlb_add_file_rmap(pte_folio); } else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) { pte_t src_pte_old = entry; struct folio *new_folio; spin_unlock(src_ptl); spin_unlock(dst_ptl); /* Do not use reserve as it's private owned */ new_folio = alloc_hugetlb_folio(dst_vma, addr, 1); if (IS_ERR(new_folio)) { folio_put(pte_folio); ret = PTR_ERR(new_folio); break; } ret = copy_user_large_folio(new_folio, pte_folio, ALIGN_DOWN(addr, sz), dst_vma); folio_put(pte_folio); if (ret) { folio_put(new_folio); break; } /* Install the new hugetlb folio if src pte stable */ dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); if (!pte_same(src_pte_old, entry)) { restore_reserve_on_error(h, dst_vma, addr, new_folio); folio_put(new_folio); /* huge_ptep of dst_pte won't change as in child */ goto again; } hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio, src_pte_old, sz); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; } if (cow) { /* * No need to notify as we are downgrading page * table protection not changing it to point * to a new page. * * See Documentation/mm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); entry = huge_pte_wrprotect(entry); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); hugetlb_count_add(npages, dst); } spin_unlock(src_ptl); spin_unlock(dst_ptl); } if (cow) { raw_write_seqcount_end(&src->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } else { hugetlb_vma_unlock_read(src_vma); } return ret; } static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, unsigned long sz) { struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; spinlock_t *src_ptl, *dst_ptl; pte_t pte; dst_ptl = huge_pte_lock(h, mm, dst_pte); src_ptl = huge_pte_lockptr(h, mm, src_pte); /* * We don't have to worry about the ordering of src and dst ptlocks * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock. */ if (src_ptl != dst_ptl) spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); if (src_ptl != dst_ptl) spin_unlock(src_ptl); spin_unlock(dst_ptl); } int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { struct hstate *h = hstate_vma(vma); struct address_space *mapping = vma->vm_file->f_mapping; unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; unsigned long old_end = old_addr + len; unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; bool shared_pmd = false; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* * In case of shared PMDs, we should cover the maximum possible * range. */ flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); /* Prevent race with file truncation */ hugetlb_vma_lock_write(vma); i_mmap_lock_write(mapping); for (; old_addr < old_end; old_addr += sz, new_addr += sz) { src_pte = hugetlb_walk(vma, old_addr, sz); if (!src_pte) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte))) continue; if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { shared_pmd = true; old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); if (!dst_pte) break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); } if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, old_end - len, old_end); mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); return len + old_addr - old_end; } void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long address; pte_t *ptep; pte_t pte; spinlock_t *ptl; struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); bool adjust_reservation = false; unsigned long last_addr_mask; bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); /* * This is a hugetlb vma, all the pte entries should point * to huge page. */ tlb_change_page_size(tlb, sz); tlb_start_vma(tlb, vma); last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) { address |= last_addr_mask; continue; } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { spin_unlock(ptl); tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); force_flush = true; address |= last_addr_mask; continue; } pte = huge_ptep_get(mm, address, ptep); if (huge_pte_none(pte)) { spin_unlock(ptl); continue; } /* * Migrating hugepage or HWPoisoned hugepage is already * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { /* * If the pte was wr-protected by uffd-wp in any of the * swap forms, meanwhile the caller does not want to * drop the uffd-wp bit in this zap, then replace the * pte with a marker. */ if (pte_swp_uffd_wp_any(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); else huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } page = pte_page(pte); /* * If a reference page is supplied, it is because a specific * page is being unmapped, not a range. Ensure the page we * are about to unmap is the actual page of interest. */ if (ref_page) { if (page != ref_page) { spin_unlock(ptl); continue; } /* * Mark the VMA as having unmapped its page so that * future faults in this VMA will fail rather than * looking like data was lost */ set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); } pte = huge_ptep_get_and_clear(mm, address, ptep); tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); /* Leave a uffd-wp pte marker if needed */ if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); hugetlb_count_sub(pages_per_huge_page(h), mm); hugetlb_remove_rmap(page_folio(page)); /* * Restore the reservation for anonymous page, otherwise the * backing page could be stolen by someone. * If there we are freeing a surplus, do not set the restore * reservation bit. */ if (!h->surplus_huge_pages && __vma_private_lock(vma) && folio_test_anon(page_folio(page))) { folio_set_hugetlb_restore_reserve(page_folio(page)); /* Reservation to be adjusted after the spin lock */ adjust_reservation = true; } spin_unlock(ptl); /* * Adjust the reservation for the region that will have the * reserve restored. Keep in mind that vma_needs_reservation() changes * resv->adds_in_progress if it succeeds. If this is not done, * do_exit() will not see it, and will keep the reservation * forever. */ if (adjust_reservation) { int rc = vma_needs_reservation(h, vma, address); if (rc < 0) /* Pressumably allocate_file_region_entries failed * to allocate a file_region struct. Clear * hugetlb_restore_reserve so that global reserve * count will not be incremented by free_huge_folio. * Act as if we consumed the reservation. */ folio_clear_hugetlb_restore_reserve(page_folio(page)); else if (rc) vma_add_reservation(h, vma, address); } tlb_remove_page_size(tlb, page, huge_page_size(h)); /* * Bail out after unmapping reference page if supplied */ if (ref_page) break; } tlb_end_vma(tlb, vma); /* * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We * could defer the flush until now, since by holding i_mmap_rwsem we * guaranteed that the last refernece would not be dropped. But we must * do the flushing before we return, as otherwise i_mmap_rwsem will be * dropped and the last reference to the shared PMDs page might be * dropped as well. * * In theory we could defer the freeing of the PMD pages as well, but * huge_pmd_unshare() relies on the exact page_count for the PMD page to * detect sharing, so we cannot defer the release of the page either. * Instead, do flush now. */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); } void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; adjust_range_if_pmd_sharing_possible(vma, start, end); hugetlb_vma_lock_write(vma); if (vma->vm_file) i_mmap_lock_write(vma->vm_file->f_mapping); } void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { zap_flags_t zap_flags = details ? details->zap_flags : 0; if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */ /* * Unlock and free the vma lock before releasing i_mmap_rwsem. * When the vma_lock is freed, this makes the vma ineligible * for pmd sharing. And, i_mmap_rwsem is required to set up * pmd sharing. This is important as page tables for this * unmapped range will be asynchrously deleted. If the page * tables are shared, there will be issues when accessed by * someone else. */ __hugetlb_vma_unlock_write_free(vma); } else { hugetlb_vma_unlock_write(vma); } if (vma->vm_file) i_mmap_unlock_write(vma->vm_file->f_mapping); } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { struct mmu_notifier_range range; struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); tlb_gather_mmu(&tlb, vma->vm_mm); __unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } /* * This is called when the original mapper is failing to COW a MAP_PRIVATE * mapping it owns the reserve page for. The intention is to unmap the page * from other VMAs and let the children be SIGKILLed if they are faulting the * same region. */ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page, unsigned long address) { struct hstate *h = hstate_vma(vma); struct vm_area_struct *iter_vma; struct address_space *mapping; pgoff_t pgoff; /* * vm_pgoff is in PAGE_SIZE units, hence the different calculation * from page cache lookup which is in HPAGE_SIZE units. */ address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; mapping = vma->vm_file->f_mapping; /* * Take the mapping lock for the duration of the table walk. As * this mapping should be shared between all the VMAs, * __unmap_hugepage_range() is called as the lock is already held */ i_mmap_lock_write(mapping); vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) continue; /* * Shared VMAs have their own reserves and do not affect * MAP_PRIVATE accounting but it is possible that a shared * VMA is using the same page so check and skip such VMAs. */ if (iter_vma->vm_flags & VM_MAYSHARE) continue; /* * Unmap the page from other VMAs without their own reserves. * They get marked to be SIGKILLed if they fault in these * areas. This is because a future no-page fault on this VMA * could insert a zeroed page instead of the data existing * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), page, 0); } i_mmap_unlock_write(mapping); } /* * hugetlb_wp() should be called with page lock of the original hugepage held. * Called with hugetlb_fault_mutex_table held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio, struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; pte_t pte = huge_ptep_get(mm, vmf->address, vmf->pte); struct hstate *h = hstate_vma(vma); struct folio *old_folio; struct folio *new_folio; int outside_reserve = 0; vm_fault_t ret = 0; struct mmu_notifier_range range; /* * Never handle CoW for uffd-wp protected pages. It should be only * handled when the uffd-wp protection is removed. * * Note that only the CoW optimization path (in hugetlb_no_page()) * can trigger this, because hugetlb_fault() will always resolve * uffd-wp bit first. */ if (!unshare && huge_pte_uffd_wp(pte)) return 0; /* * hugetlb does not support FOLL_FORCE-style write faults that keep the * PTE mapped R/O such as maybe_mkwrite() would do. */ if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE))) return VM_FAULT_SIGSEGV; /* Let's take out MAP_SHARED mappings first. */ if (vma->vm_flags & VM_MAYSHARE) { set_huge_ptep_writable(vma, vmf->address, vmf->pte); return 0; } old_folio = page_folio(pte_page(pte)); delayacct_wpcopy_start(); retry_avoidcopy: /* * If no-one else is actually using this page, we're the exclusive * owner and can reuse this page. * * Note that we don't rely on the (safer) folio refcount here, because * copying the hugetlb folio when there are unexpected (temporary) * folio references could harm simple fork()+exit() users when * we run out of free hugetlb folios: we would have to kill processes * in scenarios that used to work. As a side effect, there can still * be leaks between processes, for example, with FOLL_GET users. */ if (folio_mapcount(old_folio) == 1 && folio_test_anon(old_folio)) { if (!PageAnonExclusive(&old_folio->page)) { folio_move_anon_rmap(old_folio, vma); SetPageAnonExclusive(&old_folio->page); } if (likely(!unshare)) set_huge_ptep_writable(vma, vmf->address, vmf->pte); delayacct_wpcopy_end(); return 0; } VM_BUG_ON_PAGE(folio_test_anon(old_folio) && PageAnonExclusive(&old_folio->page), &old_folio->page); /* * If the process that created a MAP_PRIVATE mapping is about to * perform a COW due to a shared page count, attempt to satisfy * the allocation without using the existing reserves. The pagecache * page is used to determine if the reserve at this address was * consumed or not. If reserves were used, a partial faulted mapping * at the time of fork() could consume its reserves on COW instead * of the full address range. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_folio != pagecache_folio) outside_reserve = 1; folio_get(old_folio); /* * Drop page table lock as buddy allocator may be called. It will * be acquired again before returning to the caller, as expected. */ spin_unlock(vmf->ptl); new_folio = alloc_hugetlb_folio(vma, vmf->address, outside_reserve); if (IS_ERR(new_folio)) { /* * If a process owning a MAP_PRIVATE mapping fails to COW, * it is due to references held by a child and an insufficient * huge page pool. To guarantee the original mappers * reliability, unmap the page from child processes. The child * may get SIGKILLed if it later faults. */ if (outside_reserve) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx; u32 hash; folio_put(old_folio); /* * Drop hugetlb_fault_mutex and vma_lock before * unmapping. unmapping needs to hold vma_lock * in write mode. Dropping vma_lock in read mode * here is OK as COW mappings do not interact with * PMD sharing. * * Reacquire both after unmap operation. */ idx = vma_hugecache_offset(h, vma, vmf->address); hash = hugetlb_fault_mutex_hash(mapping, idx); hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); unmap_ref_private(mm, vma, &old_folio->page, vmf->address); mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(vma); spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte))) goto retry_avoidcopy; /* * race occurs while re-acquiring page table * lock, and our job is done. */ delayacct_wpcopy_end(); return 0; } ret = vmf_error(PTR_ERR(new_folio)); goto out_release_old; } /* * When the original hugepage is shared one, it does not have * anon_vma prepared. */ ret = __vmf_anon_prepare(vmf); if (unlikely(ret)) goto out_release_all; if (copy_user_large_folio(new_folio, old_folio, vmf->real_address, vma)) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_release_all; } __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address, vmf->address + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); /* * Retake the page table lock to check for racing updates * before the page tables are altered */ spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte))) { pte_t newpte = make_huge_pte(vma, &new_folio->page, !unshare); /* Break COW or unshare */ huge_ptep_clear_flush(vma, vmf->address, vmf->pte); hugetlb_remove_rmap(old_folio); hugetlb_add_new_anon_rmap(new_folio, vma, vmf->address); if (huge_pte_uffd_wp(pte)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(mm, vmf->address, vmf->pte, newpte, huge_page_size(h)); folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ new_folio = old_folio; } spin_unlock(vmf->ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: /* * No restore in case of successful pagetable update (Break COW or * unshare) */ if (new_folio != old_folio) restore_reserve_on_error(h, vma, vmf->address, new_folio); folio_put(new_folio); out_release_old: folio_put(old_folio); spin_lock(vmf->ptl); /* Caller expects lock to be held */ delayacct_wpcopy_end(); return ret; } /* * Return whether there is a pagecache page to back given address within VMA. */ bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = linear_page_index(vma, address); struct folio *folio; folio = filemap_get_folio(mapping, idx); if (IS_ERR(folio)) return false; folio_put(folio); return true; } int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx) { struct inode *inode = mapping->host; struct hstate *h = hstate_inode(inode); int err; idx <<= huge_page_order(h); __folio_set_locked(folio); err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL); if (unlikely(err)) { __folio_clear_locked(folio); return err; } folio_clear_hugetlb_restore_reserve(folio); /* * mark folio dirty so that it will not be removed from cache/file * by non-hugetlbfs specific code paths. */ folio_mark_dirty(folio); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); return 0; } static inline vm_fault_t hugetlb_handle_userfault(struct vm_fault *vmf, struct address_space *mapping, unsigned long reason) { u32 hash; /* * vma_lock and hugetlb_fault_mutex must be dropped before handling * userfault. Also mmap_lock could be dropped due to handling * userfault, any vma operation should be careful from here. */ hugetlb_vma_unlock_read(vmf->vma); hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(vmf, reason); } /* * Recheck pte with pgtable lock. Returns true if pte didn't change, or * false if pte changed or is changing. */ static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t old_pte) { spinlock_t *ptl; bool same; ptl = huge_pte_lock(h, mm, ptep); same = pte_same(huge_ptep_get(mm, addr, ptep), old_pte); spin_unlock(ptl); return same; } static vm_fault_t hugetlb_no_page(struct address_space *mapping, struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; int anon_rmap = 0; unsigned long size; struct folio *folio; pte_t new_pte; bool new_folio, new_pagecache_folio = false; u32 hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed * COW/unsharing. Warn that such a situation has occurred as it may not * be obvious. */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); goto out; } /* * Use page lock to guard against racing truncation * before we get page_table_lock. */ new_folio = false; folio = filemap_lock_hugetlb_folio(h, mapping, vmf->pgoff); if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (vmf->pgoff >= size) goto out; /* Check for page in userfault range */ if (userfaultfd_missing(vma)) { /* * Since hugetlb_no_page() was examining pte * without pgtable lock, we need to re-test under * lock because the pte may not be stable and could * have changed from under us. Try to detect * either changed or during-changing ptes and retry * properly when needed. * * Note that userfaultfd is actually fine with * false positives (e.g. caused by pte changed), * but not wrong logical events (e.g. caused by * reading a pte during changing). The latter can * confuse the userspace, so the strictness is very * much preferred. E.g., MISSING event should * never happen on the page after UFFDIO_COPY has * correctly installed the page and returned. */ if (!hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MISSING); } if (!(vma->vm_flags & VM_MAYSHARE)) { ret = __vmf_anon_prepare(vmf); if (unlikely(ret)) goto out; } folio = alloc_hugetlb_folio(vma, vmf->address, 0); if (IS_ERR(folio)) { /* * Returning error will result in faulting task being * sent SIGBUS. The hugetlb fault mutex prevents two * tasks from racing to fault in the same page which * could result in false unable to allocate errors. * Page migration does not take the fault mutex, but * does a clear then write of pte's under page table * lock. Page fault code could race with migration, * notice the clear pte and try to allocate a page * here. Before returning error, get ptl and make * sure there really is no pte entry. */ if (hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) ret = vmf_error(PTR_ERR(folio)); else ret = 0; goto out; } folio_zero_user(folio, vmf->real_address); __folio_mark_uptodate(folio); new_folio = true; if (vma->vm_flags & VM_MAYSHARE) { int err = hugetlb_add_to_page_cache(folio, mapping, vmf->pgoff); if (err) { /* * err can't be -EEXIST which implies someone * else consumed the reservation since hugetlb * fault mutex is held when add a hugetlb page * to the page cache. So it's safe to call * restore_reserve_on_error() here. */ restore_reserve_on_error(h, vma, vmf->address, folio); folio_put(folio); ret = VM_FAULT_SIGBUS; goto out; } new_pagecache_folio = true; } else { folio_lock(folio); anon_rmap = 1; } } else { /* * If memory error occurs between mmap() and fault, some process * don't have hwpoisoned swap entry for errored virtual address. * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(folio_test_hwpoison(folio))) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } /* Check for page in userfault range. */ if (userfaultfd_minor(vma)) { folio_unlock(folio); folio_put(folio); /* See comment in userfaultfd_missing() block above */ if (!hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MINOR); } } /* * If we are going to COW a private mapping later, we examine the * pending reservations for this page now. This will ensure that * any allocations necessary to record that reservation occur outside * the spinlock. */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { if (vma_needs_reservation(h, vma, vmf->address) < 0) { ret = VM_FAULT_OOM; goto backout_unlocked; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf->address); } vmf->ptl = huge_pte_lock(h, mm, vmf->pte); ret = 0; /* If pte changed from under us, retry */ if (!pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), vmf->orig_pte)) goto backout; if (anon_rmap) hugetlb_add_new_anon_rmap(folio, vma, vmf->address); else hugetlb_add_file_rmap(folio); new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); /* * If this pte was previously wr-protected, keep it wr-protected even * if populated. */ if (unlikely(pte_marker_uffd_wp(vmf->orig_pte))) new_pte = huge_pte_mkuffd_wp(new_pte); set_huge_pte_at(mm, vmf->address, vmf->pte, new_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), mm); if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ ret = hugetlb_wp(folio, vmf); } spin_unlock(vmf->ptl); /* * Only set hugetlb_migratable in newly allocated pages. Existing pages * found in the pagecache may not have hugetlb_migratable if they have * been isolated for migration. */ if (new_folio) folio_set_hugetlb_migratable(folio); folio_unlock(folio); out: hugetlb_vma_unlock_read(vma); /* * We must check to release the per-VMA lock. __vmf_anon_prepare() is * the only way ret can be set to VM_FAULT_RETRY. */ if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return ret; backout: spin_unlock(vmf->ptl); backout_unlocked: if (new_folio && !new_pagecache_folio) restore_reserve_on_error(h, vma, vmf->address, folio); folio_unlock(folio); folio_put(folio); goto out; } #ifdef CONFIG_SMP u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; key[0] = (unsigned long) mapping; key[1] = idx; hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } #else /* * For uniprocessor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } #endif vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { vm_fault_t ret; u32 hash; struct folio *folio = NULL; struct folio *pagecache_folio = NULL; struct hstate *h = hstate_vma(vma); struct address_space *mapping; int need_wait_lock = 0; struct vm_fault vmf = { .vma = vma, .address = address & huge_page_mask(h), .real_address = address, .flags = flags, .pgoff = vma_hugecache_offset(h, vma, address & huge_page_mask(h)), /* TODO: Track hugetlb faults using vm_fault */ /* * Some fields may not be initialized, be careful as it may * be hard to debug if called functions make assumptions */ }; /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ mapping = vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(mapping, vmf.pgoff); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* * Acquire vma lock before calling huge_pte_alloc and hold * until finished with vmf.pte. This prevents huge_pmd_unshare from * being called elsewhere and making the vmf.pte no longer valid. */ hugetlb_vma_lock_read(vma); vmf.pte = huge_pte_alloc(mm, vma, vmf.address, huge_page_size(h)); if (!vmf.pte) { hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return VM_FAULT_OOM; } vmf.orig_pte = huge_ptep_get(mm, vmf.address, vmf.pte); if (huge_pte_none_mostly(vmf.orig_pte)) { if (is_pte_marker(vmf.orig_pte)) { pte_marker marker = pte_marker_get(pte_to_swp_entry(vmf.orig_pte)); if (marker & PTE_MARKER_POISONED) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } } /* * Other PTE markers should be handled the same way as none PTE. * * hugetlb_no_page will drop vma lock and hugetlb fault * mutex internally, which make us return immediately. */ return hugetlb_no_page(mapping, &vmf); } ret = 0; /* * vmf.orig_pte could be a migration/hwpoison vmf.orig_pte at this * point, so this check prevents the kernel from going below assuming * that we have an active hugepage in pagecache. This goto expects * the 2nd page fault, and is_hugetlb_entry_(migration|hwpoisoned) * check will properly handle it. */ if (!pte_present(vmf.orig_pte)) { if (unlikely(is_hugetlb_entry_migration(vmf.orig_pte))) { /* * Release the hugetlb fault lock now, but retain * the vma lock, because it is needed to guard the * huge_pte_lockptr() later in * migration_entry_wait_huge(). The vma lock will * be released there. */ mutex_unlock(&hugetlb_fault_mutex_table[hash]); migration_entry_wait_huge(vma, vmf.address, vmf.pte); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(vmf.orig_pte))) ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } /* * If we are going to COW/unshare the mapping later, we examine the * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the * spinlock. Also lookup the pagecache page now as it is used to * determine if a reservation has been consumed. */ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(vmf.orig_pte)) { if (vma_needs_reservation(h, vma, vmf.address) < 0) { ret = VM_FAULT_OOM; goto out_mutex; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf.address); pagecache_folio = filemap_lock_hugetlb_folio(h, mapping, vmf.pgoff); if (IS_ERR(pagecache_folio)) pagecache_folio = NULL; } vmf.ptl = huge_pte_lock(h, mm, vmf.pte); /* Check for a racing update before calling hugetlb_wp() */ if (unlikely(!pte_same(vmf.orig_pte, huge_ptep_get(mm, vmf.address, vmf.pte)))) goto out_ptl; /* Handle userfault-wp first, before trying to lock more pages */ if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(mm, vmf.address, vmf.pte)) && (flags & FAULT_FLAG_WRITE) && !huge_pte_write(vmf.orig_pte)) { if (!userfaultfd_wp_async(vma)) { spin_unlock(vmf.ptl); if (pagecache_folio) { folio_unlock(pagecache_folio); folio_put(pagecache_folio); } hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(&vmf, VM_UFFD_WP); } vmf.orig_pte = huge_pte_clear_uffd_wp(vmf.orig_pte); set_huge_pte_at(mm, vmf.address, vmf.pte, vmf.orig_pte, huge_page_size(hstate_vma(vma))); /* Fallthrough to CoW */ } /* * hugetlb_wp() requires page locks of pte_page(vmf.orig_pte) and * pagecache_folio, so here we need take the former one * when folio != pagecache_folio or !pagecache_folio. */ folio = page_folio(pte_page(vmf.orig_pte)); if (folio != pagecache_folio) if (!folio_trylock(folio)) { need_wait_lock = 1; goto out_ptl; } folio_get(folio); if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!huge_pte_write(vmf.orig_pte)) { ret = hugetlb_wp(pagecache_folio, &vmf); goto out_put_page; } else if (likely(flags & FAULT_FLAG_WRITE)) { vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte); } } vmf.orig_pte = pte_mkyoung(vmf.orig_pte); if (huge_ptep_set_access_flags(vma, vmf.address, vmf.pte, vmf.orig_pte, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, vmf.address, vmf.pte); out_put_page: if (folio != pagecache_folio) folio_unlock(folio); folio_put(folio); out_ptl: spin_unlock(vmf.ptl); if (pagecache_folio) { folio_unlock(pagecache_folio); folio_put(pagecache_folio); } out_mutex: hugetlb_vma_unlock_read(vma); /* * We must check to release the per-VMA lock. __vmf_anon_prepare() in * hugetlb_wp() is the only way ret can be set to VM_FAULT_RETRY. */ if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); /* * Generally it's safe to hold refcount during waiting page lock. But * here we just wait to defer the next page fault to avoid busy loop and * the page is not used after unlocked before returning from the current * page fault. So we are safe from accessing freed page, even if we wait * here without taking refcount. */ if (need_wait_lock) folio_wait_locked(folio); return ret; } #ifdef CONFIG_USERFAULTFD /* * Can probably be eliminated, but still used by hugetlb_mfill_atomic_pte(). */ static struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct mempolicy *mpol; nodemask_t *nodemask; struct folio *folio; gfp_t gfp_mask; int node; gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); /* * This is used to allocate a temporary hugetlb to hold the copied * content, which will then be copied again to the final hugetlb * consuming a reservation. Set the alloc_fallback to false to indicate * that breaking the per-node hugetlb pool is not allowed in this case. */ folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask, false); mpol_cond_put(mpol); return folio; } /* * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte * with modifications for hugetlb pages. */ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { struct mm_struct *dst_mm = dst_vma->vm_mm; bool is_continue = uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE); bool wp_enabled = (flags & MFILL_ATOMIC_WP); struct hstate *h = hstate_vma(dst_vma); struct address_space *mapping = dst_vma->vm_file->f_mapping; pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); unsigned long size = huge_page_size(h); int vm_shared = dst_vma->vm_flags & VM_SHARED; pte_t _dst_pte; spinlock_t *ptl; int ret = -ENOMEM; struct folio *folio; int writable; bool folio_in_pagecache = false; if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON)) { ptl = huge_pte_lock(h, dst_mm, dst_pte); /* Don't overwrite any existing PTEs (even markers) */ if (!huge_pte_none(huge_ptep_get(dst_mm, dst_addr, dst_pte))) { spin_unlock(ptl); return -EEXIST; } _dst_pte = make_pte_marker(PTE_MARKER_POISONED); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, size); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); return 0; } if (is_continue) { ret = -EFAULT; folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) goto out; folio_in_pagecache = true; } else if (!*foliop) { /* If a folio already exists, then it's UFFDIO_COPY for * a non-missing case. Return -EEXIST. */ if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { ret = -EEXIST; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); if (IS_ERR(folio)) { ret = -ENOMEM; goto out; } ret = copy_folio_from_user(folio, (const void __user *) src_addr, false); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; /* Free the allocated folio which may have * consumed a reservation. */ restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); /* Allocate a temporary folio to hold the copied * contents. */ folio = alloc_hugetlb_folio_vma(h, dst_vma, dst_addr); if (!folio) { ret = -ENOMEM; goto out; } *foliop = folio; /* Set the outparam foliop and return to the caller to * copy the contents outside the lock. Don't free the * folio. */ goto out; } } else { if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { folio_put(*foliop); ret = -EEXIST; *foliop = NULL; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); if (IS_ERR(folio)) { folio_put(*foliop); ret = -ENOMEM; *foliop = NULL; goto out; } ret = copy_user_large_folio(folio, *foliop, ALIGN_DOWN(dst_addr, size), dst_vma); folio_put(*foliop); *foliop = NULL; if (ret) { folio_put(folio); goto out; } } /* * If we just allocated a new page, we need a memory barrier to ensure * that preceding stores to the page become visible before the * set_pte_at() write. The memory barrier inside __folio_mark_uptodate * is what we need. * * In the case where we have not allocated a new page (is_continue), * the page must already be uptodate. UFFDIO_CONTINUE already includes * an earlier smp_wmb() to ensure that prior stores will be visible * before the set_pte_at() write. */ if (!is_continue) __folio_mark_uptodate(folio); else WARN_ON_ONCE(!folio_test_uptodate(folio)); /* Add shared, newly allocated pages to the page cache. */ if (vm_shared && !is_continue) { ret = -EFAULT; if (idx >= (i_size_read(mapping->host) >> huge_page_shift(h))) goto out_release_nounlock; /* * Serialization between remove_inode_hugepages() and * hugetlb_add_to_page_cache() below happens through the * hugetlb_fault_mutex_table that here must be hold by * the caller. */ ret = hugetlb_add_to_page_cache(folio, mapping, idx); if (ret) goto out_release_nounlock; folio_in_pagecache = true; } ptl = huge_pte_lock(h, dst_mm, dst_pte); ret = -EIO; if (folio_test_hwpoison(folio)) goto out_release_unlock; /* * We allow to overwrite a pte marker: consider when both MISSING|WP * registered, we firstly wr-protect a none pte which has no page cache * page backing it, then access the page. */ ret = -EEXIST; if (!huge_pte_none_mostly(huge_ptep_get(dst_mm, dst_addr, dst_pte))) goto out_release_unlock; if (folio_in_pagecache) hugetlb_add_file_rmap(folio); else hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr); /* * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY * with wp flag set, don't set pte write bit. */ if (wp_enabled || (is_continue && !vm_shared)) writable = 0; else writable = dst_vma->vm_flags & VM_WRITE; _dst_pte = make_huge_pte(dst_vma, &folio->page, writable); /* * Always mark UFFDIO_COPY page dirty; note that this may not be * extremely important for hugetlbfs for now since swapping is not * supported, but we should still be clear in that this page cannot be * thrown away at will, even if write bit not set. */ _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); if (wp_enabled) _dst_pte = huge_pte_mkuffd_wp(_dst_pte); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, size); hugetlb_count_add(pages_per_huge_page(h), dst_mm); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); if (!is_continue) folio_set_hugetlb_migratable(folio); if (vm_shared || is_continue) folio_unlock(folio); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); if (vm_shared || is_continue) folio_unlock(folio); out_release_nounlock: if (!folio_in_pagecache) restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); goto out; } #endif /* CONFIG_USERFAULTFD */ long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; /* * In the case of shared PMDs, the area to flush could be beyond * start/end. Set range.start/range.end to cover the maximum possible * range if PMD sharing is possible. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); last_addr_mask = hugetlb_mask_last_page(h); for (; address < end; address += psize) { spinlock_t *ptl; ptep = hugetlb_walk(vma, address, psize); if (!ptep) { if (!uffd_wp) { address |= last_addr_mask; continue; } /* * Userfaultfd wr-protect requires pgtable * pre-allocations to install pte markers. */ ptep = huge_pte_alloc(mm, vma, address, psize); if (!ptep) { pages = -ENOMEM; break; } } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it * happened due to some reason. */ WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); shared_pmd = true; address |= last_addr_mask; continue; } pte = huge_ptep_get(mm, address, ptep); if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { /* Nothing to do. */ } else if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); struct page *page = pfn_swap_entry_to_page(entry); pte_t newpte = pte; if (is_writable_migration_entry(entry)) { if (PageAnon(page)) entry = make_readable_exclusive_migration_entry( swp_offset(entry)); else entry = make_readable_migration_entry( swp_offset(entry)); newpte = swp_entry_to_pte(entry); pages++; } if (uffd_wp) newpte = pte_swp_mkuffd_wp(newpte); else if (uffd_wp_resolve) newpte = pte_swp_clear_uffd_wp(newpte); if (!pte_same(pte, newpte)) set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { /* * Do nothing on a poison marker; page is * corrupted, permissons do not apply. Here * pte_marker_uffd_wp()==true implies !poison * because they're mutual exclusive. */ if (pte_marker_uffd_wp(pte) && uffd_wp_resolve) /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); } else if (!huge_pte_none(pte)) { pte_t old_pte; unsigned int shift = huge_page_shift(hstate_vma(vma)); old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = huge_pte_modify(old_pte, newprot); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (uffd_wp) pte = huge_pte_mkuffd_wp(pte); else if (uffd_wp_resolve) pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; } else { /* None pte */ if (unlikely(uffd_wp)) /* Safe to modify directly (none->non-present). */ set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), psize); } spin_unlock(ptl); } /* * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: * once we release i_mmap_rwsem, another task can do the final put_page * and that page table be reused and filled with junk. If we actually * did unshare a page of pmds, flush the range corresponding to the pud. */ if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, start, end); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new * page. * * See Documentation/mm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); return pages > 0 ? (pages << h->order) : pages; } /* Return true if reservation was successful, false otherwise. */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags) { long chg = -1, add = -1; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; struct hugetlb_cgroup *h_cg = NULL; long gbl_reserve, regions_needed = 0; /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); return false; } /* * vma specific semaphore used for pmd sharing and fault/truncation * synchronization */ hugetlb_vma_lock_alloc(vma); /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page * without using reserves */ if (vm_flags & VM_NORESERVE) return true; /* * Shared mappings base their reservation on the number of pages that * are already allocated on behalf of the file. Private mappings need * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ if (!vma || vma->vm_flags & VM_MAYSHARE) { /* * resv_map can not be NULL as hugetlb_reserve_pages is only * called for inodes for which resv_maps were created (see * hugetlbfs_get_inode). */ resv_map = inode_resv_map(inode); chg = region_chg(resv_map, from, to, ®ions_needed); } else { /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) goto out_err; chg = to - from; set_vma_resv_map(vma, resv_map); set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } if (chg < 0) goto out_err; if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), &h_cg) < 0) goto out_err; if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { /* For private mappings, the hugetlb_cgroup uncharge info hangs * of the resv_map. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h); } /* * There must be enough pages in the subpool for the mapping. If * the subpool has a minimum size, there may be some global * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); if (gbl_reserve < 0) goto out_uncharge_cgroup; /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; /* * Account for the reservations made. Shared mappings record regions * that have reservations as they are shared by multiple VMAs. * When the last VMA disappears, the region map says how much * the reservation was and the page cache tells how much of * the reservation was consumed. Private mappings are per-VMA and * only the consumed reservations are tracked. When the VMA * disappears, the original reservation is the VMA size and the * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) { add = region_add(resv_map, from, to, regions_needed, h, h_cg); if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); goto out_put_pages; } else if (unlikely(chg > add)) { /* * pages in this range were added to the reserve * map between region_chg and region_add. This * indicates a race with alloc_hugetlb_folio. Adjust * the subpool and reserve counts modified above * based on the difference. */ long rsv_adjust; /* * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the * reference to h_cg->css. See comment below for detail. */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); } else if (h_cg) { /* * The file_regions will hold their own reference to * h_cg->css. So we should release the reference held * via hugetlb_cgroup_charge_cgroup_rsvd() when we are * done. */ hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return true; out_put_pages: /* put back original number of pages, chg */ (void)hugepage_subpool_put_pages(spool, chg); out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg); out_err: hugetlb_vma_lock_free(vma); if (!vma || vma->vm_flags & VM_MAYSHARE) /* Only call region_abort if the region_chg succeeded but the * region_add failed or didn't run. */ if (chg >= 0 && add < 0) region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { kref_put(&resv_map->refs, resv_map_release); set_vma_resv_map(vma, NULL); } return false; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed) { struct hstate *h = hstate_inode(inode); struct resv_map *resv_map = inode_resv_map(inode); long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); long gbl_reserve; /* * Since this routine can be called in the evict inode path for all * hugetlbfs inodes, resv_map could be NULL. */ if (resv_map) { chg = region_del(resv_map, start, end); /* * region_del() can fail in the rare case where a region * must be split and another region descriptor can not be * allocated. If end == LONG_MAX, it will not fail. */ if (chg < 0) return chg; } spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); /* * If the subpool has a minimum size, the number of global * reservations to be released may be adjusted. * * Note that !resv_map implies freed == 0. So (chg - freed) * won't go negative. */ gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -gbl_reserve); return 0; } #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static unsigned long page_table_shareable(struct vm_area_struct *svma, struct vm_area_struct *vma, unsigned long addr, pgoff_t idx) { unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + svma->vm_start; unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; /* Allow segments to share if only one is marked locked */ unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED_MASK; unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED_MASK; /* * match the virtual addresses, permission and the alignment of the * page table page. * * Also, vma_lock (vm_private_data) is required for sharing. */ if (pmd_index(addr) != pmd_index(saddr) || vm_flags != svm_flags || !range_in_vma(svma, sbase, s_end) || !svma->vm_private_data) return 0; return saddr; } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { unsigned long start = addr & PUD_MASK; unsigned long end = start + PUD_SIZE; #ifdef CONFIG_USERFAULTFD if (uffd_disable_huge_pmd_share(vma)) return false; #endif /* * check on proper vm_flags and page table alignment */ if (!(vma->vm_flags & VM_MAYSHARE)) return false; if (!vma->vm_private_data) /* vma lock required for sharing */ return false; if (!range_in_vma(vma, start, end)) return false; return true; } /* * Determine if start,end range within vma could be mapped by shared pmd. * If yes, adjust start and end to cover range associated with possible * shared pmd mappings. */ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); /* * vma needs to span at least one aligned PUD size, and the range * must be at least partially within in. */ if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || (*end <= v_start) || (*start >= v_end)) return; /* Extend the range to be PUD aligned for a worst case scenario */ if (*start > v_start) *start = ALIGN_DOWN(*start, PUD_SIZE); if (*end < v_end) *end = ALIGN(*end, PUD_SIZE); } /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the * code much cleaner. pmd allocation is essential for the shared case because * pud has to be populated inside the same i_mmap_rwsem section - otherwise * racing tasks could either miss the sharing (see huge_pte_offset) or select a * bad pmd for sharing. */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; pte_t *pte; i_mmap_lock_read(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; saddr = page_table_shareable(svma, vma, addr, idx); if (saddr) { spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { get_page(virt_to_page(spte)); break; } } } if (!spte) goto out; spin_lock(&mm->page_table_lock); if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { put_page(virt_to_page(spte)); } spin_unlock(&mm->page_table_lock); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); i_mmap_unlock_read(mapping); return pte; } /* * unmap huge page backed by shared pte. * * Hugetlb pte page is ref counted at the time of mapping. If pte is shared * indicated by page_count > 1, unmap is achieved by clearing pud and * decrementing the ref count. If count == 1, the pte page is not shared. * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user */ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); BUG_ON(page_count(virt_to_page(ptep)) == 0); if (page_count(virt_to_page(ptep)) == 1) return 0; pud_clear(pud); put_page(virt_to_page(ptep)); mm_dec_nr_pmds(mm); return 1; } #else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { return NULL; } int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { return false; } #endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; } else { BUG_ON(sz != PMD_SIZE); if (want_pmd_share(vma, addr) && pud_none(*pud)) pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); } } if (pte) { pte_t pteval = ptep_get_lockless(pte); BUG_ON(pte_present(pteval) && !pte_huge(pteval)); } return pte; } /* * huge_pte_offset() - Walk the page table to resolve the hugepage * entry at address @addr * * Return: Pointer to page table entry (PUD or PMD) for * address @addr, or NULL if a !p*d_present() entry is encountered and the * size @sz doesn't match the hugepage size at this level of the page * table. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) return NULL; p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return NULL; pud = pud_offset(p4d, addr); if (sz == PUD_SIZE) /* must be pud huge, non-present or none */ return (pte_t *)pud; if (!pud_present(*pud)) return NULL; /* must have a valid entry and size to go further */ pmd = pmd_offset(pud, addr); /* must be pmd huge, non-present or none */ return (pte_t *)pmd; } /* * Return a mask that can be used to update an address to the last huge * page in a page table page mapping size. Used to skip non-present * page table entries when linearly scanning address ranges. Architectures * with unique huge page to page table relationships can define their own * version of this routine. */ unsigned long hugetlb_mask_last_page(struct hstate *h) { unsigned long hp_size = huge_page_size(h); if (hp_size == PUD_SIZE) return P4D_SIZE - PUD_SIZE; else if (hp_size == PMD_SIZE) return PUD_SIZE - PMD_SIZE; else return 0UL; } #else /* See description above. Architectures can provide their own version. */ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) { #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING if (huge_page_size(h) == PMD_SIZE) return PUD_SIZE - PMD_SIZE; #endif return 0UL; } #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ bool isolate_hugetlb(struct folio *folio, struct list_head *list) { bool ret = true; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio) || !folio_test_hugetlb_migratable(folio) || !folio_try_get(folio)) { ret = false; goto unlock; } folio_clear_hugetlb_migratable(folio); list_move_tail(&folio->lru, list); unlock: spin_unlock_irq(&hugetlb_lock); return ret; } int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { int ret = 0; *hugetlb = false; spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { *hugetlb = true; if (folio_test_hugetlb_freed(folio)) ret = 0; else if (folio_test_hugetlb_migratable(folio) || unpoison) ret = folio_try_get(folio); else ret = -EBUSY; } spin_unlock_irq(&hugetlb_lock); return ret; } int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { int ret; spin_lock_irq(&hugetlb_lock); ret = __get_huge_page_for_hwpoison(pfn, flags, migratable_cleared); spin_unlock_irq(&hugetlb_lock); return ret; } void folio_putback_active_hugetlb(struct folio *folio) { spin_lock_irq(&hugetlb_lock); folio_set_hugetlb_migratable(folio); list_move_tail(&folio->lru, &(folio_hstate(folio))->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); folio_put(folio); } void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { struct hstate *h = folio_hstate(old_folio); hugetlb_cgroup_migrate(old_folio, new_folio); set_page_owner_migrate_reason(&new_folio->page, reason); /* * transfer temporary state of the new hugetlb folio. This is * reverse to other transitions because the newpage is going to * be final while the old one will be freed so it takes over * the temporary status. * * Also note that we have to transfer the per-node surplus state * here as well otherwise the global surplus count will not match * the per-node's. */ if (folio_test_hugetlb_temporary(new_folio)) { int old_nid = folio_nid(old_folio); int new_nid = folio_nid(new_folio); folio_set_hugetlb_temporary(old_folio); folio_clear_hugetlb_temporary(new_folio); /* * There is no need to transfer the per-node surplus state * when we do not cross the node. */ if (new_nid == old_nid) return; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { h->surplus_huge_pages_node[old_nid]--; h->surplus_huge_pages_node[new_nid]++; } spin_unlock_irq(&hugetlb_lock); } } static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; if (start >= end) return; flush_cache_range(vma, start, end); /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); for (address = start; address < end; address += PUD_SIZE) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); huge_pmd_unshare(mm, vma, address, ptep); spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); } /* * This function will unconditionally remove all the shared pmd pgtable entries * within the specific vma for a hugetlbfs memory range. */ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } #ifdef CONFIG_CMA static bool cma_reserve_called __initdata; static int __init cmdline_parse_hugetlb_cma(char *p) { int nid, count = 0; unsigned long tmp; char *s = p; while (*s) { if (sscanf(s, "%lu%n", &tmp, &count) != 1) break; if (s[count] == ':') { if (tmp >= MAX_NUMNODES) break; nid = array_index_nospec(tmp, MAX_NUMNODES); s += count + 1; tmp = memparse(s, &s); hugetlb_cma_size_in_node[nid] = tmp; hugetlb_cma_size += tmp; /* * Skip the separator if have one, otherwise * break the parsing. */ if (*s == ',') s++; else break; } else { hugetlb_cma_size = memparse(p, &p); break; } } return 0; } early_param("hugetlb_cma", cmdline_parse_hugetlb_cma); void __init hugetlb_cma_reserve(int order) { unsigned long size, reserved, per_node; bool node_specific_cma_alloc = false; int nid; /* * HugeTLB CMA reservation is required for gigantic * huge pages which could not be allocated via the * page allocator. Just warn if there is any change * breaking this assumption. */ VM_WARN_ON(order <= MAX_PAGE_ORDER); cma_reserve_called = true; if (!hugetlb_cma_size) return; for (nid = 0; nid < MAX_NUMNODES; nid++) { if (hugetlb_cma_size_in_node[nid] == 0) continue; if (!node_online(nid)) { pr_warn("hugetlb_cma: invalid node %d specified\n", nid); hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; hugetlb_cma_size_in_node[nid] = 0; continue; } if (hugetlb_cma_size_in_node[nid] < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area of node %d should be at least %lu MiB\n", nid, (PAGE_SIZE << order) / SZ_1M); hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; hugetlb_cma_size_in_node[nid] = 0; } else { node_specific_cma_alloc = true; } } /* Validate the CMA size again in case some invalid nodes specified. */ if (!hugetlb_cma_size) return; if (hugetlb_cma_size < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n", (PAGE_SIZE << order) / SZ_1M); hugetlb_cma_size = 0; return; } if (!node_specific_cma_alloc) { /* * If 3 GB area is requested on a machine with 4 numa nodes, * let's allocate 1 GB on first three nodes and ignore the last one. */ per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", hugetlb_cma_size / SZ_1M, per_node / SZ_1M); } reserved = 0; for_each_online_node(nid) { int res; char name[CMA_MAX_NAME]; if (node_specific_cma_alloc) { if (hugetlb_cma_size_in_node[nid] == 0) continue; size = hugetlb_cma_size_in_node[nid]; } else { size = min(per_node, hugetlb_cma_size - reserved); } size = round_up(size, PAGE_SIZE << order); snprintf(name, sizeof(name), "hugetlb%d", nid); /* * Note that 'order per bit' is based on smallest size that * may be returned to CMA allocator in the case of * huge page demotion. */ res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order, HUGETLB_PAGE_ORDER, false, name, &hugetlb_cma[nid], nid); if (res) { pr_warn("hugetlb_cma: reservation failed: err %d, node %d", res, nid); continue; } reserved += size; pr_info("hugetlb_cma: reserved %lu MiB on node %d\n", size / SZ_1M, nid); if (reserved >= hugetlb_cma_size) break; } if (!reserved) /* * hugetlb_cma_size is used to determine if allocations from * cma are possible. Set to zero if no cma regions are set up. */ hugetlb_cma_size = 0; } static void __init hugetlb_cma_check(void) { if (!hugetlb_cma_size || cma_reserve_called) return; pr_warn("hugetlb_cma: the option isn't supported by current arch\n"); } #endif /* CONFIG_CMA */ |
| 5 5 5 5 5 5 1 1 1 6 20 6 14 6 6 6 6 6 18 13 1 13 1 13 2 1 12 12 7 4 4 8 6 2 8 2 2 2 20 2 2 7 3 1 6 5 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <net/ip.h> #include <net/tcp.h> #include <net/netlink.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_synproxy.h> #include <net/netfilter/nf_synproxy.h> #include <linux/netfilter/nf_tables.h> #include <linux/netfilter/nf_synproxy.h> struct nft_synproxy { struct nf_synproxy_info info; }; static const struct nla_policy nft_synproxy_policy[NFTA_SYNPROXY_MAX + 1] = { [NFTA_SYNPROXY_MSS] = { .type = NLA_U16 }, [NFTA_SYNPROXY_WSCALE] = { .type = NLA_U8 }, [NFTA_SYNPROXY_FLAGS] = { .type = NLA_U32 }, }; static void nft_synproxy_tcp_options(struct synproxy_options *opts, const struct tcphdr *tcp, struct synproxy_net *snet, struct nf_synproxy_info *info, const struct nft_synproxy *priv) { this_cpu_inc(snet->stats->syn_received); if (tcp->ece && tcp->cwr) opts->options |= NF_SYNPROXY_OPT_ECN; opts->options &= priv->info.options; opts->mss_encode = opts->mss_option; opts->mss_option = info->mss; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, opts); else opts->options &= ~(NF_SYNPROXY_OPT_WSCALE | NF_SYNPROXY_OPT_SACK_PERM | NF_SYNPROXY_OPT_ECN); } static void nft_synproxy_eval_v4(const struct nft_synproxy *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt, const struct tcphdr *tcp, struct tcphdr *_tcph, struct synproxy_options *opts) { struct nf_synproxy_info info = priv->info; struct net *net = nft_net(pkt); struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *skb = pkt->skb; if (tcp->syn) { /* Initial SYN from client */ nft_synproxy_tcp_options(opts, tcp, snet, &info, priv); synproxy_send_client_synack(net, skb, tcp, opts); consume_skb(skb); regs->verdict.code = NF_STOLEN; } else if (tcp->ack) { /* ACK from client */ if (synproxy_recv_client_ack(net, skb, tcp, opts, ntohl(tcp->seq))) { consume_skb(skb); regs->verdict.code = NF_STOLEN; } else { regs->verdict.code = NF_DROP; } } } #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) static void nft_synproxy_eval_v6(const struct nft_synproxy *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt, const struct tcphdr *tcp, struct tcphdr *_tcph, struct synproxy_options *opts) { struct nf_synproxy_info info = priv->info; struct net *net = nft_net(pkt); struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *skb = pkt->skb; if (tcp->syn) { /* Initial SYN from client */ nft_synproxy_tcp_options(opts, tcp, snet, &info, priv); synproxy_send_client_synack_ipv6(net, skb, tcp, opts); consume_skb(skb); regs->verdict.code = NF_STOLEN; } else if (tcp->ack) { /* ACK from client */ if (synproxy_recv_client_ack_ipv6(net, skb, tcp, opts, ntohl(tcp->seq))) { consume_skb(skb); regs->verdict.code = NF_STOLEN; } else { regs->verdict.code = NF_DROP; } } } #endif /* CONFIG_NF_TABLES_IPV6*/ static void nft_synproxy_do_eval(const struct nft_synproxy *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct synproxy_options opts = {}; struct sk_buff *skb = pkt->skb; int thoff = nft_thoff(pkt); const struct tcphdr *tcp; struct tcphdr _tcph; if (pkt->tprot != IPPROTO_TCP) { regs->verdict.code = NFT_BREAK; return; } if (nf_ip_checksum(skb, nft_hook(pkt), thoff, IPPROTO_TCP)) { regs->verdict.code = NF_DROP; return; } tcp = skb_header_pointer(skb, thoff, sizeof(struct tcphdr), &_tcph); if (!tcp) { regs->verdict.code = NF_DROP; return; } if (!synproxy_parse_options(skb, thoff, tcp, &opts)) { regs->verdict.code = NF_DROP; return; } switch (skb->protocol) { case htons(ETH_P_IP): nft_synproxy_eval_v4(priv, regs, pkt, tcp, &_tcph, &opts); return; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case htons(ETH_P_IPV6): nft_synproxy_eval_v6(priv, regs, pkt, tcp, &_tcph, &opts); return; #endif } regs->verdict.code = NFT_BREAK; } static int nft_synproxy_do_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_synproxy *priv) { struct synproxy_net *snet = synproxy_pernet(ctx->net); u32 flags; int err; if (tb[NFTA_SYNPROXY_MSS]) priv->info.mss = ntohs(nla_get_be16(tb[NFTA_SYNPROXY_MSS])); if (tb[NFTA_SYNPROXY_WSCALE]) priv->info.wscale = nla_get_u8(tb[NFTA_SYNPROXY_WSCALE]); if (tb[NFTA_SYNPROXY_FLAGS]) { flags = ntohl(nla_get_be32(tb[NFTA_SYNPROXY_FLAGS])); if (flags & ~NF_SYNPROXY_OPT_MASK) return -EOPNOTSUPP; priv->info.options = flags; } err = nf_ct_netns_get(ctx->net, ctx->family); if (err) return err; switch (ctx->family) { case NFPROTO_IPV4: err = nf_synproxy_ipv4_init(snet, ctx->net); if (err) goto nf_ct_failure; break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: err = nf_synproxy_ipv6_init(snet, ctx->net); if (err) goto nf_ct_failure; break; #endif case NFPROTO_INET: err = nf_synproxy_ipv4_init(snet, ctx->net); if (err) goto nf_ct_failure; err = nf_synproxy_ipv6_init(snet, ctx->net); if (err) { nf_synproxy_ipv4_fini(snet, ctx->net); goto nf_ct_failure; } break; } return 0; nf_ct_failure: nf_ct_netns_put(ctx->net, ctx->family); return err; } static void nft_synproxy_do_destroy(const struct nft_ctx *ctx) { struct synproxy_net *snet = synproxy_pernet(ctx->net); switch (ctx->family) { case NFPROTO_IPV4: nf_synproxy_ipv4_fini(snet, ctx->net); break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: nf_synproxy_ipv6_fini(snet, ctx->net); break; #endif case NFPROTO_INET: nf_synproxy_ipv4_fini(snet, ctx->net); nf_synproxy_ipv6_fini(snet, ctx->net); break; } nf_ct_netns_put(ctx->net, ctx->family); } static int nft_synproxy_do_dump(struct sk_buff *skb, struct nft_synproxy *priv) { if (nla_put_be16(skb, NFTA_SYNPROXY_MSS, htons(priv->info.mss)) || nla_put_u8(skb, NFTA_SYNPROXY_WSCALE, priv->info.wscale) || nla_put_be32(skb, NFTA_SYNPROXY_FLAGS, htonl(priv->info.options))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static void nft_synproxy_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_synproxy *priv = nft_expr_priv(expr); nft_synproxy_do_eval(priv, regs, pkt); } static int nft_synproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET) return -EOPNOTSUPP; return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD)); } static int nft_synproxy_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_synproxy *priv = nft_expr_priv(expr); return nft_synproxy_do_init(ctx, tb, priv); } static void nft_synproxy_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nft_synproxy_do_destroy(ctx); } static int nft_synproxy_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_synproxy *priv = nft_expr_priv(expr); return nft_synproxy_do_dump(skb, priv); } static struct nft_expr_type nft_synproxy_type; static const struct nft_expr_ops nft_synproxy_ops = { .eval = nft_synproxy_eval, .size = NFT_EXPR_SIZE(sizeof(struct nft_synproxy)), .init = nft_synproxy_init, .destroy = nft_synproxy_destroy, .dump = nft_synproxy_dump, .type = &nft_synproxy_type, .validate = nft_synproxy_validate, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_synproxy_type __read_mostly = { .ops = &nft_synproxy_ops, .name = "synproxy", .owner = THIS_MODULE, .policy = nft_synproxy_policy, .maxattr = NFTA_SYNPROXY_MAX, }; static int nft_synproxy_obj_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_object *obj) { struct nft_synproxy *priv = nft_obj_data(obj); return nft_synproxy_do_init(ctx, tb, priv); } static void nft_synproxy_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { nft_synproxy_do_destroy(ctx); } static int nft_synproxy_obj_dump(struct sk_buff *skb, struct nft_object *obj, bool reset) { struct nft_synproxy *priv = nft_obj_data(obj); return nft_synproxy_do_dump(skb, priv); } static void nft_synproxy_obj_eval(struct nft_object *obj, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_synproxy *priv = nft_obj_data(obj); nft_synproxy_do_eval(priv, regs, pkt); } static void nft_synproxy_obj_update(struct nft_object *obj, struct nft_object *newobj) { struct nft_synproxy *newpriv = nft_obj_data(newobj); struct nft_synproxy *priv = nft_obj_data(obj); priv->info = newpriv->info; } static struct nft_object_type nft_synproxy_obj_type; static const struct nft_object_ops nft_synproxy_obj_ops = { .type = &nft_synproxy_obj_type, .size = sizeof(struct nft_synproxy), .init = nft_synproxy_obj_init, .destroy = nft_synproxy_obj_destroy, .dump = nft_synproxy_obj_dump, .eval = nft_synproxy_obj_eval, .update = nft_synproxy_obj_update, }; static struct nft_object_type nft_synproxy_obj_type __read_mostly = { .type = NFT_OBJECT_SYNPROXY, .ops = &nft_synproxy_obj_ops, .maxattr = NFTA_SYNPROXY_MAX, .policy = nft_synproxy_policy, .owner = THIS_MODULE, }; static int __init nft_synproxy_module_init(void) { int err; err = nft_register_obj(&nft_synproxy_obj_type); if (err < 0) return err; err = nft_register_expr(&nft_synproxy_type); if (err < 0) goto err; return 0; err: nft_unregister_obj(&nft_synproxy_obj_type); return err; } static void __exit nft_synproxy_module_exit(void) { nft_unregister_expr(&nft_synproxy_type); nft_unregister_obj(&nft_synproxy_obj_type); } module_init(nft_synproxy_module_init); module_exit(nft_synproxy_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Fernando Fernandez <ffmancera@riseup.net>"); MODULE_ALIAS_NFT_EXPR("synproxy"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_SYNPROXY); MODULE_DESCRIPTION("nftables SYNPROXY expression support"); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Copyright (C) 1996 Mike Shaver (shaver@zeroknowledge.com) */ #include <linux/mm.h> #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/spinlock.h> #include <net/ax25.h> static int min_ipdefmode[1], max_ipdefmode[] = {1}; static int min_axdefmode[1], max_axdefmode[] = {1}; static int min_backoff[1], max_backoff[] = {2}; static int min_conmode[1], max_conmode[] = {2}; static int min_window[] = {1}, max_window[] = {7}; static int min_ewindow[] = {1}, max_ewindow[] = {63}; static int min_t1[] = {1}, max_t1[] = {30000}; static int min_t2[] = {1}, max_t2[] = {20000}; static int min_t3[1], max_t3[] = {3600000}; static int min_idle[1], max_idle[] = {65535000}; static int min_n2[] = {1}, max_n2[] = {31}; static int min_paclen[] = {1}, max_paclen[] = {512}; static int min_proto[1], max_proto[] = { AX25_PROTO_MAX }; #ifdef CONFIG_AX25_DAMA_SLAVE static int min_ds_timeout[1], max_ds_timeout[] = {65535000}; #endif static const struct ctl_table ax25_param_table[] = { { .procname = "ip_default_mode", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_ipdefmode, .extra2 = &max_ipdefmode }, { .procname = "ax25_default_mode", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_axdefmode, .extra2 = &max_axdefmode }, { .procname = "backoff_type", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_backoff, .extra2 = &max_backoff }, { .procname = "connect_mode", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_conmode, .extra2 = &max_conmode }, { .procname = "standard_window_size", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_window, .extra2 = &max_window }, { .procname = "extended_window_size", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_ewindow, .extra2 = &max_ewindow }, { .procname = "t1_timeout", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_t1, .extra2 = &max_t1 }, { .procname = "t2_timeout", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_t2, .extra2 = &max_t2 }, { .procname = "t3_timeout", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_t3, .extra2 = &max_t3 }, { .procname = "idle_timeout", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_idle, .extra2 = &max_idle }, { .procname = "maximum_retry_count", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_n2, .extra2 = &max_n2 }, { .procname = "maximum_packet_length", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_paclen, .extra2 = &max_paclen }, { .procname = "protocol", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_proto, .extra2 = &max_proto }, #ifdef CONFIG_AX25_DAMA_SLAVE { .procname = "dama_slave_timeout", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_ds_timeout, .extra2 = &max_ds_timeout }, #endif }; int ax25_register_dev_sysctl(ax25_dev *ax25_dev) { char path[sizeof("net/ax25/") + IFNAMSIZ]; int k; struct ctl_table *table; table = kmemdup(ax25_param_table, sizeof(ax25_param_table), GFP_KERNEL); if (!table) return -ENOMEM; BUILD_BUG_ON(ARRAY_SIZE(ax25_param_table) != AX25_MAX_VALUES); for (k = 0; k < AX25_MAX_VALUES; k++) table[k].data = &ax25_dev->values[k]; snprintf(path, sizeof(path), "net/ax25/%s", ax25_dev->dev->name); ax25_dev->sysheader = register_net_sysctl_sz(&init_net, path, table, ARRAY_SIZE(ax25_param_table)); if (!ax25_dev->sysheader) { kfree(table); return -ENOMEM; } return 0; } void ax25_unregister_dev_sysctl(ax25_dev *ax25_dev) { struct ctl_table_header *header = ax25_dev->sysheader; const struct ctl_table *table; if (header) { ax25_dev->sysheader = NULL; table = header->ctl_table_arg; unregister_net_sysctl_table(header); kfree(table); } } |
| 216 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 | // SPDX-License-Identifier: GPL-2.0 /* * This is a maximally equidistributed combined Tausworthe generator * based on code from GNU Scientific Library 1.5 (30 Jun 2004) * * lfsr113 version: * * x_n = (s1_n ^ s2_n ^ s3_n ^ s4_n) * * s1_{n+1} = (((s1_n & 4294967294) << 18) ^ (((s1_n << 6) ^ s1_n) >> 13)) * s2_{n+1} = (((s2_n & 4294967288) << 2) ^ (((s2_n << 2) ^ s2_n) >> 27)) * s3_{n+1} = (((s3_n & 4294967280) << 7) ^ (((s3_n << 13) ^ s3_n) >> 21)) * s4_{n+1} = (((s4_n & 4294967168) << 13) ^ (((s4_n << 3) ^ s4_n) >> 12)) * * The period of this generator is about 2^113 (see erratum paper). * * From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe * Generators", Mathematics of Computation, 65, 213 (1996), 203--213: * http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps * ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps * * There is an erratum in the paper "Tables of Maximally Equidistributed * Combined LFSR Generators", Mathematics of Computation, 68, 225 (1999), * 261--269: http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps * * ... the k_j most significant bits of z_j must be non-zero, * for each j. (Note: this restriction also applies to the * computer code given in [4], but was mistakenly not mentioned * in that paper.) * * This affects the seeding procedure by imposing the requirement * s1 > 1, s2 > 7, s3 > 15, s4 > 127. */ #include <linux/types.h> #include <linux/percpu.h> #include <linux/export.h> #include <linux/jiffies.h> #include <linux/random.h> #include <linux/sched.h> #include <linux/bitops.h> #include <linux/slab.h> #include <linux/unaligned.h> /** * prandom_u32_state - seeded pseudo-random number generator. * @state: pointer to state structure holding seeded state. * * This is used for pseudo-randomness with no outside seeding. * For more random results, use get_random_u32(). */ u32 prandom_u32_state(struct rnd_state *state) { #define TAUSWORTHE(s, a, b, c, d) ((s & c) << d) ^ (((s << a) ^ s) >> b) state->s1 = TAUSWORTHE(state->s1, 6U, 13U, 4294967294U, 18U); state->s2 = TAUSWORTHE(state->s2, 2U, 27U, 4294967288U, 2U); state->s3 = TAUSWORTHE(state->s3, 13U, 21U, 4294967280U, 7U); state->s4 = TAUSWORTHE(state->s4, 3U, 12U, 4294967168U, 13U); return (state->s1 ^ state->s2 ^ state->s3 ^ state->s4); } EXPORT_SYMBOL(prandom_u32_state); /** * prandom_bytes_state - get the requested number of pseudo-random bytes * * @state: pointer to state structure holding seeded state. * @buf: where to copy the pseudo-random bytes to * @bytes: the requested number of bytes * * This is used for pseudo-randomness with no outside seeding. * For more random results, use get_random_bytes(). */ void prandom_bytes_state(struct rnd_state *state, void *buf, size_t bytes) { u8 *ptr = buf; while (bytes >= sizeof(u32)) { put_unaligned(prandom_u32_state(state), (u32 *) ptr); ptr += sizeof(u32); bytes -= sizeof(u32); } if (bytes > 0) { u32 rem = prandom_u32_state(state); do { *ptr++ = (u8) rem; bytes--; rem >>= BITS_PER_BYTE; } while (bytes > 0); } } EXPORT_SYMBOL(prandom_bytes_state); static void prandom_warmup(struct rnd_state *state) { /* Calling RNG ten times to satisfy recurrence condition */ prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); } void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state) { int i; for_each_possible_cpu(i) { struct rnd_state *state = per_cpu_ptr(pcpu_state, i); u32 seeds[4]; get_random_bytes(&seeds, sizeof(seeds)); state->s1 = __seed(seeds[0], 2U); state->s2 = __seed(seeds[1], 8U); state->s3 = __seed(seeds[2], 16U); state->s4 = __seed(seeds[3], 128U); prandom_warmup(state); } } EXPORT_SYMBOL(prandom_seed_full_state); #ifdef CONFIG_RANDOM32_SELFTEST static struct prandom_test1 { u32 seed; u32 result; } test1[] = { { 1U, 3484351685U }, { 2U, 2623130059U }, { 3U, 3125133893U }, { 4U, 984847254U }, }; static struct prandom_test2 { u32 seed; u32 iteration; u32 result; } test2[] = { /* Test cases against taus113 from GSL library. */ { 931557656U, 959U, 2975593782U }, { 1339693295U, 876U, 3887776532U }, { 1545556285U, 961U, 1615538833U }, { 601730776U, 723U, 1776162651U }, { 1027516047U, 687U, 511983079U }, { 416526298U, 700U, 916156552U }, { 1395522032U, 652U, 2222063676U }, { 366221443U, 617U, 2992857763U }, { 1539836965U, 714U, 3783265725U }, { 556206671U, 994U, 799626459U }, { 684907218U, 799U, 367789491U }, { 2121230701U, 931U, 2115467001U }, { 1668516451U, 644U, 3620590685U }, { 768046066U, 883U, 2034077390U }, { 1989159136U, 833U, 1195767305U }, { 536585145U, 996U, 3577259204U }, { 1008129373U, 642U, 1478080776U }, { 1740775604U, 939U, 1264980372U }, { 1967883163U, 508U, 10734624U }, { 1923019697U, 730U, 3821419629U }, { 442079932U, 560U, 3440032343U }, { 1961302714U, 845U, 841962572U }, { 2030205964U, 962U, 1325144227U }, { 1160407529U, 507U, 240940858U }, { 635482502U, 779U, 4200489746U }, { 1252788931U, 699U, 867195434U }, { 1961817131U, 719U, 668237657U }, { 1071468216U, 983U, 917876630U }, { 1281848367U, 932U, 1003100039U }, { 582537119U, 780U, 1127273778U }, { 1973672777U, 853U, 1071368872U }, { 1896756996U, 762U, 1127851055U }, { 847917054U, 500U, 1717499075U }, { 1240520510U, 951U, 2849576657U }, { 1685071682U, 567U, 1961810396U }, { 1516232129U, 557U, 3173877U }, { 1208118903U, 612U, 1613145022U }, { 1817269927U, 693U, 4279122573U }, { 1510091701U, 717U, 638191229U }, { 365916850U, 807U, 600424314U }, { 399324359U, 702U, 1803598116U }, { 1318480274U, 779U, 2074237022U }, { 697758115U, 840U, 1483639402U }, { 1696507773U, 840U, 577415447U }, { 2081979121U, 981U, 3041486449U }, { 955646687U, 742U, 3846494357U }, { 1250683506U, 749U, 836419859U }, { 595003102U, 534U, 366794109U }, { 47485338U, 558U, 3521120834U }, { 619433479U, 610U, 3991783875U }, { 704096520U, 518U, 4139493852U }, { 1712224984U, 606U, 2393312003U }, { 1318233152U, 922U, 3880361134U }, { 855572992U, 761U, 1472974787U }, { 64721421U, 703U, 683860550U }, { 678931758U, 840U, 380616043U }, { 692711973U, 778U, 1382361947U }, { 677703619U, 530U, 2826914161U }, { 92393223U, 586U, 1522128471U }, { 1222592920U, 743U, 3466726667U }, { 358288986U, 695U, 1091956998U }, { 1935056945U, 958U, 514864477U }, { 735675993U, 990U, 1294239989U }, { 1560089402U, 897U, 2238551287U }, { 70616361U, 829U, 22483098U }, { 368234700U, 731U, 2913875084U }, { 20221190U, 879U, 1564152970U }, { 539444654U, 682U, 1835141259U }, { 1314987297U, 840U, 1801114136U }, { 2019295544U, 645U, 3286438930U }, { 469023838U, 716U, 1637918202U }, { 1843754496U, 653U, 2562092152U }, { 400672036U, 809U, 4264212785U }, { 404722249U, 965U, 2704116999U }, { 600702209U, 758U, 584979986U }, { 519953954U, 667U, 2574436237U }, { 1658071126U, 694U, 2214569490U }, { 420480037U, 749U, 3430010866U }, { 690103647U, 969U, 3700758083U }, { 1029424799U, 937U, 3787746841U }, { 2012608669U, 506U, 3362628973U }, { 1535432887U, 998U, 42610943U }, { 1330635533U, 857U, 3040806504U }, { 1223800550U, 539U, 3954229517U }, { 1322411537U, 680U, 3223250324U }, { 1877847898U, 945U, 2915147143U }, { 1646356099U, 874U, 965988280U }, { 805687536U, 744U, 4032277920U }, { 1948093210U, 633U, 1346597684U }, { 392609744U, 783U, 1636083295U }, { 690241304U, 770U, 1201031298U }, { 1360302965U, 696U, 1665394461U }, { 1220090946U, 780U, 1316922812U }, { 447092251U, 500U, 3438743375U }, { 1613868791U, 592U, 828546883U }, { 523430951U, 548U, 2552392304U }, { 726692899U, 810U, 1656872867U }, { 1364340021U, 836U, 3710513486U }, { 1986257729U, 931U, 935013962U }, { 407983964U, 921U, 728767059U }, }; static void prandom_state_selftest_seed(struct rnd_state *state, u32 seed) { #define LCG(x) ((x) * 69069U) /* super-duper LCG */ state->s1 = __seed(LCG(seed), 2U); state->s2 = __seed(LCG(state->s1), 8U); state->s3 = __seed(LCG(state->s2), 16U); state->s4 = __seed(LCG(state->s3), 128U); } static int __init prandom_state_selftest(void) { int i, j, errors = 0, runs = 0; bool error = false; for (i = 0; i < ARRAY_SIZE(test1); i++) { struct rnd_state state; prandom_state_selftest_seed(&state, test1[i].seed); prandom_warmup(&state); if (test1[i].result != prandom_u32_state(&state)) error = true; } if (error) pr_warn("prandom: seed boundary self test failed\n"); else pr_info("prandom: seed boundary self test passed\n"); for (i = 0; i < ARRAY_SIZE(test2); i++) { struct rnd_state state; prandom_state_selftest_seed(&state, test2[i].seed); prandom_warmup(&state); for (j = 0; j < test2[i].iteration - 1; j++) prandom_u32_state(&state); if (test2[i].result != prandom_u32_state(&state)) errors++; runs++; cond_resched(); } if (errors) pr_warn("prandom: %d/%d self tests failed\n", errors, runs); else pr_info("prandom: %d self tests passed\n", runs); return 0; } core_initcall(prandom_state_selftest); #endif |
| 15 11 4 14 10 10 1 10 1 10 10 1 10 1 10 1 10 2 15 28 3 28 4 28 3 39 28 37 16 21 1 31 4 2 29 1 1 28 1 1 1 1 1 1 30 39 26 26 8 26 14 1 14 7 26 14 123 123 123 83 123 3 3 2 80 50 30 1 1 1 69 69 16 53 16 122 16 13 13 2 3 39 39 39 39 39 39 43 39 43 2 3 5 3 3 2 3 3 1 1 1 3 3 1 1 2 3 3 13 13 1 12 11 11 1 10 10 10 10 3 3 3 3 3 1 2 2 3 1 2 2 3 79 80 79 78 78 78 64 63 29 34 78 63 63 12 12 12 12 12 5 5 2 5 5 5 5 5 5 5 2 1 2 2 2 2 2 2 2 2 2 2 2 1 1 1 2 2 2 2 1 2 2 2 2 2 23 11 23 12 3 3 11 1 11 11 11 6 4 13 13 6 8 13 1 12 3 12 8 12 2 12 7 12 6 1 6 1 12 9 12 7 12 11 7 4 3 4 3 11 13 41 28 41 40 27 27 25 41 41 41 1 1 1 1 1 1 1 1 1 1 1 2 3 1 2 2 2 2 1 2 2 1 2 1 2 3 1 2 2 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This file contains vfs inode ops for the 9P2000 protocol. * * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/namei.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/posix_acl.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include "v9fs.h" #include "v9fs_vfs.h" #include "fid.h" #include "cache.h" #include "xattr.h" #include "acl.h" static const struct inode_operations v9fs_dir_inode_operations; static const struct inode_operations v9fs_dir_inode_operations_dotu; static const struct inode_operations v9fs_file_inode_operations; static const struct inode_operations v9fs_symlink_inode_operations; /** * unixmode2p9mode - convert unix mode bits to plan 9 * @v9ses: v9fs session information * @mode: mode to convert * */ static u32 unixmode2p9mode(struct v9fs_session_info *v9ses, umode_t mode) { int res; res = mode & 0777; if (S_ISDIR(mode)) res |= P9_DMDIR; if (v9fs_proto_dotu(v9ses)) { if (v9ses->nodev == 0) { if (S_ISSOCK(mode)) res |= P9_DMSOCKET; if (S_ISFIFO(mode)) res |= P9_DMNAMEDPIPE; if (S_ISBLK(mode)) res |= P9_DMDEVICE; if (S_ISCHR(mode)) res |= P9_DMDEVICE; } if ((mode & S_ISUID) == S_ISUID) res |= P9_DMSETUID; if ((mode & S_ISGID) == S_ISGID) res |= P9_DMSETGID; if ((mode & S_ISVTX) == S_ISVTX) res |= P9_DMSETVTX; } return res; } /** * p9mode2perm- convert plan9 mode bits to unix permission bits * @v9ses: v9fs session information * @stat: p9_wstat from which mode need to be derived * */ static int p9mode2perm(struct v9fs_session_info *v9ses, struct p9_wstat *stat) { int res; int mode = stat->mode; res = mode & 0777; /* S_IRWXUGO */ if (v9fs_proto_dotu(v9ses)) { if ((mode & P9_DMSETUID) == P9_DMSETUID) res |= S_ISUID; if ((mode & P9_DMSETGID) == P9_DMSETGID) res |= S_ISGID; if ((mode & P9_DMSETVTX) == P9_DMSETVTX) res |= S_ISVTX; } return res; } /** * p9mode2unixmode- convert plan9 mode bits to unix mode bits * @v9ses: v9fs session information * @stat: p9_wstat from which mode need to be derived * @rdev: major number, minor number in case of device files. * */ static umode_t p9mode2unixmode(struct v9fs_session_info *v9ses, struct p9_wstat *stat, dev_t *rdev) { int res, r; u32 mode = stat->mode; *rdev = 0; res = p9mode2perm(v9ses, stat); if ((mode & P9_DMDIR) == P9_DMDIR) res |= S_IFDIR; else if ((mode & P9_DMSYMLINK) && (v9fs_proto_dotu(v9ses))) res |= S_IFLNK; else if ((mode & P9_DMSOCKET) && (v9fs_proto_dotu(v9ses)) && (v9ses->nodev == 0)) res |= S_IFSOCK; else if ((mode & P9_DMNAMEDPIPE) && (v9fs_proto_dotu(v9ses)) && (v9ses->nodev == 0)) res |= S_IFIFO; else if ((mode & P9_DMDEVICE) && (v9fs_proto_dotu(v9ses)) && (v9ses->nodev == 0)) { char type = 0; int major = -1, minor = -1; r = sscanf(stat->extension, "%c %i %i", &type, &major, &minor); if (r != 3) { p9_debug(P9_DEBUG_ERROR, "invalid device string, umode will be bogus: %s\n", stat->extension); return res; } switch (type) { case 'c': res |= S_IFCHR; break; case 'b': res |= S_IFBLK; break; default: p9_debug(P9_DEBUG_ERROR, "Unknown special type %c %s\n", type, stat->extension); } *rdev = MKDEV(major, minor); } else res |= S_IFREG; return res; } /** * v9fs_uflags2omode- convert posix open flags to plan 9 mode bits * @uflags: flags to convert * @extended: if .u extensions are active */ int v9fs_uflags2omode(int uflags, int extended) { int ret; switch (uflags&3) { default: case O_RDONLY: ret = P9_OREAD; break; case O_WRONLY: ret = P9_OWRITE; break; case O_RDWR: ret = P9_ORDWR; break; } if (uflags & O_TRUNC) ret |= P9_OTRUNC; if (extended) { if (uflags & O_EXCL) ret |= P9_OEXCL; if (uflags & O_APPEND) ret |= P9_OAPPEND; } return ret; } /** * v9fs_blank_wstat - helper function to setup a 9P stat structure * @wstat: structure to initialize * */ void v9fs_blank_wstat(struct p9_wstat *wstat) { wstat->type = ~0; wstat->dev = ~0; wstat->qid.type = ~0; wstat->qid.version = ~0; *((long long *)&wstat->qid.path) = ~0; wstat->mode = ~0; wstat->atime = ~0; wstat->mtime = ~0; wstat->length = ~0; wstat->name = NULL; wstat->uid = NULL; wstat->gid = NULL; wstat->muid = NULL; wstat->n_uid = INVALID_UID; wstat->n_gid = INVALID_GID; wstat->n_muid = INVALID_UID; wstat->extension = NULL; } /** * v9fs_alloc_inode - helper function to allocate an inode * @sb: The superblock to allocate the inode from */ struct inode *v9fs_alloc_inode(struct super_block *sb) { struct v9fs_inode *v9inode; v9inode = alloc_inode_sb(sb, v9fs_inode_cache, GFP_KERNEL); if (!v9inode) return NULL; v9inode->cache_validity = 0; mutex_init(&v9inode->v_mutex); return &v9inode->netfs.inode; } /** * v9fs_free_inode - destroy an inode * @inode: The inode to be freed */ void v9fs_free_inode(struct inode *inode) { kmem_cache_free(v9fs_inode_cache, V9FS_I(inode)); } /* * Set parameters for the netfs library */ void v9fs_set_netfs_context(struct inode *inode) { struct v9fs_inode *v9inode = V9FS_I(inode); netfs_inode_init(&v9inode->netfs, &v9fs_req_ops, true); } int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t rdev) { int err = 0; inode_init_owner(&nop_mnt_idmap, inode, NULL, mode); inode->i_blocks = 0; inode->i_rdev = rdev; simple_inode_init_ts(inode); inode->i_mapping->a_ops = &v9fs_addr_operations; inode->i_private = NULL; switch (mode & S_IFMT) { case S_IFIFO: case S_IFBLK: case S_IFCHR: case S_IFSOCK: if (v9fs_proto_dotl(v9ses)) { inode->i_op = &v9fs_file_inode_operations_dotl; } else if (v9fs_proto_dotu(v9ses)) { inode->i_op = &v9fs_file_inode_operations; } else { p9_debug(P9_DEBUG_ERROR, "special files without extended mode\n"); err = -EINVAL; goto error; } init_special_inode(inode, inode->i_mode, inode->i_rdev); break; case S_IFREG: if (v9fs_proto_dotl(v9ses)) { inode->i_op = &v9fs_file_inode_operations_dotl; inode->i_fop = &v9fs_file_operations_dotl; } else { inode->i_op = &v9fs_file_inode_operations; inode->i_fop = &v9fs_file_operations; } break; case S_IFLNK: if (!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses)) { p9_debug(P9_DEBUG_ERROR, "extended modes used with legacy protocol\n"); err = -EINVAL; goto error; } if (v9fs_proto_dotl(v9ses)) inode->i_op = &v9fs_symlink_inode_operations_dotl; else inode->i_op = &v9fs_symlink_inode_operations; break; case S_IFDIR: inc_nlink(inode); if (v9fs_proto_dotl(v9ses)) inode->i_op = &v9fs_dir_inode_operations_dotl; else if (v9fs_proto_dotu(v9ses)) inode->i_op = &v9fs_dir_inode_operations_dotu; else inode->i_op = &v9fs_dir_inode_operations; if (v9fs_proto_dotl(v9ses)) inode->i_fop = &v9fs_dir_operations_dotl; else inode->i_fop = &v9fs_dir_operations; break; default: p9_debug(P9_DEBUG_ERROR, "BAD mode 0x%hx S_IFMT 0x%x\n", mode, mode & S_IFMT); err = -EINVAL; goto error; } error: return err; } /** * v9fs_evict_inode - Remove an inode from the inode cache * @inode: inode to release * */ void v9fs_evict_inode(struct inode *inode) { struct v9fs_inode __maybe_unused *v9inode = V9FS_I(inode); __le32 __maybe_unused version; if (!is_bad_inode(inode)) { netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); version = cpu_to_le32(v9inode->qid.version); netfs_clear_inode_writeback(inode, &version); clear_inode(inode); filemap_fdatawrite(&inode->i_data); #ifdef CONFIG_9P_FSCACHE if (v9fs_inode_cookie(v9inode)) fscache_relinquish_cookie(v9fs_inode_cookie(v9inode), false); #endif } else clear_inode(inode); } static int v9fs_test_inode(struct inode *inode, void *data) { int umode; dev_t rdev; struct v9fs_inode *v9inode = V9FS_I(inode); struct p9_wstat *st = (struct p9_wstat *)data; struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); umode = p9mode2unixmode(v9ses, st, &rdev); /* don't match inode of different type */ if (inode_wrong_type(inode, umode)) return 0; /* compare qid details */ if (memcmp(&v9inode->qid.version, &st->qid.version, sizeof(v9inode->qid.version))) return 0; if (v9inode->qid.type != st->qid.type) return 0; if (v9inode->qid.path != st->qid.path) return 0; return 1; } static int v9fs_test_new_inode(struct inode *inode, void *data) { return 0; } static int v9fs_set_inode(struct inode *inode, void *data) { struct v9fs_inode *v9inode = V9FS_I(inode); struct p9_wstat *st = (struct p9_wstat *)data; memcpy(&v9inode->qid, &st->qid, sizeof(st->qid)); return 0; } static struct inode *v9fs_qid_iget(struct super_block *sb, struct p9_qid *qid, struct p9_wstat *st, int new) { dev_t rdev; int retval; umode_t umode; struct inode *inode; struct v9fs_session_info *v9ses = sb->s_fs_info; int (*test)(struct inode *inode, void *data); if (new) test = v9fs_test_new_inode; else test = v9fs_test_inode; inode = iget5_locked(sb, QID2INO(qid), test, v9fs_set_inode, st); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; /* * initialize the inode with the stat info * FIXME!! we may need support for stale inodes * later. */ inode->i_ino = QID2INO(qid); umode = p9mode2unixmode(v9ses, st, &rdev); retval = v9fs_init_inode(v9ses, inode, umode, rdev); if (retval) goto error; v9fs_stat2inode(st, inode, sb, 0); v9fs_set_netfs_context(inode); v9fs_cache_inode_get_cookie(inode); unlock_new_inode(inode); return inode; error: iget_failed(inode); return ERR_PTR(retval); } struct inode * v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid, struct super_block *sb, int new) { struct p9_wstat *st; struct inode *inode = NULL; st = p9_client_stat(fid); if (IS_ERR(st)) return ERR_CAST(st); inode = v9fs_qid_iget(sb, &st->qid, st, new); p9stat_free(st); kfree(st); return inode; } /** * v9fs_at_to_dotl_flags- convert Linux specific AT flags to * plan 9 AT flag. * @flags: flags to convert */ static int v9fs_at_to_dotl_flags(int flags) { int rflags = 0; if (flags & AT_REMOVEDIR) rflags |= P9_DOTL_AT_REMOVEDIR; return rflags; } /** * v9fs_dec_count - helper functon to drop i_nlink. * * If a directory had nlink <= 2 (including . and ..), then we should not drop * the link count, which indicates the underlying exported fs doesn't maintain * nlink accurately. e.g. * - overlayfs sets nlink to 1 for merged dir * - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more * than EXT4_LINK_MAX (65000) links. * * @inode: inode whose nlink is being dropped */ static void v9fs_dec_count(struct inode *inode) { if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2) drop_nlink(inode); } /** * v9fs_remove - helper function to remove files and directories * @dir: directory inode that is being deleted * @dentry: dentry that is being deleted * @flags: removing a directory * */ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags) { struct inode *inode; int retval = -EOPNOTSUPP; struct p9_fid *v9fid, *dfid; struct v9fs_session_info *v9ses; p9_debug(P9_DEBUG_VFS, "inode: %p dentry: %p rmdir: %x\n", dir, dentry, flags); v9ses = v9fs_inode2v9ses(dir); inode = d_inode(dentry); dfid = v9fs_parent_fid(dentry); if (IS_ERR(dfid)) { retval = PTR_ERR(dfid); p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", retval); return retval; } if (v9fs_proto_dotl(v9ses)) retval = p9_client_unlinkat(dfid, dentry->d_name.name, v9fs_at_to_dotl_flags(flags)); p9_fid_put(dfid); if (retval == -EOPNOTSUPP) { /* Try the one based on path */ v9fid = v9fs_fid_clone(dentry); if (IS_ERR(v9fid)) return PTR_ERR(v9fid); retval = p9_client_remove(v9fid); } if (!retval) { /* * directories on unlink should have zero * link count */ if (flags & AT_REMOVEDIR) { clear_nlink(inode); v9fs_dec_count(dir); } else v9fs_dec_count(inode); v9fs_invalidate_inode_attr(inode); v9fs_invalidate_inode_attr(dir); /* invalidate all fids associated with dentry */ /* NOTE: This will not include open fids */ dentry->d_op->d_release(dentry); } return retval; } /** * v9fs_create - Create a file * @v9ses: session information * @dir: directory that dentry is being created in * @dentry: dentry that is being created * @extension: 9p2000.u extension string to support devices, etc. * @perm: create permissions * @mode: open mode * */ static struct p9_fid * v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir, struct dentry *dentry, char *extension, u32 perm, u8 mode) { int err; const unsigned char *name; struct p9_fid *dfid, *ofid = NULL, *fid = NULL; struct inode *inode; p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry); name = dentry->d_name.name; dfid = v9fs_parent_fid(dentry); if (IS_ERR(dfid)) { err = PTR_ERR(dfid); p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err); return ERR_PTR(err); } /* clone a fid to use for creation */ ofid = clone_fid(dfid); if (IS_ERR(ofid)) { err = PTR_ERR(ofid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); goto error; } err = p9_client_fcreate(ofid, name, perm, mode, extension); if (err < 0) { p9_debug(P9_DEBUG_VFS, "p9_client_fcreate failed %d\n", err); goto error; } if (!(perm & P9_DMLINK)) { /* now walk from the parent so we can get unopened fid */ fid = p9_client_walk(dfid, 1, &name, 1); if (IS_ERR(fid)) { err = PTR_ERR(fid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); goto error; } /* * instantiate inode and assign the unopened fid to the dentry */ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err); goto error; } v9fs_fid_add(dentry, &fid); d_instantiate(dentry, inode); } p9_fid_put(dfid); return ofid; error: p9_fid_put(dfid); p9_fid_put(ofid); p9_fid_put(fid); return ERR_PTR(err); } /** * v9fs_vfs_create - VFS hook to create a regular file * @idmap: idmap of the mount * @dir: The parent directory * @dentry: The name of file to be created * @mode: The UNIX file mode to set * @excl: True if the file must not yet exist * * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open(). This is only called * for mknod(2). * */ static int v9fs_vfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); u32 perm = unixmode2p9mode(v9ses, mode); struct p9_fid *fid; /* P9_OEXCL? */ fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_ORDWR); if (IS_ERR(fid)) return PTR_ERR(fid); v9fs_invalidate_inode_attr(dir); p9_fid_put(fid); return 0; } /** * v9fs_vfs_mkdir - VFS mkdir hook to create a directory * @idmap: idmap of the mount * @dir: inode that is being unlinked * @dentry: dentry that is being unlinked * @mode: mode for new directory * */ static int v9fs_vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int err; u32 perm; struct p9_fid *fid; struct v9fs_session_info *v9ses; p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry); err = 0; v9ses = v9fs_inode2v9ses(dir); perm = unixmode2p9mode(v9ses, mode | S_IFDIR); fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_OREAD); if (IS_ERR(fid)) { err = PTR_ERR(fid); fid = NULL; } else { inc_nlink(dir); v9fs_invalidate_inode_attr(dir); } if (fid) p9_fid_put(fid); return err; } /** * v9fs_vfs_lookup - VFS lookup hook to "walk" to a new inode * @dir: inode that is being walked from * @dentry: dentry that is being walked to? * @flags: lookup flags (unused) * */ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct dentry *res; struct v9fs_session_info *v9ses; struct p9_fid *dfid, *fid; struct inode *inode; const unsigned char *name; p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%pd) %p flags: %x\n", dir, dentry, dentry, flags); if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); v9ses = v9fs_inode2v9ses(dir); /* We can walk d_parent because we hold the dir->i_mutex */ dfid = v9fs_parent_fid(dentry); if (IS_ERR(dfid)) return ERR_CAST(dfid); /* * Make sure we don't use a wrong inode due to parallel * unlink. For cached mode create calls request for new * inode. But with cache disabled, lookup should do this. */ name = dentry->d_name.name; fid = p9_client_walk(dfid, 1, &name, 1); p9_fid_put(dfid); if (fid == ERR_PTR(-ENOENT)) inode = NULL; else if (IS_ERR(fid)) inode = ERR_CAST(fid); else if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb); else inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); /* * If we had a rename on the server and a parallel lookup * for the new name, then make sure we instantiate with * the new name. ie look up for a/b, while on server somebody * moved b under k and client parallely did a lookup for * k/b. */ res = d_splice_alias(inode, dentry); if (!IS_ERR(fid)) { if (!res) v9fs_fid_add(dentry, &fid); else if (!IS_ERR(res)) v9fs_fid_add(res, &fid); else p9_fid_put(fid); } return res; } static int v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned int flags, umode_t mode) { int err; u32 perm; struct v9fs_inode __maybe_unused *v9inode; struct v9fs_session_info *v9ses; struct p9_fid *fid; struct dentry *res = NULL; struct inode *inode; int p9_omode; if (d_in_lookup(dentry)) { res = v9fs_vfs_lookup(dir, dentry, 0); if (IS_ERR(res)) return PTR_ERR(res); if (res) dentry = res; } /* Only creates */ if (!(flags & O_CREAT) || d_really_is_positive(dentry)) return finish_no_open(file, res); v9ses = v9fs_inode2v9ses(dir); perm = unixmode2p9mode(v9ses, mode); p9_omode = v9fs_uflags2omode(flags, v9fs_proto_dotu(v9ses)); if ((v9ses->cache & CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { p9_omode = (p9_omode & ~P9_OWRITE) | P9_ORDWR; p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, creating w/ O_RDWR\n"); } fid = v9fs_create(v9ses, dir, dentry, NULL, perm, p9_omode); if (IS_ERR(fid)) { err = PTR_ERR(fid); goto error; } v9fs_invalidate_inode_attr(dir); inode = d_inode(dentry); v9inode = V9FS_I(inode); err = finish_open(file, dentry, generic_file_open); if (err) goto error; file->private_data = fid; #ifdef CONFIG_9P_FSCACHE if (v9ses->cache & CACHE_FSCACHE) fscache_use_cookie(v9fs_inode_cookie(v9inode), file->f_mode & FMODE_WRITE); #endif v9fs_fid_add_modes(fid, v9ses->flags, v9ses->cache, file->f_flags); v9fs_open_fid_add(inode, &fid); file->f_mode |= FMODE_CREATED; out: dput(res); return err; error: p9_fid_put(fid); goto out; } /** * v9fs_vfs_unlink - VFS unlink hook to delete an inode * @i: inode that is being unlinked * @d: dentry that is being unlinked * */ int v9fs_vfs_unlink(struct inode *i, struct dentry *d) { return v9fs_remove(i, d, 0); } /** * v9fs_vfs_rmdir - VFS unlink hook to delete a directory * @i: inode that is being unlinked * @d: dentry that is being unlinked * */ int v9fs_vfs_rmdir(struct inode *i, struct dentry *d) { return v9fs_remove(i, d, AT_REMOVEDIR); } /** * v9fs_vfs_rename - VFS hook to rename an inode * @idmap: The idmap of the mount * @old_dir: old dir inode * @old_dentry: old dentry * @new_dir: new dir inode * @new_dentry: new dentry * @flags: RENAME_* flags * */ int v9fs_vfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { int retval; struct inode *old_inode; struct inode *new_inode; struct v9fs_session_info *v9ses; struct p9_fid *oldfid = NULL, *dfid = NULL; struct p9_fid *olddirfid = NULL; struct p9_fid *newdirfid = NULL; struct p9_wstat wstat; if (flags) return -EINVAL; p9_debug(P9_DEBUG_VFS, "\n"); old_inode = d_inode(old_dentry); new_inode = d_inode(new_dentry); v9ses = v9fs_inode2v9ses(old_inode); oldfid = v9fs_fid_lookup(old_dentry); if (IS_ERR(oldfid)) return PTR_ERR(oldfid); dfid = v9fs_parent_fid(old_dentry); olddirfid = clone_fid(dfid); p9_fid_put(dfid); dfid = NULL; if (IS_ERR(olddirfid)) { retval = PTR_ERR(olddirfid); goto error; } dfid = v9fs_parent_fid(new_dentry); newdirfid = clone_fid(dfid); p9_fid_put(dfid); dfid = NULL; if (IS_ERR(newdirfid)) { retval = PTR_ERR(newdirfid); goto error; } down_write(&v9ses->rename_sem); if (v9fs_proto_dotl(v9ses)) { retval = p9_client_renameat(olddirfid, old_dentry->d_name.name, newdirfid, new_dentry->d_name.name); if (retval == -EOPNOTSUPP) retval = p9_client_rename(oldfid, newdirfid, new_dentry->d_name.name); if (retval != -EOPNOTSUPP) goto error_locked; } if (old_dentry->d_parent != new_dentry->d_parent) { /* * 9P .u can only handle file rename in the same directory */ p9_debug(P9_DEBUG_ERROR, "old dir and new dir are different\n"); retval = -EXDEV; goto error_locked; } v9fs_blank_wstat(&wstat); wstat.muid = v9ses->uname; wstat.name = new_dentry->d_name.name; retval = p9_client_wstat(oldfid, &wstat); error_locked: if (!retval) { if (new_inode) { if (S_ISDIR(new_inode->i_mode)) clear_nlink(new_inode); else v9fs_dec_count(new_inode); } if (S_ISDIR(old_inode->i_mode)) { if (!new_inode) inc_nlink(new_dir); v9fs_dec_count(old_dir); } v9fs_invalidate_inode_attr(old_inode); v9fs_invalidate_inode_attr(old_dir); v9fs_invalidate_inode_attr(new_dir); /* successful rename */ d_move(old_dentry, new_dentry); } up_write(&v9ses->rename_sem); error: p9_fid_put(newdirfid); p9_fid_put(olddirfid); p9_fid_put(oldfid); return retval; } /** * v9fs_vfs_getattr - retrieve file metadata * @idmap: idmap of the mount * @path: Object to query * @stat: metadata structure to populate * @request_mask: Mask of STATX_xxx flags indicating the caller's interests * @flags: AT_STATX_xxx setting * */ static int v9fs_vfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); struct v9fs_session_info *v9ses; struct p9_fid *fid; struct p9_wstat *st; p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry); v9ses = v9fs_dentry2v9ses(dentry); if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) { generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); return 0; } else if (v9ses->cache & CACHE_WRITEBACK) { if (S_ISREG(inode->i_mode)) { int retval = filemap_fdatawrite(inode->i_mapping); if (retval) p9_debug(P9_DEBUG_ERROR, "flushing writeback during getattr returned %d\n", retval); } } fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) return PTR_ERR(fid); st = p9_client_stat(fid); p9_fid_put(fid); if (IS_ERR(st)) return PTR_ERR(st); v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb, 0); generic_fillattr(&nop_mnt_idmap, request_mask, d_inode(dentry), stat); p9stat_free(st); kfree(st); return 0; } /** * v9fs_vfs_setattr - set file metadata * @idmap: idmap of the mount * @dentry: file whose metadata to set * @iattr: metadata assignment structure * */ static int v9fs_vfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { int retval, use_dentry = 0; struct inode *inode = d_inode(dentry); struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL; struct p9_wstat wstat; p9_debug(P9_DEBUG_VFS, "\n"); retval = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (retval) return retval; v9ses = v9fs_dentry2v9ses(dentry); if (iattr->ia_valid & ATTR_FILE) { fid = iattr->ia_file->private_data; WARN_ON(!fid); } if (!fid) { fid = v9fs_fid_lookup(dentry); use_dentry = 1; } if (IS_ERR(fid)) return PTR_ERR(fid); v9fs_blank_wstat(&wstat); if (iattr->ia_valid & ATTR_MODE) wstat.mode = unixmode2p9mode(v9ses, iattr->ia_mode); if (iattr->ia_valid & ATTR_MTIME) wstat.mtime = iattr->ia_mtime.tv_sec; if (iattr->ia_valid & ATTR_ATIME) wstat.atime = iattr->ia_atime.tv_sec; if (iattr->ia_valid & ATTR_SIZE) wstat.length = iattr->ia_size; if (v9fs_proto_dotu(v9ses)) { if (iattr->ia_valid & ATTR_UID) wstat.n_uid = iattr->ia_uid; if (iattr->ia_valid & ATTR_GID) wstat.n_gid = iattr->ia_gid; } /* Write all dirty data */ if (d_is_reg(dentry)) { retval = filemap_fdatawrite(inode->i_mapping); if (retval) p9_debug(P9_DEBUG_ERROR, "flushing writeback during setattr returned %d\n", retval); } retval = p9_client_wstat(fid, &wstat); if (use_dentry) p9_fid_put(fid); if (retval < 0) return retval; if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size != i_size_read(inode)) { truncate_setsize(inode, iattr->ia_size); netfs_resize_file(netfs_inode(inode), iattr->ia_size, true); #ifdef CONFIG_9P_FSCACHE if (v9ses->cache & CACHE_FSCACHE) { struct v9fs_inode *v9inode = V9FS_I(inode); fscache_resize_cookie(v9fs_inode_cookie(v9inode), iattr->ia_size); } #endif } v9fs_invalidate_inode_attr(inode); setattr_copy(&nop_mnt_idmap, inode, iattr); mark_inode_dirty(inode); return 0; } /** * v9fs_stat2inode - populate an inode structure with mistat info * @stat: Plan 9 metadata (mistat) structure * @inode: inode to populate * @sb: superblock of filesystem * @flags: control flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE) * */ void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, struct super_block *sb, unsigned int flags) { umode_t mode; struct v9fs_session_info *v9ses = sb->s_fs_info; struct v9fs_inode *v9inode = V9FS_I(inode); inode_set_atime(inode, stat->atime, 0); inode_set_mtime(inode, stat->mtime, 0); inode_set_ctime(inode, stat->mtime, 0); inode->i_uid = v9ses->dfltuid; inode->i_gid = v9ses->dfltgid; if (v9fs_proto_dotu(v9ses)) { inode->i_uid = stat->n_uid; inode->i_gid = stat->n_gid; } if ((S_ISREG(inode->i_mode)) || (S_ISDIR(inode->i_mode))) { if (v9fs_proto_dotu(v9ses)) { unsigned int i_nlink; /* * Hadlink support got added later to the .u extension. * So there can be a server out there that doesn't * support this even with .u extension. That would * just leave us with stat->extension being an empty * string, though. */ /* HARDLINKCOUNT %u */ if (sscanf(stat->extension, " HARDLINKCOUNT %u", &i_nlink) == 1) set_nlink(inode, i_nlink); } } mode = p9mode2perm(v9ses, stat); mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; v9inode->netfs.remote_i_size = stat->length; if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) v9fs_i_size_write(inode, stat->length); /* not real number of blocks, but 512 byte ones ... */ inode->i_blocks = (stat->length + 512 - 1) >> 9; v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR; } /** * v9fs_vfs_get_link - follow a symlink path * @dentry: dentry for symlink * @inode: inode for symlink * @done: delayed call for when we are done with the return value */ static const char *v9fs_vfs_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct v9fs_session_info *v9ses; struct p9_fid *fid; struct p9_wstat *st; char *res; if (!dentry) return ERR_PTR(-ECHILD); v9ses = v9fs_dentry2v9ses(dentry); if (!v9fs_proto_dotu(v9ses)) return ERR_PTR(-EBADF); p9_debug(P9_DEBUG_VFS, "%pd\n", dentry); fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) return ERR_CAST(fid); st = p9_client_stat(fid); p9_fid_put(fid); if (IS_ERR(st)) return ERR_CAST(st); if (!(st->mode & P9_DMSYMLINK)) { p9stat_free(st); kfree(st); return ERR_PTR(-EINVAL); } res = st->extension; st->extension = NULL; if (strlen(res) >= PATH_MAX) res[PATH_MAX - 1] = '\0'; p9stat_free(st); kfree(st); set_delayed_call(done, kfree_link, res); return res; } /** * v9fs_vfs_mkspecial - create a special file * @dir: inode to create special file in * @dentry: dentry to create * @perm: mode to create special file * @extension: 9p2000.u format extension string representing special file * */ static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry, u32 perm, const char *extension) { struct p9_fid *fid; struct v9fs_session_info *v9ses; v9ses = v9fs_inode2v9ses(dir); if (!v9fs_proto_dotu(v9ses)) { p9_debug(P9_DEBUG_ERROR, "not extended\n"); return -EPERM; } fid = v9fs_create(v9ses, dir, dentry, (char *) extension, perm, P9_OREAD); if (IS_ERR(fid)) return PTR_ERR(fid); v9fs_invalidate_inode_attr(dir); p9_fid_put(fid); return 0; } /** * v9fs_vfs_symlink - helper function to create symlinks * @idmap: idmap of the mount * @dir: directory inode containing symlink * @dentry: dentry for symlink * @symname: symlink data * * See Also: 9P2000.u RFC for more information * */ static int v9fs_vfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { p9_debug(P9_DEBUG_VFS, " %lu,%pd,%s\n", dir->i_ino, dentry, symname); return v9fs_vfs_mkspecial(dir, dentry, P9_DMSYMLINK, symname); } #define U32_MAX_DIGITS 10 /** * v9fs_vfs_link - create a hardlink * @old_dentry: dentry for file to link to * @dir: inode destination for new link * @dentry: dentry for link * */ static int v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { int retval; char name[1 + U32_MAX_DIGITS + 2]; /* sign + number + \n + \0 */ struct p9_fid *oldfid; p9_debug(P9_DEBUG_VFS, " %lu,%pd,%pd\n", dir->i_ino, dentry, old_dentry); oldfid = v9fs_fid_clone(old_dentry); if (IS_ERR(oldfid)) return PTR_ERR(oldfid); sprintf(name, "%d\n", oldfid->fid); retval = v9fs_vfs_mkspecial(dir, dentry, P9_DMLINK, name); if (!retval) { v9fs_refresh_inode(oldfid, d_inode(old_dentry)); v9fs_invalidate_inode_attr(dir); } p9_fid_put(oldfid); return retval; } /** * v9fs_vfs_mknod - create a special file * @idmap: idmap of the mount * @dir: inode destination for new link * @dentry: dentry for file * @mode: mode for creation * @rdev: device associated with special file * */ static int v9fs_vfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); int retval; char name[2 + U32_MAX_DIGITS + 1 + U32_MAX_DIGITS + 1]; u32 perm; p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %x MAJOR: %u MINOR: %u\n", dir->i_ino, dentry, mode, MAJOR(rdev), MINOR(rdev)); /* build extension */ if (S_ISBLK(mode)) sprintf(name, "b %u %u", MAJOR(rdev), MINOR(rdev)); else if (S_ISCHR(mode)) sprintf(name, "c %u %u", MAJOR(rdev), MINOR(rdev)); else *name = 0; perm = unixmode2p9mode(v9ses, mode); retval = v9fs_vfs_mkspecial(dir, dentry, perm, name); return retval; } int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) { int umode; dev_t rdev; struct p9_wstat *st; struct v9fs_session_info *v9ses; unsigned int flags; v9ses = v9fs_inode2v9ses(inode); st = p9_client_stat(fid); if (IS_ERR(st)) return PTR_ERR(st); /* * Don't update inode if the file type is different */ umode = p9mode2unixmode(v9ses, st, &rdev); if (inode_wrong_type(inode, umode)) goto out; /* * We don't want to refresh inode->i_size, * because we may have cached data */ flags = (v9ses->cache & CACHE_LOOSE) ? V9FS_STAT2INODE_KEEP_ISIZE : 0; v9fs_stat2inode(st, inode, inode->i_sb, flags); out: p9stat_free(st); kfree(st); return 0; } static const struct inode_operations v9fs_dir_inode_operations_dotu = { .create = v9fs_vfs_create, .lookup = v9fs_vfs_lookup, .atomic_open = v9fs_vfs_atomic_open, .symlink = v9fs_vfs_symlink, .link = v9fs_vfs_link, .unlink = v9fs_vfs_unlink, .mkdir = v9fs_vfs_mkdir, .rmdir = v9fs_vfs_rmdir, .mknod = v9fs_vfs_mknod, .rename = v9fs_vfs_rename, .getattr = v9fs_vfs_getattr, .setattr = v9fs_vfs_setattr, }; static const struct inode_operations v9fs_dir_inode_operations = { .create = v9fs_vfs_create, .lookup = v9fs_vfs_lookup, .atomic_open = v9fs_vfs_atomic_open, .unlink = v9fs_vfs_unlink, .mkdir = v9fs_vfs_mkdir, .rmdir = v9fs_vfs_rmdir, .mknod = v9fs_vfs_mknod, .rename = v9fs_vfs_rename, .getattr = v9fs_vfs_getattr, .setattr = v9fs_vfs_setattr, }; static const struct inode_operations v9fs_file_inode_operations = { .getattr = v9fs_vfs_getattr, .setattr = v9fs_vfs_setattr, }; static const struct inode_operations v9fs_symlink_inode_operations = { .get_link = v9fs_vfs_get_link, .getattr = v9fs_vfs_getattr, .setattr = v9fs_vfs_setattr, }; |
| 11 9 9 9 9 9 9 9 5 1 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2005 Marc Kleine-Budde, Pengutronix * Copyright (C) 2006 Andrey Volkov, Varma Electronics * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/workqueue.h> #include <linux/can.h> #include <linux/can/can-ml.h> #include <linux/can/dev.h> #include <linux/can/skb.h> #include <linux/gpio/consumer.h> #include <linux/of.h> static void can_update_state_error_stats(struct net_device *dev, enum can_state new_state) { struct can_priv *priv = netdev_priv(dev); if (new_state <= priv->state) return; switch (new_state) { case CAN_STATE_ERROR_WARNING: priv->can_stats.error_warning++; break; case CAN_STATE_ERROR_PASSIVE: priv->can_stats.error_passive++; break; case CAN_STATE_BUS_OFF: priv->can_stats.bus_off++; break; default: break; } } static int can_tx_state_to_frame(struct net_device *dev, enum can_state state) { switch (state) { case CAN_STATE_ERROR_ACTIVE: return CAN_ERR_CRTL_ACTIVE; case CAN_STATE_ERROR_WARNING: return CAN_ERR_CRTL_TX_WARNING; case CAN_STATE_ERROR_PASSIVE: return CAN_ERR_CRTL_TX_PASSIVE; default: return 0; } } static int can_rx_state_to_frame(struct net_device *dev, enum can_state state) { switch (state) { case CAN_STATE_ERROR_ACTIVE: return CAN_ERR_CRTL_ACTIVE; case CAN_STATE_ERROR_WARNING: return CAN_ERR_CRTL_RX_WARNING; case CAN_STATE_ERROR_PASSIVE: return CAN_ERR_CRTL_RX_PASSIVE; default: return 0; } } const char *can_get_state_str(const enum can_state state) { switch (state) { case CAN_STATE_ERROR_ACTIVE: return "Error Active"; case CAN_STATE_ERROR_WARNING: return "Error Warning"; case CAN_STATE_ERROR_PASSIVE: return "Error Passive"; case CAN_STATE_BUS_OFF: return "Bus Off"; case CAN_STATE_STOPPED: return "Stopped"; case CAN_STATE_SLEEPING: return "Sleeping"; default: return "<unknown>"; } return "<unknown>"; } EXPORT_SYMBOL_GPL(can_get_state_str); static enum can_state can_state_err_to_state(u16 err) { if (err < CAN_ERROR_WARNING_THRESHOLD) return CAN_STATE_ERROR_ACTIVE; if (err < CAN_ERROR_PASSIVE_THRESHOLD) return CAN_STATE_ERROR_WARNING; if (err < CAN_BUS_OFF_THRESHOLD) return CAN_STATE_ERROR_PASSIVE; return CAN_STATE_BUS_OFF; } void can_state_get_by_berr_counter(const struct net_device *dev, const struct can_berr_counter *bec, enum can_state *tx_state, enum can_state *rx_state) { *tx_state = can_state_err_to_state(bec->txerr); *rx_state = can_state_err_to_state(bec->rxerr); } EXPORT_SYMBOL_GPL(can_state_get_by_berr_counter); void can_change_state(struct net_device *dev, struct can_frame *cf, enum can_state tx_state, enum can_state rx_state) { struct can_priv *priv = netdev_priv(dev); enum can_state new_state = max(tx_state, rx_state); if (unlikely(new_state == priv->state)) { netdev_warn(dev, "%s: oops, state did not change", __func__); return; } netdev_dbg(dev, "Controller changed from %s State (%d) into %s State (%d).\n", can_get_state_str(priv->state), priv->state, can_get_state_str(new_state), new_state); can_update_state_error_stats(dev, new_state); priv->state = new_state; if (!cf) return; if (unlikely(new_state == CAN_STATE_BUS_OFF)) { cf->can_id |= CAN_ERR_BUSOFF; return; } cf->can_id |= CAN_ERR_CRTL; cf->data[1] |= tx_state >= rx_state ? can_tx_state_to_frame(dev, tx_state) : 0; cf->data[1] |= tx_state <= rx_state ? can_rx_state_to_frame(dev, rx_state) : 0; } EXPORT_SYMBOL_GPL(can_change_state); /* CAN device restart for bus-off recovery */ static void can_restart(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); struct sk_buff *skb; struct can_frame *cf; int err; if (netif_carrier_ok(dev)) netdev_err(dev, "Attempt to restart for bus-off recovery, but carrier is OK?\n"); /* No synchronization needed because the device is bus-off and * no messages can come in or go out. */ can_flush_echo_skb(dev); /* send restart message upstream */ skb = alloc_can_err_skb(dev, &cf); if (skb) { cf->can_id |= CAN_ERR_RESTARTED; netif_rx(skb); } /* Now restart the device */ netif_carrier_on(dev); err = priv->do_set_mode(dev, CAN_MODE_START); if (err) { netdev_err(dev, "Restart failed, error %pe\n", ERR_PTR(err)); netif_carrier_off(dev); } else { netdev_dbg(dev, "Restarted\n"); priv->can_stats.restarts++; } } static void can_restart_work(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct can_priv *priv = container_of(dwork, struct can_priv, restart_work); can_restart(priv->dev); } int can_restart_now(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); /* A manual restart is only permitted if automatic restart is * disabled and the device is in the bus-off state */ if (priv->restart_ms) return -EINVAL; if (priv->state != CAN_STATE_BUS_OFF) return -EBUSY; cancel_delayed_work_sync(&priv->restart_work); can_restart(dev); return 0; } /* CAN bus-off * * This functions should be called when the device goes bus-off to * tell the netif layer that no more packets can be sent or received. * If enabled, a timer is started to trigger bus-off recovery. */ void can_bus_off(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); if (priv->restart_ms) netdev_info(dev, "bus-off, scheduling restart in %d ms\n", priv->restart_ms); else netdev_info(dev, "bus-off\n"); netif_carrier_off(dev); if (priv->restart_ms) schedule_delayed_work(&priv->restart_work, msecs_to_jiffies(priv->restart_ms)); } EXPORT_SYMBOL_GPL(can_bus_off); void can_setup(struct net_device *dev) { dev->type = ARPHRD_CAN; dev->mtu = CAN_MTU; dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 10; /* New-style flags. */ dev->flags = IFF_NOARP; dev->features = NETIF_F_HW_CSUM; } /* Allocate and setup space for the CAN network device */ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, unsigned int txqs, unsigned int rxqs) { struct can_ml_priv *can_ml; struct net_device *dev; struct can_priv *priv; int size; /* We put the driver's priv, the CAN mid layer priv and the * echo skb into the netdevice's priv. The memory layout for * the netdev_priv is like this: * * +-------------------------+ * | driver's priv | * +-------------------------+ * | struct can_ml_priv | * +-------------------------+ * | array of struct sk_buff | * +-------------------------+ */ size = ALIGN(sizeof_priv, NETDEV_ALIGN) + sizeof(struct can_ml_priv); if (echo_skb_max) size = ALIGN(size, sizeof(struct sk_buff *)) + echo_skb_max * sizeof(struct sk_buff *); dev = alloc_netdev_mqs(size, "can%d", NET_NAME_UNKNOWN, can_setup, txqs, rxqs); if (!dev) return NULL; priv = netdev_priv(dev); priv->dev = dev; can_ml = (void *)priv + ALIGN(sizeof_priv, NETDEV_ALIGN); can_set_ml_priv(dev, can_ml); if (echo_skb_max) { priv->echo_skb_max = echo_skb_max; priv->echo_skb = (void *)priv + (size - echo_skb_max * sizeof(struct sk_buff *)); } priv->state = CAN_STATE_STOPPED; INIT_DELAYED_WORK(&priv->restart_work, can_restart_work); return dev; } EXPORT_SYMBOL_GPL(alloc_candev_mqs); /* Free space of the CAN network device */ void free_candev(struct net_device *dev) { free_netdev(dev); } EXPORT_SYMBOL_GPL(free_candev); /* changing MTU and control mode for CAN/CANFD devices */ int can_change_mtu(struct net_device *dev, int new_mtu) { struct can_priv *priv = netdev_priv(dev); u32 ctrlmode_static = can_get_static_ctrlmode(priv); /* Do not allow changing the MTU while running */ if (dev->flags & IFF_UP) return -EBUSY; /* allow change of MTU according to the CANFD ability of the device */ switch (new_mtu) { case CAN_MTU: /* 'CANFD-only' controllers can not switch to CAN_MTU */ if (ctrlmode_static & CAN_CTRLMODE_FD) return -EINVAL; priv->ctrlmode &= ~CAN_CTRLMODE_FD; break; case CANFD_MTU: /* check for potential CANFD ability */ if (!(priv->ctrlmode_supported & CAN_CTRLMODE_FD) && !(ctrlmode_static & CAN_CTRLMODE_FD)) return -EINVAL; priv->ctrlmode |= CAN_CTRLMODE_FD; break; default: return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL_GPL(can_change_mtu); /* generic implementation of netdev_ops::ndo_eth_ioctl for CAN devices * supporting hardware timestamps */ int can_eth_ioctl_hwts(struct net_device *netdev, struct ifreq *ifr, int cmd) { struct hwtstamp_config hwts_cfg = { 0 }; switch (cmd) { case SIOCSHWTSTAMP: /* set */ if (copy_from_user(&hwts_cfg, ifr->ifr_data, sizeof(hwts_cfg))) return -EFAULT; if (hwts_cfg.tx_type == HWTSTAMP_TX_ON && hwts_cfg.rx_filter == HWTSTAMP_FILTER_ALL) return 0; return -ERANGE; case SIOCGHWTSTAMP: /* get */ hwts_cfg.tx_type = HWTSTAMP_TX_ON; hwts_cfg.rx_filter = HWTSTAMP_FILTER_ALL; if (copy_to_user(ifr->ifr_data, &hwts_cfg, sizeof(hwts_cfg))) return -EFAULT; return 0; default: return -EOPNOTSUPP; } } EXPORT_SYMBOL(can_eth_ioctl_hwts); /* generic implementation of ethtool_ops::get_ts_info for CAN devices * supporting hardware timestamps */ int can_ethtool_op_get_ts_info_hwts(struct net_device *dev, struct kernel_ethtool_ts_info *info) { info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | SOF_TIMESTAMPING_TX_HARDWARE | SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; info->tx_types = BIT(HWTSTAMP_TX_ON); info->rx_filters = BIT(HWTSTAMP_FILTER_ALL); return 0; } EXPORT_SYMBOL(can_ethtool_op_get_ts_info_hwts); /* Common open function when the device gets opened. * * This function should be called in the open function of the device * driver. */ int open_candev(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); if (!priv->bittiming.bitrate) { netdev_err(dev, "bit-timing not yet defined\n"); return -EINVAL; } /* For CAN FD the data bitrate has to be >= the arbitration bitrate */ if ((priv->ctrlmode & CAN_CTRLMODE_FD) && (!priv->data_bittiming.bitrate || priv->data_bittiming.bitrate < priv->bittiming.bitrate)) { netdev_err(dev, "incorrect/missing data bit-timing\n"); return -EINVAL; } /* Switch carrier on if device was stopped while in bus-off state */ if (!netif_carrier_ok(dev)) netif_carrier_on(dev); return 0; } EXPORT_SYMBOL_GPL(open_candev); #ifdef CONFIG_OF /* Common function that can be used to understand the limitation of * a transceiver when it provides no means to determine these limitations * at runtime. */ void of_can_transceiver(struct net_device *dev) { struct device_node *dn; struct can_priv *priv = netdev_priv(dev); struct device_node *np = dev->dev.parent->of_node; int ret; dn = of_get_child_by_name(np, "can-transceiver"); if (!dn) return; ret = of_property_read_u32(dn, "max-bitrate", &priv->bitrate_max); of_node_put(dn); if ((ret && ret != -EINVAL) || (!ret && !priv->bitrate_max)) netdev_warn(dev, "Invalid value for transceiver max bitrate. Ignoring bitrate limit.\n"); } EXPORT_SYMBOL_GPL(of_can_transceiver); #endif /* Common close function for cleanup before the device gets closed. * * This function should be called in the close function of the device * driver. */ void close_candev(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); cancel_delayed_work_sync(&priv->restart_work); can_flush_echo_skb(dev); } EXPORT_SYMBOL_GPL(close_candev); static int can_set_termination(struct net_device *ndev, u16 term) { struct can_priv *priv = netdev_priv(ndev); int set; if (term == priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_ENABLED]) set = 1; else set = 0; gpiod_set_value(priv->termination_gpio, set); return 0; } static int can_get_termination(struct net_device *ndev) { struct can_priv *priv = netdev_priv(ndev); struct device *dev = ndev->dev.parent; struct gpio_desc *gpio; u32 term; int ret; /* Disabling termination by default is the safe choice: Else if many * bus participants enable it, no communication is possible at all. */ gpio = devm_gpiod_get_optional(dev, "termination", GPIOD_OUT_LOW); if (IS_ERR(gpio)) return dev_err_probe(dev, PTR_ERR(gpio), "Cannot get termination-gpios\n"); if (!gpio) return 0; ret = device_property_read_u32(dev, "termination-ohms", &term); if (ret) { netdev_err(ndev, "Cannot get termination-ohms: %pe\n", ERR_PTR(ret)); return ret; } if (term > U16_MAX) { netdev_err(ndev, "Invalid termination-ohms value (%u > %u)\n", term, U16_MAX); return -EINVAL; } priv->termination_const_cnt = ARRAY_SIZE(priv->termination_gpio_ohms); priv->termination_const = priv->termination_gpio_ohms; priv->termination_gpio = gpio; priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_DISABLED] = CAN_TERMINATION_DISABLED; priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_ENABLED] = term; priv->do_set_termination = can_set_termination; return 0; } static bool can_bittiming_const_valid(const struct can_bittiming_const *btc) { if (!btc) return true; if (!btc->sjw_max) return false; return true; } /* Register the CAN network device */ int register_candev(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); int err; /* Ensure termination_const, termination_const_cnt and * do_set_termination consistency. All must be either set or * unset. */ if ((!priv->termination_const != !priv->termination_const_cnt) || (!priv->termination_const != !priv->do_set_termination)) return -EINVAL; if (!priv->bitrate_const != !priv->bitrate_const_cnt) return -EINVAL; if (!priv->data_bitrate_const != !priv->data_bitrate_const_cnt) return -EINVAL; /* We only support either fixed bit rates or bit timing const. */ if ((priv->bitrate_const || priv->data_bitrate_const) && (priv->bittiming_const || priv->data_bittiming_const)) return -EINVAL; if (!can_bittiming_const_valid(priv->bittiming_const) || !can_bittiming_const_valid(priv->data_bittiming_const)) return -EINVAL; if (!priv->termination_const) { err = can_get_termination(dev); if (err) return err; } dev->rtnl_link_ops = &can_link_ops; netif_carrier_off(dev); return register_netdev(dev); } EXPORT_SYMBOL_GPL(register_candev); /* Unregister the CAN network device */ void unregister_candev(struct net_device *dev) { unregister_netdev(dev); } EXPORT_SYMBOL_GPL(unregister_candev); /* Test if a network device is a candev based device * and return the can_priv* if so. */ struct can_priv *safe_candev_priv(struct net_device *dev) { if (dev->type != ARPHRD_CAN || dev->rtnl_link_ops != &can_link_ops) return NULL; return netdev_priv(dev); } EXPORT_SYMBOL_GPL(safe_candev_priv); static __init int can_dev_init(void) { int err; err = can_netlink_register(); if (!err) pr_info("CAN device driver interface\n"); return err; } module_init(can_dev_init); static __exit void can_dev_exit(void) { can_netlink_unregister(); } module_exit(can_dev_exit); MODULE_ALIAS_RTNL_LINK("can"); |
| 25 20 11 11 25 22 24 1 2 2 3 2 2 2 2 1 2 2 3 3 3 3 3 3 21 20 20 20 3 20 20 3 22 4 4 4 4 4 2 1 4 1 4 4 1 1 4 28 8 4 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 | // SPDX-License-Identifier: GPL-2.0-or-later /* * tcp_diag.c Module for monitoring TCP transport protocols sockets. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/net.h> #include <linux/sock_diag.h> #include <linux/inet_diag.h> #include <linux/tcp.h> #include <net/netlink.h> #include <net/tcp.h> static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, void *_info) { struct tcp_info *info = _info; if (inet_sk_state_load(sk) == TCP_LISTEN) { r->idiag_rqueue = READ_ONCE(sk->sk_ack_backlog); r->idiag_wqueue = READ_ONCE(sk->sk_max_ack_backlog); } else if (sk->sk_type == SOCK_STREAM) { const struct tcp_sock *tp = tcp_sk(sk); r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq), 0); r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una; } if (info) tcp_get_info(sk, info); } #ifdef CONFIG_TCP_MD5SIG static void tcp_diag_md5sig_fill(struct tcp_diag_md5sig *info, const struct tcp_md5sig_key *key) { info->tcpm_family = key->family; info->tcpm_prefixlen = key->prefixlen; info->tcpm_keylen = key->keylen; memcpy(info->tcpm_key, key->key, key->keylen); if (key->family == AF_INET) info->tcpm_addr[0] = key->addr.a4.s_addr; #if IS_ENABLED(CONFIG_IPV6) else if (key->family == AF_INET6) memcpy(&info->tcpm_addr, &key->addr.a6, sizeof(info->tcpm_addr)); #endif } static int tcp_diag_put_md5sig(struct sk_buff *skb, const struct tcp_md5sig_info *md5sig) { const struct tcp_md5sig_key *key; struct tcp_diag_md5sig *info; struct nlattr *attr; int md5sig_count = 0; hlist_for_each_entry_rcu(key, &md5sig->head, node) md5sig_count++; if (md5sig_count == 0) return 0; attr = nla_reserve(skb, INET_DIAG_MD5SIG, md5sig_count * sizeof(struct tcp_diag_md5sig)); if (!attr) return -EMSGSIZE; info = nla_data(attr); memset(info, 0, md5sig_count * sizeof(struct tcp_diag_md5sig)); hlist_for_each_entry_rcu(key, &md5sig->head, node) { tcp_diag_md5sig_fill(info++, key); if (--md5sig_count == 0) break; } return 0; } #endif static int tcp_diag_put_ulp(struct sk_buff *skb, struct sock *sk, const struct tcp_ulp_ops *ulp_ops) { struct nlattr *nest; int err; nest = nla_nest_start_noflag(skb, INET_DIAG_ULP_INFO); if (!nest) return -EMSGSIZE; err = nla_put_string(skb, INET_ULP_INFO_NAME, ulp_ops->name); if (err) goto nla_failure; if (ulp_ops->get_info) err = ulp_ops->get_info(sk, skb); if (err) goto nla_failure; nla_nest_end(skb, nest); return 0; nla_failure: nla_nest_cancel(skb, nest); return err; } static int tcp_diag_get_aux(struct sock *sk, bool net_admin, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); int err = 0; #ifdef CONFIG_TCP_MD5SIG if (net_admin) { struct tcp_md5sig_info *md5sig; rcu_read_lock(); md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info); if (md5sig) err = tcp_diag_put_md5sig(skb, md5sig); rcu_read_unlock(); if (err < 0) return err; } #endif if (net_admin) { const struct tcp_ulp_ops *ulp_ops; ulp_ops = icsk->icsk_ulp_ops; if (ulp_ops) err = tcp_diag_put_ulp(skb, sk, ulp_ops); if (err) return err; } return 0; } static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin) { struct inet_connection_sock *icsk = inet_csk(sk); size_t size = 0; #ifdef CONFIG_TCP_MD5SIG if (net_admin && sk_fullsock(sk)) { const struct tcp_md5sig_info *md5sig; const struct tcp_md5sig_key *key; size_t md5sig_count = 0; rcu_read_lock(); md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info); if (md5sig) { hlist_for_each_entry_rcu(key, &md5sig->head, node) md5sig_count++; } rcu_read_unlock(); size += nla_total_size(md5sig_count * sizeof(struct tcp_diag_md5sig)); } #endif if (net_admin && sk_fullsock(sk)) { const struct tcp_ulp_ops *ulp_ops; ulp_ops = icsk->icsk_ulp_ops; if (ulp_ops) { size += nla_total_size(0) + nla_total_size(TCP_ULP_NAME_MAX); if (ulp_ops->get_info_size) size += ulp_ops->get_info_size(sk); } } return size; } static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { struct inet_hashinfo *hinfo; hinfo = sock_net(cb->skb->sk)->ipv4.tcp_death_row.hashinfo; inet_diag_dump_icsk(hinfo, skb, cb, r); } static int tcp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { struct inet_hashinfo *hinfo; hinfo = sock_net(cb->skb->sk)->ipv4.tcp_death_row.hashinfo; return inet_diag_dump_one_icsk(hinfo, cb, req); } #ifdef CONFIG_INET_DIAG_DESTROY static int tcp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { struct net *net = sock_net(in_skb->sk); struct inet_hashinfo *hinfo; struct sock *sk; int err; hinfo = net->ipv4.tcp_death_row.hashinfo; sk = inet_diag_find_one_icsk(net, hinfo, req); if (IS_ERR(sk)) return PTR_ERR(sk); err = sock_diag_destroy(sk, ECONNABORTED); sock_gen_put(sk); return err; } #endif static const struct inet_diag_handler tcp_diag_handler = { .owner = THIS_MODULE, .dump = tcp_diag_dump, .dump_one = tcp_diag_dump_one, .idiag_get_info = tcp_diag_get_info, .idiag_get_aux = tcp_diag_get_aux, .idiag_get_aux_size = tcp_diag_get_aux_size, .idiag_type = IPPROTO_TCP, .idiag_info_size = sizeof(struct tcp_info), #ifdef CONFIG_INET_DIAG_DESTROY .destroy = tcp_diag_destroy, #endif }; static int __init tcp_diag_init(void) { return inet_diag_register(&tcp_diag_handler); } static void __exit tcp_diag_exit(void) { inet_diag_unregister(&tcp_diag_handler); } module_init(tcp_diag_init); module_exit(tcp_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("TCP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-6 /* AF_INET - IPPROTO_TCP */); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_STATFS_H #define _LINUX_STATFS_H #include <linux/types.h> #include <asm/statfs.h> #include <asm/byteorder.h> struct kstatfs { long f_type; long f_bsize; u64 f_blocks; u64 f_bfree; u64 f_bavail; u64 f_files; u64 f_ffree; __kernel_fsid_t f_fsid; long f_namelen; long f_frsize; long f_flags; long f_spare[4]; }; /* * Definitions for the flag in f_flag. * * Generally these flags are equivalent to the MS_ flags used in the mount * ABI. The exception is ST_VALID which has the same value as MS_REMOUNT * which doesn't make any sense for statfs. */ #define ST_RDONLY 0x0001 /* mount read-only */ #define ST_NOSUID 0x0002 /* ignore suid and sgid bits */ #define ST_NODEV 0x0004 /* disallow access to device special files */ #define ST_NOEXEC 0x0008 /* disallow program execution */ #define ST_SYNCHRONOUS 0x0010 /* writes are synced at once */ #define ST_VALID 0x0020 /* f_flags support is implemented */ #define ST_MANDLOCK 0x0040 /* allow mandatory locks on an FS */ /* 0x0080 used for ST_WRITE in glibc */ /* 0x0100 used for ST_APPEND in glibc */ /* 0x0200 used for ST_IMMUTABLE in glibc */ #define ST_NOATIME 0x0400 /* do not update access times */ #define ST_NODIRATIME 0x0800 /* do not update directory access times */ #define ST_RELATIME 0x1000 /* update atime relative to mtime/ctime */ #define ST_NOSYMFOLLOW 0x2000 /* do not follow symlinks */ struct dentry; extern int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid); static inline __kernel_fsid_t u64_to_fsid(u64 v) { return (__kernel_fsid_t){.val = {(u32)v, (u32)(v>>32)}}; } /* Fold 16 bytes uuid to 64 bit fsid */ static inline __kernel_fsid_t uuid_to_fsid(__u8 *uuid) { return u64_to_fsid(le64_to_cpup((void *)uuid) ^ le64_to_cpup((void *)(uuid + sizeof(u64)))); } #endif |
| 1 2 2 2 2 1 370 369 63 46 3 35 34 3 3 34 33 3 1 11 8 6 5 5 4 3 295 296 1 1 295 2 33 31 2 295 296 43 13 13 13 13 13 296 43 296 43 3 296 43 2 296 295 296 6 3 2 2 260 35 34 33 32 9 7 33 33 33 32 2 2 33 33 33 33 33 33 264 32 2 1 263 288 46 11 6 3 45 35 3 35 33 33 20 19 15 1 14 14 14 18 7 18 20 29 29 29 1 28 26 3 3 2 2 2 3 3 3 3 3 1 1 1 1 3 3 2 2 2 2 2 2 2 2 2 3 3 3 3 3 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 5 2 3 2 5 5 5 5 4 2 5 2 2 2 6 5 1 5 5 5 3 5 2 2 4 6 357 273 5 5 4 4 4 1 4 2 4 4 4 4 6 6 2 6 5 4 3 3 5 4 1 1 6 6 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine driver for Linux * cpuid support routines * * derived from arch/x86/kvm/x86.c * * Copyright 2011 Red Hat, Inc. and/or its affiliates. * Copyright IBM Corporation, 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "linux/lockdep.h" #include <linux/export.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> #include <linux/sched/stat.h> #include <asm/processor.h> #include <asm/user.h> #include <asm/fpu/xstate.h> #include <asm/sgx.h> #include <asm/cpuid.h> #include "cpuid.h" #include "lapic.h" #include "mmu.h" #include "trace.h" #include "pmu.h" #include "xen.h" /* * Unlike "struct cpuinfo_x86.x86_capability", kvm_cpu_caps doesn't need to be * aligned to sizeof(unsigned long) because it's not accessed via bitops. */ u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly; EXPORT_SYMBOL_GPL(kvm_cpu_caps); u32 xstate_required_size(u64 xstate_bv, bool compacted) { int feature_bit = 0; u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; xstate_bv &= XFEATURE_MASK_EXTEND; while (xstate_bv) { if (xstate_bv & 0x1) { u32 eax, ebx, ecx, edx, offset; cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx); /* ECX[1]: 64B alignment in compacted form */ if (compacted) offset = (ecx & 0x2) ? ALIGN(ret, 64) : ret; else offset = ebx; ret = max(ret, offset + eax); } xstate_bv >>= 1; feature_bit++; } return ret; } #define F feature_bit /* Scattered Flag - For features that are scattered by cpufeatures.h. */ #define SF(name) \ ({ \ BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0); \ }) /* * Magic value used by KVM when querying userspace-provided CPUID entries and * doesn't care about the CPIUD index because the index of the function in * question is not significant. Note, this magic value must have at least one * bit set in bits[63:32] and must be consumed as a u64 by cpuid_entry2_find() * to avoid false positives when processing guest CPUID input. */ #define KVM_CPUID_INDEX_NOT_SIGNIFICANT -1ull static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( struct kvm_cpuid_entry2 *entries, int nent, u32 function, u64 index) { struct kvm_cpuid_entry2 *e; int i; /* * KVM has a semi-arbitrary rule that querying the guest's CPUID model * with IRQs disabled is disallowed. The CPUID model can legitimately * have over one hundred entries, i.e. the lookup is slow, and IRQs are * typically disabled in KVM only when KVM is in a performance critical * path, e.g. the core VM-Enter/VM-Exit run loop. Nothing will break * if this rule is violated, this assertion is purely to flag potential * performance issues. If this fires, consider moving the lookup out * of the hotpath, e.g. by caching information during CPUID updates. */ lockdep_assert_irqs_enabled(); for (i = 0; i < nent; i++) { e = &entries[i]; if (e->function != function) continue; /* * If the index isn't significant, use the first entry with a * matching function. It's userspace's responsibility to not * provide "duplicate" entries in all cases. */ if (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index) return e; /* * Similarly, use the first matching entry if KVM is doing a * lookup (as opposed to emulating CPUID) for a function that's * architecturally defined as not having a significant index. */ if (index == KVM_CPUID_INDEX_NOT_SIGNIFICANT) { /* * Direct lookups from KVM should not diverge from what * KVM defines internally (the architectural behavior). */ WARN_ON_ONCE(cpuid_function_is_indexed(function)); return e; } } return NULL; } static int kvm_check_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, int nent) { struct kvm_cpuid_entry2 *best; u64 xfeatures; /* * The existing code assumes virtual address is 48-bit or 57-bit in the * canonical address checks; exit if it is ever changed. */ best = cpuid_entry2_find(entries, nent, 0x80000008, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { int vaddr_bits = (best->eax & 0xff00) >> 8; if (vaddr_bits != 48 && vaddr_bits != 57 && vaddr_bits != 0) return -EINVAL; } /* * Exposing dynamic xfeatures to the guest requires additional * enabling in the FPU, e.g. to expand the guest XSAVE state size. */ best = cpuid_entry2_find(entries, nent, 0xd, 0); if (!best) return 0; xfeatures = best->eax | ((u64)best->edx << 32); xfeatures &= XFEATURE_MASK_USER_DYNAMIC; if (!xfeatures) return 0; return fpu_enable_guest_xfd_features(&vcpu->arch.guest_fpu, xfeatures); } /* Check whether the supplied CPUID data is equal to what is already set for the vCPU. */ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, int nent) { struct kvm_cpuid_entry2 *orig; int i; if (nent != vcpu->arch.cpuid_nent) return -EINVAL; for (i = 0; i < nent; i++) { orig = &vcpu->arch.cpuid_entries[i]; if (e2[i].function != orig->function || e2[i].index != orig->index || e2[i].flags != orig->flags || e2[i].eax != orig->eax || e2[i].ebx != orig->ebx || e2[i].ecx != orig->ecx || e2[i].edx != orig->edx) return -EINVAL; } return 0; } static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_entry2 *entries, int nent, const char *sig) { struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; u32 base; for_each_possible_hypervisor_cpuid_base(base) { entry = cpuid_entry2_find(entries, nent, base, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (entry) { u32 signature[3]; signature[0] = entry->ebx; signature[1] = entry->ecx; signature[2] = entry->edx; if (!memcmp(signature, sig, sizeof(signature))) { cpuid.base = base; cpuid.limit = entry->eax; break; } } } return cpuid; } static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, const char *sig) { return __kvm_get_hypervisor_cpuid(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, sig); } static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_cpuid_entry2 *entries, int nent, u32 kvm_cpuid_base) { return cpuid_entry2_find(entries, nent, kvm_cpuid_base | KVM_CPUID_FEATURES, KVM_CPUID_INDEX_NOT_SIGNIFICANT); } static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) { u32 base = vcpu->arch.kvm_cpuid.base; if (!base) return NULL; return __kvm_find_kvm_cpuid_features(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, base); } void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best = kvm_find_kvm_cpuid_features(vcpu); /* * save the feature bitmap to avoid cpuid lookup for every PV * operation */ if (best) vcpu->arch.pv_cpuid.features = best->eax; } /* * Calculate guest's supported XCR0 taking into account guest CPUID data and * KVM's supported XCR0 (comprised of host's XCR0 and KVM_SUPPORTED_XCR0). */ static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent) { struct kvm_cpuid_entry2 *best; best = cpuid_entry2_find(entries, nent, 0xd, 0); if (!best) return 0; return (best->eax | ((u64)best->edx << 32)) & kvm_caps.supported_xcr0; } static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, int nent) { struct kvm_cpuid_entry2 *best; struct kvm_hypervisor_cpuid kvm_cpuid; best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { /* Update OSXSAVE bit */ if (boot_cpu_has(X86_FEATURE_XSAVE)) cpuid_entry_change(best, X86_FEATURE_OSXSAVE, kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)); cpuid_entry_change(best, X86_FEATURE_APIC, vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE); } best = cpuid_entry2_find(entries, nent, 7, 0); if (best && boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7) cpuid_entry_change(best, X86_FEATURE_OSPKE, kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE)); best = cpuid_entry2_find(entries, nent, 0xD, 0); if (best) best->ebx = xstate_required_size(vcpu->arch.xcr0, false); best = cpuid_entry2_find(entries, nent, 0xD, 1); if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) || cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); kvm_cpuid = __kvm_get_hypervisor_cpuid(entries, nent, KVM_SIGNATURE); if (kvm_cpuid.base) { best = __kvm_find_kvm_cpuid_features(entries, nent, kvm_cpuid.base); if (kvm_hlt_in_guest(vcpu->kvm) && best) best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); } if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = cpuid_entry2_find(entries, nent, 0x1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) cpuid_entry_change(best, X86_FEATURE_MWAIT, vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT); } } void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) { __kvm_update_cpuid_runtime(vcpu, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); } EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime); static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent) { #ifdef CONFIG_KVM_HYPERV struct kvm_cpuid_entry2 *entry; entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE, KVM_CPUID_INDEX_NOT_SIGNIFICANT); return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX; #else return false; #endif } static bool guest_cpuid_is_amd_or_hygon(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *entry; entry = kvm_find_cpuid_entry(vcpu, 0); if (!entry) return false; return is_guest_vendor_amd(entry->ebx, entry->ecx, entry->edx) || is_guest_vendor_hygon(entry->ebx, entry->ecx, entry->edx); } static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; bool allow_gbpages; BUILD_BUG_ON(KVM_NR_GOVERNED_FEATURES > KVM_MAX_NR_GOVERNED_FEATURES); bitmap_zero(vcpu->arch.governed_features.enabled, KVM_MAX_NR_GOVERNED_FEATURES); /* * If TDP is enabled, let the guest use GBPAGES if they're supported in * hardware. The hardware page walker doesn't let KVM disable GBPAGES, * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA * walk for performance and complexity reasons. Not to mention KVM * _can't_ solve the problem because GVA->GPA walks aren't visible to * KVM once a TDP translation is installed. Mimic hardware behavior so * that KVM's is at least consistent, i.e. doesn't randomly inject #PF. * If TDP is disabled, honor *only* guest CPUID as KVM has full control * and can install smaller shadow pages if the host lacks 1GiB support. */ allow_gbpages = tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) : guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES); if (allow_gbpages) kvm_governed_feature_set(vcpu, X86_FEATURE_GBPAGES); best = kvm_find_cpuid_entry(vcpu, 1); if (best && apic) { if (cpuid_entry_has(best, X86_FEATURE_TSC_DEADLINE_TIMER)) apic->lapic_timer.timer_mode_mask = 3 << 17; else apic->lapic_timer.timer_mode_mask = 1 << 17; kvm_apic_set_version(vcpu); } vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); kvm_update_pv_runtime(vcpu); vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); kvm_pmu_refresh(vcpu); vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(guest_cpuid_has, vcpu); kvm_hv_set_cpuid(vcpu, kvm_cpuid_has_hyperv(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent)); /* Invoke the vendor callback only after the above state is updated. */ kvm_x86_call(vcpu_after_set_cpuid)(vcpu); /* * Except for the MMU, which needs to do its thing any vendor specific * adjustments to the reserved GPA bits. */ kvm_mmu_after_set_cpuid(vcpu); } int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; best = kvm_find_cpuid_entry(vcpu, 0x80000000); if (!best || best->eax < 0x80000008) goto not_found; best = kvm_find_cpuid_entry(vcpu, 0x80000008); if (best) return best->eax & 0xff; not_found: return 36; } /* * This "raw" version returns the reserved GPA bits without any adjustments for * encryption technologies that usurp bits. The raw mask should be used if and * only if hardware does _not_ strip the usurped bits, e.g. in virtual MTRRs. */ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu) { return rsvd_bits(cpuid_maxphyaddr(vcpu), 63); } static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, int nent) { int r; __kvm_update_cpuid_runtime(vcpu, e2, nent); /* * KVM does not correctly handle changing guest CPUID after KVM_RUN, as * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page * faults due to reusing SPs/SPTEs. In practice no sane VMM mucks with * the core vCPU model on the fly. It would've been better to forbid any * KVM_SET_CPUID{,2} calls after KVM_RUN altogether but unfortunately * some VMMs (e.g. QEMU) reuse vCPU fds for CPU hotplug/unplug and do * KVM_SET_CPUID{,2} again. To support this legacy behavior, check * whether the supplied CPUID data is equal to what's already set. */ if (kvm_vcpu_has_run(vcpu)) { r = kvm_cpuid_check_equal(vcpu, e2, nent); if (r) return r; kvfree(e2); return 0; } #ifdef CONFIG_KVM_HYPERV if (kvm_cpuid_has_hyperv(e2, nent)) { r = kvm_hv_vcpu_init(vcpu); if (r) return r; } #endif r = kvm_check_cpuid(vcpu, e2, nent); if (r) return r; kvfree(vcpu->arch.cpuid_entries); vcpu->arch.cpuid_entries = e2; vcpu->arch.cpuid_nent = nent; vcpu->arch.kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); #ifdef CONFIG_KVM_XEN vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); #endif kvm_vcpu_after_set_cpuid(vcpu); return 0; } /* when an old userspace process fills a new kernel module */ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, struct kvm_cpuid_entry __user *entries) { int r, i; struct kvm_cpuid_entry *e = NULL; struct kvm_cpuid_entry2 *e2 = NULL; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) return -E2BIG; if (cpuid->nent) { e = vmemdup_array_user(entries, cpuid->nent, sizeof(*e)); if (IS_ERR(e)) return PTR_ERR(e); e2 = kvmalloc_array(cpuid->nent, sizeof(*e2), GFP_KERNEL_ACCOUNT); if (!e2) { r = -ENOMEM; goto out_free_cpuid; } } for (i = 0; i < cpuid->nent; i++) { e2[i].function = e[i].function; e2[i].eax = e[i].eax; e2[i].ebx = e[i].ebx; e2[i].ecx = e[i].ecx; e2[i].edx = e[i].edx; e2[i].index = 0; e2[i].flags = 0; e2[i].padding[0] = 0; e2[i].padding[1] = 0; e2[i].padding[2] = 0; } r = kvm_set_cpuid(vcpu, e2, cpuid->nent); if (r) kvfree(e2); out_free_cpuid: kvfree(e); return r; } int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { struct kvm_cpuid_entry2 *e2 = NULL; int r; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) return -E2BIG; if (cpuid->nent) { e2 = vmemdup_array_user(entries, cpuid->nent, sizeof(*e2)); if (IS_ERR(e2)) return PTR_ERR(e2); } r = kvm_set_cpuid(vcpu, e2, cpuid->nent); if (r) kvfree(e2); return r; } int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { if (cpuid->nent < vcpu->arch.cpuid_nent) return -E2BIG; if (copy_to_user(entries, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) return -EFAULT; cpuid->nent = vcpu->arch.cpuid_nent; return 0; } /* Mask kvm_cpu_caps for @leaf with the raw CPUID capabilities of this CPU. */ static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf) { const struct cpuid_reg cpuid = x86_feature_cpuid(leaf * 32); struct kvm_cpuid_entry2 entry; reverse_cpuid_check(leaf); cpuid_count(cpuid.function, cpuid.index, &entry.eax, &entry.ebx, &entry.ecx, &entry.edx); kvm_cpu_caps[leaf] &= *__cpuid_entry_get_reg(&entry, cpuid.reg); } static __always_inline void kvm_cpu_cap_init_kvm_defined(enum kvm_only_cpuid_leafs leaf, u32 mask) { /* Use kvm_cpu_cap_mask for leafs that aren't KVM-only. */ BUILD_BUG_ON(leaf < NCAPINTS); kvm_cpu_caps[leaf] = mask; __kvm_cpu_cap_mask(leaf); } static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) { /* Use kvm_cpu_cap_init_kvm_defined for KVM-only leafs. */ BUILD_BUG_ON(leaf >= NCAPINTS); kvm_cpu_caps[leaf] &= mask; __kvm_cpu_cap_mask(leaf); } void kvm_set_cpu_caps(void) { #ifdef CONFIG_X86_64 unsigned int f_gbpages = F(GBPAGES); unsigned int f_lm = F(LM); unsigned int f_xfd = F(XFD); #else unsigned int f_gbpages = 0; unsigned int f_lm = 0; unsigned int f_xfd = 0; #endif memset(kvm_cpu_caps, 0, sizeof(kvm_cpu_caps)); BUILD_BUG_ON(sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps)) > sizeof(boot_cpu_data.x86_capability)); memcpy(&kvm_cpu_caps, &boot_cpu_data.x86_capability, sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps))); kvm_cpu_cap_mask(CPUID_1_ECX, /* * NOTE: MONITOR (and MWAIT) are emulated as NOP, but *not* * advertised to guests via CPUID! */ F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | 0 /* DS-CPL, VMX, SMX, EST */ | 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | F(FMA) | F(CX16) | 0 /* xTPR Update */ | F(PDCM) | F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) | F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | F(F16C) | F(RDRAND) ); /* KVM emulates x2apic in software irrespective of host support. */ kvm_cpu_cap_set(X86_FEATURE_X2APIC); kvm_cpu_cap_mask(CPUID_1_EDX, F(FPU) | F(VME) | F(DE) | F(PSE) | F(TSC) | F(MSR) | F(PAE) | F(MCE) | F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) | 0 /* Reserved, DS, ACPI */ | F(MMX) | F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | 0 /* HTT, TM, Reserved, PBE */ ); kvm_cpu_cap_mask(CPUID_7_0_EBX, F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | F(FDP_EXCPTN_ONLY) | F(SMEP) | F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | F(ZERO_FCS_FDS) | 0 /*MPX*/ | F(AVX512F) | F(AVX512DQ) | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512IFMA) | F(CLFLUSHOPT) | F(CLWB) | 0 /*INTEL_PT*/ | F(AVX512PF) | F(AVX512ER) | F(AVX512CD) | F(SHA_NI) | F(AVX512BW) | F(AVX512VL)); kvm_cpu_cap_mask(CPUID_7_ECX, F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/ | F(SGX_LC) | F(BUS_LOCK_DETECT) ); /* Set LA57 based on hardware capability. */ if (cpuid_ecx(7) & F(LA57)) kvm_cpu_cap_set(X86_FEATURE_LA57); /* * PKU not yet implemented for shadow paging and requires OSPKE * to be set on the host. Clear it if that is not the case */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) kvm_cpu_cap_clear(X86_FEATURE_PKU); kvm_cpu_cap_mask(CPUID_7_EDX, F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) | F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16) | F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) | F(FLUSH_L1D) ); /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ kvm_cpu_cap_set(X86_FEATURE_TSC_ADJUST); kvm_cpu_cap_set(X86_FEATURE_ARCH_CAPABILITIES); if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS)) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL); if (boot_cpu_has(X86_FEATURE_STIBP)) kvm_cpu_cap_set(X86_FEATURE_INTEL_STIBP); if (boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); kvm_cpu_cap_mask(CPUID_7_1_EAX, F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(FZRM) | F(FSRS) | F(FSRC) | F(AMX_FP16) | F(AVX_IFMA) | F(LAM) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) | F(AMX_COMPLEX) | F(AVX10) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) | F(BHI_CTRL) | F(MCDT_NO) ); kvm_cpu_cap_mask(CPUID_D_1_EAX, F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd ); kvm_cpu_cap_init_kvm_defined(CPUID_12_EAX, SF(SGX1) | SF(SGX2) | SF(SGX_EDECCSSA) ); kvm_cpu_cap_init_kvm_defined(CPUID_24_0_EBX, F(AVX10_128) | F(AVX10_256) | F(AVX10_512) ); kvm_cpu_cap_mask(CPUID_8000_0001_ECX, F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | F(TOPOEXT) | 0 /* PERFCTR_CORE */ ); kvm_cpu_cap_mask(CPUID_8000_0001_EDX, F(FPU) | F(VME) | F(DE) | F(PSE) | F(TSC) | F(MSR) | F(PAE) | F(MCE) | F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | F(PAT) | F(PSE36) | 0 /* Reserved */ | F(NX) | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) | 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW) ); if (!tdp_enabled && IS_ENABLED(CONFIG_X86_64)) kvm_cpu_cap_set(X86_FEATURE_GBPAGES); kvm_cpu_cap_init_kvm_defined(CPUID_8000_0007_EDX, SF(CONSTANT_TSC) ); kvm_cpu_cap_mask(CPUID_8000_0008_EBX, F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) | F(AMD_PSFD) ); /* * AMD has separate bits for each SPEC_CTRL bit. * arch/x86/kernel/cpu/bugs.c is kind enough to * record that in cpufeatures so use them. */ if (boot_cpu_has(X86_FEATURE_IBPB)) kvm_cpu_cap_set(X86_FEATURE_AMD_IBPB); if (boot_cpu_has(X86_FEATURE_IBRS)) kvm_cpu_cap_set(X86_FEATURE_AMD_IBRS); if (boot_cpu_has(X86_FEATURE_STIBP)) kvm_cpu_cap_set(X86_FEATURE_AMD_STIBP); if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) kvm_cpu_cap_set(X86_FEATURE_AMD_SSBD); if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) kvm_cpu_cap_set(X86_FEATURE_AMD_SSB_NO); /* * The preference is to use SPEC CTRL MSR instead of the * VIRT_SPEC MSR. */ if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) && !boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); /* * Hide all SVM features by default, SVM will set the cap bits for * features it emulates and/or exposes for L1. */ kvm_cpu_cap_mask(CPUID_8000_000A_EDX, 0); kvm_cpu_cap_mask(CPUID_8000_001F_EAX, 0 /* SME */ | 0 /* SEV */ | 0 /* VM_PAGE_FLUSH */ | 0 /* SEV_ES */ | F(SME_COHERENT)); kvm_cpu_cap_mask(CPUID_8000_0021_EAX, F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ | F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ | F(WRMSR_XX_BASE_NS) ); kvm_cpu_cap_check_and_set(X86_FEATURE_SBPB); kvm_cpu_cap_check_and_set(X86_FEATURE_IBPB_BRTYPE); kvm_cpu_cap_check_and_set(X86_FEATURE_SRSO_NO); kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, F(PERFMON_V2) ); /* * Synthesize "LFENCE is serializing" into the AMD-defined entry in * KVM's supported CPUID if the feature is reported as supported by the * kernel. LFENCE_RDTSC was a Linux-defined synthetic feature long * before AMD joined the bandwagon, e.g. LFENCE is serializing on most * CPUs that support SSE2. On CPUs that don't support AMD's leaf, * kvm_cpu_cap_mask() will unfortunately drop the flag due to ANDing * the mask with the raw host CPUID, and reporting support in AMD's * leaf can make it easier for userspace to detect the feature. */ if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) kvm_cpu_cap_set(X86_FEATURE_LFENCE_RDTSC); if (!static_cpu_has_bug(X86_BUG_NULL_SEG)) kvm_cpu_cap_set(X86_FEATURE_NULL_SEL_CLR_BASE); kvm_cpu_cap_set(X86_FEATURE_NO_SMM_CTL_MSR); kvm_cpu_cap_mask(CPUID_C000_0001_EDX, F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | F(PMM) | F(PMM_EN) ); /* * Hide RDTSCP and RDPID if either feature is reported as supported but * probing MSR_TSC_AUX failed. This is purely a sanity check and * should never happen, but the guest will likely crash if RDTSCP or * RDPID is misreported, and KVM has botched MSR_TSC_AUX emulation in * the past. For example, the sanity check may fire if this instance of * KVM is running as L1 on top of an older, broken KVM. */ if (WARN_ON((kvm_cpu_cap_has(X86_FEATURE_RDTSCP) || kvm_cpu_cap_has(X86_FEATURE_RDPID)) && !kvm_is_supported_user_return_msr(MSR_TSC_AUX))) { kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); kvm_cpu_cap_clear(X86_FEATURE_RDPID); } } EXPORT_SYMBOL_GPL(kvm_set_cpu_caps); struct kvm_cpuid_array { struct kvm_cpuid_entry2 *entries; int maxnent; int nent; }; static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array) { if (array->nent >= array->maxnent) return NULL; return &array->entries[array->nent++]; } static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, u32 function, u32 index) { struct kvm_cpuid_entry2 *entry = get_next_cpuid(array); if (!entry) return NULL; memset(entry, 0, sizeof(*entry)); entry->function = function; entry->index = index; switch (function & 0xC0000000) { case 0x40000000: /* Hypervisor leaves are always synthesized by __do_cpuid_func. */ return entry; case 0x80000000: /* * 0x80000021 is sometimes synthesized by __do_cpuid_func, which * would result in out-of-bounds calls to do_host_cpuid. */ { static int max_cpuid_80000000; if (!READ_ONCE(max_cpuid_80000000)) WRITE_ONCE(max_cpuid_80000000, cpuid_eax(0x80000000)); if (function > READ_ONCE(max_cpuid_80000000)) return entry; } break; default: break; } cpuid_count(entry->function, entry->index, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); if (cpuid_function_is_indexed(function)) entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; return entry; } static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) { struct kvm_cpuid_entry2 *entry; if (array->nent >= array->maxnent) return -E2BIG; entry = &array->entries[array->nent]; entry->function = func; entry->index = 0; entry->flags = 0; switch (func) { case 0: entry->eax = 7; ++array->nent; break; case 1: entry->ecx = F(MOVBE); ++array->nent; break; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; entry->eax = 0; if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) entry->ecx = F(RDPID); ++array->nent; break; default: break; } return 0; } static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) { struct kvm_cpuid_entry2 *entry; int r, i, max_idx; /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); r = -E2BIG; entry = do_host_cpuid(array, function, 0); if (!entry) goto out; switch (function) { case 0: /* Limited to the highest leaf implemented in KVM. */ entry->eax = min(entry->eax, 0x24U); break; case 1: cpuid_entry_override(entry, CPUID_1_EDX); cpuid_entry_override(entry, CPUID_1_ECX); break; case 2: /* * On ancient CPUs, function 2 entries are STATEFUL. That is, * CPUID(function=2, index=0) may return different results each * time, with the least-significant byte in EAX enumerating the * number of times software should do CPUID(2, 0). * * Modern CPUs, i.e. every CPU KVM has *ever* run on are less * idiotic. Intel's SDM states that EAX & 0xff "will always * return 01H. Software should ignore this value and not * interpret it as an informational descriptor", while AMD's * APM states that CPUID(2) is reserved. * * WARN if a frankenstein CPU that supports virtualization and * a stateful CPUID.0x2 is encountered. */ WARN_ON_ONCE((entry->eax & 0xff) > 1); break; /* functions 4 and 0x8000001d have additional index. */ case 4: case 0x8000001d: /* * Read entries until the cache type in the previous entry is * zero, i.e. indicates an invalid entry. */ for (i = 1; entry->eax & 0x1f; ++i) { entry = do_host_cpuid(array, function, i); if (!entry) goto out; } break; case 6: /* Thermal management */ entry->eax = 0x4; /* allow ARAT */ entry->ebx = 0; entry->ecx = 0; entry->edx = 0; break; /* function 7 has additional index. */ case 7: max_idx = entry->eax = min(entry->eax, 2u); cpuid_entry_override(entry, CPUID_7_0_EBX); cpuid_entry_override(entry, CPUID_7_ECX); cpuid_entry_override(entry, CPUID_7_EDX); /* KVM only supports up to 0x7.2, capped above via min(). */ if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; cpuid_entry_override(entry, CPUID_7_1_EAX); cpuid_entry_override(entry, CPUID_7_1_EDX); entry->ebx = 0; entry->ecx = 0; } if (max_idx >= 2) { entry = do_host_cpuid(array, function, 2); if (!entry) goto out; cpuid_entry_override(entry, CPUID_7_2_EDX); entry->ecx = 0; entry->ebx = 0; entry->eax = 0; } break; case 0xa: { /* Architectural Performance Monitoring */ union cpuid10_eax eax; union cpuid10_edx edx; if (!enable_pmu || !static_cpu_has(X86_FEATURE_ARCH_PERFMON)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } eax.split.version_id = kvm_pmu_cap.version; eax.split.num_counters = kvm_pmu_cap.num_counters_gp; eax.split.bit_width = kvm_pmu_cap.bit_width_gp; eax.split.mask_length = kvm_pmu_cap.events_mask_len; edx.split.num_counters_fixed = kvm_pmu_cap.num_counters_fixed; edx.split.bit_width_fixed = kvm_pmu_cap.bit_width_fixed; if (kvm_pmu_cap.version) edx.split.anythread_deprecated = 1; edx.split.reserved1 = 0; edx.split.reserved2 = 0; entry->eax = eax.full; entry->ebx = kvm_pmu_cap.events_mask; entry->ecx = 0; entry->edx = edx.full; break; } case 0x1f: case 0xb: /* * No topology; a valid topology is indicated by the presence * of subleaf 1. */ entry->eax = entry->ebx = entry->ecx = 0; break; case 0xd: { u64 permitted_xcr0 = kvm_get_filtered_xcr0(); u64 permitted_xss = kvm_caps.supported_xss; entry->eax &= permitted_xcr0; entry->ebx = xstate_required_size(permitted_xcr0, false); entry->ecx = entry->ebx; entry->edx &= permitted_xcr0 >> 32; if (!permitted_xcr0) break; entry = do_host_cpuid(array, function, 1); if (!entry) goto out; cpuid_entry_override(entry, CPUID_D_1_EAX); if (entry->eax & (F(XSAVES)|F(XSAVEC))) entry->ebx = xstate_required_size(permitted_xcr0 | permitted_xss, true); else { WARN_ON_ONCE(permitted_xss != 0); entry->ebx = 0; } entry->ecx &= permitted_xss; entry->edx &= permitted_xss >> 32; for (i = 2; i < 64; ++i) { bool s_state; if (permitted_xcr0 & BIT_ULL(i)) s_state = false; else if (permitted_xss & BIT_ULL(i)) s_state = true; else continue; entry = do_host_cpuid(array, function, i); if (!entry) goto out; /* * The supported check above should have filtered out * invalid sub-leafs. Only valid sub-leafs should * reach this point, and they should have a non-zero * save state size. Furthermore, check whether the * processor agrees with permitted_xcr0/permitted_xss * on whether this is an XCR0- or IA32_XSS-managed area. */ if (WARN_ON_ONCE(!entry->eax || (entry->ecx & 0x1) != s_state)) { --array->nent; continue; } if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) entry->ecx &= ~BIT_ULL(2); entry->edx = 0; } break; } case 0x12: /* Intel SGX */ if (!kvm_cpu_cap_has(X86_FEATURE_SGX)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } /* * Index 0: Sub-features, MISCSELECT (a.k.a extended features) * and max enclave sizes. The SGX sub-features and MISCSELECT * are restricted by kernel and KVM capabilities (like most * feature flags), while enclave size is unrestricted. */ cpuid_entry_override(entry, CPUID_12_EAX); entry->ebx &= SGX_MISC_EXINFO; entry = do_host_cpuid(array, function, 1); if (!entry) goto out; /* * Index 1: SECS.ATTRIBUTES. ATTRIBUTES are restricted a la * feature flags. Advertise all supported flags, including * privileged attributes that require explicit opt-in from * userspace. ATTRIBUTES.XFRM is not adjusted as userspace is * expected to derive it from supported XCR0. */ entry->eax &= SGX_ATTR_PRIV_MASK | SGX_ATTR_UNPRIV_MASK; entry->ebx &= 0; break; /* Intel PT */ case 0x14: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } for (i = 1, max_idx = entry->eax; i <= max_idx; ++i) { if (!do_host_cpuid(array, function, i)) goto out; } break; /* Intel AMX TILE */ case 0x1d: if (!kvm_cpu_cap_has(X86_FEATURE_AMX_TILE)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } for (i = 1, max_idx = entry->eax; i <= max_idx; ++i) { if (!do_host_cpuid(array, function, i)) goto out; } break; case 0x1e: /* TMUL information */ if (!kvm_cpu_cap_has(X86_FEATURE_AMX_TILE)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } break; case 0x24: { u8 avx10_version; if (!kvm_cpu_cap_has(X86_FEATURE_AVX10)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } /* * The AVX10 version is encoded in EBX[7:0]. Note, the version * is guaranteed to be >=1 if AVX10 is supported. Note #2, the * version needs to be captured before overriding EBX features! */ avx10_version = min_t(u8, entry->ebx & 0xff, 1); cpuid_entry_override(entry, CPUID_24_0_EBX); entry->ebx |= avx10_version; entry->eax = 0; entry->ecx = 0; entry->edx = 0; break; } case KVM_CPUID_SIGNATURE: { const u32 *sigptr = (const u32 *)KVM_SIGNATURE; entry->eax = KVM_CPUID_FEATURES; entry->ebx = sigptr[0]; entry->ecx = sigptr[1]; entry->edx = sigptr[2]; break; } case KVM_CPUID_FEATURES: entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) | (1 << KVM_FEATURE_NOP_IO_DELAY) | (1 << KVM_FEATURE_CLOCKSOURCE2) | (1 << KVM_FEATURE_ASYNC_PF) | (1 << KVM_FEATURE_PV_EOI) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) | (1 << KVM_FEATURE_PV_UNHALT) | (1 << KVM_FEATURE_PV_TLB_FLUSH) | (1 << KVM_FEATURE_ASYNC_PF_VMEXIT) | (1 << KVM_FEATURE_PV_SEND_IPI) | (1 << KVM_FEATURE_POLL_CONTROL) | (1 << KVM_FEATURE_PV_SCHED_YIELD) | (1 << KVM_FEATURE_ASYNC_PF_INT); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); entry->ebx = 0; entry->ecx = 0; entry->edx = 0; break; case 0x80000000: entry->eax = min(entry->eax, 0x80000022); /* * Serializing LFENCE is reported in a multitude of ways, and * NullSegClearsBase is not reported in CPUID on Zen2; help * userspace by providing the CPUID leaf ourselves. * * However, only do it if the host has CPUID leaf 0x8000001d. * QEMU thinks that it can query the host blindly for that * CPUID leaf if KVM reports that it supports 0x8000001d or * above. The processor merrily returns values from the * highest Intel leaf which QEMU tries to use as the guest's * 0x8000001d. Even worse, this can result in an infinite * loop if said highest leaf has no subleaves indexed by ECX. */ if (entry->eax >= 0x8000001d && (static_cpu_has(X86_FEATURE_LFENCE_RDTSC) || !static_cpu_has_bug(X86_BUG_NULL_SEG))) entry->eax = max(entry->eax, 0x80000021); break; case 0x80000001: entry->ebx &= ~GENMASK(27, 16); cpuid_entry_override(entry, CPUID_8000_0001_EDX); cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; case 0x80000005: /* Pass host L1 cache and TLB info. */ break; case 0x80000006: /* Drop reserved bits, pass host L2 cache and TLB info. */ entry->edx &= ~GENMASK(17, 16); break; case 0x80000007: /* Advanced power management */ cpuid_entry_override(entry, CPUID_8000_0007_EDX); /* mask against host */ entry->edx &= boot_cpu_data.x86_power; entry->eax = entry->ebx = entry->ecx = 0; break; case 0x80000008: { /* * GuestPhysAddrSize (EAX[23:16]) is intended for software * use. * * KVM's ABI is to report the effective MAXPHYADDR for the * guest in PhysAddrSize (phys_as), and the maximum * *addressable* GPA in GuestPhysAddrSize (g_phys_as). * * GuestPhysAddrSize is valid if and only if TDP is enabled, * in which case the max GPA that can be addressed by KVM may * be less than the max GPA that can be legally generated by * the guest, e.g. if MAXPHYADDR>48 but the CPU doesn't * support 5-level TDP. */ unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U); unsigned int phys_as, g_phys_as; /* * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as * the guest operates in the same PA space as the host, i.e. * reductions in MAXPHYADDR for memory encryption affect shadow * paging, too. * * If TDP is enabled, use the raw bare metal MAXPHYADDR as * reductions to the HPAs do not affect GPAs. The max * addressable GPA is the same as the max effective GPA, except * that it's capped at 48 bits if 5-level TDP isn't supported * (hardware processes bits 51:48 only when walking the fifth * level page table). */ if (!tdp_enabled) { phys_as = boot_cpu_data.x86_phys_bits; g_phys_as = 0; } else { phys_as = entry->eax & 0xff; g_phys_as = phys_as; if (kvm_mmu_get_max_tdp_level() < 5) g_phys_as = min(g_phys_as, 48); } entry->eax = phys_as | (virt_as << 8) | (g_phys_as << 16); entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); break; } case 0x8000000A: if (!kvm_cpu_cap_has(X86_FEATURE_SVM)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } entry->eax = 1; /* SVM revision 1 */ entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper ASID emulation to nested SVM */ entry->ecx = 0; /* Reserved */ cpuid_entry_override(entry, CPUID_8000_000A_EDX); break; case 0x80000019: entry->ecx = entry->edx = 0; break; case 0x8000001a: entry->eax &= GENMASK(2, 0); entry->ebx = entry->ecx = entry->edx = 0; break; case 0x8000001e: /* Do not return host topology information. */ entry->eax = entry->ebx = entry->ecx = 0; entry->edx = 0; /* reserved */ break; case 0x8000001F: if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; } else { cpuid_entry_override(entry, CPUID_8000_001F_EAX); /* Clear NumVMPL since KVM does not support VMPL. */ entry->ebx &= ~GENMASK(31, 12); /* * Enumerate '0' for "PA bits reduction", the adjusted * MAXPHYADDR is enumerated directly (see 0x80000008). */ entry->ebx &= ~GENMASK(11, 6); } break; case 0x80000020: entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; case 0x80000021: entry->ebx = entry->ecx = entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0021_EAX); break; /* AMD Extended Performance Monitoring and Debug */ case 0x80000022: { union cpuid_0x80000022_ebx ebx; entry->ecx = entry->edx = 0; if (!enable_pmu || !kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) { entry->eax = entry->ebx; break; } cpuid_entry_override(entry, CPUID_8000_0022_EAX); if (kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) ebx.split.num_core_pmc = kvm_pmu_cap.num_counters_gp; else if (kvm_cpu_cap_has(X86_FEATURE_PERFCTR_CORE)) ebx.split.num_core_pmc = AMD64_NUM_COUNTERS_CORE; else ebx.split.num_core_pmc = AMD64_NUM_COUNTERS; entry->ebx = ebx.full; break; } /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: /*Just support up to 0xC0000004 now*/ entry->eax = min(entry->eax, 0xC0000004); break; case 0xC0000001: cpuid_entry_override(entry, CPUID_C000_0001_EDX); break; case 3: /* Processor serial number */ case 5: /* MONITOR/MWAIT */ case 0xC0000002: case 0xC0000003: case 0xC0000004: default: entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } r = 0; out: put_cpu(); return r; } static int do_cpuid_func(struct kvm_cpuid_array *array, u32 func, unsigned int type) { if (type == KVM_GET_EMULATED_CPUID) return __do_cpuid_func_emulated(array, func); return __do_cpuid_func(array, func); } #define CENTAUR_CPUID_SIGNATURE 0xC0000000 static int get_cpuid_func(struct kvm_cpuid_array *array, u32 func, unsigned int type) { u32 limit; int r; if (func == CENTAUR_CPUID_SIGNATURE && boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR) return 0; r = do_cpuid_func(array, func, type); if (r) return r; limit = array->entries[array->nent - 1].eax; for (func = func + 1; func <= limit; ++func) { r = do_cpuid_func(array, func, type); if (r) break; } return r; } static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries, __u32 num_entries, unsigned int ioctl_type) { int i; __u32 pad[3]; if (ioctl_type != KVM_GET_EMULATED_CPUID) return false; /* * We want to make sure that ->padding is being passed clean from * userspace in case we want to use it for something in the future. * * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we * have to give ourselves satisfied only with the emulated side. /me * sheds a tear. */ for (i = 0; i < num_entries; i++) { if (copy_from_user(pad, entries[i].padding, sizeof(pad))) return true; if (pad[0] || pad[1] || pad[2]) return true; } return false; } int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries, unsigned int type) { static const u32 funcs[] = { 0, 0x80000000, CENTAUR_CPUID_SIGNATURE, KVM_CPUID_SIGNATURE, }; struct kvm_cpuid_array array = { .nent = 0, }; int r, i; if (cpuid->nent < 1) return -E2BIG; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) cpuid->nent = KVM_MAX_CPUID_ENTRIES; if (sanity_check_entries(entries, cpuid->nent, type)) return -EINVAL; array.entries = kvcalloc(cpuid->nent, sizeof(struct kvm_cpuid_entry2), GFP_KERNEL); if (!array.entries) return -ENOMEM; array.maxnent = cpuid->nent; for (i = 0; i < ARRAY_SIZE(funcs); i++) { r = get_cpuid_func(&array, funcs[i], type); if (r) goto out_free; } cpuid->nent = array.nent; if (copy_to_user(entries, array.entries, array.nent * sizeof(struct kvm_cpuid_entry2))) r = -EFAULT; out_free: kvfree(array.entries); return r; } struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, u32 function, u32 index) { return cpuid_entry2_find(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, function, index); } EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry_index); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function) { return cpuid_entry2_find(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, function, KVM_CPUID_INDEX_NOT_SIGNIFICANT); } EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); /* * Intel CPUID semantics treats any query for an out-of-range leaf as if the * highest basic leaf (i.e. CPUID.0H:EAX) were requested. AMD CPUID semantics * returns all zeroes for any undefined leaf, whether or not the leaf is in * range. Centaur/VIA follows Intel semantics. * * A leaf is considered out-of-range if its function is higher than the maximum * supported leaf of its associated class or if its associated class does not * exist. * * There are three primary classes to be considered, with their respective * ranges described as "<base> - <top>[,<base2> - <top2>] inclusive. A primary * class exists if a guest CPUID entry for its <base> leaf exists. For a given * class, CPUID.<base>.EAX contains the max supported leaf for the class. * * - Basic: 0x00000000 - 0x3fffffff, 0x50000000 - 0x7fffffff * - Hypervisor: 0x40000000 - 0x4fffffff * - Extended: 0x80000000 - 0xbfffffff * - Centaur: 0xc0000000 - 0xcfffffff * * The Hypervisor class is further subdivided into sub-classes that each act as * their own independent class associated with a 0x100 byte range. E.g. if Qemu * is advertising support for both HyperV and KVM, the resulting Hypervisor * CPUID sub-classes are: * * - HyperV: 0x40000000 - 0x400000ff * - KVM: 0x40000100 - 0x400001ff */ static struct kvm_cpuid_entry2 * get_out_of_range_cpuid_entry(struct kvm_vcpu *vcpu, u32 *fn_ptr, u32 index) { struct kvm_cpuid_entry2 *basic, *class; u32 function = *fn_ptr; basic = kvm_find_cpuid_entry(vcpu, 0); if (!basic) return NULL; if (is_guest_vendor_amd(basic->ebx, basic->ecx, basic->edx) || is_guest_vendor_hygon(basic->ebx, basic->ecx, basic->edx)) return NULL; if (function >= 0x40000000 && function <= 0x4fffffff) class = kvm_find_cpuid_entry(vcpu, function & 0xffffff00); else if (function >= 0xc0000000) class = kvm_find_cpuid_entry(vcpu, 0xc0000000); else class = kvm_find_cpuid_entry(vcpu, function & 0x80000000); if (class && function <= class->eax) return NULL; /* * Leaf specific adjustments are also applied when redirecting to the * max basic entry, e.g. if the max basic leaf is 0xb but there is no * entry for CPUID.0xb.index (see below), then the output value for EDX * needs to be pulled from CPUID.0xb.1. */ *fn_ptr = basic->eax; /* * The class does not exist or the requested function is out of range; * the effective CPUID entry is the max basic leaf. Note, the index of * the original requested leaf is observed! */ return kvm_find_cpuid_entry_index(vcpu, basic->eax, index); } bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only) { u32 orig_function = *eax, function = *eax, index = *ecx; struct kvm_cpuid_entry2 *entry; bool exact, used_max_basic = false; entry = kvm_find_cpuid_entry_index(vcpu, function, index); exact = !!entry; if (!entry && !exact_only) { entry = get_out_of_range_cpuid_entry(vcpu, &function, index); used_max_basic = !!entry; } if (entry) { *eax = entry->eax; *ebx = entry->ebx; *ecx = entry->ecx; *edx = entry->edx; if (function == 7 && index == 0) { u64 data; if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) && (data & TSX_CTRL_CPUID_CLEAR)) *ebx &= ~(F(RTM) | F(HLE)); } else if (function == 0x80000007) { if (kvm_hv_invtsc_suppressed(vcpu)) *edx &= ~SF(CONSTANT_TSC); } } else { *eax = *ebx = *ecx = *edx = 0; /* * When leaf 0BH or 1FH is defined, CL is pass-through * and EDX is always the x2APIC ID, even for undefined * subleaves. Index 1 will exist iff the leaf is * implemented, so we pass through CL iff leaf 1 * exists. EDX can be copied from any existing index. */ if (function == 0xb || function == 0x1f) { entry = kvm_find_cpuid_entry_index(vcpu, function, 1); if (entry) { *ecx = index & 0xff; *edx = entry->edx; } } } trace_kvm_cpuid(orig_function, index, *eax, *ebx, *ecx, *edx, exact, used_max_basic); return exact; } EXPORT_SYMBOL_GPL(kvm_cpuid); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu) { u32 eax, ebx, ecx, edx; if (cpuid_fault_enabled(vcpu) && !kvm_require_cpl(vcpu, 0)) return 1; eax = kvm_rax_read(vcpu); ecx = kvm_rcx_read(vcpu); kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, false); kvm_rax_write(vcpu, eax); kvm_rbx_write(vcpu, ebx); kvm_rcx_write(vcpu, ecx); kvm_rdx_write(vcpu, edx); return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); |
| 3 3 3 3 39 39 39 39 39 39 4 3 3 4 2 1 12 12 12 12 12 12 12 12 12 12 12 12 12 12 39 39 39 39 39 39 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/seq_file.h> #include <net/protocol.h> #include <net/netfilter/nf_log.h> #include "nf_internals.h" /* Internal logging interface, which relies on the real LOG target modules */ #define NFLOGGER_NAME_LEN 64 int sysctl_nf_log_all_netns __read_mostly; EXPORT_SYMBOL(sysctl_nf_log_all_netns); static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly; static DEFINE_MUTEX(nf_log_mutex); #define nft_log_dereference(logger) \ rcu_dereference_protected(logger, lockdep_is_held(&nf_log_mutex)) static struct nf_logger *__find_logger(int pf, const char *str_logger) { struct nf_logger *log; int i; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { log = nft_log_dereference(loggers[pf][i]); if (!log) continue; if (!strncasecmp(str_logger, log->name, strlen(log->name))) return log; } return NULL; } int nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger) { const struct nf_logger *log; if (pf == NFPROTO_UNSPEC || pf >= ARRAY_SIZE(net->nf.nf_loggers)) return -EOPNOTSUPP; mutex_lock(&nf_log_mutex); log = nft_log_dereference(net->nf.nf_loggers[pf]); if (log == NULL) rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } EXPORT_SYMBOL(nf_log_set); void nf_log_unset(struct net *net, const struct nf_logger *logger) { int i; const struct nf_logger *log; mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) { log = nft_log_dereference(net->nf.nf_loggers[i]); if (log == logger) RCU_INIT_POINTER(net->nf.nf_loggers[i], NULL); } mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unset); /* return EEXIST if the same logger is registered, 0 on success. */ int nf_log_register(u_int8_t pf, struct nf_logger *logger) { int i; int ret = 0; if (pf >= ARRAY_SIZE(init_net.nf.nf_loggers)) return -EINVAL; mutex_lock(&nf_log_mutex); if (pf == NFPROTO_UNSPEC) { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { if (rcu_access_pointer(loggers[i][logger->type])) { ret = -EEXIST; goto unlock; } } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) rcu_assign_pointer(loggers[i][logger->type], logger); } else { if (rcu_access_pointer(loggers[pf][logger->type])) { ret = -EEXIST; goto unlock; } rcu_assign_pointer(loggers[pf][logger->type], logger); } unlock: mutex_unlock(&nf_log_mutex); return ret; } EXPORT_SYMBOL(nf_log_register); void nf_log_unregister(struct nf_logger *logger) { const struct nf_logger *log; int i; mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) { log = nft_log_dereference(loggers[i][logger->type]); if (log == logger) RCU_INIT_POINTER(loggers[i][logger->type], NULL); } mutex_unlock(&nf_log_mutex); synchronize_rcu(); } EXPORT_SYMBOL(nf_log_unregister); int nf_log_bind_pf(struct net *net, u_int8_t pf, const struct nf_logger *logger) { if (pf >= ARRAY_SIZE(net->nf.nf_loggers)) return -EINVAL; mutex_lock(&nf_log_mutex); if (__find_logger(pf, logger->name) == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; } rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } EXPORT_SYMBOL(nf_log_bind_pf); void nf_log_unbind_pf(struct net *net, u_int8_t pf) { if (pf >= ARRAY_SIZE(net->nf.nf_loggers)) return; mutex_lock(&nf_log_mutex); RCU_INIT_POINTER(net->nf.nf_loggers[pf], NULL); mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unbind_pf); int nf_logger_find_get(int pf, enum nf_log_type type) { struct nf_logger *logger; int ret = -ENOENT; if (pf >= ARRAY_SIZE(loggers)) return -EINVAL; if (type >= NF_LOG_TYPE_MAX) return -EINVAL; if (pf == NFPROTO_INET) { ret = nf_logger_find_get(NFPROTO_IPV4, type); if (ret < 0) return ret; ret = nf_logger_find_get(NFPROTO_IPV6, type); if (ret < 0) { nf_logger_put(NFPROTO_IPV4, type); return ret; } return 0; } rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (logger == NULL) goto out; if (try_module_get(logger->me)) ret = 0; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(nf_logger_find_get); void nf_logger_put(int pf, enum nf_log_type type) { struct nf_logger *logger; if (pf == NFPROTO_INET) { nf_logger_put(NFPROTO_IPV4, type); nf_logger_put(NFPROTO_IPV6, type); return; } rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (!logger) WARN_ON_ONCE(1); else module_put(logger->me); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_logger_put); void nf_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *loginfo, const char *fmt, ...) { va_list args; char prefix[NF_LOG_PREFIXLEN]; const struct nf_logger *logger; rcu_read_lock(); if (loginfo != NULL) logger = rcu_dereference(loggers[pf][loginfo->type]); else logger = rcu_dereference(net->nf.nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); } rcu_read_unlock(); } EXPORT_SYMBOL(nf_log_packet); void nf_log_trace(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *loginfo, const char *fmt, ...) { va_list args; char prefix[NF_LOG_PREFIXLEN]; const struct nf_logger *logger; rcu_read_lock(); logger = rcu_dereference(net->nf.nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); } rcu_read_unlock(); } EXPORT_SYMBOL(nf_log_trace); #define S_SIZE (1024 - (sizeof(unsigned int) + 1)) struct nf_log_buf { unsigned int count; char buf[S_SIZE + 1]; }; static struct nf_log_buf emergency, *emergency_ptr = &emergency; __printf(2, 3) int nf_log_buf_add(struct nf_log_buf *m, const char *f, ...) { va_list args; int len; if (likely(m->count < S_SIZE)) { va_start(args, f); len = vsnprintf(m->buf + m->count, S_SIZE - m->count, f, args); va_end(args); if (likely(m->count + len < S_SIZE)) { m->count += len; return 0; } } m->count = S_SIZE; printk_once(KERN_ERR KBUILD_MODNAME " please increase S_SIZE\n"); return -1; } EXPORT_SYMBOL_GPL(nf_log_buf_add); struct nf_log_buf *nf_log_buf_open(void) { struct nf_log_buf *m = kmalloc(sizeof(*m), GFP_ATOMIC); if (unlikely(!m)) { local_bh_disable(); do { m = xchg(&emergency_ptr, NULL); } while (!m); } m->count = 0; return m; } EXPORT_SYMBOL_GPL(nf_log_buf_open); void nf_log_buf_close(struct nf_log_buf *m) { m->buf[m->count] = 0; printk("%s\n", m->buf); if (likely(m != &emergency)) kfree(m); else { emergency_ptr = m; local_bh_enable(); } } EXPORT_SYMBOL_GPL(nf_log_buf_close); #ifdef CONFIG_PROC_FS static void *seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); mutex_lock(&nf_log_mutex); if (*pos >= ARRAY_SIZE(net->nf.nf_loggers)) return NULL; return pos; } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { struct net *net = seq_file_net(s); (*pos)++; if (*pos >= ARRAY_SIZE(net->nf.nf_loggers)) return NULL; return pos; } static void seq_stop(struct seq_file *s, void *v) { mutex_unlock(&nf_log_mutex); } static int seq_show(struct seq_file *s, void *v) { loff_t *pos = v; const struct nf_logger *logger; int i; struct net *net = seq_file_net(s); logger = nft_log_dereference(net->nf.nf_loggers[*pos]); if (!logger) seq_printf(s, "%2lld NONE (", *pos); else seq_printf(s, "%2lld %s (", *pos, logger->name); if (seq_has_overflowed(s)) return -ENOSPC; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { if (loggers[*pos][i] == NULL) continue; logger = nft_log_dereference(loggers[*pos][i]); seq_puts(s, logger->name); if (i == 0 && loggers[*pos][i + 1] != NULL) seq_puts(s, ","); if (seq_has_overflowed(s)) return -ENOSPC; } seq_puts(s, ")\n"); if (seq_has_overflowed(s)) return -ENOSPC; return 0; } static const struct seq_operations nflog_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ #ifdef CONFIG_SYSCTL static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO]; static struct ctl_table_header *nf_log_sysctl_fhdr; static struct ctl_table nf_log_sysctl_ftable[] = { { .procname = "nf_log_all_netns", .data = &sysctl_nf_log_all_netns, .maxlen = sizeof(sysctl_nf_log_all_netns), .mode = 0644, .proc_handler = proc_dointvec, }, }; static int nf_log_proc_dostring(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; char buf[NFLOGGER_NAME_LEN]; int r = 0; int tindex = (unsigned long)table->extra1; struct net *net = table->extra2; if (write) { struct ctl_table tmp = *table; /* proc_dostring() can append to existing strings, so we need to * initialize it as an empty string. */ buf[0] = '\0'; tmp.data = buf; r = proc_dostring(&tmp, write, buffer, lenp, ppos); if (r) return r; if (!strcmp(buf, "NONE")) { nf_log_unbind_pf(net, tindex); return 0; } mutex_lock(&nf_log_mutex); logger = __find_logger(tindex, buf); if (logger == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; } rcu_assign_pointer(net->nf.nf_loggers[tindex], logger); mutex_unlock(&nf_log_mutex); } else { struct ctl_table tmp = *table; tmp.data = buf; mutex_lock(&nf_log_mutex); logger = nft_log_dereference(net->nf.nf_loggers[tindex]); if (!logger) strscpy(buf, "NONE", sizeof(buf)); else strscpy(buf, logger->name, sizeof(buf)); mutex_unlock(&nf_log_mutex); r = proc_dostring(&tmp, write, buffer, lenp, ppos); } return r; } static int netfilter_log_sysctl_init(struct net *net) { int i; struct ctl_table *table; table = nf_log_sysctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(nf_log_sysctl_table, sizeof(nf_log_sysctl_table), GFP_KERNEL); if (!table) goto err_alloc; } else { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { snprintf(nf_log_sysctl_fnames[i], 3, "%d", i); nf_log_sysctl_table[i].procname = nf_log_sysctl_fnames[i]; nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN; nf_log_sysctl_table[i].mode = 0644; nf_log_sysctl_table[i].proc_handler = nf_log_proc_dostring; nf_log_sysctl_table[i].extra1 = (void *)(unsigned long) i; } nf_log_sysctl_fhdr = register_net_sysctl(net, "net/netfilter", nf_log_sysctl_ftable); if (!nf_log_sysctl_fhdr) goto err_freg; } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) table[i].extra2 = net; net->nf.nf_log_dir_header = register_net_sysctl_sz(net, "net/netfilter/nf_log", table, ARRAY_SIZE(nf_log_sysctl_table)); if (!net->nf.nf_log_dir_header) goto err_reg; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); else unregister_net_sysctl_table(nf_log_sysctl_fhdr); err_freg: err_alloc: return -ENOMEM; } static void netfilter_log_sysctl_exit(struct net *net) { const struct ctl_table *table; table = net->nf.nf_log_dir_header->ctl_table_arg; unregister_net_sysctl_table(net->nf.nf_log_dir_header); if (!net_eq(net, &init_net)) kfree(table); else unregister_net_sysctl_table(nf_log_sysctl_fhdr); } #else static int netfilter_log_sysctl_init(struct net *net) { return 0; } static void netfilter_log_sysctl_exit(struct net *net) { } #endif /* CONFIG_SYSCTL */ static int __net_init nf_log_net_init(struct net *net) { int ret = -ENOMEM; #ifdef CONFIG_PROC_FS if (!proc_create_net("nf_log", 0444, net->nf.proc_netfilter, &nflog_seq_ops, sizeof(struct seq_net_private))) return ret; #endif ret = netfilter_log_sysctl_init(net); if (ret < 0) goto out_sysctl; return 0; out_sysctl: #ifdef CONFIG_PROC_FS remove_proc_entry("nf_log", net->nf.proc_netfilter); #endif return ret; } static void __net_exit nf_log_net_exit(struct net *net) { netfilter_log_sysctl_exit(net); #ifdef CONFIG_PROC_FS remove_proc_entry("nf_log", net->nf.proc_netfilter); #endif } static struct pernet_operations nf_log_net_ops = { .init = nf_log_net_init, .exit = nf_log_net_exit, }; int __init netfilter_log_init(void) { return register_pernet_subsys(&nf_log_net_ops); } |
| 20 70 73 72 69 13 69 70 3 3 38 38 9 9 37 8 11 37 37 37 20 20 20 7 29 10 12 21 10 6 8 6 7 28 28 37 37 37 12 12 37 37 37 37 30 37 29 29 29 29 29 30 30 30 85 85 79 84 37 37 7 37 29 29 29 29 29 19 29 19 19 29 6 6 25 2 29 13 13 11 11 11 10 9 9 9 5 5 5 10 11 11 14 14 13 14 13 12 13 11 4 14 14 30 30 30 30 29 30 30 30 30 30 14 13 12 11 11 10 12 14 30 30 30 19 19 19 15 30 30 37 37 37 31 37 29 29 29 2 27 30 14 30 30 30 17 17 17 2 2 2 17 17 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 3 4 4 1 4 4 4 4 4 4 4 4 4 4 58 49 38 38 37 37 38 37 37 37 36 7 37 36 30 1 1 1 1 53 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 | /* * net/tipc/name_table.c: TIPC name table code * * Copyright (c) 2000-2006, 2014-2018, Ericsson AB * Copyright (c) 2004-2008, 2010-2014, Wind River Systems * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include <net/sock.h> #include <linux/list_sort.h> #include <linux/rbtree_augmented.h> #include "core.h" #include "netlink.h" #include "name_table.h" #include "name_distr.h" #include "subscr.h" #include "bcast.h" #include "addr.h" #include "node.h" #include "group.h" /** * struct service_range - container for all bindings of a service range * @lower: service range lower bound * @upper: service range upper bound * @tree_node: member of service range RB tree * @max: largest 'upper' in this node subtree * @local_publ: list of identical publications made from this node * Used by closest_first lookup and multicast lookup algorithm * @all_publ: all publications identical to this one, whatever node and scope * Used by round-robin lookup algorithm */ struct service_range { u32 lower; u32 upper; struct rb_node tree_node; u32 max; struct list_head local_publ; struct list_head all_publ; }; /** * struct tipc_service - container for all published instances of a service type * @type: 32 bit 'type' value for service * @publ_cnt: increasing counter for publications in this service * @ranges: rb tree containing all service ranges for this service * @service_list: links to adjacent name ranges in hash chain * @subscriptions: list of subscriptions for this service type * @lock: spinlock controlling access to pertaining service ranges/publications * @rcu: RCU callback head used for deferred freeing */ struct tipc_service { u32 type; u32 publ_cnt; struct rb_root ranges; struct hlist_node service_list; struct list_head subscriptions; spinlock_t lock; /* Covers service range list */ struct rcu_head rcu; }; #define service_range_upper(sr) ((sr)->upper) RB_DECLARE_CALLBACKS_MAX(static, sr_callbacks, struct service_range, tree_node, u32, max, service_range_upper) #define service_range_entry(rbtree_node) \ (container_of(rbtree_node, struct service_range, tree_node)) #define service_range_overlap(sr, start, end) \ ((sr)->lower <= (end) && (sr)->upper >= (start)) /** * service_range_foreach_match - iterate over tipc service rbtree for each * range match * @sr: the service range pointer as a loop cursor * @sc: the pointer to tipc service which holds the service range rbtree * @start: beginning of the search range (end >= start) for matching * @end: end of the search range (end >= start) for matching */ #define service_range_foreach_match(sr, sc, start, end) \ for (sr = service_range_match_first((sc)->ranges.rb_node, \ start, \ end); \ sr; \ sr = service_range_match_next(&(sr)->tree_node, \ start, \ end)) /** * service_range_match_first - find first service range matching a range * @n: the root node of service range rbtree for searching * @start: beginning of the search range (end >= start) for matching * @end: end of the search range (end >= start) for matching * * Return: the leftmost service range node in the rbtree that overlaps the * specific range if any. Otherwise, returns NULL. */ static struct service_range *service_range_match_first(struct rb_node *n, u32 start, u32 end) { struct service_range *sr; struct rb_node *l, *r; /* Non overlaps in tree at all? */ if (!n || service_range_entry(n)->max < start) return NULL; while (n) { l = n->rb_left; if (l && service_range_entry(l)->max >= start) { /* A leftmost overlap range node must be one in the left * subtree. If not, it has lower > end, then nodes on * the right side cannot satisfy the condition either. */ n = l; continue; } /* No one in the left subtree can match, return if this node is * an overlap i.e. leftmost. */ sr = service_range_entry(n); if (service_range_overlap(sr, start, end)) return sr; /* Ok, try to lookup on the right side */ r = n->rb_right; if (sr->lower <= end && r && service_range_entry(r)->max >= start) { n = r; continue; } break; } return NULL; } /** * service_range_match_next - find next service range matching a range * @n: a node in service range rbtree from which the searching starts * @start: beginning of the search range (end >= start) for matching * @end: end of the search range (end >= start) for matching * * Return: the next service range node to the given node in the rbtree that * overlaps the specific range if any. Otherwise, returns NULL. */ static struct service_range *service_range_match_next(struct rb_node *n, u32 start, u32 end) { struct service_range *sr; struct rb_node *p, *r; while (n) { r = n->rb_right; if (r && service_range_entry(r)->max >= start) /* A next overlap range node must be one in the right * subtree. If not, it has lower > end, then any next * successor (- an ancestor) of this node cannot * satisfy the condition either. */ return service_range_match_first(r, start, end); /* No one in the right subtree can match, go up to find an * ancestor of this node which is parent of a left-hand child. */ while ((p = rb_parent(n)) && n == p->rb_right) n = p; if (!p) break; /* Return if this ancestor is an overlap */ sr = service_range_entry(p); if (service_range_overlap(sr, start, end)) return sr; /* Ok, try to lookup more from this ancestor */ if (sr->lower <= end) { n = p; continue; } break; } return NULL; } static int hash(int x) { return x & (TIPC_NAMETBL_SIZE - 1); } /** * tipc_publ_create - create a publication structure * @ua: the service range the user is binding to * @sk: the address of the socket that is bound * @key: publication key */ static struct publication *tipc_publ_create(struct tipc_uaddr *ua, struct tipc_socket_addr *sk, u32 key) { struct publication *p = kzalloc(sizeof(*p), GFP_ATOMIC); if (!p) return NULL; p->sr = ua->sr; p->sk = *sk; p->scope = ua->scope; p->key = key; INIT_LIST_HEAD(&p->binding_sock); INIT_LIST_HEAD(&p->binding_node); INIT_LIST_HEAD(&p->local_publ); INIT_LIST_HEAD(&p->all_publ); INIT_LIST_HEAD(&p->list); return p; } /** * tipc_service_create - create a service structure for the specified 'type' * @net: network namespace * @ua: address representing the service to be bound * * Allocates a single range structure and sets it to all 0's. */ static struct tipc_service *tipc_service_create(struct net *net, struct tipc_uaddr *ua) { struct name_table *nt = tipc_name_table(net); struct tipc_service *service; struct hlist_head *hd; service = kzalloc(sizeof(*service), GFP_ATOMIC); if (!service) { pr_warn("Service creation failed, no memory\n"); return NULL; } spin_lock_init(&service->lock); service->type = ua->sr.type; service->ranges = RB_ROOT; INIT_HLIST_NODE(&service->service_list); INIT_LIST_HEAD(&service->subscriptions); hd = &nt->services[hash(ua->sr.type)]; hlist_add_head_rcu(&service->service_list, hd); return service; } /* tipc_service_find_range - find service range matching publication parameters */ static struct service_range *tipc_service_find_range(struct tipc_service *sc, struct tipc_uaddr *ua) { struct service_range *sr; service_range_foreach_match(sr, sc, ua->sr.lower, ua->sr.upper) { /* Look for exact match */ if (sr->lower == ua->sr.lower && sr->upper == ua->sr.upper) return sr; } return NULL; } static struct service_range *tipc_service_create_range(struct tipc_service *sc, struct publication *p) { struct rb_node **n, *parent = NULL; struct service_range *sr; u32 lower = p->sr.lower; u32 upper = p->sr.upper; n = &sc->ranges.rb_node; while (*n) { parent = *n; sr = service_range_entry(parent); if (lower == sr->lower && upper == sr->upper) return sr; if (sr->max < upper) sr->max = upper; if (lower <= sr->lower) n = &parent->rb_left; else n = &parent->rb_right; } sr = kzalloc(sizeof(*sr), GFP_ATOMIC); if (!sr) return NULL; sr->lower = lower; sr->upper = upper; sr->max = upper; INIT_LIST_HEAD(&sr->local_publ); INIT_LIST_HEAD(&sr->all_publ); rb_link_node(&sr->tree_node, parent, n); rb_insert_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); return sr; } static bool tipc_service_insert_publ(struct net *net, struct tipc_service *sc, struct publication *p) { struct tipc_subscription *sub, *tmp; struct service_range *sr; struct publication *_p; u32 node = p->sk.node; bool first = false; bool res = false; u32 key = p->key; spin_lock_bh(&sc->lock); sr = tipc_service_create_range(sc, p); if (!sr) goto exit; first = list_empty(&sr->all_publ); /* Return if the publication already exists */ list_for_each_entry(_p, &sr->all_publ, all_publ) { if (_p->key == key && (!_p->sk.node || _p->sk.node == node)) { pr_debug("Failed to bind duplicate %u,%u,%u/%u:%u/%u\n", p->sr.type, p->sr.lower, p->sr.upper, node, p->sk.ref, key); goto exit; } } if (in_own_node(net, p->sk.node)) list_add(&p->local_publ, &sr->local_publ); list_add(&p->all_publ, &sr->all_publ); p->id = sc->publ_cnt++; /* Any subscriptions waiting for notification? */ list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { tipc_sub_report_overlap(sub, p, TIPC_PUBLISHED, first); } res = true; exit: if (!res) pr_warn("Failed to bind to %u,%u,%u\n", p->sr.type, p->sr.lower, p->sr.upper); spin_unlock_bh(&sc->lock); return res; } /** * tipc_service_remove_publ - remove a publication from a service * @r: service_range to remove publication from * @sk: address publishing socket * @key: target publication key */ static struct publication *tipc_service_remove_publ(struct service_range *r, struct tipc_socket_addr *sk, u32 key) { struct publication *p; u32 node = sk->node; list_for_each_entry(p, &r->all_publ, all_publ) { if (p->key != key || (node && node != p->sk.node)) continue; list_del(&p->all_publ); list_del(&p->local_publ); return p; } return NULL; } /* * Code reused: time_after32() for the same purpose */ #define publication_after(pa, pb) time_after32((pa)->id, (pb)->id) static int tipc_publ_sort(void *priv, const struct list_head *a, const struct list_head *b) { struct publication *pa, *pb; pa = container_of(a, struct publication, list); pb = container_of(b, struct publication, list); return publication_after(pa, pb); } /** * tipc_service_subscribe - attach a subscription, and optionally * issue the prescribed number of events if there is any service * range overlapping with the requested range * @service: the tipc_service to attach the @sub to * @sub: the subscription to attach */ static void tipc_service_subscribe(struct tipc_service *service, struct tipc_subscription *sub) { struct publication *p, *first, *tmp; struct list_head publ_list; struct service_range *sr; u32 filter, lower, upper; filter = sub->s.filter; lower = sub->s.seq.lower; upper = sub->s.seq.upper; tipc_sub_get(sub); list_add(&sub->service_list, &service->subscriptions); if (filter & TIPC_SUB_NO_STATUS) return; INIT_LIST_HEAD(&publ_list); service_range_foreach_match(sr, service, lower, upper) { first = NULL; list_for_each_entry(p, &sr->all_publ, all_publ) { if (filter & TIPC_SUB_PORTS) list_add_tail(&p->list, &publ_list); else if (!first || publication_after(first, p)) /* Pick this range's *first* publication */ first = p; } if (first) list_add_tail(&first->list, &publ_list); } /* Sort the publications before reporting */ list_sort(NULL, &publ_list, tipc_publ_sort); list_for_each_entry_safe(p, tmp, &publ_list, list) { tipc_sub_report_overlap(sub, p, TIPC_PUBLISHED, true); list_del_init(&p->list); } } static struct tipc_service *tipc_service_find(struct net *net, struct tipc_uaddr *ua) { struct name_table *nt = tipc_name_table(net); struct hlist_head *service_head; struct tipc_service *service; service_head = &nt->services[hash(ua->sr.type)]; hlist_for_each_entry_rcu(service, service_head, service_list) { if (service->type == ua->sr.type) return service; } return NULL; }; struct publication *tipc_nametbl_insert_publ(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk, u32 key) { struct tipc_service *sc; struct publication *p; p = tipc_publ_create(ua, sk, key); if (!p) return NULL; sc = tipc_service_find(net, ua); if (!sc) sc = tipc_service_create(net, ua); if (sc && tipc_service_insert_publ(net, sc, p)) return p; kfree(p); return NULL; } struct publication *tipc_nametbl_remove_publ(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk, u32 key) { struct tipc_subscription *sub, *tmp; struct publication *p = NULL; struct service_range *sr; struct tipc_service *sc; bool last; sc = tipc_service_find(net, ua); if (!sc) goto exit; spin_lock_bh(&sc->lock); sr = tipc_service_find_range(sc, ua); if (!sr) goto unlock; p = tipc_service_remove_publ(sr, sk, key); if (!p) goto unlock; /* Notify any waiting subscriptions */ last = list_empty(&sr->all_publ); list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { tipc_sub_report_overlap(sub, p, TIPC_WITHDRAWN, last); } /* Remove service range item if this was its last publication */ if (list_empty(&sr->all_publ)) { rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); kfree(sr); } /* Delete service item if no more publications and subscriptions */ if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) { hlist_del_init_rcu(&sc->service_list); kfree_rcu(sc, rcu); } unlock: spin_unlock_bh(&sc->lock); exit: if (!p) { pr_err("Failed to remove unknown binding: %u,%u,%u/%u:%u/%u\n", ua->sr.type, ua->sr.lower, ua->sr.upper, sk->node, sk->ref, key); } return p; } /** * tipc_nametbl_lookup_anycast - perform service instance to socket translation * @net: network namespace * @ua: service address to look up * @sk: address to socket we want to find * * On entry, a non-zero 'sk->node' indicates the node where we want lookup to be * performed, which may not be this one. * * On exit: * * - If lookup is deferred to another node, leave 'sk->node' unchanged and * return 'true'. * - If lookup is successful, set the 'sk->node' and 'sk->ref' (== portid) which * represent the bound socket and return 'true'. * - If lookup fails, return 'false' * * Note that for legacy users (node configured with Z.C.N address format) the * 'closest-first' lookup algorithm must be maintained, i.e., if sk.node is 0 * we must look in the local binding list first */ bool tipc_nametbl_lookup_anycast(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk) { struct tipc_net *tn = tipc_net(net); bool legacy = tn->legacy_addr_format; u32 self = tipc_own_addr(net); u32 inst = ua->sa.instance; struct service_range *r; struct tipc_service *sc; struct publication *p; struct list_head *l; bool res = false; if (!tipc_in_scope(legacy, sk->node, self)) return true; rcu_read_lock(); sc = tipc_service_find(net, ua); if (unlikely(!sc)) goto exit; spin_lock_bh(&sc->lock); service_range_foreach_match(r, sc, inst, inst) { /* Select lookup algo: local, closest-first or round-robin */ if (sk->node == self) { l = &r->local_publ; if (list_empty(l)) continue; p = list_first_entry(l, struct publication, local_publ); list_move_tail(&p->local_publ, &r->local_publ); } else if (legacy && !sk->node && !list_empty(&r->local_publ)) { l = &r->local_publ; p = list_first_entry(l, struct publication, local_publ); list_move_tail(&p->local_publ, &r->local_publ); } else { l = &r->all_publ; p = list_first_entry(l, struct publication, all_publ); list_move_tail(&p->all_publ, &r->all_publ); } *sk = p->sk; res = true; /* Todo: as for legacy, pick the first matching range only, a * "true" round-robin will be performed as needed. */ break; } spin_unlock_bh(&sc->lock); exit: rcu_read_unlock(); return res; } /* tipc_nametbl_lookup_group(): lookup destinaton(s) in a communication group * Returns a list of one (== group anycast) or more (== group multicast) * destination socket/node pairs matching the given address. * The requester may or may not want to exclude himself from the list. */ bool tipc_nametbl_lookup_group(struct net *net, struct tipc_uaddr *ua, struct list_head *dsts, int *dstcnt, u32 exclude, bool mcast) { u32 self = tipc_own_addr(net); u32 inst = ua->sa.instance; struct service_range *sr; struct tipc_service *sc; struct publication *p; *dstcnt = 0; rcu_read_lock(); sc = tipc_service_find(net, ua); if (unlikely(!sc)) goto exit; spin_lock_bh(&sc->lock); /* Todo: a full search i.e. service_range_foreach_match() instead? */ sr = service_range_match_first(sc->ranges.rb_node, inst, inst); if (!sr) goto no_match; list_for_each_entry(p, &sr->all_publ, all_publ) { if (p->scope != ua->scope) continue; if (p->sk.ref == exclude && p->sk.node == self) continue; tipc_dest_push(dsts, p->sk.node, p->sk.ref); (*dstcnt)++; if (mcast) continue; list_move_tail(&p->all_publ, &sr->all_publ); break; } no_match: spin_unlock_bh(&sc->lock); exit: rcu_read_unlock(); return !list_empty(dsts); } /* tipc_nametbl_lookup_mcast_sockets(): look up node local destinaton sockets * matching the given address * Used on nodes which have received a multicast/broadcast message * Returns a list of local sockets */ void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua, struct list_head *dports) { struct service_range *sr; struct tipc_service *sc; struct publication *p; u8 scope = ua->scope; rcu_read_lock(); sc = tipc_service_find(net, ua); if (!sc) goto exit; spin_lock_bh(&sc->lock); service_range_foreach_match(sr, sc, ua->sr.lower, ua->sr.upper) { list_for_each_entry(p, &sr->local_publ, local_publ) { if (scope == p->scope || scope == TIPC_ANY_SCOPE) tipc_dest_push(dports, 0, p->sk.ref); } } spin_unlock_bh(&sc->lock); exit: rcu_read_unlock(); } /* tipc_nametbl_lookup_mcast_nodes(): look up all destination nodes matching * the given address. Used in sending node. * Used on nodes which are sending out a multicast/broadcast message * Returns a list of nodes, including own node if applicable */ void tipc_nametbl_lookup_mcast_nodes(struct net *net, struct tipc_uaddr *ua, struct tipc_nlist *nodes) { struct service_range *sr; struct tipc_service *sc; struct publication *p; rcu_read_lock(); sc = tipc_service_find(net, ua); if (!sc) goto exit; spin_lock_bh(&sc->lock); service_range_foreach_match(sr, sc, ua->sr.lower, ua->sr.upper) { list_for_each_entry(p, &sr->all_publ, all_publ) { tipc_nlist_add(nodes, p->sk.node); } } spin_unlock_bh(&sc->lock); exit: rcu_read_unlock(); } /* tipc_nametbl_build_group - build list of communication group members */ void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, struct tipc_uaddr *ua) { struct service_range *sr; struct tipc_service *sc; struct publication *p; struct rb_node *n; rcu_read_lock(); sc = tipc_service_find(net, ua); if (!sc) goto exit; spin_lock_bh(&sc->lock); for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { sr = container_of(n, struct service_range, tree_node); list_for_each_entry(p, &sr->all_publ, all_publ) { if (p->scope != ua->scope) continue; tipc_group_add_member(grp, p->sk.node, p->sk.ref, p->sr.lower); } } spin_unlock_bh(&sc->lock); exit: rcu_read_unlock(); } /* tipc_nametbl_publish - add service binding to name table */ struct publication *tipc_nametbl_publish(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk, u32 key) { struct name_table *nt = tipc_name_table(net); struct tipc_net *tn = tipc_net(net); struct publication *p = NULL; struct sk_buff *skb = NULL; u32 rc_dests; spin_lock_bh(&tn->nametbl_lock); if (nt->local_publ_count >= TIPC_MAX_PUBL) { pr_warn("Bind failed, max limit %u reached\n", TIPC_MAX_PUBL); goto exit; } p = tipc_nametbl_insert_publ(net, ua, sk, key); if (p) { nt->local_publ_count++; skb = tipc_named_publish(net, p); } rc_dests = nt->rc_dests; exit: spin_unlock_bh(&tn->nametbl_lock); if (skb) tipc_node_broadcast(net, skb, rc_dests); return p; } /** * tipc_nametbl_withdraw - withdraw a service binding * @net: network namespace * @ua: service address/range being unbound * @sk: address of the socket being unbound from * @key: target publication key */ void tipc_nametbl_withdraw(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk, u32 key) { struct name_table *nt = tipc_name_table(net); struct tipc_net *tn = tipc_net(net); struct sk_buff *skb = NULL; struct publication *p; u32 rc_dests; spin_lock_bh(&tn->nametbl_lock); p = tipc_nametbl_remove_publ(net, ua, sk, key); if (p) { nt->local_publ_count--; skb = tipc_named_withdraw(net, p); list_del_init(&p->binding_sock); kfree_rcu(p, rcu); } rc_dests = nt->rc_dests; spin_unlock_bh(&tn->nametbl_lock); if (skb) tipc_node_broadcast(net, skb, rc_dests); } /** * tipc_nametbl_subscribe - add a subscription object to the name table * @sub: subscription to add */ bool tipc_nametbl_subscribe(struct tipc_subscription *sub) { struct tipc_net *tn = tipc_net(sub->net); u32 type = sub->s.seq.type; struct tipc_service *sc; struct tipc_uaddr ua; bool res = true; tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_NODE_SCOPE, type, sub->s.seq.lower, sub->s.seq.upper); spin_lock_bh(&tn->nametbl_lock); sc = tipc_service_find(sub->net, &ua); if (!sc) sc = tipc_service_create(sub->net, &ua); if (sc) { spin_lock_bh(&sc->lock); tipc_service_subscribe(sc, sub); spin_unlock_bh(&sc->lock); } else { pr_warn("Failed to subscribe for {%u,%u,%u}\n", type, sub->s.seq.lower, sub->s.seq.upper); res = false; } spin_unlock_bh(&tn->nametbl_lock); return res; } /** * tipc_nametbl_unsubscribe - remove a subscription object from name table * @sub: subscription to remove */ void tipc_nametbl_unsubscribe(struct tipc_subscription *sub) { struct tipc_net *tn = tipc_net(sub->net); struct tipc_service *sc; struct tipc_uaddr ua; tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_NODE_SCOPE, sub->s.seq.type, sub->s.seq.lower, sub->s.seq.upper); spin_lock_bh(&tn->nametbl_lock); sc = tipc_service_find(sub->net, &ua); if (!sc) goto exit; spin_lock_bh(&sc->lock); list_del_init(&sub->service_list); tipc_sub_put(sub); /* Delete service item if no more publications and subscriptions */ if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) { hlist_del_init_rcu(&sc->service_list); kfree_rcu(sc, rcu); } spin_unlock_bh(&sc->lock); exit: spin_unlock_bh(&tn->nametbl_lock); } int tipc_nametbl_init(struct net *net) { struct tipc_net *tn = tipc_net(net); struct name_table *nt; int i; nt = kzalloc(sizeof(*nt), GFP_KERNEL); if (!nt) return -ENOMEM; for (i = 0; i < TIPC_NAMETBL_SIZE; i++) INIT_HLIST_HEAD(&nt->services[i]); INIT_LIST_HEAD(&nt->node_scope); INIT_LIST_HEAD(&nt->cluster_scope); rwlock_init(&nt->cluster_scope_lock); tn->nametbl = nt; spin_lock_init(&tn->nametbl_lock); return 0; } /** * tipc_service_delete - purge all publications for a service and delete it * @net: the associated network namespace * @sc: tipc_service to delete */ static void tipc_service_delete(struct net *net, struct tipc_service *sc) { struct service_range *sr, *tmpr; struct publication *p, *tmp; spin_lock_bh(&sc->lock); rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) { list_for_each_entry_safe(p, tmp, &sr->all_publ, all_publ) { tipc_service_remove_publ(sr, &p->sk, p->key); kfree_rcu(p, rcu); } rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); kfree(sr); } hlist_del_init_rcu(&sc->service_list); spin_unlock_bh(&sc->lock); kfree_rcu(sc, rcu); } void tipc_nametbl_stop(struct net *net) { struct name_table *nt = tipc_name_table(net); struct tipc_net *tn = tipc_net(net); struct hlist_head *service_head; struct tipc_service *service; u32 i; /* Verify name table is empty and purge any lingering * publications, then release the name table */ spin_lock_bh(&tn->nametbl_lock); for (i = 0; i < TIPC_NAMETBL_SIZE; i++) { if (hlist_empty(&nt->services[i])) continue; service_head = &nt->services[i]; hlist_for_each_entry_rcu(service, service_head, service_list) { tipc_service_delete(net, service); } } spin_unlock_bh(&tn->nametbl_lock); synchronize_net(); kfree(nt); } static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, struct tipc_service *service, struct service_range *sr, u32 *last_key) { struct publication *p; struct nlattr *attrs; struct nlattr *b; void *hdr; if (*last_key) { list_for_each_entry(p, &sr->all_publ, all_publ) if (p->key == *last_key) break; if (list_entry_is_head(p, &sr->all_publ, all_publ)) return -EPIPE; } else { p = list_first_entry(&sr->all_publ, struct publication, all_publ); } list_for_each_entry_from(p, &sr->all_publ, all_publ) { *last_key = p->key; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_NAME_TABLE_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NAME_TABLE); if (!attrs) goto msg_full; b = nla_nest_start_noflag(msg->skb, TIPC_NLA_NAME_TABLE_PUBL); if (!b) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_TYPE, service->type)) goto publ_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_LOWER, sr->lower)) goto publ_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_UPPER, sr->upper)) goto publ_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_SCOPE, p->scope)) goto publ_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_NODE, p->sk.node)) goto publ_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_REF, p->sk.ref)) goto publ_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_KEY, p->key)) goto publ_msg_full; nla_nest_end(msg->skb, b); nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); } *last_key = 0; return 0; publ_msg_full: nla_nest_cancel(msg->skb, b); attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } static int __tipc_nl_service_range_list(struct tipc_nl_msg *msg, struct tipc_service *sc, u32 *last_lower, u32 *last_key) { struct service_range *sr; struct rb_node *n; int err; for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { sr = container_of(n, struct service_range, tree_node); if (sr->lower < *last_lower) continue; err = __tipc_nl_add_nametable_publ(msg, sc, sr, last_key); if (err) { *last_lower = sr->lower; return err; } } *last_lower = 0; return 0; } static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg, u32 *last_type, u32 *last_lower, u32 *last_key) { struct tipc_net *tn = tipc_net(net); struct tipc_service *service = NULL; struct hlist_head *head; struct tipc_uaddr ua; int err; int i; if (*last_type) i = hash(*last_type); else i = 0; for (; i < TIPC_NAMETBL_SIZE; i++) { head = &tn->nametbl->services[i]; if (*last_type || (!i && *last_key && (*last_lower == *last_key))) { tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_NODE_SCOPE, *last_type, *last_lower, *last_lower); service = tipc_service_find(net, &ua); if (!service) return -EPIPE; } else { hlist_for_each_entry_rcu(service, head, service_list) break; if (!service) continue; } hlist_for_each_entry_from_rcu(service, service_list) { spin_lock_bh(&service->lock); err = __tipc_nl_service_range_list(msg, service, last_lower, last_key); if (err) { *last_type = service->type; spin_unlock_bh(&service->lock); return err; } spin_unlock_bh(&service->lock); } *last_type = 0; } return 0; } int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); u32 last_type = cb->args[0]; u32 last_lower = cb->args[1]; u32 last_key = cb->args[2]; int done = cb->args[3]; struct tipc_nl_msg msg; int err; if (done) return 0; msg.skb = skb; msg.portid = NETLINK_CB(cb->skb).portid; msg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); err = tipc_nl_service_list(net, &msg, &last_type, &last_lower, &last_key); if (!err) { done = 1; } else if (err != -EMSGSIZE) { /* We never set seq or call nl_dump_check_consistent() this * means that setting prev_seq here will cause the consistence * check to fail in the netlink callback handler. Resulting in * the NLMSG_DONE message having the NLM_F_DUMP_INTR flag set if * we got an error. */ cb->prev_seq = 1; } rcu_read_unlock(); cb->args[0] = last_type; cb->args[1] = last_lower; cb->args[2] = last_key; cb->args[3] = done; return skb->len; } struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port) { struct tipc_dest *dst; list_for_each_entry(dst, l, list) { if (dst->node == node && dst->port == port) return dst; } return NULL; } bool tipc_dest_push(struct list_head *l, u32 node, u32 port) { struct tipc_dest *dst; if (tipc_dest_find(l, node, port)) return false; dst = kmalloc(sizeof(*dst), GFP_ATOMIC); if (unlikely(!dst)) return false; dst->node = node; dst->port = port; list_add(&dst->list, l); return true; } bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port) { struct tipc_dest *dst; if (list_empty(l)) return false; dst = list_first_entry(l, typeof(*dst), list); if (port) *port = dst->port; if (node) *node = dst->node; list_del(&dst->list); kfree(dst); return true; } bool tipc_dest_del(struct list_head *l, u32 node, u32 port) { struct tipc_dest *dst; dst = tipc_dest_find(l, node, port); if (!dst) return false; list_del(&dst->list); kfree(dst); return true; } void tipc_dest_list_purge(struct list_head *l) { struct tipc_dest *dst, *tmp; list_for_each_entry_safe(dst, tmp, l, list) { list_del(&dst->list); kfree(dst); } } |
| 8 8 8 7 7 63 4 8 4 5 4 7 2 7 6 6 6 3 6 5 63 5 5 2 2 5 5 5 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/binfmt_script.c * * Copyright (C) 1996 Martin von Löwis * original #!-checking implemented by tytso. */ #include <linux/module.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/binfmts.h> #include <linux/init.h> #include <linux/file.h> #include <linux/err.h> #include <linux/fs.h> static inline bool spacetab(char c) { return c == ' ' || c == '\t'; } static inline const char *next_non_spacetab(const char *first, const char *last) { for (; first <= last; first++) if (!spacetab(*first)) return first; return NULL; } static inline const char *next_terminator(const char *first, const char *last) { for (; first <= last; first++) if (spacetab(*first) || !*first) return first; return NULL; } static int load_script(struct linux_binprm *bprm) { const char *i_name, *i_sep, *i_arg, *i_end, *buf_end; struct file *file; int retval; /* Not ours to exec if we don't start with "#!". */ if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) return -ENOEXEC; /* * This section handles parsing the #! line into separate * interpreter path and argument strings. We must be careful * because bprm->buf is not yet guaranteed to be NUL-terminated * (though the buffer will have trailing NUL padding when the * file size was smaller than the buffer size). * * We do not want to exec a truncated interpreter path, so either * we find a newline (which indicates nothing is truncated), or * we find a space/tab/NUL after the interpreter path (which * itself may be preceded by spaces/tabs). Truncating the * arguments is fine: the interpreter can re-read the script to * parse them on its own. */ buf_end = bprm->buf + sizeof(bprm->buf) - 1; i_end = strnchr(bprm->buf, sizeof(bprm->buf), '\n'); if (!i_end) { i_end = next_non_spacetab(bprm->buf + 2, buf_end); if (!i_end) return -ENOEXEC; /* Entire buf is spaces/tabs */ /* * If there is no later space/tab/NUL we must assume the * interpreter path is truncated. */ if (!next_terminator(i_end, buf_end)) return -ENOEXEC; i_end = buf_end; } /* Trim any trailing spaces/tabs from i_end */ while (spacetab(i_end[-1])) i_end--; /* Skip over leading spaces/tabs */ i_name = next_non_spacetab(bprm->buf+2, i_end); if (!i_name || (i_name == i_end)) return -ENOEXEC; /* No interpreter name found */ /* Is there an optional argument? */ i_arg = NULL; i_sep = next_terminator(i_name, i_end); if (i_sep && (*i_sep != '\0')) i_arg = next_non_spacetab(i_sep, i_end); /* * If the script filename will be inaccessible after exec, typically * because it is a "/dev/fd/<fd>/.." path against an O_CLOEXEC fd, give * up now (on the assumption that the interpreter will want to load * this file). */ if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) return -ENOENT; /* * OK, we've parsed out the interpreter name and * (optional) argument. * Splice in (1) the interpreter's name for argv[0] * (2) (optional) argument to interpreter * (3) filename of shell script (replace argv[0]) * * This is done in reverse order, because of how the * user environment and arguments are stored. */ retval = remove_arg_zero(bprm); if (retval) return retval; retval = copy_string_kernel(bprm->interp, bprm); if (retval < 0) return retval; bprm->argc++; *((char *)i_end) = '\0'; if (i_arg) { *((char *)i_sep) = '\0'; retval = copy_string_kernel(i_arg, bprm); if (retval < 0) return retval; bprm->argc++; } retval = copy_string_kernel(i_name, bprm); if (retval) return retval; bprm->argc++; retval = bprm_change_interp(i_name, bprm); if (retval < 0) return retval; /* * OK, now restart the process with the interpreter's dentry. */ file = open_exec(i_name); if (IS_ERR(file)) return PTR_ERR(file); bprm->interpreter = file; return 0; } static struct linux_binfmt script_format = { .module = THIS_MODULE, .load_binary = load_script, }; static int __init init_script_binfmt(void) { register_binfmt(&script_format); return 0; } static void __exit exit_script_binfmt(void) { unregister_binfmt(&script_format); } core_initcall(init_script_binfmt); module_exit(exit_script_binfmt); MODULE_DESCRIPTION("Kernel support for scripts starting with #!"); MODULE_LICENSE("GPL"); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | // SPDX-License-Identifier: GPL-2.0-only /* * Binary Increase Congestion control for TCP * Home page: * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC * This is from the implementation of BICTCP in * Lison-Xu, Kahaled Harfoush, and Injong Rhee. * "Binary Increase Congestion Control for Fast, Long Distance * Networks" in InfoComm 2004 * Available from: * http://netsrv.csc.ncsu.edu/export/bitcp.pdf * * Unless BIC is enabled and congestion window is large * this behaves the same as the original Reno. */ #include <linux/mm.h> #include <linux/module.h> #include <net/tcp.h> #define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation * max_cwnd = snd_cwnd * beta */ #define BICTCP_B 4 /* * In binary search, * go to point (max+min)/N */ static int fast_convergence = 1; static int max_increment = 16; static int low_window = 14; static int beta = 819; /* = 819/1024 (BICTCP_BETA_SCALE) */ static int initial_ssthresh; static int smooth_part = 20; module_param(fast_convergence, int, 0644); MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence"); module_param(max_increment, int, 0644); MODULE_PARM_DESC(max_increment, "Limit on increment allowed during binary search"); module_param(low_window, int, 0644); MODULE_PARM_DESC(low_window, "lower bound on congestion window (for TCP friendliness)"); module_param(beta, int, 0644); MODULE_PARM_DESC(beta, "beta for multiplicative increase"); module_param(initial_ssthresh, int, 0644); MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold"); module_param(smooth_part, int, 0644); MODULE_PARM_DESC(smooth_part, "log(B/(B*Smin))/log(B/(B-1))+B, # of RTT from Wmax-B to Wmax"); /* BIC TCP Parameters */ struct bictcp { u32 cnt; /* increase cwnd by 1 after ACKs */ u32 last_max_cwnd; /* last maximum snd_cwnd */ u32 last_cwnd; /* the last snd_cwnd */ u32 last_time; /* time when updated last_cwnd */ u32 epoch_start; /* beginning of an epoch */ #define ACK_RATIO_SHIFT 4 u32 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */ }; static inline void bictcp_reset(struct bictcp *ca) { ca->cnt = 0; ca->last_max_cwnd = 0; ca->last_cwnd = 0; ca->last_time = 0; ca->epoch_start = 0; ca->delayed_ack = 2 << ACK_RATIO_SHIFT; } static void bictcp_init(struct sock *sk) { struct bictcp *ca = inet_csk_ca(sk); bictcp_reset(ca); if (initial_ssthresh) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } /* * Compute congestion window to use. */ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) { if (ca->last_cwnd == cwnd && (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) return; ca->last_cwnd = cwnd; ca->last_time = tcp_jiffies32; if (ca->epoch_start == 0) /* record the beginning of an epoch */ ca->epoch_start = tcp_jiffies32; /* start off normal */ if (cwnd <= low_window) { ca->cnt = cwnd; return; } /* binary increase */ if (cwnd < ca->last_max_cwnd) { __u32 dist = (ca->last_max_cwnd - cwnd) / BICTCP_B; if (dist > max_increment) /* linear increase */ ca->cnt = cwnd / max_increment; else if (dist <= 1U) /* binary search increase */ ca->cnt = (cwnd * smooth_part) / BICTCP_B; else /* binary search increase */ ca->cnt = cwnd / dist; } else { /* slow start AMD linear increase */ if (cwnd < ca->last_max_cwnd + BICTCP_B) /* slow start */ ca->cnt = (cwnd * smooth_part) / BICTCP_B; else if (cwnd < ca->last_max_cwnd + max_increment*(BICTCP_B-1)) /* slow start */ ca->cnt = (cwnd * (BICTCP_B-1)) / (cwnd - ca->last_max_cwnd); else /* linear increase */ ca->cnt = cwnd / max_increment; } /* if in slow start or link utilization is very low */ if (ca->last_max_cwnd == 0) { if (ca->cnt > 20) /* increase cwnd 5% per RTT */ ca->cnt = 20; } ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack; if (ca->cnt == 0) /* cannot be zero */ ca->cnt = 1; } static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); if (!tcp_is_cwnd_limited(sk)) return; if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; } bictcp_update(ca, tcp_snd_cwnd(tp)); tcp_cong_avoid_ai(tp, ca->cnt, acked); } /* * behave like Reno until low_window is reached, * then increase congestion window slowly */ static u32 bictcp_recalc_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); ca->epoch_start = 0; /* end of epoch */ /* Wmax and fast convergence */ if (tcp_snd_cwnd(tp) < ca->last_max_cwnd && fast_convergence) ca->last_max_cwnd = (tcp_snd_cwnd(tp) * (BICTCP_BETA_SCALE + beta)) / (2 * BICTCP_BETA_SCALE); else ca->last_max_cwnd = tcp_snd_cwnd(tp); if (tcp_snd_cwnd(tp) <= low_window) return max(tcp_snd_cwnd(tp) >> 1U, 2U); else return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U); } static void bictcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Loss) bictcp_reset(inet_csk_ca(sk)); } /* Track delayed acknowledgment ratio using sliding window * ratio = (15*ratio + sample) / 16 */ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_state == TCP_CA_Open) { struct bictcp *ca = inet_csk_ca(sk); ca->delayed_ack += sample->pkts_acked - (ca->delayed_ack >> ACK_RATIO_SHIFT); } } static struct tcp_congestion_ops bictcp __read_mostly = { .init = bictcp_init, .ssthresh = bictcp_recalc_ssthresh, .cong_avoid = bictcp_cong_avoid, .set_state = bictcp_state, .undo_cwnd = tcp_reno_undo_cwnd, .pkts_acked = bictcp_acked, .owner = THIS_MODULE, .name = "bic", }; static int __init bictcp_register(void) { BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&bictcp); } static void __exit bictcp_unregister(void) { tcp_unregister_congestion_control(&bictcp); } module_init(bictcp_register); module_exit(bictcp_unregister); MODULE_AUTHOR("Stephen Hemminger"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("BIC TCP"); |
| 27 27 26 26 26 25 26 26 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 | /* * net/tipc/discover.c * * Copyright (c) 2003-2006, 2014-2018, Ericsson AB * Copyright (c) 2005-2006, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "core.h" #include "node.h" #include "discover.h" /* min delay during bearer start up */ #define TIPC_DISC_INIT msecs_to_jiffies(125) /* max delay if bearer has no links */ #define TIPC_DISC_FAST msecs_to_jiffies(1000) /* max delay if bearer has links */ #define TIPC_DISC_SLOW msecs_to_jiffies(60000) /* indicates no timer in use */ #define TIPC_DISC_INACTIVE 0xffffffff /** * struct tipc_discoverer - information about an ongoing link setup request * @bearer_id: identity of bearer issuing requests * @net: network namespace instance * @dest: destination address for request messages * @domain: network domain to which links can be established * @num_nodes: number of nodes currently discovered (i.e. with an active link) * @lock: spinlock for controlling access to requests * @skb: request message to be (repeatedly) sent * @timer: timer governing period between requests * @timer_intv: current interval between requests (in ms) */ struct tipc_discoverer { u32 bearer_id; struct tipc_media_addr dest; struct net *net; u32 domain; int num_nodes; spinlock_t lock; struct sk_buff *skb; struct timer_list timer; unsigned long timer_intv; }; /** * tipc_disc_init_msg - initialize a link setup message * @net: the applicable net namespace * @skb: buffer containing message * @mtyp: message type (request or response) * @b: ptr to bearer issuing message */ static void tipc_disc_init_msg(struct net *net, struct sk_buff *skb, u32 mtyp, struct tipc_bearer *b) { struct tipc_net *tn = tipc_net(net); u32 dest_domain = b->domain; struct tipc_msg *hdr; hdr = buf_msg(skb); tipc_msg_init(tn->trial_addr, hdr, LINK_CONFIG, mtyp, MAX_H_SIZE, dest_domain); msg_set_size(hdr, MAX_H_SIZE + NODE_ID_LEN); msg_set_non_seq(hdr, 1); msg_set_node_sig(hdr, tn->random); msg_set_node_capabilities(hdr, TIPC_NODE_CAPABILITIES); msg_set_dest_domain(hdr, dest_domain); msg_set_bc_netid(hdr, tn->net_id); b->media->addr2msg(msg_media_addr(hdr), &b->addr); msg_set_peer_net_hash(hdr, tipc_net_hash_mixes(net, tn->random)); msg_set_node_id(hdr, tipc_own_id(net)); } static void tipc_disc_msg_xmit(struct net *net, u32 mtyp, u32 dst, u32 src, u32 sugg_addr, struct tipc_media_addr *maddr, struct tipc_bearer *b) { struct tipc_msg *hdr; struct sk_buff *skb; skb = tipc_buf_acquire(MAX_H_SIZE + NODE_ID_LEN, GFP_ATOMIC); if (!skb) return; hdr = buf_msg(skb); tipc_disc_init_msg(net, skb, mtyp, b); msg_set_sugg_node_addr(hdr, sugg_addr); msg_set_dest_domain(hdr, dst); tipc_bearer_xmit_skb(net, b->identity, skb, maddr); } /** * disc_dupl_alert - issue node address duplication alert * @b: pointer to bearer detecting duplication * @node_addr: duplicated node address * @media_addr: media address advertised by duplicated node */ static void disc_dupl_alert(struct tipc_bearer *b, u32 node_addr, struct tipc_media_addr *media_addr) { char media_addr_str[64]; tipc_media_addr_printf(media_addr_str, sizeof(media_addr_str), media_addr); pr_warn("Duplicate %x using %s seen on <%s>\n", node_addr, media_addr_str, b->name); } /* tipc_disc_addr_trial(): - handle an address uniqueness trial from peer * Returns true if message should be dropped by caller, i.e., if it is a * trial message or we are inside trial period. Otherwise false. */ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, struct tipc_media_addr *maddr, struct tipc_bearer *b, u32 dst, u32 src, u32 sugg_addr, u8 *peer_id, int mtyp) { struct net *net = d->net; struct tipc_net *tn = tipc_net(net); u32 self = tipc_own_addr(net); bool trial = time_before(jiffies, tn->addr_trial_end) && !self; if (mtyp == DSC_TRIAL_FAIL_MSG) { if (!trial) return true; /* Ignore if somebody else already gave new suggestion */ if (dst != tn->trial_addr) return true; /* Otherwise update trial address and restart trial period */ tn->trial_addr = sugg_addr; msg_set_prevnode(buf_msg(d->skb), sugg_addr); tn->addr_trial_end = jiffies + msecs_to_jiffies(1000); return true; } /* Apply trial address if we just left trial period */ if (!trial && !self) { schedule_work(&tn->work); msg_set_prevnode(buf_msg(d->skb), tn->trial_addr); msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); } /* Accept regular link requests/responses only after trial period */ if (mtyp != DSC_TRIAL_MSG) return trial; sugg_addr = tipc_node_try_addr(net, peer_id, src); if (sugg_addr) tipc_disc_msg_xmit(net, DSC_TRIAL_FAIL_MSG, src, self, sugg_addr, maddr, b); return true; } /** * tipc_disc_rcv - handle incoming discovery message (request or response) * @net: applicable net namespace * @skb: buffer containing message * @b: bearer that message arrived on */ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) { struct tipc_net *tn = tipc_net(net); struct tipc_msg *hdr = buf_msg(skb); u32 pnet_hash = msg_peer_net_hash(hdr); u16 caps = msg_node_capabilities(hdr); bool legacy = tn->legacy_addr_format; u32 sugg = msg_sugg_node_addr(hdr); u32 signature = msg_node_sig(hdr); u8 peer_id[NODE_ID_LEN] = {0,}; u32 dst = msg_dest_domain(hdr); u32 net_id = msg_bc_netid(hdr); struct tipc_media_addr maddr; u32 src = msg_prevnode(hdr); u32 mtyp = msg_type(hdr); bool dupl_addr = false; bool respond = false; u32 self; int err; if (skb_linearize(skb)) { kfree_skb(skb); return; } hdr = buf_msg(skb); if (caps & TIPC_NODE_ID128) memcpy(peer_id, msg_node_id(hdr), NODE_ID_LEN); else sprintf(peer_id, "%x", src); err = b->media->msg2addr(b, &maddr, msg_media_addr(hdr)); kfree_skb(skb); if (err || maddr.broadcast) { pr_warn_ratelimited("Rcv corrupt discovery message\n"); return; } /* Ignore discovery messages from own node */ if (!memcmp(&maddr, &b->addr, sizeof(maddr))) return; if (net_id != tn->net_id) return; if (tipc_disc_addr_trial_msg(b->disc, &maddr, b, dst, src, sugg, peer_id, mtyp)) return; self = tipc_own_addr(net); /* Message from somebody using this node's address */ if (in_own_node(net, src)) { disc_dupl_alert(b, self, &maddr); return; } if (!tipc_in_scope(legacy, dst, self)) return; if (!tipc_in_scope(legacy, b->domain, src)) return; tipc_node_check_dest(net, src, peer_id, b, caps, signature, pnet_hash, &maddr, &respond, &dupl_addr); if (dupl_addr) disc_dupl_alert(b, src, &maddr); if (!respond) return; if (mtyp != DSC_REQ_MSG) return; tipc_disc_msg_xmit(net, DSC_RESP_MSG, src, self, 0, &maddr, b); } /* tipc_disc_add_dest - increment set of discovered nodes */ void tipc_disc_add_dest(struct tipc_discoverer *d) { spin_lock_bh(&d->lock); d->num_nodes++; spin_unlock_bh(&d->lock); } /* tipc_disc_remove_dest - decrement set of discovered nodes */ void tipc_disc_remove_dest(struct tipc_discoverer *d) { int intv, num; spin_lock_bh(&d->lock); d->num_nodes--; num = d->num_nodes; intv = d->timer_intv; if (!num && (intv == TIPC_DISC_INACTIVE || intv > TIPC_DISC_FAST)) { d->timer_intv = TIPC_DISC_INIT; mod_timer(&d->timer, jiffies + d->timer_intv); } spin_unlock_bh(&d->lock); } /* tipc_disc_timeout - send a periodic link setup request * Called whenever a link setup request timer associated with a bearer expires. * - Keep doubling time between sent request until limit is reached; * - Hold at fast polling rate if we don't have any associated nodes * - Otherwise hold at slow polling rate */ static void tipc_disc_timeout(struct timer_list *t) { struct tipc_discoverer *d = from_timer(d, t, timer); struct tipc_net *tn = tipc_net(d->net); struct tipc_media_addr maddr; struct sk_buff *skb = NULL; struct net *net = d->net; u32 bearer_id; spin_lock_bh(&d->lock); /* Stop searching if only desired node has been found */ if (tipc_node(d->domain) && d->num_nodes) { d->timer_intv = TIPC_DISC_INACTIVE; goto exit; } /* Did we just leave trial period ? */ if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) { mod_timer(&d->timer, jiffies + TIPC_DISC_INIT); spin_unlock_bh(&d->lock); schedule_work(&tn->work); return; } /* Adjust timeout interval according to discovery phase */ if (time_before(jiffies, tn->addr_trial_end)) { d->timer_intv = TIPC_DISC_INIT; } else { d->timer_intv *= 2; if (d->num_nodes && d->timer_intv > TIPC_DISC_SLOW) d->timer_intv = TIPC_DISC_SLOW; else if (!d->num_nodes && d->timer_intv > TIPC_DISC_FAST) d->timer_intv = TIPC_DISC_FAST; msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); msg_set_prevnode(buf_msg(d->skb), tn->trial_addr); } mod_timer(&d->timer, jiffies + d->timer_intv); memcpy(&maddr, &d->dest, sizeof(maddr)); skb = skb_clone(d->skb, GFP_ATOMIC); bearer_id = d->bearer_id; exit: spin_unlock_bh(&d->lock); if (skb) tipc_bearer_xmit_skb(net, bearer_id, skb, &maddr); } /** * tipc_disc_create - create object to send periodic link setup requests * @net: the applicable net namespace * @b: ptr to bearer issuing requests * @dest: destination address for request messages * @skb: pointer to created frame * * Return: 0 if successful, otherwise -errno. */ int tipc_disc_create(struct net *net, struct tipc_bearer *b, struct tipc_media_addr *dest, struct sk_buff **skb) { struct tipc_net *tn = tipc_net(net); struct tipc_discoverer *d; d = kmalloc(sizeof(*d), GFP_ATOMIC); if (!d) return -ENOMEM; d->skb = tipc_buf_acquire(MAX_H_SIZE + NODE_ID_LEN, GFP_ATOMIC); if (!d->skb) { kfree(d); return -ENOMEM; } tipc_disc_init_msg(net, d->skb, DSC_REQ_MSG, b); /* Do we need an address trial period first ? */ if (!tipc_own_addr(net)) { tn->addr_trial_end = jiffies + msecs_to_jiffies(1000); msg_set_type(buf_msg(d->skb), DSC_TRIAL_MSG); } memcpy(&d->dest, dest, sizeof(*dest)); d->net = net; d->bearer_id = b->identity; d->domain = b->domain; d->num_nodes = 0; d->timer_intv = TIPC_DISC_INIT; spin_lock_init(&d->lock); timer_setup(&d->timer, tipc_disc_timeout, 0); mod_timer(&d->timer, jiffies + d->timer_intv); b->disc = d; *skb = skb_clone(d->skb, GFP_ATOMIC); return 0; } /** * tipc_disc_delete - destroy object sending periodic link setup requests * @d: ptr to link dest structure */ void tipc_disc_delete(struct tipc_discoverer *d) { timer_shutdown_sync(&d->timer); kfree_skb(d->skb); kfree(d); } /** * tipc_disc_reset - reset object to send periodic link setup requests * @net: the applicable net namespace * @b: ptr to bearer issuing requests */ void tipc_disc_reset(struct net *net, struct tipc_bearer *b) { struct tipc_discoverer *d = b->disc; struct tipc_media_addr maddr; struct sk_buff *skb; spin_lock_bh(&d->lock); tipc_disc_init_msg(net, d->skb, DSC_REQ_MSG, b); d->net = net; d->bearer_id = b->identity; d->domain = b->domain; d->num_nodes = 0; d->timer_intv = TIPC_DISC_INIT; memcpy(&maddr, &d->dest, sizeof(maddr)); mod_timer(&d->timer, jiffies + d->timer_intv); skb = skb_clone(d->skb, GFP_ATOMIC); spin_unlock_bh(&d->lock); if (skb) tipc_bearer_xmit_skb(net, b->identity, skb, &maddr); } |
| 2 5 1 4 138 138 5 138 129 128 28 28 28 27 21 14 14 2 2 11 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Neil Brown 2002 * Copyright (C) Christoph Hellwig 2007 * * This file contains the code mapping from inodes to NFS file handles, * and for mapping back from file handles to dentries. * * For details on why we do all the strange and hairy things in here * take a look at Documentation/filesystems/nfs/exporting.rst. */ #include <linux/exportfs.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/sched.h> #include <linux/cred.h> #define dprintk(fmt, args...) pr_debug(fmt, ##args) static int get_name(const struct path *path, char *name, struct dentry *child); static int exportfs_get_name(struct vfsmount *mnt, struct dentry *dir, char *name, struct dentry *child) { const struct export_operations *nop = dir->d_sb->s_export_op; struct path path = {.mnt = mnt, .dentry = dir}; if (nop->get_name) return nop->get_name(dir, name, child); else return get_name(&path, name, child); } /* * Check if the dentry or any of it's aliases is acceptable. */ static struct dentry * find_acceptable_alias(struct dentry *result, int (*acceptable)(void *context, struct dentry *dentry), void *context) { struct dentry *dentry, *toput = NULL; struct inode *inode; if (acceptable(context, result)) return result; inode = result->d_inode; spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { dget(dentry); spin_unlock(&inode->i_lock); if (toput) dput(toput); if (dentry != result && acceptable(context, dentry)) { dput(result); return dentry; } spin_lock(&inode->i_lock); toput = dentry; } spin_unlock(&inode->i_lock); if (toput) dput(toput); return NULL; } static bool dentry_connected(struct dentry *dentry) { dget(dentry); while (dentry->d_flags & DCACHE_DISCONNECTED) { struct dentry *parent = dget_parent(dentry); dput(dentry); if (dentry == parent) { dput(parent); return false; } dentry = parent; } dput(dentry); return true; } static void clear_disconnected(struct dentry *dentry) { dget(dentry); while (dentry->d_flags & DCACHE_DISCONNECTED) { struct dentry *parent = dget_parent(dentry); WARN_ON_ONCE(IS_ROOT(dentry)); spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_DISCONNECTED; spin_unlock(&dentry->d_lock); dput(dentry); dentry = parent; } dput(dentry); } /* * Reconnect a directory dentry with its parent. * * This can return a dentry, or NULL, or an error. * * In the first case the returned dentry is the parent of the given * dentry, and may itself need to be reconnected to its parent. * * In the NULL case, a concurrent VFS operation has either renamed or * removed this directory. The concurrent operation has reconnected our * dentry, so we no longer need to. */ static struct dentry *reconnect_one(struct vfsmount *mnt, struct dentry *dentry, char *nbuf) { struct dentry *parent; struct dentry *tmp; int err; parent = ERR_PTR(-EACCES); inode_lock(dentry->d_inode); if (mnt->mnt_sb->s_export_op->get_parent) parent = mnt->mnt_sb->s_export_op->get_parent(dentry); inode_unlock(dentry->d_inode); if (IS_ERR(parent)) { dprintk("get_parent of %lu failed, err %ld\n", dentry->d_inode->i_ino, PTR_ERR(parent)); return parent; } dprintk("%s: find name of %lu in %lu\n", __func__, dentry->d_inode->i_ino, parent->d_inode->i_ino); err = exportfs_get_name(mnt, parent, nbuf, dentry); if (err == -ENOENT) goto out_reconnected; if (err) goto out_err; dprintk("%s: found name: %s\n", __func__, nbuf); tmp = lookup_one_unlocked(mnt_idmap(mnt), nbuf, parent, strlen(nbuf)); if (IS_ERR(tmp)) { dprintk("lookup failed: %ld\n", PTR_ERR(tmp)); err = PTR_ERR(tmp); goto out_err; } if (tmp != dentry) { /* * Somebody has renamed it since exportfs_get_name(); * great, since it could've only been renamed if it * got looked up and thus connected, and it would * remain connected afterwards. We are done. */ dput(tmp); goto out_reconnected; } dput(tmp); if (IS_ROOT(dentry)) { err = -ESTALE; goto out_err; } return parent; out_err: dput(parent); return ERR_PTR(err); out_reconnected: dput(parent); /* * Someone must have renamed our entry into another parent, in * which case it has been reconnected by the rename. * * Or someone removed it entirely, in which case filehandle * lookup will succeed but the directory is now IS_DEAD and * subsequent operations on it will fail. * * Alternatively, maybe there was no race at all, and the * filesystem is just corrupt and gave us a parent that doesn't * actually contain any entry pointing to this inode. So, * double check that this worked and return -ESTALE if not: */ if (!dentry_connected(dentry)) return ERR_PTR(-ESTALE); return NULL; } /* * Make sure target_dir is fully connected to the dentry tree. * * On successful return, DCACHE_DISCONNECTED will be cleared on * target_dir, and target_dir->d_parent->...->d_parent will reach the * root of the filesystem. * * Whenever DCACHE_DISCONNECTED is unset, target_dir is fully connected. * But the converse is not true: target_dir may have DCACHE_DISCONNECTED * set but already be connected. In that case we'll verify the * connection to root and then clear the flag. * * Note that target_dir could be removed by a concurrent operation. In * that case reconnect_path may still succeed with target_dir fully * connected, but further operations using the filehandle will fail when * necessary (due to S_DEAD being set on the directory). */ static int reconnect_path(struct vfsmount *mnt, struct dentry *target_dir, char *nbuf) { struct dentry *dentry, *parent; dentry = dget(target_dir); while (dentry->d_flags & DCACHE_DISCONNECTED) { BUG_ON(dentry == mnt->mnt_sb->s_root); if (IS_ROOT(dentry)) parent = reconnect_one(mnt, dentry, nbuf); else parent = dget_parent(dentry); if (!parent) break; dput(dentry); if (IS_ERR(parent)) return PTR_ERR(parent); dentry = parent; } dput(dentry); clear_disconnected(target_dir); return 0; } struct getdents_callback { struct dir_context ctx; char *name; /* name that was found. It already points to a buffer NAME_MAX+1 is size */ u64 ino; /* the inum we are looking for */ int found; /* inode matched? */ int sequence; /* sequence counter */ }; /* * A rather strange filldir function to capture * the name matching the specified inode number. */ static bool filldir_one(struct dir_context *ctx, const char *name, int len, loff_t pos, u64 ino, unsigned int d_type) { struct getdents_callback *buf = container_of(ctx, struct getdents_callback, ctx); buf->sequence++; if (buf->ino == ino && len <= NAME_MAX && !is_dot_dotdot(name, len)) { memcpy(buf->name, name, len); buf->name[len] = '\0'; buf->found = 1; return false; // no more } return true; } /** * get_name - default export_operations->get_name function * @path: the directory in which to find a name * @name: a pointer to a %NAME_MAX+1 char buffer to store the name * @child: the dentry for the child directory. * * calls readdir on the parent until it finds an entry with * the same inode number as the child, and returns that. */ static int get_name(const struct path *path, char *name, struct dentry *child) { const struct cred *cred = current_cred(); struct inode *dir = path->dentry->d_inode; int error; struct file *file; struct kstat stat; struct path child_path = { .mnt = path->mnt, .dentry = child, }; struct getdents_callback buffer = { .ctx.actor = filldir_one, .name = name, }; error = -ENOTDIR; if (!dir || !S_ISDIR(dir->i_mode)) goto out; error = -EINVAL; if (!dir->i_fop) goto out; /* * inode->i_ino is unsigned long, kstat->ino is u64, so the * former would be insufficient on 32-bit hosts when the * filesystem supports 64-bit inode numbers. So we need to * actually call ->getattr, not just read i_ino: */ error = vfs_getattr_nosec(&child_path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT); if (error) return error; buffer.ino = stat.ino; /* * Open the directory ... */ file = dentry_open(path, O_RDONLY, cred); error = PTR_ERR(file); if (IS_ERR(file)) goto out; error = -EINVAL; if (!file->f_op->iterate_shared) goto out_close; buffer.sequence = 0; while (1) { int old_seq = buffer.sequence; error = iterate_dir(file, &buffer.ctx); if (buffer.found) { error = 0; break; } if (error < 0) break; error = -ENOENT; if (old_seq == buffer.sequence) break; } out_close: fput(file); out: return error; } #define FILEID_INO64_GEN_LEN 3 /** * exportfs_encode_ino64_fid - encode non-decodeable 64bit ino file id * @inode: the object to encode * @fid: where to store the file handle fragment * @max_len: maximum length to store there (in 4 byte units) * * This generic function is used to encode a non-decodeable file id for * fanotify for filesystems that do not support NFS export. */ static int exportfs_encode_ino64_fid(struct inode *inode, struct fid *fid, int *max_len) { if (*max_len < FILEID_INO64_GEN_LEN) { *max_len = FILEID_INO64_GEN_LEN; return FILEID_INVALID; } fid->i64.ino = inode->i_ino; fid->i64.gen = inode->i_generation; *max_len = FILEID_INO64_GEN_LEN; return FILEID_INO64_GEN; } /** * exportfs_encode_inode_fh - encode a file handle from inode * @inode: the object to encode * @fid: where to store the file handle fragment * @max_len: maximum length to store there * @parent: parent directory inode, if wanted * @flags: properties of the requested file handle * * Returns an enum fid_type or a negative errno. */ int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, int *max_len, struct inode *parent, int flags) { const struct export_operations *nop = inode->i_sb->s_export_op; if (!exportfs_can_encode_fh(nop, flags)) return -EOPNOTSUPP; if (!nop && (flags & EXPORT_FH_FID)) return exportfs_encode_ino64_fid(inode, fid, max_len); return nop->encode_fh(inode, fid->raw, max_len, parent); } EXPORT_SYMBOL_GPL(exportfs_encode_inode_fh); /** * exportfs_encode_fh - encode a file handle from dentry * @dentry: the object to encode * @fid: where to store the file handle fragment * @max_len: maximum length to store there * @flags: properties of the requested file handle * * Returns an enum fid_type or a negative errno. */ int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len, int flags) { int error; struct dentry *p = NULL; struct inode *inode = dentry->d_inode, *parent = NULL; if ((flags & EXPORT_FH_CONNECTABLE) && !S_ISDIR(inode->i_mode)) { p = dget_parent(dentry); /* * note that while p might've ceased to be our parent already, * it's still pinned by and still positive. */ parent = p->d_inode; } error = exportfs_encode_inode_fh(inode, fid, max_len, parent, flags); dput(p); return error; } EXPORT_SYMBOL_GPL(exportfs_encode_fh); struct dentry * exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len, int fileid_type, unsigned int flags, int (*acceptable)(void *, struct dentry *), void *context) { const struct export_operations *nop = mnt->mnt_sb->s_export_op; struct dentry *result, *alias; char nbuf[NAME_MAX+1]; int err; /* * Try to get any dentry for the given file handle from the filesystem. */ if (!exportfs_can_decode_fh(nop)) return ERR_PTR(-ESTALE); result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type); if (IS_ERR_OR_NULL(result)) return result; if ((flags & EXPORT_FH_DIR_ONLY) && !d_is_dir(result)) { err = -ENOTDIR; goto err_result; } /* * If no acceptance criteria was specified by caller, a disconnected * dentry is also accepatable. Callers may use this mode to query if * file handle is stale or to get a reference to an inode without * risking the high overhead caused by directory reconnect. */ if (!acceptable) return result; if (d_is_dir(result)) { /* * This request is for a directory. * * On the positive side there is only one dentry for each * directory inode. On the negative side this implies that we * to ensure our dentry is connected all the way up to the * filesystem root. */ if (result->d_flags & DCACHE_DISCONNECTED) { err = reconnect_path(mnt, result, nbuf); if (err) goto err_result; } if (!acceptable(context, result)) { err = -EACCES; goto err_result; } return result; } else { /* * It's not a directory. Life is a little more complicated. */ struct dentry *target_dir, *nresult; /* * See if either the dentry we just got from the filesystem * or any alias for it is acceptable. This is always true * if this filesystem is exported without the subtreecheck * option. If the filesystem is exported with the subtree * check option there's a fair chance we need to look at * the parent directory in the file handle and make sure * it's connected to the filesystem root. */ alias = find_acceptable_alias(result, acceptable, context); if (alias) return alias; /* * Try to extract a dentry for the parent directory from the * file handle. If this fails we'll have to give up. */ err = -ESTALE; if (!nop->fh_to_parent) goto err_result; target_dir = nop->fh_to_parent(mnt->mnt_sb, fid, fh_len, fileid_type); if (!target_dir) goto err_result; err = PTR_ERR(target_dir); if (IS_ERR(target_dir)) goto err_result; /* * And as usual we need to make sure the parent directory is * connected to the filesystem root. The VFS really doesn't * like disconnected directories.. */ err = reconnect_path(mnt, target_dir, nbuf); if (err) { dput(target_dir); goto err_result; } /* * Now that we've got both a well-connected parent and a * dentry for the inode we're after, make sure that our * inode is actually connected to the parent. */ err = exportfs_get_name(mnt, target_dir, nbuf, result); if (err) { dput(target_dir); goto err_result; } inode_lock(target_dir->d_inode); nresult = lookup_one(mnt_idmap(mnt), nbuf, target_dir, strlen(nbuf)); if (!IS_ERR(nresult)) { if (unlikely(nresult->d_inode != result->d_inode)) { dput(nresult); nresult = ERR_PTR(-ESTALE); } } inode_unlock(target_dir->d_inode); /* * At this point we are done with the parent, but it's pinned * by the child dentry anyway. */ dput(target_dir); if (IS_ERR(nresult)) { err = PTR_ERR(nresult); goto err_result; } dput(result); result = nresult; /* * And finally make sure the dentry is actually acceptable * to NFSD. */ alias = find_acceptable_alias(result, acceptable, context); if (!alias) { err = -EACCES; goto err_result; } return alias; } err_result: dput(result); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(exportfs_decode_fh_raw); struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, int fh_len, int fileid_type, int (*acceptable)(void *, struct dentry *), void *context) { struct dentry *ret; ret = exportfs_decode_fh_raw(mnt, fid, fh_len, fileid_type, 0, acceptable, context); if (IS_ERR_OR_NULL(ret)) { if (ret == ERR_PTR(-ENOMEM)) return ret; return ERR_PTR(-ESTALE); } return ret; } EXPORT_SYMBOL_GPL(exportfs_decode_fh); MODULE_LICENSE("GPL"); |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 | // SPDX-License-Identifier: GPL-2.0-only /* * stack_o2cb.c * * Code which interfaces ocfs2 with the o2cb stack. * * Copyright (C) 2007 Oracle. All rights reserved. */ #include <linux/kernel.h> #include <linux/crc32.h> #include <linux/slab.h> #include <linux/module.h> /* Needed for AOP_TRUNCATED_PAGE in mlog_errno() */ #include <linux/fs.h> #include "cluster/masklog.h" #include "cluster/nodemanager.h" #include "cluster/heartbeat.h" #include "cluster/tcp.h" #include "stackglue.h" struct o2dlm_private { struct dlm_eviction_cb op_eviction_cb; }; static struct ocfs2_stack_plugin o2cb_stack; /* These should be identical */ #if (DLM_LOCK_IV != LKM_IVMODE) # error Lock modes do not match #endif #if (DLM_LOCK_NL != LKM_NLMODE) # error Lock modes do not match #endif #if (DLM_LOCK_CR != LKM_CRMODE) # error Lock modes do not match #endif #if (DLM_LOCK_CW != LKM_CWMODE) # error Lock modes do not match #endif #if (DLM_LOCK_PR != LKM_PRMODE) # error Lock modes do not match #endif #if (DLM_LOCK_PW != LKM_PWMODE) # error Lock modes do not match #endif #if (DLM_LOCK_EX != LKM_EXMODE) # error Lock modes do not match #endif static inline int mode_to_o2dlm(int mode) { BUG_ON(mode > LKM_MAXMODE); return mode; } static int flags_to_o2dlm(u32 flags) { int o2dlm_flags = 0; if (flags & DLM_LKF_NOQUEUE) o2dlm_flags |= LKM_NOQUEUE; if (flags & DLM_LKF_CANCEL) o2dlm_flags |= LKM_CANCEL; if (flags & DLM_LKF_CONVERT) o2dlm_flags |= LKM_CONVERT; if (flags & DLM_LKF_VALBLK) o2dlm_flags |= LKM_VALBLK; if (flags & DLM_LKF_IVVALBLK) o2dlm_flags |= LKM_INVVALBLK; if (flags & DLM_LKF_ORPHAN) o2dlm_flags |= LKM_ORPHAN; if (flags & DLM_LKF_FORCEUNLOCK) o2dlm_flags |= LKM_FORCE; if (flags & DLM_LKF_TIMEOUT) o2dlm_flags |= LKM_TIMEOUT; if (flags & DLM_LKF_LOCAL) o2dlm_flags |= LKM_LOCAL; return o2dlm_flags; } /* * Map an o2dlm status to standard errno values. * * o2dlm only uses a handful of these, and returns even fewer to the * caller. Still, we try to assign sane values to each error. * * The following value pairs have special meanings to dlmglue, thus * the right hand side needs to stay unique - never duplicate the * mapping elsewhere in the table! * * DLM_NORMAL: 0 * DLM_NOTQUEUED: -EAGAIN * DLM_CANCELGRANT: -EBUSY * DLM_CANCEL: -DLM_ECANCEL */ /* Keep in sync with dlmapi.h */ static int status_map[] = { [DLM_NORMAL] = 0, /* Success */ [DLM_GRANTED] = -EINVAL, [DLM_DENIED] = -EACCES, [DLM_DENIED_NOLOCKS] = -EACCES, [DLM_WORKING] = -EACCES, [DLM_BLOCKED] = -EINVAL, [DLM_BLOCKED_ORPHAN] = -EINVAL, [DLM_DENIED_GRACE_PERIOD] = -EACCES, [DLM_SYSERR] = -ENOMEM, /* It is what it is */ [DLM_NOSUPPORT] = -EPROTO, [DLM_CANCELGRANT] = -EBUSY, /* Cancel after grant */ [DLM_IVLOCKID] = -EINVAL, [DLM_SYNC] = -EINVAL, [DLM_BADTYPE] = -EINVAL, [DLM_BADRESOURCE] = -EINVAL, [DLM_MAXHANDLES] = -ENOMEM, [DLM_NOCLINFO] = -EINVAL, [DLM_NOLOCKMGR] = -EINVAL, [DLM_NOPURGED] = -EINVAL, [DLM_BADARGS] = -EINVAL, [DLM_VOID] = -EINVAL, [DLM_NOTQUEUED] = -EAGAIN, /* Trylock failed */ [DLM_IVBUFLEN] = -EINVAL, [DLM_CVTUNGRANT] = -EPERM, [DLM_BADPARAM] = -EINVAL, [DLM_VALNOTVALID] = -EINVAL, [DLM_REJECTED] = -EPERM, [DLM_ABORT] = -EINVAL, [DLM_CANCEL] = -DLM_ECANCEL, /* Successful cancel */ [DLM_IVRESHANDLE] = -EINVAL, [DLM_DEADLOCK] = -EDEADLK, [DLM_DENIED_NOASTS] = -EINVAL, [DLM_FORWARD] = -EINVAL, [DLM_TIMEOUT] = -ETIMEDOUT, [DLM_IVGROUPID] = -EINVAL, [DLM_VERS_CONFLICT] = -EOPNOTSUPP, [DLM_BAD_DEVICE_PATH] = -ENOENT, [DLM_NO_DEVICE_PERMISSION] = -EPERM, [DLM_NO_CONTROL_DEVICE] = -ENOENT, [DLM_RECOVERING] = -ENOTCONN, [DLM_MIGRATING] = -ERESTART, [DLM_MAXSTATS] = -EINVAL, }; static int dlm_status_to_errno(enum dlm_status status) { BUG_ON(status < 0 || status >= ARRAY_SIZE(status_map)); return status_map[status]; } static void o2dlm_lock_ast_wrapper(void *astarg) { struct ocfs2_dlm_lksb *lksb = astarg; lksb->lksb_conn->cc_proto->lp_lock_ast(lksb); } static void o2dlm_blocking_ast_wrapper(void *astarg, int level) { struct ocfs2_dlm_lksb *lksb = astarg; lksb->lksb_conn->cc_proto->lp_blocking_ast(lksb, level); } static void o2dlm_unlock_ast_wrapper(void *astarg, enum dlm_status status) { struct ocfs2_dlm_lksb *lksb = astarg; int error = dlm_status_to_errno(status); /* * In o2dlm, you can get both the lock_ast() for the lock being * granted and the unlock_ast() for the CANCEL failing. A * successful cancel sends DLM_NORMAL here. If the * lock grant happened before the cancel arrived, you get * DLM_CANCELGRANT. * * There's no need for the double-ast. If we see DLM_CANCELGRANT, * we just ignore it. We expect the lock_ast() to handle the * granted lock. */ if (status == DLM_CANCELGRANT) return; lksb->lksb_conn->cc_proto->lp_unlock_ast(lksb, error); } static int o2cb_dlm_lock(struct ocfs2_cluster_connection *conn, int mode, struct ocfs2_dlm_lksb *lksb, u32 flags, void *name, unsigned int namelen) { enum dlm_status status; int o2dlm_mode = mode_to_o2dlm(mode); int o2dlm_flags = flags_to_o2dlm(flags); int ret; status = dlmlock(conn->cc_lockspace, o2dlm_mode, &lksb->lksb_o2dlm, o2dlm_flags, name, namelen, o2dlm_lock_ast_wrapper, lksb, o2dlm_blocking_ast_wrapper); ret = dlm_status_to_errno(status); return ret; } static int o2cb_dlm_unlock(struct ocfs2_cluster_connection *conn, struct ocfs2_dlm_lksb *lksb, u32 flags) { enum dlm_status status; int o2dlm_flags = flags_to_o2dlm(flags); int ret; status = dlmunlock(conn->cc_lockspace, &lksb->lksb_o2dlm, o2dlm_flags, o2dlm_unlock_ast_wrapper, lksb); ret = dlm_status_to_errno(status); return ret; } static int o2cb_dlm_lock_status(struct ocfs2_dlm_lksb *lksb) { return dlm_status_to_errno(lksb->lksb_o2dlm.status); } /* * o2dlm aways has a "valid" LVB. If the dlm loses track of the LVB * contents, it will zero out the LVB. Thus the caller can always trust * the contents. */ static int o2cb_dlm_lvb_valid(struct ocfs2_dlm_lksb *lksb) { return 1; } static void *o2cb_dlm_lvb(struct ocfs2_dlm_lksb *lksb) { return (void *)(lksb->lksb_o2dlm.lvb); } static void o2cb_dump_lksb(struct ocfs2_dlm_lksb *lksb) { dlm_print_one_lock(lksb->lksb_o2dlm.lockid); } /* * Check if this node is heartbeating and is connected to all other * heartbeating nodes. */ static int o2cb_cluster_check(void) { u8 node_num; int i; unsigned long hbmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; unsigned long netmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; node_num = o2nm_this_node(); if (node_num == O2NM_MAX_NODES) { printk(KERN_ERR "o2cb: This node has not been configured.\n"); return -EINVAL; } /* * o2dlm expects o2net sockets to be created. If not, then * dlm_join_domain() fails with a stack of errors which are both cryptic * and incomplete. The idea here is to detect upfront whether we have * managed to connect to all nodes or not. If not, then list the nodes * to allow the user to check the configuration (incorrect IP, firewall, * etc.) Yes, this is racy. But its not the end of the world. */ #define O2CB_MAP_STABILIZE_COUNT 60 for (i = 0; i < O2CB_MAP_STABILIZE_COUNT; ++i) { o2hb_fill_node_map(hbmap, O2NM_MAX_NODES); if (!test_bit(node_num, hbmap)) { printk(KERN_ERR "o2cb: %s heartbeat has not been " "started.\n", (o2hb_global_heartbeat_active() ? "Global" : "Local")); return -EINVAL; } o2net_fill_node_map(netmap, O2NM_MAX_NODES); /* Force set the current node to allow easy compare */ set_bit(node_num, netmap); if (bitmap_equal(hbmap, netmap, O2NM_MAX_NODES)) return 0; if (i < O2CB_MAP_STABILIZE_COUNT - 1) msleep(1000); } printk(KERN_ERR "o2cb: This node could not connect to nodes:"); i = -1; while ((i = find_next_bit(hbmap, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) { if (!test_bit(i, netmap)) printk(" %u", i); } printk(".\n"); return -ENOTCONN; } /* * Called from the dlm when it's about to evict a node. This is how the * classic stack signals node death. */ static void o2dlm_eviction_cb(int node_num, void *data) { struct ocfs2_cluster_connection *conn = data; printk(KERN_NOTICE "o2cb: o2dlm has evicted node %d from domain %.*s\n", node_num, conn->cc_namelen, conn->cc_name); conn->cc_recovery_handler(node_num, conn->cc_recovery_data); } static int o2cb_cluster_connect(struct ocfs2_cluster_connection *conn) { int rc = 0; u32 dlm_key; struct dlm_ctxt *dlm; struct o2dlm_private *priv; struct dlm_protocol_version fs_version; BUG_ON(conn == NULL); BUG_ON(conn->cc_proto == NULL); /* Ensure cluster stack is up and all nodes are connected */ rc = o2cb_cluster_check(); if (rc) { printk(KERN_ERR "o2cb: Cluster check failed. Fix errors " "before retrying.\n"); goto out; } priv = kzalloc(sizeof(struct o2dlm_private), GFP_KERNEL); if (!priv) { rc = -ENOMEM; goto out_free; } /* This just fills the structure in. It is safe to pass conn. */ dlm_setup_eviction_cb(&priv->op_eviction_cb, o2dlm_eviction_cb, conn); conn->cc_private = priv; /* used by the dlm code to make message headers unique, each * node in this domain must agree on this. */ dlm_key = crc32_le(0, conn->cc_name, conn->cc_namelen); fs_version.pv_major = conn->cc_version.pv_major; fs_version.pv_minor = conn->cc_version.pv_minor; dlm = dlm_register_domain(conn->cc_name, dlm_key, &fs_version); if (IS_ERR(dlm)) { rc = PTR_ERR(dlm); mlog_errno(rc); goto out_free; } conn->cc_version.pv_major = fs_version.pv_major; conn->cc_version.pv_minor = fs_version.pv_minor; conn->cc_lockspace = dlm; dlm_register_eviction_cb(dlm, &priv->op_eviction_cb); out_free: if (rc) kfree(conn->cc_private); out: return rc; } static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn) { struct dlm_ctxt *dlm = conn->cc_lockspace; struct o2dlm_private *priv = conn->cc_private; dlm_unregister_eviction_cb(&priv->op_eviction_cb); conn->cc_private = NULL; kfree(priv); dlm_unregister_domain(dlm); conn->cc_lockspace = NULL; return 0; } static int o2cb_cluster_this_node(struct ocfs2_cluster_connection *conn, unsigned int *node) { int node_num; node_num = o2nm_this_node(); if (node_num == O2NM_INVALID_NODE_NUM) return -ENOENT; if (node_num >= O2NM_MAX_NODES) return -EOVERFLOW; *node = node_num; return 0; } static const struct ocfs2_stack_operations o2cb_stack_ops = { .connect = o2cb_cluster_connect, .disconnect = o2cb_cluster_disconnect, .this_node = o2cb_cluster_this_node, .dlm_lock = o2cb_dlm_lock, .dlm_unlock = o2cb_dlm_unlock, .lock_status = o2cb_dlm_lock_status, .lvb_valid = o2cb_dlm_lvb_valid, .lock_lvb = o2cb_dlm_lvb, .dump_lksb = o2cb_dump_lksb, }; static struct ocfs2_stack_plugin o2cb_stack = { .sp_name = "o2cb", .sp_ops = &o2cb_stack_ops, .sp_owner = THIS_MODULE, }; static int __init o2cb_stack_init(void) { return ocfs2_stack_glue_register(&o2cb_stack); } static void __exit o2cb_stack_exit(void) { ocfs2_stack_glue_unregister(&o2cb_stack); } MODULE_AUTHOR("Oracle"); MODULE_DESCRIPTION("ocfs2 driver for the classic o2cb stack"); MODULE_LICENSE("GPL"); module_init(o2cb_stack_init); module_exit(o2cb_stack_exit); |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 | /* * fs/nfs/idmap.c * * UID and GID to name mapping for clients. * * Copyright (c) 2002 The Regents of the University of Michigan. * All rights reserved. * * Marius Aamodt Eriksen <marius@umich.edu> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the University nor the names of its * contributors may be used to endorse or promote products derived * from this software without specific prior written permission. * * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ #include <linux/types.h> #include <linux/parser.h> #include <linux/fs.h> #include <net/net_namespace.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/nfs_fs.h> #include <linux/nfs_fs_sb.h> #include <linux/key.h> #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> #include <keys/request_key_auth-type.h> #include <linux/module.h> #include <linux/user_namespace.h> #include "internal.h" #include "netns.h" #include "nfs4idmap.h" #include "nfs4trace.h" #define NFS_UINT_MAXLEN 11 static const struct cred *id_resolver_cache; static struct key_type key_type_id_resolver_legacy; struct idmap_legacy_upcalldata { struct rpc_pipe_msg pipe_msg; struct idmap_msg idmap_msg; struct key *authkey; struct idmap *idmap; }; struct idmap { struct rpc_pipe_dir_object idmap_pdo; struct rpc_pipe *idmap_pipe; struct idmap_legacy_upcalldata *idmap_upcall_data; struct mutex idmap_mutex; struct user_namespace *user_ns; }; static struct user_namespace *idmap_userns(const struct idmap *idmap) { if (idmap && idmap->user_ns) return idmap->user_ns; return &init_user_ns; } /** * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields * @fattr: fully initialised struct nfs_fattr * @owner_name: owner name string cache * @group_name: group name string cache */ void nfs_fattr_init_names(struct nfs_fattr *fattr, struct nfs4_string *owner_name, struct nfs4_string *group_name) { fattr->owner_name = owner_name; fattr->group_name = group_name; } static void nfs_fattr_free_owner_name(struct nfs_fattr *fattr) { fattr->valid &= ~NFS_ATTR_FATTR_OWNER_NAME; kfree(fattr->owner_name->data); } static void nfs_fattr_free_group_name(struct nfs_fattr *fattr) { fattr->valid &= ~NFS_ATTR_FATTR_GROUP_NAME; kfree(fattr->group_name->data); } static bool nfs_fattr_map_owner_name(struct nfs_server *server, struct nfs_fattr *fattr) { struct nfs4_string *owner = fattr->owner_name; kuid_t uid; if (!(fattr->valid & NFS_ATTR_FATTR_OWNER_NAME)) return false; if (nfs_map_name_to_uid(server, owner->data, owner->len, &uid) == 0) { fattr->uid = uid; fattr->valid |= NFS_ATTR_FATTR_OWNER; } return true; } static bool nfs_fattr_map_group_name(struct nfs_server *server, struct nfs_fattr *fattr) { struct nfs4_string *group = fattr->group_name; kgid_t gid; if (!(fattr->valid & NFS_ATTR_FATTR_GROUP_NAME)) return false; if (nfs_map_group_to_gid(server, group->data, group->len, &gid) == 0) { fattr->gid = gid; fattr->valid |= NFS_ATTR_FATTR_GROUP; } return true; } /** * nfs_fattr_free_names - free up the NFSv4 owner and group strings * @fattr: a fully initialised nfs_fattr structure */ void nfs_fattr_free_names(struct nfs_fattr *fattr) { if (fattr->valid & NFS_ATTR_FATTR_OWNER_NAME) nfs_fattr_free_owner_name(fattr); if (fattr->valid & NFS_ATTR_FATTR_GROUP_NAME) nfs_fattr_free_group_name(fattr); } /** * nfs_fattr_map_and_free_names - map owner/group strings into uid/gid and free * @server: pointer to the filesystem nfs_server structure * @fattr: a fully initialised nfs_fattr structure * * This helper maps the cached NFSv4 owner/group strings in fattr into * their numeric uid/gid equivalents, and then frees the cached strings. */ void nfs_fattr_map_and_free_names(struct nfs_server *server, struct nfs_fattr *fattr) { if (nfs_fattr_map_owner_name(server, fattr)) nfs_fattr_free_owner_name(fattr); if (nfs_fattr_map_group_name(server, fattr)) nfs_fattr_free_group_name(fattr); } int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res) { unsigned long val; char buf[16]; if (memchr(name, '@', namelen) != NULL || namelen >= sizeof(buf)) return 0; memcpy(buf, name, namelen); buf[namelen] = '\0'; if (kstrtoul(buf, 0, &val) != 0) return 0; *res = val; return 1; } EXPORT_SYMBOL_GPL(nfs_map_string_to_numeric); static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen) { return snprintf(buf, buflen, "%u", id); } static struct key_type key_type_id_resolver = { .name = "id_resolver", .preparse = user_preparse, .free_preparse = user_free_preparse, .instantiate = generic_key_instantiate, .revoke = user_revoke, .destroy = user_destroy, .describe = user_describe, .read = user_read, }; int nfs_idmap_init(void) { struct cred *cred; struct key *keyring; int ret = 0; printk(KERN_NOTICE "NFS: Registering the %s key type\n", key_type_id_resolver.name); cred = prepare_kernel_cred(&init_task); if (!cred) return -ENOMEM; keyring = keyring_alloc(".id_resolver", GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred, (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ, KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); if (IS_ERR(keyring)) { ret = PTR_ERR(keyring); goto failed_put_cred; } ret = register_key_type(&key_type_id_resolver); if (ret < 0) goto failed_put_key; ret = register_key_type(&key_type_id_resolver_legacy); if (ret < 0) goto failed_reg_legacy; set_bit(KEY_FLAG_ROOT_CAN_CLEAR, &keyring->flags); cred->thread_keyring = keyring; cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; id_resolver_cache = cred; return 0; failed_reg_legacy: unregister_key_type(&key_type_id_resolver); failed_put_key: key_put(keyring); failed_put_cred: put_cred(cred); return ret; } void nfs_idmap_quit(void) { key_revoke(id_resolver_cache->thread_keyring); unregister_key_type(&key_type_id_resolver); unregister_key_type(&key_type_id_resolver_legacy); put_cred(id_resolver_cache); } /* * Assemble the description to pass to request_key() * This function will allocate a new string and update dest to point * at it. The caller is responsible for freeing dest. * * On error 0 is returned. Otherwise, the length of dest is returned. */ static ssize_t nfs_idmap_get_desc(const char *name, size_t namelen, const char *type, size_t typelen, char **desc) { char *cp; size_t desclen = typelen + namelen + 2; *desc = kmalloc(desclen, GFP_KERNEL); if (!*desc) return -ENOMEM; cp = *desc; memcpy(cp, type, typelen); cp += typelen; *cp++ = ':'; memcpy(cp, name, namelen); cp += namelen; *cp = '\0'; return desclen; } static struct key *nfs_idmap_request_key(const char *name, size_t namelen, const char *type, struct idmap *idmap) { char *desc; struct key *rkey = ERR_PTR(-EAGAIN); ssize_t ret; ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc); if (ret < 0) return ERR_PTR(ret); if (!idmap->user_ns || idmap->user_ns == &init_user_ns) rkey = request_key(&key_type_id_resolver, desc, ""); if (IS_ERR(rkey)) { mutex_lock(&idmap->idmap_mutex); rkey = request_key_with_auxdata(&key_type_id_resolver_legacy, desc, NULL, "", 0, idmap); mutex_unlock(&idmap->idmap_mutex); } if (!IS_ERR(rkey)) set_bit(KEY_FLAG_ROOT_CAN_INVAL, &rkey->flags); kfree(desc); return rkey; } static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, const char *type, void *data, size_t data_size, struct idmap *idmap) { const struct cred *saved_cred; struct key *rkey; const struct user_key_payload *payload; ssize_t ret; saved_cred = override_creds(id_resolver_cache); rkey = nfs_idmap_request_key(name, namelen, type, idmap); revert_creds(saved_cred); if (IS_ERR(rkey)) { ret = PTR_ERR(rkey); goto out; } rcu_read_lock(); rkey->perm |= KEY_USR_VIEW; ret = key_validate(rkey); if (ret < 0) goto out_up; payload = user_key_payload_rcu(rkey); if (IS_ERR_OR_NULL(payload)) { ret = PTR_ERR(payload); goto out_up; } ret = payload->datalen; if (ret > 0 && ret <= data_size) memcpy(data, payload->data, ret); else ret = -EINVAL; out_up: rcu_read_unlock(); key_put(rkey); out: return ret; } /* ID -> Name */ static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf, size_t buflen, struct idmap *idmap) { char id_str[NFS_UINT_MAXLEN]; int id_len; ssize_t ret; id_len = nfs_map_numeric_to_string(id, id_str, sizeof(id_str)); ret = nfs_idmap_get_key(id_str, id_len, type, buf, buflen, idmap); if (ret < 0) return -EINVAL; return ret; } /* Name -> ID */ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *type, __u32 *id, struct idmap *idmap) { char id_str[NFS_UINT_MAXLEN]; long id_long; ssize_t data_size; int ret = 0; data_size = nfs_idmap_get_key(name, namelen, type, id_str, NFS_UINT_MAXLEN, idmap); if (data_size <= 0) { ret = -EINVAL; } else { ret = kstrtol(id_str, 10, &id_long); if (!ret) *id = (__u32)id_long; } return ret; } /* idmap classic begins here */ enum { Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err }; static const match_table_t nfs_idmap_tokens = { { Opt_find_uid, "uid:%s" }, { Opt_find_gid, "gid:%s" }, { Opt_find_user, "user:%s" }, { Opt_find_group, "group:%s" }, { Opt_find_err, NULL } }; static int nfs_idmap_legacy_upcall(struct key *, void *); static ssize_t idmap_pipe_downcall(struct file *, const char __user *, size_t); static void idmap_release_pipe(struct inode *); static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *); static const struct rpc_pipe_ops idmap_upcall_ops = { .upcall = rpc_pipe_generic_upcall, .downcall = idmap_pipe_downcall, .release_pipe = idmap_release_pipe, .destroy_msg = idmap_pipe_destroy_msg, }; static struct key_type key_type_id_resolver_legacy = { .name = "id_legacy", .preparse = user_preparse, .free_preparse = user_free_preparse, .instantiate = generic_key_instantiate, .revoke = user_revoke, .destroy = user_destroy, .describe = user_describe, .read = user_read, .request_key = nfs_idmap_legacy_upcall, }; static void nfs_idmap_pipe_destroy(struct dentry *dir, struct rpc_pipe_dir_object *pdo) { struct idmap *idmap = pdo->pdo_data; struct rpc_pipe *pipe = idmap->idmap_pipe; if (pipe->dentry) { rpc_unlink(pipe->dentry); pipe->dentry = NULL; } } static int nfs_idmap_pipe_create(struct dentry *dir, struct rpc_pipe_dir_object *pdo) { struct idmap *idmap = pdo->pdo_data; struct rpc_pipe *pipe = idmap->idmap_pipe; struct dentry *dentry; dentry = rpc_mkpipe_dentry(dir, "idmap", idmap, pipe); if (IS_ERR(dentry)) return PTR_ERR(dentry); pipe->dentry = dentry; return 0; } static const struct rpc_pipe_dir_object_ops nfs_idmap_pipe_dir_object_ops = { .create = nfs_idmap_pipe_create, .destroy = nfs_idmap_pipe_destroy, }; int nfs_idmap_new(struct nfs_client *clp) { struct idmap *idmap; struct rpc_pipe *pipe; int error; idmap = kzalloc(sizeof(*idmap), GFP_KERNEL); if (idmap == NULL) return -ENOMEM; mutex_init(&idmap->idmap_mutex); idmap->user_ns = get_user_ns(clp->cl_rpcclient->cl_cred->user_ns); rpc_init_pipe_dir_object(&idmap->idmap_pdo, &nfs_idmap_pipe_dir_object_ops, idmap); pipe = rpc_mkpipe_data(&idmap_upcall_ops, 0); if (IS_ERR(pipe)) { error = PTR_ERR(pipe); goto err; } idmap->idmap_pipe = pipe; error = rpc_add_pipe_dir_object(clp->cl_net, &clp->cl_rpcclient->cl_pipedir_objects, &idmap->idmap_pdo); if (error) goto err_destroy_pipe; clp->cl_idmap = idmap; return 0; err_destroy_pipe: rpc_destroy_pipe_data(idmap->idmap_pipe); err: put_user_ns(idmap->user_ns); kfree(idmap); return error; } void nfs_idmap_delete(struct nfs_client *clp) { struct idmap *idmap = clp->cl_idmap; if (!idmap) return; clp->cl_idmap = NULL; rpc_remove_pipe_dir_object(clp->cl_net, &clp->cl_rpcclient->cl_pipedir_objects, &idmap->idmap_pdo); rpc_destroy_pipe_data(idmap->idmap_pipe); put_user_ns(idmap->user_ns); kfree(idmap); } static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap, struct idmap_msg *im, struct rpc_pipe_msg *msg) { substring_t substr; int token, ret; im->im_type = IDMAP_TYPE_GROUP; token = match_token(desc, nfs_idmap_tokens, &substr); switch (token) { case Opt_find_uid: im->im_type = IDMAP_TYPE_USER; fallthrough; case Opt_find_gid: im->im_conv = IDMAP_CONV_NAMETOID; ret = match_strlcpy(im->im_name, &substr, IDMAP_NAMESZ); break; case Opt_find_user: im->im_type = IDMAP_TYPE_USER; fallthrough; case Opt_find_group: im->im_conv = IDMAP_CONV_IDTONAME; ret = match_int(&substr, &im->im_id); if (ret) goto out; break; default: ret = -EINVAL; goto out; } msg->data = im; msg->len = sizeof(struct idmap_msg); out: return ret; } static bool nfs_idmap_prepare_pipe_upcall(struct idmap *idmap, struct idmap_legacy_upcalldata *data) { if (idmap->idmap_upcall_data != NULL) { WARN_ON_ONCE(1); return false; } idmap->idmap_upcall_data = data; return true; } static void nfs_idmap_complete_pipe_upcall(struct idmap_legacy_upcalldata *data, int ret) { complete_request_key(data->authkey, ret); key_put(data->authkey); kfree(data); } static void nfs_idmap_abort_pipe_upcall(struct idmap *idmap, struct idmap_legacy_upcalldata *data, int ret) { if (cmpxchg(&idmap->idmap_upcall_data, data, NULL) == data) nfs_idmap_complete_pipe_upcall(data, ret); } static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) { struct idmap_legacy_upcalldata *data; struct request_key_auth *rka = get_request_key_auth(authkey); struct rpc_pipe_msg *msg; struct idmap_msg *im; struct idmap *idmap = aux; struct key *key = rka->target_key; int ret = -ENOKEY; if (!aux) goto out1; /* msg and im are freed in idmap_pipe_destroy_msg */ ret = -ENOMEM; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) goto out1; msg = &data->pipe_msg; im = &data->idmap_msg; data->idmap = idmap; data->authkey = key_get(authkey); ret = nfs_idmap_prepare_message(key->description, idmap, im, msg); if (ret < 0) goto out2; ret = -EAGAIN; if (!nfs_idmap_prepare_pipe_upcall(idmap, data)) goto out2; ret = rpc_queue_upcall(idmap->idmap_pipe, msg); if (ret < 0) nfs_idmap_abort_pipe_upcall(idmap, data, ret); return ret; out2: kfree(data); out1: complete_request_key(authkey, ret); return ret; } static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data, size_t datalen) { return key_instantiate_and_link(key, data, datalen, id_resolver_cache->thread_keyring, authkey); } static int nfs_idmap_read_and_verify_message(struct idmap_msg *im, struct idmap_msg *upcall, struct key *key, struct key *authkey) { char id_str[NFS_UINT_MAXLEN]; size_t len; int ret = -ENOKEY; /* ret = -ENOKEY */ if (upcall->im_type != im->im_type || upcall->im_conv != im->im_conv) goto out; switch (im->im_conv) { case IDMAP_CONV_NAMETOID: if (strcmp(upcall->im_name, im->im_name) != 0) break; /* Note: here we store the NUL terminator too */ len = 1 + nfs_map_numeric_to_string(im->im_id, id_str, sizeof(id_str)); ret = nfs_idmap_instantiate(key, authkey, id_str, len); break; case IDMAP_CONV_IDTONAME: if (upcall->im_id != im->im_id) break; len = strlen(im->im_name); ret = nfs_idmap_instantiate(key, authkey, im->im_name, len); break; default: ret = -EINVAL; } out: return ret; } static ssize_t idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { struct request_key_auth *rka; struct rpc_inode *rpci = RPC_I(file_inode(filp)); struct idmap *idmap = (struct idmap *)rpci->private; struct idmap_legacy_upcalldata *data; struct key *authkey; struct idmap_msg im; size_t namelen_in; int ret = -ENOKEY; /* If instantiation is successful, anyone waiting for key construction * will have been woken up and someone else may now have used * idmap_key_cons - so after this point we may no longer touch it. */ data = xchg(&idmap->idmap_upcall_data, NULL); if (data == NULL) goto out_noupcall; authkey = data->authkey; rka = get_request_key_auth(authkey); if (mlen != sizeof(im)) { ret = -ENOSPC; goto out; } if (copy_from_user(&im, src, mlen) != 0) { ret = -EFAULT; goto out; } if (!(im.im_status & IDMAP_STATUS_SUCCESS)) { ret = -ENOKEY; goto out; } namelen_in = strnlen(im.im_name, IDMAP_NAMESZ); if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) { ret = -EINVAL; goto out; } ret = nfs_idmap_read_and_verify_message(&im, &data->idmap_msg, rka->target_key, authkey); if (ret >= 0) { key_set_timeout(rka->target_key, nfs_idmap_cache_timeout); ret = mlen; } out: nfs_idmap_complete_pipe_upcall(data, ret); out_noupcall: return ret; } static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg) { struct idmap_legacy_upcalldata *data = container_of(msg, struct idmap_legacy_upcalldata, pipe_msg); struct idmap *idmap = data->idmap; if (msg->errno) nfs_idmap_abort_pipe_upcall(idmap, data, msg->errno); } static void idmap_release_pipe(struct inode *inode) { struct rpc_inode *rpci = RPC_I(inode); struct idmap *idmap = (struct idmap *)rpci->private; struct idmap_legacy_upcalldata *data; data = xchg(&idmap->idmap_upcall_data, NULL); if (data) nfs_idmap_complete_pipe_upcall(data, -EPIPE); } int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, kuid_t *uid) { struct idmap *idmap = server->nfs_client->cl_idmap; __u32 id = -1; int ret = 0; if (!nfs_map_string_to_numeric(name, namelen, &id)) ret = nfs_idmap_lookup_id(name, namelen, "uid", &id, idmap); if (ret == 0) { *uid = make_kuid(idmap_userns(idmap), id); if (!uid_valid(*uid)) ret = -ERANGE; } trace_nfs4_map_name_to_uid(name, namelen, id, ret); return ret; } int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, kgid_t *gid) { struct idmap *idmap = server->nfs_client->cl_idmap; __u32 id = -1; int ret = 0; if (!nfs_map_string_to_numeric(name, namelen, &id)) ret = nfs_idmap_lookup_id(name, namelen, "gid", &id, idmap); if (ret == 0) { *gid = make_kgid(idmap_userns(idmap), id); if (!gid_valid(*gid)) ret = -ERANGE; } trace_nfs4_map_group_to_gid(name, namelen, id, ret); return ret; } int nfs_map_uid_to_name(const struct nfs_server *server, kuid_t uid, char *buf, size_t buflen) { struct idmap *idmap = server->nfs_client->cl_idmap; int ret = -EINVAL; __u32 id; id = from_kuid_munged(idmap_userns(idmap), uid); if (!(server->caps & NFS_CAP_UIDGID_NOMAP)) ret = nfs_idmap_lookup_name(id, "user", buf, buflen, idmap); if (ret < 0) ret = nfs_map_numeric_to_string(id, buf, buflen); trace_nfs4_map_uid_to_name(buf, ret, id, ret); return ret; } int nfs_map_gid_to_group(const struct nfs_server *server, kgid_t gid, char *buf, size_t buflen) { struct idmap *idmap = server->nfs_client->cl_idmap; int ret = -EINVAL; __u32 id; id = from_kgid_munged(idmap_userns(idmap), gid); if (!(server->caps & NFS_CAP_UIDGID_NOMAP)) ret = nfs_idmap_lookup_name(id, "group", buf, buflen, idmap); if (ret < 0) ret = nfs_map_numeric_to_string(id, buf, buflen); trace_nfs4_map_gid_to_group(buf, ret, id, ret); return ret; } |
| 10 10 10 10 10 10 10 10 10 10 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-or-later /* X.509 certificate parser * * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) "X.509: "fmt #include <linux/kernel.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/oid_registry.h> #include <crypto/public_key.h> #include "x509_parser.h" #include "x509.asn1.h" #include "x509_akid.asn1.h" struct x509_parse_context { struct x509_certificate *cert; /* Certificate being constructed */ unsigned long data; /* Start of data */ const void *key; /* Key data */ size_t key_size; /* Size of key data */ const void *params; /* Key parameters */ size_t params_size; /* Size of key parameters */ enum OID key_algo; /* Algorithm used by the cert's key */ enum OID last_oid; /* Last OID encountered */ enum OID sig_algo; /* Algorithm used to sign the cert */ u8 o_size; /* Size of organizationName (O) */ u8 cn_size; /* Size of commonName (CN) */ u8 email_size; /* Size of emailAddress */ u16 o_offset; /* Offset of organizationName (O) */ u16 cn_offset; /* Offset of commonName (CN) */ u16 email_offset; /* Offset of emailAddress */ unsigned raw_akid_size; const void *raw_akid; /* Raw authorityKeyId in ASN.1 */ const void *akid_raw_issuer; /* Raw directoryName in authorityKeyId */ unsigned akid_raw_issuer_size; }; /* * Free an X.509 certificate */ void x509_free_certificate(struct x509_certificate *cert) { if (cert) { public_key_free(cert->pub); public_key_signature_free(cert->sig); kfree(cert->issuer); kfree(cert->subject); kfree(cert->id); kfree(cert->skid); kfree(cert); } } EXPORT_SYMBOL_GPL(x509_free_certificate); /* * Parse an X.509 certificate */ struct x509_certificate *x509_cert_parse(const void *data, size_t datalen) { struct x509_certificate *cert __free(x509_free_certificate); struct x509_parse_context *ctx __free(kfree) = NULL; struct asymmetric_key_id *kid; long ret; cert = kzalloc(sizeof(struct x509_certificate), GFP_KERNEL); if (!cert) return ERR_PTR(-ENOMEM); cert->pub = kzalloc(sizeof(struct public_key), GFP_KERNEL); if (!cert->pub) return ERR_PTR(-ENOMEM); cert->sig = kzalloc(sizeof(struct public_key_signature), GFP_KERNEL); if (!cert->sig) return ERR_PTR(-ENOMEM); ctx = kzalloc(sizeof(struct x509_parse_context), GFP_KERNEL); if (!ctx) return ERR_PTR(-ENOMEM); ctx->cert = cert; ctx->data = (unsigned long)data; /* Attempt to decode the certificate */ ret = asn1_ber_decoder(&x509_decoder, ctx, data, datalen); if (ret < 0) return ERR_PTR(ret); /* Decode the AuthorityKeyIdentifier */ if (ctx->raw_akid) { pr_devel("AKID: %u %*phN\n", ctx->raw_akid_size, ctx->raw_akid_size, ctx->raw_akid); ret = asn1_ber_decoder(&x509_akid_decoder, ctx, ctx->raw_akid, ctx->raw_akid_size); if (ret < 0) { pr_warn("Couldn't decode AuthKeyIdentifier\n"); return ERR_PTR(ret); } } cert->pub->key = kmemdup(ctx->key, ctx->key_size, GFP_KERNEL); if (!cert->pub->key) return ERR_PTR(-ENOMEM); cert->pub->keylen = ctx->key_size; cert->pub->params = kmemdup(ctx->params, ctx->params_size, GFP_KERNEL); if (!cert->pub->params) return ERR_PTR(-ENOMEM); cert->pub->paramlen = ctx->params_size; cert->pub->algo = ctx->key_algo; /* Grab the signature bits */ ret = x509_get_sig_params(cert); if (ret < 0) return ERR_PTR(ret); /* Generate cert issuer + serial number key ID */ kid = asymmetric_key_generate_id(cert->raw_serial, cert->raw_serial_size, cert->raw_issuer, cert->raw_issuer_size); if (IS_ERR(kid)) return ERR_CAST(kid); cert->id = kid; /* Detect self-signed certificates */ ret = x509_check_for_self_signed(cert); if (ret < 0) return ERR_PTR(ret); return_ptr(cert); } EXPORT_SYMBOL_GPL(x509_cert_parse); /* * Note an OID when we find one for later processing when we know how * to interpret it. */ int x509_note_OID(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; ctx->last_oid = look_up_OID(value, vlen); if (ctx->last_oid == OID__NR) { char buffer[50]; sprint_oid(value, vlen, buffer, sizeof(buffer)); pr_debug("Unknown OID: [%lu] %s\n", (unsigned long)value - ctx->data, buffer); } return 0; } /* * Save the position of the TBS data so that we can check the signature over it * later. */ int x509_note_tbs_certificate(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; pr_debug("x509_note_tbs_certificate(,%zu,%02x,%ld,%zu)!\n", hdrlen, tag, (unsigned long)value - ctx->data, vlen); ctx->cert->tbs = value - hdrlen; ctx->cert->tbs_size = vlen + hdrlen; return 0; } /* * Record the algorithm that was used to sign this certificate. */ int x509_note_sig_algo(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; pr_debug("PubKey Algo: %u\n", ctx->last_oid); switch (ctx->last_oid) { default: return -ENOPKG; /* Unsupported combination */ case OID_sha1WithRSAEncryption: ctx->cert->sig->hash_algo = "sha1"; goto rsa_pkcs1; case OID_sha256WithRSAEncryption: ctx->cert->sig->hash_algo = "sha256"; goto rsa_pkcs1; case OID_sha384WithRSAEncryption: ctx->cert->sig->hash_algo = "sha384"; goto rsa_pkcs1; case OID_sha512WithRSAEncryption: ctx->cert->sig->hash_algo = "sha512"; goto rsa_pkcs1; case OID_sha224WithRSAEncryption: ctx->cert->sig->hash_algo = "sha224"; goto rsa_pkcs1; case OID_id_ecdsa_with_sha1: ctx->cert->sig->hash_algo = "sha1"; goto ecdsa; case OID_id_rsassa_pkcs1_v1_5_with_sha3_256: ctx->cert->sig->hash_algo = "sha3-256"; goto rsa_pkcs1; case OID_id_rsassa_pkcs1_v1_5_with_sha3_384: ctx->cert->sig->hash_algo = "sha3-384"; goto rsa_pkcs1; case OID_id_rsassa_pkcs1_v1_5_with_sha3_512: ctx->cert->sig->hash_algo = "sha3-512"; goto rsa_pkcs1; case OID_id_ecdsa_with_sha224: ctx->cert->sig->hash_algo = "sha224"; goto ecdsa; case OID_id_ecdsa_with_sha256: ctx->cert->sig->hash_algo = "sha256"; goto ecdsa; case OID_id_ecdsa_with_sha384: ctx->cert->sig->hash_algo = "sha384"; goto ecdsa; case OID_id_ecdsa_with_sha512: ctx->cert->sig->hash_algo = "sha512"; goto ecdsa; case OID_id_ecdsa_with_sha3_256: ctx->cert->sig->hash_algo = "sha3-256"; goto ecdsa; case OID_id_ecdsa_with_sha3_384: ctx->cert->sig->hash_algo = "sha3-384"; goto ecdsa; case OID_id_ecdsa_with_sha3_512: ctx->cert->sig->hash_algo = "sha3-512"; goto ecdsa; case OID_gost2012Signature256: ctx->cert->sig->hash_algo = "streebog256"; goto ecrdsa; case OID_gost2012Signature512: ctx->cert->sig->hash_algo = "streebog512"; goto ecrdsa; } rsa_pkcs1: ctx->cert->sig->pkey_algo = "rsa"; ctx->cert->sig->encoding = "pkcs1"; ctx->sig_algo = ctx->last_oid; return 0; ecrdsa: ctx->cert->sig->pkey_algo = "ecrdsa"; ctx->cert->sig->encoding = "raw"; ctx->sig_algo = ctx->last_oid; return 0; ecdsa: ctx->cert->sig->pkey_algo = "ecdsa"; ctx->cert->sig->encoding = "x962"; ctx->sig_algo = ctx->last_oid; return 0; } /* * Note the whereabouts and type of the signature. */ int x509_note_signature(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; pr_debug("Signature: alg=%u, size=%zu\n", ctx->last_oid, vlen); /* * In X.509 certificates, the signature's algorithm is stored in two * places: inside the TBSCertificate (the data that is signed), and * alongside the signature. These *must* match. */ if (ctx->last_oid != ctx->sig_algo) { pr_warn("signatureAlgorithm (%u) differs from tbsCertificate.signature (%u)\n", ctx->last_oid, ctx->sig_algo); return -EINVAL; } if (strcmp(ctx->cert->sig->pkey_algo, "rsa") == 0 || strcmp(ctx->cert->sig->pkey_algo, "ecrdsa") == 0 || strcmp(ctx->cert->sig->pkey_algo, "ecdsa") == 0) { /* Discard the BIT STRING metadata */ if (vlen < 1 || *(const u8 *)value != 0) return -EBADMSG; value++; vlen--; } ctx->cert->raw_sig = value; ctx->cert->raw_sig_size = vlen; return 0; } /* * Note the certificate serial number */ int x509_note_serial(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; ctx->cert->raw_serial = value; ctx->cert->raw_serial_size = vlen; return 0; } /* * Note some of the name segments from which we'll fabricate a name. */ int x509_extract_name_segment(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; switch (ctx->last_oid) { case OID_commonName: ctx->cn_size = vlen; ctx->cn_offset = (unsigned long)value - ctx->data; break; case OID_organizationName: ctx->o_size = vlen; ctx->o_offset = (unsigned long)value - ctx->data; break; case OID_email_address: ctx->email_size = vlen; ctx->email_offset = (unsigned long)value - ctx->data; break; default: break; } return 0; } /* * Fabricate and save the issuer and subject names */ static int x509_fabricate_name(struct x509_parse_context *ctx, size_t hdrlen, unsigned char tag, char **_name, size_t vlen) { const void *name, *data = (const void *)ctx->data; size_t namesize; char *buffer; if (*_name) return -EINVAL; /* Empty name string if no material */ if (!ctx->cn_size && !ctx->o_size && !ctx->email_size) { buffer = kmalloc(1, GFP_KERNEL); if (!buffer) return -ENOMEM; buffer[0] = 0; goto done; } if (ctx->cn_size && ctx->o_size) { /* Consider combining O and CN, but use only the CN if it is * prefixed by the O, or a significant portion thereof. */ namesize = ctx->cn_size; name = data + ctx->cn_offset; if (ctx->cn_size >= ctx->o_size && memcmp(data + ctx->cn_offset, data + ctx->o_offset, ctx->o_size) == 0) goto single_component; if (ctx->cn_size >= 7 && ctx->o_size >= 7 && memcmp(data + ctx->cn_offset, data + ctx->o_offset, 7) == 0) goto single_component; buffer = kmalloc(ctx->o_size + 2 + ctx->cn_size + 1, GFP_KERNEL); if (!buffer) return -ENOMEM; memcpy(buffer, data + ctx->o_offset, ctx->o_size); buffer[ctx->o_size + 0] = ':'; buffer[ctx->o_size + 1] = ' '; memcpy(buffer + ctx->o_size + 2, data + ctx->cn_offset, ctx->cn_size); buffer[ctx->o_size + 2 + ctx->cn_size] = 0; goto done; } else if (ctx->cn_size) { namesize = ctx->cn_size; name = data + ctx->cn_offset; } else if (ctx->o_size) { namesize = ctx->o_size; name = data + ctx->o_offset; } else { namesize = ctx->email_size; name = data + ctx->email_offset; } single_component: buffer = kmalloc(namesize + 1, GFP_KERNEL); if (!buffer) return -ENOMEM; memcpy(buffer, name, namesize); buffer[namesize] = 0; done: *_name = buffer; ctx->cn_size = 0; ctx->o_size = 0; ctx->email_size = 0; return 0; } int x509_note_issuer(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; struct asymmetric_key_id *kid; ctx->cert->raw_issuer = value; ctx->cert->raw_issuer_size = vlen; if (!ctx->cert->sig->auth_ids[2]) { kid = asymmetric_key_generate_id(value, vlen, "", 0); if (IS_ERR(kid)) return PTR_ERR(kid); ctx->cert->sig->auth_ids[2] = kid; } return x509_fabricate_name(ctx, hdrlen, tag, &ctx->cert->issuer, vlen); } int x509_note_subject(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; ctx->cert->raw_subject = value; ctx->cert->raw_subject_size = vlen; return x509_fabricate_name(ctx, hdrlen, tag, &ctx->cert->subject, vlen); } /* * Extract the parameters for the public key */ int x509_note_params(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; /* * AlgorithmIdentifier is used three times in the x509, we should skip * first and ignore third, using second one which is after subject and * before subjectPublicKey. */ if (!ctx->cert->raw_subject || ctx->key) return 0; ctx->params = value - hdrlen; ctx->params_size = vlen + hdrlen; return 0; } /* * Extract the data for the public key algorithm */ int x509_extract_key_data(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; enum OID oid; ctx->key_algo = ctx->last_oid; switch (ctx->last_oid) { case OID_rsaEncryption: ctx->cert->pub->pkey_algo = "rsa"; break; case OID_gost2012PKey256: case OID_gost2012PKey512: ctx->cert->pub->pkey_algo = "ecrdsa"; break; case OID_id_ecPublicKey: if (parse_OID(ctx->params, ctx->params_size, &oid) != 0) return -EBADMSG; switch (oid) { case OID_id_prime192v1: ctx->cert->pub->pkey_algo = "ecdsa-nist-p192"; break; case OID_id_prime256v1: ctx->cert->pub->pkey_algo = "ecdsa-nist-p256"; break; case OID_id_ansip384r1: ctx->cert->pub->pkey_algo = "ecdsa-nist-p384"; break; case OID_id_ansip521r1: ctx->cert->pub->pkey_algo = "ecdsa-nist-p521"; break; default: return -ENOPKG; } break; default: return -ENOPKG; } /* Discard the BIT STRING metadata */ if (vlen < 1 || *(const u8 *)value != 0) return -EBADMSG; ctx->key = value + 1; ctx->key_size = vlen - 1; return 0; } /* The keyIdentifier in AuthorityKeyIdentifier SEQUENCE is tag(CONT,PRIM,0) */ #define SEQ_TAG_KEYID (ASN1_CONT << 6) /* * Process certificate extensions that are used to qualify the certificate. */ int x509_process_extension(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; struct asymmetric_key_id *kid; const unsigned char *v = value; pr_debug("Extension: %u\n", ctx->last_oid); if (ctx->last_oid == OID_subjectKeyIdentifier) { /* Get hold of the key fingerprint */ if (ctx->cert->skid || vlen < 3) return -EBADMSG; if (v[0] != ASN1_OTS || v[1] != vlen - 2) return -EBADMSG; v += 2; vlen -= 2; ctx->cert->raw_skid_size = vlen; ctx->cert->raw_skid = v; kid = asymmetric_key_generate_id(v, vlen, "", 0); if (IS_ERR(kid)) return PTR_ERR(kid); ctx->cert->skid = kid; pr_debug("subjkeyid %*phN\n", kid->len, kid->data); return 0; } if (ctx->last_oid == OID_keyUsage) { /* * Get hold of the keyUsage bit string * v[1] is the encoding size * (Expect either 0x02 or 0x03, making it 1 or 2 bytes) * v[2] is the number of unused bits in the bit string * (If >= 3 keyCertSign is missing when v[1] = 0x02) * v[3] and possibly v[4] contain the bit string * * From RFC 5280 4.2.1.3: * 0x04 is where keyCertSign lands in this bit string * 0x80 is where digitalSignature lands in this bit string */ if (v[0] != ASN1_BTS) return -EBADMSG; if (vlen < 4) return -EBADMSG; if (v[2] >= 8) return -EBADMSG; if (v[3] & 0x80) ctx->cert->pub->key_eflags |= 1 << KEY_EFLAG_DIGITALSIG; if (v[1] == 0x02 && v[2] <= 2 && (v[3] & 0x04)) ctx->cert->pub->key_eflags |= 1 << KEY_EFLAG_KEYCERTSIGN; else if (vlen > 4 && v[1] == 0x03 && (v[3] & 0x04)) ctx->cert->pub->key_eflags |= 1 << KEY_EFLAG_KEYCERTSIGN; return 0; } if (ctx->last_oid == OID_authorityKeyIdentifier) { /* Get hold of the CA key fingerprint */ ctx->raw_akid = v; ctx->raw_akid_size = vlen; return 0; } if (ctx->last_oid == OID_basicConstraints) { /* * Get hold of the basicConstraints * v[1] is the encoding size * (Expect 0x2 or greater, making it 1 or more bytes) * v[2] is the encoding type * (Expect an ASN1_BOOL for the CA) * v[3] is the contents of the ASN1_BOOL * (Expect 1 if the CA is TRUE) * vlen should match the entire extension size */ if (v[0] != (ASN1_CONS_BIT | ASN1_SEQ)) return -EBADMSG; if (vlen < 2) return -EBADMSG; if (v[1] != vlen - 2) return -EBADMSG; if (vlen >= 4 && v[1] != 0 && v[2] == ASN1_BOOL && v[3] == 1) ctx->cert->pub->key_eflags |= 1 << KEY_EFLAG_CA; return 0; } return 0; } /** * x509_decode_time - Decode an X.509 time ASN.1 object * @_t: The time to fill in * @hdrlen: The length of the object header * @tag: The object tag * @value: The object value * @vlen: The size of the object value * * Decode an ASN.1 universal time or generalised time field into a struct the * kernel can handle and check it for validity. The time is decoded thus: * * [RFC5280 §4.1.2.5] * CAs conforming to this profile MUST always encode certificate validity * dates through the year 2049 as UTCTime; certificate validity dates in * 2050 or later MUST be encoded as GeneralizedTime. Conforming * applications MUST be able to process validity dates that are encoded in * either UTCTime or GeneralizedTime. */ int x509_decode_time(time64_t *_t, size_t hdrlen, unsigned char tag, const unsigned char *value, size_t vlen) { static const unsigned char month_lengths[] = { 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31 }; const unsigned char *p = value; unsigned year, mon, day, hour, min, sec, mon_len; #define dec2bin(X) ({ unsigned char x = (X) - '0'; if (x > 9) goto invalid_time; x; }) #define DD2bin(P) ({ unsigned x = dec2bin(P[0]) * 10 + dec2bin(P[1]); P += 2; x; }) if (tag == ASN1_UNITIM) { /* UTCTime: YYMMDDHHMMSSZ */ if (vlen != 13) goto unsupported_time; year = DD2bin(p); if (year >= 50) year += 1900; else year += 2000; } else if (tag == ASN1_GENTIM) { /* GenTime: YYYYMMDDHHMMSSZ */ if (vlen != 15) goto unsupported_time; year = DD2bin(p) * 100 + DD2bin(p); if (year >= 1950 && year <= 2049) goto invalid_time; } else { goto unsupported_time; } mon = DD2bin(p); day = DD2bin(p); hour = DD2bin(p); min = DD2bin(p); sec = DD2bin(p); if (*p != 'Z') goto unsupported_time; if (year < 1970 || mon < 1 || mon > 12) goto invalid_time; mon_len = month_lengths[mon - 1]; if (mon == 2) { if (year % 4 == 0) { mon_len = 29; if (year % 100 == 0) { mon_len = 28; if (year % 400 == 0) mon_len = 29; } } } if (day < 1 || day > mon_len || hour > 24 || /* ISO 8601 permits 24:00:00 as midnight tomorrow */ min > 59 || sec > 60) /* ISO 8601 permits leap seconds [X.680 46.3] */ goto invalid_time; *_t = mktime64(year, mon, day, hour, min, sec); return 0; unsupported_time: pr_debug("Got unsupported time [tag %02x]: '%*phN'\n", tag, (int)vlen, value); return -EBADMSG; invalid_time: pr_debug("Got invalid time [tag %02x]: '%*phN'\n", tag, (int)vlen, value); return -EBADMSG; } EXPORT_SYMBOL_GPL(x509_decode_time); int x509_note_not_before(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; return x509_decode_time(&ctx->cert->valid_from, hdrlen, tag, value, vlen); } int x509_note_not_after(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; return x509_decode_time(&ctx->cert->valid_to, hdrlen, tag, value, vlen); } /* * Note a key identifier-based AuthorityKeyIdentifier */ int x509_akid_note_kid(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; struct asymmetric_key_id *kid; pr_debug("AKID: keyid: %*phN\n", (int)vlen, value); if (ctx->cert->sig->auth_ids[1]) return 0; kid = asymmetric_key_generate_id(value, vlen, "", 0); if (IS_ERR(kid)) return PTR_ERR(kid); pr_debug("authkeyid %*phN\n", kid->len, kid->data); ctx->cert->sig->auth_ids[1] = kid; return 0; } /* * Note a directoryName in an AuthorityKeyIdentifier */ int x509_akid_note_name(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; pr_debug("AKID: name: %*phN\n", (int)vlen, value); ctx->akid_raw_issuer = value; ctx->akid_raw_issuer_size = vlen; return 0; } /* * Note a serial number in an AuthorityKeyIdentifier */ int x509_akid_note_serial(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; struct asymmetric_key_id *kid; pr_debug("AKID: serial: %*phN\n", (int)vlen, value); if (!ctx->akid_raw_issuer || ctx->cert->sig->auth_ids[0]) return 0; kid = asymmetric_key_generate_id(value, vlen, ctx->akid_raw_issuer, ctx->akid_raw_issuer_size); if (IS_ERR(kid)) return PTR_ERR(kid); pr_debug("authkeyid %*phN\n", kid->len, kid->data); ctx->cert->sig->auth_ids[0] = kid; return 0; } |
| 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 | // SPDX-License-Identifier: GPL-2.0 /* RTT/RTO calculation. * * Adapted from TCP for AF_RXRPC by David Howells (dhowells@redhat.com) * * https://tools.ietf.org/html/rfc6298 * https://tools.ietf.org/html/rfc1122#section-4.2.3.1 * http://ccr.sigcomm.org/archive/1995/jan95/ccr-9501-partridge87.pdf */ #include <linux/net.h> #include "ar-internal.h" #define RXRPC_RTO_MAX (120 * USEC_PER_SEC) #define RXRPC_TIMEOUT_INIT ((unsigned int)(1 * MSEC_PER_SEC)) /* RFC6298 2.1 initial RTO value */ #define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) { return 200; } static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer) { return (peer->srtt_us >> 3) + peer->rttvar_us; } static u32 rxrpc_bound_rto(u32 rto) { return min(rto, RXRPC_RTO_MAX); } /* * Called to compute a smoothed rtt estimate. The data fed to this * routine either comes from timestamps, or from segments that were * known _not_ to have been retransmitted [see Karn/Partridge * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88 * piece by Van Jacobson. * NOTE: the next three routines used to be one big routine. * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics */ static void rxrpc_rtt_estimator(struct rxrpc_peer *peer, long sample_rtt_us) { long m = sample_rtt_us; /* RTT */ u32 srtt = peer->srtt_us; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev * are scaled versions of rtt and mean deviation. * This is designed to be as fast as possible * m stands for "measurement". * * On a 1990 paper the rto value is changed to: * RTO = rtt + 4 * mdev * * Funny. This algorithm seems to be very broken. * These formulae increase RTO, when it should be decreased, increase * too slowly, when it should be increased quickly, decrease too quickly * etc. I guess in BSD RTO takes ONE value, so that it is absolutely * does not matter how to _calculate_ it. Seems, it was trap * that VJ failed to avoid. 8) */ if (srtt != 0) { m -= (srtt >> 3); /* m is now error in rtt est */ srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ m -= (peer->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain * for mdev in this case (alpha*beta). * Like Eifel it also prevents growth of rto, * but also it limits too fast rto decreases, * happening in pure Eifel. */ if (m > 0) m >>= 3; } else { m -= (peer->mdev_us >> 2); /* similar update on mdev */ } peer->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ if (peer->mdev_us > peer->mdev_max_us) { peer->mdev_max_us = peer->mdev_us; if (peer->mdev_max_us > peer->rttvar_us) peer->rttvar_us = peer->mdev_max_us; } } else { /* no previous measure. */ srtt = m << 3; /* take the measured time to be rtt */ peer->mdev_us = m << 1; /* make sure rto = 3*rtt */ peer->rttvar_us = max(peer->mdev_us, rxrpc_rto_min_us(peer)); peer->mdev_max_us = peer->rttvar_us; } peer->srtt_us = max(1U, srtt); } /* * Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ static void rxrpc_set_rto(struct rxrpc_peer *peer) { u32 rto; /* 1. If rtt variance happened to be less 50msec, it is hallucination. * It cannot be less due to utterly erratic ACK generation made * at least by solaris and freebsd. "Erratic ACKs" has _nothing_ * to do with delayed acks, because at cwnd>2 true delack timeout * is invisible. Actually, Linux-2.4 also generates erratic * ACKs in some circumstances. */ rto = __rxrpc_set_rto(peer); /* 2. Fixups made earlier cannot be right. * If we do not estimate RTO correctly without them, * all the algo is pure shit and should be replaced * with correct one. It is exactly, which we pretend to do. */ /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo * guarantees that rto is higher. */ peer->rto_us = rxrpc_bound_rto(rto); } static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us) { if (rtt_us < 0) return; //rxrpc_update_rtt_min(peer, rtt_us); rxrpc_rtt_estimator(peer, rtt_us); rxrpc_set_rto(peer); /* RFC6298: only reset backoff on valid RTT measurement. */ peer->backoff = 0; } /* * Add RTT information to cache. This is called in softirq mode and has * exclusive access to the peer RTT data. */ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, int rtt_slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, ktime_t send_time, ktime_t resp_time) { struct rxrpc_peer *peer = call->peer; s64 rtt_us; rtt_us = ktime_to_us(ktime_sub(resp_time, send_time)); if (rtt_us < 0) return; spin_lock(&peer->rtt_input_lock); rxrpc_ack_update_rtt(peer, rtt_us); if (peer->rtt_count < 3) peer->rtt_count++; spin_unlock(&peer->rtt_input_lock); trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, peer->srtt_us >> 3, peer->rto_us); } /* * Get the retransmission timeout to set in nanoseconds, backing it off each * time we retransmit. */ ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans) { u64 timo_us; u32 backoff = READ_ONCE(peer->backoff); timo_us = peer->rto_us; timo_us <<= backoff; if (retrans && timo_us * 2 <= RXRPC_RTO_MAX) WRITE_ONCE(peer->backoff, backoff + 1); if (timo_us < 1) timo_us = 1; return ns_to_ktime(timo_us * NSEC_PER_USEC); } void rxrpc_peer_init_rtt(struct rxrpc_peer *peer) { peer->rto_us = RXRPC_TIMEOUT_INIT; peer->mdev_us = RXRPC_TIMEOUT_INIT; peer->backoff = 0; //minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U); } |
| 2 25 8 8 8 8 2 2 12 18 8 2 2 8 7 2 2 2 2 7 7 7 2 5 5 7 2 5 12 1 2 7 7 5 5 5 5 5 5 5 4 8 10 5 4 5 5 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * ext4.h * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/include/linux/minix_fs.h * * Copyright (C) 1991, 1992 Linus Torvalds */ #ifndef _EXT4_H #define _EXT4_H #include <linux/refcount.h> #include <linux/types.h> #include <linux/blkdev.h> #include <linux/magic.h> #include <linux/jbd2.h> #include <linux/quota.h> #include <linux/rwsem.h> #include <linux/rbtree.h> #include <linux/seqlock.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/wait.h> #include <linux/sched/signal.h> #include <linux/blockgroup_lock.h> #include <linux/percpu_counter.h> #include <linux/ratelimit.h> #include <crypto/hash.h> #include <linux/falloc.h> #include <linux/percpu-rwsem.h> #include <linux/fiemap.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif #include <uapi/linux/ext4.h> #include <linux/fscrypt.h> #include <linux/fsverity.h> #include <linux/compiler.h> /* * The fourth extended filesystem constants/structures */ /* * with AGGRESSIVE_CHECK allocator runs consistency checks over * structures. these checks slow things down a lot */ #define AGGRESSIVE_CHECK__ /* * with DOUBLE_CHECK defined mballoc creates persistent in-core * bitmaps, maintains and uses them to check for double allocations */ #define DOUBLE_CHECK__ /* * Define EXT4FS_DEBUG to produce debug messages */ #undef EXT4FS_DEBUG /* * Debug code */ #ifdef EXT4FS_DEBUG #define ext4_debug(f, a...) \ do { \ printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:", \ __FILE__, __LINE__, __func__); \ printk(KERN_DEBUG f, ## a); \ } while (0) #else #define ext4_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif /* * Turn on EXT_DEBUG to enable ext4_ext_show_path/leaf/move in extents.c */ #define EXT_DEBUG__ /* * Dynamic printk for controlled extents debugging. */ #ifdef CONFIG_EXT4_DEBUG #define ext_debug(ino, fmt, ...) \ pr_debug("[%s/%d] EXT4-fs (%s): ino %lu: (%s, %d): %s:" fmt, \ current->comm, task_pid_nr(current), \ ino->i_sb->s_id, ino->i_ino, __FILE__, __LINE__, \ __func__, ##__VA_ARGS__) #else #define ext_debug(ino, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif #define ASSERT(assert) \ do { \ if (unlikely(!(assert))) { \ printk(KERN_EMERG \ "Assertion failure in %s() at %s:%d: '%s'\n", \ __func__, __FILE__, __LINE__, #assert); \ BUG(); \ } \ } while (0) /* data type for block offset of block group */ typedef int ext4_grpblk_t; /* data type for filesystem-wide blocks number */ typedef unsigned long long ext4_fsblk_t; /* data type for file logical block number */ typedef __u32 ext4_lblk_t; /* data type for block group number */ typedef unsigned int ext4_group_t; enum SHIFT_DIRECTION { SHIFT_LEFT = 0, SHIFT_RIGHT, }; /* * For each criteria, mballoc has slightly different way of finding * the required blocks nad usually, higher the criteria the slower the * allocation. We start at lower criterias and keep falling back to * higher ones if we are not able to find any blocks. Lower (earlier) * criteria are faster. */ enum criteria { /* * Used when number of blocks needed is a power of 2. This * doesn't trigger any disk IO except prefetch and is the * fastest criteria. */ CR_POWER2_ALIGNED, /* * Tries to lookup in-memory data structures to find the most * suitable group that satisfies goal request. No disk IO * except block prefetch. */ CR_GOAL_LEN_FAST, /* * Same as CR_GOAL_LEN_FAST but is allowed to reduce the goal * length to the best available length for faster allocation. */ CR_BEST_AVAIL_LEN, /* * Reads each block group sequentially, performing disk IO if * necessary, to find find_suitable block group. Tries to * allocate goal length but might trim the request if nothing * is found after enough tries. */ CR_GOAL_LEN_SLOW, /* * Finds the first free set of blocks and allocates * those. This is only used in rare cases when * CR_GOAL_LEN_SLOW also fails to allocate anything. */ CR_ANY_FREE, /* * Number of criterias defined. */ EXT4_MB_NUM_CRS }; /* * Flags used in mballoc's allocation_context flags field. * * Also used to show what's going on for debugging purposes when the * flag field is exported via the traceport interface */ /* prefer goal again. length */ #define EXT4_MB_HINT_MERGE 0x0001 /* blocks already reserved */ #define EXT4_MB_HINT_RESERVED 0x0002 /* metadata is being allocated */ #define EXT4_MB_HINT_METADATA 0x0004 /* first blocks in the file */ #define EXT4_MB_HINT_FIRST 0x0008 /* search for the best chunk */ #define EXT4_MB_HINT_BEST 0x0010 /* data is being allocated */ #define EXT4_MB_HINT_DATA 0x0020 /* don't preallocate (for tails) */ #define EXT4_MB_HINT_NOPREALLOC 0x0040 /* allocate for locality group */ #define EXT4_MB_HINT_GROUP_ALLOC 0x0080 /* allocate goal blocks or none */ #define EXT4_MB_HINT_GOAL_ONLY 0x0100 /* goal is meaningful */ #define EXT4_MB_HINT_TRY_GOAL 0x0200 /* blocks already pre-reserved by delayed allocation */ #define EXT4_MB_DELALLOC_RESERVED 0x0400 /* We are doing stream allocation */ #define EXT4_MB_STREAM_ALLOC 0x0800 /* Use reserved root blocks if needed */ #define EXT4_MB_USE_ROOT_BLOCKS 0x1000 /* Use blocks from reserved pool */ #define EXT4_MB_USE_RESERVED 0x2000 /* Do strict check for free blocks while retrying block allocation */ #define EXT4_MB_STRICT_CHECK 0x4000 /* Large fragment size list lookup succeeded at least once for * CR_POWER2_ALIGNED */ #define EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED 0x8000 /* Avg fragment size rb tree lookup succeeded at least once for * CR_GOAL_LEN_FAST */ #define EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED 0x00010000 /* Avg fragment size rb tree lookup succeeded at least once for * CR_BEST_AVAIL_LEN */ #define EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED 0x00020000 struct ext4_allocation_request { /* target inode for block we're allocating */ struct inode *inode; /* how many blocks we want to allocate */ unsigned int len; /* logical block in target inode */ ext4_lblk_t logical; /* the closest logical allocated block to the left */ ext4_lblk_t lleft; /* the closest logical allocated block to the right */ ext4_lblk_t lright; /* phys. target (a hint) */ ext4_fsblk_t goal; /* phys. block for the closest logical allocated block to the left */ ext4_fsblk_t pleft; /* phys. block for the closest logical allocated block to the right */ ext4_fsblk_t pright; /* flags. see above EXT4_MB_HINT_* */ unsigned int flags; }; /* * Logical to physical block mapping, used by ext4_map_blocks() * * This structure is used to pass requests into ext4_map_blocks() as * well as to store the information returned by ext4_map_blocks(). It * takes less room on the stack than a struct buffer_head. */ #define EXT4_MAP_NEW BIT(BH_New) #define EXT4_MAP_MAPPED BIT(BH_Mapped) #define EXT4_MAP_UNWRITTEN BIT(BH_Unwritten) #define EXT4_MAP_BOUNDARY BIT(BH_Boundary) #define EXT4_MAP_DELAYED BIT(BH_Delay) #define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\ EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\ EXT4_MAP_DELAYED) struct ext4_map_blocks { ext4_fsblk_t m_pblk; ext4_lblk_t m_lblk; unsigned int m_len; unsigned int m_flags; }; /* * Block validity checking, system zone rbtree. */ struct ext4_system_blocks { struct rb_root root; struct rcu_head rcu; }; /* * Flags for ext4_io_end->flags */ #define EXT4_IO_END_UNWRITTEN 0x0001 struct ext4_io_end_vec { struct list_head list; /* list of io_end_vec */ loff_t offset; /* offset in the file */ ssize_t size; /* size of the extent */ }; /* * For converting unwritten extents on a work queue. 'handle' is used for * buffered writeback. */ typedef struct ext4_io_end { struct list_head list; /* per-file finished IO list */ handle_t *handle; /* handle reserved for extent * conversion */ struct inode *inode; /* file being written to */ struct bio *bio; /* Linked list of completed * bios covering the extent */ unsigned int flag; /* unwritten or not */ refcount_t count; /* reference counter */ struct list_head list_vec; /* list of ext4_io_end_vec */ } ext4_io_end_t; struct ext4_io_submit { struct writeback_control *io_wbc; struct bio *io_bio; ext4_io_end_t *io_end; sector_t io_next_block; }; /* * Special inodes numbers */ #define EXT4_BAD_INO 1 /* Bad blocks inode */ #define EXT4_ROOT_INO 2 /* Root inode */ #define EXT4_USR_QUOTA_INO 3 /* User quota inode */ #define EXT4_GRP_QUOTA_INO 4 /* Group quota inode */ #define EXT4_BOOT_LOADER_INO 5 /* Boot loader inode */ #define EXT4_UNDEL_DIR_INO 6 /* Undelete directory inode */ #define EXT4_RESIZE_INO 7 /* Reserved group descriptors inode */ #define EXT4_JOURNAL_INO 8 /* Journal inode */ /* First non-reserved inode for old ext4 filesystems */ #define EXT4_GOOD_OLD_FIRST_INO 11 /* * Maximal count of links to a file */ #define EXT4_LINK_MAX 65000 /* * Macro-instructions used to manage several block sizes */ #define EXT4_MIN_BLOCK_SIZE 1024 #define EXT4_MAX_BLOCK_SIZE 65536 #define EXT4_MIN_BLOCK_LOG_SIZE 10 #define EXT4_MAX_BLOCK_LOG_SIZE 16 #define EXT4_MAX_CLUSTER_LOG_SIZE 30 #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) #else # define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size) #endif #define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof(__u32)) #define EXT4_CLUSTER_SIZE(s) (EXT4_BLOCK_SIZE(s) << \ EXT4_SB(s)->s_cluster_bits) #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) # define EXT4_CLUSTER_BITS(s) (EXT4_SB(s)->s_cluster_bits) #else # define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10) #endif #ifdef __KERNEL__ #define EXT4_ADDR_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_addr_per_block_bits) #define EXT4_INODE_SIZE(s) (EXT4_SB(s)->s_inode_size) #define EXT4_FIRST_INO(s) (EXT4_SB(s)->s_first_ino) #else #define EXT4_INODE_SIZE(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \ EXT4_GOOD_OLD_INODE_SIZE : \ (s)->s_inode_size) #define EXT4_FIRST_INO(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \ EXT4_GOOD_OLD_FIRST_INO : \ (s)->s_first_ino) #endif #define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits))) #define EXT4_MAX_BLOCKS(size, offset, blkbits) \ ((EXT4_BLOCK_ALIGN(size + offset, blkbits) >> blkbits) - (offset >> \ blkbits)) /* Translate a block number to a cluster number */ #define EXT4_B2C(sbi, blk) ((blk) >> (sbi)->s_cluster_bits) /* Translate a cluster number to a block number */ #define EXT4_C2B(sbi, cluster) ((cluster) << (sbi)->s_cluster_bits) /* Translate # of blks to # of clusters */ #define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \ (sbi)->s_cluster_bits) /* Mask out the low bits to get the starting block of the cluster */ #define EXT4_PBLK_CMASK(s, pblk) ((pblk) & \ ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1)) #define EXT4_LBLK_CMASK(s, lblk) ((lblk) & \ ~((ext4_lblk_t) (s)->s_cluster_ratio - 1)) /* Fill in the low bits to get the last block of the cluster */ #define EXT4_LBLK_CFILL(sbi, lblk) ((lblk) | \ ((ext4_lblk_t) (sbi)->s_cluster_ratio - 1)) /* Get the cluster offset */ #define EXT4_PBLK_COFF(s, pblk) ((pblk) & \ ((ext4_fsblk_t) (s)->s_cluster_ratio - 1)) #define EXT4_LBLK_COFF(s, lblk) ((lblk) & \ ((ext4_lblk_t) (s)->s_cluster_ratio - 1)) /* * Structure of a blocks group descriptor */ struct ext4_group_desc { __le32 bg_block_bitmap_lo; /* Blocks bitmap block */ __le32 bg_inode_bitmap_lo; /* Inodes bitmap block */ __le32 bg_inode_table_lo; /* Inodes table block */ __le16 bg_free_blocks_count_lo;/* Free blocks count */ __le16 bg_free_inodes_count_lo;/* Free inodes count */ __le16 bg_used_dirs_count_lo; /* Directories count */ __le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */ __le32 bg_exclude_bitmap_lo; /* Exclude bitmap for snapshots */ __le16 bg_block_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+bbitmap) LE */ __le16 bg_inode_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+ibitmap) LE */ __le16 bg_itable_unused_lo; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ __le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ __le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */ __le32 bg_inode_table_hi; /* Inodes table block MSB */ __le16 bg_free_blocks_count_hi;/* Free blocks count MSB */ __le16 bg_free_inodes_count_hi;/* Free inodes count MSB */ __le16 bg_used_dirs_count_hi; /* Directories count MSB */ __le16 bg_itable_unused_hi; /* Unused inodes count MSB */ __le32 bg_exclude_bitmap_hi; /* Exclude bitmap block MSB */ __le16 bg_block_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+bbitmap) BE */ __le16 bg_inode_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+ibitmap) BE */ __u32 bg_reserved; }; #define EXT4_BG_INODE_BITMAP_CSUM_HI_END \ (offsetof(struct ext4_group_desc, bg_inode_bitmap_csum_hi) + \ sizeof(__le16)) #define EXT4_BG_BLOCK_BITMAP_CSUM_HI_END \ (offsetof(struct ext4_group_desc, bg_block_bitmap_csum_hi) + \ sizeof(__le16)) /* * Structure of a flex block group info */ struct flex_groups { atomic64_t free_clusters; atomic_t free_inodes; atomic_t used_dirs; }; #define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */ #define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */ #define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */ /* * Macro-instructions used to manage group descriptors */ #define EXT4_MIN_DESC_SIZE 32 #define EXT4_MIN_DESC_SIZE_64BIT 64 #define EXT4_MAX_DESC_SIZE EXT4_MIN_BLOCK_SIZE #define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size) #ifdef __KERNEL__ # define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group) # define EXT4_CLUSTERS_PER_GROUP(s) (EXT4_SB(s)->s_clusters_per_group) # define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block) # define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group) # define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits) #else # define EXT4_BLOCKS_PER_GROUP(s) ((s)->s_blocks_per_group) # define EXT4_DESC_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s)) # define EXT4_INODES_PER_GROUP(s) ((s)->s_inodes_per_group) #endif /* * Constants relative to the data blocks */ #define EXT4_NDIR_BLOCKS 12 #define EXT4_IND_BLOCK EXT4_NDIR_BLOCKS #define EXT4_DIND_BLOCK (EXT4_IND_BLOCK + 1) #define EXT4_TIND_BLOCK (EXT4_DIND_BLOCK + 1) #define EXT4_N_BLOCKS (EXT4_TIND_BLOCK + 1) /* * Inode flags */ #define EXT4_SECRM_FL 0x00000001 /* Secure deletion */ #define EXT4_UNRM_FL 0x00000002 /* Undelete */ #define EXT4_COMPR_FL 0x00000004 /* Compress file */ #define EXT4_SYNC_FL 0x00000008 /* Synchronous updates */ #define EXT4_IMMUTABLE_FL 0x00000010 /* Immutable file */ #define EXT4_APPEND_FL 0x00000020 /* writes to file may only append */ #define EXT4_NODUMP_FL 0x00000040 /* do not dump file */ #define EXT4_NOATIME_FL 0x00000080 /* do not update atime */ /* Reserved for compression usage... */ #define EXT4_DIRTY_FL 0x00000100 #define EXT4_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ #define EXT4_NOCOMPR_FL 0x00000400 /* Don't compress */ /* nb: was previously EXT2_ECOMPR_FL */ #define EXT4_ENCRYPT_FL 0x00000800 /* encrypted file */ /* End compression flags --- maybe not all used */ #define EXT4_INDEX_FL 0x00001000 /* hash-indexed directory */ #define EXT4_IMAGIC_FL 0x00002000 /* AFS directory */ #define EXT4_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ #define EXT4_NOTAIL_FL 0x00008000 /* file tail should not be merged */ #define EXT4_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ #define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ #define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */ #define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ #define EXT4_VERITY_FL 0x00100000 /* Verity protected inode */ #define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */ /* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */ #define EXT4_DAX_FL 0x02000000 /* Inode is DAX */ #define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ #define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded directory */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ /* User modifiable flags */ #define EXT4_FL_USER_MODIFIABLE (EXT4_SECRM_FL | \ EXT4_UNRM_FL | \ EXT4_COMPR_FL | \ EXT4_SYNC_FL | \ EXT4_IMMUTABLE_FL | \ EXT4_APPEND_FL | \ EXT4_NODUMP_FL | \ EXT4_NOATIME_FL | \ EXT4_JOURNAL_DATA_FL | \ EXT4_NOTAIL_FL | \ EXT4_DIRSYNC_FL | \ EXT4_TOPDIR_FL | \ EXT4_EXTENTS_FL | \ 0x00400000 /* EXT4_EOFBLOCKS_FL */ | \ EXT4_DAX_FL | \ EXT4_PROJINHERIT_FL | \ EXT4_CASEFOLD_FL) /* User visible flags */ #define EXT4_FL_USER_VISIBLE (EXT4_FL_USER_MODIFIABLE | \ EXT4_DIRTY_FL | \ EXT4_COMPRBLK_FL | \ EXT4_NOCOMPR_FL | \ EXT4_ENCRYPT_FL | \ EXT4_INDEX_FL | \ EXT4_VERITY_FL | \ EXT4_INLINE_DATA_FL) /* Flags that should be inherited by new inodes from their parent. */ #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\ EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\ EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\ EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\ EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\ EXT4_DAX_FL) /* Flags that are appropriate for regular files (all but dir-specific ones). */ #define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\ EXT4_PROJINHERIT_FL)) /* Flags that are appropriate for non-directories/regular files. */ #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL) /* The only flags that should be swapped */ #define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL) /* Flags which are mutually exclusive to DAX */ #define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\ EXT4_JOURNAL_DATA_FL | EXT4_INLINE_DATA_FL) /* Mask out flags that are inappropriate for the given type of inode. */ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags) { if (S_ISDIR(mode)) return flags; else if (S_ISREG(mode)) return flags & EXT4_REG_FLMASK; else return flags & EXT4_OTHER_FLMASK; } /* * Inode flags used for atomic set/get */ enum { EXT4_INODE_SECRM = 0, /* Secure deletion */ EXT4_INODE_UNRM = 1, /* Undelete */ EXT4_INODE_COMPR = 2, /* Compress file */ EXT4_INODE_SYNC = 3, /* Synchronous updates */ EXT4_INODE_IMMUTABLE = 4, /* Immutable file */ EXT4_INODE_APPEND = 5, /* writes to file may only append */ EXT4_INODE_NODUMP = 6, /* do not dump file */ EXT4_INODE_NOATIME = 7, /* do not update atime */ /* Reserved for compression usage... */ EXT4_INODE_DIRTY = 8, EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */ EXT4_INODE_NOCOMPR = 10, /* Don't compress */ EXT4_INODE_ENCRYPT = 11, /* Encrypted file */ /* End compression flags --- maybe not all used */ EXT4_INODE_INDEX = 12, /* hash-indexed directory */ EXT4_INODE_IMAGIC = 13, /* AFS directory */ EXT4_INODE_JOURNAL_DATA = 14, /* file data should be journaled */ EXT4_INODE_NOTAIL = 15, /* file tail should not be merged */ EXT4_INODE_DIRSYNC = 16, /* dirsync behaviour (directories only) */ EXT4_INODE_TOPDIR = 17, /* Top of directory hierarchies*/ EXT4_INODE_HUGE_FILE = 18, /* Set to each huge file */ EXT4_INODE_EXTENTS = 19, /* Inode uses extents */ EXT4_INODE_VERITY = 20, /* Verity protected inode */ EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */ /* 22 was formerly EXT4_INODE_EOFBLOCKS */ EXT4_INODE_DAX = 25, /* Inode is DAX */ EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */ EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */ EXT4_INODE_CASEFOLD = 30, /* Casefolded directory */ EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */ }; /* * Since it's pretty easy to mix up bit numbers and hex values, we use a * build-time check to make sure that EXT4_XXX_FL is consistent with respect to * EXT4_INODE_XXX. If all is well, the macros will be dropped, so, it won't cost * any extra space in the compiled kernel image, otherwise, the build will fail. * It's important that these values are the same, since we are using * EXT4_INODE_XXX to test for flag values, but EXT4_XXX_FL must be consistent * with the values of FS_XXX_FL defined in include/linux/fs.h and the on-disk * values found in ext2, ext3 and ext4 filesystems, and of course the values * defined in e2fsprogs. * * It's not paranoia if the Murphy's Law really *is* out to get you. :-) */ #define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1U << EXT4_INODE_##FLAG)) #define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG)) static inline void ext4_check_flag_values(void) { CHECK_FLAG_VALUE(SECRM); CHECK_FLAG_VALUE(UNRM); CHECK_FLAG_VALUE(COMPR); CHECK_FLAG_VALUE(SYNC); CHECK_FLAG_VALUE(IMMUTABLE); CHECK_FLAG_VALUE(APPEND); CHECK_FLAG_VALUE(NODUMP); CHECK_FLAG_VALUE(NOATIME); CHECK_FLAG_VALUE(DIRTY); CHECK_FLAG_VALUE(COMPRBLK); CHECK_FLAG_VALUE(NOCOMPR); CHECK_FLAG_VALUE(ENCRYPT); CHECK_FLAG_VALUE(INDEX); CHECK_FLAG_VALUE(IMAGIC); CHECK_FLAG_VALUE(JOURNAL_DATA); CHECK_FLAG_VALUE(NOTAIL); CHECK_FLAG_VALUE(DIRSYNC); CHECK_FLAG_VALUE(TOPDIR); CHECK_FLAG_VALUE(HUGE_FILE); CHECK_FLAG_VALUE(EXTENTS); CHECK_FLAG_VALUE(VERITY); CHECK_FLAG_VALUE(EA_INODE); CHECK_FLAG_VALUE(INLINE_DATA); CHECK_FLAG_VALUE(PROJINHERIT); CHECK_FLAG_VALUE(CASEFOLD); CHECK_FLAG_VALUE(RESERVED); } #if defined(__KERNEL__) && defined(CONFIG_COMPAT) struct compat_ext4_new_group_input { u32 group; compat_u64 block_bitmap; compat_u64 inode_bitmap; compat_u64 inode_table; u32 blocks_count; u16 reserved_blocks; u16 unused; }; #endif /* The struct ext4_new_group_input in kernel space, with free_blocks_count */ struct ext4_new_group_data { __u32 group; __u64 block_bitmap; __u64 inode_bitmap; __u64 inode_table; __u32 blocks_count; __u16 reserved_blocks; __u16 mdata_blocks; __u32 free_clusters_count; }; /* Indexes used to index group tables in ext4_new_group_data */ enum { BLOCK_BITMAP = 0, /* block bitmap */ INODE_BITMAP, /* inode bitmap */ INODE_TABLE, /* inode tables */ GROUP_TABLE_COUNT, }; /* * Flags used by ext4_map_blocks() */ /* Allocate any needed blocks and/or convert an unwritten extent to be an initialized ext4 */ #define EXT4_GET_BLOCKS_CREATE 0x0001 /* Request the creation of an unwritten extent */ #define EXT4_GET_BLOCKS_UNWRIT_EXT 0x0002 #define EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT (EXT4_GET_BLOCKS_UNWRIT_EXT|\ EXT4_GET_BLOCKS_CREATE) /* Caller is from the delayed allocation writeout path * finally doing the actual allocation of delayed blocks */ #define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004 /* caller is from the direct IO path, request to creation of an unwritten extents if not allocated, split the unwritten extent if blocks has been preallocated already*/ #define EXT4_GET_BLOCKS_PRE_IO 0x0008 #define EXT4_GET_BLOCKS_CONVERT 0x0010 #define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT) /* Convert extent to initialized after IO complete */ #define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT) /* Eventual metadata allocation (due to growing extent tree) * should not fail, so try to use reserved blocks for that.*/ #define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020 /* Don't normalize allocation size (used for fallocate) */ #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 /* Convert written extents to unwritten */ #define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0100 /* Write zeros to newly created written extents */ #define EXT4_GET_BLOCKS_ZERO 0x0200 #define EXT4_GET_BLOCKS_CREATE_ZERO (EXT4_GET_BLOCKS_CREATE |\ EXT4_GET_BLOCKS_ZERO) /* Caller will submit data before dropping transaction handle. This * allows jbd2 to avoid submitting data before commit. */ #define EXT4_GET_BLOCKS_IO_SUBMIT 0x0400 /* Caller is in the atomic contex, find extent if it has been cached */ #define EXT4_GET_BLOCKS_CACHED_NOWAIT 0x0800 /* * The bit position of these flags must not overlap with any of the * EXT4_GET_BLOCKS_*. They are used by ext4_find_extent(), * read_extent_tree_block(), ext4_split_extent_at(), * ext4_ext_insert_extent(), and ext4_ext_create_new_leaf(). * EXT4_EX_NOCACHE is used to indicate that the we shouldn't be * caching the extents when reading from the extent tree while a * truncate or punch hole operation is in progress. */ #define EXT4_EX_NOCACHE 0x40000000 #define EXT4_EX_FORCE_CACHE 0x20000000 #define EXT4_EX_NOFAIL 0x10000000 /* * Flags used by ext4_free_blocks */ #define EXT4_FREE_BLOCKS_METADATA 0x0001 #define EXT4_FREE_BLOCKS_FORGET 0x0002 #define EXT4_FREE_BLOCKS_VALIDATED 0x0004 #define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008 #define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020 #define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER 0x0040 #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* * ioctl commands in 32 bit emulation */ #define EXT4_IOC32_GETVERSION _IOR('f', 3, int) #define EXT4_IOC32_SETVERSION _IOW('f', 4, int) #define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int) #define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int) #define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) #define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input) #define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION #define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION #endif /* Max physical block we can address w/o extents */ #define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF /* Max logical block we can support */ #define EXT4_MAX_LOGICAL_BLOCK 0xFFFFFFFE /* * Structure of an inode on the disk */ struct ext4_inode { __le16 i_mode; /* File mode */ __le16 i_uid; /* Low 16 bits of Owner Uid */ __le32 i_size_lo; /* Size in bytes */ __le32 i_atime; /* Access time */ __le32 i_ctime; /* Inode Change time */ __le32 i_mtime; /* Modification time */ __le32 i_dtime; /* Deletion Time */ __le16 i_gid; /* Low 16 bits of Group Id */ __le16 i_links_count; /* Links count */ __le32 i_blocks_lo; /* Blocks count */ __le32 i_flags; /* File flags */ union { struct { __le32 l_i_version; } linux1; struct { __u32 h_i_translator; } hurd1; struct { __u32 m_i_reserved1; } masix1; } osd1; /* OS dependent 1 */ __le32 i_block[EXT4_N_BLOCKS];/* Pointers to blocks */ __le32 i_generation; /* File version (for NFS) */ __le32 i_file_acl_lo; /* File ACL */ __le32 i_size_high; __le32 i_obso_faddr; /* Obsoleted fragment address */ union { struct { __le16 l_i_blocks_high; /* were l_i_reserved1 */ __le16 l_i_file_acl_high; __le16 l_i_uid_high; /* these 2 fields */ __le16 l_i_gid_high; /* were reserved2[0] */ __le16 l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */ __le16 l_i_reserved; } linux2; struct { __le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */ __u16 h_i_mode_high; __u16 h_i_uid_high; __u16 h_i_gid_high; __u32 h_i_author; } hurd2; struct { __le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */ __le16 m_i_file_acl_high; __u32 m_i_reserved2[2]; } masix2; } osd2; /* OS dependent 2 */ __le16 i_extra_isize; __le16 i_checksum_hi; /* crc32c(uuid+inum+inode) BE */ __le32 i_ctime_extra; /* extra Change time (nsec << 2 | epoch) */ __le32 i_mtime_extra; /* extra Modification time(nsec << 2 | epoch) */ __le32 i_atime_extra; /* extra Access time (nsec << 2 | epoch) */ __le32 i_crtime; /* File Creation time */ __le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */ __le32 i_version_hi; /* high 32 bits for 64-bit version */ __le32 i_projid; /* Project ID */ }; #define EXT4_EPOCH_BITS 2 #define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1) #define EXT4_NSEC_MASK (~0UL << EXT4_EPOCH_BITS) /* * Extended fields will fit into an inode if the filesystem was formatted * with large inodes (-I 256 or larger) and there are not currently any EAs * consuming all of the available space. For new inodes we always reserve * enough space for the kernel's known extended fields, but for inodes * created with an old kernel this might not have been the case. None of * the extended inode fields is critical for correct filesystem operation. * This macro checks if a certain field fits in the inode. Note that * inode-size = GOOD_OLD_INODE_SIZE + i_extra_isize */ #define EXT4_FITS_IN_INODE(ext4_inode, einode, field) \ ((offsetof(typeof(*ext4_inode), field) + \ sizeof((ext4_inode)->field)) \ <= (EXT4_GOOD_OLD_INODE_SIZE + \ (einode)->i_extra_isize)) \ /* * We use an encoding that preserves the times for extra epoch "00": * * extra msb of adjust for signed * epoch 32-bit 32-bit tv_sec to * bits time decoded 64-bit tv_sec 64-bit tv_sec valid time range * 0 0 1 -0x80000000..-0x00000001 0x000000000 1901-12-13..1969-12-31 * 0 0 0 0x000000000..0x07fffffff 0x000000000 1970-01-01..2038-01-19 * 0 1 1 0x080000000..0x0ffffffff 0x100000000 2038-01-19..2106-02-07 * 0 1 0 0x100000000..0x17fffffff 0x100000000 2106-02-07..2174-02-25 * 1 0 1 0x180000000..0x1ffffffff 0x200000000 2174-02-25..2242-03-16 * 1 0 0 0x200000000..0x27fffffff 0x200000000 2242-03-16..2310-04-04 * 1 1 1 0x280000000..0x2ffffffff 0x300000000 2310-04-04..2378-04-22 * 1 1 0 0x300000000..0x37fffffff 0x300000000 2378-04-22..2446-05-10 * * Note that previous versions of the kernel on 64-bit systems would * incorrectly use extra epoch bits 1,1 for dates between 1901 and * 1970. e2fsck will correct this, assuming that it is run on the * affected filesystem before 2242. */ static inline __le32 ext4_encode_extra_time(struct timespec64 ts) { u32 extra = ((ts.tv_sec - (s32)ts.tv_sec) >> 32) & EXT4_EPOCH_MASK; return cpu_to_le32(extra | (ts.tv_nsec << EXT4_EPOCH_BITS)); } static inline struct timespec64 ext4_decode_extra_time(__le32 base, __le32 extra) { struct timespec64 ts = { .tv_sec = (signed)le32_to_cpu(base) }; if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK))) ts.tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32; ts.tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; return ts; } #define EXT4_INODE_SET_XTIME_VAL(xtime, inode, raw_inode, ts) \ do { \ if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) { \ (raw_inode)->xtime = cpu_to_le32((ts).tv_sec); \ (raw_inode)->xtime ## _extra = ext4_encode_extra_time(ts); \ } else \ (raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (ts).tv_sec, S32_MIN, S32_MAX)); \ } while (0) #define EXT4_INODE_SET_ATIME(inode, raw_inode) \ EXT4_INODE_SET_XTIME_VAL(i_atime, inode, raw_inode, inode_get_atime(inode)) #define EXT4_INODE_SET_MTIME(inode, raw_inode) \ EXT4_INODE_SET_XTIME_VAL(i_mtime, inode, raw_inode, inode_get_mtime(inode)) #define EXT4_INODE_SET_CTIME(inode, raw_inode) \ EXT4_INODE_SET_XTIME_VAL(i_ctime, inode, raw_inode, inode_get_ctime(inode)) #define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ EXT4_INODE_SET_XTIME_VAL(xtime, &((einode)->vfs_inode), \ raw_inode, (einode)->xtime) #define EXT4_INODE_GET_XTIME_VAL(xtime, inode, raw_inode) \ (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra) ? \ ext4_decode_extra_time((raw_inode)->xtime, \ (raw_inode)->xtime ## _extra) : \ (struct timespec64) { \ .tv_sec = (signed)le32_to_cpu((raw_inode)->xtime) \ }) #define EXT4_INODE_GET_ATIME(inode, raw_inode) \ do { \ inode_set_atime_to_ts(inode, \ EXT4_INODE_GET_XTIME_VAL(i_atime, inode, raw_inode)); \ } while (0) #define EXT4_INODE_GET_MTIME(inode, raw_inode) \ do { \ inode_set_mtime_to_ts(inode, \ EXT4_INODE_GET_XTIME_VAL(i_mtime, inode, raw_inode)); \ } while (0) #define EXT4_INODE_GET_CTIME(inode, raw_inode) \ do { \ inode_set_ctime_to_ts(inode, \ EXT4_INODE_GET_XTIME_VAL(i_ctime, inode, raw_inode)); \ } while (0) #define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \ do { \ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ (einode)->xtime = \ EXT4_INODE_GET_XTIME_VAL(xtime, &(einode->vfs_inode), \ raw_inode); \ else \ (einode)->xtime = (struct timespec64){0, 0}; \ } while (0) #define i_disk_version osd1.linux1.l_i_version #if defined(__KERNEL__) || defined(__linux__) #define i_reserved1 osd1.linux1.l_i_reserved1 #define i_file_acl_high osd2.linux2.l_i_file_acl_high #define i_blocks_high osd2.linux2.l_i_blocks_high #define i_uid_low i_uid #define i_gid_low i_gid #define i_uid_high osd2.linux2.l_i_uid_high #define i_gid_high osd2.linux2.l_i_gid_high #define i_checksum_lo osd2.linux2.l_i_checksum_lo #elif defined(__GNU__) #define i_translator osd1.hurd1.h_i_translator #define i_uid_high osd2.hurd2.h_i_uid_high #define i_gid_high osd2.hurd2.h_i_gid_high #define i_author osd2.hurd2.h_i_author #elif defined(__masix__) #define i_reserved1 osd1.masix1.m_i_reserved1 #define i_file_acl_high osd2.masix2.m_i_file_acl_high #define i_reserved2 osd2.masix2.m_i_reserved2 #endif /* defined(__KERNEL__) || defined(__linux__) */ #include "extents_status.h" #include "fast_commit.h" /* * Lock subclasses for i_data_sem in the ext4_inode_info structure. * * These are needed to avoid lockdep false positives when we need to * allocate blocks to the quota inode during ext4_map_blocks(), while * holding i_data_sem for a normal (non-quota) inode. Since we don't * do quota tracking for the quota inode, this avoids deadlock (as * well as infinite recursion, since it isn't turtles all the way * down...) * * I_DATA_SEM_NORMAL - Used for most inodes * I_DATA_SEM_OTHER - Used by move_inode.c for the second normal inode * where the second inode has larger inode number * than the first * I_DATA_SEM_QUOTA - Used for quota inodes only * I_DATA_SEM_EA - Used for ea_inodes only */ enum { I_DATA_SEM_NORMAL = 0, I_DATA_SEM_OTHER, I_DATA_SEM_QUOTA, I_DATA_SEM_EA }; /* * fourth extended file system inode data in memory */ struct ext4_inode_info { __le32 i_data[15]; /* unconverted */ __u32 i_dtime; ext4_fsblk_t i_file_acl; /* * i_block_group is the number of the block group which contains * this file's inode. Constant across the lifetime of the inode, * it is used for making block allocation decisions - we try to * place a file's data blocks near its inode block, and new inodes * near to their parent directory's inode. */ ext4_group_t i_block_group; ext4_lblk_t i_dir_start_lookup; #if (BITS_PER_LONG < 64) unsigned long i_state_flags; /* Dynamic state flags */ #endif unsigned long i_flags; /* * Extended attributes can be read independently of the main file * data. Taking i_rwsem even when reading would cause contention * between readers of EAs and writers of regular file data, so * instead we synchronize on xattr_sem when reading or changing * EAs. */ struct rw_semaphore xattr_sem; /* * Inodes with EXT4_STATE_ORPHAN_FILE use i_orphan_idx. Otherwise * i_orphan is used. */ union { struct list_head i_orphan; /* unlinked but open inodes */ unsigned int i_orphan_idx; /* Index in orphan file */ }; /* Fast commit related info */ /* For tracking dentry create updates */ struct list_head i_fc_dilist; struct list_head i_fc_list; /* * inodes that need fast commit * protected by sbi->s_fc_lock. */ /* Start of lblk range that needs to be committed in this fast commit */ ext4_lblk_t i_fc_lblk_start; /* End of lblk range that needs to be committed in this fast commit */ ext4_lblk_t i_fc_lblk_len; /* Number of ongoing updates on this inode */ atomic_t i_fc_updates; atomic_t i_unwritten; /* Nr. of inflight conversions pending */ /* Fast commit wait queue for this inode */ wait_queue_head_t i_fc_wait; /* Protect concurrent accesses on i_fc_lblk_start, i_fc_lblk_len */ struct mutex i_fc_lock; /* * i_disksize keeps track of what the inode size is ON DISK, not * in memory. During truncate, i_size is set to the new size by * the VFS prior to calling ext4_truncate(), but the filesystem won't * set i_disksize to 0 until the truncate is actually under way. * * The intent is that i_disksize always represents the blocks which * are used by this file. This allows recovery to restart truncate * on orphans if we crash during truncate. We actually write i_disksize * into the on-disk inode when writing inodes out, instead of i_size. * * The only time when i_disksize and i_size may be different is when * a truncate is in progress. The only things which change i_disksize * are ext4_get_block (growth) and ext4_truncate (shrinkth). */ loff_t i_disksize; /* * i_data_sem is for serialising ext4_truncate() against * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's * data tree are chopped off during truncate. We can't do that in * ext4 because whenever we perform intermediate commits during * truncate, the inode and all the metadata blocks *must* be in a * consistent state which allows truncation of the orphans to restart * during recovery. Hence we must fix the get_block-vs-truncate race * by other means, so we have i_data_sem. */ struct rw_semaphore i_data_sem; struct inode vfs_inode; struct jbd2_inode *jinode; spinlock_t i_raw_lock; /* protects updates to the raw inode */ /* * File creation time. Its function is same as that of * struct timespec64 i_{a,c,m}time in the generic inode. */ struct timespec64 i_crtime; /* mballoc */ atomic_t i_prealloc_active; /* allocation reservation info for delalloc */ /* In case of bigalloc, this refer to clusters rather than blocks */ unsigned int i_reserved_data_blocks; struct rb_root i_prealloc_node; rwlock_t i_prealloc_lock; /* extents status tree */ struct ext4_es_tree i_es_tree; rwlock_t i_es_lock; struct list_head i_es_list; unsigned int i_es_all_nr; /* protected by i_es_lock */ unsigned int i_es_shk_nr; /* protected by i_es_lock */ ext4_lblk_t i_es_shrink_lblk; /* Offset where we start searching for extents to shrink. Protected by i_es_lock */ /* ialloc */ ext4_group_t i_last_alloc_group; /* pending cluster reservations for bigalloc file systems */ struct ext4_pending_tree i_pending_tree; /* on-disk additional length */ __u16 i_extra_isize; /* Indicate the inline data space. */ u16 i_inline_off; u16 i_inline_size; #ifdef CONFIG_QUOTA /* quota space reservation, managed internally by quota code */ qsize_t i_reserved_quota; #endif /* Lock protecting lists below */ spinlock_t i_completed_io_lock; /* * Completed IOs that need unwritten extents handling and have * transaction reserved */ struct list_head i_rsv_conversion_list; struct work_struct i_rsv_conversion_work; spinlock_t i_block_reservation_lock; /* * Transactions that contain inode's metadata needed to complete * fsync and fdatasync, respectively. */ tid_t i_sync_tid; tid_t i_datasync_tid; #ifdef CONFIG_QUOTA struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif /* Precomputed uuid+inum+igen checksum for seeding inode checksums */ __u32 i_csum_seed; kprojid_t i_projid; }; /* * File system states */ #define EXT4_VALID_FS 0x0001 /* Unmounted cleanly */ #define EXT4_ERROR_FS 0x0002 /* Errors detected */ #define EXT4_ORPHAN_FS 0x0004 /* Orphans being recovered */ #define EXT4_FC_REPLAY 0x0020 /* Fast commit replay ongoing */ /* * Misc. filesystem flags */ #define EXT2_FLAGS_SIGNED_HASH 0x0001 /* Signed dirhash in use */ #define EXT2_FLAGS_UNSIGNED_HASH 0x0002 /* Unsigned dirhash in use */ #define EXT2_FLAGS_TEST_FILESYS 0x0004 /* to test development code */ /* * Mount flags set via mount options or defaults */ #define EXT4_MOUNT_NO_MBCACHE 0x00001 /* Do not use mbcache */ #define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ #define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ #define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ #define EXT4_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */ #define EXT4_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */ #define EXT4_MOUNT_ERRORS_MASK 0x00070 #define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ #define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ #ifdef CONFIG_FS_DAX #define EXT4_MOUNT_DAX_ALWAYS 0x00200 /* Direct Access */ #else #define EXT4_MOUNT_DAX_ALWAYS 0 #endif #define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ #define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ #define EXT4_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ #define EXT4_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */ #define EXT4_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */ #define EXT4_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ #define EXT4_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ #define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ #define EXT4_MOUNT_NO_AUTO_DA_ALLOC 0x10000 /* No auto delalloc mapping */ #define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */ #define EXT4_MOUNT_QUOTA 0x40000 /* Some quota option set */ #define EXT4_MOUNT_USRQUOTA 0x80000 /* "old" user quota, * enable enforcement for hidden * quota files */ #define EXT4_MOUNT_GRPQUOTA 0x100000 /* "old" group quota, enable * enforcement for hidden quota * files */ #define EXT4_MOUNT_PRJQUOTA 0x200000 /* Enable project quota * enforcement */ #define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */ #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */ #define EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS 0x4000000 #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ #define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */ #define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */ /* * Mount flags set either automatically (could not be set by mount option) * based on per file system feature or property or in special cases such as * distinguishing between explicit mount option definition and default. */ #define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly specified delalloc */ #define EXT4_MOUNT2_STD_GROUP_SIZE 0x00000002 /* We have standard group size of blocksize * 8 blocks */ #define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated file systems */ #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly specified journal checksum */ #define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */ #define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */ #define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */ #define EXT4_MOUNT2_MB_OPTIMIZE_SCAN 0x00000080 /* Optimize group * scanning in mballoc */ #define EXT4_MOUNT2_ABORT 0x00000100 /* Abort filesystem */ #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt #define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \ EXT4_MOUNT_##opt #define test_opt(sb, opt) (EXT4_SB(sb)->s_mount_opt & \ EXT4_MOUNT_##opt) #define clear_opt2(sb, opt) EXT4_SB(sb)->s_mount_opt2 &= \ ~EXT4_MOUNT2_##opt #define set_opt2(sb, opt) EXT4_SB(sb)->s_mount_opt2 |= \ EXT4_MOUNT2_##opt #define test_opt2(sb, opt) (EXT4_SB(sb)->s_mount_opt2 & \ EXT4_MOUNT2_##opt) #define ext4_test_and_set_bit __test_and_set_bit_le #define ext4_set_bit __set_bit_le #define ext4_test_and_clear_bit __test_and_clear_bit_le #define ext4_clear_bit __clear_bit_le #define ext4_test_bit test_bit_le #define ext4_find_next_zero_bit find_next_zero_bit_le #define ext4_find_next_bit find_next_bit_le extern void mb_set_bits(void *bm, int cur, int len); /* * Maximal mount counts between two filesystem checks */ #define EXT4_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */ #define EXT4_DFL_CHECKINTERVAL 0 /* Don't use interval check */ /* * Behaviour when detecting errors */ #define EXT4_ERRORS_CONTINUE 1 /* Continue execution */ #define EXT4_ERRORS_RO 2 /* Remount fs read-only */ #define EXT4_ERRORS_PANIC 3 /* Panic */ #define EXT4_ERRORS_DEFAULT EXT4_ERRORS_CONTINUE /* Metadata checksum algorithm codes */ #define EXT4_CRC32C_CHKSUM 1 #define EXT4_LABEL_MAX 16 /* * Structure of the super block */ struct ext4_super_block { /*00*/ __le32 s_inodes_count; /* Inodes count */ __le32 s_blocks_count_lo; /* Blocks count */ __le32 s_r_blocks_count_lo; /* Reserved blocks count */ __le32 s_free_blocks_count_lo; /* Free blocks count */ /*10*/ __le32 s_free_inodes_count; /* Free inodes count */ __le32 s_first_data_block; /* First Data Block */ __le32 s_log_block_size; /* Block size */ __le32 s_log_cluster_size; /* Allocation cluster size */ /*20*/ __le32 s_blocks_per_group; /* # Blocks per group */ __le32 s_clusters_per_group; /* # Clusters per group */ __le32 s_inodes_per_group; /* # Inodes per group */ __le32 s_mtime; /* Mount time */ /*30*/ __le32 s_wtime; /* Write time */ __le16 s_mnt_count; /* Mount count */ __le16 s_max_mnt_count; /* Maximal mount count */ __le16 s_magic; /* Magic signature */ __le16 s_state; /* File system state */ __le16 s_errors; /* Behaviour when detecting errors */ __le16 s_minor_rev_level; /* minor revision level */ /*40*/ __le32 s_lastcheck; /* time of last check */ __le32 s_checkinterval; /* max. time between checks */ __le32 s_creator_os; /* OS */ __le32 s_rev_level; /* Revision level */ /*50*/ __le16 s_def_resuid; /* Default uid for reserved blocks */ __le16 s_def_resgid; /* Default gid for reserved blocks */ /* * These fields are for EXT4_DYNAMIC_REV superblocks only. * * Note: the difference between the compatible feature set and * the incompatible feature set is that if there is a bit set * in the incompatible feature set that the kernel doesn't * know about, it should refuse to mount the filesystem. * * e2fsck's requirements are more strict; if it doesn't know * about a feature in either the compatible or incompatible * feature set, it must abort and not try to meddle with * things it doesn't understand... */ __le32 s_first_ino; /* First non-reserved inode */ __le16 s_inode_size; /* size of inode structure */ __le16 s_block_group_nr; /* block group # of this superblock */ __le32 s_feature_compat; /* compatible feature set */ /*60*/ __le32 s_feature_incompat; /* incompatible feature set */ __le32 s_feature_ro_compat; /* readonly-compatible feature set */ /*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ /*78*/ char s_volume_name[EXT4_LABEL_MAX] __nonstring; /* volume name */ /*88*/ char s_last_mounted[64] __nonstring; /* directory where last mounted */ /*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ /* * Performance hints. Directory preallocation should only * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on. */ __u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/ __u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */ __le16 s_reserved_gdt_blocks; /* Per group desc for online growth */ /* * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set. */ /*D0*/ __u8 s_journal_uuid[16]; /* uuid of journal superblock */ /*E0*/ __le32 s_journal_inum; /* inode number of journal file */ __le32 s_journal_dev; /* device number of journal file */ __le32 s_last_orphan; /* start of list of inodes to delete */ __le32 s_hash_seed[4]; /* HTREE hash seed */ __u8 s_def_hash_version; /* Default hash version to use */ __u8 s_jnl_backup_type; __le16 s_desc_size; /* size of group descriptor */ /*100*/ __le32 s_default_mount_opts; __le32 s_first_meta_bg; /* First metablock block group */ __le32 s_mkfs_time; /* When the filesystem was created */ __le32 s_jnl_blocks[17]; /* Backup of the journal inode */ /* 64bit support valid if EXT4_FEATURE_INCOMPAT_64BIT */ /*150*/ __le32 s_blocks_count_hi; /* Blocks count */ __le32 s_r_blocks_count_hi; /* Reserved blocks count */ __le32 s_free_blocks_count_hi; /* Free blocks count */ __le16 s_min_extra_isize; /* All inodes have at least # bytes */ __le16 s_want_extra_isize; /* New inodes should reserve # bytes */ __le32 s_flags; /* Miscellaneous flags */ __le16 s_raid_stride; /* RAID stride */ __le16 s_mmp_update_interval; /* # seconds to wait in MMP checking */ __le64 s_mmp_block; /* Block for multi-mount protection */ __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ __u8 s_log_groups_per_flex; /* FLEX_BG group size */ __u8 s_checksum_type; /* metadata checksum algorithm used */ __u8 s_encryption_level; /* versioning level for encryption */ __u8 s_reserved_pad; /* Padding to next 32bits */ __le64 s_kbytes_written; /* nr of lifetime kilobytes written */ __le32 s_snapshot_inum; /* Inode number of active snapshot */ __le32 s_snapshot_id; /* sequential ID of active snapshot */ __le64 s_snapshot_r_blocks_count; /* reserved blocks for active snapshot's future use */ __le32 s_snapshot_list; /* inode number of the head of the on-disk snapshot list */ #define EXT4_S_ERR_START offsetof(struct ext4_super_block, s_error_count) __le32 s_error_count; /* number of fs errors */ __le32 s_first_error_time; /* first time an error happened */ __le32 s_first_error_ino; /* inode involved in first error */ __le64 s_first_error_block; /* block involved of first error */ __u8 s_first_error_func[32] __nonstring; /* function where the error happened */ __le32 s_first_error_line; /* line number where error happened */ __le32 s_last_error_time; /* most recent time of an error */ __le32 s_last_error_ino; /* inode involved in last error */ __le32 s_last_error_line; /* line number where error happened */ __le64 s_last_error_block; /* block involved of last error */ __u8 s_last_error_func[32] __nonstring; /* function where the error happened */ #define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts) __u8 s_mount_opts[64]; __le32 s_usr_quota_inum; /* inode for tracking user quota */ __le32 s_grp_quota_inum; /* inode for tracking group quota */ __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */ __le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */ __u8 s_encrypt_algos[4]; /* Encryption algorithms in use */ __u8 s_encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ __le32 s_lpf_ino; /* Location of the lost+found inode */ __le32 s_prj_quota_inum; /* inode for tracking project quota */ __le32 s_checksum_seed; /* crc32c(uuid) if csum_seed set */ __u8 s_wtime_hi; __u8 s_mtime_hi; __u8 s_mkfs_time_hi; __u8 s_lastcheck_hi; __u8 s_first_error_time_hi; __u8 s_last_error_time_hi; __u8 s_first_error_errcode; __u8 s_last_error_errcode; __le16 s_encoding; /* Filename charset encoding */ __le16 s_encoding_flags; /* Filename charset encoding flags */ __le32 s_orphan_file_inum; /* Inode for tracking orphan inodes */ __le32 s_reserved[94]; /* Padding to the end of the block */ __le32 s_checksum; /* crc32c(superblock) */ }; #define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START) #ifdef __KERNEL__ /* Number of quota types we support */ #define EXT4_MAXQUOTAS 3 #define EXT4_ENC_UTF8_12_1 1 /* Types of ext4 journal triggers */ enum ext4_journal_trigger_type { EXT4_JTR_ORPHAN_FILE, EXT4_JTR_NONE /* This must be the last entry for indexing to work! */ }; #define EXT4_JOURNAL_TRIGGER_COUNT EXT4_JTR_NONE struct ext4_journal_trigger { struct jbd2_buffer_trigger_type tr_triggers; struct super_block *sb; }; static inline struct ext4_journal_trigger *EXT4_TRIGGER( struct jbd2_buffer_trigger_type *trigger) { return container_of(trigger, struct ext4_journal_trigger, tr_triggers); } #define EXT4_ORPHAN_BLOCK_MAGIC 0x0b10ca04 /* Structure at the tail of orphan block */ struct ext4_orphan_block_tail { __le32 ob_magic; __le32 ob_checksum; }; static inline int ext4_inodes_per_orphan_block(struct super_block *sb) { return (sb->s_blocksize - sizeof(struct ext4_orphan_block_tail)) / sizeof(u32); } struct ext4_orphan_block { atomic_t ob_free_entries; /* Number of free orphan entries in block */ struct buffer_head *ob_bh; /* Buffer for orphan block */ }; /* * Info about orphan file. */ struct ext4_orphan_info { int of_blocks; /* Number of orphan blocks in a file */ __u32 of_csum_seed; /* Checksum seed for orphan file */ struct ext4_orphan_block *of_binfo; /* Array with info about orphan * file blocks */ }; /* * fourth extended-fs super-block data in memory */ struct ext4_sb_info { unsigned long s_desc_size; /* Size of a group descriptor in bytes */ unsigned long s_inodes_per_block;/* Number of inodes per block */ unsigned long s_blocks_per_group;/* Number of blocks in a group */ unsigned long s_clusters_per_group; /* Number of clusters in a group */ unsigned long s_inodes_per_group;/* Number of inodes in a group */ unsigned long s_itb_per_group; /* Number of inode table blocks per group */ unsigned long s_gdb_count; /* Number of group descriptor blocks */ unsigned long s_desc_per_block; /* Number of group descriptors per block */ ext4_group_t s_groups_count; /* Number of groups in the fs */ ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */ unsigned long s_overhead; /* # of fs overhead clusters */ unsigned int s_cluster_ratio; /* Number of blocks per cluster */ unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */ loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ /* Array of bh's for the block group descriptors */ struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; unsigned long s_mount_flags; unsigned int s_def_mount_opt; unsigned int s_def_mount_opt2; ext4_fsblk_t s_sb_block; atomic64_t s_resv_clusters; kuid_t s_resuid; kgid_t s_resgid; unsigned short s_mount_state; unsigned short s_pad; int s_addr_per_block_bits; int s_desc_per_block_bits; int s_inode_size; int s_first_ino; unsigned int s_inode_readahead_blks; unsigned int s_inode_goal; u32 s_hash_seed[4]; int s_def_hash_version; int s_hash_unsigned; /* 3 if hash should be unsigned, 0 if not */ struct percpu_counter s_freeclusters_counter; struct percpu_counter s_freeinodes_counter; struct percpu_counter s_dirs_counter; struct percpu_counter s_dirtyclusters_counter; struct percpu_counter s_sra_exceeded_retry_limit; struct blockgroup_lock *s_blockgroup_lock; struct proc_dir_entry *s_proc; struct kobject s_kobj; struct completion s_kobj_unregister; struct super_block *s_sb; struct buffer_head *s_mmp_bh; /* Journaling */ struct journal_s *s_journal; unsigned long s_ext4_flags; /* Ext4 superblock flags */ struct mutex s_orphan_lock; /* Protects on disk list changes */ struct list_head s_orphan; /* List of orphaned inodes in on disk list */ struct ext4_orphan_info s_orphan_info; unsigned long s_commit_interval; u32 s_max_batch_time; u32 s_min_batch_time; struct file *s_journal_bdev_file; #ifdef CONFIG_QUOTA /* Names of quota files with journalled quota */ char __rcu *s_qf_names[EXT4_MAXQUOTAS]; int s_jquota_fmt; /* Format of quota to use */ #endif unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ struct ext4_system_blocks __rcu *s_system_blks; #ifdef EXTENTS_STATS /* ext4 extents stats */ unsigned long s_ext_min; unsigned long s_ext_max; unsigned long s_depth_max; spinlock_t s_ext_stats_lock; unsigned long s_ext_blocks; unsigned long s_ext_extents; #endif /* for buddy allocator */ struct ext4_group_info ** __rcu *s_group_info; struct inode *s_buddy_cache; spinlock_t s_md_lock; unsigned short *s_mb_offsets; unsigned int *s_mb_maxs; unsigned int s_group_info_size; unsigned int s_mb_free_pending; struct list_head s_freed_data_list[2]; /* List of blocks to be freed after commit completed */ struct list_head s_discard_list; struct work_struct s_discard_work; atomic_t s_retry_alloc_pending; struct list_head *s_mb_avg_fragment_size; rwlock_t *s_mb_avg_fragment_size_locks; struct list_head *s_mb_largest_free_orders; rwlock_t *s_mb_largest_free_orders_locks; /* tunables */ unsigned long s_stripe; unsigned int s_mb_max_linear_groups; unsigned int s_mb_stream_request; unsigned int s_mb_max_to_scan; unsigned int s_mb_min_to_scan; unsigned int s_mb_stats; unsigned int s_mb_order2_reqs; unsigned int s_mb_group_prealloc; unsigned int s_max_dir_size_kb; /* where last allocation was done - for stream allocation */ unsigned long s_mb_last_group; unsigned long s_mb_last_start; unsigned int s_mb_prefetch; unsigned int s_mb_prefetch_limit; unsigned int s_mb_best_avail_max_trim_order; /* stats for buddy allocator */ atomic_t s_bal_reqs; /* number of reqs with len > 1 */ atomic_t s_bal_success; /* we found long enough chunks */ atomic_t s_bal_allocated; /* in blocks */ atomic_t s_bal_ex_scanned; /* total extents scanned */ atomic_t s_bal_cX_ex_scanned[EXT4_MB_NUM_CRS]; /* total extents scanned */ atomic_t s_bal_groups_scanned; /* number of groups scanned */ atomic_t s_bal_goals; /* goal hits */ atomic_t s_bal_len_goals; /* len goal hits */ atomic_t s_bal_breaks; /* too long searches */ atomic_t s_bal_2orders; /* 2^order hits */ atomic_t s_bal_p2_aligned_bad_suggestions; atomic_t s_bal_goal_fast_bad_suggestions; atomic_t s_bal_best_avail_bad_suggestions; atomic64_t s_bal_cX_groups_considered[EXT4_MB_NUM_CRS]; atomic64_t s_bal_cX_hits[EXT4_MB_NUM_CRS]; atomic64_t s_bal_cX_failed[EXT4_MB_NUM_CRS]; /* cX loop didn't find blocks */ atomic_t s_mb_buddies_generated; /* number of buddies generated */ atomic64_t s_mb_generation_time; atomic_t s_mb_lost_chunks; atomic_t s_mb_preallocated; atomic_t s_mb_discarded; atomic_t s_lock_busy; /* locality groups */ struct ext4_locality_group __percpu *s_locality_groups; /* for write statistics */ unsigned long s_sectors_written_start; u64 s_kbytes_written; /* the size of zero-out chunk */ unsigned int s_extent_max_zeroout_kb; unsigned int s_log_groups_per_flex; struct flex_groups * __rcu *s_flex_groups; ext4_group_t s_flex_groups_allocated; /* workqueue for reserved extent conversions (buffered io) */ struct workqueue_struct *rsv_conversion_wq; /* timer for periodic error stats printing */ struct timer_list s_err_report; /* Lazy inode table initialization info */ struct ext4_li_request *s_li_request; /* Wait multiplier for lazy initialization thread */ unsigned int s_li_wait_mult; /* Kernel thread for multiple mount protection */ struct task_struct *s_mmp_tsk; /* record the last minlen when FITRIM is called. */ unsigned long s_last_trim_minblks; /* Reference to checksum algorithm driver via cryptoapi */ struct crypto_shash *s_chksum_driver; /* Precomputed FS UUID checksum for seeding other checksums */ __u32 s_csum_seed; /* Reclaim extents from extent status tree */ struct shrinker *s_es_shrinker; struct list_head s_es_list; /* List of inodes with reclaimable extents */ long s_es_nr_inode; struct ext4_es_stats s_es_stats; struct mb_cache *s_ea_block_cache; struct mb_cache *s_ea_inode_cache; spinlock_t s_es_lock ____cacheline_aligned_in_smp; /* Journal triggers for checksum computation */ struct ext4_journal_trigger s_journal_triggers[EXT4_JOURNAL_TRIGGER_COUNT]; /* Ratelimit ext4 messages. */ struct ratelimit_state s_err_ratelimit_state; struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; atomic_t s_warning_count; atomic_t s_msg_count; /* Encryption policy for '-o test_dummy_encryption' */ struct fscrypt_dummy_policy s_dummy_enc_policy; /* * Barrier between writepages ops and changing any inode's JOURNAL_DATA * or EXTENTS flag or between writepages ops and changing DELALLOC or * DIOREAD_NOLOCK mount options on remount. */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; u64 s_dax_part_off; #ifdef CONFIG_EXT4_DEBUG unsigned long s_simulate_fail; #endif /* Record the errseq of the backing block device */ errseq_t s_bdev_wb_err; spinlock_t s_bdev_wb_lock; /* Information about errors that happened during this mount */ spinlock_t s_error_lock; int s_add_error_count; int s_first_error_code; __u32 s_first_error_line; __u32 s_first_error_ino; __u64 s_first_error_block; const char *s_first_error_func; time64_t s_first_error_time; int s_last_error_code; __u32 s_last_error_line; __u32 s_last_error_ino; __u64 s_last_error_block; const char *s_last_error_func; time64_t s_last_error_time; /* * If we are in a context where we cannot update the on-disk * superblock, we queue the work here. This is used to update * the error information in the superblock, and for periodic * updates of the superblock called from the commit callback * function. */ struct work_struct s_sb_upd_work; /* Ext4 fast commit sub transaction ID */ atomic_t s_fc_subtid; /* * After commit starts, the main queue gets locked, and the further * updates get added in the staging queue. */ #define FC_Q_MAIN 0 #define FC_Q_STAGING 1 struct list_head s_fc_q[2]; /* Inodes staged for fast commit * that have data changes in them. */ struct list_head s_fc_dentry_q[2]; /* directory entry updates */ unsigned int s_fc_bytes; /* * Main fast commit lock. This lock protects accesses to the * following fields: * ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh. */ spinlock_t s_fc_lock; struct buffer_head *s_fc_bh; struct ext4_fc_stats s_fc_stats; tid_t s_fc_ineligible_tid; #ifdef CONFIG_EXT4_DEBUG int s_fc_debug_max_replay; #endif struct ext4_fc_replay_state s_fc_replay_state; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) { return sb->s_fs_info; } static inline struct ext4_inode_info *EXT4_I(struct inode *inode) { return container_of(inode, struct ext4_inode_info, vfs_inode); } static inline int ext4_writepages_down_read(struct super_block *sb) { percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); return memalloc_nofs_save(); } static inline void ext4_writepages_up_read(struct super_block *sb, int ctx) { memalloc_nofs_restore(ctx); percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); } static inline int ext4_writepages_down_write(struct super_block *sb) { percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem); return memalloc_nofs_save(); } static inline void ext4_writepages_up_write(struct super_block *sb, int ctx) { memalloc_nofs_restore(ctx); percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem); } static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || (ino >= EXT4_FIRST_INO(sb) && ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } /* * Returns: sbi->field[index] * Used to access an array element from the following sbi fields which require * rcu protection to avoid dereferencing an invalid pointer due to reassignment * - s_group_desc * - s_group_info * - s_flex_group */ #define sbi_array_rcu_deref(sbi, field, index) \ ({ \ typeof(*((sbi)->field)) _v; \ rcu_read_lock(); \ _v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index]; \ rcu_read_unlock(); \ _v; \ }) /* * run-time mount flags */ enum { EXT4_MF_MNTDIR_SAMPLED, EXT4_MF_FC_INELIGIBLE /* Fast commit ineligible */ }; static inline void ext4_set_mount_flag(struct super_block *sb, int bit) { set_bit(bit, &EXT4_SB(sb)->s_mount_flags); } static inline void ext4_clear_mount_flag(struct super_block *sb, int bit) { clear_bit(bit, &EXT4_SB(sb)->s_mount_flags); } static inline int ext4_test_mount_flag(struct super_block *sb, int bit) { return test_bit(bit, &EXT4_SB(sb)->s_mount_flags); } /* * Simulate_fail codes */ #define EXT4_SIM_BBITMAP_EIO 1 #define EXT4_SIM_BBITMAP_CRC 2 #define EXT4_SIM_IBITMAP_EIO 3 #define EXT4_SIM_IBITMAP_CRC 4 #define EXT4_SIM_INODE_EIO 5 #define EXT4_SIM_INODE_CRC 6 #define EXT4_SIM_DIRBLOCK_EIO 7 #define EXT4_SIM_DIRBLOCK_CRC 8 static inline bool ext4_simulate_fail(struct super_block *sb, unsigned long code) { #ifdef CONFIG_EXT4_DEBUG struct ext4_sb_info *sbi = EXT4_SB(sb); if (unlikely(sbi->s_simulate_fail == code)) { sbi->s_simulate_fail = 0; return true; } #endif return false; } static inline void ext4_simulate_fail_bh(struct super_block *sb, struct buffer_head *bh, unsigned long code) { if (!IS_ERR(bh) && ext4_simulate_fail(sb, code)) clear_buffer_uptodate(bh); } /* * Error number codes for s_{first,last}_error_errno * * Linux errno numbers are architecture specific, so we need to translate * them into something which is architecture independent. We don't define * codes for all errno's; just the ones which are most likely to be the cause * of an ext4_error() call. */ #define EXT4_ERR_UNKNOWN 1 #define EXT4_ERR_EIO 2 #define EXT4_ERR_ENOMEM 3 #define EXT4_ERR_EFSBADCRC 4 #define EXT4_ERR_EFSCORRUPTED 5 #define EXT4_ERR_ENOSPC 6 #define EXT4_ERR_ENOKEY 7 #define EXT4_ERR_EROFS 8 #define EXT4_ERR_EFBIG 9 #define EXT4_ERR_EEXIST 10 #define EXT4_ERR_ERANGE 11 #define EXT4_ERR_EOVERFLOW 12 #define EXT4_ERR_EBUSY 13 #define EXT4_ERR_ENOTDIR 14 #define EXT4_ERR_ENOTEMPTY 15 #define EXT4_ERR_ESHUTDOWN 16 #define EXT4_ERR_EFAULT 17 /* * Inode dynamic state flags */ enum { EXT4_STATE_NEW, /* inode is newly created */ EXT4_STATE_XATTR, /* has in-inode xattrs */ EXT4_STATE_NO_EXPAND, /* No space for expansion */ EXT4_STATE_DA_ALLOC_CLOSE, /* Alloc DA blks on close */ EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */ EXT4_STATE_NEWENTRY, /* File just added to dir */ EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */ EXT4_STATE_EXT_PRECACHED, /* extents have been precached */ EXT4_STATE_LUSTRE_EA_INODE, /* Lustre-style ea_inode */ EXT4_STATE_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */ EXT4_STATE_FC_COMMITTING, /* Fast commit ongoing */ EXT4_STATE_ORPHAN_FILE, /* Inode orphaned in orphan file */ }; #define EXT4_INODE_BIT_FNS(name, field, offset) \ static inline int ext4_test_inode_##name(struct inode *inode, int bit) \ { \ return test_bit(bit + (offset), &EXT4_I(inode)->i_##field); \ } \ static inline void ext4_set_inode_##name(struct inode *inode, int bit) \ { \ set_bit(bit + (offset), &EXT4_I(inode)->i_##field); \ } \ static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \ { \ clear_bit(bit + (offset), &EXT4_I(inode)->i_##field); \ } /* Add these declarations here only so that these functions can be * found by name. Otherwise, they are very hard to locate. */ static inline int ext4_test_inode_flag(struct inode *inode, int bit); static inline void ext4_set_inode_flag(struct inode *inode, int bit); static inline void ext4_clear_inode_flag(struct inode *inode, int bit); EXT4_INODE_BIT_FNS(flag, flags, 0) /* Add these declarations here only so that these functions can be * found by name. Otherwise, they are very hard to locate. */ static inline int ext4_test_inode_state(struct inode *inode, int bit); static inline void ext4_set_inode_state(struct inode *inode, int bit); static inline void ext4_clear_inode_state(struct inode *inode, int bit); #if (BITS_PER_LONG < 64) EXT4_INODE_BIT_FNS(state, state_flags, 0) static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) { (ei)->i_state_flags = 0; } #else EXT4_INODE_BIT_FNS(state, flags, 32) static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) { /* We depend on the fact that callers will set i_flags */ } #endif #else /* Assume that user mode programs are passing in an ext4fs superblock, not * a kernel struct super_block. This will allow us to call the feature-test * macros from user land. */ #define EXT4_SB(sb) (sb) #endif static inline bool ext4_verity_in_progress(struct inode *inode) { return IS_ENABLED(CONFIG_FS_VERITY) && ext4_test_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); } #define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime /* * Codes for operating systems */ #define EXT4_OS_LINUX 0 #define EXT4_OS_HURD 1 #define EXT4_OS_MASIX 2 #define EXT4_OS_FREEBSD 3 #define EXT4_OS_LITES 4 /* * Revision levels */ #define EXT4_GOOD_OLD_REV 0 /* The good old (original) format */ #define EXT4_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ #define EXT4_MAX_SUPP_REV EXT4_DYNAMIC_REV #define EXT4_GOOD_OLD_INODE_SIZE 128 #define EXT4_EXTRA_TIMESTAMP_MAX (((s64)1 << 34) - 1 + S32_MIN) #define EXT4_NON_EXTRA_TIMESTAMP_MAX S32_MAX #define EXT4_TIMESTAMP_MIN S32_MIN /* * Feature set definitions */ #define EXT4_FEATURE_COMPAT_DIR_PREALLOC 0x0001 #define EXT4_FEATURE_COMPAT_IMAGIC_INODES 0x0002 #define EXT4_FEATURE_COMPAT_HAS_JOURNAL 0x0004 #define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008 #define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 #define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200 /* * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes * incompatible only if fast commit blocks are present in the FS. Since we * clear the journal (and thus the fast commit blocks), we don't mark FS as * incompatible. We also have a JBD2 incompat feature, which gets set when * there are fast commit blocks present in the journal. */ #define EXT4_FEATURE_COMPAT_FAST_COMMIT 0x0400 #define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800 #define EXT4_FEATURE_COMPAT_ORPHAN_FILE 0x1000 /* Orphan file exists */ #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 #define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 #define EXT4_FEATURE_RO_COMPAT_HUGE_FILE 0x0008 #define EXT4_FEATURE_RO_COMPAT_GDT_CSUM 0x0010 #define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020 #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040 #define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100 #define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200 /* * METADATA_CSUM also enables group descriptor checksums (GDT_CSUM). When * METADATA_CSUM is set, group descriptor checksums use the same algorithm as * all other data structures' checksums. However, the METADATA_CSUM and * GDT_CSUM bits are mutually exclusive. */ #define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400 #define EXT4_FEATURE_RO_COMPAT_READONLY 0x1000 #define EXT4_FEATURE_RO_COMPAT_PROJECT 0x2000 #define EXT4_FEATURE_RO_COMPAT_VERITY 0x8000 #define EXT4_FEATURE_RO_COMPAT_ORPHAN_PRESENT 0x10000 /* Orphan file may be non-empty */ #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 #define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 #define EXT4_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */ #define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */ #define EXT4_FEATURE_INCOMPAT_META_BG 0x0010 #define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */ #define EXT4_FEATURE_INCOMPAT_64BIT 0x0080 #define EXT4_FEATURE_INCOMPAT_MMP 0x0100 #define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200 #define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */ #define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */ #define EXT4_FEATURE_INCOMPAT_CSUM_SEED 0x2000 #define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */ #define EXT4_FEATURE_INCOMPAT_INLINE_DATA 0x8000 /* data in inode */ #define EXT4_FEATURE_INCOMPAT_ENCRYPT 0x10000 #define EXT4_FEATURE_INCOMPAT_CASEFOLD 0x20000 extern void ext4_update_dynamic_rev(struct super_block *sb); #define EXT4_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool ext4_has_feature_##name(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_compat & \ cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname)) != 0); \ } \ static inline void ext4_set_feature_##name(struct super_block *sb) \ { \ ext4_update_dynamic_rev(sb); \ EXT4_SB(sb)->s_es->s_feature_compat |= \ cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \ } \ static inline void ext4_clear_feature_##name(struct super_block *sb) \ { \ EXT4_SB(sb)->s_es->s_feature_compat &= \ ~cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \ } #define EXT4_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline bool ext4_has_feature_##name(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \ cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname)) != 0); \ } \ static inline void ext4_set_feature_##name(struct super_block *sb) \ { \ ext4_update_dynamic_rev(sb); \ EXT4_SB(sb)->s_es->s_feature_ro_compat |= \ cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \ } \ static inline void ext4_clear_feature_##name(struct super_block *sb) \ { \ EXT4_SB(sb)->s_es->s_feature_ro_compat &= \ ~cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \ } #define EXT4_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline bool ext4_has_feature_##name(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_incompat & \ cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname)) != 0); \ } \ static inline void ext4_set_feature_##name(struct super_block *sb) \ { \ ext4_update_dynamic_rev(sb); \ EXT4_SB(sb)->s_es->s_feature_incompat |= \ cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \ } \ static inline void ext4_clear_feature_##name(struct super_block *sb) \ { \ EXT4_SB(sb)->s_es->s_feature_incompat &= \ ~cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \ } EXT4_FEATURE_COMPAT_FUNCS(dir_prealloc, DIR_PREALLOC) EXT4_FEATURE_COMPAT_FUNCS(imagic_inodes, IMAGIC_INODES) EXT4_FEATURE_COMPAT_FUNCS(journal, HAS_JOURNAL) EXT4_FEATURE_COMPAT_FUNCS(xattr, EXT_ATTR) EXT4_FEATURE_COMPAT_FUNCS(resize_inode, RESIZE_INODE) EXT4_FEATURE_COMPAT_FUNCS(dir_index, DIR_INDEX) EXT4_FEATURE_COMPAT_FUNCS(sparse_super2, SPARSE_SUPER2) EXT4_FEATURE_COMPAT_FUNCS(fast_commit, FAST_COMMIT) EXT4_FEATURE_COMPAT_FUNCS(stable_inodes, STABLE_INODES) EXT4_FEATURE_COMPAT_FUNCS(orphan_file, ORPHAN_FILE) EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super, SPARSE_SUPER) EXT4_FEATURE_RO_COMPAT_FUNCS(large_file, LARGE_FILE) EXT4_FEATURE_RO_COMPAT_FUNCS(btree_dir, BTREE_DIR) EXT4_FEATURE_RO_COMPAT_FUNCS(huge_file, HUGE_FILE) EXT4_FEATURE_RO_COMPAT_FUNCS(gdt_csum, GDT_CSUM) EXT4_FEATURE_RO_COMPAT_FUNCS(dir_nlink, DIR_NLINK) EXT4_FEATURE_RO_COMPAT_FUNCS(extra_isize, EXTRA_ISIZE) EXT4_FEATURE_RO_COMPAT_FUNCS(quota, QUOTA) EXT4_FEATURE_RO_COMPAT_FUNCS(bigalloc, BIGALLOC) EXT4_FEATURE_RO_COMPAT_FUNCS(metadata_csum, METADATA_CSUM) EXT4_FEATURE_RO_COMPAT_FUNCS(readonly, READONLY) EXT4_FEATURE_RO_COMPAT_FUNCS(project, PROJECT) EXT4_FEATURE_RO_COMPAT_FUNCS(verity, VERITY) EXT4_FEATURE_RO_COMPAT_FUNCS(orphan_present, ORPHAN_PRESENT) EXT4_FEATURE_INCOMPAT_FUNCS(compression, COMPRESSION) EXT4_FEATURE_INCOMPAT_FUNCS(filetype, FILETYPE) EXT4_FEATURE_INCOMPAT_FUNCS(journal_needs_recovery, RECOVER) EXT4_FEATURE_INCOMPAT_FUNCS(journal_dev, JOURNAL_DEV) EXT4_FEATURE_INCOMPAT_FUNCS(meta_bg, META_BG) EXT4_FEATURE_INCOMPAT_FUNCS(extents, EXTENTS) EXT4_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) EXT4_FEATURE_INCOMPAT_FUNCS(mmp, MMP) EXT4_FEATURE_INCOMPAT_FUNCS(flex_bg, FLEX_BG) EXT4_FEATURE_INCOMPAT_FUNCS(ea_inode, EA_INODE) EXT4_FEATURE_INCOMPAT_FUNCS(dirdata, DIRDATA) EXT4_FEATURE_INCOMPAT_FUNCS(csum_seed, CSUM_SEED) EXT4_FEATURE_INCOMPAT_FUNCS(largedir, LARGEDIR) EXT4_FEATURE_INCOMPAT_FUNCS(inline_data, INLINE_DATA) EXT4_FEATURE_INCOMPAT_FUNCS(encrypt, ENCRYPT) EXT4_FEATURE_INCOMPAT_FUNCS(casefold, CASEFOLD) #define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR #define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_META_BG) #define EXT2_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) #define EXT3_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR #define EXT3_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_RECOVER| \ EXT4_FEATURE_INCOMPAT_META_BG) #define EXT3_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) #define EXT4_FEATURE_COMPAT_SUPP (EXT4_FEATURE_COMPAT_EXT_ATTR| \ EXT4_FEATURE_COMPAT_ORPHAN_FILE) #define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_RECOVER| \ EXT4_FEATURE_INCOMPAT_META_BG| \ EXT4_FEATURE_INCOMPAT_EXTENTS| \ EXT4_FEATURE_INCOMPAT_64BIT| \ EXT4_FEATURE_INCOMPAT_FLEX_BG| \ EXT4_FEATURE_INCOMPAT_EA_INODE| \ EXT4_FEATURE_INCOMPAT_MMP | \ EXT4_FEATURE_INCOMPAT_INLINE_DATA | \ EXT4_FEATURE_INCOMPAT_ENCRYPT | \ EXT4_FEATURE_INCOMPAT_CASEFOLD | \ EXT4_FEATURE_INCOMPAT_CSUM_SEED | \ EXT4_FEATURE_INCOMPAT_LARGEDIR) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \ EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \ EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\ EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\ EXT4_FEATURE_RO_COMPAT_QUOTA |\ EXT4_FEATURE_RO_COMPAT_PROJECT |\ EXT4_FEATURE_RO_COMPAT_VERITY |\ EXT4_FEATURE_RO_COMPAT_ORPHAN_PRESENT) #define EXTN_FEATURE_FUNCS(ver) \ static inline bool ext4_has_unknown_ext##ver##_compat_features(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_compat & \ cpu_to_le32(~EXT##ver##_FEATURE_COMPAT_SUPP)) != 0); \ } \ static inline bool ext4_has_unknown_ext##ver##_ro_compat_features(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \ cpu_to_le32(~EXT##ver##_FEATURE_RO_COMPAT_SUPP)) != 0); \ } \ static inline bool ext4_has_unknown_ext##ver##_incompat_features(struct super_block *sb) \ { \ return ((EXT4_SB(sb)->s_es->s_feature_incompat & \ cpu_to_le32(~EXT##ver##_FEATURE_INCOMPAT_SUPP)) != 0); \ } EXTN_FEATURE_FUNCS(2) EXTN_FEATURE_FUNCS(3) EXTN_FEATURE_FUNCS(4) static inline bool ext4_has_compat_features(struct super_block *sb) { return (EXT4_SB(sb)->s_es->s_feature_compat != 0); } static inline bool ext4_has_ro_compat_features(struct super_block *sb) { return (EXT4_SB(sb)->s_es->s_feature_ro_compat != 0); } static inline bool ext4_has_incompat_features(struct super_block *sb) { return (EXT4_SB(sb)->s_es->s_feature_incompat != 0); } extern int ext4_feature_set_ok(struct super_block *sb, int readonly); /* * Superblock flags */ #define EXT4_FLAGS_RESIZING 0 #define EXT4_FLAGS_SHUTDOWN 1 #define EXT4_FLAGS_BDEV_IS_DAX 2 static inline int ext4_forced_shutdown(struct super_block *sb) { return test_bit(EXT4_FLAGS_SHUTDOWN, &EXT4_SB(sb)->s_ext4_flags); } /* * Default values for user and/or group using reserved blocks */ #define EXT4_DEF_RESUID 0 #define EXT4_DEF_RESGID 0 /* * Default project ID */ #define EXT4_DEF_PROJID 0 #define EXT4_DEF_INODE_READAHEAD_BLKS 32 /* * Default mount options */ #define EXT4_DEFM_DEBUG 0x0001 #define EXT4_DEFM_BSDGROUPS 0x0002 #define EXT4_DEFM_XATTR_USER 0x0004 #define EXT4_DEFM_ACL 0x0008 #define EXT4_DEFM_UID16 0x0010 #define EXT4_DEFM_JMODE 0x0060 #define EXT4_DEFM_JMODE_DATA 0x0020 #define EXT4_DEFM_JMODE_ORDERED 0x0040 #define EXT4_DEFM_JMODE_WBACK 0x0060 #define EXT4_DEFM_NOBARRIER 0x0100 #define EXT4_DEFM_BLOCK_VALIDITY 0x0200 #define EXT4_DEFM_DISCARD 0x0400 #define EXT4_DEFM_NODELALLOC 0x0800 /* * Default journal batch times */ #define EXT4_DEF_MIN_BATCH_TIME 0 #define EXT4_DEF_MAX_BATCH_TIME 15000 /* 15ms */ /* * Minimum number of groups in a flexgroup before we separate out * directories into the first block group of a flexgroup */ #define EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME 4 /* * Structure of a directory entry */ #define EXT4_NAME_LEN 255 /* * Base length of the ext4 directory entry excluding the name length */ #define EXT4_BASE_DIR_LEN (sizeof(struct ext4_dir_entry_2) - EXT4_NAME_LEN) struct ext4_dir_entry { __le32 inode; /* Inode number */ __le16 rec_len; /* Directory entry length */ __le16 name_len; /* Name length */ char name[EXT4_NAME_LEN]; /* File name */ }; /* * Encrypted Casefolded entries require saving the hash on disk. This structure * followed ext4_dir_entry_2's name[name_len] at the next 4 byte aligned * boundary. */ struct ext4_dir_entry_hash { __le32 hash; __le32 minor_hash; }; /* * The new version of the directory entry. Since EXT4 structures are * stored in intel byte order, and the name_len field could never be * bigger than 255 chars, it's safe to reclaim the extra byte for the * file_type field. */ struct ext4_dir_entry_2 { __le32 inode; /* Inode number */ __le16 rec_len; /* Directory entry length */ __u8 name_len; /* Name length */ __u8 file_type; /* See file type macros EXT4_FT_* below */ char name[EXT4_NAME_LEN]; /* File name */ }; /* * Access the hashes at the end of ext4_dir_entry_2 */ #define EXT4_DIRENT_HASHES(entry) \ ((struct ext4_dir_entry_hash *) \ (((void *)(entry)) + \ ((8 + (entry)->name_len + EXT4_DIR_ROUND) & ~EXT4_DIR_ROUND))) #define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(entry)->hash) #define EXT4_DIRENT_MINOR_HASH(entry) \ le32_to_cpu(EXT4_DIRENT_HASHES(entry)->minor_hash) static inline bool ext4_hash_in_dirent(const struct inode *inode) { return IS_CASEFOLDED(inode) && IS_ENCRYPTED(inode); } /* * This is a bogus directory entry at the end of each leaf block that * records checksums. */ struct ext4_dir_entry_tail { __le32 det_reserved_zero1; /* Pretend to be unused */ __le16 det_rec_len; /* 12 */ __u8 det_reserved_zero2; /* Zero name length */ __u8 det_reserved_ft; /* 0xDE, fake file type */ __le32 det_checksum; /* crc32c(uuid+inum+dirblock) */ }; #define EXT4_DIRENT_TAIL(block, blocksize) \ ((struct ext4_dir_entry_tail *)(((void *)(block)) + \ ((blocksize) - \ sizeof(struct ext4_dir_entry_tail)))) /* * Ext4 directory file types. Only the low 3 bits are used. The * other bits are reserved for now. */ #define EXT4_FT_UNKNOWN 0 #define EXT4_FT_REG_FILE 1 #define EXT4_FT_DIR 2 #define EXT4_FT_CHRDEV 3 #define EXT4_FT_BLKDEV 4 #define EXT4_FT_FIFO 5 #define EXT4_FT_SOCK 6 #define EXT4_FT_SYMLINK 7 #define EXT4_FT_MAX 8 #define EXT4_FT_DIR_CSUM 0xDE /* * EXT4_DIR_PAD defines the directory entries boundaries * * NOTE: It must be a multiple of 4 */ #define EXT4_DIR_PAD 4 #define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) #define EXT4_MAX_REC_LEN ((1<<16)-1) /* * The rec_len is dependent on the type of directory. Directories that are * casefolded and encrypted need to store the hash as well, so we add room for * ext4_extended_dir_entry_2. For all entries related to '.' or '..' you should * pass NULL for dir, as those entries do not use the extra fields. */ static inline unsigned int ext4_dir_rec_len(__u8 name_len, const struct inode *dir) { int rec_len = (name_len + 8 + EXT4_DIR_ROUND); if (dir && ext4_hash_in_dirent(dir)) rec_len += sizeof(struct ext4_dir_entry_hash); return (rec_len & ~EXT4_DIR_ROUND); } /* * If we ever get support for fs block sizes > page_size, we'll need * to remove the #if statements in the next two functions... */ static inline unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize) { unsigned len = le16_to_cpu(dlen); #if (PAGE_SIZE >= 65536) if (len == EXT4_MAX_REC_LEN || len == 0) return blocksize; return (len & 65532) | ((len & 3) << 16); #else return len; #endif } static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) { BUG_ON((len > blocksize) || (blocksize > (1 << 18)) || (len & 3)); #if (PAGE_SIZE >= 65536) if (len < 65536) return cpu_to_le16(len); if (len == blocksize) { if (blocksize == 65536) return cpu_to_le16(EXT4_MAX_REC_LEN); else return cpu_to_le16(0); } return cpu_to_le16((len & 65532) | ((len >> 16) & 3)); #else return cpu_to_le16(len); #endif } /* * Hash Tree Directory indexing * (c) Daniel Phillips, 2001 */ #define is_dx(dir) (ext4_has_feature_dir_index((dir)->i_sb) && \ ext4_test_inode_flag((dir), EXT4_INODE_INDEX)) #define EXT4_DIR_LINK_MAX(dir) unlikely((dir)->i_nlink >= EXT4_LINK_MAX && \ !(ext4_has_feature_dir_nlink((dir)->i_sb) && is_dx(dir))) #define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) /* Legal values for the dx_root hash_version field: */ #define DX_HASH_LEGACY 0 #define DX_HASH_HALF_MD4 1 #define DX_HASH_TEA 2 #define DX_HASH_LEGACY_UNSIGNED 3 #define DX_HASH_HALF_MD4_UNSIGNED 4 #define DX_HASH_TEA_UNSIGNED 5 #define DX_HASH_SIPHASH 6 #define DX_HASH_LAST DX_HASH_SIPHASH static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, const void *address, unsigned int length) { struct { struct shash_desc shash; char ctx[4]; } desc; BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx)); desc.shash.tfm = sbi->s_chksum_driver; *(u32 *)desc.ctx = crc; BUG_ON(crypto_shash_update(&desc.shash, address, length)); return *(u32 *)desc.ctx; } #ifdef __KERNEL__ /* hash info structure used by the directory hash */ struct dx_hash_info { u32 hash; u32 minor_hash; int hash_version; u32 *seed; }; /* 32 and 64 bit signed EOF for dx directories */ #define EXT4_HTREE_EOF_32BIT ((1UL << (32 - 1)) - 1) #define EXT4_HTREE_EOF_64BIT ((1ULL << (64 - 1)) - 1) /* * Control parameters used by ext4_htree_next_block */ #define HASH_NB_ALWAYS 1 struct ext4_filename { const struct qstr *usr_fname; struct fscrypt_str disk_name; struct dx_hash_info hinfo; #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_str crypto_buf; #endif #if IS_ENABLED(CONFIG_UNICODE) struct qstr cf_name; #endif }; #define fname_name(p) ((p)->disk_name.name) #define fname_usr_name(p) ((p)->usr_fname->name) #define fname_len(p) ((p)->disk_name.len) /* * Describe an inode's exact location on disk and in memory */ struct ext4_iloc { struct buffer_head *bh; unsigned long offset; ext4_group_t block_group; }; static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc) { return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset); } static inline bool ext4_is_quota_file(struct inode *inode) { return IS_NOQUOTA(inode) && !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL); } /* * This structure is stuffed into the struct file's private_data field * for directories. It is where we put information so that we can do * readdir operations in hash tree order. */ struct dir_private_info { struct rb_root root; struct rb_node *curr_node; struct fname *extra_fname; loff_t last_pos; __u32 curr_hash; __u32 curr_minor_hash; __u32 next_hash; u64 cookie; bool initialized; }; /* calculate the first block number of the group */ static inline ext4_fsblk_t ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no) { return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); } /* * Special error return code only used by dx_probe() and its callers. */ #define ERR_BAD_DX_DIR (-(MAX_ERRNO - 1)) /* htree levels for ext4 */ #define EXT4_HTREE_LEVEL_COMPAT 2 #define EXT4_HTREE_LEVEL 3 static inline int ext4_dir_htree_level(struct super_block *sb) { return ext4_has_feature_largedir(sb) ? EXT4_HTREE_LEVEL : EXT4_HTREE_LEVEL_COMPAT; } /* * Timeout and state flag for lazy initialization inode thread. */ #define EXT4_DEF_LI_WAIT_MULT 10 #define EXT4_DEF_LI_MAX_START_DELAY 5 #define EXT4_LAZYINIT_QUIT 0x0001 #define EXT4_LAZYINIT_RUNNING 0x0002 /* * Lazy inode table initialization info */ struct ext4_lazy_init { unsigned long li_state; struct list_head li_request_list; struct mutex li_list_mtx; }; enum ext4_li_mode { EXT4_LI_MODE_PREFETCH_BBITMAP, EXT4_LI_MODE_ITABLE, }; struct ext4_li_request { struct super_block *lr_super; enum ext4_li_mode lr_mode; ext4_group_t lr_first_not_zeroed; ext4_group_t lr_next_group; struct list_head lr_request; unsigned long lr_next_sched; unsigned long lr_timeout; }; struct ext4_features { struct kobject f_kobj; struct completion f_kobj_unregister; }; /* * This structure will be used for multiple mount protection. It will be * written into the block number saved in the s_mmp_block field in the * superblock. Programs that check MMP should assume that if * SEQ_FSCK (or any unknown code above SEQ_MAX) is present then it is NOT safe * to use the filesystem, regardless of how old the timestamp is. */ #define EXT4_MMP_MAGIC 0x004D4D50U /* ASCII for MMP */ #define EXT4_MMP_SEQ_CLEAN 0xFF4D4D50U /* mmp_seq value for clean unmount */ #define EXT4_MMP_SEQ_FSCK 0xE24D4D50U /* mmp_seq value when being fscked */ #define EXT4_MMP_SEQ_MAX 0xE24D4D4FU /* maximum valid mmp_seq value */ struct mmp_struct { __le32 mmp_magic; /* Magic number for MMP */ __le32 mmp_seq; /* Sequence no. updated periodically */ /* * mmp_time, mmp_nodename & mmp_bdevname are only used for information * purposes and do not affect the correctness of the algorithm */ __le64 mmp_time; /* Time last updated */ char mmp_nodename[64]; /* Node which last updated MMP block */ char mmp_bdevname[32]; /* Bdev which last updated MMP block */ /* * mmp_check_interval is used to verify if the MMP block has been * updated on the block device. The value is updated based on the * maximum time to write the MMP block during an update cycle. */ __le16 mmp_check_interval; __le16 mmp_pad1; __le32 mmp_pad2[226]; __le32 mmp_checksum; /* crc32c(uuid+mmp_block) */ }; /* arguments passed to the mmp thread */ struct mmpd_data { struct buffer_head *bh; /* bh from initial read_mmp_block() */ struct super_block *sb; /* super block of the fs */ }; /* * Check interval multiplier * The MMP block is written every update interval and initially checked every * update interval x the multiplier (the value is then adapted based on the * write latency). The reason is that writes can be delayed under load and we * don't want readers to incorrectly assume that the filesystem is no longer * in use. */ #define EXT4_MMP_CHECK_MULT 2UL /* * Minimum interval for MMP checking in seconds. */ #define EXT4_MMP_MIN_CHECK_INTERVAL 5UL /* * Maximum interval for MMP checking in seconds. */ #define EXT4_MMP_MAX_CHECK_INTERVAL 300UL /* * Function prototypes */ /* * Ok, these declarations are also in <linux/kernel.h> but none of the * ext4 source programs needs to include it so they are duplicated here. */ # define NORET_TYPE /**/ # define ATTRIB_NORET __attribute__((noreturn)) # define NORET_AND noreturn, /* bitmap.c */ extern unsigned int ext4_count_free(char *bitmap, unsigned numchars); void ext4_inode_bitmap_csum_set(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh); int ext4_inode_bitmap_csum_verify(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh); void ext4_block_bitmap_csum_set(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh); int ext4_block_bitmap_csum_verify(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh); /* balloc.c */ extern void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp); extern ext4_group_t ext4_get_group_number(struct super_block *sb, ext4_fsblk_t block); extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group); extern unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group); extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, ext4_fsblk_t goal, unsigned int flags, unsigned long *count, int *errp); extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi, s64 nclusters, unsigned int flags); extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, ext4_group_t block_group, struct buffer_head ** bh); extern struct ext4_group_info *ext4_get_group_info(struct super_block *sb, ext4_group_t group); extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group, bool ignore_locked); extern int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, struct buffer_head *bh); extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group); extern unsigned ext4_free_clusters_after_init(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); #if IS_ENABLED(CONFIG_UNICODE) extern int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, struct ext4_filename *fname); static inline void ext4_fname_free_ci_filename(struct ext4_filename *fname) { kfree(fname->cf_name.name); fname->cf_name.name = NULL; } #else static inline int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, struct ext4_filename *fname) { return 0; } static inline void ext4_fname_free_ci_filename(struct ext4_filename *fname) { } #endif /* ext4 encryption related stuff goes here crypto.c */ #ifdef CONFIG_FS_ENCRYPTION extern const struct fscrypt_operations ext4_cryptops; int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct ext4_filename *fname); int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, struct ext4_filename *fname); void ext4_fname_free_filename(struct ext4_filename *fname); int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg); #else /* !CONFIG_FS_ENCRYPTION */ static inline int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct ext4_filename *fname) { fname->usr_fname = iname; fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; return ext4_fname_setup_ci_filename(dir, iname, fname); } static inline int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, struct ext4_filename *fname) { return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname); } static inline void ext4_fname_free_filename(struct ext4_filename *fname) { ext4_fname_free_ci_filename(fname); } static inline int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg) { return -EOPNOTSUPP; } #endif /* !CONFIG_FS_ENCRYPTION */ /* dir.c */ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, struct file *, struct ext4_dir_entry_2 *, struct buffer_head *, char *, int, unsigned int); #define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \ unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \ (de), (bh), (buf), (size), (offset))) extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, struct ext4_dir_entry_2 *dirent, struct fscrypt_str *ent_name); extern void ext4_htree_free_dir_info(struct dir_private_info *p); extern int ext4_find_dest_de(struct inode *dir, struct inode *inode, struct buffer_head *bh, void *buf, int buf_size, struct ext4_filename *fname, struct ext4_dir_entry_2 **dest_de); void ext4_insert_dentry(struct inode *dir, struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { if (!ext4_has_feature_dir_index(inode->i_sb) && ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { /* ext4_iget() should have caught this... */ WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); } } static const unsigned char ext4_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK }; static inline unsigned char get_dtype(struct super_block *sb, int filetype) { if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX) return DT_UNKNOWN; return ext4_filetype_table[filetype]; } extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size); /* fsync.c */ extern int ext4_sync_file(struct file *, loff_t, loff_t, int); /* hash.c */ extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len, struct dx_hash_info *hinfo); /* ialloc.c */ extern int ext4_mark_inode_used(struct super_block *sb, int ino); extern struct inode *__ext4_new_inode(struct mnt_idmap *, handle_t *, struct inode *, umode_t, const struct qstr *qstr, __u32 goal, uid_t *owner, __u32 i_flags, int handle_type, unsigned int line_no, int nblocks); #define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \ __ext4_new_inode(&nop_mnt_idmap, (handle), (dir), (mode), (qstr), \ (goal), (owner), i_flags, 0, 0, 0) #define ext4_new_inode_start_handle(idmap, dir, mode, qstr, goal, owner, \ type, nblocks) \ __ext4_new_inode((idmap), NULL, (dir), (mode), (qstr), (goal), (owner), \ 0, (type), __LINE__, (nblocks)) extern void ext4_free_inode(handle_t *, struct inode *); extern struct inode * ext4_orphan_get(struct super_block *, unsigned long); extern unsigned long ext4_count_free_inodes(struct super_block *); extern unsigned long ext4_count_dirs(struct super_block *); extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap); extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, int barrier); extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate); /* fast_commit.c */ int ext4_fc_info_show(struct seq_file *seq, void *v); void ext4_fc_init(struct super_block *sb, journal_t *journal); void ext4_fc_init_inode(struct inode *inode); void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end); void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode, struct dentry *dentry); void __ext4_fc_track_link(handle_t *handle, struct inode *inode, struct dentry *dentry); void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry); void ext4_fc_track_link(handle_t *handle, struct dentry *dentry); void __ext4_fc_track_create(handle_t *handle, struct inode *inode, struct dentry *dentry); void ext4_fc_track_create(handle_t *handle, struct dentry *dentry); void ext4_fc_track_inode(handle_t *handle, struct inode *inode); void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle); void ext4_fc_start_update(struct inode *inode); void ext4_fc_stop_update(struct inode *inode); void ext4_fc_del(struct inode *inode); bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block); void ext4_fc_replay_cleanup(struct super_block *sb); int ext4_fc_commit(journal_t *journal, tid_t commit_tid); int __init ext4_fc_init_dentry_cache(void); void ext4_fc_destroy_dentry_cache(void); int ext4_fc_record_regions(struct super_block *sb, int ino, ext4_lblk_t lblk, ext4_fsblk_t pblk, int len, int replay); /* mballoc.c */ extern const struct seq_operations ext4_mb_seq_groups_ops; extern const struct seq_operations ext4_mb_seq_structs_summary_ops; extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset); extern int ext4_mb_init(struct super_block *); extern void ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); extern void ext4_discard_preallocations(struct inode *); extern int __init ext4_init_mballoc(void); extern void ext4_exit_mballoc(void); extern ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, unsigned int nr, int *cnt); extern void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, unsigned int nr); extern void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags); extern int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups); extern int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t i, struct ext4_group_desc *desc); extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count); extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid); extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, int len, bool state); static inline bool ext4_mb_cr_expensive(enum criteria cr) { return cr >= CR_GOAL_LEN_SLOW; } /* inode.c */ void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei); int ext4_inode_is_fast_symlink(struct inode *inode); struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int); struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int); int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count, bool wait, struct buffer_head **bhs); int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create); int ext4_walk_page_buffers(handle_t *handle, struct inode *inode, struct buffer_head *head, unsigned from, unsigned to, int *partial, int (*fn)(handle_t *handle, struct inode *inode, struct buffer_head *bh)); int do_journal_get_write_access(handle_t *handle, struct inode *inode, struct buffer_head *bh); #define FALL_BACK_TO_NONDELALLOC 1 #define CONVERT_INLINE_DATA 2 typedef enum { EXT4_IGET_NORMAL = 0, EXT4_IGET_SPECIAL = 0x0001, /* OK to iget a system inode */ EXT4_IGET_HANDLE = 0x0002, /* Inode # is from a handle */ EXT4_IGET_BAD = 0x0004, /* Allow to iget a bad inode */ EXT4_IGET_EA_INODE = 0x0008 /* Inode should contain an EA value */ } ext4_iget_flags; extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ext4_iget_flags flags, const char *function, unsigned int line); #define ext4_iget(sb, ino, flags) \ __ext4_iget((sb), (ino), (flags), __func__, __LINE__) extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern u32 ext4_dio_alignment(struct inode *inode); extern int ext4_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern void ext4_evict_inode(struct inode *); extern void ext4_clear_inode(struct inode *); extern int ext4_file_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern void ext4_dirty_inode(struct inode *, int); extern int ext4_change_inode_journal_flag(struct inode *, int); extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); extern int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino, struct ext4_iloc *iloc); extern int ext4_inode_attach_jinode(struct inode *inode); extern int ext4_can_truncate(struct inode *inode); extern int ext4_truncate(struct inode *); extern int ext4_break_layouts(struct inode *); extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length); extern void ext4_set_inode_flags(struct inode *, bool init); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); extern int ext4_writepage_trans_blocks(struct inode *); extern int ext4_normal_submit_inode_data_buffers(struct jbd2_inode *jinode); extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t lend); extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern int ext4_get_projid(struct inode *inode, kprojid_t *projid); extern void ext4_da_release_space(struct inode *inode, int to_free); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, ext4_lblk_t len); /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks); extern void ext4_ind_truncate(handle_t *, struct inode *inode); extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end); /* ioctl.c */ extern long ext4_ioctl(struct file *, unsigned int, unsigned long); extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); int ext4_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); int ext4_update_overhead(struct super_block *sb, bool force); int ext4_force_shutdown(struct super_block *sb, u32 flags); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); extern int ext4_ind_migrate(struct inode *inode); /* namei.c */ extern int ext4_init_new_dir(handle_t *handle, struct inode *dir, struct inode *inode); extern int ext4_dirblock_csum_verify(struct inode *inode, struct buffer_head *bh); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, __u32 start_minor_hash, __u32 *next_hash); extern int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, struct inode *dir, struct ext4_filename *fname, unsigned int offset, struct ext4_dir_entry_2 **res_dir); extern int ext4_generic_delete_entry(struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, void *entry_buf, int buf_size, int csum_size); extern bool ext4_empty_dir(struct inode *inode); /* resize.c */ extern void ext4_kvfree_array_rcu(void *to_free); extern int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input); extern int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, ext4_fsblk_t n_blocks_count); extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count); extern unsigned int ext4_list_backups(struct super_block *sb, unsigned int *three, unsigned int *five, unsigned int *seven); /* super.c */ extern struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, blk_opf_t op_flags); extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block); extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io); extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io); extern int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait); extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block); extern int ext4_seq_options_show(struct seq_file *seq, void *offset); extern int ext4_calculate_overhead(struct super_block *sb); extern __le32 ext4_superblock_csum(struct super_block *sb, struct ext4_super_block *es); extern void ext4_superblock_csum_set(struct super_block *sb); extern int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup); extern const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]); extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t block_group, unsigned int flags); extern unsigned int ext4_num_base_meta_blocks(struct super_block *sb, ext4_group_t block_group); extern __printf(7, 8) void __ext4_error(struct super_block *, const char *, unsigned int, bool, int, __u64, const char *, ...); extern __printf(6, 7) void __ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t, int, const char *, ...); extern __printf(5, 6) void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t, const char *, ...); extern void __ext4_std_error(struct super_block *, const char *, unsigned int, int); extern __printf(4, 5) void __ext4_warning(struct super_block *, const char *, unsigned int, const char *, ...); extern __printf(4, 5) void __ext4_warning_inode(const struct inode *inode, const char *function, unsigned int line, const char *fmt, ...); extern __printf(3, 4) void __ext4_msg(struct super_block *, const char *, const char *, ...); extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp, const char *, unsigned int, const char *); extern __printf(7, 8) void __ext4_grp_locked_error(const char *, unsigned int, struct super_block *, ext4_group_t, unsigned long, ext4_fsblk_t, const char *, ...); #define EXT4_ERROR_INODE(inode, fmt, a...) \ ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a) #define EXT4_ERROR_INODE_ERR(inode, err, fmt, a...) \ __ext4_error_inode((inode), __func__, __LINE__, 0, (err), (fmt), ## a) #define ext4_error_inode_block(inode, block, err, fmt, a...) \ __ext4_error_inode((inode), __func__, __LINE__, (block), (err), \ (fmt), ## a) #define EXT4_ERROR_FILE(file, block, fmt, a...) \ ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a) #define ext4_abort(sb, err, fmt, a...) \ __ext4_error((sb), __func__, __LINE__, true, (err), 0, (fmt), ## a) #ifdef CONFIG_PRINTK #define ext4_error_inode(inode, func, line, block, fmt, ...) \ __ext4_error_inode(inode, func, line, block, 0, fmt, ##__VA_ARGS__) #define ext4_error_inode_err(inode, func, line, block, err, fmt, ...) \ __ext4_error_inode((inode), (func), (line), (block), \ (err), (fmt), ##__VA_ARGS__) #define ext4_error_file(file, func, line, block, fmt, ...) \ __ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__) #define ext4_error(sb, fmt, ...) \ __ext4_error((sb), __func__, __LINE__, false, 0, 0, (fmt), \ ##__VA_ARGS__) #define ext4_error_err(sb, err, fmt, ...) \ __ext4_error((sb), __func__, __LINE__, false, (err), 0, (fmt), \ ##__VA_ARGS__) #define ext4_warning(sb, fmt, ...) \ __ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__) #define ext4_warning_inode(inode, fmt, ...) \ __ext4_warning_inode(inode, __func__, __LINE__, fmt, ##__VA_ARGS__) #define ext4_msg(sb, level, fmt, ...) \ __ext4_msg(sb, level, fmt, ##__VA_ARGS__) #define dump_mmp_msg(sb, mmp, msg) \ __dump_mmp_msg(sb, mmp, __func__, __LINE__, msg) #define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...) \ __ext4_grp_locked_error(__func__, __LINE__, sb, grp, ino, block, \ fmt, ##__VA_ARGS__) #else #define ext4_error_inode(inode, func, line, block, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_error_inode(inode, "", 0, block, 0, " "); \ } while (0) #define ext4_error_inode_err(inode, func, line, block, err, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_error_inode(inode, "", 0, block, err, " "); \ } while (0) #define ext4_error_file(file, func, line, block, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_error_file(file, "", 0, block, " "); \ } while (0) #define ext4_error(sb, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_error(sb, "", 0, false, 0, 0, " "); \ } while (0) #define ext4_error_err(sb, err, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_error(sb, "", 0, false, err, 0, " "); \ } while (0) #define ext4_warning(sb, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_warning(sb, "", 0, " "); \ } while (0) #define ext4_warning_inode(inode, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_warning_inode(inode, "", 0, " "); \ } while (0) #define ext4_msg(sb, level, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_msg(sb, "", " "); \ } while (0) #define dump_mmp_msg(sb, mmp, msg) \ __dump_mmp_msg(sb, mmp, "", 0, "") #define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ __ext4_grp_locked_error("", 0, sb, grp, ino, block, " "); \ } while (0) #endif extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg); extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, struct ext4_group_desc *bg); extern ext4_fsblk_t ext4_inode_table(struct super_block *sb, struct ext4_group_desc *bg); extern __u32 ext4_free_group_clusters(struct super_block *sb, struct ext4_group_desc *bg); extern __u32 ext4_free_inodes_count(struct super_block *sb, struct ext4_group_desc *bg); extern __u32 ext4_used_dirs_count(struct super_block *sb, struct ext4_group_desc *bg); extern __u32 ext4_itable_unused_count(struct super_block *sb, struct ext4_group_desc *bg); extern void ext4_block_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk); extern void ext4_inode_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk); extern void ext4_inode_table_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk); extern void ext4_free_group_clusters_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_free_inodes_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group, struct ext4_group_desc *gdp); extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group, struct ext4_group_desc *gdp); extern int ext4_register_li_request(struct super_block *sb, ext4_group_t first_not_zeroed); static inline int ext4_has_metadata_csum(struct super_block *sb) { WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) && !EXT4_SB(sb)->s_chksum_driver); return ext4_has_feature_metadata_csum(sb) && (EXT4_SB(sb)->s_chksum_driver != NULL); } static inline int ext4_has_group_desc_csum(struct super_block *sb) { return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb); } #define ext4_read_incompat_64bit_val(es, name) \ (((es)->s_feature_incompat & cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT) \ ? (ext4_fsblk_t)le32_to_cpu(es->name##_hi) << 32 : 0) | \ le32_to_cpu(es->name##_lo)) static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { return ext4_read_incompat_64bit_val(es, s_blocks_count); } static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es) { return ext4_read_incompat_64bit_val(es, s_r_blocks_count); } static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es) { return ext4_read_incompat_64bit_val(es, s_free_blocks_count); } static inline void ext4_blocks_count_set(struct ext4_super_block *es, ext4_fsblk_t blk) { es->s_blocks_count_lo = cpu_to_le32((u32)blk); es->s_blocks_count_hi = cpu_to_le32(blk >> 32); } static inline void ext4_free_blocks_count_set(struct ext4_super_block *es, ext4_fsblk_t blk) { es->s_free_blocks_count_lo = cpu_to_le32((u32)blk); es->s_free_blocks_count_hi = cpu_to_le32(blk >> 32); } static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, ext4_fsblk_t blk) { es->s_r_blocks_count_lo = cpu_to_le32((u32)blk); es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32); } static inline loff_t ext4_isize(struct super_block *sb, struct ext4_inode *raw_inode) { if (ext4_has_feature_largedir(sb) || S_ISREG(le16_to_cpu(raw_inode->i_mode))) return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) | le32_to_cpu(raw_inode->i_size_lo); return (loff_t) le32_to_cpu(raw_inode->i_size_lo); } static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size) { raw_inode->i_size_lo = cpu_to_le32(i_size); raw_inode->i_size_high = cpu_to_le32(i_size >> 32); } /* * Reading s_groups_count requires using smp_rmb() afterwards. See * the locking protocol documented in the comments of ext4_group_add() * in resize.c */ static inline ext4_group_t ext4_get_groups_count(struct super_block *sb) { ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; smp_rmb(); return ngroups; } static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi, ext4_group_t block_group) { return block_group >> sbi->s_log_groups_per_flex; } static inline unsigned int ext4_flex_bg_size(struct ext4_sb_info *sbi) { return 1 << sbi->s_log_groups_per_flex; } #define ext4_std_error(sb, errno) \ do { \ if ((errno)) \ __ext4_std_error((sb), __func__, __LINE__, (errno)); \ } while (0) #ifdef CONFIG_SMP /* Each CPU can accumulate percpu_counter_batch clusters in their local * counters. So we need to make sure we have free clusters more * than percpu_counter_batch * nr_cpu_ids. Also add a window of 4 times. */ #define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids)) #else #define EXT4_FREECLUSTERS_WATERMARK 0 #endif /* Update i_disksize. Requires i_rwsem to avoid races with truncate */ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) { WARN_ON_ONCE(S_ISREG(inode->i_mode) && !inode_is_locked(inode)); down_write(&EXT4_I(inode)->i_data_sem); if (newsize > EXT4_I(inode)->i_disksize) WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize); up_write(&EXT4_I(inode)->i_data_sem); } /* Update i_size, i_disksize. Requires i_rwsem to avoid races with truncate */ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize) { int changed = 0; if (newsize > inode->i_size) { i_size_write(inode, newsize); changed = 1; } if (newsize > EXT4_I(inode)->i_disksize) { ext4_update_i_disksize(inode, newsize); changed |= 2; } return changed; } int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, loff_t len); struct ext4_group_info { unsigned long bb_state; #ifdef AGGRESSIVE_CHECK unsigned long bb_check_counter; #endif struct rb_root bb_free_root; ext4_grpblk_t bb_first_free; /* first free block */ ext4_grpblk_t bb_free; /* total free blocks */ ext4_grpblk_t bb_fragments; /* nr of freespace fragments */ int bb_avg_fragment_size_order; /* order of average fragment in BG */ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */ ext4_group_t bb_group; /* Group number */ struct list_head bb_prealloc_list; #ifdef DOUBLE_CHECK void *bb_bitmap; #endif struct rw_semaphore alloc_sem; struct list_head bb_avg_fragment_size_node; struct list_head bb_largest_free_order_node; ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block * regions, index is order. * bb_counters[3] = 5 means * 5 free 8-block regions. */ }; #define EXT4_GROUP_INFO_NEED_INIT_BIT 0 #define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1 #define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2 #define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT 3 #define EXT4_GROUP_INFO_BBITMAP_CORRUPT \ (1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT) #define EXT4_GROUP_INFO_IBITMAP_CORRUPT \ (1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT) #define EXT4_GROUP_INFO_BBITMAP_READ_BIT 4 #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_BBITMAP_CORRUPT(grp) \ (test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_IBITMAP_CORRUPT(grp) \ (test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_WAS_TRIMMED(grp) \ (test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_SET_TRIMMED(grp) \ (set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \ (clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_TEST_AND_SET_READ(grp) \ (test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state))) #define EXT4_MAX_CONTENTION 8 #define EXT4_CONTENTION_THRESHOLD 2 static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb, ext4_group_t group) { return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group); } /* * Returns true if the filesystem is busy enough that attempts to * access the block group locks has run into contention. */ static inline int ext4_fs_is_busy(struct ext4_sb_info *sbi) { return (atomic_read(&sbi->s_lock_busy) > EXT4_CONTENTION_THRESHOLD); } static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group) { spinlock_t *lock = ext4_group_lock_ptr(sb, group); if (spin_trylock(lock)) /* * We're able to grab the lock right away, so drop the * lock contention counter. */ atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, -1, 0); else { /* * The lock is busy, so bump the contention counter, * and then wait on the spin lock. */ atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, 1, EXT4_MAX_CONTENTION); spin_lock(lock); } } static inline void ext4_unlock_group(struct super_block *sb, ext4_group_t group) { spin_unlock(ext4_group_lock_ptr(sb, group)); } #ifdef CONFIG_QUOTA static inline bool ext4_quota_capable(struct super_block *sb) { return (test_opt(sb, QUOTA) || ext4_has_feature_quota(sb)); } static inline bool ext4_is_quota_journalled(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); return (ext4_has_feature_quota(sb) || sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]); } int ext4_enable_quotas(struct super_block *sb); #endif /* * Block validity checking */ #define ext4_check_indirect_blockref(inode, bh) \ ext4_check_blockref(__func__, __LINE__, inode, \ (__le32 *)(bh)->b_data, \ EXT4_ADDR_PER_BLOCK((inode)->i_sb)) #define ext4_ind_check_inode(inode) \ ext4_check_blockref(__func__, __LINE__, inode, \ EXT4_I(inode)->i_data, \ EXT4_NDIR_BLOCKS) /* * Inodes and files operations */ /* dir.c */ extern const struct file_operations ext4_dir_operations; /* file.c */ extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); /* inline.c */ extern int ext4_get_max_inline_size(struct inode *inode); extern int ext4_find_inline_data_nolock(struct inode *inode); extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode); int ext4_readpage_inline(struct inode *inode, struct folio *folio); extern int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, struct folio **foliop); int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct folio *folio); extern int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); extern int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode); extern int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent, struct inode *inode); extern int ext4_read_inline_dir(struct file *filp, struct dir_context *ctx, int *has_inline_data); extern int ext4_inlinedir_to_tree(struct file *dir_file, struct inode *dir, ext4_lblk_t block, struct dx_hash_info *hinfo, __u32 start_hash, __u32 start_minor_hash, int *has_inline_data); extern struct buffer_head *ext4_find_inline_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir, int *has_inline_data); extern int ext4_delete_inline_entry(handle_t *handle, struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, int *has_inline_data); extern bool empty_inline_dir(struct inode *dir, int *has_inline_data); extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode, struct ext4_dir_entry_2 **parent_de, int *retval); extern void *ext4_read_inline_link(struct inode *inode); struct iomap; extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap); extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline); extern int ext4_convert_inline_data(struct inode *inode); static inline int ext4_has_inline_data(struct inode *inode) { return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) && EXT4_I(inode)->i_inline_off; } /* namei.c */ extern const struct inode_operations ext4_dir_inode_operations; extern const struct inode_operations ext4_special_inode_operations; extern struct dentry *ext4_get_parent(struct dentry *child); extern struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, struct ext4_dir_entry_2 *de, int blocksize, int csum_size, unsigned int parent_ino, int dotdot_real_len); extern void ext4_initialize_dirent_tail(struct buffer_head *bh, unsigned int blocksize); extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode, struct buffer_head *bh); extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name, struct inode *inode, struct dentry *dentry); extern int __ext4_link(struct inode *dir, struct inode *inode, struct dentry *dentry); #define S_SHIFT 12 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { [S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = EXT4_FT_DIR, [S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV, [S_IFBLK >> S_SHIFT] = EXT4_FT_BLKDEV, [S_IFIFO >> S_SHIFT] = EXT4_FT_FIFO, [S_IFSOCK >> S_SHIFT] = EXT4_FT_SOCK, [S_IFLNK >> S_SHIFT] = EXT4_FT_SYMLINK, }; static inline void ext4_set_de_type(struct super_block *sb, struct ext4_dir_entry_2 *de, umode_t mode) { if (ext4_has_feature_filetype(sb)) de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; } /* readpages.c */ extern int ext4_mpage_readpages(struct inode *inode, struct readahead_control *rac, struct folio *folio); extern int __init ext4_init_post_read_processing(void); extern void ext4_exit_post_read_processing(void); /* symlink.c */ extern const struct inode_operations ext4_encrypted_symlink_inode_operations; extern const struct inode_operations ext4_symlink_inode_operations; extern const struct inode_operations ext4_fast_symlink_inode_operations; /* sysfs.c */ extern void ext4_notify_error_sysfs(struct ext4_sb_info *sbi); extern int ext4_register_sysfs(struct super_block *sb); extern void ext4_unregister_sysfs(struct super_block *sb); extern int __init ext4_init_sysfs(void); extern void ext4_exit_sysfs(void); /* block_validity */ extern void ext4_release_system_zone(struct super_block *sb); extern int ext4_setup_system_zone(struct super_block *sb); extern int __init ext4_init_system_zone(void); extern void ext4_exit_system_zone(void); extern int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, unsigned int count); extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int); extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode, ext4_fsblk_t start_blk, unsigned int count); /* extents.c */ struct ext4_ext_path; struct ext4_extent; /* * Maximum number of logical blocks in a file; ext4_extent's ee_block is * __le32. */ #define EXT_MAX_BLOCKS 0xffffffff extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode); extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents); extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); extern int ext4_ext_truncate(handle_t *, struct inode *); extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end); extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); extern long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len); extern int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end); extern int ext4_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, struct ext4_ext_path *path); extern struct ext4_ext_path *ext4_ext_insert_extent( handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *newext, int gb_flags); extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t, struct ext4_ext_path *, int flags); extern void ext4_free_ext_path(struct ext4_ext_path *); extern int ext4_ext_check_inode(struct inode *inode); extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); extern int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); extern int ext4_ext_precache(struct inode *inode); extern int ext4_swap_extents(handle_t *handle, struct inode *inode1, struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2, ext4_lblk_t count, int mark_unwritten,int *err); extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu); extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode, int check_cred, int restart_cred, int revoke_cred); extern void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end); extern int ext4_ext_replay_set_iblocks(struct inode *inode); extern int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start, int len, int unwritten, ext4_fsblk_t pblk); extern int ext4_ext_clear_bb(struct inode *inode); /* move_extent.c */ extern void ext4_double_down_write_data_sem(struct inode *first, struct inode *second); extern void ext4_double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode); extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 start_orig, __u64 start_donor, __u64 len, __u64 *moved_len); /* page-io.c */ extern int __init ext4_init_pageio(void); extern void ext4_exit_pageio(void); extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags); extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end); extern int ext4_put_io_end(ext4_io_end_t *io_end); extern void ext4_put_io_end_defer(ext4_io_end_t *io_end); extern void ext4_io_submit_init(struct ext4_io_submit *io, struct writeback_control *wbc); extern void ext4_end_io_rsv_work(struct work_struct *work); extern void ext4_io_submit(struct ext4_io_submit *io); int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *page, size_t len); extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end); extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end); /* mmp.c */ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); /* mmp.c */ extern void ext4_stop_mmpd(struct ext4_sb_info *sbi); /* verity.c */ extern const struct fsverity_operations ext4_verityops; /* orphan.c */ extern int ext4_orphan_add(handle_t *, struct inode *); extern int ext4_orphan_del(handle_t *, struct inode *); extern void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es); extern void ext4_release_orphan_info(struct super_block *sb); extern int ext4_init_orphan_info(struct super_block *sb); extern int ext4_orphan_file_empty(struct super_block *sb); extern void ext4_orphan_file_block_trigger( struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh, void *data, size_t size); /* * Add new method to test whether block and inode bitmaps are properly * initialized. With uninit_bg reading the block from disk is not enough * to mark the bitmap uptodate. We need to also zero-out the bitmap */ #define BH_BITMAP_UPTODATE BH_JBDPrivateStart static inline int bitmap_uptodate(struct buffer_head *bh) { return (buffer_uptodate(bh) && test_bit(BH_BITMAP_UPTODATE, &(bh)->b_state)); } static inline void set_bitmap_uptodate(struct buffer_head *bh) { set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state); } /* For ioend & aio unwritten conversion wait queues */ #define EXT4_WQ_HASH_SZ 37 #define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\ EXT4_WQ_HASH_SZ]) extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; extern int ext4_resize_begin(struct super_block *sb); extern int ext4_resize_end(struct super_block *sb, bool update_backups); static inline void ext4_set_io_unwritten_flag(struct inode *inode, struct ext4_io_end *io_end) { if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { io_end->flag |= EXT4_IO_END_UNWRITTEN; atomic_inc(&EXT4_I(inode)->i_unwritten); } } static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) { struct inode *inode = io_end->inode; if (io_end->flag & EXT4_IO_END_UNWRITTEN) { io_end->flag &= ~EXT4_IO_END_UNWRITTEN; /* Wake up anyone waiting on unwritten extent conversion */ if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) wake_up_all(ext4_ioend_wq(inode)); } } extern const struct iomap_ops ext4_iomap_ops; extern const struct iomap_ops ext4_iomap_overwrite_ops; extern const struct iomap_ops ext4_iomap_report_ops; static inline int ext4_buffer_uptodate(struct buffer_head *bh) { /* * If the buffer has the write error flag, we have failed * to write out data in the block. In this case, we don't * have to read the block because we may read the old data * successfully. */ if (buffer_write_io_error(bh)) set_buffer_uptodate(bh); return buffer_uptodate(bh); } extern int ext4_block_write_begin(handle_t *handle, struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block); #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _EXT4_H */ |
| 8 3 23 5 21 42 19 23 23 23 23 23 23 23 8 48 10 20 5 5 5 3 3 2 1 7 7 2 7 6 7 6 10 7 11 26 27 24 23 27 9 8 2 43 46 46 46 46 46 34 45 46 5 5 43 46 46 1 4 1 1 1 3 2 1 1 3 3 3 3 3 3 8 8 8 8 3 4 12 9 3 6 6 3 6 4 4 5 4 8 3 3 3 3 3 12 12 12 12 20 20 20 14 23 63 63 62 62 20 20 20 20 1 20 20 19 19 19 19 18 18 18 18 19 19 19 19 19 19 19 19 2 18 19 19 20 20 20 3 1 1 1 1 2 2 1 2 1 1 3 1 2 1 2 1 3 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Loopback soundcard * * Original code: * Copyright (c) by Jaroslav Kysela <perex@perex.cz> * * More accurate positioning and full-duplex support: * Copyright (c) Ahmet İnan <ainan at mathematik.uni-freiburg.de> * * Major (almost complete) rewrite: * Copyright (c) by Takashi Iwai <tiwai@suse.de> * * A next major update in 2010 (separate timers for playback and capture): * Copyright (c) Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/jiffies.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/wait.h> #include <linux/module.h> #include <linux/platform_device.h> #include <sound/core.h> #include <sound/control.h> #include <sound/pcm.h> #include <sound/pcm_params.h> #include <sound/info.h> #include <sound/initval.h> #include <sound/timer.h> MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>"); MODULE_DESCRIPTION("A loopback soundcard"); MODULE_LICENSE("GPL"); #define MAX_PCM_SUBSTREAMS 8 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */ static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */ static bool enable[SNDRV_CARDS] = {1, [1 ... (SNDRV_CARDS - 1)] = 0}; static int pcm_substreams[SNDRV_CARDS] = {[0 ... (SNDRV_CARDS - 1)] = 8}; static int pcm_notify[SNDRV_CARDS]; static char *timer_source[SNDRV_CARDS]; module_param_array(index, int, NULL, 0444); MODULE_PARM_DESC(index, "Index value for loopback soundcard."); module_param_array(id, charp, NULL, 0444); MODULE_PARM_DESC(id, "ID string for loopback soundcard."); module_param_array(enable, bool, NULL, 0444); MODULE_PARM_DESC(enable, "Enable this loopback soundcard."); module_param_array(pcm_substreams, int, NULL, 0444); MODULE_PARM_DESC(pcm_substreams, "PCM substreams # (1-8) for loopback driver."); module_param_array(pcm_notify, int, NULL, 0444); MODULE_PARM_DESC(pcm_notify, "Break capture when PCM format/rate/channels changes."); module_param_array(timer_source, charp, NULL, 0444); MODULE_PARM_DESC(timer_source, "Sound card name or number and device/subdevice number of timer to be used. Empty string for jiffies timer [default]."); #define NO_PITCH 100000 #define CABLE_VALID_PLAYBACK BIT(SNDRV_PCM_STREAM_PLAYBACK) #define CABLE_VALID_CAPTURE BIT(SNDRV_PCM_STREAM_CAPTURE) #define CABLE_VALID_BOTH (CABLE_VALID_PLAYBACK | CABLE_VALID_CAPTURE) struct loopback_cable; struct loopback_pcm; struct loopback_ops { /* optional * call in loopback->cable_lock */ int (*open)(struct loopback_pcm *dpcm); /* required * call in cable->lock */ int (*start)(struct loopback_pcm *dpcm); /* required * call in cable->lock */ int (*stop)(struct loopback_pcm *dpcm); /* optional */ int (*stop_sync)(struct loopback_pcm *dpcm); /* optional */ int (*close_substream)(struct loopback_pcm *dpcm); /* optional * call in loopback->cable_lock */ int (*close_cable)(struct loopback_pcm *dpcm); /* optional * call in cable->lock */ unsigned int (*pos_update)(struct loopback_cable *cable); /* optional */ void (*dpcm_info)(struct loopback_pcm *dpcm, struct snd_info_buffer *buffer); }; struct loopback_cable { spinlock_t lock; struct loopback_pcm *streams[2]; struct snd_pcm_hardware hw; /* flags */ unsigned int valid; unsigned int running; unsigned int pause; /* timer specific */ const struct loopback_ops *ops; /* If sound timer is used */ struct { int stream; struct snd_timer_id id; struct work_struct event_work; struct snd_timer_instance *instance; } snd_timer; }; struct loopback_setup { unsigned int notify: 1; unsigned int rate_shift; snd_pcm_format_t format; unsigned int rate; snd_pcm_access_t access; unsigned int channels; struct snd_ctl_elem_id active_id; struct snd_ctl_elem_id format_id; struct snd_ctl_elem_id rate_id; struct snd_ctl_elem_id channels_id; struct snd_ctl_elem_id access_id; }; struct loopback { struct snd_card *card; struct mutex cable_lock; struct loopback_cable *cables[MAX_PCM_SUBSTREAMS][2]; struct snd_pcm *pcm[2]; struct loopback_setup setup[MAX_PCM_SUBSTREAMS][2]; const char *timer_source; }; struct loopback_pcm { struct loopback *loopback; struct snd_pcm_substream *substream; struct loopback_cable *cable; unsigned int pcm_buffer_size; unsigned int buf_pos; /* position in buffer */ unsigned int silent_size; /* PCM parameters */ unsigned int pcm_period_size; unsigned int pcm_bps; /* bytes per second */ unsigned int pcm_salign; /* bytes per sample * channels */ unsigned int pcm_rate_shift; /* rate shift value */ /* flags */ unsigned int period_update_pending :1; /* timer stuff */ unsigned int irq_pos; /* fractional IRQ position in jiffies * ticks */ unsigned int period_size_frac; /* period size in jiffies ticks */ unsigned int last_drift; unsigned long last_jiffies; /* If jiffies timer is used */ struct timer_list timer; /* size of per channel buffer in case of non-interleaved access */ unsigned int channel_buf_n; }; static struct platform_device *devices[SNDRV_CARDS]; static inline unsigned int byte_pos(struct loopback_pcm *dpcm, unsigned int x) { if (dpcm->pcm_rate_shift == NO_PITCH) { x /= HZ; } else { x = div_u64(NO_PITCH * (unsigned long long)x, HZ * (unsigned long long)dpcm->pcm_rate_shift); } return x - (x % dpcm->pcm_salign); } static inline unsigned int frac_pos(struct loopback_pcm *dpcm, unsigned int x) { if (dpcm->pcm_rate_shift == NO_PITCH) { /* no pitch */ return x * HZ; } else { x = div_u64(dpcm->pcm_rate_shift * (unsigned long long)x * HZ, NO_PITCH); } return x; } static inline struct loopback_setup *get_setup(struct loopback_pcm *dpcm) { int device = dpcm->substream->pstr->pcm->device; if (dpcm->substream->stream == SNDRV_PCM_STREAM_PLAYBACK) device ^= 1; return &dpcm->loopback->setup[dpcm->substream->number][device]; } static inline unsigned int get_notify(struct loopback_pcm *dpcm) { return get_setup(dpcm)->notify; } static inline unsigned int get_rate_shift(struct loopback_pcm *dpcm) { return get_setup(dpcm)->rate_shift; } /* call in cable->lock */ static int loopback_jiffies_timer_start(struct loopback_pcm *dpcm) { unsigned long tick; unsigned int rate_shift = get_rate_shift(dpcm); if (rate_shift != dpcm->pcm_rate_shift) { dpcm->pcm_rate_shift = rate_shift; dpcm->period_size_frac = frac_pos(dpcm, dpcm->pcm_period_size); } if (dpcm->period_size_frac <= dpcm->irq_pos) { dpcm->irq_pos %= dpcm->period_size_frac; dpcm->period_update_pending = 1; } tick = dpcm->period_size_frac - dpcm->irq_pos; tick = DIV_ROUND_UP(tick, dpcm->pcm_bps); mod_timer(&dpcm->timer, jiffies + tick); return 0; } /* call in cable->lock */ static int loopback_snd_timer_start(struct loopback_pcm *dpcm) { struct loopback_cable *cable = dpcm->cable; int err; /* Loopback device has to use same period as timer card. Therefore * wake up for each snd_pcm_period_elapsed() call of timer card. */ err = snd_timer_start(cable->snd_timer.instance, 1); if (err < 0) { /* do not report error if trying to start but already * running. For example called by opposite substream * of the same cable */ if (err == -EBUSY) return 0; pcm_err(dpcm->substream->pcm, "snd_timer_start(%d,%d,%d) failed with %d", cable->snd_timer.id.card, cable->snd_timer.id.device, cable->snd_timer.id.subdevice, err); } return err; } /* call in cable->lock */ static inline int loopback_jiffies_timer_stop(struct loopback_pcm *dpcm) { del_timer(&dpcm->timer); dpcm->timer.expires = 0; return 0; } /* call in cable->lock */ static int loopback_snd_timer_stop(struct loopback_pcm *dpcm) { struct loopback_cable *cable = dpcm->cable; int err; /* only stop if both devices (playback and capture) are not running */ if (cable->running ^ cable->pause) return 0; err = snd_timer_stop(cable->snd_timer.instance); if (err < 0) { pcm_err(dpcm->substream->pcm, "snd_timer_stop(%d,%d,%d) failed with %d", cable->snd_timer.id.card, cable->snd_timer.id.device, cable->snd_timer.id.subdevice, err); } return err; } static inline int loopback_jiffies_timer_stop_sync(struct loopback_pcm *dpcm) { del_timer_sync(&dpcm->timer); return 0; } /* call in loopback->cable_lock */ static int loopback_snd_timer_close_cable(struct loopback_pcm *dpcm) { struct loopback_cable *cable = dpcm->cable; /* snd_timer was not opened */ if (!cable->snd_timer.instance) return 0; /* will only be called from free_cable() when other stream was * already closed. Other stream cannot be reopened as long as * loopback->cable_lock is locked. Therefore no need to lock * cable->lock; */ snd_timer_close(cable->snd_timer.instance); /* wait till drain work has finished if requested */ cancel_work_sync(&cable->snd_timer.event_work); snd_timer_instance_free(cable->snd_timer.instance); memset(&cable->snd_timer, 0, sizeof(cable->snd_timer)); return 0; } static bool is_access_interleaved(snd_pcm_access_t access) { switch (access) { case SNDRV_PCM_ACCESS_MMAP_INTERLEAVED: case SNDRV_PCM_ACCESS_RW_INTERLEAVED: return true; default: return false; } }; static int loopback_check_format(struct loopback_cable *cable, int stream) { struct snd_pcm_runtime *runtime, *cruntime; struct loopback_setup *setup; struct snd_card *card; int check; if (cable->valid != CABLE_VALID_BOTH) { if (stream == SNDRV_PCM_STREAM_PLAYBACK) goto __notify; return 0; } runtime = cable->streams[SNDRV_PCM_STREAM_PLAYBACK]-> substream->runtime; cruntime = cable->streams[SNDRV_PCM_STREAM_CAPTURE]-> substream->runtime; check = runtime->format != cruntime->format || runtime->rate != cruntime->rate || runtime->channels != cruntime->channels || is_access_interleaved(runtime->access) != is_access_interleaved(cruntime->access); if (!check) return 0; if (stream == SNDRV_PCM_STREAM_CAPTURE) { return -EIO; } else { snd_pcm_stop(cable->streams[SNDRV_PCM_STREAM_CAPTURE]-> substream, SNDRV_PCM_STATE_DRAINING); __notify: runtime = cable->streams[SNDRV_PCM_STREAM_PLAYBACK]-> substream->runtime; setup = get_setup(cable->streams[SNDRV_PCM_STREAM_PLAYBACK]); card = cable->streams[SNDRV_PCM_STREAM_PLAYBACK]->loopback->card; if (setup->format != runtime->format) { snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &setup->format_id); setup->format = runtime->format; } if (setup->rate != runtime->rate) { snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &setup->rate_id); setup->rate = runtime->rate; } if (setup->channels != runtime->channels) { snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &setup->channels_id); setup->channels = runtime->channels; } if (is_access_interleaved(setup->access) != is_access_interleaved(runtime->access)) { snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &setup->access_id); setup->access = runtime->access; } } return 0; } static void loopback_active_notify(struct loopback_pcm *dpcm) { snd_ctl_notify(dpcm->loopback->card, SNDRV_CTL_EVENT_MASK_VALUE, &get_setup(dpcm)->active_id); } static int loopback_trigger(struct snd_pcm_substream *substream, int cmd) { struct snd_pcm_runtime *runtime = substream->runtime; struct loopback_pcm *dpcm = runtime->private_data; struct loopback_cable *cable = dpcm->cable; int err = 0, stream = 1 << substream->stream; switch (cmd) { case SNDRV_PCM_TRIGGER_START: err = loopback_check_format(cable, substream->stream); if (err < 0) return err; dpcm->last_jiffies = jiffies; dpcm->pcm_rate_shift = 0; dpcm->last_drift = 0; spin_lock(&cable->lock); cable->running |= stream; cable->pause &= ~stream; err = cable->ops->start(dpcm); spin_unlock(&cable->lock); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) loopback_active_notify(dpcm); break; case SNDRV_PCM_TRIGGER_STOP: spin_lock(&cable->lock); cable->running &= ~stream; cable->pause &= ~stream; err = cable->ops->stop(dpcm); spin_unlock(&cable->lock); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) loopback_active_notify(dpcm); break; case SNDRV_PCM_TRIGGER_PAUSE_PUSH: case SNDRV_PCM_TRIGGER_SUSPEND: spin_lock(&cable->lock); cable->pause |= stream; err = cable->ops->stop(dpcm); spin_unlock(&cable->lock); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) loopback_active_notify(dpcm); break; case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: case SNDRV_PCM_TRIGGER_RESUME: spin_lock(&cable->lock); dpcm->last_jiffies = jiffies; cable->pause &= ~stream; err = cable->ops->start(dpcm); spin_unlock(&cable->lock); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) loopback_active_notify(dpcm); break; default: return -EINVAL; } return err; } static void params_change(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; struct loopback_pcm *dpcm = runtime->private_data; struct loopback_cable *cable = dpcm->cable; cable->hw.formats = pcm_format_to_bits(runtime->format); cable->hw.rate_min = runtime->rate; cable->hw.rate_max = runtime->rate; cable->hw.channels_min = runtime->channels; cable->hw.channels_max = runtime->channels; if (cable->snd_timer.instance) { cable->hw.period_bytes_min = frames_to_bytes(runtime, runtime->period_size); cable->hw.period_bytes_max = cable->hw.period_bytes_min; } } static int loopback_prepare(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; struct loopback_pcm *dpcm = runtime->private_data; struct loopback_cable *cable = dpcm->cable; int err, bps, salign; if (cable->ops->stop_sync) { err = cable->ops->stop_sync(dpcm); if (err < 0) return err; } salign = (snd_pcm_format_physical_width(runtime->format) * runtime->channels) / 8; bps = salign * runtime->rate; if (bps <= 0 || salign <= 0) return -EINVAL; dpcm->buf_pos = 0; dpcm->pcm_buffer_size = frames_to_bytes(runtime, runtime->buffer_size); dpcm->channel_buf_n = dpcm->pcm_buffer_size / runtime->channels; if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) { /* clear capture buffer */ dpcm->silent_size = dpcm->pcm_buffer_size; snd_pcm_format_set_silence(runtime->format, runtime->dma_area, runtime->buffer_size * runtime->channels); } dpcm->irq_pos = 0; dpcm->period_update_pending = 0; dpcm->pcm_bps = bps; dpcm->pcm_salign = salign; dpcm->pcm_period_size = frames_to_bytes(runtime, runtime->period_size); mutex_lock(&dpcm->loopback->cable_lock); if (!(cable->valid & ~(1 << substream->stream)) || (get_setup(dpcm)->notify && substream->stream == SNDRV_PCM_STREAM_PLAYBACK)) params_change(substream); cable->valid |= 1 << substream->stream; mutex_unlock(&dpcm->loopback->cable_lock); return 0; } static void clear_capture_buf(struct loopback_pcm *dpcm, unsigned int bytes) { struct snd_pcm_runtime *runtime = dpcm->substream->runtime; char *dst = runtime->dma_area; unsigned int dst_off = dpcm->buf_pos; if (dpcm->silent_size >= dpcm->pcm_buffer_size) return; if (dpcm->silent_size + bytes > dpcm->pcm_buffer_size) bytes = dpcm->pcm_buffer_size - dpcm->silent_size; for (;;) { unsigned int size = bytes; if (dst_off + size > dpcm->pcm_buffer_size) size = dpcm->pcm_buffer_size - dst_off; snd_pcm_format_set_silence(runtime->format, dst + dst_off, bytes_to_frames(runtime, size) * runtime->channels); dpcm->silent_size += size; bytes -= size; if (!bytes) break; dst_off = 0; } } static void copy_play_buf_part_n(struct loopback_pcm *play, struct loopback_pcm *capt, unsigned int size, unsigned int src_off, unsigned int dst_off) { unsigned int channels = capt->substream->runtime->channels; unsigned int size_p_ch = size / channels; unsigned int src_off_ch = src_off / channels; unsigned int dst_off_ch = dst_off / channels; int i; for (i = 0; i < channels; i++) { memcpy(capt->substream->runtime->dma_area + capt->channel_buf_n * i + dst_off_ch, play->substream->runtime->dma_area + play->channel_buf_n * i + src_off_ch, size_p_ch); } } static void copy_play_buf(struct loopback_pcm *play, struct loopback_pcm *capt, unsigned int bytes) { struct snd_pcm_runtime *runtime = play->substream->runtime; char *src = runtime->dma_area; char *dst = capt->substream->runtime->dma_area; unsigned int src_off = play->buf_pos; unsigned int dst_off = capt->buf_pos; unsigned int clear_bytes = 0; /* check if playback is draining, trim the capture copy size * when our pointer is at the end of playback ring buffer */ if (runtime->state == SNDRV_PCM_STATE_DRAINING && snd_pcm_playback_hw_avail(runtime) < runtime->buffer_size) { snd_pcm_uframes_t appl_ptr, appl_ptr1, diff; appl_ptr = appl_ptr1 = runtime->control->appl_ptr; appl_ptr1 -= appl_ptr1 % runtime->buffer_size; appl_ptr1 += play->buf_pos / play->pcm_salign; if (appl_ptr < appl_ptr1) appl_ptr1 -= runtime->buffer_size; diff = (appl_ptr - appl_ptr1) * play->pcm_salign; if (diff < bytes) { clear_bytes = bytes - diff; bytes = diff; } } for (;;) { unsigned int size = bytes; if (src_off + size > play->pcm_buffer_size) size = play->pcm_buffer_size - src_off; if (dst_off + size > capt->pcm_buffer_size) size = capt->pcm_buffer_size - dst_off; if (!is_access_interleaved(runtime->access)) copy_play_buf_part_n(play, capt, size, src_off, dst_off); else memcpy(dst + dst_off, src + src_off, size); capt->silent_size = 0; bytes -= size; if (!bytes) break; src_off = (src_off + size) % play->pcm_buffer_size; dst_off = (dst_off + size) % capt->pcm_buffer_size; } if (clear_bytes > 0) { clear_capture_buf(capt, clear_bytes); capt->silent_size = 0; } } static inline unsigned int bytepos_delta(struct loopback_pcm *dpcm, unsigned int jiffies_delta) { unsigned long last_pos; unsigned int delta; last_pos = byte_pos(dpcm, dpcm->irq_pos); dpcm->irq_pos += jiffies_delta * dpcm->pcm_bps; delta = byte_pos(dpcm, dpcm->irq_pos) - last_pos; if (delta >= dpcm->last_drift) delta -= dpcm->last_drift; dpcm->last_drift = 0; if (dpcm->irq_pos >= dpcm->period_size_frac) { dpcm->irq_pos %= dpcm->period_size_frac; dpcm->period_update_pending = 1; } return delta; } static inline void bytepos_finish(struct loopback_pcm *dpcm, unsigned int delta) { dpcm->buf_pos += delta; dpcm->buf_pos %= dpcm->pcm_buffer_size; } /* call in cable->lock */ static unsigned int loopback_jiffies_timer_pos_update (struct loopback_cable *cable) { struct loopback_pcm *dpcm_play = cable->streams[SNDRV_PCM_STREAM_PLAYBACK]; struct loopback_pcm *dpcm_capt = cable->streams[SNDRV_PCM_STREAM_CAPTURE]; unsigned long delta_play = 0, delta_capt = 0, cur_jiffies; unsigned int running, count1, count2; cur_jiffies = jiffies; running = cable->running ^ cable->pause; if (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) { delta_play = cur_jiffies - dpcm_play->last_jiffies; dpcm_play->last_jiffies += delta_play; } if (running & (1 << SNDRV_PCM_STREAM_CAPTURE)) { delta_capt = cur_jiffies - dpcm_capt->last_jiffies; dpcm_capt->last_jiffies += delta_capt; } if (delta_play == 0 && delta_capt == 0) goto unlock; if (delta_play > delta_capt) { count1 = bytepos_delta(dpcm_play, delta_play - delta_capt); bytepos_finish(dpcm_play, count1); delta_play = delta_capt; } else if (delta_play < delta_capt) { count1 = bytepos_delta(dpcm_capt, delta_capt - delta_play); clear_capture_buf(dpcm_capt, count1); bytepos_finish(dpcm_capt, count1); delta_capt = delta_play; } if (delta_play == 0 && delta_capt == 0) goto unlock; /* note delta_capt == delta_play at this moment */ count1 = bytepos_delta(dpcm_play, delta_play); count2 = bytepos_delta(dpcm_capt, delta_capt); if (count1 < count2) { dpcm_capt->last_drift = count2 - count1; count1 = count2; } else if (count1 > count2) { dpcm_play->last_drift = count1 - count2; } copy_play_buf(dpcm_play, dpcm_capt, count1); bytepos_finish(dpcm_play, count1); bytepos_finish(dpcm_capt, count1); unlock: return running; } static void loopback_jiffies_timer_function(struct timer_list *t) { struct loopback_pcm *dpcm = from_timer(dpcm, t, timer); unsigned long flags; spin_lock_irqsave(&dpcm->cable->lock, flags); if (loopback_jiffies_timer_pos_update(dpcm->cable) & (1 << dpcm->substream->stream)) { loopback_jiffies_timer_start(dpcm); if (dpcm->period_update_pending) { dpcm->period_update_pending = 0; spin_unlock_irqrestore(&dpcm->cable->lock, flags); /* need to unlock before calling below */ snd_pcm_period_elapsed(dpcm->substream); return; } } spin_unlock_irqrestore(&dpcm->cable->lock, flags); } /* call in cable->lock */ static int loopback_snd_timer_check_resolution(struct snd_pcm_runtime *runtime, unsigned long resolution) { if (resolution != runtime->timer_resolution) { struct loopback_pcm *dpcm = runtime->private_data; struct loopback_cable *cable = dpcm->cable; /* Worst case estimation of possible values for resolution * resolution <= (512 * 1024) frames / 8kHz in nsec * resolution <= 65.536.000.000 nsec * * period_size <= 65.536.000.000 nsec / 1000nsec/usec * 192kHz + * 500.000 * period_size <= 12.582.912.000.000 <64bit * / 1.000.000 usec/sec */ snd_pcm_uframes_t period_size_usec = resolution / 1000 * runtime->rate; /* round to nearest sample rate */ snd_pcm_uframes_t period_size = (period_size_usec + 500 * 1000) / (1000 * 1000); pcm_err(dpcm->substream->pcm, "Period size (%lu frames) of loopback device is not corresponding to timer resolution (%lu nsec = %lu frames) of card timer %d,%d,%d. Use period size of %lu frames for loopback device.", runtime->period_size, resolution, period_size, cable->snd_timer.id.card, cable->snd_timer.id.device, cable->snd_timer.id.subdevice, period_size); return -EINVAL; } return 0; } static void loopback_snd_timer_period_elapsed(struct loopback_cable *cable, int event, unsigned long resolution) { struct loopback_pcm *dpcm_play, *dpcm_capt; struct snd_pcm_substream *substream_play, *substream_capt; struct snd_pcm_runtime *valid_runtime; unsigned int running, elapsed_bytes; unsigned long flags; spin_lock_irqsave(&cable->lock, flags); running = cable->running ^ cable->pause; /* no need to do anything if no stream is running */ if (!running) { spin_unlock_irqrestore(&cable->lock, flags); return; } dpcm_play = cable->streams[SNDRV_PCM_STREAM_PLAYBACK]; dpcm_capt = cable->streams[SNDRV_PCM_STREAM_CAPTURE]; if (event == SNDRV_TIMER_EVENT_MSTOP) { if (!dpcm_play || dpcm_play->substream->runtime->state != SNDRV_PCM_STATE_DRAINING) { spin_unlock_irqrestore(&cable->lock, flags); return; } } substream_play = (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) ? dpcm_play->substream : NULL; substream_capt = (running & (1 << SNDRV_PCM_STREAM_CAPTURE)) ? dpcm_capt->substream : NULL; valid_runtime = (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) ? dpcm_play->substream->runtime : dpcm_capt->substream->runtime; /* resolution is only valid for SNDRV_TIMER_EVENT_TICK events */ if (event == SNDRV_TIMER_EVENT_TICK) { /* The hardware rules guarantee that playback and capture period * are the same. Therefore only one device has to be checked * here. */ if (loopback_snd_timer_check_resolution(valid_runtime, resolution) < 0) { spin_unlock_irqrestore(&cable->lock, flags); if (substream_play) snd_pcm_stop_xrun(substream_play); if (substream_capt) snd_pcm_stop_xrun(substream_capt); return; } } elapsed_bytes = frames_to_bytes(valid_runtime, valid_runtime->period_size); /* The same timer interrupt is used for playback and capture device */ if ((running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) && (running & (1 << SNDRV_PCM_STREAM_CAPTURE))) { copy_play_buf(dpcm_play, dpcm_capt, elapsed_bytes); bytepos_finish(dpcm_play, elapsed_bytes); bytepos_finish(dpcm_capt, elapsed_bytes); } else if (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) { bytepos_finish(dpcm_play, elapsed_bytes); } else if (running & (1 << SNDRV_PCM_STREAM_CAPTURE)) { clear_capture_buf(dpcm_capt, elapsed_bytes); bytepos_finish(dpcm_capt, elapsed_bytes); } spin_unlock_irqrestore(&cable->lock, flags); if (substream_play) snd_pcm_period_elapsed(substream_play); if (substream_capt) snd_pcm_period_elapsed(substream_capt); } static void loopback_snd_timer_function(struct snd_timer_instance *timeri, unsigned long resolution, unsigned long ticks) { struct loopback_cable *cable = timeri->callback_data; loopback_snd_timer_period_elapsed(cable, SNDRV_TIMER_EVENT_TICK, resolution); } static void loopback_snd_timer_work(struct work_struct *work) { struct loopback_cable *cable; cable = container_of(work, struct loopback_cable, snd_timer.event_work); loopback_snd_timer_period_elapsed(cable, SNDRV_TIMER_EVENT_MSTOP, 0); } static void loopback_snd_timer_event(struct snd_timer_instance *timeri, int event, struct timespec64 *tstamp, unsigned long resolution) { /* Do not lock cable->lock here because timer->lock is already hold. * There are other functions which first lock cable->lock and than * timer->lock e.g. * loopback_trigger() * spin_lock(&cable->lock) * loopback_snd_timer_start() * snd_timer_start() * spin_lock(&timer->lock) * Therefore when using the oposit order of locks here it could result * in a deadlock. */ if (event == SNDRV_TIMER_EVENT_MSTOP) { struct loopback_cable *cable = timeri->callback_data; /* sound card of the timer was stopped. Therefore there will not * be any further timer callbacks. Due to this forward audio * data from here if in draining state. When still in running * state the streaming will be aborted by the usual timeout. It * should not be aborted here because may be the timer sound * card does only a recovery and the timer is back soon. * This work triggers loopback_snd_timer_work() */ schedule_work(&cable->snd_timer.event_work); } } static void loopback_jiffies_timer_dpcm_info(struct loopback_pcm *dpcm, struct snd_info_buffer *buffer) { snd_iprintf(buffer, " update_pending:\t%u\n", dpcm->period_update_pending); snd_iprintf(buffer, " irq_pos:\t\t%u\n", dpcm->irq_pos); snd_iprintf(buffer, " period_frac:\t%u\n", dpcm->period_size_frac); snd_iprintf(buffer, " last_jiffies:\t%lu (%lu)\n", dpcm->last_jiffies, jiffies); snd_iprintf(buffer, " timer_expires:\t%lu\n", dpcm->timer.expires); } static void loopback_snd_timer_dpcm_info(struct loopback_pcm *dpcm, struct snd_info_buffer *buffer) { struct loopback_cable *cable = dpcm->cable; snd_iprintf(buffer, " sound timer:\thw:%d,%d,%d\n", cable->snd_timer.id.card, cable->snd_timer.id.device, cable->snd_timer.id.subdevice); snd_iprintf(buffer, " timer open:\t\t%s\n", snd_pcm_direction_name(cable->snd_timer.stream)); } static snd_pcm_uframes_t loopback_pointer(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; struct loopback_pcm *dpcm = runtime->private_data; snd_pcm_uframes_t pos; spin_lock(&dpcm->cable->lock); if (dpcm->cable->ops->pos_update) dpcm->cable->ops->pos_update(dpcm->cable); pos = dpcm->buf_pos; spin_unlock(&dpcm->cable->lock); return bytes_to_frames(runtime, pos); } static const struct snd_pcm_hardware loopback_pcm_hardware = { .info = (SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_MMAP_VALID | SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_RESUME | SNDRV_PCM_INFO_NONINTERLEAVED), .formats = (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S16_BE | SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S24_BE | SNDRV_PCM_FMTBIT_S24_3LE | SNDRV_PCM_FMTBIT_S24_3BE | SNDRV_PCM_FMTBIT_S32_LE | SNDRV_PCM_FMTBIT_S32_BE | SNDRV_PCM_FMTBIT_FLOAT_LE | SNDRV_PCM_FMTBIT_FLOAT_BE | SNDRV_PCM_FMTBIT_DSD_U8 | SNDRV_PCM_FMTBIT_DSD_U16_LE | SNDRV_PCM_FMTBIT_DSD_U16_BE | SNDRV_PCM_FMTBIT_DSD_U32_LE | SNDRV_PCM_FMTBIT_DSD_U32_BE), .rates = SNDRV_PCM_RATE_CONTINUOUS | SNDRV_PCM_RATE_8000_768000, .rate_min = 8000, .rate_max = 768000, .channels_min = 1, .channels_max = 32, .buffer_bytes_max = 2 * 1024 * 1024, .period_bytes_min = 64, /* note check overflow in frac_pos() using pcm_rate_shift before changing period_bytes_max value */ .period_bytes_max = 1024 * 1024, .periods_min = 1, .periods_max = 1024, .fifo_size = 0, }; static void loopback_runtime_free(struct snd_pcm_runtime *runtime) { struct loopback_pcm *dpcm = runtime->private_data; kfree(dpcm); } static int loopback_hw_free(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; struct loopback_pcm *dpcm = runtime->private_data; struct loopback_cable *cable = dpcm->cable; mutex_lock(&dpcm->loopback->cable_lock); cable->valid &= ~(1 << substream->stream); mutex_unlock(&dpcm->loopback->cable_lock); return 0; } static unsigned int get_cable_index(struct snd_pcm_substream *substream) { if (!substream->pcm->device) return substream->stream; else return !substream->stream; } static int rule_format(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct loopback_pcm *dpcm = rule->private; struct loopback_cable *cable = dpcm->cable; struct snd_mask m; snd_mask_none(&m); mutex_lock(&dpcm->loopback->cable_lock); m.bits[0] = (u_int32_t)cable->hw.formats; m.bits[1] = (u_int32_t)(cable->hw.formats >> 32); mutex_unlock(&dpcm->loopback->cable_lock); return snd_mask_refine(hw_param_mask(params, rule->var), &m); } static int rule_rate(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct loopback_pcm *dpcm = rule->private; struct loopback_cable *cable = dpcm->cable; struct snd_interval t; mutex_lock(&dpcm->loopback->cable_lock); t.min = cable->hw.rate_min; t.max = cable->hw.rate_max; mutex_unlock(&dpcm->loopback->cable_lock); t.openmin = t.openmax = 0; t.integer = 0; return snd_interval_refine(hw_param_interval(params, rule->var), &t); } static int rule_channels(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct loopback_pcm *dpcm = rule->private; struct loopback_cable *cable = dpcm->cable; struct snd_interval t; mutex_lock(&dpcm->loopback->cable_lock); t.min = cable->hw.channels_min; t.max = cable->hw.channels_max; mutex_unlock(&dpcm->loopback->cable_lock); t.openmin = t.openmax = 0; t.integer = 0; return snd_interval_refine(hw_param_interval(params, rule->var), &t); } static int rule_period_bytes(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct loopback_pcm *dpcm = rule->private; struct loopback_cable *cable = dpcm->cable; struct snd_interval t; mutex_lock(&dpcm->loopback->cable_lock); t.min = cable->hw.period_bytes_min; t.max = cable->hw.period_bytes_max; mutex_unlock(&dpcm->loopback->cable_lock); t.openmin = 0; t.openmax = 0; t.integer = 0; return snd_interval_refine(hw_param_interval(params, rule->var), &t); } static void free_cable(struct snd_pcm_substream *substream) { struct loopback *loopback = substream->private_data; int dev = get_cable_index(substream); struct loopback_cable *cable; cable = loopback->cables[substream->number][dev]; if (!cable) return; if (cable->streams[!substream->stream]) { /* other stream is still alive */ spin_lock_irq(&cable->lock); cable->streams[substream->stream] = NULL; spin_unlock_irq(&cable->lock); } else { struct loopback_pcm *dpcm = substream->runtime->private_data; if (cable->ops && cable->ops->close_cable && dpcm) cable->ops->close_cable(dpcm); /* free the cable */ loopback->cables[substream->number][dev] = NULL; kfree(cable); } } static int loopback_jiffies_timer_open(struct loopback_pcm *dpcm) { timer_setup(&dpcm->timer, loopback_jiffies_timer_function, 0); return 0; } static const struct loopback_ops loopback_jiffies_timer_ops = { .open = loopback_jiffies_timer_open, .start = loopback_jiffies_timer_start, .stop = loopback_jiffies_timer_stop, .stop_sync = loopback_jiffies_timer_stop_sync, .close_substream = loopback_jiffies_timer_stop_sync, .pos_update = loopback_jiffies_timer_pos_update, .dpcm_info = loopback_jiffies_timer_dpcm_info, }; static int loopback_parse_timer_id(const char *str, struct snd_timer_id *tid) { /* [<pref>:](<card name>|<card idx>)[{.,}<dev idx>[{.,}<subdev idx>]] */ const char * const sep_dev = ".,"; const char * const sep_pref = ":"; const char *name = str; char *sep, save = '\0'; int card_idx = 0, dev = 0, subdev = 0; int err; sep = strpbrk(str, sep_pref); if (sep) name = sep + 1; sep = strpbrk(name, sep_dev); if (sep) { save = *sep; *sep = '\0'; } err = kstrtoint(name, 0, &card_idx); if (err == -EINVAL) { /* Must be the name, not number */ for (card_idx = 0; card_idx < snd_ecards_limit; card_idx++) { struct snd_card *card = snd_card_ref(card_idx); if (card) { if (!strcmp(card->id, name)) err = 0; snd_card_unref(card); } if (!err) break; } } if (sep) { *sep = save; if (!err) { char *sep2, save2 = '\0'; sep2 = strpbrk(sep + 1, sep_dev); if (sep2) { save2 = *sep2; *sep2 = '\0'; } err = kstrtoint(sep + 1, 0, &dev); if (sep2) { *sep2 = save2; if (!err) err = kstrtoint(sep2 + 1, 0, &subdev); } } } if (card_idx == -1) tid->dev_class = SNDRV_TIMER_CLASS_GLOBAL; if (!err && tid) { tid->card = card_idx; tid->device = dev; tid->subdevice = subdev; } return err; } /* call in loopback->cable_lock */ static int loopback_snd_timer_open(struct loopback_pcm *dpcm) { int err = 0; struct snd_timer_id tid = { .dev_class = SNDRV_TIMER_CLASS_PCM, .dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION, }; struct snd_timer_instance *timeri; struct loopback_cable *cable = dpcm->cable; /* check if timer was already opened. It is only opened once * per playback and capture subdevice (aka cable). */ if (cable->snd_timer.instance) goto exit; err = loopback_parse_timer_id(dpcm->loopback->timer_source, &tid); if (err < 0) { pcm_err(dpcm->substream->pcm, "Parsing timer source \'%s\' failed with %d", dpcm->loopback->timer_source, err); goto exit; } cable->snd_timer.stream = dpcm->substream->stream; cable->snd_timer.id = tid; timeri = snd_timer_instance_new(dpcm->loopback->card->id); if (!timeri) { err = -ENOMEM; goto exit; } /* The callback has to be called from another work. If * SNDRV_TIMER_IFLG_FAST is specified it will be called from the * snd_pcm_period_elapsed() call of the selected sound card. * snd_pcm_period_elapsed() helds snd_pcm_stream_lock_irqsave(). * Due to our callback loopback_snd_timer_function() also calls * snd_pcm_period_elapsed() which calls snd_pcm_stream_lock_irqsave(). * This would end up in a dead lock. */ timeri->flags |= SNDRV_TIMER_IFLG_AUTO; timeri->callback = loopback_snd_timer_function; timeri->callback_data = (void *)cable; timeri->ccallback = loopback_snd_timer_event; /* initialise a work used for draining */ INIT_WORK(&cable->snd_timer.event_work, loopback_snd_timer_work); /* The mutex loopback->cable_lock is kept locked. * Therefore snd_timer_open() cannot be called a second time * by the other device of the same cable. * Therefore the following issue cannot happen: * [proc1] Call loopback_timer_open() -> * Unlock cable->lock for snd_timer_close/open() call * [proc2] Call loopback_timer_open() -> snd_timer_open(), * snd_timer_start() * [proc1] Call snd_timer_open() and overwrite running timer * instance */ err = snd_timer_open(timeri, &cable->snd_timer.id, current->pid); if (err < 0) { pcm_err(dpcm->substream->pcm, "snd_timer_open (%d,%d,%d) failed with %d", cable->snd_timer.id.card, cable->snd_timer.id.device, cable->snd_timer.id.subdevice, err); snd_timer_instance_free(timeri); goto exit; } cable->snd_timer.instance = timeri; exit: return err; } /* stop_sync() is not required for sound timer because it does not need to be * restarted in loopback_prepare() on Xrun recovery */ static const struct loopback_ops loopback_snd_timer_ops = { .open = loopback_snd_timer_open, .start = loopback_snd_timer_start, .stop = loopback_snd_timer_stop, .close_cable = loopback_snd_timer_close_cable, .dpcm_info = loopback_snd_timer_dpcm_info, }; static int loopback_open(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; struct loopback *loopback = substream->private_data; struct loopback_pcm *dpcm; struct loopback_cable *cable = NULL; int err = 0; int dev = get_cable_index(substream); mutex_lock(&loopback->cable_lock); dpcm = kzalloc(sizeof(*dpcm), GFP_KERNEL); if (!dpcm) { err = -ENOMEM; goto unlock; } dpcm->loopback = loopback; dpcm->substream = substream; cable = loopback->cables[substream->number][dev]; if (!cable) { cable = kzalloc(sizeof(*cable), GFP_KERNEL); if (!cable) { err = -ENOMEM; goto unlock; } spin_lock_init(&cable->lock); cable->hw = loopback_pcm_hardware; if (loopback->timer_source) cable->ops = &loopback_snd_timer_ops; else cable->ops = &loopback_jiffies_timer_ops; loopback->cables[substream->number][dev] = cable; } dpcm->cable = cable; runtime->private_data = dpcm; if (cable->ops->open) { err = cable->ops->open(dpcm); if (err < 0) goto unlock; } snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); /* use dynamic rules based on actual runtime->hw values */ /* note that the default rules created in the PCM midlevel code */ /* are cached -> they do not reflect the actual state */ err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT, rule_format, dpcm, SNDRV_PCM_HW_PARAM_FORMAT, -1); if (err < 0) goto unlock; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, rule_rate, dpcm, SNDRV_PCM_HW_PARAM_RATE, -1); if (err < 0) goto unlock; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, rule_channels, dpcm, SNDRV_PCM_HW_PARAM_CHANNELS, -1); if (err < 0) goto unlock; /* In case of sound timer the period time of both devices of the same * loop has to be the same. * This rule only takes effect if a sound timer was chosen */ if (cable->snd_timer.instance) { err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_BYTES, rule_period_bytes, dpcm, SNDRV_PCM_HW_PARAM_PERIOD_BYTES, -1); if (err < 0) goto unlock; } /* loopback_runtime_free() has not to be called if kfree(dpcm) was * already called here. Otherwise it will end up with a double free. */ runtime->private_free = loopback_runtime_free; if (get_notify(dpcm)) runtime->hw = loopback_pcm_hardware; else runtime->hw = cable->hw; spin_lock_irq(&cable->lock); cable->streams[substream->stream] = dpcm; spin_unlock_irq(&cable->lock); unlock: if (err < 0) { free_cable(substream); kfree(dpcm); } mutex_unlock(&loopback->cable_lock); return err; } static int loopback_close(struct snd_pcm_substream *substream) { struct loopback *loopback = substream->private_data; struct loopback_pcm *dpcm = substream->runtime->private_data; int err = 0; if (dpcm->cable->ops->close_substream) err = dpcm->cable->ops->close_substream(dpcm); mutex_lock(&loopback->cable_lock); free_cable(substream); mutex_unlock(&loopback->cable_lock); return err; } static const struct snd_pcm_ops loopback_pcm_ops = { .open = loopback_open, .close = loopback_close, .hw_free = loopback_hw_free, .prepare = loopback_prepare, .trigger = loopback_trigger, .pointer = loopback_pointer, }; static int loopback_pcm_new(struct loopback *loopback, int device, int substreams) { struct snd_pcm *pcm; int err; err = snd_pcm_new(loopback->card, "Loopback PCM", device, substreams, substreams, &pcm); if (err < 0) return err; snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &loopback_pcm_ops); snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &loopback_pcm_ops); snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_VMALLOC, NULL, 0, 0); pcm->private_data = loopback; pcm->info_flags = 0; strcpy(pcm->name, "Loopback PCM"); loopback->pcm[device] = pcm; return 0; } static int loopback_rate_shift_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; uinfo->count = 1; uinfo->value.integer.min = 80000; uinfo->value.integer.max = 120000; uinfo->value.integer.step = 1; return 0; } static int loopback_rate_shift_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct loopback *loopback = snd_kcontrol_chip(kcontrol); mutex_lock(&loopback->cable_lock); ucontrol->value.integer.value[0] = loopback->setup[kcontrol->id.subdevice] [kcontrol->id.device].rate_shift; mutex_unlock(&loopback->cable_lock); return 0; } static int loopback_rate_shift_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct loopback *loopback = snd_kcontrol_chip(kcontrol); unsigned int val; int change = 0; val = ucontrol->value.integer.value[0]; if (val < 80000) val = 80000; if (val > 120000) val = 120000; mutex_lock(&loopback->cable_lock); if (val != loopback->setup[kcontrol->id.subdevice] [kcontrol->id.device].rate_shift) { loopback->setup[kcontrol->id.subdevice] [kcontrol->id.device].rate_shift = val; change = 1; } mutex_unlock(&loopback->cable_lock); return change; } static int loopback_notify_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct loopback *loopback = snd_kcontrol_chip(kcontrol); mutex_lock(&loopback->cable_lock); ucontrol->value.integer.value[0] = loopback->setup[kcontrol->id.subdevice] [kcontrol->id.device].notify; mutex_unlock(&loopback->cable_lock); return 0; } static int loopback_notify_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct loopback *loopback = snd_kcontrol_chip(kcontrol); unsigned int val; int change = 0; val = ucontrol->value.integer.value[0] ? 1 : 0; mutex_lock(&loopback->cable_lock); if (val != loopback->setup[kcontrol->id.subdevice] [kcontrol->id.device].notify) { loopback->setup[kcontrol->id.subdevice] [kcontrol->id.device].notify = val; change = 1; } mutex_unlock(&loopback->cable_lock); return change; } static int loopback_active_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct loopback *loopback = snd_kcontrol_chip(kcontrol); struct loopback_cable *cable; unsigned int val = 0; mutex_lock(&loopback->cable_lock); cable = loopback->cables[kcontrol->id.subdevice][kcontrol->id.device ^ 1]; if (cable != NULL) { unsigned int running = cable->running ^ cable->pause; val = (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) ? 1 : 0; } mutex_unlock(&loopback->cable_lock); ucontrol->value.integer.value[0] = val; return 0; } static int loopback_format_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; uinfo->count = 1; uinfo->value.integer.min = 0; uinfo->value.integer.max = (__force int)SNDRV_PCM_FORMAT_LAST; uinfo->value.integer.step = 1; return 0; } static int loopback_format_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct loopback *loopback = snd_kcontrol_chip(kcontrol); ucontrol->value.integer.value[0] = (__force int)loopback->setup[kcontrol->id.subdevice] [kcontrol->id.device].format; return 0; } static int loopback_rate_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; uinfo->count = 1; uinfo->value.integer.min = 0; uinfo->value.integer.max = 192000; uinfo->value.integer.step = 1; return 0; } static int loopback_rate_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct loopback *loopback = snd_kcontrol_chip(kcontrol); mutex_lock(&loopback->cable_lock); ucontrol->value.integer.value[0] = loopback->setup[kcontrol->id.subdevice] [kcontrol->id.device].rate; mutex_unlock(&loopback->cable_lock); return 0; } static int loopback_channels_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; uinfo->count = 1; uinfo->value.integer.min = 1; uinfo->value.integer.max = 1024; uinfo->value.integer.step = 1; return 0; } static int loopback_channels_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct loopback *loopback = snd_kcontrol_chip(kcontrol); mutex_lock(&loopback->cable_lock); ucontrol->value.integer.value[0] = loopback->setup[kcontrol->id.subdevice] [kcontrol->id.device].channels; mutex_unlock(&loopback->cable_lock); return 0; } static int loopback_access_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { const char * const texts[] = {"Interleaved", "Non-interleaved"}; return snd_ctl_enum_info(uinfo, 1, ARRAY_SIZE(texts), texts); } static int loopback_access_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct loopback *loopback = snd_kcontrol_chip(kcontrol); snd_pcm_access_t access; mutex_lock(&loopback->cable_lock); access = loopback->setup[kcontrol->id.subdevice][kcontrol->id.device].access; ucontrol->value.enumerated.item[0] = !is_access_interleaved(access); mutex_unlock(&loopback->cable_lock); return 0; } static const struct snd_kcontrol_new loopback_controls[] = { { .iface = SNDRV_CTL_ELEM_IFACE_PCM, .name = "PCM Rate Shift 100000", .info = loopback_rate_shift_info, .get = loopback_rate_shift_get, .put = loopback_rate_shift_put, }, { .iface = SNDRV_CTL_ELEM_IFACE_PCM, .name = "PCM Notify", .info = snd_ctl_boolean_mono_info, .get = loopback_notify_get, .put = loopback_notify_put, }, #define ACTIVE_IDX 2 { .access = SNDRV_CTL_ELEM_ACCESS_READ, .iface = SNDRV_CTL_ELEM_IFACE_PCM, .name = "PCM Slave Active", .info = snd_ctl_boolean_mono_info, .get = loopback_active_get, }, #define FORMAT_IDX 3 { .access = SNDRV_CTL_ELEM_ACCESS_READ, .iface = SNDRV_CTL_ELEM_IFACE_PCM, .name = "PCM Slave Format", .info = loopback_format_info, .get = loopback_format_get }, #define RATE_IDX 4 { .access = SNDRV_CTL_ELEM_ACCESS_READ, .iface = SNDRV_CTL_ELEM_IFACE_PCM, .name = "PCM Slave Rate", .info = loopback_rate_info, .get = loopback_rate_get }, #define CHANNELS_IDX 5 { .access = SNDRV_CTL_ELEM_ACCESS_READ, .iface = SNDRV_CTL_ELEM_IFACE_PCM, .name = "PCM Slave Channels", .info = loopback_channels_info, .get = loopback_channels_get }, #define ACCESS_IDX 6 { .access = SNDRV_CTL_ELEM_ACCESS_READ, .iface = SNDRV_CTL_ELEM_IFACE_PCM, .name = "PCM Slave Access Mode", .info = loopback_access_info, .get = loopback_access_get, }, }; static int loopback_mixer_new(struct loopback *loopback, int notify) { struct snd_card *card = loopback->card; struct snd_pcm *pcm; struct snd_kcontrol *kctl; struct loopback_setup *setup; int err, dev, substr, substr_count, idx; strcpy(card->mixername, "Loopback Mixer"); for (dev = 0; dev < 2; dev++) { pcm = loopback->pcm[dev]; substr_count = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream_count; for (substr = 0; substr < substr_count; substr++) { setup = &loopback->setup[substr][dev]; setup->notify = notify; setup->rate_shift = NO_PITCH; setup->format = SNDRV_PCM_FORMAT_S16_LE; setup->access = SNDRV_PCM_ACCESS_RW_INTERLEAVED; setup->rate = 48000; setup->channels = 2; for (idx = 0; idx < ARRAY_SIZE(loopback_controls); idx++) { kctl = snd_ctl_new1(&loopback_controls[idx], loopback); if (!kctl) return -ENOMEM; kctl->id.device = dev; kctl->id.subdevice = substr; /* Add the control before copying the id so that * the numid field of the id is set in the copy. */ err = snd_ctl_add(card, kctl); if (err < 0) return err; switch (idx) { case ACTIVE_IDX: setup->active_id = kctl->id; break; case FORMAT_IDX: setup->format_id = kctl->id; break; case RATE_IDX: setup->rate_id = kctl->id; break; case CHANNELS_IDX: setup->channels_id = kctl->id; break; case ACCESS_IDX: setup->access_id = kctl->id; break; default: break; } } } } return 0; } static void print_dpcm_info(struct snd_info_buffer *buffer, struct loopback_pcm *dpcm, const char *id) { snd_iprintf(buffer, " %s\n", id); if (dpcm == NULL) { snd_iprintf(buffer, " inactive\n"); return; } snd_iprintf(buffer, " buffer_size:\t%u\n", dpcm->pcm_buffer_size); snd_iprintf(buffer, " buffer_pos:\t\t%u\n", dpcm->buf_pos); snd_iprintf(buffer, " silent_size:\t%u\n", dpcm->silent_size); snd_iprintf(buffer, " period_size:\t%u\n", dpcm->pcm_period_size); snd_iprintf(buffer, " bytes_per_sec:\t%u\n", dpcm->pcm_bps); snd_iprintf(buffer, " sample_align:\t%u\n", dpcm->pcm_salign); snd_iprintf(buffer, " rate_shift:\t\t%u\n", dpcm->pcm_rate_shift); if (dpcm->cable->ops->dpcm_info) dpcm->cable->ops->dpcm_info(dpcm, buffer); } static void print_substream_info(struct snd_info_buffer *buffer, struct loopback *loopback, int sub, int num) { struct loopback_cable *cable = loopback->cables[sub][num]; snd_iprintf(buffer, "Cable %i substream %i:\n", num, sub); if (cable == NULL) { snd_iprintf(buffer, " inactive\n"); return; } snd_iprintf(buffer, " valid: %u\n", cable->valid); snd_iprintf(buffer, " running: %u\n", cable->running); snd_iprintf(buffer, " pause: %u\n", cable->pause); print_dpcm_info(buffer, cable->streams[0], "Playback"); print_dpcm_info(buffer, cable->streams[1], "Capture"); } static void print_cable_info(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct loopback *loopback = entry->private_data; int sub, num; mutex_lock(&loopback->cable_lock); num = entry->name[strlen(entry->name)-1]; num = num == '0' ? 0 : 1; for (sub = 0; sub < MAX_PCM_SUBSTREAMS; sub++) print_substream_info(buffer, loopback, sub, num); mutex_unlock(&loopback->cable_lock); } static int loopback_cable_proc_new(struct loopback *loopback, int cidx) { char name[32]; snprintf(name, sizeof(name), "cable#%d", cidx); return snd_card_ro_proc_new(loopback->card, name, loopback, print_cable_info); } static void loopback_set_timer_source(struct loopback *loopback, const char *value) { if (loopback->timer_source) { devm_kfree(loopback->card->dev, loopback->timer_source); loopback->timer_source = NULL; } if (value && *value) loopback->timer_source = devm_kstrdup(loopback->card->dev, value, GFP_KERNEL); } static void print_timer_source_info(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct loopback *loopback = entry->private_data; mutex_lock(&loopback->cable_lock); snd_iprintf(buffer, "%s\n", loopback->timer_source ? loopback->timer_source : ""); mutex_unlock(&loopback->cable_lock); } static void change_timer_source_info(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct loopback *loopback = entry->private_data; char line[64]; mutex_lock(&loopback->cable_lock); if (!snd_info_get_line(buffer, line, sizeof(line))) loopback_set_timer_source(loopback, strim(line)); mutex_unlock(&loopback->cable_lock); } static int loopback_timer_source_proc_new(struct loopback *loopback) { return snd_card_rw_proc_new(loopback->card, "timer_source", loopback, print_timer_source_info, change_timer_source_info); } static int loopback_probe(struct platform_device *devptr) { struct snd_card *card; struct loopback *loopback; int dev = devptr->id; int err; err = snd_devm_card_new(&devptr->dev, index[dev], id[dev], THIS_MODULE, sizeof(struct loopback), &card); if (err < 0) return err; loopback = card->private_data; if (pcm_substreams[dev] < 1) pcm_substreams[dev] = 1; if (pcm_substreams[dev] > MAX_PCM_SUBSTREAMS) pcm_substreams[dev] = MAX_PCM_SUBSTREAMS; loopback->card = card; loopback_set_timer_source(loopback, timer_source[dev]); mutex_init(&loopback->cable_lock); err = loopback_pcm_new(loopback, 0, pcm_substreams[dev]); if (err < 0) return err; err = loopback_pcm_new(loopback, 1, pcm_substreams[dev]); if (err < 0) return err; err = loopback_mixer_new(loopback, pcm_notify[dev] ? 1 : 0); if (err < 0) return err; loopback_cable_proc_new(loopback, 0); loopback_cable_proc_new(loopback, 1); loopback_timer_source_proc_new(loopback); strcpy(card->driver, "Loopback"); strcpy(card->shortname, "Loopback"); sprintf(card->longname, "Loopback %i", dev + 1); err = snd_card_register(card); if (err < 0) return err; platform_set_drvdata(devptr, card); return 0; } static int loopback_suspend(struct device *pdev) { struct snd_card *card = dev_get_drvdata(pdev); snd_power_change_state(card, SNDRV_CTL_POWER_D3hot); return 0; } static int loopback_resume(struct device *pdev) { struct snd_card *card = dev_get_drvdata(pdev); snd_power_change_state(card, SNDRV_CTL_POWER_D0); return 0; } static DEFINE_SIMPLE_DEV_PM_OPS(loopback_pm, loopback_suspend, loopback_resume); #define SND_LOOPBACK_DRIVER "snd_aloop" static struct platform_driver loopback_driver = { .probe = loopback_probe, .driver = { .name = SND_LOOPBACK_DRIVER, .pm = &loopback_pm, }, }; static void loopback_unregister_all(void) { int i; for (i = 0; i < ARRAY_SIZE(devices); ++i) platform_device_unregister(devices[i]); platform_driver_unregister(&loopback_driver); } static int __init alsa_card_loopback_init(void) { int i, err, cards; err = platform_driver_register(&loopback_driver); if (err < 0) return err; cards = 0; for (i = 0; i < SNDRV_CARDS; i++) { struct platform_device *device; if (!enable[i]) continue; device = platform_device_register_simple(SND_LOOPBACK_DRIVER, i, NULL, 0); if (IS_ERR(device)) continue; if (!platform_get_drvdata(device)) { platform_device_unregister(device); continue; } devices[i] = device; cards++; } if (!cards) { #ifdef MODULE pr_err("aloop: No loopback enabled\n"); #endif loopback_unregister_all(); return -ENODEV; } return 0; } static void __exit alsa_card_loopback_exit(void) { loopback_unregister_all(); } module_init(alsa_card_loopback_init) module_exit(alsa_card_loopback_exit) |
| 15592 14518 13344 2162 4736 15152 341 13657 4178 16109 265 45 135 191 155 192 191 9 9 302 226 235 408 177 155 37 103 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SPINLOCK_H #define __LINUX_SPINLOCK_H #define __LINUX_INSIDE_SPINLOCK_H /* * include/linux/spinlock.h - generic spinlock/rwlock declarations * * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the * initializers * * linux/spinlock_types_raw: * The raw types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the arch_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types_raw: * The raw RT types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the arch_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ #include <linux/typecheck.h> #include <linux/preempt.h> #include <linux/linkage.h> #include <linux/compiler.h> #include <linux/irqflags.h> #include <linux/thread_info.h> #include <linux/stringify.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/barrier.h> #include <asm/mmiowb.h> /* * Must define these before including other files, inline functions need them */ #define LOCK_SECTION_NAME ".text..lock."KBUILD_BASENAME #define LOCK_SECTION_START(extra) \ ".subsection 1\n\t" \ extra \ ".ifndef " LOCK_SECTION_NAME "\n\t" \ LOCK_SECTION_NAME ":\n\t" \ ".endif\n" #define LOCK_SECTION_END \ ".previous\n\t" #define __lockfunc __section(".spinlock.text") /* * Pull the arch_spinlock_t and arch_rwlock_t definitions: */ #include <linux/spinlock_types.h> /* * Pull the arch_spin*() functions/declarations (UP-nondebug doesn't need them): */ #ifdef CONFIG_SMP # include <asm/spinlock.h> #else # include <linux/spinlock_up.h> #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, struct lock_class_key *key, short inner); # define raw_spin_loc |